diff options
113 files changed, 4814 insertions, 1989 deletions
@@ -7,3 +7,8 @@ path_classifiers: # "undefined export" alerts - numpy/random/__init__.py +extraction: + python: + python_setup: + requirements: + - cython>=0.29 diff --git a/.travis.yml b/.travis.yml index cf67134d3..29b04f296 100644 --- a/.travis.yml +++ b/.travis.yml @@ -41,7 +41,7 @@ matrix: sudo: true # travis-ci/travis-ci#9069 env: INSTALL_PICKLE5=1 - python: 3.6 - env: USE_CHROOT=1 ARCH=i386 DIST=bionic PYTHON=3.6 + env: USE_CHROOT=1 ARCH=i386 DIST=bionic sudo: true addons: apt: diff --git a/benchmarks/benchmarks/bench_shape_base.py b/benchmarks/benchmarks/bench_shape_base.py index e48ea0adb..187b923cd 100644 --- a/benchmarks/benchmarks/bench_shape_base.py +++ b/benchmarks/benchmarks/bench_shape_base.py @@ -88,10 +88,18 @@ class Block2D(Benchmark): class Block3D(Benchmark): - params = [1, 10, 100] - param_names = ['size'] - - def setup(self, n): + """This benchmark concatenates an array of size ``(5n)^3``""" + # Having copy as a `mode` of the block3D + # allows us to directly compare the benchmark of block + # to that of a direct memory copy into new buffers with + # the ASV framework. + # block and copy will be plotted on the same graph + # as opposed to being displayed as separate benchmarks + params = [[1, 10, 100], + ['block', 'copy']] + param_names = ['n', 'mode'] + + def setup(self, n, mode): # Slow setup method: hence separated from the others above self.a000 = np.ones((2 * n, 2 * n, 2 * n), int) * 1 @@ -105,8 +113,7 @@ class Block3D(Benchmark): self.a111 = np.ones((3 * n, 3 * n, 3 * n), int) * 8 - def time_3d(self, n): - np.block([ + self.block = [ [ [self.a000, self.a001], [self.a010, self.a011], @@ -115,7 +122,17 @@ class Block3D(Benchmark): [self.a100, self.a101], [self.a110, self.a111], ] - ]) + ] + self.arr_list = [a + for two_d in self.block + for one_d in two_d + for a in one_d] + + def time_3d(self, n, mode): + if mode == 'block': + np.block(self.block) + else: # mode == 'copy' + [arr.copy() for arr in self.arr_list] # Retain old benchmark name for backward compat time_3d.benchmark_name = "bench_shape_base.Block.time_3d" diff --git a/doc/RELEASE_WALKTHROUGH.rst.txt b/doc/RELEASE_WALKTHROUGH.rst.txt index c3400194c..bb6ca49f7 100644 --- a/doc/RELEASE_WALKTHROUGH.rst.txt +++ b/doc/RELEASE_WALKTHROUGH.rst.txt @@ -46,7 +46,7 @@ repository:: $ git checkout maintenance/1.14.x $ git pull upstream maintenance/1.14.x $ git submodule update - $ git clean -xdf + $ git clean -xdf > /dev/null Edit pavement.py and setup.py as detailed in HOWTO_RELEASE:: @@ -94,7 +94,7 @@ Edit the ``.travis.yml`` and ``.appveyor.yml`` files to make sure they have the correct version, and put in the commit hash for the ``REL`` commit created above for ``BUILD_COMMIT``, see the _example from `v1.14.3`:: - $ gvim .travis.yml appveyor.yml + $ gvim .travis.yml .appveyor.yml $ git commit -a $ git push origin HEAD @@ -137,6 +137,7 @@ Generate the README files This needs to be done after all installers are present, but before the pavement file is updated for continued development. + $ cd ../numpy $ paver write_release_and_log diff --git a/doc/changelog/1.15.3-changelog.rst b/doc/changelog/1.15.3-changelog.rst new file mode 100644 index 000000000..9e03df454 --- /dev/null +++ b/doc/changelog/1.15.3-changelog.rst @@ -0,0 +1,32 @@ + +Contributors +============ + +A total of 7 people contributed to this release. People with a "+" by their +names contributed a patch for the first time. + +* Allan Haldane +* Charles Harris +* Jeroen Demeyer +* Kevin Sheppard +* Matthew Bowden + +* Matti Picus +* Tyler Reddy + +Pull requests merged +==================== + +A total of 12 pull requests were merged for this release. + +* `#12080 <https://github.com/numpy/numpy/pull/12080>`__: MAINT: Blacklist some MSVC complex functions. +* `#12083 <https://github.com/numpy/numpy/pull/12083>`__: TST: Add azure CI testing to 1.15.x branch. +* `#12084 <https://github.com/numpy/numpy/pull/12084>`__: BUG: test_path() now uses Path.resolve() +* `#12085 <https://github.com/numpy/numpy/pull/12085>`__: TST, MAINT: Fix some failing tests on azure-pipelines mac and... +* `#12187 <https://github.com/numpy/numpy/pull/12187>`__: BUG: Fix memory leak in mapping.c +* `#12188 <https://github.com/numpy/numpy/pull/12188>`__: BUG: Allow boolean subtract in histogram +* `#12189 <https://github.com/numpy/numpy/pull/12189>`__: BUG: Fix in-place permutation +* `#12190 <https://github.com/numpy/numpy/pull/12190>`__: BUG: limit default for get_num_build_jobs() to 8 +* `#12191 <https://github.com/numpy/numpy/pull/12191>`__: BUG: OBJECT_to_* should check for errors +* `#12192 <https://github.com/numpy/numpy/pull/12192>`__: DOC: Prepare for NumPy 1.15.3 release. +* `#12237 <https://github.com/numpy/numpy/pull/12237>`__: BUG: Fix MaskedArray fill_value type conversion. +* `#12238 <https://github.com/numpy/numpy/pull/12238>`__: TST: Backport azure-pipeline testing fixes for Mac diff --git a/doc/neps/nep-0027-zero-rank-arrarys.rst b/doc/neps/nep-0027-zero-rank-arrarys.rst index 11ea44dbd..d932bb609 100644 --- a/doc/neps/nep-0027-zero-rank-arrarys.rst +++ b/doc/neps/nep-0027-zero-rank-arrarys.rst @@ -3,19 +3,21 @@ NEP 27 — Zero Rank Arrays ========================= :Author: Alexander Belopolsky (sasha), transcribed Matt Picus <matti.picus@gmail.com> -:Status: Draft +:Status: Final :Type: Informational :Created: 2006-06-10 +:Resolution: https://mail.python.org/pipermail/numpy-discussion/2018-October/078824.html -Abstract --------- +.. note :: -NumPy has both zero rank arrays and scalars. This design document, adapted from -a `2006 wiki entry`_, describes what zero rank arrays are and why they exist. -It was transcribed 2018-10-13 into a NEP and links were updated. + NumPy has both zero rank arrays and scalars. This design document, adapted + from a `2006 wiki entry`_, describes what zero rank arrays are and why they + exist. It was transcribed 2018-10-13 into a NEP and links were updated. + The pull request sparked `a lively discussion`_ about the continued need + for zero rank arrays and scalars in NumPy. -Note that some of the information here is dated, for instance indexing of 0-D -arrays now is now implemented and does not error. + Some of the information here is dated, for instance indexing of 0-D arrays + now is now implemented and does not error. Zero-Rank Arrays ---------------- @@ -158,7 +160,7 @@ On the other hand there are several cases that make sense for rank-zero arrays. Ellipsis and empty tuple ~~~~~~~~~~~~~~~~~~~~~~~~ -Sasha started a `Jan 2006 discussion`_ on scipy-dev +Alexander started a `Jan 2006 discussion`_ on scipy-dev with the following proposal: ... it may be reasonable to allow ``a[...]``. This way @@ -186,7 +188,7 @@ Francesc's proposal was:: There is a consensus that for a zero-rank array ``x``, both ``x[...]`` and ``x[()]`` should be valid, but the question remains on what should be the type of the result - zero rank ndarray or ``x.dtype``? -(Sasha) +(Alexander) First, whatever choice is made for ``x[...]`` and ``x[()]`` they should be the same because ``...`` is just syntactic sugar for "as many `:` as necessary", which in the case of zero rank leads to ``... = (:,)*0 = ()``. @@ -249,3 +251,4 @@ The original document appeared on the scipy.org wiki, with no Copyright notice, .. _`9024ff0`: https://github.com/numpy/numpy/commit/9024ff0dc052888b5922dde0f3e615607a9e99d7 .. _`743d922`: https://github.com/numpy/numpy/commit/743d922bf5893acf00ac92e823fe12f460726f90 .. _`b32744e`: https://github.com/numpy/numpy/commit/b32744e3fc5b40bdfbd626dcc1f72907d77c01c4 +.. _`a lively discussion`: https://github.com/numpy/numpy/pull/12166 diff --git a/doc/release/1.15.3-notes.rst b/doc/release/1.15.3-notes.rst new file mode 100644 index 000000000..753eecec9 --- /dev/null +++ b/doc/release/1.15.3-notes.rst @@ -0,0 +1,49 @@ +========================== +NumPy 1.15.3 Release Notes +========================== + +This is a bugfix release for bugs and regressions reported following the 1.15.2 +release. The Python versions supported by this release are 2.7, 3.4-3.7. The +wheels are linked with OpenBLAS v0.3.0, which should fix some of the linalg +problems reported for NumPy 1.14. + +Compatibility Note +================== + +The NumPy 1.15.x OS X wheels released on PyPI no longer contain 32-bit +binaries. That will also be the case in future releases. See +`#11625 <https://github.com/numpy/numpy/issues/11625>`__ for the related +discussion. Those needing 32-bit support should look elsewhere or build +from source. + +Contributors +============ + +A total of 7 people contributed to this release. People with a "+" by their +names contributed a patch for the first time. + +* Allan Haldane +* Charles Harris +* Jeroen Demeyer +* Kevin Sheppard +* Matthew Bowden + +* Matti Picus +* Tyler Reddy + +Pull requests merged +==================== + +A total of 12 pull requests were merged for this release. + +* `#12080 <https://github.com/numpy/numpy/pull/12080>`__: MAINT: Blacklist some MSVC complex functions. +* `#12083 <https://github.com/numpy/numpy/pull/12083>`__: TST: Add azure CI testing to 1.15.x branch. +* `#12084 <https://github.com/numpy/numpy/pull/12084>`__: BUG: test_path() now uses Path.resolve() +* `#12085 <https://github.com/numpy/numpy/pull/12085>`__: TST, MAINT: Fix some failing tests on azure-pipelines mac and... +* `#12187 <https://github.com/numpy/numpy/pull/12187>`__: BUG: Fix memory leak in mapping.c +* `#12188 <https://github.com/numpy/numpy/pull/12188>`__: BUG: Allow boolean subtract in histogram +* `#12189 <https://github.com/numpy/numpy/pull/12189>`__: BUG: Fix in-place permutation +* `#12190 <https://github.com/numpy/numpy/pull/12190>`__: BUG: limit default for get_num_build_jobs() to 8 +* `#12191 <https://github.com/numpy/numpy/pull/12191>`__: BUG: OBJECT_to_* should check for errors +* `#12192 <https://github.com/numpy/numpy/pull/12192>`__: DOC: Prepare for NumPy 1.15.3 release. +* `#12237 <https://github.com/numpy/numpy/pull/12237>`__: BUG: Fix MaskedArray fill_value type conversion. +* `#12238 <https://github.com/numpy/numpy/pull/12238>`__: TST: Backport azure-pipeline testing fixes for Mac diff --git a/doc/release/1.16.0-notes.rst b/doc/release/1.16.0-notes.rst index 389added8..bb2b17782 100644 --- a/doc/release/1.16.0-notes.rst +++ b/doc/release/1.16.0-notes.rst @@ -102,6 +102,8 @@ for unraveling. ``dims`` remains supported, but is now deprecated. C API changes ============= +The :c:data:`NPY_API_VERSION` was incremented to 0x0000D since +``core_dim_flags`` and ``core_dim_sizes`` were added to :c:type:`PyUFuncObject`. New Features ============ @@ -111,6 +113,12 @@ New Features New keyword ``max_rows`` in `numpy.loadtxt` sets the maximum rows of the content to be read after ``skiprows``, as in `numpy.genfromtxt`. +modulus operator support added for ``np.timedelta64`` operands +-------------------------------------------------------------- +The modulus (remainder) operator is now supported for two operands +of type ``np.timedelta64``. The operands may have different units +and the return value will match the type of the operands. + Improvements ============ @@ -172,6 +180,45 @@ behavior will be appending. This applied to: `LDFLAGS`, `F77FLAGS`, `F90FLAGS`, `FREEFLAGS`, `FOPT`, `FDEBUG`, and `FFLAGS`. See gh-11525 for more details. +Generalized ufunc signatures now allow fixed-size dimensions +------------------------------------------------------------ +By using a numerical value in the signature of a generalized ufunc, one can +indicate that the given function requires input or output to have dimensions +with the given size. E.g., the signature of a function that converts a polar +angle to a two-dimensional cartesian unit vector would be ``()->(2)``; that +for one that converts two spherical angles to a three-dimensional unit vector +would be ``(),()->(3)``; and that for the cross product of two +three-dimensional vectors would be ``(3),(3)->(3)``. + +Note that to the elementary function these dimensions are not treated any +differently from variable ones indicated with a name starting with a letter; +the loop still is passed the corresponding size, but it can now count on that +size being equal to the fixed one given in the signature. + +Generalized ufunc signatures now allow flexible dimensions +---------------------------------------------------------- + +Some functions, in particular numpy's implementation of ``@`` as ``matmul``, +are very similar to generalized ufuncs in that they operate over core +dimensions, but one could not present them as such because they were able to +deal with inputs in which a dimension is missing. To support this, it is now +allowed to postfix a dimension name with a question mark to indicate that the +dimension does not necessarily have to be present. + +With this addition, the signature for ``matmul`` can be expressed as +``(m?,n),(n,p?)->(m?,p?)``. This indicates that if, e.g., the second operand +has only one dimension, for the purposes of the elementary function it will be +treated as if that input has core shape ``(n, 1)``, and the output has the +corresponding core shape of ``(m, 1)``. The actual output array, however, has +the flexible dimension removed, i.e., it will have shape ``(..., m)``. +Similarly, if both arguments have only a single dimension, the inputs will be +presented as having shapes ``(1, n)`` and ``(n, 1)`` to the elementary +function, and the output as ``(1, 1)``, while the actual output array returned +will have shape ``()``. In this way, the signature allows one to use a +single elementary function for four related but different signatures, +``(m,n),(n,p)->(m,p)``, ``(n),(n,p)->(p)``, ``(m,n),(n)->(m)`` and +``(n),(n)->()``. + ``np.clip`` and the ``clip`` method check for memory overlap ------------------------------------------------------------ The ``out`` argument to these functions is now always tested for memory overlap @@ -183,6 +230,15 @@ The ``help`` function, when applied to numeric types such as `np.intc`, `np.int_`, and `np.longlong`, now lists all of the aliased names for that type, distinguishing between platform -dependent and -independent aliases. +``__module__`` attribute now points to public modules +----------------------------------------------------- +The ``__module__`` attribute on most NumPy functions has been updated to refer +to the preferred public module from which to access a function, rather than +the module in which the function happens to be defined. This produces more +informative displays for functions in tools such as IPython, e.g., instead of +``<function 'numpy.core.fromnumeric.sum'>`` you now see +``<function 'numpy.sum'>``. + Large allocations marked as suitable for transparent hugepages -------------------------------------------------------------- On systems that support transparent hugepages over the madvise system call @@ -205,6 +261,26 @@ Previously we had a broken default that sometimes would not report underflow, overflow, and invalid floating point operations. Now we can support non-glibc distrubutions like Alpine Linux as long as they ship `fenv.h`. +Speedup ``np.block`` for large arrays +------------------------------------- +Large arrays (greater than ``512 * 512``) now use a blocking algorithm based on +copying the data directly into the appropriate slice of the resulting array. +This results in significant speedups for these large arrays, particularly for +arrays being blocked along more than 2 dimensions. + +Speedup ``np.take`` for read-only arrays +---------------------------------------- +The implementation of ``np.take`` no longer makes an unnecessary copy of the +source array when its ``writeable`` flag is set to ``False``. + +Support path-like objects for more functions +-------------------------------------------- +The ``np.core.records.fromfile`` function now supports ``pathlib.Path`` +and other path-like objects in addition to a file object. Furthermore, the +``np.load`` function now also supports path-like objects when +using memory mapping (``mmap_mode`` keyword argument). + + Changes ======= @@ -225,12 +301,13 @@ if ``np.positive(array)`` raises a ``TypeError``. For ``ndarray`` subclasses that override the default ``__array_ufunc__`` implementation, the ``TypeError`` is passed on. -``maximum`` and ``minimum`` set invalid float status for more dtypes --------------------------------------------------------------------- -Previously only ``float32`` and ``float64`` set invalid float status (by -default emitting a `RuntimeWarning`) when a Nan is encountered in -`numpy.maximum` and `numpy.minimum`. Now ``float16``, ``complex64``, -``complex128`` and ``complex256`` will do so as well. +``maximum`` and ``minimum`` no longer emit warnings +--------------------------------------------------- +As part of code introduced in 1.10, ``float32`` and ``float64`` set invalid +float status when a Nan is encountered in `numpy.maximum` and `numpy.minimum`, +when using SSE2 semantics. This caused a `RuntimeWarning` to sometimes be +emitted. In 1.15 we fixed the inconsistencies which caused the warnings to +become more conspicuous. Now no warnings will be emitted. Umath and multiarray c-extension modules merged into a single module -------------------------------------------------------------------- diff --git a/doc/source/reference/arrays.datetime.rst b/doc/source/reference/arrays.datetime.rst index e64d0c17e..387515f59 100644 --- a/doc/source/reference/arrays.datetime.rst +++ b/doc/source/reference/arrays.datetime.rst @@ -119,6 +119,9 @@ simple datetime calculations. >>> np.timedelta64(1,'W') / np.timedelta64(1,'D') 7.0 + >>> np.timedelta64(1,'W') % np.timedelta64(10,'D') + numpy.timedelta64(7,'D') + There are two Timedelta units ('Y', years and 'M', months) which are treated specially, because how much time they represent changes depending on when they are used. While a timedelta day unit is equivalent to diff --git a/doc/source/reference/c-api.generalized-ufuncs.rst b/doc/source/reference/c-api.generalized-ufuncs.rst index 2c631531f..b59f077ad 100644 --- a/doc/source/reference/c-api.generalized-ufuncs.rst +++ b/doc/source/reference/c-api.generalized-ufuncs.rst @@ -127,38 +127,56 @@ The formal syntax of signatures is as follows:: <Output arguments> ::= <Argument list> <Argument list> ::= nil | <Argument> | <Argument> "," <Argument list> <Argument> ::= "(" <Core dimension list> ")" - <Core dimension list> ::= nil | <Core dimension name> | - <Core dimension name> "," <Core dimension list> - <Core dimension name> ::= valid Python variable name - + <Core dimension list> ::= nil | <Core dimension> | + <Core dimension> "," <Core dimension list> + <Core dimension> ::= <Dimension name> <Dimension modifier> + <Dimension name> ::= valid Python variable name | valid integer + <Dimension modifier> ::= nil | "?" Notes: #. All quotes are for clarity. -#. Core dimensions that share the same name must have the exact same size. +#. Unmodified core dimensions that share the same name must have the same size. Each dimension name typically corresponds to one level of looping in the elementary function's implementation. #. White spaces are ignored. +#. An integer as a dimension name freezes that dimension to the value. +#. If the name is suffixed with the "?" modifier, the dimension is a core + dimension only if it exists on all inputs and outputs that share it; + otherwise it is ignored (and replaced by a dimension of size 1 for the + elementary function). Here are some examples of signatures: -+-------------+------------------------+-----------------------------------+ -| add | ``(),()->()`` | | -+-------------+------------------------+-----------------------------------+ -| sum1d | ``(i)->()`` | | -+-------------+------------------------+-----------------------------------+ -| inner1d | ``(i),(i)->()`` | | -+-------------+------------------------+-----------------------------------+ -| matmat | ``(m,n),(n,p)->(m,p)`` | matrix multiplication | -+-------------+------------------------+-----------------------------------+ -| vecmat | ``(n),(n,p)->(p)`` | vector-matrix multiplication | -+-------------+------------------------+-----------------------------------+ -| matvec | ``(m,n),(n)->(m)`` | matrix-vector multiplication | -+-------------+------------------------+-----------------------------------+ -| outer_inner | ``(i,t),(j,t)->(i,j)`` | inner over the last dimension, | -| | | outer over the second to last, | -| | | and loop/broadcast over the rest. | -+-------------+------------------------+-----------------------------------+ ++-------------+----------------------------+-----------------------------------+ +| name | signature | common usage | ++=============+============================+===================================+ +| add | ``(),()->()`` | binary ufunc | ++-------------+----------------------------+-----------------------------------+ +| sum1d | ``(i)->()`` | reduction | ++-------------+----------------------------+-----------------------------------+ +| inner1d | ``(i),(i)->()`` | vector-vector multiplication | ++-------------+----------------------------+-----------------------------------+ +| matmat | ``(m,n),(n,p)->(m,p)`` | matrix multiplication | ++-------------+----------------------------+-----------------------------------+ +| vecmat | ``(n),(n,p)->(p)`` | vector-matrix multiplication | ++-------------+----------------------------+-----------------------------------+ +| matvec | ``(m,n),(n)->(m)`` | matrix-vector multiplication | ++-------------+----------------------------+-----------------------------------+ +| matmul | ``(m?,n),(n,p?)->(m?,p?)`` | combination of the four above | ++-------------+----------------------------+-----------------------------------+ +| outer_inner | ``(i,t),(j,t)->(i,j)`` | inner over the last dimension, | +| | | outer over the second to last, | +| | | and loop/broadcast over the rest. | ++-------------+----------------------------+-----------------------------------+ +| cross1d | ``(3),(3)->(3)`` | cross product where the last | +| | | dimension is frozen and must be 3 | ++-------------+----------------------------+-----------------------------------+ + +.. _frozen: + +The last is an instance of freezing a core dimension and can be used to +improve ufunc performance C-API for implementing Elementary Functions ------------------------------------------- diff --git a/doc/source/reference/c-api.types-and-structures.rst b/doc/source/reference/c-api.types-and-structures.rst index 095693c5b..f04d65ee1 100644 --- a/doc/source/reference/c-api.types-and-structures.rst +++ b/doc/source/reference/c-api.types-and-structures.rst @@ -182,8 +182,18 @@ PyArrayDescr_Type .. c:type:: PyArray_Descr - The format of the :c:type:`PyArray_Descr` structure that lies at the - heart of the :c:data:`PyArrayDescr_Type` is + The :c:type:`PyArray_Descr` structure lies at the heart of the + :c:data:`PyArrayDescr_Type`. While it is described here for + completeness, it should be considered internal to NumPy and manipulated via + ``PyArrayDescr_*`` or ``PyDataType*`` functions and macros. The size of this + structure is subject to change across versions of NumPy. To ensure + compatibility: + + - Never declare a non-pointer instance of the struct + - Never perform pointer arithmatic + - Never use ``sizof(PyArray_Descr)`` + + It has the following structure: .. code-block:: c @@ -685,7 +695,14 @@ PyUFunc_Type the information needed to call the underlying C-code loops that perform the actual work. While it is described here for completeness, it should be considered internal to NumPy and manipulated via ``PyUFunc_*`` - functions. It has the following structure: + functions. The size of this structure is subject to change across versions + of NumPy. To ensure compatibility: + + - Never declare a non-pointer instance of the struct + - Never perform pointer arithmetic + - Never use ``sizeof(PyUFuncObject)`` + + It has the following structure: .. code-block:: c @@ -713,10 +730,13 @@ PyUFunc_Type char *core_signature; PyUFunc_TypeResolutionFunc *type_resolver; PyUFunc_LegacyInnerLoopSelectionFunc *legacy_inner_loop_selector; - void *reserved2; PyUFunc_MaskedInnerLoopSelectionFunc *masked_inner_loop_selector; npy_uint32 *op_flags; npy_uint32 *iter_flags; + /* new in API version 0x0000000D */ + npy_intp *core_dim_sizes; + npy_intp *core_dim_flags; + } PyUFuncObject; .. c:macro: PyUFuncObject.PyObject_HEAD @@ -776,6 +796,10 @@ PyUFunc_Type specifies how many different 1-d loops (of the builtin data types) are available. + .. c:member:: int PyUFuncObject.reserved1 + + Unused. + .. c:member:: char *PyUFuncObject.name A string name for the ufunc. This is used dynamically to build @@ -870,6 +894,21 @@ PyUFunc_Type Override the default nditer flags for the ufunc. + Added in API version 0x0000000D + + .. c:member:: npy_intp *PyUFuncObject.core_dim_sizes + + For each distinct core dimension, the possible + :ref:`frozen <frozen>` size if :c:data:`UFUNC_CORE_DIM_SIZE_INFERRED` is 0 + + .. c:member:: npy_uint32 *PyUFuncObject.core_dim_flags + + For each distinct core dimension, a set of ``UFUNC_CORE_DIM*`` flags + + - :c:data:`UFUNC_CORE_DIM_CAN_IGNORE` if the dim name ends in ``?`` + - :c:data:`UFUNC_CORE_DIM_SIZE_INFERRED` if the dim size will be + determined from the operands and not from a :ref:`frozen <frozen>` signature + PyArrayIter_Type ---------------- diff --git a/doc/source/release.rst b/doc/source/release.rst index 7f0197f3f..4a5da3959 100644 --- a/doc/source/release.rst +++ b/doc/source/release.rst @@ -3,6 +3,7 @@ Release Notes ************* .. include:: ../release/1.16.0-notes.rst +.. include:: ../release/1.15.3-notes.rst .. include:: ../release/1.15.2-notes.rst .. include:: ../release/1.15.1-notes.rst .. include:: ../release/1.15.0-notes.rst diff --git a/doc/source/user/basics.broadcasting.rst b/doc/source/user/basics.broadcasting.rst index 65584b1fd..4e9016ee0 100644 --- a/doc/source/user/basics.broadcasting.rst +++ b/doc/source/user/basics.broadcasting.rst @@ -2,6 +2,10 @@ Broadcasting ************ -.. seealso:: :class:`numpy.broadcast` +.. seealso:: + :class:`numpy.broadcast` + + :ref:`array-broadcasting-in-numpy` + An introduction to the concepts discussed here .. automodule:: numpy.doc.broadcasting diff --git a/doc/source/user/theory.broadcast_1.gif b/doc/source/user/theory.broadcast_1.gif Binary files differnew file mode 100644 index 000000000..541ec734b --- /dev/null +++ b/doc/source/user/theory.broadcast_1.gif diff --git a/doc/source/user/theory.broadcast_2.gif b/doc/source/user/theory.broadcast_2.gif Binary files differnew file mode 100644 index 000000000..163a8473f --- /dev/null +++ b/doc/source/user/theory.broadcast_2.gif diff --git a/doc/source/user/theory.broadcast_3.gif b/doc/source/user/theory.broadcast_3.gif Binary files differnew file mode 100644 index 000000000..83f61f2df --- /dev/null +++ b/doc/source/user/theory.broadcast_3.gif diff --git a/doc/source/user/theory.broadcast_4.gif b/doc/source/user/theory.broadcast_4.gif Binary files differnew file mode 100644 index 000000000..9b21ff582 --- /dev/null +++ b/doc/source/user/theory.broadcast_4.gif diff --git a/doc/source/user/theory.broadcast_5.png b/doc/source/user/theory.broadcast_5.png Binary files differnew file mode 100644 index 000000000..3aa2f0536 --- /dev/null +++ b/doc/source/user/theory.broadcast_5.png diff --git a/doc/source/user/theory.broadcasting.rst b/doc/source/user/theory.broadcasting.rst new file mode 100644 index 000000000..b37edeacc --- /dev/null +++ b/doc/source/user/theory.broadcasting.rst @@ -0,0 +1,229 @@ +:orphan: + +.. _array-broadcasting-in-numpy: + +=========================== +Array Broadcasting in Numpy +=========================== + +.. + Originally part of the scipy.org wiki, available `here + <https://scipy.github.io/old-wiki/pages/EricsBroadcastingDoc>`_ or from the + `github repo + <https://github.com/scipy/old-wiki/blob/gh-pages/pages/EricsBroadcastingDoc.html>`_ + +Let's explore a more advanced concept in numpy called broadcasting. The +term broadcasting describes how numpy treats arrays with different shapes +during arithmetic operations. Subject to certain constraints, the smaller array +is "broadcast" across the larger array so that they have compatible shapes. +Broadcasting provides a means of vectorizing array operations so that looping +occurs in C instead of Python. It does this without making needless copies of +data and usually leads to efficient algorithm implementations. There are also +cases where broadcasting is a bad idea because it leads to inefficient use of +memory that slows computation. This article provides a gentle introduction to +broadcasting with numerous examples ranging from simple to involved. It also +provides hints on when and when not to use broadcasting. + +numpy operations are usually done element-by-element which requires two arrays +to have exactly the same shape: + +.. code-block:: python + :caption: Example 1 + :name: example-1 + + >>> from numpy import array + >>> a = array([1.0, 2.0, 3.0]) + >>> b = array([2.0, 2.0, 2.0]) + >>> a * b + array([ 2., 4., 6.]) + +numpy's broadcasting rule relaxes this constraint when the arrays' shapes meet +certain constraints. The simplest broadcasting example occurs when an array and +a scalar value are combined in an operation: + +.. code-block:: python + :caption: Example 2 + :name: example-2 + + >>> from numpy import array + >>> a = array([1.0,2.0,3.0]) + >>> b = 2.0 + >>> a * b + array([ 2., 4., 6.]) + +The result is equivalent to the previous example where ``b`` was an array. We +can think of the scalar ``b`` being stretched during the arithmetic operation +into an array with the same shape as ``a``. The new elements in ``b``, as shown +in :ref:`figure-1`, are simply copies of the original scalar. The stretching +analogy is only conceptual. numpy is smart enough to use the original scalar +value without actually making copies so that broadcasting operations are as +memory and computationally efficient as possible. Because :ref:`example-2` +moves less memory, (``b`` is a scalar, not an array) around during the +multiplication, it is about 10% faster than :ref:`example-1` using the standard +numpy on Windows 2000 with one million element arrays. + +.. figure:: theory.broadcast_1.gif + :alt: Vector-Scalar multiplication + :name: figure-1 + + *Figure 1* + + *In the simplest example of broadcasting, the scalar ``b`` is + stretched to become an array of with the same shape as ``a`` so the shapes + are compatible for element-by-element multiplication.* + + +The rule governing whether two arrays have compatible shapes for broadcasting +can be expressed in a single sentence. + +.. admonition:: The Broadcasting Rule + + **In order to broadcast, the size of the trailing axes for both arrays in + an operation must either be the same size or one of them must be one.** + +If this condition is not met, a ``ValueError('frames are not aligned')`` +exception is thrown indicating that the arrays have incompatible shapes. The +size of the result array created by broadcast operations is the maximum size +along each dimension from the input arrays. Note that the rule does not say +anything about the two arrays needing to have the same number of dimensions. +So, for example, if you have a 256 x 256 x 3 array of RGB values, and you want +to scale each color in the image by a different value, you can multiply the +image by a one-dimensional array with 3 values. Lining up the sizes of the +trailing axes of these arrays according to the broadcast rule shows that they +are compatible + ++-------+------------+-------+-------+---+ +|Image | (3d array) | 256 x | 256 x | 3 | ++-------+------------+-------+-------+---+ +|Scale | (1d array) | | | 3 | ++-------+------------+-------+-------+---+ +|Result | (3d array) | 256 x | 256 x | 3 | ++-------+------------+-------+-------+---+ + +In the following example, both the ``A`` and ``B`` arrays have axes with length +one that are expanded to a larger size in a broadcast operation. + ++-------+------------+-----+-----+-----+---+ +|A | (4d array) | 8 x | 1 x | 6 x | 1 | ++-------+------------+-----+-----+-----+---+ +|B | (3d array) | | 7 x | 1 x | 5 | ++-------+------------+-----+-----+-----+---+ +|Result | (4d array) | 8 x | 7 x | 6 x | 5 | ++-------+------------+-----+-----+-----+---+ + +Below, are several code examples and graphical representations that help make +the broadcast rule visually obvious. :ref:`example-3` adds a one-dimensional array +to a two-dimensional array: + +.. code-block:: python + :caption: Example 3 + :name: example-3 + + >>> from numpy import array + >>> a = array([[ 0.0, 0.0, 0.0], + ... [10.0, 10.0, 10.0], + ... [20.0, 20.0, 20.0], + ... [30.0, 30.0, 30.0]]) + >>> b = array([1.0, 2.0, 3.0]) + >>> a + b + array([[ 1., 2., 3.], + [ 11., 12., 13.], + [ 21., 22., 23.], + [ 31., 32., 33.]]) + +As shown in :ref:`figure-2`, ``b`` is added to each row of ``a``. When ``b`` is +longer than the rows of ``a``, as in :ref:`figure-3`, an exception is raised +because of the incompatible shapes. + +.. figure:: theory.broadcast_2.gif + :alt: Matrix-Vector + :name: figure-2 + + *Figure 2* + + *A two dimensional array multiplied by a one dimensional array results in + broadcasting if number of 1-d array elements matches the number of 2-d + array columns.* + +.. figure:: theory.broadcast_3.gif + :alt: Matrix-Vector-with-error + :name: figure-3 + + *Figure 3* + + *When the trailing dimensions of the arrays are unequal, broadcasting fails + because it is impossible to align the values in the rows of the 1st array + with the elements of the 2nd arrays for element-by-element addition.* + +Broadcasting provides a convenient way of taking the outer product (or any +other outer operation) of two arrays. The following example shows an outer +addition operation of two 1-d arrays that produces the same result as +:ref:`example-3` + +.. code-block:: python + :caption: Example 4 + :name: example-4 + + >>> from numpy import array, newaxis + >>> a = array([0.0, 10.0, 20.0, 30.0]) + >>> b = array([1.0, 2.0, 3.0]) + >>> a[:,newaxis] + b + array([[ 1., 2., 3.], + [ 11., 12., 13.], + [ 21., 22., 23.], + [ 31., 32., 33.]]) + +Here the newaxis index operator inserts a new axis into ``a``, making it a +two-dimensional 4x1 array. :ref:`figure-4` illustrates the stretching of both +arrays to produce the desired 4x3 output array. + +.. figure:: theory.broadcast_4.gif + :alt: vector-vector with newaxis + :name: figure-4 + + *Figure 4* + + In some cases, broadcasting stretches both arrays to form an output array + larger than either of the initial arrays.* + +A Practical Example: Vector Quantization. +========================================= + +Broadcasting comes up quite often in real world problems. A typical example +occurs in the vector quantization (VQ) algorithm used in information theory, +classification, and other related areas. The basic operation in VQ [#f0] finds +the closest point in a set of points, called codes in VQ jargon, to a given +point, called the observation. In the very simple, two-dimensional case shown +in :ref:`figure-5`, the values in observation describe the weight and height of an +athlete to be classified. The codes represent different classes of +athletes. [#f1]_ Finding the closest point requires calculating the distance +between observation and each of the codes. The shortest distance provides the +best match. In this example, ``codes[0]`` is the closest class indicating that +the athlete is likely a basketball player. + +.. figure:: theory.broadcast_5.png + :alt: vector quantitization example + :name: figure-5 + + *Figure 5* + + *The basic operation of vector quantization calculates the distance between + an object to be classified, the dark square, and multiple known codes, the + gray circles. In this simple case, the codes represent individual classes. + More complex cases use multiple codes per class.* + + +.. rubric:: Footnotes + +.. [#f0] Vector Quantization J. Makhoul, S. Roucos, and H. Gish, "Vector Quantization in Speech Coding," Proc. IEEE, vol. 73, pp. 1551-1587, Nov. 1985. +.. [#f1] + In this example, weight has more impact on the distance calculation + than height because of the larger values. In practice, it is important to + normalize the height and weight, often by their standard deviation across the + data set, so that both have equal influence on the distance calculation. + +.. note:: + + The code to produce the figures is part of the `AstroML book + <http://www.astroml.org/book_figures/appendix/fig_broadcast_visual.html>`_ + diff --git a/numpy/__init__.py b/numpy/__init__.py index e1df236bb..ba88c733f 100644 --- a/numpy/__init__.py +++ b/numpy/__init__.py @@ -163,6 +163,8 @@ else: from __builtin__ import bool, int, float, complex, object, unicode, str from .core import round, abs, max, min + # now that numpy modules are imported, can initialize limits + core.getlimits._register_known_types() __all__.extend(['__version__', 'show_config']) __all__.extend(core.__all__) diff --git a/numpy/compat/py3k.py b/numpy/compat/py3k.py index ce4543bc3..8e06ead78 100644 --- a/numpy/compat/py3k.py +++ b/numpy/compat/py3k.py @@ -8,13 +8,13 @@ __all__ = ['bytes', 'asbytes', 'isfileobj', 'getexception', 'strchar', 'unicode', 'asunicode', 'asbytes_nested', 'asunicode_nested', 'asstr', 'open_latin1', 'long', 'basestring', 'sixu', 'integer_types', 'is_pathlib_path', 'npy_load_module', 'Path', - 'contextlib_nullcontext'] + 'contextlib_nullcontext', 'os_fspath', 'os_PathLike'] import sys try: - from pathlib import Path + from pathlib import Path, PurePath except ImportError: - Path = None + Path = PurePath = None if sys.version_info[0] >= 3: import io @@ -95,6 +95,8 @@ def asunicode_nested(x): def is_pathlib_path(obj): """ Check whether obj is a pathlib.Path object. + + Prefer using `isinstance(obj, os_PathLike)` instead of this function. """ return Path is not None and isinstance(obj, Path) @@ -177,3 +179,65 @@ else: finally: fo.close() return mod + +# backport abc.ABC +import abc +if sys.version_info[:2] >= (3, 4): + abc_ABC = abc.ABC +else: + abc_ABC = abc.ABCMeta('ABC', (object,), {'__slots__': ()}) + + +# Backport os.fs_path, os.PathLike, and PurePath.__fspath__ +if sys.version_info[:2] >= (3, 6): + import os + os_fspath = os.fspath + os_PathLike = os.PathLike +else: + def _PurePath__fspath__(self): + return str(self) + + class os_PathLike(abc_ABC): + """Abstract base class for implementing the file system path protocol.""" + + @abc.abstractmethod + def __fspath__(self): + """Return the file system path representation of the object.""" + raise NotImplementedError + + @classmethod + def __subclasshook__(cls, subclass): + if PurePath is not None and issubclass(subclass, PurePath): + return True + return hasattr(subclass, '__fspath__') + + + def os_fspath(path): + """Return the path representation of a path-like object. + If str or bytes is passed in, it is returned unchanged. Otherwise the + os.PathLike interface is used to get the path representation. If the + path representation is not str or bytes, TypeError is raised. If the + provided path is not str, bytes, or os.PathLike, TypeError is raised. + """ + if isinstance(path, (str, bytes)): + return path + + # Work from the object's type to match method resolution of other magic + # methods. + path_type = type(path) + try: + path_repr = path_type.__fspath__(path) + except AttributeError: + if hasattr(path_type, '__fspath__'): + raise + elif PurePath is not None and issubclass(path_type, PurePath): + return _PurePath__fspath__(path) + else: + raise TypeError("expected str, bytes or os.PathLike object, " + "not " + path_type.__name__) + if isinstance(path_repr, (str, bytes)): + return path_repr + else: + raise TypeError("expected {}.__fspath__() to return str or bytes, " + "not {}".format(path_type.__name__, + type(path_repr).__name__)) diff --git a/numpy/core/_add_newdocs.py b/numpy/core/_add_newdocs.py index ffd4971f5..ea472f1b3 100644 --- a/numpy/core/_add_newdocs.py +++ b/numpy/core/_add_newdocs.py @@ -947,66 +947,6 @@ add_newdoc('numpy.core.multiarray', 'empty', """) -add_newdoc('numpy.core.multiarray', 'empty_like', - """ - empty_like(prototype, dtype=None, order='K', subok=True) - - Return a new array with the same shape and type as a given array. - - Parameters - ---------- - prototype : array_like - The shape and data-type of `prototype` define these same attributes - of the returned array. - dtype : data-type, optional - Overrides the data type of the result. - - .. versionadded:: 1.6.0 - order : {'C', 'F', 'A', or 'K'}, optional - Overrides the memory layout of the result. 'C' means C-order, - 'F' means F-order, 'A' means 'F' if ``prototype`` is Fortran - contiguous, 'C' otherwise. 'K' means match the layout of ``prototype`` - as closely as possible. - - .. versionadded:: 1.6.0 - subok : bool, optional. - If True, then the newly created array will use the sub-class - type of 'a', otherwise it will be a base-class array. Defaults - to True. - - Returns - ------- - out : ndarray - Array of uninitialized (arbitrary) data with the same - shape and type as `prototype`. - - See Also - -------- - ones_like : Return an array of ones with shape and type of input. - zeros_like : Return an array of zeros with shape and type of input. - full_like : Return a new array with shape of input filled with value. - empty : Return a new uninitialized array. - - Notes - ----- - This function does *not* initialize the returned array; to do that use - `zeros_like` or `ones_like` instead. It may be marginally faster than - the functions that do set the array values. - - Examples - -------- - >>> a = ([1,2,3], [4,5,6]) # a is array-like - >>> np.empty_like(a) - array([[-1073741821, -1073741821, 3], #random - [ 0, 0, -1073741821]]) - >>> a = np.array([[1., 2., 3.],[4.,5.,6.]]) - >>> np.empty_like(a) - array([[ -2.00000715e+000, 1.48219694e-323, -2.00000572e+000],#random - [ 4.38791518e-305, -2.00000715e+000, 4.17269252e-309]]) - - """) - - add_newdoc('numpy.core.multiarray', 'scalar', """ scalar(dtype, obj) @@ -1284,163 +1224,6 @@ add_newdoc('numpy.core.multiarray', 'frombuffer', """) -add_newdoc('numpy.core.multiarray', 'concatenate', - """ - concatenate((a1, a2, ...), axis=0, out=None) - - Join a sequence of arrays along an existing axis. - - Parameters - ---------- - a1, a2, ... : sequence of array_like - The arrays must have the same shape, except in the dimension - corresponding to `axis` (the first, by default). - axis : int, optional - The axis along which the arrays will be joined. If axis is None, - arrays are flattened before use. Default is 0. - out : ndarray, optional - If provided, the destination to place the result. The shape must be - correct, matching that of what concatenate would have returned if no - out argument were specified. - - Returns - ------- - res : ndarray - The concatenated array. - - See Also - -------- - ma.concatenate : Concatenate function that preserves input masks. - array_split : Split an array into multiple sub-arrays of equal or - near-equal size. - split : Split array into a list of multiple sub-arrays of equal size. - hsplit : Split array into multiple sub-arrays horizontally (column wise) - vsplit : Split array into multiple sub-arrays vertically (row wise) - dsplit : Split array into multiple sub-arrays along the 3rd axis (depth). - stack : Stack a sequence of arrays along a new axis. - hstack : Stack arrays in sequence horizontally (column wise) - vstack : Stack arrays in sequence vertically (row wise) - dstack : Stack arrays in sequence depth wise (along third dimension) - block : Assemble arrays from blocks. - - Notes - ----- - When one or more of the arrays to be concatenated is a MaskedArray, - this function will return a MaskedArray object instead of an ndarray, - but the input masks are *not* preserved. In cases where a MaskedArray - is expected as input, use the ma.concatenate function from the masked - array module instead. - - Examples - -------- - >>> a = np.array([[1, 2], [3, 4]]) - >>> b = np.array([[5, 6]]) - >>> np.concatenate((a, b), axis=0) - array([[1, 2], - [3, 4], - [5, 6]]) - >>> np.concatenate((a, b.T), axis=1) - array([[1, 2, 5], - [3, 4, 6]]) - >>> np.concatenate((a, b), axis=None) - array([1, 2, 3, 4, 5, 6]) - - This function will not preserve masking of MaskedArray inputs. - - >>> a = np.ma.arange(3) - >>> a[1] = np.ma.masked - >>> b = np.arange(2, 5) - >>> a - masked_array(data=[0, --, 2], - mask=[False, True, False], - fill_value=999999) - >>> b - array([2, 3, 4]) - >>> np.concatenate([a, b]) - masked_array(data=[0, 1, 2, 2, 3, 4], - mask=False, - fill_value=999999) - >>> np.ma.concatenate([a, b]) - masked_array(data=[0, --, 2, 2, 3, 4], - mask=[False, True, False, False, False, False], - fill_value=999999) - - """) - -add_newdoc('numpy.core', 'inner', - """ - inner(a, b) - - Inner product of two arrays. - - Ordinary inner product of vectors for 1-D arrays (without complex - conjugation), in higher dimensions a sum product over the last axes. - - Parameters - ---------- - a, b : array_like - If `a` and `b` are nonscalar, their last dimensions must match. - - Returns - ------- - out : ndarray - `out.shape = a.shape[:-1] + b.shape[:-1]` - - Raises - ------ - ValueError - If the last dimension of `a` and `b` has different size. - - See Also - -------- - tensordot : Sum products over arbitrary axes. - dot : Generalised matrix product, using second last dimension of `b`. - einsum : Einstein summation convention. - - Notes - ----- - For vectors (1-D arrays) it computes the ordinary inner-product:: - - np.inner(a, b) = sum(a[:]*b[:]) - - More generally, if `ndim(a) = r > 0` and `ndim(b) = s > 0`:: - - np.inner(a, b) = np.tensordot(a, b, axes=(-1,-1)) - - or explicitly:: - - np.inner(a, b)[i0,...,ir-1,j0,...,js-1] - = sum(a[i0,...,ir-1,:]*b[j0,...,js-1,:]) - - In addition `a` or `b` may be scalars, in which case:: - - np.inner(a,b) = a*b - - Examples - -------- - Ordinary inner product for vectors: - - >>> a = np.array([1,2,3]) - >>> b = np.array([0,1,0]) - >>> np.inner(a, b) - 2 - - A multidimensional example: - - >>> a = np.arange(24).reshape((2,3,4)) - >>> b = np.arange(4) - >>> np.inner(a, b) - array([[ 14, 38, 62], - [ 86, 110, 134]]) - - An example where `b` is a scalar: - - >>> np.inner(np.eye(2), 7) - array([[ 7., 0.], - [ 0., 7.]]) - - """) - add_newdoc('numpy.core', 'fastCopyAndTranspose', """_fastCopyAndTranspose(a)""") @@ -1575,263 +1358,6 @@ add_newdoc('numpy.core.multiarray', 'set_numeric_ops', """) -add_newdoc('numpy.core.multiarray', 'where', - """ - where(condition, [x, y]) - - Return elements chosen from `x` or `y` depending on `condition`. - - .. note:: - When only `condition` is provided, this function is a shorthand for - ``np.asarray(condition).nonzero()``. Using `nonzero` directly should be - preferred, as it behaves correctly for subclasses. The rest of this - documentation covers only the case where all three arguments are - provided. - - Parameters - ---------- - condition : array_like, bool - Where True, yield `x`, otherwise yield `y`. - x, y : array_like - Values from which to choose. `x`, `y` and `condition` need to be - broadcastable to some shape. - - Returns - ------- - out : ndarray - An array with elements from `x` where `condition` is True, and elements - from `y` elsewhere. - - See Also - -------- - choose - nonzero : The function that is called when x and y are omitted - - Notes - ----- - If all the arrays are 1-D, `where` is equivalent to:: - - [xv if c else yv - for c, xv, yv in zip(condition, x, y)] - - Examples - -------- - >>> a = np.arange(10) - >>> a - array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9]) - >>> np.where(a < 5, a, 10*a) - array([ 0, 1, 2, 3, 4, 50, 60, 70, 80, 90]) - - This can be used on multidimensional arrays too: - - >>> np.where([[True, False], [True, True]], - ... [[1, 2], [3, 4]], - ... [[9, 8], [7, 6]]) - array([[1, 8], - [3, 4]]) - - The shapes of x, y, and the condition are broadcast together: - - >>> x, y = np.ogrid[:3, :4] - >>> np.where(x < y, x, 10 + y) # both x and 10+y are broadcast - array([[10, 0, 0, 0], - [10, 11, 1, 1], - [10, 11, 12, 2]]) - - >>> a = np.array([[0, 1, 2], - ... [0, 2, 4], - ... [0, 3, 6]]) - >>> np.where(a < 4, a, -1) # -1 is broadcast - array([[ 0, 1, 2], - [ 0, 2, -1], - [ 0, 3, -1]]) - """) - - -add_newdoc('numpy.core.multiarray', 'lexsort', - """ - lexsort(keys, axis=-1) - - Perform an indirect stable sort using a sequence of keys. - - Given multiple sorting keys, which can be interpreted as columns in a - spreadsheet, lexsort returns an array of integer indices that describes - the sort order by multiple columns. The last key in the sequence is used - for the primary sort order, the second-to-last key for the secondary sort - order, and so on. The keys argument must be a sequence of objects that - can be converted to arrays of the same shape. If a 2D array is provided - for the keys argument, it's rows are interpreted as the sorting keys and - sorting is according to the last row, second last row etc. - - Parameters - ---------- - keys : (k, N) array or tuple containing k (N,)-shaped sequences - The `k` different "columns" to be sorted. The last column (or row if - `keys` is a 2D array) is the primary sort key. - axis : int, optional - Axis to be indirectly sorted. By default, sort over the last axis. - - Returns - ------- - indices : (N,) ndarray of ints - Array of indices that sort the keys along the specified axis. - - See Also - -------- - argsort : Indirect sort. - ndarray.sort : In-place sort. - sort : Return a sorted copy of an array. - - Examples - -------- - Sort names: first by surname, then by name. - - >>> surnames = ('Hertz', 'Galilei', 'Hertz') - >>> first_names = ('Heinrich', 'Galileo', 'Gustav') - >>> ind = np.lexsort((first_names, surnames)) - >>> ind - array([1, 2, 0]) - - >>> [surnames[i] + ", " + first_names[i] for i in ind] - ['Galilei, Galileo', 'Hertz, Gustav', 'Hertz, Heinrich'] - - Sort two columns of numbers: - - >>> a = [1,5,1,4,3,4,4] # First column - >>> b = [9,4,0,4,0,2,1] # Second column - >>> ind = np.lexsort((b,a)) # Sort by a, then by b - >>> print(ind) - [2 0 4 6 5 3 1] - - >>> [(a[i],b[i]) for i in ind] - [(1, 0), (1, 9), (3, 0), (4, 1), (4, 2), (4, 4), (5, 4)] - - Note that sorting is first according to the elements of ``a``. - Secondary sorting is according to the elements of ``b``. - - A normal ``argsort`` would have yielded: - - >>> [(a[i],b[i]) for i in np.argsort(a)] - [(1, 9), (1, 0), (3, 0), (4, 4), (4, 2), (4, 1), (5, 4)] - - Structured arrays are sorted lexically by ``argsort``: - - >>> x = np.array([(1,9), (5,4), (1,0), (4,4), (3,0), (4,2), (4,1)], - ... dtype=np.dtype([('x', int), ('y', int)])) - - >>> np.argsort(x) # or np.argsort(x, order=('x', 'y')) - array([2, 0, 4, 6, 5, 3, 1]) - - """) - -add_newdoc('numpy.core.multiarray', 'can_cast', - """ - can_cast(from_, to, casting='safe') - - Returns True if cast between data types can occur according to the - casting rule. If from is a scalar or array scalar, also returns - True if the scalar value can be cast without overflow or truncation - to an integer. - - Parameters - ---------- - from_ : dtype, dtype specifier, scalar, or array - Data type, scalar, or array to cast from. - to : dtype or dtype specifier - Data type to cast to. - casting : {'no', 'equiv', 'safe', 'same_kind', 'unsafe'}, optional - Controls what kind of data casting may occur. - - * 'no' means the data types should not be cast at all. - * 'equiv' means only byte-order changes are allowed. - * 'safe' means only casts which can preserve values are allowed. - * 'same_kind' means only safe casts or casts within a kind, - like float64 to float32, are allowed. - * 'unsafe' means any data conversions may be done. - - Returns - ------- - out : bool - True if cast can occur according to the casting rule. - - Notes - ----- - Starting in NumPy 1.9, can_cast function now returns False in 'safe' - casting mode for integer/float dtype and string dtype if the string dtype - length is not long enough to store the max integer/float value converted - to a string. Previously can_cast in 'safe' mode returned True for - integer/float dtype and a string dtype of any length. - - See also - -------- - dtype, result_type - - Examples - -------- - Basic examples - - >>> np.can_cast(np.int32, np.int64) - True - >>> np.can_cast(np.float64, complex) - True - >>> np.can_cast(complex, float) - False - - >>> np.can_cast('i8', 'f8') - True - >>> np.can_cast('i8', 'f4') - False - >>> np.can_cast('i4', 'S4') - False - - Casting scalars - - >>> np.can_cast(100, 'i1') - True - >>> np.can_cast(150, 'i1') - False - >>> np.can_cast(150, 'u1') - True - - >>> np.can_cast(3.5e100, np.float32) - False - >>> np.can_cast(1000.0, np.float32) - True - - Array scalar checks the value, array does not - - >>> np.can_cast(np.array(1000.0), np.float32) - True - >>> np.can_cast(np.array([1000.0]), np.float32) - False - - Using the casting rules - - >>> np.can_cast('i8', 'i8', 'no') - True - >>> np.can_cast('<i8', '>i8', 'no') - False - - >>> np.can_cast('<i8', '>i8', 'equiv') - True - >>> np.can_cast('<i4', '>i8', 'equiv') - False - - >>> np.can_cast('<i4', '>i8', 'safe') - True - >>> np.can_cast('<i8', '>i4', 'safe') - False - - >>> np.can_cast('<i8', '>i4', 'same_kind') - True - >>> np.can_cast('<i8', '>u4', 'same_kind') - False - - >>> np.can_cast('<i8', '>u4', 'unsafe') - True - - """) - add_newdoc('numpy.core.multiarray', 'promote_types', """ promote_types(type1, type2) @@ -1892,123 +1418,6 @@ add_newdoc('numpy.core.multiarray', 'promote_types', """) -add_newdoc('numpy.core.multiarray', 'min_scalar_type', - """ - min_scalar_type(a) - - For scalar ``a``, returns the data type with the smallest size - and smallest scalar kind which can hold its value. For non-scalar - array ``a``, returns the vector's dtype unmodified. - - Floating point values are not demoted to integers, - and complex values are not demoted to floats. - - Parameters - ---------- - a : scalar or array_like - The value whose minimal data type is to be found. - - Returns - ------- - out : dtype - The minimal data type. - - Notes - ----- - .. versionadded:: 1.6.0 - - See Also - -------- - result_type, promote_types, dtype, can_cast - - Examples - -------- - >>> np.min_scalar_type(10) - dtype('uint8') - - >>> np.min_scalar_type(-260) - dtype('int16') - - >>> np.min_scalar_type(3.1) - dtype('float16') - - >>> np.min_scalar_type(1e50) - dtype('float64') - - >>> np.min_scalar_type(np.arange(4,dtype='f8')) - dtype('float64') - - """) - -add_newdoc('numpy.core.multiarray', 'result_type', - """ - result_type(*arrays_and_dtypes) - - Returns the type that results from applying the NumPy - type promotion rules to the arguments. - - Type promotion in NumPy works similarly to the rules in languages - like C++, with some slight differences. When both scalars and - arrays are used, the array's type takes precedence and the actual value - of the scalar is taken into account. - - For example, calculating 3*a, where a is an array of 32-bit floats, - intuitively should result in a 32-bit float output. If the 3 is a - 32-bit integer, the NumPy rules indicate it can't convert losslessly - into a 32-bit float, so a 64-bit float should be the result type. - By examining the value of the constant, '3', we see that it fits in - an 8-bit integer, which can be cast losslessly into the 32-bit float. - - Parameters - ---------- - arrays_and_dtypes : list of arrays and dtypes - The operands of some operation whose result type is needed. - - Returns - ------- - out : dtype - The result type. - - See also - -------- - dtype, promote_types, min_scalar_type, can_cast - - Notes - ----- - .. versionadded:: 1.6.0 - - The specific algorithm used is as follows. - - Categories are determined by first checking which of boolean, - integer (int/uint), or floating point (float/complex) the maximum - kind of all the arrays and the scalars are. - - If there are only scalars or the maximum category of the scalars - is higher than the maximum category of the arrays, - the data types are combined with :func:`promote_types` - to produce the return value. - - Otherwise, `min_scalar_type` is called on each array, and - the resulting data types are all combined with :func:`promote_types` - to produce the return value. - - The set of int values is not a subset of the uint values for types - with the same number of bits, something not reflected in - :func:`min_scalar_type`, but handled as a special case in `result_type`. - - Examples - -------- - >>> np.result_type(3, np.arange(7, dtype='i1')) - dtype('int8') - - >>> np.result_type('i4', 'c8') - dtype('complex128') - - >>> np.result_type(3.0, -2) - dtype('float64') - - """) - add_newdoc('numpy.core.multiarray', 'newbuffer', """ newbuffer(size) @@ -2061,91 +1470,6 @@ add_newdoc('numpy.core.multiarray', 'getbuffer', """) -add_newdoc('numpy.core', 'dot', - """ - dot(a, b, out=None) - - Dot product of two arrays. Specifically, - - - If both `a` and `b` are 1-D arrays, it is inner product of vectors - (without complex conjugation). - - - If both `a` and `b` are 2-D arrays, it is matrix multiplication, - but using :func:`matmul` or ``a @ b`` is preferred. - - - If either `a` or `b` is 0-D (scalar), it is equivalent to :func:`multiply` - and using ``numpy.multiply(a, b)`` or ``a * b`` is preferred. - - - If `a` is an N-D array and `b` is a 1-D array, it is a sum product over - the last axis of `a` and `b`. - - - If `a` is an N-D array and `b` is an M-D array (where ``M>=2``), it is a - sum product over the last axis of `a` and the second-to-last axis of `b`:: - - dot(a, b)[i,j,k,m] = sum(a[i,j,:] * b[k,:,m]) - - Parameters - ---------- - a : array_like - First argument. - b : array_like - Second argument. - out : ndarray, optional - Output argument. This must have the exact kind that would be returned - if it was not used. In particular, it must have the right type, must be - C-contiguous, and its dtype must be the dtype that would be returned - for `dot(a,b)`. This is a performance feature. Therefore, if these - conditions are not met, an exception is raised, instead of attempting - to be flexible. - - Returns - ------- - output : ndarray - Returns the dot product of `a` and `b`. If `a` and `b` are both - scalars or both 1-D arrays then a scalar is returned; otherwise - an array is returned. - If `out` is given, then it is returned. - - Raises - ------ - ValueError - If the last dimension of `a` is not the same size as - the second-to-last dimension of `b`. - - See Also - -------- - vdot : Complex-conjugating dot product. - tensordot : Sum products over arbitrary axes. - einsum : Einstein summation convention. - matmul : '@' operator as method with out parameter. - - Examples - -------- - >>> np.dot(3, 4) - 12 - - Neither argument is complex-conjugated: - - >>> np.dot([2j, 3j], [2j, 3j]) - (-13+0j) - - For 2-D arrays it is the matrix product: - - >>> a = [[1, 0], [0, 1]] - >>> b = [[4, 1], [2, 2]] - >>> np.dot(a, b) - array([[4, 1], - [2, 2]]) - - >>> a = np.arange(3*4*5*6).reshape((3,4,5,6)) - >>> b = np.arange(3*4*5*6)[::-1].reshape((5,4,6,3)) - >>> np.dot(a, b)[2,3,2,1,2,2] - 499128 - >>> sum(a[2,3,2,:] * b[1,2,:,2]) - 499128 - - """) - add_newdoc('numpy.core', 'matmul', """ matmul(a, b, out=None) @@ -2269,61 +1593,6 @@ add_newdoc('numpy.core', 'matmul', """) -add_newdoc('numpy.core', 'vdot', - """ - vdot(a, b) - - Return the dot product of two vectors. - - The vdot(`a`, `b`) function handles complex numbers differently than - dot(`a`, `b`). If the first argument is complex the complex conjugate - of the first argument is used for the calculation of the dot product. - - Note that `vdot` handles multidimensional arrays differently than `dot`: - it does *not* perform a matrix product, but flattens input arguments - to 1-D vectors first. Consequently, it should only be used for vectors. - - Parameters - ---------- - a : array_like - If `a` is complex the complex conjugate is taken before calculation - of the dot product. - b : array_like - Second argument to the dot product. - - Returns - ------- - output : ndarray - Dot product of `a` and `b`. Can be an int, float, or - complex depending on the types of `a` and `b`. - - See Also - -------- - dot : Return the dot product without using the complex conjugate of the - first argument. - - Examples - -------- - >>> a = np.array([1+2j,3+4j]) - >>> b = np.array([5+6j,7+8j]) - >>> np.vdot(a, b) - (70-8j) - >>> np.vdot(b, a) - (70+8j) - - Note that higher-dimensional arrays are flattened! - - >>> a = np.array([[1, 4], [5, 6]]) - >>> b = np.array([[4, 1], [2, 2]]) - >>> np.vdot(a, b) - 30 - >>> np.vdot(b, a) - 30 - >>> 1*4 + 4*1 + 5*2 + 6*2 - 30 - - """) - add_newdoc('numpy.core.multiarray', 'c_einsum', """ c_einsum(subscripts, *operands, out=None, dtype=None, order='K', @@ -6795,211 +6064,6 @@ add_newdoc('numpy.core.multiarray', 'busdaycalendar', ('weekmask', add_newdoc('numpy.core.multiarray', 'busdaycalendar', ('holidays', """A copy of the holiday array indicating additional invalid days.""")) -add_newdoc('numpy.core.multiarray', 'is_busday', - """ - is_busday(dates, weekmask='1111100', holidays=None, busdaycal=None, out=None) - - Calculates which of the given dates are valid days, and which are not. - - .. versionadded:: 1.7.0 - - Parameters - ---------- - dates : array_like of datetime64[D] - The array of dates to process. - weekmask : str or array_like of bool, optional - A seven-element array indicating which of Monday through Sunday are - valid days. May be specified as a length-seven list or array, like - [1,1,1,1,1,0,0]; a length-seven string, like '1111100'; or a string - like "Mon Tue Wed Thu Fri", made up of 3-character abbreviations for - weekdays, optionally separated by white space. Valid abbreviations - are: Mon Tue Wed Thu Fri Sat Sun - holidays : array_like of datetime64[D], optional - An array of dates to consider as invalid dates. They may be - specified in any order, and NaT (not-a-time) dates are ignored. - This list is saved in a normalized form that is suited for - fast calculations of valid days. - busdaycal : busdaycalendar, optional - A `busdaycalendar` object which specifies the valid days. If this - parameter is provided, neither weekmask nor holidays may be - provided. - out : array of bool, optional - If provided, this array is filled with the result. - - Returns - ------- - out : array of bool - An array with the same shape as ``dates``, containing True for - each valid day, and False for each invalid day. - - See Also - -------- - busdaycalendar: An object that specifies a custom set of valid days. - busday_offset : Applies an offset counted in valid days. - busday_count : Counts how many valid days are in a half-open date range. - - Examples - -------- - >>> # The weekdays are Friday, Saturday, and Monday - ... np.is_busday(['2011-07-01', '2011-07-02', '2011-07-18'], - ... holidays=['2011-07-01', '2011-07-04', '2011-07-17']) - array([False, False, True], dtype='bool') - """) - -add_newdoc('numpy.core.multiarray', 'busday_offset', - """ - busday_offset(dates, offsets, roll='raise', weekmask='1111100', holidays=None, busdaycal=None, out=None) - - First adjusts the date to fall on a valid day according to - the ``roll`` rule, then applies offsets to the given dates - counted in valid days. - - .. versionadded:: 1.7.0 - - Parameters - ---------- - dates : array_like of datetime64[D] - The array of dates to process. - offsets : array_like of int - The array of offsets, which is broadcast with ``dates``. - roll : {'raise', 'nat', 'forward', 'following', 'backward', 'preceding', 'modifiedfollowing', 'modifiedpreceding'}, optional - How to treat dates that do not fall on a valid day. The default - is 'raise'. - - * 'raise' means to raise an exception for an invalid day. - * 'nat' means to return a NaT (not-a-time) for an invalid day. - * 'forward' and 'following' mean to take the first valid day - later in time. - * 'backward' and 'preceding' mean to take the first valid day - earlier in time. - * 'modifiedfollowing' means to take the first valid day - later in time unless it is across a Month boundary, in which - case to take the first valid day earlier in time. - * 'modifiedpreceding' means to take the first valid day - earlier in time unless it is across a Month boundary, in which - case to take the first valid day later in time. - weekmask : str or array_like of bool, optional - A seven-element array indicating which of Monday through Sunday are - valid days. May be specified as a length-seven list or array, like - [1,1,1,1,1,0,0]; a length-seven string, like '1111100'; or a string - like "Mon Tue Wed Thu Fri", made up of 3-character abbreviations for - weekdays, optionally separated by white space. Valid abbreviations - are: Mon Tue Wed Thu Fri Sat Sun - holidays : array_like of datetime64[D], optional - An array of dates to consider as invalid dates. They may be - specified in any order, and NaT (not-a-time) dates are ignored. - This list is saved in a normalized form that is suited for - fast calculations of valid days. - busdaycal : busdaycalendar, optional - A `busdaycalendar` object which specifies the valid days. If this - parameter is provided, neither weekmask nor holidays may be - provided. - out : array of datetime64[D], optional - If provided, this array is filled with the result. - - Returns - ------- - out : array of datetime64[D] - An array with a shape from broadcasting ``dates`` and ``offsets`` - together, containing the dates with offsets applied. - - See Also - -------- - busdaycalendar: An object that specifies a custom set of valid days. - is_busday : Returns a boolean array indicating valid days. - busday_count : Counts how many valid days are in a half-open date range. - - Examples - -------- - >>> # First business day in October 2011 (not accounting for holidays) - ... np.busday_offset('2011-10', 0, roll='forward') - numpy.datetime64('2011-10-03','D') - >>> # Last business day in February 2012 (not accounting for holidays) - ... np.busday_offset('2012-03', -1, roll='forward') - numpy.datetime64('2012-02-29','D') - >>> # Third Wednesday in January 2011 - ... np.busday_offset('2011-01', 2, roll='forward', weekmask='Wed') - numpy.datetime64('2011-01-19','D') - >>> # 2012 Mother's Day in Canada and the U.S. - ... np.busday_offset('2012-05', 1, roll='forward', weekmask='Sun') - numpy.datetime64('2012-05-13','D') - - >>> # First business day on or after a date - ... np.busday_offset('2011-03-20', 0, roll='forward') - numpy.datetime64('2011-03-21','D') - >>> np.busday_offset('2011-03-22', 0, roll='forward') - numpy.datetime64('2011-03-22','D') - >>> # First business day after a date - ... np.busday_offset('2011-03-20', 1, roll='backward') - numpy.datetime64('2011-03-21','D') - >>> np.busday_offset('2011-03-22', 1, roll='backward') - numpy.datetime64('2011-03-23','D') - """) - -add_newdoc('numpy.core.multiarray', 'busday_count', - """ - busday_count(begindates, enddates, weekmask='1111100', holidays=[], busdaycal=None, out=None) - - Counts the number of valid days between `begindates` and - `enddates`, not including the day of `enddates`. - - If ``enddates`` specifies a date value that is earlier than the - corresponding ``begindates`` date value, the count will be negative. - - .. versionadded:: 1.7.0 - - Parameters - ---------- - begindates : array_like of datetime64[D] - The array of the first dates for counting. - enddates : array_like of datetime64[D] - The array of the end dates for counting, which are excluded - from the count themselves. - weekmask : str or array_like of bool, optional - A seven-element array indicating which of Monday through Sunday are - valid days. May be specified as a length-seven list or array, like - [1,1,1,1,1,0,0]; a length-seven string, like '1111100'; or a string - like "Mon Tue Wed Thu Fri", made up of 3-character abbreviations for - weekdays, optionally separated by white space. Valid abbreviations - are: Mon Tue Wed Thu Fri Sat Sun - holidays : array_like of datetime64[D], optional - An array of dates to consider as invalid dates. They may be - specified in any order, and NaT (not-a-time) dates are ignored. - This list is saved in a normalized form that is suited for - fast calculations of valid days. - busdaycal : busdaycalendar, optional - A `busdaycalendar` object which specifies the valid days. If this - parameter is provided, neither weekmask nor holidays may be - provided. - out : array of int, optional - If provided, this array is filled with the result. - - Returns - ------- - out : array of int - An array with a shape from broadcasting ``begindates`` and ``enddates`` - together, containing the number of valid days between - the begin and end dates. - - See Also - -------- - busdaycalendar: An object that specifies a custom set of valid days. - is_busday : Returns a boolean array indicating valid days. - busday_offset : Applies an offset counted in valid days. - - Examples - -------- - >>> # Number of weekdays in January 2011 - ... np.busday_count('2011-01', '2011-02') - 21 - >>> # Number of weekdays in 2011 - ... np.busday_count('2011', '2012') - 260 - >>> # Number of Saturdays in 2011 - ... np.busday_count('2011', '2012', weekmask='Sat') - 53 - """) - add_newdoc('numpy.core.multiarray', 'normalize_axis_index', """ normalize_axis_index(axis, ndim, msg_prefix=None) @@ -7051,67 +6115,6 @@ add_newdoc('numpy.core.multiarray', 'normalize_axis_index', AxisError: axes_arg: axis -4 is out of bounds for array of dimension 3 """) -add_newdoc('numpy.core.multiarray', 'datetime_as_string', - """ - datetime_as_string(arr, unit=None, timezone='naive', casting='same_kind') - - Convert an array of datetimes into an array of strings. - - Parameters - ---------- - arr : array_like of datetime64 - The array of UTC timestamps to format. - unit : str - One of None, 'auto', or a :ref:`datetime unit <arrays.dtypes.dateunits>`. - timezone : {'naive', 'UTC', 'local'} or tzinfo - Timezone information to use when displaying the datetime. If 'UTC', end - with a Z to indicate UTC time. If 'local', convert to the local timezone - first, and suffix with a +-#### timezone offset. If a tzinfo object, - then do as with 'local', but use the specified timezone. - casting : {'no', 'equiv', 'safe', 'same_kind', 'unsafe'} - Casting to allow when changing between datetime units. - - Returns - ------- - str_arr : ndarray - An array of strings the same shape as `arr`. - - Examples - -------- - >>> d = np.arange('2002-10-27T04:30', 4*60, 60, dtype='M8[m]') - >>> d - array(['2002-10-27T04:30', '2002-10-27T05:30', '2002-10-27T06:30', - '2002-10-27T07:30'], dtype='datetime64[m]') - - Setting the timezone to UTC shows the same information, but with a Z suffix - - >>> np.datetime_as_string(d, timezone='UTC') - array(['2002-10-27T04:30Z', '2002-10-27T05:30Z', '2002-10-27T06:30Z', - '2002-10-27T07:30Z'], dtype='<U35') - - Note that we picked datetimes that cross a DST boundary. Passing in a - ``pytz`` timezone object will print the appropriate offset - - >>> np.datetime_as_string(d, timezone=pytz.timezone('US/Eastern')) - array(['2002-10-27T00:30-0400', '2002-10-27T01:30-0400', - '2002-10-27T01:30-0500', '2002-10-27T02:30-0500'], dtype='<U39') - - Passing in a unit will change the precision - - >>> np.datetime_as_string(d, unit='h') - array(['2002-10-27T04', '2002-10-27T05', '2002-10-27T06', '2002-10-27T07'], - dtype='<U32') - >>> np.datetime_as_string(d, unit='s') - array(['2002-10-27T04:30:00', '2002-10-27T05:30:00', '2002-10-27T06:30:00', - '2002-10-27T07:30:00'], dtype='<U38') - - 'casting' can be used to specify whether precision can be changed - - >>> np.datetime_as_string(d, unit='h', casting='safe') - TypeError: Cannot create a datetime string as units 'h' from a NumPy - datetime with units 'm' according to the rule 'safe' - """) - add_newdoc('numpy.core.multiarray', 'datetime_data', """ datetime_data(dtype, /) diff --git a/numpy/core/_dtype.py b/numpy/core/_dtype.py index d115e0fa6..3a12c8fad 100644 --- a/numpy/core/_dtype.py +++ b/numpy/core/_dtype.py @@ -138,7 +138,9 @@ def _scalar_str(dtype, short): else: return "'%sU%d'" % (byteorder, dtype.itemsize / 4) - elif dtype.type == np.void: + # unlike the other types, subclasses of void are preserved - but + # historically the repr does not actually reveal the subclass + elif issubclass(dtype.type, np.void): if _isunsized(dtype): return "'V'" else: diff --git a/numpy/core/_dtype_ctypes.py b/numpy/core/_dtype_ctypes.py new file mode 100644 index 000000000..f10b4e99f --- /dev/null +++ b/numpy/core/_dtype_ctypes.py @@ -0,0 +1,68 @@ +""" +Conversion from ctypes to dtype. + +In an ideal world, we could acheive this through the PEP3118 buffer protocol, +something like:: + + def dtype_from_ctypes_type(t): + # needed to ensure that the shape of `t` is within memoryview.format + class DummyStruct(ctypes.Structure): + _fields_ = [('a', t)] + + # empty to avoid memory allocation + ctype_0 = (DummyStruct * 0)() + mv = memoryview(ctype_0) + + # convert the struct, and slice back out the field + return _dtype_from_pep3118(mv.format)['a'] + +Unfortunately, this fails because: + +* ctypes cannot handle length-0 arrays with PEP3118 (bpo-32782) +* PEP3118 cannot represent unions, but both numpy and ctypes can +* ctypes cannot handle big-endian structs with PEP3118 (bpo-32780) +""" +import _ctypes +import ctypes + +import numpy as np + + +def _from_ctypes_array(t): + return np.dtype((dtype_from_ctypes_type(t._type_), (t._length_,))) + + +def _from_ctypes_structure(t): + # TODO: gh-10533, gh-10532 + fields = [] + for item in t._fields_: + if len(item) > 2: + raise TypeError( + "ctypes bitfields have no dtype equivalent") + fname, ftyp = item + fields.append((fname, dtype_from_ctypes_type(ftyp))) + + # by default, ctypes structs are aligned + return np.dtype(fields, align=True) + + +def dtype_from_ctypes_type(t): + """ + Construct a dtype object from a ctypes type + """ + if issubclass(t, _ctypes.Array): + return _from_ctypes_array(t) + elif issubclass(t, _ctypes._Pointer): + raise TypeError("ctypes pointers have no dtype equivalent") + elif issubclass(t, _ctypes.Structure): + return _from_ctypes_structure(t) + elif issubclass(t, _ctypes.Union): + # TODO + raise NotImplementedError( + "conversion from ctypes.Union types like {} to dtype" + .format(t.__name__)) + elif isinstance(t._type_, str): + return np.dtype(t._type_) + else: + raise NotImplementedError( + "Unknown ctypes type {}".format(t.__name__)) diff --git a/numpy/core/_internal.py b/numpy/core/_internal.py index c4d967dc2..30069f0ca 100644 --- a/numpy/core/_internal.py +++ b/numpy/core/_internal.py @@ -796,13 +796,13 @@ def _ufunc_doc_signature_formatter(ufunc): ) -def _is_from_ctypes(obj): - # determine if an object comes from ctypes, in order to work around +def npy_ctypes_check(cls): + # determine if a class comes from ctypes, in order to work around # a bug in the buffer protocol for those objects, bpo-10746 try: # ctypes class are new-style, so have an __mro__. This probably fails # for ctypes classes with multiple inheritance. - ctype_base = type(obj).__mro__[-2] + ctype_base = cls.__mro__[-2] # right now, they're part of the _ctypes module return 'ctypes' in ctype_base.__module__ except Exception: diff --git a/numpy/core/arrayprint.py b/numpy/core/arrayprint.py index 1b9fbbfa9..ccc1468c4 100644 --- a/numpy/core/arrayprint.py +++ b/numpy/core/arrayprint.py @@ -506,7 +506,7 @@ def _array2string_dispatcher( return (a,) -@array_function_dispatch(_array2string_dispatcher) +@array_function_dispatch(_array2string_dispatcher, module='numpy') def array2string(a, max_line_width=None, precision=None, suppress_small=None, separator=' ', prefix="", style=np._NoValue, formatter=None, threshold=None, @@ -1381,12 +1381,59 @@ def dtype_short_repr(dtype): return typename +def _array_repr_implementation( + arr, max_line_width=None, precision=None, suppress_small=None, + array2string=array2string): + """Internal version of array_repr() that allows overriding array2string.""" + if max_line_width is None: + max_line_width = _format_options['linewidth'] + + if type(arr) is not ndarray: + class_name = type(arr).__name__ + else: + class_name = "array" + + skipdtype = dtype_is_implied(arr.dtype) and arr.size > 0 + + prefix = class_name + "(" + suffix = ")" if skipdtype else "," + + if (_format_options['legacy'] == '1.13' and + arr.shape == () and not arr.dtype.names): + lst = repr(arr.item()) + elif arr.size > 0 or arr.shape == (0,): + lst = array2string(arr, max_line_width, precision, suppress_small, + ', ', prefix, suffix=suffix) + else: # show zero-length shape unless it is (0,) + lst = "[], shape=%s" % (repr(arr.shape),) + + arr_str = prefix + lst + suffix + + if skipdtype: + return arr_str + + dtype_str = "dtype={})".format(dtype_short_repr(arr.dtype)) + + # compute whether we should put dtype on a new line: Do so if adding the + # dtype would extend the last line past max_line_width. + # Note: This line gives the correct result even when rfind returns -1. + last_line_len = len(arr_str) - (arr_str.rfind('\n') + 1) + spacer = " " + if _format_options['legacy'] == '1.13': + if issubclass(arr.dtype.type, flexible): + spacer = '\n' + ' '*len(class_name + "(") + elif last_line_len + len(dtype_str) + 1 > max_line_width: + spacer = '\n' + ' '*len(class_name + "(") + + return arr_str + spacer + dtype_str + + def _array_repr_dispatcher( arr, max_line_width=None, precision=None, suppress_small=None): return (arr,) -@array_function_dispatch(_array_repr_dispatcher) +@array_function_dispatch(_array_repr_dispatcher, module='numpy') def array_repr(arr, max_line_width=None, precision=None, suppress_small=None): """ Return the string representation of an array. @@ -1429,50 +1476,31 @@ def array_repr(arr, max_line_width=None, precision=None, suppress_small=None): 'array([ 0.000001, 0. , 2. , 3. ])' """ - if max_line_width is None: - max_line_width = _format_options['linewidth'] + return _array_repr_implementation( + arr, max_line_width, precision, suppress_small) - if type(arr) is not ndarray: - class_name = type(arr).__name__ - else: - class_name = "array" - skipdtype = dtype_is_implied(arr.dtype) and arr.size > 0 +_guarded_str = _recursive_guard()(str) - prefix = class_name + "(" - suffix = ")" if skipdtype else "," +def _array_str_implementation( + a, max_line_width=None, precision=None, suppress_small=None, + array2string=array2string): + """Internal version of array_str() that allows overriding array2string.""" if (_format_options['legacy'] == '1.13' and - arr.shape == () and not arr.dtype.names): - lst = repr(arr.item()) - elif arr.size > 0 or arr.shape == (0,): - lst = array2string(arr, max_line_width, precision, suppress_small, - ', ', prefix, suffix=suffix) - else: # show zero-length shape unless it is (0,) - lst = "[], shape=%s" % (repr(arr.shape),) - - arr_str = prefix + lst + suffix - - if skipdtype: - return arr_str - - dtype_str = "dtype={})".format(dtype_short_repr(arr.dtype)) - - # compute whether we should put dtype on a new line: Do so if adding the - # dtype would extend the last line past max_line_width. - # Note: This line gives the correct result even when rfind returns -1. - last_line_len = len(arr_str) - (arr_str.rfind('\n') + 1) - spacer = " " - if _format_options['legacy'] == '1.13': - if issubclass(arr.dtype.type, flexible): - spacer = '\n' + ' '*len(class_name + "(") - elif last_line_len + len(dtype_str) + 1 > max_line_width: - spacer = '\n' + ' '*len(class_name + "(") - - return arr_str + spacer + dtype_str + a.shape == () and not a.dtype.names): + return str(a.item()) + # the str of 0d arrays is a special case: It should appear like a scalar, + # so floats are not truncated by `precision`, and strings are not wrapped + # in quotes. So we return the str of the scalar value. + if a.shape == (): + # obtain a scalar and call str on it, avoiding problems for subclasses + # for which indexing with () returns a 0d instead of a scalar by using + # ndarray's getindex. Also guard against recursive 0d object arrays. + return _guarded_str(np.ndarray.__getitem__(a, ())) -_guarded_str = _recursive_guard()(str) + return array2string(a, max_line_width, precision, suppress_small, ' ', "") def _array_str_dispatcher( @@ -1480,7 +1508,7 @@ def _array_str_dispatcher( return (a,) -@array_function_dispatch(_array_str_dispatcher) +@array_function_dispatch(_array_str_dispatcher, module='numpy') def array_str(a, max_line_width=None, precision=None, suppress_small=None): """ Return a string representation of the data in an array. @@ -1515,20 +1543,15 @@ def array_str(a, max_line_width=None, precision=None, suppress_small=None): '[0 1 2]' """ - if (_format_options['legacy'] == '1.13' and - a.shape == () and not a.dtype.names): - return str(a.item()) + return _array_str_implementation( + a, max_line_width, precision, suppress_small) - # the str of 0d arrays is a special case: It should appear like a scalar, - # so floats are not truncated by `precision`, and strings are not wrapped - # in quotes. So we return the str of the scalar value. - if a.shape == (): - # obtain a scalar and call str on it, avoiding problems for subclasses - # for which indexing with () returns a 0d instead of a scalar by using - # ndarray's getindex. Also guard against recursive 0d object arrays. - return _guarded_str(np.ndarray.__getitem__(a, ())) - return array2string(a, max_line_width, precision, suppress_small, ' ', "") +_default_array_str = functools.partial(_array_str_implementation, + array2string=array2string.__wrapped__) +_default_array_repr = functools.partial(_array_repr_implementation, + array2string=array2string.__wrapped__) + def set_string_function(f, repr=True): """ @@ -1583,11 +1606,11 @@ def set_string_function(f, repr=True): """ if f is None: if repr: - return multiarray.set_string_function(array_repr, 1) + return multiarray.set_string_function(_default_array_repr, 1) else: - return multiarray.set_string_function(array_str, 0) + return multiarray.set_string_function(_default_array_str, 0) else: return multiarray.set_string_function(f, repr) -set_string_function(array_str, 0) -set_string_function(array_repr, 1) +set_string_function(_default_array_str, 0) +set_string_function(_default_array_repr, 1) diff --git a/numpy/core/code_generators/cversions.txt b/numpy/core/code_generators/cversions.txt index 43c32eac6..c8b998bfc 100644 --- a/numpy/core/code_generators/cversions.txt +++ b/numpy/core/code_generators/cversions.txt @@ -43,3 +43,5 @@ # PyArray_SetWritebackIfCopyBase and deprecated PyArray_SetUpdateIfCopyBase. 0x0000000c = a1bc756c5782853ec2e3616cf66869d8 +# Version 13 (Numpy 1.16) Added fields core_dim_flags and core_dim_sizes to PyUFuncObject +0x0000000d = a1bc756c5782853ec2e3616cf66869d8 diff --git a/numpy/core/code_generators/generate_umath.py b/numpy/core/code_generators/generate_umath.py index 6dc01877b..199ad831b 100644 --- a/numpy/core/code_generators/generate_umath.py +++ b/numpy/core/code_generators/generate_umath.py @@ -791,8 +791,9 @@ defdict = { 'remainder': Ufunc(2, 1, None, docstrings.get('numpy.core.umath.remainder'), - None, + 'PyUFunc_RemainderTypeResolver', TD(intflt), + [TypeDescription('m', FullTypeDescr, 'mm', 'm')], TD(O, f='PyNumber_Remainder'), ), 'divmod': diff --git a/numpy/core/defchararray.py b/numpy/core/defchararray.py index 6d0a0add5..e86086012 100644 --- a/numpy/core/defchararray.py +++ b/numpy/core/defchararray.py @@ -17,11 +17,13 @@ The preferred alias for `defchararray` is `numpy.char`. """ from __future__ import division, absolute_import, print_function +import functools import sys from .numerictypes import string_, unicode_, integer, object_, bool_, character from .numeric import ndarray, compare_chararrays from .numeric import array as narray from numpy.core.multiarray import _vec_string +from numpy.core import overrides from numpy.compat import asbytes, long import numpy @@ -47,6 +49,10 @@ else: _bytes = str _len = len +array_function_dispatch = functools.partial( + overrides.array_function_dispatch, module='numpy.char') + + def _use_unicode(*args): """ Helper function for determining the output type of some string @@ -95,6 +101,11 @@ def _get_num_chars(a): return a.itemsize +def _binary_op_dispatcher(x1, x2): + return (x1, x2) + + +@array_function_dispatch(_binary_op_dispatcher) def equal(x1, x2): """ Return (x1 == x2) element-wise. @@ -119,6 +130,8 @@ def equal(x1, x2): """ return compare_chararrays(x1, x2, '==', True) + +@array_function_dispatch(_binary_op_dispatcher) def not_equal(x1, x2): """ Return (x1 != x2) element-wise. @@ -143,6 +156,8 @@ def not_equal(x1, x2): """ return compare_chararrays(x1, x2, '!=', True) + +@array_function_dispatch(_binary_op_dispatcher) def greater_equal(x1, x2): """ Return (x1 >= x2) element-wise. @@ -168,6 +183,8 @@ def greater_equal(x1, x2): """ return compare_chararrays(x1, x2, '>=', True) + +@array_function_dispatch(_binary_op_dispatcher) def less_equal(x1, x2): """ Return (x1 <= x2) element-wise. @@ -192,6 +209,8 @@ def less_equal(x1, x2): """ return compare_chararrays(x1, x2, '<=', True) + +@array_function_dispatch(_binary_op_dispatcher) def greater(x1, x2): """ Return (x1 > x2) element-wise. @@ -216,6 +235,8 @@ def greater(x1, x2): """ return compare_chararrays(x1, x2, '>', True) + +@array_function_dispatch(_binary_op_dispatcher) def less(x1, x2): """ Return (x1 < x2) element-wise. @@ -240,6 +261,12 @@ def less(x1, x2): """ return compare_chararrays(x1, x2, '<', True) + +def _unary_op_dispatcher(a): + return (a,) + + +@array_function_dispatch(_unary_op_dispatcher) def str_len(a): """ Return len(a) element-wise. @@ -259,6 +286,8 @@ def str_len(a): """ return _vec_string(a, integer, '__len__') + +@array_function_dispatch(_binary_op_dispatcher) def add(x1, x2): """ Return element-wise string concatenation for two arrays of str or unicode. @@ -285,6 +314,12 @@ def add(x1, x2): dtype = _use_unicode(arr1, arr2) return _vec_string(arr1, (dtype, out_size), '__add__', (arr2,)) + +def _multiply_dispatcher(a, i): + return (a,) + + +@array_function_dispatch(_multiply_dispatcher) def multiply(a, i): """ Return (a * i), that is string multiple concatenation, @@ -313,6 +348,12 @@ def multiply(a, i): return _vec_string( a_arr, (a_arr.dtype.type, out_size), '__mul__', (i_arr,)) + +def _mod_dispatcher(a, values): + return (a, values) + + +@array_function_dispatch(_mod_dispatcher) def mod(a, values): """ Return (a % i), that is pre-Python 2.6 string formatting @@ -339,6 +380,8 @@ def mod(a, values): return _to_string_or_unicode_array( _vec_string(a, object_, '__mod__', (values,))) + +@array_function_dispatch(_unary_op_dispatcher) def capitalize(a): """ Return a copy of `a` with only the first character of each element @@ -377,6 +420,11 @@ def capitalize(a): return _vec_string(a_arr, a_arr.dtype, 'capitalize') +def _center_dispatcher(a, width, fillchar=None): + return (a,) + + +@array_function_dispatch(_center_dispatcher) def center(a, width, fillchar=' '): """ Return a copy of `a` with its elements centered in a string of @@ -413,6 +461,11 @@ def center(a, width, fillchar=' '): a_arr, (a_arr.dtype.type, size), 'center', (width_arr, fillchar)) +def _count_dispatcher(a, sub, start=None, end=None): + return (a,) + + +@array_function_dispatch(_count_dispatcher) def count(a, sub, start=0, end=None): """ Returns an array with the number of non-overlapping occurrences of @@ -459,6 +512,11 @@ def count(a, sub, start=0, end=None): return _vec_string(a, integer, 'count', [sub, start] + _clean_args(end)) +def _code_dispatcher(a, encoding=None, errors=None): + return (a,) + + +@array_function_dispatch(_code_dispatcher) def decode(a, encoding=None, errors=None): """ Calls `str.decode` element-wise. @@ -505,6 +563,7 @@ def decode(a, encoding=None, errors=None): _vec_string(a, object_, 'decode', _clean_args(encoding, errors))) +@array_function_dispatch(_code_dispatcher) def encode(a, encoding=None, errors=None): """ Calls `str.encode` element-wise. @@ -540,6 +599,11 @@ def encode(a, encoding=None, errors=None): _vec_string(a, object_, 'encode', _clean_args(encoding, errors))) +def _endswith_dispatcher(a, suffix, start=None, end=None): + return (a,) + + +@array_function_dispatch(_endswith_dispatcher) def endswith(a, suffix, start=0, end=None): """ Returns a boolean array which is `True` where the string element @@ -584,6 +648,11 @@ def endswith(a, suffix, start=0, end=None): a, bool_, 'endswith', [suffix, start] + _clean_args(end)) +def _expandtabs_dispatcher(a, tabsize=None): + return (a,) + + +@array_function_dispatch(_expandtabs_dispatcher) def expandtabs(a, tabsize=8): """ Return a copy of each string element where all tab characters are @@ -619,6 +688,7 @@ def expandtabs(a, tabsize=8): _vec_string(a, object_, 'expandtabs', (tabsize,))) +@array_function_dispatch(_count_dispatcher) def find(a, sub, start=0, end=None): """ For each element, return the lowest index in the string where @@ -654,6 +724,7 @@ def find(a, sub, start=0, end=None): a, integer, 'find', [sub, start] + _clean_args(end)) +@array_function_dispatch(_count_dispatcher) def index(a, sub, start=0, end=None): """ Like `find`, but raises `ValueError` when the substring is not found. @@ -681,6 +752,8 @@ def index(a, sub, start=0, end=None): return _vec_string( a, integer, 'index', [sub, start] + _clean_args(end)) + +@array_function_dispatch(_unary_op_dispatcher) def isalnum(a): """ Returns true for each element if all characters in the string are @@ -705,6 +778,8 @@ def isalnum(a): """ return _vec_string(a, bool_, 'isalnum') + +@array_function_dispatch(_unary_op_dispatcher) def isalpha(a): """ Returns true for each element if all characters in the string are @@ -729,6 +804,8 @@ def isalpha(a): """ return _vec_string(a, bool_, 'isalpha') + +@array_function_dispatch(_unary_op_dispatcher) def isdigit(a): """ Returns true for each element if all characters in the string are @@ -753,6 +830,8 @@ def isdigit(a): """ return _vec_string(a, bool_, 'isdigit') + +@array_function_dispatch(_unary_op_dispatcher) def islower(a): """ Returns true for each element if all cased characters in the @@ -778,6 +857,8 @@ def islower(a): """ return _vec_string(a, bool_, 'islower') + +@array_function_dispatch(_unary_op_dispatcher) def isspace(a): """ Returns true for each element if there are only whitespace @@ -803,6 +884,8 @@ def isspace(a): """ return _vec_string(a, bool_, 'isspace') + +@array_function_dispatch(_unary_op_dispatcher) def istitle(a): """ Returns true for each element if the element is a titlecased @@ -827,6 +910,8 @@ def istitle(a): """ return _vec_string(a, bool_, 'istitle') + +@array_function_dispatch(_unary_op_dispatcher) def isupper(a): """ Returns true for each element if all cased characters in the @@ -852,6 +937,12 @@ def isupper(a): """ return _vec_string(a, bool_, 'isupper') + +def _join_dispatcher(sep, seq): + return (sep, seq) + + +@array_function_dispatch(_join_dispatcher) def join(sep, seq): """ Return a string which is the concatenation of the strings in the @@ -877,6 +968,12 @@ def join(sep, seq): _vec_string(sep, object_, 'join', (seq,))) + +def _just_dispatcher(a, width, fillchar=None): + return (a,) + + +@array_function_dispatch(_just_dispatcher) def ljust(a, width, fillchar=' '): """ Return an array with the elements of `a` left-justified in a @@ -912,6 +1009,7 @@ def ljust(a, width, fillchar=' '): a_arr, (a_arr.dtype.type, size), 'ljust', (width_arr, fillchar)) +@array_function_dispatch(_unary_op_dispatcher) def lower(a): """ Return an array with the elements converted to lowercase. @@ -948,6 +1046,11 @@ def lower(a): return _vec_string(a_arr, a_arr.dtype, 'lower') +def _strip_dispatcher(a, chars=None): + return (a,) + + +@array_function_dispatch(_strip_dispatcher) def lstrip(a, chars=None): """ For each element in `a`, return a copy with the leading characters @@ -1005,6 +1108,11 @@ def lstrip(a, chars=None): return _vec_string(a_arr, a_arr.dtype, 'lstrip', (chars,)) +def _partition_dispatcher(a, sep): + return (a,) + + +@array_function_dispatch(_partition_dispatcher) def partition(a, sep): """ Partition each element in `a` around `sep`. @@ -1040,6 +1148,11 @@ def partition(a, sep): _vec_string(a, object_, 'partition', (sep,))) +def _replace_dispatcher(a, old, new, count=None): + return (a,) + + +@array_function_dispatch(_replace_dispatcher) def replace(a, old, new, count=None): """ For each element in `a`, return a copy of the string with all @@ -1072,6 +1185,7 @@ def replace(a, old, new, count=None): a, object_, 'replace', [old, new] + _clean_args(count))) +@array_function_dispatch(_count_dispatcher) def rfind(a, sub, start=0, end=None): """ For each element in `a`, return the highest index in the string @@ -1104,6 +1218,7 @@ def rfind(a, sub, start=0, end=None): a, integer, 'rfind', [sub, start] + _clean_args(end)) +@array_function_dispatch(_count_dispatcher) def rindex(a, sub, start=0, end=None): """ Like `rfind`, but raises `ValueError` when the substring `sub` is @@ -1133,6 +1248,7 @@ def rindex(a, sub, start=0, end=None): a, integer, 'rindex', [sub, start] + _clean_args(end)) +@array_function_dispatch(_just_dispatcher) def rjust(a, width, fillchar=' '): """ Return an array with the elements of `a` right-justified in a @@ -1168,6 +1284,7 @@ def rjust(a, width, fillchar=' '): a_arr, (a_arr.dtype.type, size), 'rjust', (width_arr, fillchar)) +@array_function_dispatch(_partition_dispatcher) def rpartition(a, sep): """ Partition (split) each element around the right-most separator. @@ -1203,6 +1320,11 @@ def rpartition(a, sep): _vec_string(a, object_, 'rpartition', (sep,))) +def _split_dispatcher(a, sep=None, maxsplit=None): + return (a,) + + +@array_function_dispatch(_split_dispatcher) def rsplit(a, sep=None, maxsplit=None): """ For each element in `a`, return a list of the words in the @@ -1240,6 +1362,11 @@ def rsplit(a, sep=None, maxsplit=None): a, object_, 'rsplit', [sep] + _clean_args(maxsplit)) +def _strip_dispatcher(a, chars=None): + return (a,) + + +@array_function_dispatch(_strip_dispatcher) def rstrip(a, chars=None): """ For each element in `a`, return a copy with the trailing @@ -1284,6 +1411,7 @@ def rstrip(a, chars=None): return _vec_string(a_arr, a_arr.dtype, 'rstrip', (chars,)) +@array_function_dispatch(_split_dispatcher) def split(a, sep=None, maxsplit=None): """ For each element in `a`, return a list of the words in the @@ -1318,6 +1446,11 @@ def split(a, sep=None, maxsplit=None): a, object_, 'split', [sep] + _clean_args(maxsplit)) +def _splitlines_dispatcher(a, keepends=None): + return (a,) + + +@array_function_dispatch(_splitlines_dispatcher) def splitlines(a, keepends=None): """ For each element in `a`, return a list of the lines in the @@ -1347,6 +1480,11 @@ def splitlines(a, keepends=None): a, object_, 'splitlines', _clean_args(keepends)) +def _startswith_dispatcher(a, prefix, start=None, end=None): + return (a,) + + +@array_function_dispatch(_startswith_dispatcher) def startswith(a, prefix, start=0, end=None): """ Returns a boolean array which is `True` where the string element @@ -1378,6 +1516,7 @@ def startswith(a, prefix, start=0, end=None): a, bool_, 'startswith', [prefix, start] + _clean_args(end)) +@array_function_dispatch(_strip_dispatcher) def strip(a, chars=None): """ For each element in `a`, return a copy with the leading and @@ -1426,6 +1565,7 @@ def strip(a, chars=None): return _vec_string(a_arr, a_arr.dtype, 'strip', _clean_args(chars)) +@array_function_dispatch(_unary_op_dispatcher) def swapcase(a): """ Return element-wise a copy of the string with @@ -1463,6 +1603,7 @@ def swapcase(a): return _vec_string(a_arr, a_arr.dtype, 'swapcase') +@array_function_dispatch(_unary_op_dispatcher) def title(a): """ Return element-wise title cased version of string or unicode. @@ -1502,6 +1643,11 @@ def title(a): return _vec_string(a_arr, a_arr.dtype, 'title') +def _translate_dispatcher(a, table, deletechars=None): + return (a,) + + +@array_function_dispatch(_translate_dispatcher) def translate(a, table, deletechars=None): """ For each element in `a`, return a copy of the string where all @@ -1538,6 +1684,7 @@ def translate(a, table, deletechars=None): a_arr, a_arr.dtype, 'translate', [table] + _clean_args(deletechars)) +@array_function_dispatch(_unary_op_dispatcher) def upper(a): """ Return an array with the elements converted to uppercase. @@ -1574,6 +1721,11 @@ def upper(a): return _vec_string(a_arr, a_arr.dtype, 'upper') +def _zfill_dispatcher(a, width): + return (a,) + + +@array_function_dispatch(_zfill_dispatcher) def zfill(a, width): """ Return the numeric string left-filled with zeros @@ -1604,6 +1756,7 @@ def zfill(a, width): a_arr, (a_arr.dtype.type, size), 'zfill', (width_arr,)) +@array_function_dispatch(_unary_op_dispatcher) def isnumeric(a): """ For each element, return True if there are only numeric @@ -1635,6 +1788,7 @@ def isnumeric(a): return _vec_string(a, bool_, 'isnumeric') +@array_function_dispatch(_unary_op_dispatcher) def isdecimal(a): """ For each element, return True if there are only decimal diff --git a/numpy/core/einsumfunc.py b/numpy/core/einsumfunc.py index 1281b3c98..d9f88cb1c 100644 --- a/numpy/core/einsumfunc.py +++ b/numpy/core/einsumfunc.py @@ -9,6 +9,7 @@ import itertools from numpy.compat import basestring from numpy.core.multiarray import c_einsum from numpy.core.numeric import asanyarray, tensordot +from numpy.core.overrides import array_function_dispatch __all__ = ['einsum', 'einsum_path'] @@ -689,6 +690,17 @@ def _parse_einsum_input(operands): return (input_subscripts, output_subscript, operands) +def _einsum_path_dispatcher(*operands, **kwargs): + # NOTE: technically, we should only dispatch on array-like arguments, not + # subscripts (given as strings). But separating operands into + # arrays/subscripts is a little tricky/slow (given einsum's two supported + # signatures), so as a practical shortcut we dispatch on everything. + # Strings will be ignored for dispatching since they don't define + # __array_function__. + return operands + + +@array_function_dispatch(_einsum_path_dispatcher, module='numpy') def einsum_path(*operands, **kwargs): """ einsum_path(subscripts, *operands, optimize='greedy') @@ -980,7 +992,16 @@ def einsum_path(*operands, **kwargs): return (path, path_print) +def _einsum_dispatcher(*operands, **kwargs): + # Arguably we dispatch on more arguments that we really should; see note in + # _einsum_path_dispatcher for why. + for op in operands: + yield op + yield kwargs.get('out') + + # Rewrite einsum to handle different cases +@array_function_dispatch(_einsum_dispatcher, module='numpy') def einsum(*operands, **kwargs): """ einsum(subscripts, *operands, out=None, dtype=None, order='K', diff --git a/numpy/core/fromnumeric.py b/numpy/core/fromnumeric.py index b189dae5f..7dfb52fea 100644 --- a/numpy/core/fromnumeric.py +++ b/numpy/core/fromnumeric.py @@ -3,16 +3,17 @@ """ from __future__ import division, absolute_import, print_function +import functools import types import warnings import numpy as np from .. import VisibleDeprecationWarning from . import multiarray as mu +from . import overrides from . import umath as um from . import numerictypes as nt from .numeric import asarray, array, asanyarray, concatenate -from .overrides import array_function_dispatch from . import _methods _dt_ = nt.sctype2char @@ -32,6 +33,9 @@ _gentype = types.GeneratorType # save away Python sum _sum_ = sum +array_function_dispatch = functools.partial( + overrides.array_function_dispatch, module='numpy') + # functions that are now methods def _wrapit(obj, method, *args, **kwds): @@ -1071,10 +1075,10 @@ def argmax(a, axis=None, out=None): Examples -------- - >>> a = np.arange(6).reshape(2,3) + >>> a = np.arange(6).reshape(2,3) + 10 >>> a - array([[0, 1, 2], - [3, 4, 5]]) + array([[10, 11, 12], + [13, 14, 15]]) >>> np.argmax(a) 5 >>> np.argmax(a, axis=0) @@ -1088,7 +1092,7 @@ def argmax(a, axis=None, out=None): >>> ind (1, 2) >>> a[ind] - 5 + 15 >>> b = np.arange(6) >>> b[1] = 5 @@ -1140,10 +1144,10 @@ def argmin(a, axis=None, out=None): Examples -------- - >>> a = np.arange(6).reshape(2,3) + >>> a = np.arange(6).reshape(2,3) + 10 >>> a - array([[0, 1, 2], - [3, 4, 5]]) + array([[10, 11, 12], + [13, 14, 15]]) >>> np.argmin(a) 0 >>> np.argmin(a, axis=0) @@ -1157,12 +1161,12 @@ def argmin(a, axis=None, out=None): >>> ind (0, 0) >>> a[ind] - 0 + 10 - >>> b = np.arange(6) - >>> b[4] = 0 + >>> b = np.arange(6) + 10 + >>> b[4] = 10 >>> b - array([0, 1, 2, 3, 0, 5]) + array([10, 11, 12, 13, 10, 15]) >>> np.argmin(b) # Only the first occurrence is returned. 0 diff --git a/numpy/core/getlimits.py b/numpy/core/getlimits.py index 0e3c58793..389f16ff5 100644 --- a/numpy/core/getlimits.py +++ b/numpy/core/getlimits.py @@ -30,6 +30,32 @@ def _fr1(a): a.shape = () return a +class MachArLike(object): + """ Object to simulate MachAr instance """ + + def __init__(self, + ftype, + **kwargs): + params = _MACHAR_PARAMS[ftype] + float_conv = lambda v: array([v], ftype) + float_to_float = lambda v : _fr1(float_conv(v)) + float_to_str = lambda v: (params['fmt'] % array(_fr0(v)[0], ftype)) + + self.title = params['title'] + # Parameter types same as for discovered MachAr object. + self.epsilon = self.eps = float_to_float(kwargs.pop('eps')) + self.epsneg = float_to_float(kwargs.pop('epsneg')) + self.xmax = self.huge = float_to_float(kwargs.pop('huge')) + self.xmin = self.tiny = float_to_float(kwargs.pop('tiny')) + self.ibeta = params['itype'](kwargs.pop('ibeta')) + self.__dict__.update(kwargs) + self.precision = int(-log10(self.eps)) + self.resolution = float_to_float(float_conv(10) ** (-self.precision)) + self._str_eps = float_to_str(self.eps) + self._str_epsneg = float_to_str(self.epsneg) + self._str_xmin = float_to_str(self.xmin) + self._str_xmax = float_to_str(self.xmax) + self._str_resolution = float_to_str(self.resolution) _convert_to_float = { ntypes.csingle: ntypes.single, @@ -37,7 +63,6 @@ _convert_to_float = { ntypes.clongfloat: ntypes.longfloat } - # Parameters for creating MachAr / MachAr-like objects _title_fmt = 'numpy {} precision floating point number' _MACHAR_PARAMS = { @@ -58,194 +83,156 @@ _MACHAR_PARAMS = { fmt = '%12.5e', title = _title_fmt.format('half'))} - -class MachArLike(object): - """ Object to simulate MachAr instance """ - - def __init__(self, - ftype, - **kwargs): - params = _MACHAR_PARAMS[ftype] - float_conv = lambda v: array([v], ftype) - float_to_float = lambda v : _fr1(float_conv(v)) - self._float_to_str = lambda v: (params['fmt'] % - array(_fr0(v)[0], ftype)) - self.title = params['title'] - # Parameter types same as for discovered MachAr object. - self.epsilon = self.eps = float_to_float(kwargs.pop('eps')) - self.epsneg = float_to_float(kwargs.pop('epsneg')) - self.xmax = self.huge = float_to_float(kwargs.pop('huge')) - self.xmin = self.tiny = float_to_float(kwargs.pop('tiny')) - self.ibeta = params['itype'](kwargs.pop('ibeta')) - self.__dict__.update(kwargs) - self.precision = int(-log10(self.eps)) - self.resolution = float_to_float(float_conv(10) ** (-self.precision)) - - # Properties below to delay need for float_to_str, and thus avoid circular - # imports during early numpy module loading. - # See: https://github.com/numpy/numpy/pull/8983#discussion_r115838683 - - @property - def _str_eps(self): - return self._float_to_str(self.eps) - - @property - def _str_epsneg(self): - return self._float_to_str(self.epsneg) - - @property - def _str_xmin(self): - return self._float_to_str(self.xmin) - - @property - def _str_xmax(self): - return self._float_to_str(self.xmax) - - @property - def _str_resolution(self): - return self._float_to_str(self.resolution) - - -# Known parameters for float16 -# See docstring of MachAr class for description of parameters. -_f16 = ntypes.float16 -_float16_ma = MachArLike(_f16, - machep=-10, - negep=-11, - minexp=-14, - maxexp=16, - it=10, - iexp=5, - ibeta=2, - irnd=5, - ngrd=0, - eps=exp2(_f16(-10)), - epsneg=exp2(_f16(-11)), - huge=_f16(65504), - tiny=_f16(2 ** -14)) - -# Known parameters for float32 -_f32 = ntypes.float32 -_float32_ma = MachArLike(_f32, - machep=-23, - negep=-24, - minexp=-126, - maxexp=128, - it=23, - iexp=8, - ibeta=2, - irnd=5, - ngrd=0, - eps=exp2(_f32(-23)), - epsneg=exp2(_f32(-24)), - huge=_f32((1 - 2 ** -24) * 2**128), - tiny=exp2(_f32(-126))) - -# Known parameters for float64 -_f64 = ntypes.float64 -_epsneg_f64 = 2.0 ** -53.0 -_tiny_f64 = 2.0 ** -1022.0 -_float64_ma = MachArLike(_f64, - machep=-52, - negep=-53, - minexp=-1022, - maxexp=1024, - it=52, - iexp=11, - ibeta=2, - irnd=5, - ngrd=0, - eps=2.0 ** -52.0, - epsneg=_epsneg_f64, - huge=(1.0 - _epsneg_f64) / _tiny_f64 * _f64(4), - tiny=_tiny_f64) - -# Known parameters for IEEE 754 128-bit binary float -_ld = ntypes.longdouble -_epsneg_f128 = exp2(_ld(-113)) -_tiny_f128 = exp2(_ld(-16382)) -# Ignore runtime error when this is not f128 -with numeric.errstate(all='ignore'): - _huge_f128 = (_ld(1) - _epsneg_f128) / _tiny_f128 * _ld(4) -_float128_ma = MachArLike(_ld, - machep=-112, - negep=-113, - minexp=-16382, - maxexp=16384, - it=112, - iexp=15, - ibeta=2, - irnd=5, - ngrd=0, - eps=exp2(_ld(-112)), - epsneg=_epsneg_f128, - huge=_huge_f128, - tiny=_tiny_f128) - -# Known parameters for float80 (Intel 80-bit extended precision) -_epsneg_f80 = exp2(_ld(-64)) -_tiny_f80 = exp2(_ld(-16382)) -# Ignore runtime error when this is not f80 -with numeric.errstate(all='ignore'): - _huge_f80 = (_ld(1) - _epsneg_f80) / _tiny_f80 * _ld(4) -_float80_ma = MachArLike(_ld, - machep=-63, - negep=-64, - minexp=-16382, - maxexp=16384, - it=63, - iexp=15, - ibeta=2, - irnd=5, - ngrd=0, - eps=exp2(_ld(-63)), - epsneg=_epsneg_f80, - huge=_huge_f80, - tiny=_tiny_f80) - -# Guessed / known parameters for double double; see: -# https://en.wikipedia.org/wiki/Quadruple-precision_floating-point_format#Double-double_arithmetic -# These numbers have the same exponent range as float64, but extended number of -# digits in the significand. -_huge_dd = (umath.nextafter(_ld(inf), _ld(0)) - if hasattr(umath, 'nextafter') # Missing on some platforms? - else _float64_ma.huge) -_float_dd_ma = MachArLike(_ld, - machep=-105, - negep=-106, - minexp=-1022, - maxexp=1024, - it=105, - iexp=11, - ibeta=2, - irnd=5, - ngrd=0, - eps=exp2(_ld(-105)), - epsneg= exp2(_ld(-106)), - huge=_huge_dd, - tiny=exp2(_ld(-1022))) - - # Key to identify the floating point type. Key is result of # ftype('-0.1').newbyteorder('<').tobytes() # See: # https://perl5.git.perl.org/perl.git/blob/3118d7d684b56cbeb702af874f4326683c45f045:/Configure -_KNOWN_TYPES = { - b'\x9a\x99\x99\x99\x99\x99\xb9\xbf' : _float64_ma, - b'\xcd\xcc\xcc\xbd' : _float32_ma, - b'f\xae' : _float16_ma, +_KNOWN_TYPES = {} +def _register_type(machar, bytepat): + _KNOWN_TYPES[bytepat] = machar +_float_ma = {} + +def _register_known_types(): + # Known parameters for float16 + # See docstring of MachAr class for description of parameters. + f16 = ntypes.float16 + float16_ma = MachArLike(f16, + machep=-10, + negep=-11, + minexp=-14, + maxexp=16, + it=10, + iexp=5, + ibeta=2, + irnd=5, + ngrd=0, + eps=exp2(f16(-10)), + epsneg=exp2(f16(-11)), + huge=f16(65504), + tiny=f16(2 ** -14)) + _register_type(float16_ma, b'f\xae') + _float_ma[16] = float16_ma + + # Known parameters for float32 + f32 = ntypes.float32 + float32_ma = MachArLike(f32, + machep=-23, + negep=-24, + minexp=-126, + maxexp=128, + it=23, + iexp=8, + ibeta=2, + irnd=5, + ngrd=0, + eps=exp2(f32(-23)), + epsneg=exp2(f32(-24)), + huge=f32((1 - 2 ** -24) * 2**128), + tiny=exp2(f32(-126))) + _register_type(float32_ma, b'\xcd\xcc\xcc\xbd') + _float_ma[32] = float32_ma + + # Known parameters for float64 + f64 = ntypes.float64 + epsneg_f64 = 2.0 ** -53.0 + tiny_f64 = 2.0 ** -1022.0 + float64_ma = MachArLike(f64, + machep=-52, + negep=-53, + minexp=-1022, + maxexp=1024, + it=52, + iexp=11, + ibeta=2, + irnd=5, + ngrd=0, + eps=2.0 ** -52.0, + epsneg=epsneg_f64, + huge=(1.0 - epsneg_f64) / tiny_f64 * f64(4), + tiny=tiny_f64) + _register_type(float64_ma, b'\x9a\x99\x99\x99\x99\x99\xb9\xbf') + _float_ma[64] = float64_ma + + # Known parameters for IEEE 754 128-bit binary float + ld = ntypes.longdouble + epsneg_f128 = exp2(ld(-113)) + tiny_f128 = exp2(ld(-16382)) + # Ignore runtime error when this is not f128 + with numeric.errstate(all='ignore'): + huge_f128 = (ld(1) - epsneg_f128) / tiny_f128 * ld(4) + float128_ma = MachArLike(ld, + machep=-112, + negep=-113, + minexp=-16382, + maxexp=16384, + it=112, + iexp=15, + ibeta=2, + irnd=5, + ngrd=0, + eps=exp2(ld(-112)), + epsneg=epsneg_f128, + huge=huge_f128, + tiny=tiny_f128) + # IEEE 754 128-bit binary float + _register_type(float128_ma, + b'\x9a\x99\x99\x99\x99\x99\x99\x99\x99\x99\x99\x99\x99\x99\xfb\xbf') + _register_type(float128_ma, + b'\x9a\x99\x99\x99\x99\x99\x99\x99\x99\x99\x99\x99\x99\x99\xfb\xbf') + _float_ma[128] = float128_ma + + # Known parameters for float80 (Intel 80-bit extended precision) + epsneg_f80 = exp2(ld(-64)) + tiny_f80 = exp2(ld(-16382)) + # Ignore runtime error when this is not f80 + with numeric.errstate(all='ignore'): + huge_f80 = (ld(1) - epsneg_f80) / tiny_f80 * ld(4) + float80_ma = MachArLike(ld, + machep=-63, + negep=-64, + minexp=-16382, + maxexp=16384, + it=63, + iexp=15, + ibeta=2, + irnd=5, + ngrd=0, + eps=exp2(ld(-63)), + epsneg=epsneg_f80, + huge=huge_f80, + tiny=tiny_f80) # float80, first 10 bytes containing actual storage - b'\xcd\xcc\xcc\xcc\xcc\xcc\xcc\xcc\xfb\xbf' : _float80_ma, + _register_type(float80_ma, b'\xcd\xcc\xcc\xcc\xcc\xcc\xcc\xcc\xfb\xbf') + _float_ma[80] = float80_ma + + # Guessed / known parameters for double double; see: + # https://en.wikipedia.org/wiki/Quadruple-precision_floating-point_format#Double-double_arithmetic + # These numbers have the same exponent range as float64, but extended number of + # digits in the significand. + huge_dd = (umath.nextafter(ld(inf), ld(0)) + if hasattr(umath, 'nextafter') # Missing on some platforms? + else float64_ma.huge) + float_dd_ma = MachArLike(ld, + machep=-105, + negep=-106, + minexp=-1022, + maxexp=1024, + it=105, + iexp=11, + ibeta=2, + irnd=5, + ngrd=0, + eps=exp2(ld(-105)), + epsneg= exp2(ld(-106)), + huge=huge_dd, + tiny=exp2(ld(-1022))) # double double; low, high order (e.g. PPC 64) - b'\x9a\x99\x99\x99\x99\x99Y<\x9a\x99\x99\x99\x99\x99\xb9\xbf' : - _float_dd_ma, + _register_type(float_dd_ma, + b'\x9a\x99\x99\x99\x99\x99Y<\x9a\x99\x99\x99\x99\x99\xb9\xbf') # double double; high, low order (e.g. PPC 64 le) - b'\x9a\x99\x99\x99\x99\x99\xb9\xbf\x9a\x99\x99\x99\x99\x99Y<' : - _float_dd_ma, - # IEEE 754 128-bit binary float - b'\x9a\x99\x99\x99\x99\x99\x99\x99\x99\x99\x99\x99\x99\x99\xfb\xbf' : - _float128_ma, -} + _register_type(float_dd_ma, + b'\x9a\x99\x99\x99\x99\x99\xb9\xbf\x9a\x99\x99\x99\x99\x99Y<') + _float_ma['dd'] = float_dd_ma def _get_machar(ftype): diff --git a/numpy/core/include/numpy/ufuncobject.h b/numpy/core/include/numpy/ufuncobject.h index 9d48ab608..85f8a6c08 100644 --- a/numpy/core/include/numpy/ufuncobject.h +++ b/numpy/core/include/numpy/ufuncobject.h @@ -209,9 +209,32 @@ typedef struct _tagPyUFuncObject { * set by nditer object. */ npy_uint32 iter_flags; + + /* New in NPY_API_VERSION 0x0000000D and above */ + + /* + * for each core_num_dim_ix distinct dimension names, + * the possible "frozen" size (-1 if not frozen). + */ + npy_intp *core_dim_sizes; + + /* + * for each distinct core dimension, a set of UFUNC_CORE_DIM* flags + */ + npy_uint32 *core_dim_flags; + + + } PyUFuncObject; #include "arrayobject.h" +/* Generalized ufunc; 0x0001 reserved for possible use as CORE_ENABLED */ +/* the core dimension's size will be determined by the operands. */ +#define UFUNC_CORE_DIM_SIZE_INFERRED 0x0002 +/* the core dimension may be absent */ +#define UFUNC_CORE_DIM_CAN_IGNORE 0x0004 +/* flags inferred during execution */ +#define UFUNC_CORE_DIM_MISSING 0x00040000 #define UFUNC_ERR_IGNORE 0 #define UFUNC_ERR_WARN 1 diff --git a/numpy/core/memmap.py b/numpy/core/memmap.py index 8269f537f..f5cc68bb9 100644 --- a/numpy/core/memmap.py +++ b/numpy/core/memmap.py @@ -3,7 +3,7 @@ from __future__ import division, absolute_import, print_function import numpy as np from .numeric import uint8, ndarray, dtype from numpy.compat import ( - long, basestring, is_pathlib_path, contextlib_nullcontext + long, basestring, os_fspath, contextlib_nullcontext, is_pathlib_path ) __all__ = ['memmap'] @@ -218,10 +218,8 @@ class memmap(ndarray): if hasattr(filename, 'read'): f_ctx = contextlib_nullcontext(filename) - elif is_pathlib_path(filename): - f_ctx = filename.open(('r' if mode == 'c' else mode)+'b') else: - f_ctx = open(filename, ('r' if mode == 'c' else mode)+'b') + f_ctx = open(os_fspath(filename), ('r' if mode == 'c' else mode)+'b') with f_ctx as fid: fid.seek(0, 2) @@ -268,14 +266,13 @@ class memmap(ndarray): self.offset = offset self.mode = mode - if isinstance(filename, basestring): - self.filename = os.path.abspath(filename) - elif is_pathlib_path(filename): + if is_pathlib_path(filename): + # special case - if we were constructed with a pathlib.path, + # then filename is a path object, not a string self.filename = filename.resolve() - # py3 returns int for TemporaryFile().name - elif (hasattr(filename, "name") and - isinstance(filename.name, basestring)): - self.filename = os.path.abspath(filename.name) + elif hasattr(fid, "name") and isinstance(fid.name, basestring): + # py3 returns int for TemporaryFile().name + self.filename = os.path.abspath(fid.name) # same as memmap copies (e.g. memmap + 1) else: self.filename = None diff --git a/numpy/core/multiarray.py b/numpy/core/multiarray.py index 673328397..25debd2f8 100644 --- a/numpy/core/multiarray.py +++ b/numpy/core/multiarray.py @@ -6,7 +6,11 @@ by importing from the extension module. """ +import functools + +from . import overrides from . import _multiarray_umath +import numpy as np from numpy.core._multiarray_umath import * from numpy.core._multiarray_umath import ( _fastCopyAndTranspose, _flagdict, _insert, _reconstruct, _vec_string, @@ -35,3 +39,1120 @@ __all__ = [ 'tracemalloc_domain', 'typeinfo', 'unpackbits', 'unravel_index', 'vdot', 'where', 'zeros'] +array_function_dispatch = functools.partial( + overrides.array_function_dispatch, module='numpy') + + +def _empty_like_dispatcher(prototype, dtype=None, order=None, subok=None): + return (prototype,) + + +@array_function_dispatch(_empty_like_dispatcher) +def empty_like(prototype, dtype=None, order='K', subok=True): + """Return a new array with the same shape and type as a given array. + + Parameters + ---------- + prototype : array_like + The shape and data-type of `prototype` define these same attributes + of the returned array. + dtype : data-type, optional + Overrides the data type of the result. + + .. versionadded:: 1.6.0 + order : {'C', 'F', 'A', or 'K'}, optional + Overrides the memory layout of the result. 'C' means C-order, + 'F' means F-order, 'A' means 'F' if ``prototype`` is Fortran + contiguous, 'C' otherwise. 'K' means match the layout of ``prototype`` + as closely as possible. + + .. versionadded:: 1.6.0 + subok : bool, optional. + If True, then the newly created array will use the sub-class + type of 'a', otherwise it will be a base-class array. Defaults + to True. + + Returns + ------- + out : ndarray + Array of uninitialized (arbitrary) data with the same + shape and type as `prototype`. + + See Also + -------- + ones_like : Return an array of ones with shape and type of input. + zeros_like : Return an array of zeros with shape and type of input. + full_like : Return a new array with shape of input filled with value. + empty : Return a new uninitialized array. + + Notes + ----- + This function does *not* initialize the returned array; to do that use + `zeros_like` or `ones_like` instead. It may be marginally faster than + the functions that do set the array values. + + Examples + -------- + >>> a = ([1,2,3], [4,5,6]) # a is array-like + >>> np.empty_like(a) + array([[-1073741821, -1073741821, 3], #random + [ 0, 0, -1073741821]]) + >>> a = np.array([[1., 2., 3.],[4.,5.,6.]]) + >>> np.empty_like(a) + array([[ -2.00000715e+000, 1.48219694e-323, -2.00000572e+000],#random + [ 4.38791518e-305, -2.00000715e+000, 4.17269252e-309]]) + + """ + return _multiarray_umath.empty_like(prototype, dtype, order, subok) + + +def _concatenate_dispatcher(arrays, axis=None, out=None): + for array in arrays: + yield array + yield out + + +@array_function_dispatch(_concatenate_dispatcher) +def concatenate(arrays, axis=0, out=None): + """ + concatenate((a1, a2, ...), axis=0, out=None) + + Join a sequence of arrays along an existing axis. + + Parameters + ---------- + a1, a2, ... : sequence of array_like + The arrays must have the same shape, except in the dimension + corresponding to `axis` (the first, by default). + axis : int, optional + The axis along which the arrays will be joined. If axis is None, + arrays are flattened before use. Default is 0. + out : ndarray, optional + If provided, the destination to place the result. The shape must be + correct, matching that of what concatenate would have returned if no + out argument were specified. + + Returns + ------- + res : ndarray + The concatenated array. + + See Also + -------- + ma.concatenate : Concatenate function that preserves input masks. + array_split : Split an array into multiple sub-arrays of equal or + near-equal size. + split : Split array into a list of multiple sub-arrays of equal size. + hsplit : Split array into multiple sub-arrays horizontally (column wise) + vsplit : Split array into multiple sub-arrays vertically (row wise) + dsplit : Split array into multiple sub-arrays along the 3rd axis (depth). + stack : Stack a sequence of arrays along a new axis. + hstack : Stack arrays in sequence horizontally (column wise) + vstack : Stack arrays in sequence vertically (row wise) + dstack : Stack arrays in sequence depth wise (along third dimension) + block : Assemble arrays from blocks. + + Notes + ----- + When one or more of the arrays to be concatenated is a MaskedArray, + this function will return a MaskedArray object instead of an ndarray, + but the input masks are *not* preserved. In cases where a MaskedArray + is expected as input, use the ma.concatenate function from the masked + array module instead. + + Examples + -------- + >>> a = np.array([[1, 2], [3, 4]]) + >>> b = np.array([[5, 6]]) + >>> np.concatenate((a, b), axis=0) + array([[1, 2], + [3, 4], + [5, 6]]) + >>> np.concatenate((a, b.T), axis=1) + array([[1, 2, 5], + [3, 4, 6]]) + >>> np.concatenate((a, b), axis=None) + array([1, 2, 3, 4, 5, 6]) + + This function will not preserve masking of MaskedArray inputs. + + >>> a = np.ma.arange(3) + >>> a[1] = np.ma.masked + >>> b = np.arange(2, 5) + >>> a + masked_array(data=[0, --, 2], + mask=[False, True, False], + fill_value=999999) + >>> b + array([2, 3, 4]) + >>> np.concatenate([a, b]) + masked_array(data=[0, 1, 2, 2, 3, 4], + mask=False, + fill_value=999999) + >>> np.ma.concatenate([a, b]) + masked_array(data=[0, --, 2, 2, 3, 4], + mask=[False, True, False, False, False, False], + fill_value=999999) + + """ + return _multiarray_umath.concatenate(arrays, axis, out) + + +def _inner_dispatcher(a, b): + return (a, b) + + +@array_function_dispatch(_inner_dispatcher) +def inner(a, b): + """ + Inner product of two arrays. + + Ordinary inner product of vectors for 1-D arrays (without complex + conjugation), in higher dimensions a sum product over the last axes. + + Parameters + ---------- + a, b : array_like + If `a` and `b` are nonscalar, their last dimensions must match. + + Returns + ------- + out : ndarray + `out.shape = a.shape[:-1] + b.shape[:-1]` + + Raises + ------ + ValueError + If the last dimension of `a` and `b` has different size. + + See Also + -------- + tensordot : Sum products over arbitrary axes. + dot : Generalised matrix product, using second last dimension of `b`. + einsum : Einstein summation convention. + + Notes + ----- + For vectors (1-D arrays) it computes the ordinary inner-product:: + + np.inner(a, b) = sum(a[:]*b[:]) + + More generally, if `ndim(a) = r > 0` and `ndim(b) = s > 0`:: + + np.inner(a, b) = np.tensordot(a, b, axes=(-1,-1)) + + or explicitly:: + + np.inner(a, b)[i0,...,ir-1,j0,...,js-1] + = sum(a[i0,...,ir-1,:]*b[j0,...,js-1,:]) + + In addition `a` or `b` may be scalars, in which case:: + + np.inner(a,b) = a*b + + Examples + -------- + Ordinary inner product for vectors: + + >>> a = np.array([1,2,3]) + >>> b = np.array([0,1,0]) + >>> np.inner(a, b) + 2 + + A multidimensional example: + + >>> a = np.arange(24).reshape((2,3,4)) + >>> b = np.arange(4) + >>> np.inner(a, b) + array([[ 14, 38, 62], + [ 86, 110, 134]]) + + An example where `b` is a scalar: + + >>> np.inner(np.eye(2), 7) + array([[ 7., 0.], + [ 0., 7.]]) + + """ + return _multiarray_umath.inner(a, b) + + +def _where_dispatcher(condition, x=None, y=None): + return (condition, x, y) + + +@array_function_dispatch(_where_dispatcher) +def where(condition, x=np._NoValue, y=np._NoValue): + """ + where(condition, [x, y]) + + Return elements chosen from `x` or `y` depending on `condition`. + + .. note:: + When only `condition` is provided, this function is a shorthand for + ``np.asarray(condition).nonzero()``. Using `nonzero` directly should be + preferred, as it behaves correctly for subclasses. The rest of this + documentation covers only the case where all three arguments are + provided. + + Parameters + ---------- + condition : array_like, bool + Where True, yield `x`, otherwise yield `y`. + x, y : array_like + Values from which to choose. `x`, `y` and `condition` need to be + broadcastable to some shape. + + Returns + ------- + out : ndarray + An array with elements from `x` where `condition` is True, and elements + from `y` elsewhere. + + See Also + -------- + choose + nonzero : The function that is called when x and y are omitted + + Notes + ----- + If all the arrays are 1-D, `where` is equivalent to:: + + [xv if c else yv + for c, xv, yv in zip(condition, x, y)] + + Examples + -------- + >>> a = np.arange(10) + >>> a + array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9]) + >>> np.where(a < 5, a, 10*a) + array([ 0, 1, 2, 3, 4, 50, 60, 70, 80, 90]) + + This can be used on multidimensional arrays too: + + >>> np.where([[True, False], [True, True]], + ... [[1, 2], [3, 4]], + ... [[9, 8], [7, 6]]) + array([[1, 8], + [3, 4]]) + + The shapes of x, y, and the condition are broadcast together: + + >>> x, y = np.ogrid[:3, :4] + >>> np.where(x < y, x, 10 + y) # both x and 10+y are broadcast + array([[10, 0, 0, 0], + [10, 11, 1, 1], + [10, 11, 12, 2]]) + + >>> a = np.array([[0, 1, 2], + ... [0, 2, 4], + ... [0, 3, 6]]) + >>> np.where(a < 4, a, -1) # -1 is broadcast + array([[ 0, 1, 2], + [ 0, 2, -1], + [ 0, 3, -1]]) + """ + # _multiarray_umath.where only accepts positional arguments + args = tuple(a for a in (x, y) if a is not np._NoValue) + return _multiarray_umath.where(condition, *args) + + +def _lexsort_dispatcher(keys, axis=None): + if isinstance(keys, tuple): + return keys + else: + return (keys,) + + +@array_function_dispatch(_lexsort_dispatcher) +def lexsort(keys, axis=-1): + """ + Perform an indirect stable sort using a sequence of keys. + + Given multiple sorting keys, which can be interpreted as columns in a + spreadsheet, lexsort returns an array of integer indices that describes + the sort order by multiple columns. The last key in the sequence is used + for the primary sort order, the second-to-last key for the secondary sort + order, and so on. The keys argument must be a sequence of objects that + can be converted to arrays of the same shape. If a 2D array is provided + for the keys argument, it's rows are interpreted as the sorting keys and + sorting is according to the last row, second last row etc. + + Parameters + ---------- + keys : (k, N) array or tuple containing k (N,)-shaped sequences + The `k` different "columns" to be sorted. The last column (or row if + `keys` is a 2D array) is the primary sort key. + axis : int, optional + Axis to be indirectly sorted. By default, sort over the last axis. + + Returns + ------- + indices : (N,) ndarray of ints + Array of indices that sort the keys along the specified axis. + + See Also + -------- + argsort : Indirect sort. + ndarray.sort : In-place sort. + sort : Return a sorted copy of an array. + + Examples + -------- + Sort names: first by surname, then by name. + + >>> surnames = ('Hertz', 'Galilei', 'Hertz') + >>> first_names = ('Heinrich', 'Galileo', 'Gustav') + >>> ind = np.lexsort((first_names, surnames)) + >>> ind + array([1, 2, 0]) + + >>> [surnames[i] + ", " + first_names[i] for i in ind] + ['Galilei, Galileo', 'Hertz, Gustav', 'Hertz, Heinrich'] + + Sort two columns of numbers: + + >>> a = [1,5,1,4,3,4,4] # First column + >>> b = [9,4,0,4,0,2,1] # Second column + >>> ind = np.lexsort((b,a)) # Sort by a, then by b + >>> print(ind) + [2 0 4 6 5 3 1] + + >>> [(a[i],b[i]) for i in ind] + [(1, 0), (1, 9), (3, 0), (4, 1), (4, 2), (4, 4), (5, 4)] + + Note that sorting is first according to the elements of ``a``. + Secondary sorting is according to the elements of ``b``. + + A normal ``argsort`` would have yielded: + + >>> [(a[i],b[i]) for i in np.argsort(a)] + [(1, 9), (1, 0), (3, 0), (4, 4), (4, 2), (4, 1), (5, 4)] + + Structured arrays are sorted lexically by ``argsort``: + + >>> x = np.array([(1,9), (5,4), (1,0), (4,4), (3,0), (4,2), (4,1)], + ... dtype=np.dtype([('x', int), ('y', int)])) + + >>> np.argsort(x) # or np.argsort(x, order=('x', 'y')) + array([2, 0, 4, 6, 5, 3, 1]) + + """ + return _multiarray_umath.lexsort(keys, axis) + + +def _can_cast_dispatcher(from_, to, casting=None): + return (from_,) + + +@array_function_dispatch(_can_cast_dispatcher) +def can_cast(from_, to, casting='safe'): + """ + Returns True if cast between data types can occur according to the + casting rule. If from is a scalar or array scalar, also returns + True if the scalar value can be cast without overflow or truncation + to an integer. + + Parameters + ---------- + from_ : dtype, dtype specifier, scalar, or array + Data type, scalar, or array to cast from. + to : dtype or dtype specifier + Data type to cast to. + casting : {'no', 'equiv', 'safe', 'same_kind', 'unsafe'}, optional + Controls what kind of data casting may occur. + + * 'no' means the data types should not be cast at all. + * 'equiv' means only byte-order changes are allowed. + * 'safe' means only casts which can preserve values are allowed. + * 'same_kind' means only safe casts or casts within a kind, + like float64 to float32, are allowed. + * 'unsafe' means any data conversions may be done. + + Returns + ------- + out : bool + True if cast can occur according to the casting rule. + + Notes + ----- + Starting in NumPy 1.9, can_cast function now returns False in 'safe' + casting mode for integer/float dtype and string dtype if the string dtype + length is not long enough to store the max integer/float value converted + to a string. Previously can_cast in 'safe' mode returned True for + integer/float dtype and a string dtype of any length. + + See also + -------- + dtype, result_type + + Examples + -------- + Basic examples + + >>> np.can_cast(np.int32, np.int64) + True + >>> np.can_cast(np.float64, complex) + True + >>> np.can_cast(complex, float) + False + + >>> np.can_cast('i8', 'f8') + True + >>> np.can_cast('i8', 'f4') + False + >>> np.can_cast('i4', 'S4') + False + + Casting scalars + + >>> np.can_cast(100, 'i1') + True + >>> np.can_cast(150, 'i1') + False + >>> np.can_cast(150, 'u1') + True + + >>> np.can_cast(3.5e100, np.float32) + False + >>> np.can_cast(1000.0, np.float32) + True + + Array scalar checks the value, array does not + + >>> np.can_cast(np.array(1000.0), np.float32) + True + >>> np.can_cast(np.array([1000.0]), np.float32) + False + + Using the casting rules + + >>> np.can_cast('i8', 'i8', 'no') + True + >>> np.can_cast('<i8', '>i8', 'no') + False + + >>> np.can_cast('<i8', '>i8', 'equiv') + True + >>> np.can_cast('<i4', '>i8', 'equiv') + False + + >>> np.can_cast('<i4', '>i8', 'safe') + True + >>> np.can_cast('<i8', '>i4', 'safe') + False + + >>> np.can_cast('<i8', '>i4', 'same_kind') + True + >>> np.can_cast('<i8', '>u4', 'same_kind') + False + + >>> np.can_cast('<i8', '>u4', 'unsafe') + True + + """ + return _multiarray_umath.can_cast(from_, to, casting) + + +def _min_scalar_type_dispatcher(a): + return (a,) + + +@array_function_dispatch(_min_scalar_type_dispatcher) +def min_scalar_type(a): + """ + For scalar ``a``, returns the data type with the smallest size + and smallest scalar kind which can hold its value. For non-scalar + array ``a``, returns the vector's dtype unmodified. + + Floating point values are not demoted to integers, + and complex values are not demoted to floats. + + Parameters + ---------- + a : scalar or array_like + The value whose minimal data type is to be found. + + Returns + ------- + out : dtype + The minimal data type. + + Notes + ----- + .. versionadded:: 1.6.0 + + See Also + -------- + result_type, promote_types, dtype, can_cast + + Examples + -------- + >>> np.min_scalar_type(10) + dtype('uint8') + + >>> np.min_scalar_type(-260) + dtype('int16') + + >>> np.min_scalar_type(3.1) + dtype('float16') + + >>> np.min_scalar_type(1e50) + dtype('float64') + + >>> np.min_scalar_type(np.arange(4,dtype='f8')) + dtype('float64') + + """ + return _multiarray_umath.min_scalar_type(a) + + +def _result_type_dispatcher(*arrays_and_dtypes): + return arrays_and_dtypes + + +@array_function_dispatch(_result_type_dispatcher) +def result_type(*arrays_and_dtypes): + """ + Returns the type that results from applying the NumPy + type promotion rules to the arguments. + + Type promotion in NumPy works similarly to the rules in languages + like C++, with some slight differences. When both scalars and + arrays are used, the array's type takes precedence and the actual value + of the scalar is taken into account. + + For example, calculating 3*a, where a is an array of 32-bit floats, + intuitively should result in a 32-bit float output. If the 3 is a + 32-bit integer, the NumPy rules indicate it can't convert losslessly + into a 32-bit float, so a 64-bit float should be the result type. + By examining the value of the constant, '3', we see that it fits in + an 8-bit integer, which can be cast losslessly into the 32-bit float. + + Parameters + ---------- + arrays_and_dtypes : list of arrays and dtypes + The operands of some operation whose result type is needed. + + Returns + ------- + out : dtype + The result type. + + See also + -------- + dtype, promote_types, min_scalar_type, can_cast + + Notes + ----- + .. versionadded:: 1.6.0 + + The specific algorithm used is as follows. + + Categories are determined by first checking which of boolean, + integer (int/uint), or floating point (float/complex) the maximum + kind of all the arrays and the scalars are. + + If there are only scalars or the maximum category of the scalars + is higher than the maximum category of the arrays, + the data types are combined with :func:`promote_types` + to produce the return value. + + Otherwise, `min_scalar_type` is called on each array, and + the resulting data types are all combined with :func:`promote_types` + to produce the return value. + + The set of int values is not a subset of the uint values for types + with the same number of bits, something not reflected in + :func:`min_scalar_type`, but handled as a special case in `result_type`. + + Examples + -------- + >>> np.result_type(3, np.arange(7, dtype='i1')) + dtype('int8') + + >>> np.result_type('i4', 'c8') + dtype('complex128') + + >>> np.result_type(3.0, -2) + dtype('float64') + + """ + return _multiarray_umath.result_type(*arrays_and_dtypes) + + +def _dot_dispatcher(a, b, out=None): + return (a, b, out) + + +@array_function_dispatch(_dot_dispatcher) +def dot(a, b, out=None): + """ + Dot product of two arrays. Specifically, + + - If both `a` and `b` are 1-D arrays, it is inner product of vectors + (without complex conjugation). + + - If both `a` and `b` are 2-D arrays, it is matrix multiplication, + but using :func:`matmul` or ``a @ b`` is preferred. + + - If either `a` or `b` is 0-D (scalar), it is equivalent to :func:`multiply` + and using ``numpy.multiply(a, b)`` or ``a * b`` is preferred. + + - If `a` is an N-D array and `b` is a 1-D array, it is a sum product over + the last axis of `a` and `b`. + + - If `a` is an N-D array and `b` is an M-D array (where ``M>=2``), it is a + sum product over the last axis of `a` and the second-to-last axis of `b`:: + + dot(a, b)[i,j,k,m] = sum(a[i,j,:] * b[k,:,m]) + + Parameters + ---------- + a : array_like + First argument. + b : array_like + Second argument. + out : ndarray, optional + Output argument. This must have the exact kind that would be returned + if it was not used. In particular, it must have the right type, must be + C-contiguous, and its dtype must be the dtype that would be returned + for `dot(a,b)`. This is a performance feature. Therefore, if these + conditions are not met, an exception is raised, instead of attempting + to be flexible. + + Returns + ------- + output : ndarray + Returns the dot product of `a` and `b`. If `a` and `b` are both + scalars or both 1-D arrays then a scalar is returned; otherwise + an array is returned. + If `out` is given, then it is returned. + + Raises + ------ + ValueError + If the last dimension of `a` is not the same size as + the second-to-last dimension of `b`. + + See Also + -------- + vdot : Complex-conjugating dot product. + tensordot : Sum products over arbitrary axes. + einsum : Einstein summation convention. + matmul : '@' operator as method with out parameter. + + Examples + -------- + >>> np.dot(3, 4) + 12 + + Neither argument is complex-conjugated: + + >>> np.dot([2j, 3j], [2j, 3j]) + (-13+0j) + + For 2-D arrays it is the matrix product: + + >>> a = [[1, 0], [0, 1]] + >>> b = [[4, 1], [2, 2]] + >>> np.dot(a, b) + array([[4, 1], + [2, 2]]) + + >>> a = np.arange(3*4*5*6).reshape((3,4,5,6)) + >>> b = np.arange(3*4*5*6)[::-1].reshape((5,4,6,3)) + >>> np.dot(a, b)[2,3,2,1,2,2] + 499128 + >>> sum(a[2,3,2,:] * b[1,2,:,2]) + 499128 + + """ + return _multiarray_umath.dot(a, b, out) + + +def _vdot_dispatcher(a, b): + return (a, b) + + +@array_function_dispatch(_vdot_dispatcher) +def vdot(a, b): + """ + Return the dot product of two vectors. + + The vdot(`a`, `b`) function handles complex numbers differently than + dot(`a`, `b`). If the first argument is complex the complex conjugate + of the first argument is used for the calculation of the dot product. + + Note that `vdot` handles multidimensional arrays differently than `dot`: + it does *not* perform a matrix product, but flattens input arguments + to 1-D vectors first. Consequently, it should only be used for vectors. + + Parameters + ---------- + a : array_like + If `a` is complex the complex conjugate is taken before calculation + of the dot product. + b : array_like + Second argument to the dot product. + + Returns + ------- + output : ndarray + Dot product of `a` and `b`. Can be an int, float, or + complex depending on the types of `a` and `b`. + + See Also + -------- + dot : Return the dot product without using the complex conjugate of the + first argument. + + Examples + -------- + >>> a = np.array([1+2j,3+4j]) + >>> b = np.array([5+6j,7+8j]) + >>> np.vdot(a, b) + (70-8j) + >>> np.vdot(b, a) + (70+8j) + + Note that higher-dimensional arrays are flattened! + + >>> a = np.array([[1, 4], [5, 6]]) + >>> b = np.array([[4, 1], [2, 2]]) + >>> np.vdot(a, b) + 30 + >>> np.vdot(b, a) + 30 + >>> 1*4 + 4*1 + 5*2 + 6*2 + 30 + + """ + return _multiarray_umath.vdot(a, b) + + +def _is_busday_dispatcher( + dates, weekmask=None, holidays=None, busdaycal=None, out=None): + return (dates, weekmask, holidays, out) + + +@array_function_dispatch(_is_busday_dispatcher) +def is_busday(dates, weekmask=None, holidays=None, busdaycal=None, + out=None): + """ + is_busday(dates, weekmask='1111100', holidays=None, busdaycal=None, out=None) + + Calculates which of the given dates are valid days, and which are not. + + .. versionadded:: 1.7.0 + + Parameters + ---------- + dates : array_like of datetime64[D] + The array of dates to process. + weekmask : str or array_like of bool, optional + A seven-element array indicating which of Monday through Sunday are + valid days. May be specified as a length-seven list or array, like + [1,1,1,1,1,0,0]; a length-seven string, like '1111100'; or a string + like "Mon Tue Wed Thu Fri", made up of 3-character abbreviations for + weekdays, optionally separated by white space. Valid abbreviations + are: Mon Tue Wed Thu Fri Sat Sun + holidays : array_like of datetime64[D], optional + An array of dates to consider as invalid dates. They may be + specified in any order, and NaT (not-a-time) dates are ignored. + This list is saved in a normalized form that is suited for + fast calculations of valid days. + busdaycal : busdaycalendar, optional + A `busdaycalendar` object which specifies the valid days. If this + parameter is provided, neither weekmask nor holidays may be + provided. + out : array of bool, optional + If provided, this array is filled with the result. + + Returns + ------- + out : array of bool + An array with the same shape as ``dates``, containing True for + each valid day, and False for each invalid day. + + See Also + -------- + busdaycalendar: An object that specifies a custom set of valid days. + busday_offset : Applies an offset counted in valid days. + busday_count : Counts how many valid days are in a half-open date range. + + Examples + -------- + >>> # The weekdays are Friday, Saturday, and Monday + ... np.is_busday(['2011-07-01', '2011-07-02', '2011-07-18'], + ... holidays=['2011-07-01', '2011-07-04', '2011-07-17']) + array([False, False, True], dtype='bool') + """ + kwargs = {} + if weekmask is not None: + kwargs['weekmask'] = weekmask + if holidays is not None: + kwargs['holidays'] = holidays + if busdaycal is not None: + kwargs['busdaycal'] = busdaycal + if out is not None: + kwargs['out'] = out + return _multiarray_umath.is_busday(dates, **kwargs) + + +def _busday_offset_dispatcher(dates, offsets, roll=None, weekmask=None, + holidays=None, busdaycal=None, out=None): + return (dates, offsets, weekmask, holidays, out) + + +@array_function_dispatch(_busday_offset_dispatcher) +def busday_offset(dates, offsets, roll='raise', weekmask=None, + holidays=None, busdaycal=None, out=None): + """ + busday_offset(dates, offsets, roll='raise', weekmask='1111100', holidays=None, busdaycal=None, out=None) + + First adjusts the date to fall on a valid day according to + the ``roll`` rule, then applies offsets to the given dates + counted in valid days. + + .. versionadded:: 1.7.0 + + Parameters + ---------- + dates : array_like of datetime64[D] + The array of dates to process. + offsets : array_like of int + The array of offsets, which is broadcast with ``dates``. + roll : {'raise', 'nat', 'forward', 'following', 'backward', 'preceding', 'modifiedfollowing', 'modifiedpreceding'}, optional + How to treat dates that do not fall on a valid day. The default + is 'raise'. + + * 'raise' means to raise an exception for an invalid day. + * 'nat' means to return a NaT (not-a-time) for an invalid day. + * 'forward' and 'following' mean to take the first valid day + later in time. + * 'backward' and 'preceding' mean to take the first valid day + earlier in time. + * 'modifiedfollowing' means to take the first valid day + later in time unless it is across a Month boundary, in which + case to take the first valid day earlier in time. + * 'modifiedpreceding' means to take the first valid day + earlier in time unless it is across a Month boundary, in which + case to take the first valid day later in time. + weekmask : str or array_like of bool, optional + A seven-element array indicating which of Monday through Sunday are + valid days. May be specified as a length-seven list or array, like + [1,1,1,1,1,0,0]; a length-seven string, like '1111100'; or a string + like "Mon Tue Wed Thu Fri", made up of 3-character abbreviations for + weekdays, optionally separated by white space. Valid abbreviations + are: Mon Tue Wed Thu Fri Sat Sun + holidays : array_like of datetime64[D], optional + An array of dates to consider as invalid dates. They may be + specified in any order, and NaT (not-a-time) dates are ignored. + This list is saved in a normalized form that is suited for + fast calculations of valid days. + busdaycal : busdaycalendar, optional + A `busdaycalendar` object which specifies the valid days. If this + parameter is provided, neither weekmask nor holidays may be + provided. + out : array of datetime64[D], optional + If provided, this array is filled with the result. + + Returns + ------- + out : array of datetime64[D] + An array with a shape from broadcasting ``dates`` and ``offsets`` + together, containing the dates with offsets applied. + + See Also + -------- + busdaycalendar: An object that specifies a custom set of valid days. + is_busday : Returns a boolean array indicating valid days. + busday_count : Counts how many valid days are in a half-open date range. + + Examples + -------- + >>> # First business day in October 2011 (not accounting for holidays) + ... np.busday_offset('2011-10', 0, roll='forward') + numpy.datetime64('2011-10-03','D') + >>> # Last business day in February 2012 (not accounting for holidays) + ... np.busday_offset('2012-03', -1, roll='forward') + numpy.datetime64('2012-02-29','D') + >>> # Third Wednesday in January 2011 + ... np.busday_offset('2011-01', 2, roll='forward', weekmask='Wed') + numpy.datetime64('2011-01-19','D') + >>> # 2012 Mother's Day in Canada and the U.S. + ... np.busday_offset('2012-05', 1, roll='forward', weekmask='Sun') + numpy.datetime64('2012-05-13','D') + + >>> # First business day on or after a date + ... np.busday_offset('2011-03-20', 0, roll='forward') + numpy.datetime64('2011-03-21','D') + >>> np.busday_offset('2011-03-22', 0, roll='forward') + numpy.datetime64('2011-03-22','D') + >>> # First business day after a date + ... np.busday_offset('2011-03-20', 1, roll='backward') + numpy.datetime64('2011-03-21','D') + >>> np.busday_offset('2011-03-22', 1, roll='backward') + numpy.datetime64('2011-03-23','D') + """ + kwargs = {} + if weekmask is not None: + kwargs['weekmask'] = weekmask + if holidays is not None: + kwargs['holidays'] = holidays + if busdaycal is not None: + kwargs['busdaycal'] = busdaycal + if out is not None: + kwargs['out'] = out + return _multiarray_umath.busday_offset(dates, offsets, roll, **kwargs) + + +def _busday_count_dispatcher(begindates, enddates, weekmask=None, + holidays=None, busdaycal=None, out=None): + return (begindates, enddates, weekmask, holidays, out) + + +@array_function_dispatch(_busday_count_dispatcher) +def busday_count(begindates, enddates, weekmask=None, holidays=None, + busdaycal=None, out=None): + """ + busday_count(begindates, enddates, weekmask='1111100', holidays=[], busdaycal=None, out=None) + + Counts the number of valid days between `begindates` and + `enddates`, not including the day of `enddates`. + + If ``enddates`` specifies a date value that is earlier than the + corresponding ``begindates`` date value, the count will be negative. + + .. versionadded:: 1.7.0 + + Parameters + ---------- + begindates : array_like of datetime64[D] + The array of the first dates for counting. + enddates : array_like of datetime64[D] + The array of the end dates for counting, which are excluded + from the count themselves. + weekmask : str or array_like of bool, optional + A seven-element array indicating which of Monday through Sunday are + valid days. May be specified as a length-seven list or array, like + [1,1,1,1,1,0,0]; a length-seven string, like '1111100'; or a string + like "Mon Tue Wed Thu Fri", made up of 3-character abbreviations for + weekdays, optionally separated by white space. Valid abbreviations + are: Mon Tue Wed Thu Fri Sat Sun + holidays : array_like of datetime64[D], optional + An array of dates to consider as invalid dates. They may be + specified in any order, and NaT (not-a-time) dates are ignored. + This list is saved in a normalized form that is suited for + fast calculations of valid days. + busdaycal : busdaycalendar, optional + A `busdaycalendar` object which specifies the valid days. If this + parameter is provided, neither weekmask nor holidays may be + provided. + out : array of int, optional + If provided, this array is filled with the result. + + Returns + ------- + out : array of int + An array with a shape from broadcasting ``begindates`` and ``enddates`` + together, containing the number of valid days between + the begin and end dates. + + See Also + -------- + busdaycalendar: An object that specifies a custom set of valid days. + is_busday : Returns a boolean array indicating valid days. + busday_offset : Applies an offset counted in valid days. + + Examples + -------- + >>> # Number of weekdays in January 2011 + ... np.busday_count('2011-01', '2011-02') + 21 + >>> # Number of weekdays in 2011 + ... np.busday_count('2011', '2012') + 260 + >>> # Number of Saturdays in 2011 + ... np.busday_count('2011', '2012', weekmask='Sat') + 53 + """ + kwargs = {} + if weekmask is not None: + kwargs['weekmask'] = weekmask + if holidays is not None: + kwargs['holidays'] = holidays + if busdaycal is not None: + kwargs['busdaycal'] = busdaycal + if out is not None: + kwargs['out'] = out + return _multiarray_umath.busday_count(begindates, enddates, **kwargs) + + +def _datetime_as_string_dispatcher( + arr, unit=None, timezone=None, casting=None): + return (arr,) + + +@array_function_dispatch(_datetime_as_string_dispatcher) +def datetime_as_string(arr, unit=None, timezone='naive', casting='same_kind'): + """ + Convert an array of datetimes into an array of strings. + + Parameters + ---------- + arr : array_like of datetime64 + The array of UTC timestamps to format. + unit : str + One of None, 'auto', or a :ref:`datetime unit <arrays.dtypes.dateunits>`. + timezone : {'naive', 'UTC', 'local'} or tzinfo + Timezone information to use when displaying the datetime. If 'UTC', end + with a Z to indicate UTC time. If 'local', convert to the local timezone + first, and suffix with a +-#### timezone offset. If a tzinfo object, + then do as with 'local', but use the specified timezone. + casting : {'no', 'equiv', 'safe', 'same_kind', 'unsafe'} + Casting to allow when changing between datetime units. + + Returns + ------- + str_arr : ndarray + An array of strings the same shape as `arr`. + + Examples + -------- + >>> d = np.arange('2002-10-27T04:30', 4*60, 60, dtype='M8[m]') + >>> d + array(['2002-10-27T04:30', '2002-10-27T05:30', '2002-10-27T06:30', + '2002-10-27T07:30'], dtype='datetime64[m]') + + Setting the timezone to UTC shows the same information, but with a Z suffix + + >>> np.datetime_as_string(d, timezone='UTC') + array(['2002-10-27T04:30Z', '2002-10-27T05:30Z', '2002-10-27T06:30Z', + '2002-10-27T07:30Z'], dtype='<U35') + + Note that we picked datetimes that cross a DST boundary. Passing in a + ``pytz`` timezone object will print the appropriate offset + + >>> np.datetime_as_string(d, timezone=pytz.timezone('US/Eastern')) + array(['2002-10-27T00:30-0400', '2002-10-27T01:30-0400', + '2002-10-27T01:30-0500', '2002-10-27T02:30-0500'], dtype='<U39') + + Passing in a unit will change the precision + + >>> np.datetime_as_string(d, unit='h') + array(['2002-10-27T04', '2002-10-27T05', '2002-10-27T06', '2002-10-27T07'], + dtype='<U32') + >>> np.datetime_as_string(d, unit='s') + array(['2002-10-27T04:30:00', '2002-10-27T05:30:00', '2002-10-27T06:30:00', + '2002-10-27T07:30:00'], dtype='<U38') + + 'casting' can be used to specify whether precision can be changed + + >>> np.datetime_as_string(d, unit='h', casting='safe') + TypeError: Cannot create a datetime string as units 'h' from a NumPy + datetime with units 'm' according to the rule 'safe' + """ + return _multiarray_umath.datetime_as_string(arr, unit, timezone, casting) diff --git a/numpy/core/numeric.py b/numpy/core/numeric.py index 6e4e585c3..265c3636f 100644 --- a/numpy/core/numeric.py +++ b/numpy/core/numeric.py @@ -6,6 +6,7 @@ try: import collections.abc as collections_abc except ImportError: import collections as collections_abc +import functools import itertools import operator import sys @@ -27,8 +28,8 @@ from .multiarray import ( if sys.version_info[0] < 3: from .multiarray import newbuffer, getbuffer +from . import overrides from . import umath -from .overrides import array_function_dispatch from .umath import (multiply, invert, sin, UFUNC_BUFSIZE_DEFAULT, ERR_IGNORE, ERR_WARN, ERR_RAISE, ERR_CALL, ERR_PRINT, ERR_LOG, ERR_DEFAULT, PINF, NAN) @@ -55,6 +56,10 @@ else: import __builtin__ as builtins +array_function_dispatch = functools.partial( + overrides.array_function_dispatch, module='numpy') + + def loads(*args, **kwargs): # NumPy 1.15.0, 2017-12-10 warnings.warn( @@ -582,7 +587,7 @@ def asanyarray(a, dtype=None, order=None): def ascontiguousarray(a, dtype=None): """ - Return a contiguous array in memory (C order). + Return a contiguous array (ndim >= 1) in memory (C order). Parameters ---------- @@ -613,13 +618,16 @@ def ascontiguousarray(a, dtype=None): >>> x.flags['C_CONTIGUOUS'] True + Note: This function returns an array with at least one-dimension (1-d) + so it will not preserve 0-d arrays. + """ return array(a, dtype, copy=False, order='C', ndmin=1) def asfortranarray(a, dtype=None): """ - Return an array laid out in Fortran order in memory. + Return an array (ndim >= 1) laid out in Fortran order in memory. Parameters ---------- @@ -650,6 +658,9 @@ def asfortranarray(a, dtype=None): >>> y.flags['F_CONTIGUOUS'] True + Note: This function returns an array with at least one-dimension (1-d) + so it will not preserve 0-d arrays. + """ return array(a, dtype, copy=False, order='F', ndmin=1) diff --git a/numpy/core/overrides.py b/numpy/core/overrides.py index 906292613..85a8c32bb 100644 --- a/numpy/core/overrides.py +++ b/numpy/core/overrides.py @@ -5,7 +5,7 @@ TODO: rewrite this in C for performance. import collections import functools -from numpy.core.multiarray import ndarray +from numpy.core._multiarray_umath import ndarray from numpy.compat._inspect import getargspec @@ -71,8 +71,8 @@ def array_function_implementation_or_override( Function that implements the operation on NumPy array without overrides when called like ``implementation(*args, **kwargs)``. public_api : function - Function exposed by NumPy's public API riginally called like - ``public_api(*args, **kwargs`` on which arguments are now being + Function exposed by NumPy's public API originally called like + ``public_api(*args, **kwargs)`` on which arguments are now being checked. relevant_args : iterable Iterable of arguments to check for __array_function__ methods. @@ -105,9 +105,10 @@ def array_function_implementation_or_override( if result is not NotImplemented: return result - raise TypeError('no implementation found for {} on types that implement ' + func_name = '{}.{}'.format(public_api.__module__, public_api.__name__) + raise TypeError("no implementation found for '{}' on types that implement " '__array_function__: {}' - .format(public_api, list(map(type, overloaded_args)))) + .format(func_name, list(map(type, overloaded_args)))) ArgSpec = collections.namedtuple('ArgSpec', 'args varargs keywords defaults') @@ -135,7 +136,7 @@ def verify_matching_signatures(implementation, dispatcher): 'default argument values') -def array_function_dispatch(dispatcher, verify=True): +def array_function_dispatch(dispatcher, module=None, verify=True): """Decorator for adding dispatch with the __array_function__ protocol.""" def decorator(implementation): # TODO: only do this check when the appropriate flag is enabled or for @@ -149,6 +150,14 @@ def array_function_dispatch(dispatcher, verify=True): relevant_args = dispatcher(*args, **kwargs) return array_function_implementation_or_override( implementation, public_api, relevant_args, args, kwargs) + + if module is not None: + public_api.__module__ = module + + # TODO: remove this when we drop Python 2 support (functools.wraps + # adds __wrapped__ automatically in later versions) + public_api.__wrapped__ = implementation + return public_api return decorator diff --git a/numpy/core/records.py b/numpy/core/records.py index a483871ba..1b596e4de 100644 --- a/numpy/core/records.py +++ b/numpy/core/records.py @@ -42,7 +42,7 @@ import warnings from . import numeric as sb from . import numerictypes as nt -from numpy.compat import isfileobj, bytes, long, unicode +from numpy.compat import isfileobj, bytes, long, unicode, os_fspath from .arrayprint import get_printoptions # All of the functions allow formats to be a dtype @@ -737,9 +737,9 @@ def fromfile(fd, dtype=None, shape=None, offset=0, formats=None, names=None, titles=None, aligned=False, byteorder=None): """Create an array from binary file data - If file is a string then that file is opened, else it is assumed - to be a file object. The file object must support random access - (i.e. it must have tell and seek methods). + If file is a string or a path-like object then that file is opened, + else it is assumed to be a file object. The file object must + support random access (i.e. it must have tell and seek methods). >>> from tempfile import TemporaryFile >>> a = np.empty(10,dtype='f8,i4,a5') @@ -763,10 +763,14 @@ def fromfile(fd, dtype=None, shape=None, offset=0, formats=None, elif isinstance(shape, (int, long)): shape = (shape,) - name = 0 - if isinstance(fd, str): + if isfileobj(fd): + # file already opened + name = 0 + else: + # open file + fd = open(os_fspath(fd), 'rb') name = 1 - fd = open(fd, 'rb') + if (offset > 0): fd.seek(offset, 1) size = get_remaining_size(fd) diff --git a/numpy/core/setup.py b/numpy/core/setup.py index bea9ff392..a4429cee2 100644 --- a/numpy/core/setup.py +++ b/numpy/core/setup.py @@ -731,12 +731,15 @@ def configuration(parent_package='',top_path=None): join('src', 'common', 'lowlevel_strided_loops.h'), join('src', 'common', 'mem_overlap.h'), join('src', 'common', 'npy_config.h'), + join('src', 'common', 'npy_ctypes.h'), join('src', 'common', 'npy_extint128.h'), + join('src', 'common', 'npy_import.h'), join('src', 'common', 'npy_longdouble.h'), join('src', 'common', 'templ_common.h.src'), join('src', 'common', 'ucsnarrow.h'), join('src', 'common', 'ufunc_override.h'), join('src', 'common', 'umathmodule.h'), + join('src', 'common', 'numpyos.h'), ] common_src = [ @@ -746,6 +749,7 @@ def configuration(parent_package='',top_path=None): join('src', 'common', 'templ_common.h.src'), join('src', 'common', 'ucsnarrow.c'), join('src', 'common', 'ufunc_override.c'), + join('src', 'common', 'numpyos.c'), ] blas_info = get_info('blas_opt', 0) @@ -785,7 +789,6 @@ def configuration(parent_package='',top_path=None): join('src', 'multiarray', 'multiarraymodule.h'), join('src', 'multiarray', 'nditer_impl.h'), join('src', 'multiarray', 'number.h'), - join('src', 'multiarray', 'numpyos.h'), join('src', 'multiarray', 'refcount.h'), join('src', 'multiarray', 'scalartypes.h'), join('src', 'multiarray', 'sequence.h'), @@ -851,7 +854,6 @@ def configuration(parent_package='',top_path=None): join('src', 'multiarray', 'nditer_constr.c'), join('src', 'multiarray', 'nditer_pywrap.c'), join('src', 'multiarray', 'number.c'), - join('src', 'multiarray', 'numpyos.c'), join('src', 'multiarray', 'refcount.c'), join('src', 'multiarray', 'sequence.c'), join('src', 'multiarray', 'shape.c'), diff --git a/numpy/core/setup_common.py b/numpy/core/setup_common.py index e637dbc20..f837df112 100644 --- a/numpy/core/setup_common.py +++ b/numpy/core/setup_common.py @@ -41,7 +41,8 @@ C_ABI_VERSION = 0x01000009 # 0x0000000b - 1.13.x # 0x0000000c - 1.14.x # 0x0000000c - 1.15.x -C_API_VERSION = 0x0000000c +# 0x0000000d - 1.16.x +C_API_VERSION = 0x0000000d class MismatchCAPIWarning(Warning): pass diff --git a/numpy/core/shape_base.py b/numpy/core/shape_base.py index fde23076b..3edf0824e 100644 --- a/numpy/core/shape_base.py +++ b/numpy/core/shape_base.py @@ -3,11 +3,19 @@ from __future__ import division, absolute_import, print_function __all__ = ['atleast_1d', 'atleast_2d', 'atleast_3d', 'block', 'hstack', 'stack', 'vstack'] +import functools +import operator +import types +import warnings from . import numeric as _nx +from . import overrides from .numeric import array, asanyarray, newaxis from .multiarray import normalize_axis_index -from .overrides import array_function_dispatch + + +array_function_dispatch = functools.partial( + overrides.array_function_dispatch, module='numpy') def _atleast_1d_dispatcher(*arys): @@ -198,11 +206,22 @@ def atleast_3d(*arys): return res -def _vstack_dispatcher(tup): - return tup +def _arrays_for_stack_dispatcher(arrays, stacklevel=4): + if not hasattr(arrays, '__getitem__') and hasattr(arrays, '__iter__'): + warnings.warn('arrays to stack must be passed as a "sequence" type ' + 'such as list or tuple. Support for non-sequence ' + 'iterables such as generators is deprecated as of ' + 'NumPy 1.16 and will raise an error in the future.', + FutureWarning, stacklevel=stacklevel) + return () + return arrays + + +def _vhstack_dispatcher(tup): + return _arrays_for_stack_dispatcher(tup) -@array_function_dispatch(_vstack_dispatcher) +@array_function_dispatch(_vhstack_dispatcher) def vstack(tup): """ Stack arrays in sequence vertically (row wise). @@ -258,11 +277,7 @@ def vstack(tup): return _nx.concatenate([atleast_2d(_m) for _m in tup], 0) -def _hstack_dispatcher(tup): - return tup - - -@array_function_dispatch(_hstack_dispatcher) +@array_function_dispatch(_vhstack_dispatcher) def hstack(tup): """ Stack arrays in sequence horizontally (column wise). @@ -319,6 +334,7 @@ def hstack(tup): def _stack_dispatcher(arrays, axis=None, out=None): + arrays = _arrays_for_stack_dispatcher(arrays, stacklevel=6) for a in arrays: yield a if out is not None: @@ -432,6 +448,10 @@ def _block_check_depths_match(arrays, parent_index=[]): refer to it, and the last index along the empty axis will be `None`. max_arr_ndim : int The maximum of the ndims of the arrays nested in `arrays`. + final_size: int + The number of elements in the final array. This is used the motivate + the choice of algorithm used using benchmarking wisdom. + """ if type(arrays) is tuple: # not strictly necessary, but saves us from: @@ -450,8 +470,9 @@ def _block_check_depths_match(arrays, parent_index=[]): idxs_ndims = (_block_check_depths_match(arr, parent_index + [i]) for i, arr in enumerate(arrays)) - first_index, max_arr_ndim = next(idxs_ndims) - for index, ndim in idxs_ndims: + first_index, max_arr_ndim, final_size = next(idxs_ndims) + for index, ndim, size in idxs_ndims: + final_size += size if ndim > max_arr_ndim: max_arr_ndim = ndim if len(index) != len(first_index): @@ -466,13 +487,15 @@ def _block_check_depths_match(arrays, parent_index=[]): # propagate our flag that indicates an empty list at the bottom if index[-1] is None: first_index = index - return first_index, max_arr_ndim + + return first_index, max_arr_ndim, final_size elif type(arrays) is list and len(arrays) == 0: # We've 'bottomed out' on an empty list - return parent_index + [None], 0 + return parent_index + [None], 0, 0 else: # We've 'bottomed out' - arrays is either a scalar or an array - return parent_index, _nx.ndim(arrays) + size = _nx.size(arrays) + return parent_index, _nx.ndim(arrays), size def _atleast_nd(a, ndim): @@ -481,9 +504,132 @@ def _atleast_nd(a, ndim): return array(a, ndmin=ndim, copy=False, subok=True) +def _accumulate(values): + # Helper function because Python 2.7 doesn't have + # itertools.accumulate + value = 0 + accumulated = [] + for v in values: + value += v + accumulated.append(value) + return accumulated + + +def _concatenate_shapes(shapes, axis): + """Given array shapes, return the resulting shape and slices prefixes. + + These help in nested concatation. + Returns + ------- + shape: tuple of int + This tuple satisfies: + ``` + shape, _ = _concatenate_shapes([arr.shape for shape in arrs], axis) + shape == concatenate(arrs, axis).shape + ``` + + slice_prefixes: tuple of (slice(start, end), ) + For a list of arrays being concatenated, this returns the slice + in the larger array at axis that needs to be sliced into. + + For example, the following holds: + ``` + ret = concatenate([a, b, c], axis) + _, (sl_a, sl_b, sl_c) = concatenate_slices([a, b, c], axis) + + ret[(slice(None),) * axis + sl_a] == a + ret[(slice(None),) * axis + sl_b] == b + ret[(slice(None),) * axis + sl_c] == c + ``` + + Thses are called slice prefixes since they are used in the recursive + blocking algorithm to compute the left-most slices during the + recursion. Therefore, they must be prepended to rest of the slice + that was computed deeper in the recusion. + + These are returned as tuples to ensure that they can quickly be added + to existing slice tuple without creating a new tuple everytime. + + """ + # Cache a result that will be reused. + shape_at_axis = [shape[axis] for shape in shapes] + + # Take a shape, any shape + first_shape = shapes[0] + first_shape_pre = first_shape[:axis] + first_shape_post = first_shape[axis+1:] + + if any(shape[:axis] != first_shape_pre or + shape[axis+1:] != first_shape_post for shape in shapes): + raise ValueError( + 'Mismatched array shapes in block along axis {}.'.format(axis)) + + shape = (first_shape_pre + (sum(shape_at_axis),) + first_shape[axis+1:]) + + offsets_at_axis = _accumulate(shape_at_axis) + slice_prefixes = [(slice(start, end),) + for start, end in zip([0] + offsets_at_axis, + offsets_at_axis)] + return shape, slice_prefixes + + +def _block_info_recursion(arrays, max_depth, result_ndim, depth=0): + """ + Returns the shape of the final array, along with a list + of slices and a list of arrays that can be used for assignment inside the + new array + + Parameters + ---------- + arrays : nested list of arrays + The arrays to check + max_depth : list of int + The number of nested lists + result_ndim: int + The number of dimensions in thefinal array. + + Returns + ------- + shape : tuple of int + The shape that the final array will take on. + slices: list of tuple of slices + The slices into the full array required for assignment. These are + required to be prepended with ``(Ellipsis, )`` to obtain to correct + final index. + arrays: list of ndarray + The data to assign to each slice of the full array + + """ + if depth < max_depth: + shapes, slices, arrays = zip( + *[_block_info_recursion(arr, max_depth, result_ndim, depth+1) + for arr in arrays]) + + axis = result_ndim - max_depth + depth + shape, slice_prefixes = _concatenate_shapes(shapes, axis) + + # Prepend the slice prefix and flatten the slices + slices = [slice_prefix + the_slice + for slice_prefix, inner_slices in zip(slice_prefixes, slices) + for the_slice in inner_slices] + + # Flatten the array list + arrays = functools.reduce(operator.add, arrays) + + return shape, slices, arrays + else: + # We've 'bottomed out' - arrays is either a scalar or an array + # type(arrays) is not list + # Return the slice and the array inside a list to be consistent with + # the recursive case. + arr = _atleast_nd(arrays, result_ndim) + return arr.shape, [()], [arr] + + def _block(arrays, max_depth, result_ndim, depth=0): """ - Internal implementation of block. `arrays` is the argument passed to + Internal implementation of block based on repeated concatenation. + `arrays` is the argument passed to block. `max_depth` is the depth of nested lists within `arrays` and `result_ndim` is the greatest of the dimensions of the arrays in `arrays` and the depth of the lists in `arrays` (see block docstring @@ -499,7 +645,19 @@ def _block(arrays, max_depth, result_ndim, depth=0): return _atleast_nd(arrays, result_ndim) -# TODO: support array_function_dispatch +def _block_dispatcher(arrays): + # Use type(...) is list to match the behavior of np.block(), which special + # cases list specifically rather than allowing for generic iterables or + # tuple. Also, we know that list.__array_function__ will never exist. + if type(arrays) is list: + for subarrays in arrays: + for subarray in _block_dispatcher(subarrays): + yield subarray + else: + yield arrays + + +@array_function_dispatch(_block_dispatcher) def block(arrays): """ Assemble an nd-array from nested lists of blocks. @@ -648,7 +806,38 @@ def block(arrays): """ - bottom_index, arr_ndim = _block_check_depths_match(arrays) + arrays, list_ndim, result_ndim, final_size = _block_setup(arrays) + + # It was found through benchmarking that making an array of final size + # around 256x256 was faster by straight concatenation on a + # i7-7700HQ processor and dual channel ram 2400MHz. + # It didn't seem to matter heavily on the dtype used. + # + # A 2D array using repeated concatenation requires 2 copies of the array. + # + # The fastest algorithm will depend on the ratio of CPU power to memory + # speed. + # One can monitor the results of the benchmark + # https://pv.github.io/numpy-bench/#bench_shape_base.Block2D.time_block2d + # to tune this parameter until a C version of the `_block_info_recursion` + # algorithm is implemented which would likely be faster than the python + # version. + if list_ndim * final_size > (2 * 512 * 512): + return _block_slicing(arrays, list_ndim, result_ndim) + else: + return _block_concatenate(arrays, list_ndim, result_ndim) + + +# Theses helper functions are mostly used for testing. +# They allow us to write tests that directly call `_block_slicing` +# or `_block_concatenate` wtihout blocking large arrays to forse the wisdom +# to trigger the desired path. +def _block_setup(arrays): + """ + Returns + (`arrays`, list_ndim, result_ndim, final_size) + """ + bottom_index, arr_ndim, final_size = _block_check_depths_match(arrays) list_ndim = len(bottom_index) if bottom_index and bottom_index[-1] is None: raise ValueError( @@ -656,7 +845,31 @@ def block(arrays): _block_format_index(bottom_index) ) ) - result = _block(arrays, list_ndim, max(arr_ndim, list_ndim)) + result_ndim = max(arr_ndim, list_ndim) + return arrays, list_ndim, result_ndim, final_size + + +def _block_slicing(arrays, list_ndim, result_ndim): + shape, slices, arrays = _block_info_recursion( + arrays, list_ndim, result_ndim) + dtype = _nx.result_type(*[arr.dtype for arr in arrays]) + + # Test preferring F only in the case that all input arrays are F + F_order = all(arr.flags['F_CONTIGUOUS'] for arr in arrays) + C_order = all(arr.flags['C_CONTIGUOUS'] for arr in arrays) + order = 'F' if F_order and not C_order else 'C' + result = _nx.empty(shape=shape, dtype=dtype, order=order) + # Note: In a c implementation, the function + # PyArray_CreateMultiSortedStridePerm could be used for more advanced + # guessing of the desired order. + + for the_slice, arr in zip(slices, arrays): + result[(Ellipsis,) + the_slice] = arr + return result + + +def _block_concatenate(arrays, list_ndim, result_ndim): + result = _block(arrays, list_ndim, result_ndim) if list_ndim == 0: # Catch an edge case where _block returns a view because # `arrays` is a single numpy array and not a list of numpy arrays. diff --git a/numpy/core/src/common/npy_ctypes.h b/numpy/core/src/common/npy_ctypes.h new file mode 100644 index 000000000..f26db9e05 --- /dev/null +++ b/numpy/core/src/common/npy_ctypes.h @@ -0,0 +1,49 @@ +#ifndef NPY_CTYPES_H +#define NPY_CTYPES_H + +#include <Python.h> + +#include "npy_import.h" + +/* + * Check if a python type is a ctypes class. + * + * Works like the Py<type>_Check functions, returning true if the argument + * looks like a ctypes object. + * + * This entire function is just a wrapper around the Python function of the + * same name. + */ +NPY_INLINE static int +npy_ctypes_check(PyTypeObject *obj) +{ + static PyObject *py_func = NULL; + PyObject *ret_obj; + int ret; + + npy_cache_import("numpy.core._internal", "npy_ctypes_check", &py_func); + if (py_func == NULL) { + goto fail; + } + + ret_obj = PyObject_CallFunctionObjArgs(py_func, (PyObject *)obj, NULL); + if (ret_obj == NULL) { + goto fail; + } + + ret = PyObject_IsTrue(ret_obj); + if (ret == -1) { + goto fail; + } + + return ret; + +fail: + /* If the above fails, then we should just assume that the type is not from + * ctypes + */ + PyErr_Clear(); + return 0; +} + +#endif diff --git a/numpy/core/src/multiarray/numpyos.c b/numpy/core/src/common/numpyos.c index 52dcbf3c8..d60b1ca17 100644 --- a/numpy/core/src/multiarray/numpyos.c +++ b/numpy/core/src/common/numpyos.c @@ -769,3 +769,31 @@ NumPyOS_ascii_ftoLf(FILE *fp, long double *value) } return r; } + +NPY_NO_EXPORT npy_longlong +NumPyOS_strtoll(const char *str, char **endptr, int base) +{ +#if defined HAVE_STRTOLL + return strtoll(str, endptr, base); +#elif defined _MSC_VER + return _strtoi64(str, endptr, base); +#else + /* ok on 64 bit posix */ + return PyOS_strtol(str, endptr, base); +#endif +} + +NPY_NO_EXPORT npy_ulonglong +NumPyOS_strtoull(const char *str, char **endptr, int base) +{ +#if defined HAVE_STRTOULL + return strtoull(str, endptr, base); +#elif defined _MSC_VER + return _strtoui64(str, endptr, base); +#else + /* ok on 64 bit posix */ + return PyOS_strtoul(str, endptr, base); +#endif +} + + diff --git a/numpy/core/src/multiarray/numpyos.h b/numpy/core/src/common/numpyos.h index 7ca795a6f..4deed8400 100644 --- a/numpy/core/src/multiarray/numpyos.h +++ b/numpy/core/src/common/numpyos.h @@ -31,4 +31,11 @@ NumPyOS_ascii_ftoLf(FILE *fp, long double *value); NPY_NO_EXPORT int NumPyOS_ascii_isspace(int c); +/* Convert a string to an int in an arbitrary base */ +NPY_NO_EXPORT npy_longlong +NumPyOS_strtoll(const char *str, char **endptr, int base); + +/* Convert a string to an int in an arbitrary base */ +NPY_NO_EXPORT npy_ulonglong +NumPyOS_strtoull(const char *str, char **endptr, int base); #endif diff --git a/numpy/core/src/multiarray/arrayobject.c b/numpy/core/src/multiarray/arrayobject.c index 341682588..936a30426 100644 --- a/numpy/core/src/multiarray/arrayobject.c +++ b/numpy/core/src/multiarray/arrayobject.c @@ -471,7 +471,7 @@ array_dealloc(PyArrayObject *self) { PyArrayObject_fields *fa = (PyArrayObject_fields *)self; - _array_dealloc_buffer_info(self); + _dealloc_cached_buffer_info((PyObject*)self); if (fa->weakreflist != NULL) { PyObject_ClearWeakRefs((PyObject *)self); diff --git a/numpy/core/src/multiarray/arraytypes.c.src b/numpy/core/src/multiarray/arraytypes.c.src index 0e69cfc07..d3aa1bd92 100644 --- a/numpy/core/src/multiarray/arraytypes.c.src +++ b/numpy/core/src/multiarray/arraytypes.c.src @@ -2,7 +2,8 @@ #define PY_SSIZE_T_CLEAN #include "Python.h" #include "structmember.h" - +#include <limits.h> +#include <assert.h> #define NPY_NO_DEPRECATED_API NPY_API_VERSION #define _MULTIARRAYMODULE @@ -34,8 +35,7 @@ #include "cblasfuncs.h" #include "npy_cblas.h" -#include <limits.h> -#include <assert.h> +#include "buffer.h" /* check for sequences, but ignore the types numpy considers scalars */ static NPY_INLINE npy_bool @@ -150,32 +150,6 @@ MyPyLong_AsUnsigned@Type@ (PyObject *obj) /**end repeat**/ -static npy_longlong -npy_strtoll(const char *str, char **endptr, int base) -{ -#if defined HAVE_STRTOLL - return strtoll(str, endptr, base); -#elif defined _MSC_VER - return _strtoi64(str, endptr, base); -#else - /* ok on 64 bit posix */ - return PyOS_strtol(str, endptr, base); -#endif -} - -static npy_ulonglong -npy_strtoull(const char *str, char **endptr, int base) -{ -#if defined HAVE_STRTOULL - return strtoull(str, endptr, base); -#elif defined _MSC_VER - return _strtoui64(str, endptr, base); -#else - /* ok on 64 bit posix */ - return PyOS_strtoul(str, endptr, base); -#endif -} - /* ***************************************************************************** ** GETITEM AND SETITEM ** @@ -947,6 +921,7 @@ VOID_setitem(PyObject *op, void *input, void *vap) memset(ip + view.len, 0, itemsize - view.len); } PyBuffer_Release(&view); + _dealloc_cached_buffer_info(op); } #else { @@ -1796,8 +1771,8 @@ BOOL_scan(FILE *fp, npy_bool *ip, void *NPY_UNUSED(ignore), * #type = npy_byte, npy_ubyte, npy_short, npy_ushort, npy_int, npy_uint, * npy_long, npy_ulong, npy_longlong, npy_ulonglong, * npy_datetime, npy_timedelta# - * #func = (PyOS_strtol, PyOS_strtoul)*4, npy_strtoll, npy_strtoull, - * npy_strtoll*2# + * #func = (PyOS_strtol, PyOS_strtoul)*4, NumPyOS_strtoll, NumPyOS_strtoull, + * NumPyOS_strtoll*2# * #btype = (npy_long, npy_ulong)*4, npy_longlong, npy_ulonglong, * npy_longlong*2# */ diff --git a/numpy/core/src/multiarray/buffer.c b/numpy/core/src/multiarray/buffer.c index 9a2750aea..2f66d7f2f 100644 --- a/numpy/core/src/multiarray/buffer.c +++ b/numpy/core/src/multiarray/buffer.c @@ -922,7 +922,7 @@ fail: */ NPY_NO_EXPORT void -_array_dealloc_buffer_info(PyArrayObject *self) +_dealloc_cached_buffer_info(PyObject *self) { int reset_error_state = 0; PyObject *ptype, *pvalue, *ptraceback; @@ -936,7 +936,7 @@ _array_dealloc_buffer_info(PyArrayObject *self) PyErr_Fetch(&ptype, &pvalue, &ptraceback); } - _buffer_clear_info((PyObject*)self); + _buffer_clear_info(self); if (reset_error_state) { PyErr_Restore(ptype, pvalue, ptraceback); diff --git a/numpy/core/src/multiarray/buffer.h b/numpy/core/src/multiarray/buffer.h index d5da8f440..fae413c85 100644 --- a/numpy/core/src/multiarray/buffer.h +++ b/numpy/core/src/multiarray/buffer.h @@ -4,7 +4,7 @@ extern NPY_NO_EXPORT PyBufferProcs array_as_buffer; NPY_NO_EXPORT void -_array_dealloc_buffer_info(PyArrayObject *self); +_dealloc_cached_buffer_info(PyObject *self); NPY_NO_EXPORT PyArray_Descr* _descriptor_from_pep3118_format(char *s); diff --git a/numpy/core/src/multiarray/common.c b/numpy/core/src/multiarray/common.c index 5b4611e8a..65a290770 100644 --- a/numpy/core/src/multiarray/common.c +++ b/numpy/core/src/multiarray/common.c @@ -312,6 +312,7 @@ PyArray_DTypeFromObjectHelper(PyObject *obj, int maxdims, PyErr_Clear(); dtype = _descriptor_from_pep3118_format(buffer_view.format); PyBuffer_Release(&buffer_view); + _dealloc_cached_buffer_info(obj); if (dtype) { goto promote_types; } @@ -323,6 +324,7 @@ PyArray_DTypeFromObjectHelper(PyObject *obj, int maxdims, dtype = PyArray_DescrNewFromType(NPY_VOID); dtype->elsize = buffer_view.itemsize; PyBuffer_Release(&buffer_view); + _dealloc_cached_buffer_info(obj); goto promote_types; } else { @@ -636,6 +638,14 @@ _IsWriteable(PyArrayObject *ap) return NPY_FALSE; } PyBuffer_Release(&view); + /* + * The first call to PyObject_GetBuffer stores a reference to a struct + * _buffer_info_t (from buffer.c, with format, ndim, strides and shape) in + * a static dictionary, with id(base) as the key. Usually we release it + * after the call to PyBuffer_Release, via a call to + * _dealloc_cached_buffer_info, but in this case leave it in the cache to + * speed up future calls to _IsWriteable. + */ #else if (PyObject_AsWriteBuffer(base, &dummy, &n) < 0) { PyErr_Clear(); diff --git a/numpy/core/src/multiarray/conversion_utils.c b/numpy/core/src/multiarray/conversion_utils.c index 7e92e5991..cef3c27ed 100644 --- a/numpy/core/src/multiarray/conversion_utils.c +++ b/numpy/core/src/multiarray/conversion_utils.c @@ -16,6 +16,7 @@ #include "conversion_utils.h" #include "alloc.h" +#include "buffer.h" static int PyArray_PyIntAsInt_ErrMsg(PyObject *o, const char * msg) NPY_GCC_NONNULL(2); @@ -185,6 +186,7 @@ PyArray_BufferConverter(PyObject *obj, PyArray_Chunk *buf) * sticks around after the release. */ PyBuffer_Release(&view); + _dealloc_cached_buffer_info(obj); /* Point to the base of the buffer object if present */ if (PyMemoryView_Check(obj)) { diff --git a/numpy/core/src/multiarray/ctors.c b/numpy/core/src/multiarray/ctors.c index aaaaeee82..23a8dcea2 100644 --- a/numpy/core/src/multiarray/ctors.c +++ b/numpy/core/src/multiarray/ctors.c @@ -11,7 +11,7 @@ #include "npy_config.h" -#include "npy_import.h" +#include "npy_ctypes.h" #include "npy_pycompat.h" #include "multiarraymodule.h" @@ -743,12 +743,14 @@ discover_dimensions(PyObject *obj, int *maxndim, npy_intp *d, int check_it, d[i] = buffer_view.shape[i]; } PyBuffer_Release(&buffer_view); + _dealloc_cached_buffer_info(obj); return 0; } else if (PyObject_GetBuffer(obj, &buffer_view, PyBUF_SIMPLE) == 0) { d[0] = buffer_view.len; *maxndim = 1; PyBuffer_Release(&buffer_view); + _dealloc_cached_buffer_info(obj); return 0; } else { @@ -1381,15 +1383,7 @@ _array_from_buffer_3118(PyObject *memoryview) * Note that even if the above are fixed in master, we have to drop the * early patch versions of python to actually make use of the fixes. */ - - int is_ctypes = _is_from_ctypes(view->obj); - if (is_ctypes < 0) { - /* This error is not useful */ - PyErr_WriteUnraisable(view->obj); - is_ctypes = 0; - } - - if (!is_ctypes) { + if (!npy_ctypes_check(Py_TYPE(view->obj))) { /* This object has no excuse for a broken PEP3118 buffer */ PyErr_Format( PyExc_RuntimeError, @@ -2471,6 +2465,7 @@ PyArray_FromInterface(PyObject *origin) * sticks around after the release. */ PyBuffer_Release(&view); + _dealloc_cached_buffer_info(base); #else res = PyObject_AsWriteBuffer(base, (void **)&data, &buffer_len); if (res < 0) { @@ -3726,6 +3721,7 @@ PyArray_FromBuffer(PyObject *buf, PyArray_Descr *type, * sticks around after the release. */ PyBuffer_Release(&view); + _dealloc_cached_buffer_info(buf); #else if (PyObject_AsWriteBuffer(buf, (void *)&data, &ts) == -1) { writeable = 0; diff --git a/numpy/core/src/multiarray/datetime.c b/numpy/core/src/multiarray/datetime.c index 7f837901c..a8550d958 100644 --- a/numpy/core/src/multiarray/datetime.c +++ b/numpy/core/src/multiarray/datetime.c @@ -2845,6 +2845,16 @@ convert_pyobject_to_timedelta(PyArray_DatetimeMetaData *meta, PyObject *obj, *out = NPY_DATETIME_NAT; return 0; } + else if (PyArray_IsScalar(obj, Integer)) { + /* Use the default unit if none was specified */ + if (meta->base == NPY_FR_ERROR) { + meta->base = NPY_DATETIME_DEFAULTUNIT; + meta->num = 1; + } + + *out = PyLong_AsLongLong(obj); + return 0; + } else { PyErr_SetString(PyExc_ValueError, "Could not convert object to NumPy timedelta"); diff --git a/numpy/core/src/multiarray/descriptor.c b/numpy/core/src/multiarray/descriptor.c index 439980877..b9be3c09f 100644 --- a/numpy/core/src/multiarray/descriptor.c +++ b/numpy/core/src/multiarray/descriptor.c @@ -10,7 +10,7 @@ #include "numpy/arrayscalars.h" #include "npy_config.h" - +#include "npy_ctypes.h" #include "npy_pycompat.h" #include "_datetime.h" @@ -19,6 +19,7 @@ #include "descriptor.h" #include "alloc.h" #include "assert.h" +#include "buffer.h" /* * offset: A starting offset. @@ -54,79 +55,46 @@ Borrowed_PyMapping_GetItemString(PyObject *o, char *key) return ret; } -/* - * Creates a dtype object from ctypes inputs. - * - * Returns a new reference to a dtype object, or NULL - * if this is not possible. When it returns NULL, it does - * not set a Python exception. - */ static PyArray_Descr * -_arraydescr_fromctypes(PyObject *obj) +_arraydescr_from_ctypes_type(PyTypeObject *type) { - PyObject *dtypedescr; - PyArray_Descr *newdescr; - int ret; + PyObject *_numpy_dtype_ctypes; + PyObject *res; - /* Understand basic ctypes */ - dtypedescr = PyObject_GetAttrString(obj, "_type_"); - PyErr_Clear(); - if (dtypedescr) { - ret = PyArray_DescrConverter(dtypedescr, &newdescr); - Py_DECREF(dtypedescr); - if (ret == NPY_SUCCEED) { - PyObject *length; - /* Check for ctypes arrays */ - length = PyObject_GetAttrString(obj, "_length_"); - PyErr_Clear(); - if (length) { - /* derived type */ - PyObject *newtup; - PyArray_Descr *derived; - newtup = Py_BuildValue("N(N)", newdescr, length); - ret = PyArray_DescrConverter(newtup, &derived); - Py_DECREF(newtup); - if (ret == NPY_SUCCEED) { - return derived; - } - PyErr_Clear(); - return NULL; - } - return newdescr; - } - PyErr_Clear(); + /* Call the python function of the same name. */ + _numpy_dtype_ctypes = PyImport_ImportModule("numpy.core._dtype_ctypes"); + if (_numpy_dtype_ctypes == NULL) { return NULL; } - /* Understand ctypes structures -- - bit-fields are not supported - automatically aligns */ - dtypedescr = PyObject_GetAttrString(obj, "_fields_"); - PyErr_Clear(); - if (dtypedescr) { - ret = PyArray_DescrAlignConverter(dtypedescr, &newdescr); - Py_DECREF(dtypedescr); - if (ret == NPY_SUCCEED) { - return newdescr; - } - PyErr_Clear(); + res = PyObject_CallMethod(_numpy_dtype_ctypes, "dtype_from_ctypes_type", "O", (PyObject *)type); + Py_DECREF(_numpy_dtype_ctypes); + if (res == NULL) { + return NULL; } - return NULL; + /* + * sanity check that dtype_from_ctypes_type returned the right type, + * since getting it wrong would give segfaults. + */ + if (!PyObject_TypeCheck(res, &PyArrayDescr_Type)) { + Py_DECREF(res); + PyErr_BadInternalCall(); + return NULL; + } + + return (PyArray_Descr *)res; } /* - * This function creates a dtype object when: - * - The object has a "dtype" attribute, and it can be converted - * to a dtype object. - * - The object is a ctypes type object, including array - * and structure types. + * This function creates a dtype object when the object has a "dtype" attribute, + * and it can be converted to a dtype object. * * Returns a new reference to a dtype object, or NULL * if this is not possible. When it returns NULL, it does * not set a Python exception. */ NPY_NO_EXPORT PyArray_Descr * -_arraydescr_fromobj(PyObject *obj) +_arraydescr_from_dtype_attr(PyObject *obj) { PyObject *dtypedescr; PyArray_Descr *newdescr = NULL; @@ -135,15 +103,18 @@ _arraydescr_fromobj(PyObject *obj) /* For arbitrary objects that have a "dtype" attribute */ dtypedescr = PyObject_GetAttrString(obj, "dtype"); PyErr_Clear(); - if (dtypedescr != NULL) { - ret = PyArray_DescrConverter(dtypedescr, &newdescr); - Py_DECREF(dtypedescr); - if (ret == NPY_SUCCEED) { - return newdescr; - } + if (dtypedescr == NULL) { + return NULL; + } + + ret = PyArray_DescrConverter(dtypedescr, &newdescr); + Py_DECREF(dtypedescr); + if (ret != NPY_SUCCEED) { PyErr_Clear(); + return NULL; } - return _arraydescr_fromctypes(obj); + + return newdescr; } /* @@ -1423,10 +1394,20 @@ PyArray_DescrConverter(PyObject *obj, PyArray_Descr **at) check_num = NPY_VOID; } else { - *at = _arraydescr_fromobj(obj); + *at = _arraydescr_from_dtype_attr(obj); if (*at) { return NPY_SUCCEED; } + + /* + * Note: this comes after _arraydescr_from_dtype_attr because the ctypes + * type might override the dtype if numpy does not otherwise + * support it. + */ + if (npy_ctypes_check((PyTypeObject *)obj)) { + *at = _arraydescr_from_ctypes_type((PyTypeObject *)obj); + return *at ? NPY_SUCCEED : NPY_FAIL; + } } goto finish; } @@ -1596,13 +1577,23 @@ PyArray_DescrConverter(PyObject *obj, PyArray_Descr **at) goto fail; } else { - *at = _arraydescr_fromobj(obj); + *at = _arraydescr_from_dtype_attr(obj); if (*at) { return NPY_SUCCEED; } if (PyErr_Occurred()) { return NPY_FAIL; } + + /* + * Note: this comes after _arraydescr_from_dtype_attr because the ctypes + * type might override the dtype if numpy does not otherwise + * support it. + */ + if (npy_ctypes_check(Py_TYPE(obj))) { + *at = _arraydescr_from_ctypes_type(Py_TYPE(obj)); + return *at ? NPY_SUCCEED : NPY_FAIL; + } goto fail; } if (PyErr_Occurred()) { @@ -1770,6 +1761,7 @@ arraydescr_dealloc(PyArray_Descr *self) Py_INCREF(self); return; } + _dealloc_cached_buffer_info((PyObject*)self); Py_XDECREF(self->typeobj); Py_XDECREF(self->names); Py_XDECREF(self->fields); diff --git a/numpy/core/src/multiarray/descriptor.h b/numpy/core/src/multiarray/descriptor.h index 5a3e4b15f..a5f3b8cdf 100644 --- a/numpy/core/src/multiarray/descriptor.h +++ b/numpy/core/src/multiarray/descriptor.h @@ -8,7 +8,7 @@ NPY_NO_EXPORT PyObject * array_set_typeDict(PyObject *NPY_UNUSED(ignored), PyObject *args); NPY_NO_EXPORT PyArray_Descr * -_arraydescr_fromobj(PyObject *obj); +_arraydescr_from_dtype_attr(PyObject *obj); NPY_NO_EXPORT int diff --git a/numpy/core/src/multiarray/dtype_transfer.c b/numpy/core/src/multiarray/dtype_transfer.c index 97d899ce0..2b29d4f8c 100644 --- a/numpy/core/src/multiarray/dtype_transfer.c +++ b/numpy/core/src/multiarray/dtype_transfer.c @@ -51,6 +51,20 @@ #endif /**********************************************/ +#if NPY_DT_DBG_TRACING +/* + * Thin wrapper around print that ignores exceptions + */ +static void +_safe_print(PyObject *obj) +{ + if (PyObject_Print(obj, stdout, 0) < 0) { + PyErr_Clear(); + printf("<error during print>"); + } +} +#endif + /* * Returns a transfer function which DECREFs any references in src_type. * @@ -1042,9 +1056,9 @@ get_nbo_cast_datetime_transfer_function(int aligned, #if NPY_DT_DBG_TRACING printf("Dtype transfer from "); - PyObject_Print((PyObject *)src_dtype, stdout, 0); + _safe_print((PyObject *)src_dtype); printf(" to "); - PyObject_Print((PyObject *)dst_dtype, stdout, 0); + _safe_print((PyObject *)dst_dtype); printf("\n"); printf("has conversion fraction %lld/%lld\n", num, denom); #endif @@ -1089,9 +1103,9 @@ get_nbo_datetime_to_string_transfer_function(int aligned, #if NPY_DT_DBG_TRACING printf("Dtype transfer from "); - PyObject_Print((PyObject *)src_dtype, stdout, 0); + _safe_print((PyObject *)src_dtype); printf(" to "); - PyObject_Print((PyObject *)dst_dtype, stdout, 0); + _safe_print((PyObject *)dst_dtype); printf("\n"); #endif @@ -1211,9 +1225,9 @@ get_nbo_string_to_datetime_transfer_function(int aligned, #if NPY_DT_DBG_TRACING printf("Dtype transfer from "); - PyObject_Print((PyObject *)src_dtype, stdout, 0); + _safe_print((PyObject *)src_dtype); printf(" to "); - PyObject_Print((PyObject *)dst_dtype, stdout, 0); + _safe_print((PyObject *)dst_dtype); printf("\n"); #endif @@ -3421,9 +3435,13 @@ PyArray_GetDTypeTransferFunction(int aligned, #if NPY_DT_DBG_TRACING printf("Calculating dtype transfer from "); - PyObject_Print((PyObject *)src_dtype, stdout, 0); + if (PyObject_Print((PyObject *)src_dtype, stdout, 0) < 0) { + return NPY_FAIL; + } printf(" to "); - PyObject_Print((PyObject *)dst_dtype, stdout, 0); + if (PyObject_Print((PyObject *)dst_dtype, stdout, 0) < 0) { + return NPY_FAIL; + } printf("\n"); #endif diff --git a/numpy/core/src/multiarray/getset.c b/numpy/core/src/multiarray/getset.c index cae4273ff..24962da8a 100644 --- a/numpy/core/src/multiarray/getset.c +++ b/numpy/core/src/multiarray/getset.c @@ -20,6 +20,7 @@ #include "arrayobject.h" #include "mem_overlap.h" #include "alloc.h" +#include "buffer.h" /******************* array attribute get and set routines ******************/ @@ -143,6 +144,7 @@ array_strides_set(PyArrayObject *self, PyObject *obj) offset = PyArray_BYTES(self) - (char *)view.buf; numbytes = view.len + offset; PyBuffer_Release(&view); + _dealloc_cached_buffer_info((PyObject*)new); } #else if (PyArray_BASE(new) && @@ -376,6 +378,7 @@ array_data_set(PyArrayObject *self, PyObject *op) * sticks around after the release. */ PyBuffer_Release(&view); + _dealloc_cached_buffer_info(op); #else if (PyObject_AsWriteBuffer(op, &buf, &buf_len) < 0) { PyErr_Clear(); diff --git a/numpy/core/src/multiarray/item_selection.c b/numpy/core/src/multiarray/item_selection.c index de54ca1b3..a7c6b14f4 100644 --- a/numpy/core/src/multiarray/item_selection.c +++ b/numpy/core/src/multiarray/item_selection.c @@ -45,7 +45,7 @@ PyArray_TakeFrom(PyArrayObject *self0, PyObject *indices0, int axis, indices = NULL; self = (PyArrayObject *)PyArray_CheckAxis(self0, &axis, - NPY_ARRAY_CARRAY); + NPY_ARRAY_CARRAY_RO); if (self == NULL) { return NULL; } diff --git a/numpy/core/src/multiarray/iterators.c b/numpy/core/src/multiarray/iterators.c index 3e3248f53..a3bc8e742 100644 --- a/numpy/core/src/multiarray/iterators.c +++ b/numpy/core/src/multiarray/iterators.c @@ -92,114 +92,6 @@ parse_index_entry(PyObject *op, npy_intp *step_size, } -/* - * Parses an index that has no fancy indexing. Populates - * out_dimensions, out_strides, and out_offset. - */ -NPY_NO_EXPORT int -parse_index(PyArrayObject *self, PyObject *op, - npy_intp *out_dimensions, - npy_intp *out_strides, - npy_intp *out_offset, - int check_index) -{ - int i, j, n; - int nd_old, nd_new, n_add, n_ellipsis; - npy_intp n_steps, start, offset, step_size; - PyObject *op1 = NULL; - int is_slice; - - if (PySlice_Check(op) || op == Py_Ellipsis || op == Py_None) { - n = 1; - op1 = op; - Py_INCREF(op); - /* this relies on the fact that n==1 for loop below */ - is_slice = 1; - } - else { - if (!PySequence_Check(op)) { - PyErr_SetString(PyExc_IndexError, - "index must be either an int " - "or a sequence"); - return -1; - } - n = PySequence_Length(op); - is_slice = 0; - } - - nd_old = nd_new = 0; - - offset = 0; - for (i = 0; i < n; i++) { - if (!is_slice) { - op1 = PySequence_GetItem(op, i); - if (op1 == NULL) { - return -1; - } - } - start = parse_index_entry(op1, &step_size, &n_steps, - nd_old < PyArray_NDIM(self) ? - PyArray_DIMS(self)[nd_old] : 0, - nd_old, check_index ? - nd_old < PyArray_NDIM(self) : 0); - Py_DECREF(op1); - if (start == -1) { - break; - } - if (n_steps == NEWAXIS_INDEX) { - out_dimensions[nd_new] = 1; - out_strides[nd_new] = 0; - nd_new++; - } - else if (n_steps == ELLIPSIS_INDEX) { - for (j = i + 1, n_ellipsis = 0; j < n; j++) { - op1 = PySequence_GetItem(op, j); - if (op1 == Py_None) { - n_ellipsis++; - } - Py_DECREF(op1); - } - n_add = PyArray_NDIM(self)-(n-i-n_ellipsis-1+nd_old); - if (n_add < 0) { - PyErr_SetString(PyExc_IndexError, "too many indices"); - return -1; - } - for (j = 0; j < n_add; j++) { - out_dimensions[nd_new] = PyArray_DIMS(self)[nd_old]; - out_strides[nd_new] = PyArray_STRIDES(self)[nd_old]; - nd_new++; nd_old++; - } - } - else { - if (nd_old >= PyArray_NDIM(self)) { - PyErr_SetString(PyExc_IndexError, "too many indices"); - return -1; - } - offset += PyArray_STRIDES(self)[nd_old]*start; - nd_old++; - if (n_steps != SINGLE_INDEX) { - out_dimensions[nd_new] = n_steps; - out_strides[nd_new] = step_size * - PyArray_STRIDES(self)[nd_old-1]; - nd_new++; - } - } - } - if (i < n) { - return -1; - } - n_add = PyArray_NDIM(self)-nd_old; - for (j = 0; j < n_add; j++) { - out_dimensions[nd_new] = PyArray_DIMS(self)[nd_old]; - out_strides[nd_new] = PyArray_STRIDES(self)[nd_old]; - nd_new++; - nd_old++; - } - *out_offset = offset; - return nd_new; -} - - /*********************** Element-wise Array Iterator ***********************/ /* Aided by Peter J. Verveer's nd_image package and numpy's arraymap ****/ /* and Python's array iterator ***/ diff --git a/numpy/core/src/multiarray/iterators.h b/numpy/core/src/multiarray/iterators.h index 04f57c885..376dc154a 100644 --- a/numpy/core/src/multiarray/iterators.h +++ b/numpy/core/src/multiarray/iterators.h @@ -1,17 +1,6 @@ #ifndef _NPY_ARRAYITERATORS_H_ #define _NPY_ARRAYITERATORS_H_ -/* - * Parses an index that has no fancy indexing. Populates - * out_dimensions, out_strides, and out_offset. - */ -NPY_NO_EXPORT int -parse_index(PyArrayObject *self, PyObject *op, - npy_intp *out_dimensions, - npy_intp *out_strides, - npy_intp *out_offset, - int check_index); - NPY_NO_EXPORT PyObject *iter_subscript(PyArrayIterObject *, PyObject *); diff --git a/numpy/core/src/multiarray/scalarapi.c b/numpy/core/src/multiarray/scalarapi.c index 5ef6c0bbf..bc435d1ca 100644 --- a/numpy/core/src/multiarray/scalarapi.c +++ b/numpy/core/src/multiarray/scalarapi.c @@ -471,7 +471,7 @@ PyArray_DescrFromTypeObject(PyObject *type) /* Do special thing for VOID sub-types */ if (PyType_IsSubtype((PyTypeObject *)type, &PyVoidArrType_Type)) { new = PyArray_DescrNewFromType(NPY_VOID); - conv = _arraydescr_fromobj(type); + conv = _arraydescr_from_dtype_attr(type); if (conv) { new->fields = conv->fields; Py_INCREF(new->fields); diff --git a/numpy/core/src/multiarray/scalartypes.c.src b/numpy/core/src/multiarray/scalartypes.c.src index 6dd8b1a29..0f201b966 100644 --- a/numpy/core/src/multiarray/scalartypes.c.src +++ b/numpy/core/src/multiarray/scalartypes.c.src @@ -139,6 +139,7 @@ gentype_alloc(PyTypeObject *type, Py_ssize_t nitems) static void gentype_dealloc(PyObject *v) { + _dealloc_cached_buffer_info(v); Py_TYPE(v)->tp_free(v); } @@ -1858,6 +1859,7 @@ gentype_reduce(PyObject *self, PyObject *NPY_UNUSED(args)) * sticks around after the release. */ PyBuffer_Release(&view); + _dealloc_cached_buffer_info(self); } else { Py_DECREF(ret); diff --git a/numpy/core/src/multiarray/shape.c b/numpy/core/src/multiarray/shape.c index 3ac71e285..30820737e 100644 --- a/numpy/core/src/multiarray/shape.c +++ b/numpy/core/src/multiarray/shape.c @@ -89,11 +89,19 @@ PyArray_Resize(PyArrayObject *self, PyArray_Dims *newshape, int refcheck, return NULL; } + if (PyArray_BASE(self) != NULL + || (((PyArrayObject_fields *)self)->weakreflist != NULL)) { + PyErr_SetString(PyExc_ValueError, + "cannot resize an array that " + "references or is referenced\n" + "by another array in this way. Use the np.resize function."); + return NULL; + } if (refcheck) { #ifdef PYPY_VERSION PyErr_SetString(PyExc_ValueError, "cannot resize an array with refcheck=True on PyPy.\n" - "Use the resize function or refcheck=False"); + "Use the np.resize function or refcheck=False"); return NULL; #else refcnt = PyArray_REFCOUNT(self); @@ -102,13 +110,12 @@ PyArray_Resize(PyArrayObject *self, PyArray_Dims *newshape, int refcheck, else { refcnt = 1; } - if ((refcnt > 2) - || (PyArray_BASE(self) != NULL) - || (((PyArrayObject_fields *)self)->weakreflist != NULL)) { + if (refcnt > 2) { PyErr_SetString(PyExc_ValueError, "cannot resize an array that " "references or is referenced\n" - "by another array in this way. Use the resize function"); + "by another array in this way.\n" + "Use the np.resize function or refcheck=False"); return NULL; } diff --git a/numpy/core/src/umath/_umath_tests.c.src b/numpy/core/src/umath/_umath_tests.c.src index fcbdbe330..8cb74f177 100644 --- a/numpy/core/src/umath/_umath_tests.c.src +++ b/numpy/core/src/umath/_umath_tests.c.src @@ -128,6 +128,8 @@ static void /**end repeat**/ char *matrix_multiply_signature = "(m,n),(n,p)->(m,p)"; +/* for use with matrix_multiply code, but different signature */ +char *matmul_signature = "(m?,n),(n,p?)->(m?,p?)"; /**begin repeat @@ -195,6 +197,45 @@ static void /**end repeat**/ +char *cross1d_signature = "(3),(3)->(3)"; + +/**begin repeat + + #TYPE=LONG,DOUBLE# + #typ=npy_long, npy_double# +*/ + +/* + * This implements the cross product: + * out[n, 0] = in1[n, 1]*in2[n, 2] - in1[n, 2]*in2[n, 1] + * out[n, 1] = in1[n, 2]*in2[n, 0] - in1[n, 0]*in2[n, 2] + * out[n, 2] = in1[n, 0]*in2[n, 1] - in1[n, 1]*in2[n, 0] + */ +static void +@TYPE@_cross1d(char **args, npy_intp *dimensions, npy_intp *steps, void *NPY_UNUSED(func)) +{ + INIT_OUTER_LOOP_3 + npy_intp is1=steps[0], is2=steps[1], os = steps[2]; + BEGIN_OUTER_LOOP_3 + @typ@ i1_x = *(@typ@ *)(args[0] + 0*is1); + @typ@ i1_y = *(@typ@ *)(args[0] + 1*is1); + @typ@ i1_z = *(@typ@ *)(args[0] + 2*is1); + + @typ@ i2_x = *(@typ@ *)(args[1] + 0*is2); + @typ@ i2_y = *(@typ@ *)(args[1] + 1*is2); + @typ@ i2_z = *(@typ@ *)(args[1] + 2*is2); + char *op = args[2]; + + *(@typ@ *)op = i1_y * i2_z - i1_z * i2_y; + op += os; + *(@typ@ *)op = i1_z * i2_x - i1_x * i2_z; + op += os; + *(@typ@ *)op = i1_x * i2_y - i1_y * i2_x; + END_OUTER_LOOP +} + +/**end repeat**/ + char *euclidean_pdist_signature = "(n,d)->(p)"; /**begin repeat @@ -285,17 +326,39 @@ static void /**end repeat**/ +/* The following lines were generated using a slightly modified + version of code_generators/generate_umath.py and adding these + lines to defdict: + +defdict = { +'inner1d' : + Ufunc(2, 1, None_, + r'''inner on the last dimension and broadcast on the rest \n" + " \"(i),(i)->()\" \n''', + TD('ld'), + ), +'innerwt' : + Ufunc(3, 1, None_, + r'''inner1d with a weight argument \n" + " \"(i),(i),(i)->()\" \n''', + TD('ld'), + ), +} + +*/ static PyUFuncGenericFunction inner1d_functions[] = { LONG_inner1d, DOUBLE_inner1d }; -static void * inner1d_data[] = { (void *)NULL, (void *)NULL }; +static void *inner1d_data[] = { (void *)NULL, (void *)NULL }; static char inner1d_signatures[] = { NPY_LONG, NPY_LONG, NPY_LONG, NPY_DOUBLE, NPY_DOUBLE, NPY_DOUBLE }; static PyUFuncGenericFunction innerwt_functions[] = { LONG_innerwt, DOUBLE_innerwt }; -static void * innerwt_data[] = { (void *)NULL, (void *)NULL }; +static void *innerwt_data[] = { (void *)NULL, (void *)NULL }; static char innerwt_signatures[] = { NPY_LONG, NPY_LONG, NPY_LONG, NPY_LONG, NPY_DOUBLE, NPY_DOUBLE, NPY_DOUBLE, NPY_DOUBLE }; static PyUFuncGenericFunction matrix_multiply_functions[] = { LONG_matrix_multiply, FLOAT_matrix_multiply, DOUBLE_matrix_multiply }; static void *matrix_multiply_data[] = { (void *)NULL, (void *)NULL, (void *)NULL }; static char matrix_multiply_signatures[] = { NPY_LONG, NPY_LONG, NPY_LONG, NPY_FLOAT, NPY_FLOAT, NPY_FLOAT, NPY_DOUBLE, NPY_DOUBLE, NPY_DOUBLE }; - +static PyUFuncGenericFunction cross1d_functions[] = { LONG_cross1d, DOUBLE_cross1d }; +static void *cross1d_data[] = { (void *)NULL, (void *)NULL }; +static char cross1d_signatures[] = { NPY_LONG, NPY_LONG, NPY_LONG, NPY_DOUBLE, NPY_DOUBLE, NPY_DOUBLE }; static PyUFuncGenericFunction euclidean_pdist_functions[] = { FLOAT_euclidean_pdist, DOUBLE_euclidean_pdist }; static void *eucldiean_pdist_data[] = { (void *)NULL, (void *)NULL }; @@ -303,7 +366,7 @@ static char euclidean_pdist_signatures[] = { NPY_FLOAT, NPY_FLOAT, NPY_DOUBLE, NPY_DOUBLE }; static PyUFuncGenericFunction cumsum_functions[] = { LONG_cumsum, DOUBLE_cumsum }; -static void * cumsum_data[] = { (void *)NULL, (void *)NULL }; +static void *cumsum_data[] = { (void *)NULL, (void *)NULL }; static char cumsum_signatures[] = { NPY_LONG, NPY_LONG, NPY_DOUBLE, NPY_DOUBLE }; @@ -346,6 +409,17 @@ addUfuncs(PyObject *dictionary) { } PyDict_SetItemString(dictionary, "matrix_multiply", f); Py_DECREF(f); + f = PyUFunc_FromFuncAndDataAndSignature(matrix_multiply_functions, + matrix_multiply_data, matrix_multiply_signatures, + 3, 2, 1, PyUFunc_None, "matmul", + "matmul on last two dimensions, with some being optional\n" + " \"(m?,n),(n,p?)->(m?,p?)\" \n", + 0, matmul_signature); + if (f == NULL) { + return -1; + } + PyDict_SetItemString(dictionary, "matmul", f); + Py_DECREF(f); f = PyUFunc_FromFuncAndDataAndSignature(euclidean_pdist_functions, eucldiean_pdist_data, euclidean_pdist_signatures, 2, 1, 1, PyUFunc_None, "euclidean_pdist", @@ -376,6 +450,16 @@ addUfuncs(PyObject *dictionary) { } PyDict_SetItemString(dictionary, "inner1d_no_doc", f); Py_DECREF(f); + f = PyUFunc_FromFuncAndDataAndSignature(cross1d_functions, cross1d_data, + cross1d_signatures, 2, 2, 1, PyUFunc_None, "cross1d", + "cross product on the last dimension and broadcast on the rest \n"\ + " \"(3),(3)->(3)\" \n", + 0, cross1d_signature); + if (f == NULL) { + return -1; + } + PyDict_SetItemString(dictionary, "cross1d", f); + Py_DECREF(f); return 0; } @@ -385,9 +469,10 @@ static PyObject * UMath_Tests_test_signature(PyObject *NPY_UNUSED(dummy), PyObject *args) { int nin, nout, i; - PyObject *signature, *sig_str; - PyUFuncObject *f = NULL; - PyObject *core_num_dims = NULL, *core_dim_ixs = NULL; + PyObject *signature=NULL, *sig_str=NULL; + PyUFuncObject *f=NULL; + PyObject *core_num_dims=NULL, *core_dim_ixs=NULL; + PyObject *core_dim_flags=NULL, *core_dim_sizes=NULL; int core_enabled; int core_num_ixs = 0; @@ -442,7 +527,7 @@ UMath_Tests_test_signature(PyObject *NPY_UNUSED(dummy), PyObject *args) goto fail; } for (i = 0; i < core_num_ixs; i++) { - PyObject * val = PyLong_FromLong(f->core_dim_ixs[i]); + PyObject *val = PyLong_FromLong(f->core_dim_ixs[i]); PyTuple_SET_ITEM(core_dim_ixs, i, val); } } @@ -450,13 +535,44 @@ UMath_Tests_test_signature(PyObject *NPY_UNUSED(dummy), PyObject *args) Py_INCREF(Py_None); core_dim_ixs = Py_None; } + if (f->core_dim_flags != NULL) { + core_dim_flags = PyTuple_New(f->core_num_dim_ix); + if (core_dim_flags == NULL) { + goto fail; + } + for (i = 0; i < f->core_num_dim_ix; i++) { + PyObject *val = PyLong_FromLong(f->core_dim_flags[i]); + PyTuple_SET_ITEM(core_dim_flags, i, val); + } + } + else { + Py_INCREF(Py_None); + core_dim_flags = Py_None; + } + if (f->core_dim_sizes != NULL) { + core_dim_sizes = PyTuple_New(f->core_num_dim_ix); + if (core_dim_sizes == NULL) { + goto fail; + } + for (i = 0; i < f->core_num_dim_ix; i++) { + PyObject *val = PyLong_FromLong(f->core_dim_sizes[i]); + PyTuple_SET_ITEM(core_dim_sizes, i, val); + } + } + else { + Py_INCREF(Py_None); + core_dim_sizes = Py_None; + } Py_DECREF(f); - return Py_BuildValue("iOO", core_enabled, core_num_dims, core_dim_ixs); + return Py_BuildValue("iOOOO", core_enabled, core_num_dims, + core_dim_ixs, core_dim_flags, core_dim_sizes); fail: Py_XDECREF(f); Py_XDECREF(core_num_dims); Py_XDECREF(core_dim_ixs); + Py_XDECREF(core_dim_flags); + Py_XDECREF(core_dim_sizes); return NULL; } @@ -464,8 +580,8 @@ static PyMethodDef UMath_TestsMethods[] = { {"test_signature", UMath_Tests_test_signature, METH_VARARGS, "Test signature parsing of ufunc. \n" "Arguments: nin nout signature \n" - "If fails, it returns NULL. Otherwise it will returns 0 for scalar ufunc " - "and 1 for generalized ufunc. \n", + "If fails, it returns NULL. Otherwise it returns a tuple of ufunc " + "internals. \n", }, {NULL, NULL, 0, NULL} /* Sentinel */ }; @@ -504,6 +620,7 @@ PyMODINIT_FUNC init_umath_tests(void) { if (m == NULL) { return RETVAL(NULL); } + import_array(); import_ufunc(); diff --git a/numpy/core/src/umath/loops.c.src b/numpy/core/src/umath/loops.c.src index e62942efd..f96e621b8 100644 --- a/numpy/core/src/umath/loops.c.src +++ b/numpy/core/src/umath/loops.c.src @@ -1591,6 +1591,34 @@ TIMEDELTA_mm_d_divide(char **args, npy_intp *dimensions, npy_intp *steps, void * } } +NPY_NO_EXPORT void +TIMEDELTA_mm_m_remainder(char **args, npy_intp *dimensions, npy_intp *steps, void *NPY_UNUSED(func)) +{ + BINARY_LOOP { + const npy_timedelta in1 = *(npy_timedelta *)ip1; + const npy_timedelta in2 = *(npy_timedelta *)ip2; + if (in1 == NPY_DATETIME_NAT || in2 == NPY_DATETIME_NAT) { + *((npy_timedelta *)op1) = NPY_DATETIME_NAT; + } + else { + if (in2 == 0) { + npy_set_floatstatus_divbyzero(); + *((npy_timedelta *)op1) = 0; + } + else { + /* handle mixed case the way Python does */ + const npy_timedelta rem = in1 % in2; + if ((in1 > 0) == (in2 > 0) || rem == 0) { + *((npy_timedelta *)op1) = rem; + } + else { + *((npy_timedelta *)op1) = rem + in2; + } + } + } + } +} + /* ***************************************************************************** ** FLOAT LOOPS ** @@ -1833,10 +1861,7 @@ NPY_NO_EXPORT void if (!run_unary_reduce_simd_@kind@_@TYPE@(args, dimensions, steps)) { BINARY_REDUCE_LOOP(@type@) { const @type@ in2 = *(@type@ *)ip2; - io1 = (io1 @OP@ in2 || npy_isnan(io1)) ? io1 : in2; - } - if (npy_isnan(io1)) { - npy_set_floatstatus_invalid(); + io1 = (npy_isnan(io1) || io1 @OP@ in2) ? io1 : in2; } *((@type@ *)iop1) = io1; } @@ -1845,13 +1870,11 @@ NPY_NO_EXPORT void BINARY_LOOP { @type@ in1 = *(@type@ *)ip1; const @type@ in2 = *(@type@ *)ip2; - in1 = (in1 @OP@ in2 || npy_isnan(in1)) ? in1 : in2; - if (npy_isnan(in1)) { - npy_set_floatstatus_invalid(); - } + in1 = (npy_isnan(in1) || in1 @OP@ in2) ? in1 : in2; *((@type@ *)op1) = in1; } } + npy_clear_floatstatus_barrier((char*)dimensions); } /**end repeat1**/ @@ -1866,7 +1889,7 @@ NPY_NO_EXPORT void if (IS_BINARY_REDUCE) { BINARY_REDUCE_LOOP(@type@) { const @type@ in2 = *(@type@ *)ip2; - io1 = (io1 @OP@ in2 || npy_isnan(in2)) ? io1 : in2; + io1 = (npy_isnan(in2) || io1 @OP@ in2) ? io1 : in2; } *((@type@ *)iop1) = io1; } @@ -1874,7 +1897,7 @@ NPY_NO_EXPORT void BINARY_LOOP { const @type@ in1 = *(@type@ *)ip1; const @type@ in2 = *(@type@ *)ip2; - *((@type@ *)op1) = (in1 @OP@ in2 || npy_isnan(in2)) ? in1 : in2; + *((@type@ *)op1) = (npy_isnan(in2) || in1 @OP@ in2) ? in1 : in2; } } npy_clear_floatstatus_barrier((char*)dimensions); @@ -2195,14 +2218,11 @@ HALF_@kind@(char **args, npy_intp *dimensions, npy_intp *steps, void *NPY_UNUSED { /* */ BINARY_LOOP { - npy_half in1 = *(npy_half *)ip1; + const npy_half in1 = *(npy_half *)ip1; const npy_half in2 = *(npy_half *)ip2; - in1 = (@OP@(in1, in2) || npy_half_isnan(in1)) ? in1 : in2; - if (npy_half_isnan(in1)) { - npy_set_floatstatus_invalid(); - } - *((npy_half *)op1) = in1; + *((npy_half *)op1) = (@OP@(in1, in2) || npy_half_isnan(in1)) ? in1 : in2; } + /* npy_half_isnan will never set floatstatus_invalid, so do not clear */ } /**end repeat**/ @@ -2219,7 +2239,7 @@ HALF_@kind@(char **args, npy_intp *dimensions, npy_intp *steps, void *NPY_UNUSED const npy_half in2 = *(npy_half *)ip2; *((npy_half *)op1) = (@OP@(in1, in2) || npy_half_isnan(in2)) ? in1 : in2; } - npy_clear_floatstatus_barrier((char*)dimensions); + /* npy_half_isnan will never set floatstatus_invalid, so do not clear */ } /**end repeat**/ @@ -2761,16 +2781,14 @@ NPY_NO_EXPORT void @ftype@ in1i = ((@ftype@ *)ip1)[1]; const @ftype@ in2r = ((@ftype@ *)ip2)[0]; const @ftype@ in2i = ((@ftype@ *)ip2)[1]; - if ( !(@OP@(in1r, in1i, in2r, in2i) || npy_isnan(in1r) || npy_isnan(in1i))) { + if ( !(npy_isnan(in1r) || npy_isnan(in1i) || @OP@(in1r, in1i, in2r, in2i))) { in1r = in2r; in1i = in2i; } - if (npy_isnan(in1r) || npy_isnan(in1i)) { - npy_set_floatstatus_invalid(); - } ((@ftype@ *)op1)[0] = in1r; ((@ftype@ *)op1)[1] = in1i; } + npy_clear_floatstatus_barrier((char*)dimensions); } /**end repeat1**/ @@ -2786,7 +2804,7 @@ NPY_NO_EXPORT void const @ftype@ in1i = ((@ftype@ *)ip1)[1]; const @ftype@ in2r = ((@ftype@ *)ip2)[0]; const @ftype@ in2i = ((@ftype@ *)ip2)[1]; - if (@OP@(in1r, in1i, in2r, in2i) || npy_isnan(in2r) || npy_isnan(in2i)) { + if (npy_isnan(in2r) || npy_isnan(in2i) || @OP@(in1r, in1i, in2r, in2i)) { ((@ftype@ *)op1)[0] = in1r; ((@ftype@ *)op1)[1] = in1i; } @@ -2795,6 +2813,7 @@ NPY_NO_EXPORT void ((@ftype@ *)op1)[1] = in2i; } } + npy_clear_floatstatus_barrier((char*)dimensions); } /**end repeat1**/ diff --git a/numpy/core/src/umath/loops.h.src b/numpy/core/src/umath/loops.h.src index 5c2b2c22c..9b6327308 100644 --- a/numpy/core/src/umath/loops.h.src +++ b/numpy/core/src/umath/loops.h.src @@ -473,6 +473,9 @@ TIMEDELTA_md_m_divide(char **args, npy_intp *dimensions, npy_intp *steps, void * NPY_NO_EXPORT void TIMEDELTA_mm_d_divide(char **args, npy_intp *dimensions, npy_intp *steps, void *NPY_UNUSED(func)); +NPY_NO_EXPORT void +TIMEDELTA_mm_m_remainder(char **args, npy_intp *dimensions, npy_intp *steps, void *NPY_UNUSED(func)); + /* Special case equivalents to above functions */ #define TIMEDELTA_mq_m_true_divide TIMEDELTA_mq_m_divide diff --git a/numpy/core/src/umath/simd.inc.src b/numpy/core/src/umath/simd.inc.src index 47f9168e5..da0713b2b 100644 --- a/numpy/core/src/umath/simd.inc.src +++ b/numpy/core/src/umath/simd.inc.src @@ -1014,7 +1014,7 @@ sse2_@kind@_@TYPE@(@type@ * ip, @type@ * op, const npy_intp n) { const npy_intp stride = 16 / (npy_intp)sizeof(@type@); LOOP_BLOCK_ALIGN_VAR(ip, @type@, 16) { - *op = (*op @OP@ ip[i] || npy_isnan(*op)) ? *op : ip[i]; + *op = (npy_isnan(*op) || *op @OP@ ip[i]) ? *op : ip[i]; } assert(n < (stride) || npy_is_aligned(&ip[i], 16)); if (i + 3 * stride <= n) { @@ -1038,15 +1038,13 @@ sse2_@kind@_@TYPE@(@type@ * ip, @type@ * op, const npy_intp n) } else { @type@ tmp = sse2_horizontal_@VOP@_@vtype@(c1); - *op = (*op @OP@ tmp || npy_isnan(*op)) ? *op : tmp; + *op = (npy_isnan(*op) || *op @OP@ tmp) ? *op : tmp; } } LOOP_BLOCKED_END { - *op = (*op @OP@ ip[i] || npy_isnan(*op)) ? *op : ip[i]; - } - if (npy_isnan(*op)) { - npy_set_floatstatus_invalid(); + *op = (npy_isnan(*op) || *op @OP@ ip[i]) ? *op : ip[i]; } + npy_clear_floatstatus_barrier((char*)op); } /**end repeat1**/ diff --git a/numpy/core/src/umath/ufunc_object.c b/numpy/core/src/umath/ufunc_object.c index 459b0a594..8fb731fb7 100644 --- a/numpy/core/src/umath/ufunc_object.c +++ b/numpy/core/src/umath/ufunc_object.c @@ -46,6 +46,7 @@ #include "npy_import.h" #include "extobj.h" #include "common.h" +#include "numpyos.h" /********** PRINTF DEBUG TRACING **************/ #define NPY_UF_DBG_TRACING 0 @@ -480,7 +481,27 @@ _is_alnum_underscore(char ch) } /* - * Return the ending position of a variable name + * Convert a string into a number + */ +static npy_intp +_get_size(const char* str) +{ + char *stop; + npy_longlong size = NumPyOS_strtoll(str, &stop, 10); + + if (stop == str || _is_alpha_underscore(*stop)) { + /* not a well formed number */ + return -1; + } + if (size >= NPY_MAX_INTP || size <= NPY_MIN_INTP) { + /* len(str) too long */ + return -1; + } + return size; + } + +/* + * Return the ending position of a variable name including optional modifier */ static int _get_end_of_name(const char* str, int offset) @@ -489,6 +510,9 @@ _get_end_of_name(const char* str, int offset) while (_is_alnum_underscore(str[ret])) { ret++; } + if (str[ret] == '?') { + ret ++; + } return ret; } @@ -530,7 +554,6 @@ _parse_signature(PyUFuncObject *ufunc, const char *signature) "_parse_signature with NULL signature"); return -1; } - len = strlen(signature); ufunc->core_signature = PyArray_malloc(sizeof(char) * (len+1)); if (ufunc->core_signature) { @@ -546,13 +569,22 @@ _parse_signature(PyUFuncObject *ufunc, const char *signature) ufunc->core_enabled = 1; ufunc->core_num_dim_ix = 0; ufunc->core_num_dims = PyArray_malloc(sizeof(int) * ufunc->nargs); - ufunc->core_dim_ixs = PyArray_malloc(sizeof(int) * len); /* shrink this later */ ufunc->core_offsets = PyArray_malloc(sizeof(int) * ufunc->nargs); - if (ufunc->core_num_dims == NULL || ufunc->core_dim_ixs == NULL - || ufunc->core_offsets == NULL) { + /* The next three items will be shrunk later */ + ufunc->core_dim_ixs = PyArray_malloc(sizeof(int) * len); + ufunc->core_dim_sizes = PyArray_malloc(sizeof(npy_intp) * len); + ufunc->core_dim_flags = PyArray_malloc(sizeof(npy_uint32) * len); + + if (ufunc->core_num_dims == NULL || ufunc->core_dim_ixs == NULL || + ufunc->core_offsets == NULL || + ufunc->core_dim_sizes == NULL || + ufunc->core_dim_flags == NULL) { PyErr_NoMemory(); goto fail; } + for (i = 0; i < len; i++) { + ufunc->core_dim_flags[i] = 0; + } i = _next_non_white_space(signature, 0); while (signature[i] != '\0') { @@ -577,26 +609,70 @@ _parse_signature(PyUFuncObject *ufunc, const char *signature) i = _next_non_white_space(signature, i + 1); while (signature[i] != ')') { /* loop over core dimensions */ - int j = 0; - if (!_is_alpha_underscore(signature[i])) { - parse_error = "expect dimension name"; + int ix, i_end; + npy_intp frozen_size; + npy_bool can_ignore; + + if (signature[i] == '\0') { + parse_error = "unexpected end of signature string"; goto fail; } - while (j < ufunc->core_num_dim_ix) { - if (_is_same_name(signature+i, var_names[j])) { + /* + * Is this a variable or a fixed size dimension? + */ + if (_is_alpha_underscore(signature[i])) { + frozen_size = -1; + } + else { + frozen_size = (npy_intp)_get_size(signature + i); + if (frozen_size <= 0) { + parse_error = "expect dimension name or non-zero frozen size"; + goto fail; + } + } + /* Is this dimension flexible? */ + i_end = _get_end_of_name(signature, i); + can_ignore = (i_end > 0 && signature[i_end - 1] == '?'); + /* + * Determine whether we already saw this dimension name, + * get its index, and set its properties + */ + for(ix = 0; ix < ufunc->core_num_dim_ix; ix++) { + if (frozen_size > 0 ? + frozen_size == ufunc->core_dim_sizes[ix] : + _is_same_name(signature + i, var_names[ix])) { break; } - j++; } - if (j >= ufunc->core_num_dim_ix) { - var_names[j] = signature+i; + /* + * If a new dimension, store its properties; if old, check consistency. + */ + if (ix == ufunc->core_num_dim_ix) { ufunc->core_num_dim_ix++; + var_names[ix] = signature + i; + ufunc->core_dim_sizes[ix] = frozen_size; + if (frozen_size < 0) { + ufunc->core_dim_flags[ix] |= UFUNC_CORE_DIM_SIZE_INFERRED; + } + if (can_ignore) { + ufunc->core_dim_flags[ix] |= UFUNC_CORE_DIM_CAN_IGNORE; + } + } else { + if (can_ignore && !(ufunc->core_dim_flags[ix] & + UFUNC_CORE_DIM_CAN_IGNORE)) { + parse_error = "? cannot be used, name already seen without ?"; + goto fail; + } + if (!can_ignore && (ufunc->core_dim_flags[ix] & + UFUNC_CORE_DIM_CAN_IGNORE)) { + parse_error = "? must be used, name already seen with ?"; + goto fail; + } } - ufunc->core_dim_ixs[cur_core_dim] = j; + ufunc->core_dim_ixs[cur_core_dim] = ix; cur_core_dim++; nd++; - i = _get_end_of_name(signature, i); - i = _next_non_white_space(signature, i); + i = _next_non_white_space(signature, i_end); if (signature[i] != ',' && signature[i] != ')') { parse_error = "expect ',' or ')'"; goto fail; @@ -633,7 +709,14 @@ _parse_signature(PyUFuncObject *ufunc, const char *signature) goto fail; } ufunc->core_dim_ixs = PyArray_realloc(ufunc->core_dim_ixs, - sizeof(int)*cur_core_dim); + sizeof(int) * cur_core_dim); + ufunc->core_dim_sizes = PyArray_realloc( + ufunc->core_dim_sizes, + sizeof(npy_intp) * ufunc->core_num_dim_ix); + ufunc->core_dim_flags = PyArray_realloc( + ufunc->core_dim_flags, + sizeof(npy_uint32) * ufunc->core_num_dim_ix); + /* check for trivial core-signature, e.g. "(),()->()" */ if (cur_core_dim == 0) { ufunc->core_enabled = 0; @@ -664,7 +747,7 @@ _set_out_array(PyObject *obj, PyArrayObject **store) /* Translate None to NULL */ return 0; } - if PyArray_Check(obj) { + if (PyArray_Check(obj)) { /* If it's an array, store it */ if (PyArray_FailUnlessWriteable((PyArrayObject *)obj, "output array") < 0) { @@ -1935,6 +2018,72 @@ fail: } /* + * Validate that operands have enough dimensions, accounting for + * possible flexible dimensions that may be absent. + */ +static int +_validate_num_dims(PyUFuncObject *ufunc, PyArrayObject **op, + npy_uint32 *core_dim_flags, + int *op_core_num_dims) { + int i, j; + int nin = ufunc->nin; + int nop = ufunc->nargs; + + for (i = 0; i < nop; i++) { + if (op[i] != NULL) { + int op_ndim = PyArray_NDIM(op[i]); + + if (op_ndim < op_core_num_dims[i]) { + int core_offset = ufunc->core_offsets[i]; + /* We've too few, but some dimensions might be flexible */ + for (j = core_offset; + j < core_offset + ufunc->core_num_dims[i]; j++) { + int core_dim_index = ufunc->core_dim_ixs[j]; + if ((core_dim_flags[core_dim_index] & + UFUNC_CORE_DIM_CAN_IGNORE)) { + int i1, j1, k; + /* + * Found a dimension that can be ignored. Flag that + * it is missing, and unflag that it can be ignored, + * since we are doing so already. + */ + core_dim_flags[core_dim_index] |= UFUNC_CORE_DIM_MISSING; + core_dim_flags[core_dim_index] ^= UFUNC_CORE_DIM_CAN_IGNORE; + /* + * Reduce the number of core dimensions for all + * operands that use this one (including ours), + * and check whether we're now OK. + */ + for (i1 = 0, k=0; i1 < nop; i1++) { + for (j1 = 0; j1 < ufunc->core_num_dims[i1]; j1++) { + if (ufunc->core_dim_ixs[k++] == core_dim_index) { + op_core_num_dims[i1]--; + } + } + } + if (op_ndim == op_core_num_dims[i]) { + break; + } + } + } + if (op_ndim < op_core_num_dims[i]) { + PyErr_Format(PyExc_ValueError, + "%s: %s operand %d does not have enough " + "dimensions (has %d, gufunc core with " + "signature %s requires %d)", + ufunc_get_name_cstr(ufunc), + i < nin ? "Input" : "Output", + i < nin ? i : i - nin, PyArray_NDIM(op[i]), + ufunc->core_signature, op_core_num_dims[i]); + return -1; + } + } + } + } + return 0; +} + +/* * Check whether any of the outputs of a gufunc has core dimensions. */ static int @@ -2007,7 +2156,7 @@ _check_keepdims_support(PyUFuncObject *ufunc) { * Returns 0 on success, and -1 on failure */ static int -_parse_axes_arg(PyUFuncObject *ufunc, int core_num_dims[], PyObject *axes, +_parse_axes_arg(PyUFuncObject *ufunc, int op_core_num_dims[], PyObject *axes, PyArrayObject **op, int broadcast_ndim, int **remap_axis) { int nin = ufunc->nin; int nop = ufunc->nargs; @@ -2037,7 +2186,7 @@ _parse_axes_arg(PyUFuncObject *ufunc, int core_num_dims[], PyObject *axes, PyObject *op_axes_tuple, *axis_item; int axis, op_axis; - op_ncore = core_num_dims[iop]; + op_ncore = op_core_num_dims[iop]; if (op[iop] != NULL) { op_ndim = PyArray_NDIM(op[iop]); op_nbroadcast = op_ndim - op_ncore; @@ -2191,57 +2340,72 @@ _parse_axis_arg(PyUFuncObject *ufunc, int core_num_dims[], PyObject *axis, * * Returns 0 on success, and -1 on failure * - * The behavior has been changed in NumPy 1.10.0, and the following + * The behavior has been changed in NumPy 1.16.0, and the following * requirements must be fulfilled or an error will be raised: * * Arguments, both input and output, must have at least as many * dimensions as the corresponding number of core dimensions. In - * previous versions, 1's were prepended to the shape as needed. + * versions before 1.10, 1's were prepended to the shape as needed. * * Core dimensions with same labels must have exactly matching sizes. - * In previous versions, core dimensions of size 1 would broadcast + * In versions before 1.10, core dimensions of size 1 would broadcast * against other core dimensions with the same label. * * All core dimensions must have their size specified by a passed in - * input or output argument. In previous versions, core dimensions in + * input or output argument. In versions before 1.10, core dimensions in * an output argument that were not specified in an input argument, * and whose size could not be inferred from a passed in output * argument, would have their size set to 1. + * * Core dimensions may be fixed, new in NumPy 1.16 */ static int _get_coredim_sizes(PyUFuncObject *ufunc, PyArrayObject **op, - npy_intp* core_dim_sizes, int **remap_axis) { + int *op_core_num_dims, npy_uint32 *core_dim_flags, + npy_intp *core_dim_sizes, int **remap_axis) { int i; int nin = ufunc->nin; int nout = ufunc->nout; int nop = nin + nout; - for (i = 0; i < ufunc->core_num_dim_ix; ++i) { - core_dim_sizes[i] = -1; - } for (i = 0; i < nop; ++i) { if (op[i] != NULL) { int idim; int dim_offset = ufunc->core_offsets[i]; - int num_dims = ufunc->core_num_dims[i]; - int core_start_dim = PyArray_NDIM(op[i]) - num_dims; + int core_start_dim = PyArray_NDIM(op[i]) - op_core_num_dims[i]; + int dim_delta = 0; + + /* checked before this routine gets called */ + assert(core_start_dim >= 0); + /* * Make sure every core dimension exactly matches all other core - * dimensions with the same label. + * dimensions with the same label. Note that flexible dimensions + * may have been removed at this point, if so, they are marked + * with UFUNC_CORE_DIM_MISSING. */ - for (idim = 0; idim < num_dims; ++idim) { - int core_dim_index = ufunc->core_dim_ixs[dim_offset+idim]; - npy_intp op_dim_size = PyArray_DIM( - op[i], REMAP_AXIS(i, core_start_dim+idim)); - - if (core_dim_sizes[core_dim_index] == -1) { + for (idim = 0; idim < ufunc->core_num_dims[i]; ++idim) { + int core_index = dim_offset + idim; + int core_dim_index = ufunc->core_dim_ixs[core_index]; + npy_intp core_dim_size = core_dim_sizes[core_dim_index]; + npy_intp op_dim_size; + + /* can only happen if flexible; dimension missing altogether */ + if (core_dim_flags[core_dim_index] & UFUNC_CORE_DIM_MISSING) { + op_dim_size = 1; + dim_delta++; /* for indexing in dimensions */ + } + else { + op_dim_size = PyArray_DIM(op[i], + REMAP_AXIS(i, core_start_dim + idim - dim_delta)); + } + if (core_dim_sizes[core_dim_index] < 0) { core_dim_sizes[core_dim_index] = op_dim_size; } - else if (op_dim_size != core_dim_sizes[core_dim_index]) { + else if (op_dim_size != core_dim_size) { PyErr_Format(PyExc_ValueError, "%s: %s operand %d has a mismatch in its " "core dimension %d, with gufunc " "signature %s (size %zd is different " "from %zd)", ufunc_get_name_cstr(ufunc), i < nin ? "Input" : "Output", - i < nin ? i : i - nin, idim, + i < nin ? i : i - nin, idim - dim_delta, ufunc->core_signature, op_dim_size, core_dim_sizes[core_dim_index]); return -1; @@ -2253,39 +2417,29 @@ _get_coredim_sizes(PyUFuncObject *ufunc, PyArrayObject **op, /* * Make sure no core dimension is unspecified. */ - for (i = 0; i < ufunc->core_num_dim_ix; ++i) { - if (core_dim_sizes[i] == -1) { - break; - } - } - if (i != ufunc->core_num_dim_ix) { - /* - * There is at least one core dimension missing, find in which - * operand it comes up first (it has to be an output operand). - */ - const int missing_core_dim = i; - int out_op; - for (out_op = nin; out_op < nop; ++out_op) { - int first_idx = ufunc->core_offsets[out_op]; - int last_idx = first_idx + ufunc->core_num_dims[out_op]; - for (i = first_idx; i < last_idx; ++i) { - if (ufunc->core_dim_ixs[i] == missing_core_dim) { - break; - } - } - if (i < last_idx) { - /* Change index offsets for error message */ - out_op -= nin; - i -= first_idx; - break; + for (i = nin; i < nop; ++i) { + int idim; + int dim_offset = ufunc->core_offsets[i]; + + for (idim = 0; idim < ufunc->core_num_dims[i]; ++idim) { + int core_dim_index = ufunc->core_dim_ixs[dim_offset + idim]; + + /* check all cases where the size has not yet been set */ + if (core_dim_sizes[core_dim_index] < 0) { + /* + * Oops, this dimension was never specified + * (can only happen if output op not given) + */ + PyErr_Format(PyExc_ValueError, + "%s: Output operand %d has core dimension %d " + "unspecified, with gufunc signature %s", + ufunc_get_name_cstr(ufunc), i - nin, idim, + ufunc->core_signature); + return -1; } } - PyErr_Format(PyExc_ValueError, - "%s: Output operand %d has core dimension %d " - "unspecified, with gufunc signature %s", - ufunc_get_name_cstr(ufunc), out_op, i, ufunc->core_signature); - return -1; } + return 0; } @@ -2324,6 +2478,26 @@ _get_identity(PyUFuncObject *ufunc, npy_bool *reorderable) { } } +/* + * Copy over parts of the ufunc structure that may need to be + * changed during execution. Returns 0 on success; -1 otherwise. + */ +static int +_initialize_variable_parts(PyUFuncObject *ufunc, + int op_core_num_dims[], + npy_intp core_dim_sizes[], + npy_uint32 core_dim_flags[]) { + int i; + + for (i = 0; i < ufunc->nargs; i++) { + op_core_num_dims[i] = ufunc->core_num_dims[i]; + } + for (i = 0; i < ufunc->core_num_dim_ix; i++) { + core_dim_sizes[i] = ufunc->core_dim_sizes[i]; + core_dim_flags[i] = ufunc->core_dim_flags[i]; + } + return 0; +} static int PyUFunc_GeneralizedFunction(PyUFuncObject *ufunc, @@ -2340,10 +2514,10 @@ PyUFunc_GeneralizedFunction(PyUFuncObject *ufunc, /* Use remapped axes for generalized ufunc */ int broadcast_ndim, iter_ndim; - int core_num_dims_array[NPY_MAXARGS]; - int *core_num_dims; + int op_core_num_dims[NPY_MAXARGS]; int op_axes_arrays[NPY_MAXARGS][NPY_MAXDIMS]; int *op_axes[NPY_MAXARGS]; + npy_uint32 core_dim_flags[NPY_MAXARGS]; npy_uint32 op_flags[NPY_MAXARGS]; npy_intp iter_shape[NPY_MAXARGS]; @@ -2398,6 +2572,12 @@ PyUFunc_GeneralizedFunction(PyUFuncObject *ufunc, dtypes[i] = NULL; arr_prep[i] = NULL; } + /* Initialize possibly variable parts to the values from the ufunc */ + retval = _initialize_variable_parts(ufunc, op_core_num_dims, + core_dim_sizes, core_dim_flags); + if (retval < 0) { + goto fail; + } NPY_UF_DBG_PRINT("Getting arguments\n"); @@ -2429,41 +2609,28 @@ PyUFunc_GeneralizedFunction(PyUFuncObject *ufunc, } } /* - * If keepdims is set and true, signal all dimensions will be the same. + * If keepdims is set and true, which means all input dimensions are + * the same, signal that all output dimensions will be the same too. */ if (keepdims == 1) { - int num_dims = ufunc->core_num_dims[0]; - for (i = 0; i < nop; ++i) { - core_num_dims_array[i] = num_dims; + int num_dims = op_core_num_dims[0]; + for (i = nin; i < nop; ++i) { + op_core_num_dims[i] = num_dims; } - core_num_dims = core_num_dims_array; } else { /* keepdims was not set or was false; no adjustment necessary */ - core_num_dims = ufunc->core_num_dims; keepdims = 0; } /* * Check that operands have the minimum dimensions required. * (Just checks core; broadcast dimensions are tested by the iterator.) */ - for (i = 0; i < nop; i++) { - if (op[i] != NULL && PyArray_NDIM(op[i]) < core_num_dims[i]) { - PyErr_Format(PyExc_ValueError, - "%s: %s operand %d does not have enough " - "dimensions (has %d, gufunc core with " - "signature %s requires %d)", - ufunc_name, - i < nin ? "Input" : "Output", - i < nin ? i : i - nin, - PyArray_NDIM(op[i]), - ufunc->core_signature, - core_num_dims[i]); - retval = -1; - goto fail; - } + retval = _validate_num_dims(ufunc, op, core_dim_flags, + op_core_num_dims); + if (retval < 0) { + goto fail; } - /* * Figure out the number of iteration dimensions, which * is the broadcast result of all the input non-core @@ -2471,30 +2638,12 @@ PyUFunc_GeneralizedFunction(PyUFuncObject *ufunc, */ broadcast_ndim = 0; for (i = 0; i < nin; ++i) { - int n = PyArray_NDIM(op[i]) - core_num_dims[i]; + int n = PyArray_NDIM(op[i]) - op_core_num_dims[i]; if (n > broadcast_ndim) { broadcast_ndim = n; } } - /* - * Figure out the number of iterator creation dimensions, - * which is the broadcast dimensions + all the core dimensions of - * the outputs, so that the iterator can allocate those output - * dimensions following the rules of order='F', for example. - */ - iter_ndim = broadcast_ndim; - for (i = nin; i < nop; ++i) { - iter_ndim += core_num_dims[i]; - } - if (iter_ndim > NPY_MAXDIMS) { - PyErr_Format(PyExc_ValueError, - "too many dimensions for generalized ufunc %s", - ufunc_name); - retval = -1; - goto fail; - } - /* Possibly remap axes. */ if (axes != NULL || axis != NULL) { remap_axis = PyArray_malloc(sizeof(remap_axis[0]) * nop); @@ -2508,11 +2657,11 @@ PyUFunc_GeneralizedFunction(PyUFuncObject *ufunc, remap_axis[i] = remap_axis_memory + i * NPY_MAXDIMS; } if (axis) { - retval = _parse_axis_arg(ufunc, core_num_dims, axis, op, + retval = _parse_axis_arg(ufunc, op_core_num_dims, axis, op, broadcast_ndim, remap_axis); } else { - retval = _parse_axes_arg(ufunc, core_num_dims, axes, op, + retval = _parse_axes_arg(ufunc, op_core_num_dims, axes, op, broadcast_ndim, remap_axis); } if(retval < 0) { @@ -2521,10 +2670,28 @@ PyUFunc_GeneralizedFunction(PyUFuncObject *ufunc, } /* Collect the lengths of the labelled core dimensions */ - retval = _get_coredim_sizes(ufunc, op, core_dim_sizes, remap_axis); + retval = _get_coredim_sizes(ufunc, op, op_core_num_dims, core_dim_flags, + core_dim_sizes, remap_axis); if(retval < 0) { goto fail; } + /* + * Figure out the number of iterator creation dimensions, + * which is the broadcast dimensions + all the core dimensions of + * the outputs, so that the iterator can allocate those output + * dimensions following the rules of order='F', for example. + */ + iter_ndim = broadcast_ndim; + for (i = nin; i < nop; ++i) { + iter_ndim += op_core_num_dims[i]; + } + if (iter_ndim > NPY_MAXDIMS) { + PyErr_Format(PyExc_ValueError, + "too many dimensions for generalized ufunc %s", + ufunc_name); + retval = -1; + goto fail; + } /* Fill in the initial part of 'iter_shape' */ for (idim = 0; idim < broadcast_ndim; ++idim) { @@ -2537,11 +2704,7 @@ PyUFunc_GeneralizedFunction(PyUFuncObject *ufunc, int n; if (op[i]) { - /* - * Note that n may be negative if broadcasting - * extends into the core dimensions. - */ - n = PyArray_NDIM(op[i]) - core_num_dims[i]; + n = PyArray_NDIM(op[i]) - op_core_num_dims[i]; } else { n = broadcast_ndim; @@ -2565,24 +2728,49 @@ PyUFunc_GeneralizedFunction(PyUFuncObject *ufunc, /* Except for when it belongs to this output */ if (i >= nin) { int dim_offset = ufunc->core_offsets[i]; - int num_dims = core_num_dims[i]; + int num_removed = 0; /* * Fill in 'iter_shape' and 'op_axes' for the core dimensions * of this output. Here, we have to be careful: if keepdims - * was used, then this axis is not a real core dimension, - * but is being added back for broadcasting, so its size is 1. + * was used, then the axes are not real core dimensions, but + * are being added back for broadcasting, so their size is 1. + * If the axis was removed, we should skip altogether. */ - for (idim = 0; idim < num_dims; ++idim) { - iter_shape[j] = keepdims ? 1 : core_dim_sizes[ - ufunc->core_dim_ixs[dim_offset + idim]]; - op_axes_arrays[i][j] = REMAP_AXIS(i, n + idim); - ++j; + if (keepdims) { + for (idim = 0; idim < op_core_num_dims[i]; ++idim) { + iter_shape[j] = 1; + op_axes_arrays[i][j] = REMAP_AXIS(i, n + idim); + ++j; + } + } + else { + for (idim = 0; idim < ufunc->core_num_dims[i]; ++idim) { + int core_index = dim_offset + idim; + int core_dim_index = ufunc->core_dim_ixs[core_index]; + if ((core_dim_flags[core_dim_index] & + UFUNC_CORE_DIM_MISSING)) { + /* skip it */ + num_removed++; + continue; + } + iter_shape[j] = core_dim_sizes[ufunc->core_dim_ixs[core_index]]; + op_axes_arrays[i][j] = REMAP_AXIS(i, n + idim - num_removed); + ++j; + } } } op_axes[i] = op_axes_arrays[i]; } +#if NPY_UF_DBG_TRACING + printf("iter shapes:"); + for (j=0; j < iter_ndim; j++) { + printf(" %ld", iter_shape[j]); + } + printf("\n"); +#endif + /* Get the buffersize and errormask */ if (_get_bufsize_errmask(extobj, ufunc_name, &buffersize, &errormask) < 0) { retval = -1; @@ -2705,8 +2893,6 @@ PyUFunc_GeneralizedFunction(PyUFuncObject *ufunc, /* Copy the strides after the first nop */ idim = nop; for (i = 0; i < nop; ++i) { - int num_dims = ufunc->core_num_dims[i]; - int core_start_dim = PyArray_NDIM(op[i]) - num_dims; /* * Need to use the arrays in the iterator, not op, because * a copy with a different-sized type may have been made. @@ -2714,20 +2900,31 @@ PyUFunc_GeneralizedFunction(PyUFuncObject *ufunc, PyArrayObject *arr = NpyIter_GetOperandArray(iter)[i]; npy_intp *shape = PyArray_SHAPE(arr); npy_intp *strides = PyArray_STRIDES(arr); - for (j = 0; j < num_dims; ++j) { - if (core_start_dim + j >= 0) { - /* - * Force the stride to zero when the shape is 1, so - * that the broadcasting works right. - */ - int remapped_axis = REMAP_AXIS(i, core_start_dim + j); + /* + * Could be negative if flexible dims are used, but not for + * keepdims, since those dimensions are allocated in arr. + */ + int core_start_dim = PyArray_NDIM(arr) - op_core_num_dims[i]; + int num_removed = 0; + int dim_offset = ufunc->core_offsets[i]; + + for (j = 0; j < ufunc->core_num_dims[i]; ++j) { + int core_dim_index = ufunc->core_dim_ixs[dim_offset + j]; + /* + * Force zero stride when the shape is 1 (always the case for + * for missing dimensions), so that broadcasting works right. + */ + if (core_dim_flags[core_dim_index] & UFUNC_CORE_DIM_MISSING) { + num_removed++; + inner_strides[idim++] = 0; + } + else { + int remapped_axis = REMAP_AXIS(i, core_start_dim + j - num_removed); if (shape[remapped_axis] != 1) { inner_strides[idim++] = strides[remapped_axis]; } else { inner_strides[idim++] = 0; } - } else { - inner_strides[idim++] = 0; } } } @@ -4644,7 +4841,6 @@ PyUFunc_FromFuncAndDataAndSignature(PyUFuncGenericFunction *func, void **data, int unused, const char *signature) { PyUFuncObject *ufunc; - if (nin + nout > NPY_MAXARGS) { PyErr_Format(PyExc_ValueError, "Cannot construct a ufunc with more than %d operands " @@ -4657,11 +4853,9 @@ PyUFunc_FromFuncAndDataAndSignature(PyUFuncGenericFunction *func, void **data, if (ufunc == NULL) { return NULL; } + memset(ufunc, 0, sizeof(PyUFuncObject)); PyObject_Init((PyObject *)ufunc, &PyUFunc_Type); - ufunc->reserved1 = 0; - ufunc->reserved2 = NULL; - ufunc->nin = nin; ufunc->nout = nout; ufunc->nargs = nin+nout; @@ -4671,9 +4865,6 @@ PyUFunc_FromFuncAndDataAndSignature(PyUFuncGenericFunction *func, void **data, ufunc->data = data; ufunc->types = types; ufunc->ntypes = ntypes; - ufunc->ptr = NULL; - ufunc->obj = NULL; - ufunc->userloops=NULL; /* Type resolution and inner loop selection functions */ ufunc->type_resolver = &PyUFunc_DefaultTypeResolver; @@ -4694,15 +4885,6 @@ PyUFunc_FromFuncAndDataAndSignature(PyUFuncGenericFunction *func, void **data, } memset(ufunc->op_flags, 0, sizeof(npy_uint32)*ufunc->nargs); - ufunc->iter_flags = 0; - - /* generalized ufunc */ - ufunc->core_enabled = 0; - ufunc->core_num_dim_ix = 0; - ufunc->core_num_dims = NULL; - ufunc->core_dim_ixs = NULL; - ufunc->core_offsets = NULL; - ufunc->core_signature = NULL; if (signature != NULL) { if (_parse_signature(ufunc, signature) != 0) { Py_DECREF(ufunc); diff --git a/numpy/core/src/umath/ufunc_type_resolution.c b/numpy/core/src/umath/ufunc_type_resolution.c index 5ddfe29ef..6b042d837 100644 --- a/numpy/core/src/umath/ufunc_type_resolution.c +++ b/numpy/core/src/umath/ufunc_type_resolution.c @@ -1173,6 +1173,57 @@ PyUFunc_DivisionTypeResolver(PyUFuncObject *ufunc, } +NPY_NO_EXPORT int +PyUFunc_RemainderTypeResolver(PyUFuncObject *ufunc, + NPY_CASTING casting, + PyArrayObject **operands, + PyObject *type_tup, + PyArray_Descr **out_dtypes) +{ + int type_num1, type_num2; + int i; + + type_num1 = PyArray_DESCR(operands[0])->type_num; + type_num2 = PyArray_DESCR(operands[1])->type_num; + + /* Use the default when datetime and timedelta are not involved */ + if (!PyTypeNum_ISDATETIME(type_num1) && !PyTypeNum_ISDATETIME(type_num2)) { + return PyUFunc_DefaultTypeResolver(ufunc, casting, operands, + type_tup, out_dtypes); + } + if (type_num1 == NPY_TIMEDELTA) { + if (type_num2 == NPY_TIMEDELTA) { + out_dtypes[0] = PyArray_PromoteTypes(PyArray_DESCR(operands[0]), + PyArray_DESCR(operands[1])); + if (out_dtypes[0] == NULL) { + return -1; + } + out_dtypes[1] = out_dtypes[0]; + Py_INCREF(out_dtypes[1]); + out_dtypes[2] = out_dtypes[0]; + Py_INCREF(out_dtypes[2]); + } + else { + return raise_binary_type_reso_error(ufunc, operands); + } + } + else { + return raise_binary_type_reso_error(ufunc, operands); + } + + /* Check against the casting rules */ + if (PyUFunc_ValidateCasting(ufunc, casting, operands, out_dtypes) < 0) { + for (i = 0; i < 3; ++i) { + Py_DECREF(out_dtypes[i]); + out_dtypes[i] = NULL; + } + return -1; + } + + return 0; +} + + /* * True division should return float64 results when both inputs are integer * types. The PyUFunc_DefaultTypeResolver promotes 8 bit integers to float16 diff --git a/numpy/core/src/umath/ufunc_type_resolution.h b/numpy/core/src/umath/ufunc_type_resolution.h index fa9f1dbfa..bb4823d24 100644 --- a/numpy/core/src/umath/ufunc_type_resolution.h +++ b/numpy/core/src/umath/ufunc_type_resolution.h @@ -92,6 +92,13 @@ PyUFunc_DivisionTypeResolver(PyUFuncObject *ufunc, PyObject *type_tup, PyArray_Descr **out_dtypes); +NPY_NO_EXPORT int +PyUFunc_RemainderTypeResolver(PyUFuncObject *ufunc, + NPY_CASTING casting, + PyArrayObject **operands, + PyObject *type_tup, + PyArray_Descr **out_dtypes); + /* * Does a linear search for the best inner loop of the ufunc. * diff --git a/numpy/core/tests/test_datetime.py b/numpy/core/tests/test_datetime.py index fe0e425fd..b2ce0402a 100644 --- a/numpy/core/tests/test_datetime.py +++ b/numpy/core/tests/test_datetime.py @@ -7,6 +7,7 @@ import datetime import pytest from numpy.testing import ( assert_, assert_equal, assert_raises, assert_warns, suppress_warnings, + assert_raises_regex, ) from numpy.core.numeric import pickle @@ -257,6 +258,21 @@ class TestDateTime(object): arr = np.array([dt, dt]).astype('datetime64') assert_equal(arr.dtype, np.dtype('M8[us]')) + @pytest.mark.parametrize("unit", [ + # test all date / time units and use + # "generic" to select generic unit + ("Y"), ("M"), ("W"), ("D"), ("h"), ("m"), + ("s"), ("ms"), ("us"), ("ns"), ("ps"), + ("fs"), ("as"), ("generic") ]) + def test_timedelta_np_int_construction(self, unit): + # regression test for gh-7617 + if unit != "generic": + assert_equal(np.timedelta64(np.int64(123), unit), + np.timedelta64(123, unit)) + else: + assert_equal(np.timedelta64(np.int64(123)), + np.timedelta64(123)) + def test_timedelta_scalar_construction(self): # Construct with different units assert_equal(np.timedelta64(7, 'D'), @@ -1611,6 +1627,76 @@ class TestDateTime(object): assert_raises(TypeError, np.arange, np.timedelta64(0, 'Y'), np.timedelta64(5, 'D')) + @pytest.mark.parametrize("val1, val2, expected", [ + # case from gh-12092 + (np.timedelta64(7, 's'), + np.timedelta64(3, 's'), + np.timedelta64(1, 's')), + # negative value cases + (np.timedelta64(3, 's'), + np.timedelta64(-2, 's'), + np.timedelta64(-1, 's')), + (np.timedelta64(-3, 's'), + np.timedelta64(2, 's'), + np.timedelta64(1, 's')), + # larger value cases + (np.timedelta64(17, 's'), + np.timedelta64(22, 's'), + np.timedelta64(17, 's')), + (np.timedelta64(22, 's'), + np.timedelta64(17, 's'), + np.timedelta64(5, 's')), + # different units + (np.timedelta64(1, 'm'), + np.timedelta64(57, 's'), + np.timedelta64(3, 's')), + (np.timedelta64(1, 'us'), + np.timedelta64(727, 'ns'), + np.timedelta64(273, 'ns')), + # NaT is propagated + (np.timedelta64('NaT'), + np.timedelta64(50, 'ns'), + np.timedelta64('NaT')), + # Y % M works + (np.timedelta64(2, 'Y'), + np.timedelta64(22, 'M'), + np.timedelta64(2, 'M')), + ]) + def test_timedelta_modulus(self, val1, val2, expected): + assert_equal(val1 % val2, expected) + + @pytest.mark.parametrize("val1, val2", [ + # years and months sometimes can't be unambiguously + # divided for modulus operation + (np.timedelta64(7, 'Y'), + np.timedelta64(3, 's')), + (np.timedelta64(7, 'M'), + np.timedelta64(1, 'D')), + ]) + def test_timedelta_modulus_error(self, val1, val2): + with assert_raises_regex(TypeError, "common metadata divisor"): + val1 % val2 + + def test_timedelta_modulus_div_by_zero(self): + with assert_warns(RuntimeWarning): + actual = np.timedelta64(10, 's') % np.timedelta64(0, 's') + assert_equal(actual, np.timedelta64(0, 's')) + + @pytest.mark.parametrize("val1, val2", [ + # cases where one operand is not + # timedelta64 + (np.timedelta64(7, 'Y'), + 15,), + (7.5, + np.timedelta64(1, 'D')), + ]) + def test_timedelta_modulus_type_resolution(self, val1, val2): + # NOTE: some of the operations may be supported + # in the future + with assert_raises_regex(TypeError, + "remainder cannot use operands with types"): + val1 % val2 + def test_timedelta_arange_no_dtype(self): d = np.array(5, dtype="m8[D]") assert_equal(np.arange(d, d + 1), d) diff --git a/numpy/core/tests/test_dtype.py b/numpy/core/tests/test_dtype.py index 1bce86a5a..ecb51f72d 100644 --- a/numpy/core/tests/test_dtype.py +++ b/numpy/core/tests/test_dtype.py @@ -620,6 +620,25 @@ class TestString(object): # Pull request #4722 np.array(["", ""]).astype(object) + def test_void_subclass_unsized(self): + dt = np.dtype(np.record) + assert_equal(repr(dt), "dtype('V')") + assert_equal(str(dt), '|V0') + assert_equal(dt.name, 'record') + + def test_void_subclass_sized(self): + dt = np.dtype((np.record, 2)) + assert_equal(repr(dt), "dtype('V2')") + assert_equal(str(dt), '|V2') + assert_equal(dt.name, 'record16') + + def test_void_subclass_fields(self): + dt = np.dtype((np.record, [('a', '<u2')])) + assert_equal(repr(dt), "dtype((numpy.record, [('a', '<u2')]))") + assert_equal(str(dt), "(numpy.record, [('a', '<u2')])") + assert_equal(dt.name, 'record16') + + class TestDtypeAttributeDeletion(object): def test_dtype_non_writable_attributes_deletion(self): @@ -775,6 +794,36 @@ class TestFromCTypes(object): ], align=True) self.check(PaddedStruct, expected) + def test_bit_fields(self): + class BitfieldStruct(ctypes.Structure): + _fields_ = [ + ('a', ctypes.c_uint8, 7), + ('b', ctypes.c_uint8, 1) + ] + assert_raises(TypeError, np.dtype, BitfieldStruct) + assert_raises(TypeError, np.dtype, BitfieldStruct()) + + def test_pointer(self): + p_uint8 = ctypes.POINTER(ctypes.c_uint8) + assert_raises(TypeError, np.dtype, p_uint8) + + @pytest.mark.xfail( + reason="Unions are not implemented", + raises=NotImplementedError) + def test_union(self): + class Union(ctypes.Union): + _fields_ = [ + ('a', ctypes.c_uint8), + ('b', ctypes.c_uint16), + ] + expected = np.dtype(dict( + names=['a', 'b'], + formats=[np.uint8, np.uint16], + offsets=[0, 0], + itemsize=2 + )) + self.check(Union, expected) + @pytest.mark.xfail(reason="_pack_ is ignored - see gh-11651") def test_packed_structure(self): class PackedStructure(ctypes.Structure): diff --git a/numpy/core/tests/test_getlimits.py b/numpy/core/tests/test_getlimits.py index ca8093c62..2f6648183 100644 --- a/numpy/core/tests/test_getlimits.py +++ b/numpy/core/tests/test_getlimits.py @@ -7,10 +7,7 @@ import numpy as np from numpy.core import finfo, iinfo from numpy import half, single, double, longdouble from numpy.testing import assert_equal, assert_, assert_raises -from numpy.core.getlimits import ( - _discovered_machar, _float16_ma, _float32_ma, _float64_ma, _float128_ma, - _float80_ma - ) +from numpy.core.getlimits import _discovered_machar, _float_ma ################################################## @@ -101,9 +98,9 @@ def assert_ma_equal(discovered, ma_like): def test_known_types(): # Test we are correctly compiling parameters for known types - for ftype, ma_like in ((np.float16, _float16_ma), - (np.float32, _float32_ma), - (np.float64, _float64_ma)): + for ftype, ma_like in ((np.float16, _float_ma[16]), + (np.float32, _float_ma[32]), + (np.float64, _float_ma[64])): assert_ma_equal(_discovered_machar(ftype), ma_like) # Suppress warning for broken discovery of double double on PPC with np.errstate(all='ignore'): @@ -111,10 +108,10 @@ def test_known_types(): bytes = np.dtype(np.longdouble).itemsize if (ld_ma.it, ld_ma.maxexp) == (63, 16384) and bytes in (12, 16): # 80-bit extended precision - assert_ma_equal(ld_ma, _float80_ma) + assert_ma_equal(ld_ma, _float_ma[80]) elif (ld_ma.it, ld_ma.maxexp) == (112, 16384) and bytes == 16: # IEE 754 128-bit - assert_ma_equal(ld_ma, _float128_ma) + assert_ma_equal(ld_ma, _float_ma[128]) def test_plausible_finfo(): diff --git a/numpy/core/tests/test_half.py b/numpy/core/tests/test_half.py index d715569f8..2f2d069e5 100644 --- a/numpy/core/tests/test_half.py +++ b/numpy/core/tests/test_half.py @@ -301,21 +301,19 @@ class TestHalf(object): assert_equal(np.copysign(b, a), [2, 5, 1, 4, 3]) assert_equal(np.maximum(a, b), [0, 5, 2, 4, 3]) - with suppress_warnings() as sup: - sup.record(RuntimeWarning) - x = np.maximum(b, c) - assert_(np.isnan(x[3])) - assert_equal(len(sup.log), 1) + + x = np.maximum(b, c) + assert_(np.isnan(x[3])) x[3] = 0 assert_equal(x, [0, 5, 1, 0, 6]) + assert_equal(np.minimum(a, b), [-2, 1, 1, 4, 2]) - with suppress_warnings() as sup: - sup.record(RuntimeWarning) - x = np.minimum(b, c) - assert_(np.isnan(x[3])) - assert_equal(len(sup.log), 1) + + x = np.minimum(b, c) + assert_(np.isnan(x[3])) x[3] = 0 assert_equal(x, [-2, -1, -np.inf, 0, 3]) + assert_equal(np.fmax(a, b), [0, 5, 2, 4, 3]) assert_equal(np.fmax(b, c), [0, 5, 1, 4, 6]) assert_equal(np.fmin(a, b), [-2, 1, 1, 4, 2]) diff --git a/numpy/core/tests/test_multiarray.py b/numpy/core/tests/test_multiarray.py index 8cd0f4d92..4b2a38990 100644 --- a/numpy/core/tests/test_multiarray.py +++ b/numpy/core/tests/test_multiarray.py @@ -4829,6 +4829,12 @@ class TestResize(object): x_view.resize((0, 10)) x_view.resize((0, 100)) + def test_check_weakref(self): + x = np.array([[1, 0, 0], [0, 1, 0], [0, 0, 1]]) + xref = weakref.ref(x) + assert_raises(ValueError, x.resize, (5, 1)) + del xref # avoid pyflakes unused variable warning. + class TestRecord(object): def test_field_rename(self): diff --git a/numpy/core/tests/test_overrides.py b/numpy/core/tests/test_overrides.py index 3f87a6afe..ee6d5da4a 100644 --- a/numpy/core/tests/test_overrides.py +++ b/numpy/core/tests/test_overrides.py @@ -16,8 +16,8 @@ def _get_overloaded_args(relevant_args): return args -def _return_self(self, *args, **kwargs): - return self +def _return_not_implemented(self, *args, **kwargs): + return NotImplemented class TestGetOverloadedTypesAndArgs(object): @@ -45,7 +45,7 @@ class TestGetOverloadedTypesAndArgs(object): def test_ndarray_subclasses(self): class OverrideSub(np.ndarray): - __array_function__ = _return_self + __array_function__ = _return_not_implemented class NoOverrideSub(np.ndarray): pass @@ -70,7 +70,7 @@ class TestGetOverloadedTypesAndArgs(object): def test_ndarray_and_duck_array(self): class Other(object): - __array_function__ = _return_self + __array_function__ = _return_not_implemented array = np.array(1) other = Other() @@ -86,10 +86,10 @@ class TestGetOverloadedTypesAndArgs(object): def test_ndarray_subclass_and_duck_array(self): class OverrideSub(np.ndarray): - __array_function__ = _return_self + __array_function__ = _return_not_implemented class Other(object): - __array_function__ = _return_self + __array_function__ = _return_not_implemented array = np.array(1) subarray = np.array(1).view(OverrideSub) @@ -103,16 +103,16 @@ class TestGetOverloadedTypesAndArgs(object): def test_many_duck_arrays(self): class A(object): - __array_function__ = _return_self + __array_function__ = _return_not_implemented class B(A): - __array_function__ = _return_self + __array_function__ = _return_not_implemented class C(A): - __array_function__ = _return_self + __array_function__ = _return_not_implemented class D(object): - __array_function__ = _return_self + __array_function__ = _return_not_implemented a = A() b = B() @@ -135,7 +135,7 @@ class TestNDArrayArrayFunction(object): def test_method(self): class SubOverride(np.ndarray): - __array_function__ = _return_self + __array_function__ = _return_not_implemented class NoOverrideSub(np.ndarray): pass @@ -189,7 +189,8 @@ class TestArrayFunctionDispatch(object): assert_(obj is original) assert_(func is dispatched_one_arg) assert_equal(set(types), {MyArray}) - assert_equal(args, (original,)) + # assert_equal uses the overloaded np.iscomplexobj() internally + assert_(args == (original,)) assert_equal(kwargs, {}) def test_not_implemented(self): @@ -295,12 +296,46 @@ class TestArrayFunctionImplementation(object): def test_not_implemented(self): MyArray, implements = _new_duck_type_and_implements() - @array_function_dispatch(lambda array: (array,)) + @array_function_dispatch(lambda array: (array,), module='my') def func(array): return array array = np.array(1) assert_(func(array) is array) - with assert_raises_regex(TypeError, 'no implementation found'): + with assert_raises_regex( + TypeError, "no implementation found for 'my.func'"): func(MyArray()) + + +class TestNDArrayMethods(object): + + def test_repr(self): + # gh-12162: should still be defined even if __array_function__ doesn't + # implement np.array_repr() + + class MyArray(np.ndarray): + def __array_function__(*args, **kwargs): + return NotImplemented + + array = np.array(1).view(MyArray) + assert_equal(repr(array), 'MyArray(1)') + assert_equal(str(array), '1') + + +class TestNumPyFunctions(object): + + def test_module(self): + assert_equal(np.sum.__module__, 'numpy') + assert_equal(np.char.equal.__module__, 'numpy.char') + assert_equal(np.fft.fft.__module__, 'numpy.fft') + assert_equal(np.linalg.solve.__module__, 'numpy.linalg') + + def test_override_sum(self): + MyArray, implements = _new_duck_type_and_implements() + + @implements(np.sum) + def _(array): + return 'yes' + + assert_equal(np.sum(MyArray()), 'yes') diff --git a/numpy/core/tests/test_records.py b/numpy/core/tests/test_records.py index a77eef404..af6c86b9e 100644 --- a/numpy/core/tests/test_records.py +++ b/numpy/core/tests/test_records.py @@ -13,9 +13,10 @@ from os import path import pytest import numpy as np +from numpy.compat import Path from numpy.testing import ( assert_, assert_equal, assert_array_equal, assert_array_almost_equal, - assert_raises, assert_warns + assert_raises, assert_warns, temppath ) from numpy.core.numeric import pickle @@ -325,6 +326,24 @@ class TestFromrecords(object): assert_equal(rec['f1'], [b'', b'', b'']) +@pytest.mark.skipif(Path is None, reason="No pathlib.Path") +class TestPathUsage(object): + # Test that pathlib.Path can be used + def test_tofile_fromfile(self): + with temppath(suffix='.bin') as path: + path = Path(path) + a = np.empty(10, dtype='f8,i4,a5') + a[5] = (0.5,10,'abcde') + a.newbyteorder('<') + with path.open("wb") as fd: + a.tofile(fd) + x = np.core.records.fromfile(path, + formats='f8,i4,a5', + shape=10, + byteorder='<') + assert_array_equal(x, a) + + class TestRecord(object): def setup(self): self.data = np.rec.fromrecords([(1, 2, 3), (4, 5, 6)], diff --git a/numpy/core/tests/test_regression.py b/numpy/core/tests/test_regression.py index d53f6da84..a929b0efd 100644 --- a/numpy/core/tests/test_regression.py +++ b/numpy/core/tests/test_regression.py @@ -1557,10 +1557,7 @@ class TestRegression(object): def test_complex_nan_maximum(self): cnan = complex(0, np.nan) - with suppress_warnings() as sup: - sup.record(RuntimeWarning) - assert_equal(np.maximum(1, cnan), cnan) - assert_equal(len(sup.log), 1) + assert_equal(np.maximum(1, cnan), cnan) def test_subclass_int_tuple_assignment(self): # ticket #1563 diff --git a/numpy/core/tests/test_shape_base.py b/numpy/core/tests/test_shape_base.py index df819b73f..b2c610da6 100644 --- a/numpy/core/tests/test_shape_base.py +++ b/numpy/core/tests/test_shape_base.py @@ -1,14 +1,17 @@ from __future__ import division, absolute_import, print_function import warnings +import sys import numpy as np from numpy.core import ( array, arange, atleast_1d, atleast_2d, atleast_3d, block, vstack, hstack, newaxis, concatenate, stack ) +from numpy.core.shape_base import (_block_dispatcher, _block_setup, + _block_concatenate, _block_slicing) from numpy.testing import ( assert_, assert_raises, assert_array_equal, assert_equal, - assert_raises_regex, assert_almost_equal + assert_raises_regex, assert_warns, assert_almost_equal ) from numpy.compat import long @@ -153,6 +156,14 @@ class TestHstack(object): desired = array([[1, 1], [2, 2]]) assert_array_equal(res, desired) + def test_generator(self): + with assert_warns(FutureWarning): + hstack((np.arange(3) for _ in range(2))) + if sys.version_info.major > 2: + # map returns a list on Python 2 + with assert_warns(FutureWarning): + hstack(map(lambda x: x, np.ones((3, 2)))) + class TestVstack(object): def test_non_iterable(self): @@ -189,6 +200,10 @@ class TestVstack(object): desired = array([[1, 2], [1, 2]]) assert_array_equal(res, desired) + def test_generator(self): + with assert_warns(FutureWarning): + vstack((np.arange(3) for _ in range(2))) + class TestConcatenate(object): def test_returns_copy(self): @@ -352,7 +367,7 @@ def test_stack(): arrays = [np.random.randn(3, 4) for _ in range(10)] axes = [0, 1, 2, -1, -2, -3] expected_shapes = [(10, 3, 4), (3, 10, 4), (3, 4, 10), - (3, 4, 10), (3, 10, 4), (10, 3, 4)] + (3, 4, 10), (3, 10, 4), (10, 3, 4)] for axis, expected_shape in zip(axes, expected_shapes): assert_equal(np.stack(arrays, axis).shape, expected_shape) # empty arrays @@ -370,16 +385,69 @@ def test_stack(): stack, [np.zeros((3, 3)), np.zeros(3)], axis=1) assert_raises_regex(ValueError, 'must have the same shape', stack, [np.arange(2), np.arange(3)]) + # generator is deprecated + with assert_warns(FutureWarning): + result = stack((x for x in range(3))) + assert_array_equal(result, np.array([0, 1, 2])) + + +# See for more information on how to parametrize a whole class +# https://docs.pytest.org/en/latest/example/parametrize.html#parametrizing-test-methods-through-per-class-configuration +def pytest_generate_tests(metafunc): + # called once per each test function + if hasattr(metafunc.cls, 'params'): + arglist = metafunc.cls.params + argnames = sorted(arglist[0]) + metafunc.parametrize(argnames, + [[funcargs[name] for name in argnames] + for funcargs in arglist]) + + +# blocking small arrays and large arrays go through different paths. +# the algorithm is triggered depending on the number of element +# copies required. +# We define a test fixture that forces most tests to go through +# both code paths. +# Ultimately, this should be removed if a single algorithm is found +# to be faster for both small and large arrays.s +def _block_force_concatenate(arrays): + arrays, list_ndim, result_ndim, _ = _block_setup(arrays) + return _block_concatenate(arrays, list_ndim, result_ndim) + + +def _block_force_slicing(arrays): + arrays, list_ndim, result_ndim, _ = _block_setup(arrays) + return _block_slicing(arrays, list_ndim, result_ndim) class TestBlock(object): - def test_returns_copy(self): + params = [dict(block=block), + dict(block=_block_force_concatenate), + dict(block=_block_force_slicing)] + + def test_returns_copy(self, block): a = np.eye(3) - b = np.block(a) + b = block(a) b[0, 0] = 2 assert b[0, 0] != a[0, 0] - def test_block_simple_row_wise(self): + def test_block_total_size_estimate(self, block): + _, _, _, total_size = _block_setup([1]) + assert total_size == 1 + + _, _, _, total_size = _block_setup([[1]]) + assert total_size == 1 + + _, _, _, total_size = _block_setup([[1, 1]]) + assert total_size == 2 + + _, _, _, total_size = _block_setup([[1], [1]]) + assert total_size == 2 + + _, _, _, total_size = _block_setup([[1, 2], [3, 4]]) + assert total_size == 4 + + def test_block_simple_row_wise(self, block): a_2d = np.ones((2, 2)) b_2d = 2 * a_2d desired = np.array([[1, 1, 2, 2], @@ -387,7 +455,7 @@ class TestBlock(object): result = block([a_2d, b_2d]) assert_equal(desired, result) - def test_block_simple_column_wise(self): + def test_block_simple_column_wise(self, block): a_2d = np.ones((2, 2)) b_2d = 2 * a_2d expected = np.array([[1, 1], @@ -397,7 +465,7 @@ class TestBlock(object): result = block([[a_2d], [b_2d]]) assert_equal(expected, result) - def test_block_with_1d_arrays_row_wise(self): + def test_block_with_1d_arrays_row_wise(self, block): # # # 1-D vectors are treated as row arrays a = np.array([1, 2, 3]) b = np.array([2, 3, 4]) @@ -405,7 +473,7 @@ class TestBlock(object): result = block([a, b]) assert_equal(expected, result) - def test_block_with_1d_arrays_multiple_rows(self): + def test_block_with_1d_arrays_multiple_rows(self, block): a = np.array([1, 2, 3]) b = np.array([2, 3, 4]) expected = np.array([[1, 2, 3, 2, 3, 4], @@ -413,7 +481,7 @@ class TestBlock(object): result = block([[a, b], [a, b]]) assert_equal(expected, result) - def test_block_with_1d_arrays_column_wise(self): + def test_block_with_1d_arrays_column_wise(self, block): # # # 1-D vectors are treated as row arrays a_1d = np.array([1, 2, 3]) b_1d = np.array([2, 3, 4]) @@ -422,7 +490,7 @@ class TestBlock(object): result = block([[a_1d], [b_1d]]) assert_equal(expected, result) - def test_block_mixed_1d_and_2d(self): + def test_block_mixed_1d_and_2d(self, block): a_2d = np.ones((2, 2)) b_1d = np.array([2, 2]) result = block([[a_2d], [b_1d]]) @@ -431,7 +499,7 @@ class TestBlock(object): [2, 2]]) assert_equal(expected, result) - def test_block_complicated(self): + def test_block_complicated(self, block): # a bit more complicated one_2d = np.array([[1, 1, 1]]) two_2d = np.array([[2, 2, 2]]) @@ -455,7 +523,7 @@ class TestBlock(object): [zero_2d]]) assert_equal(result, expected) - def test_nested(self): + def test_nested(self, block): one = np.array([1, 1, 1]) two = np.array([[2, 2, 2], [2, 2, 2], [2, 2, 2]]) three = np.array([3, 3, 3]) @@ -464,9 +532,9 @@ class TestBlock(object): six = np.array([6, 6, 6, 6, 6]) zero = np.zeros((2, 6)) - result = np.block([ + result = block([ [ - np.block([ + block([ [one], [three], [four] @@ -485,7 +553,7 @@ class TestBlock(object): assert_equal(result, expected) - def test_3d(self): + def test_3d(self, block): a000 = np.ones((2, 2, 2), int) * 1 a100 = np.ones((3, 2, 2), int) * 2 @@ -498,7 +566,7 @@ class TestBlock(object): a111 = np.ones((3, 3, 3), int) * 8 - result = np.block([ + result = block([ [ [a000, a001], [a010, a011], @@ -540,55 +608,102 @@ class TestBlock(object): assert_array_equal(result, expected) - def test_block_with_mismatched_shape(self): + def test_block_with_mismatched_shape(self, block): a = np.array([0, 0]) b = np.eye(2) - assert_raises(ValueError, np.block, [a, b]) - assert_raises(ValueError, np.block, [b, a]) + assert_raises(ValueError, block, [a, b]) + assert_raises(ValueError, block, [b, a]) - def test_no_lists(self): - assert_equal(np.block(1), np.array(1)) - assert_equal(np.block(np.eye(3)), np.eye(3)) + to_block = [[np.ones((2,3)), np.ones((2,2))], + [np.ones((2,2)), np.ones((2,2))]] + assert_raises(ValueError, block, to_block) + def test_no_lists(self, block): + assert_equal(block(1), np.array(1)) + assert_equal(block(np.eye(3)), np.eye(3)) - def test_invalid_nesting(self): + def test_invalid_nesting(self, block): msg = 'depths are mismatched' - assert_raises_regex(ValueError, msg, np.block, [1, [2]]) - assert_raises_regex(ValueError, msg, np.block, [1, []]) - assert_raises_regex(ValueError, msg, np.block, [[1], 2]) - assert_raises_regex(ValueError, msg, np.block, [[], 2]) - assert_raises_regex(ValueError, msg, np.block, [ + assert_raises_regex(ValueError, msg, block, [1, [2]]) + assert_raises_regex(ValueError, msg, block, [1, []]) + assert_raises_regex(ValueError, msg, block, [[1], 2]) + assert_raises_regex(ValueError, msg, block, [[], 2]) + assert_raises_regex(ValueError, msg, block, [ [[1], [2]], [[3, 4]], [5] # missing brackets ]) - def test_empty_lists(self): - assert_raises_regex(ValueError, 'empty', np.block, []) - assert_raises_regex(ValueError, 'empty', np.block, [[]]) - assert_raises_regex(ValueError, 'empty', np.block, [[1], []]) + def test_empty_lists(self, block): + assert_raises_regex(ValueError, 'empty', block, []) + assert_raises_regex(ValueError, 'empty', block, [[]]) + assert_raises_regex(ValueError, 'empty', block, [[1], []]) - def test_tuple(self): - assert_raises_regex(TypeError, 'tuple', np.block, ([1, 2], [3, 4])) - assert_raises_regex(TypeError, 'tuple', np.block, [(1, 2), (3, 4)]) + def test_tuple(self, block): + assert_raises_regex(TypeError, 'tuple', block, ([1, 2], [3, 4])) + assert_raises_regex(TypeError, 'tuple', block, [(1, 2), (3, 4)]) - def test_different_ndims(self): + def test_different_ndims(self, block): a = 1. b = 2 * np.ones((1, 2)) c = 3 * np.ones((1, 1, 3)) - result = np.block([a, b, c]) + result = block([a, b, c]) expected = np.array([[[1., 2., 2., 3., 3., 3.]]]) assert_equal(result, expected) - def test_different_ndims_depths(self): + def test_different_ndims_depths(self, block): a = 1. b = 2 * np.ones((1, 2)) c = 3 * np.ones((1, 2, 3)) - result = np.block([[a, b], [c]]) + result = block([[a, b], [c]]) expected = np.array([[[1., 2., 2.], [3., 3., 3.], [3., 3., 3.]]]) assert_equal(result, expected) + + def test_block_memory_order(self, block): + # 3D + arr_c = np.zeros((3,)*3, order='C') + arr_f = np.zeros((3,)*3, order='F') + + b_c = [[[arr_c, arr_c], + [arr_c, arr_c]], + [[arr_c, arr_c], + [arr_c, arr_c]]] + + b_f = [[[arr_f, arr_f], + [arr_f, arr_f]], + [[arr_f, arr_f], + [arr_f, arr_f]]] + + assert block(b_c).flags['C_CONTIGUOUS'] + assert block(b_f).flags['F_CONTIGUOUS'] + + arr_c = np.zeros((3, 3), order='C') + arr_f = np.zeros((3, 3), order='F') + # 2D + b_c = [[arr_c, arr_c], + [arr_c, arr_c]] + + b_f = [[arr_f, arr_f], + [arr_f, arr_f]] + + assert block(b_c).flags['C_CONTIGUOUS'] + assert block(b_f).flags['F_CONTIGUOUS'] + + +def test_block_dispatcher(): + class ArrayLike(object): + pass + a = ArrayLike() + b = ArrayLike() + c = ArrayLike() + assert_equal(list(_block_dispatcher(a)), [a]) + assert_equal(list(_block_dispatcher([a])), [a]) + assert_equal(list(_block_dispatcher([a, b])), [a, b]) + assert_equal(list(_block_dispatcher([[a], [b, [c]]])), [a, b, c]) + # don't recurse into non-lists + assert_equal(list(_block_dispatcher((a, b))), [(a, b)]) diff --git a/numpy/core/tests/test_ufunc.py b/numpy/core/tests/test_ufunc.py index 3881d3cb1..b83b8ccff 100644 --- a/numpy/core/tests/test_ufunc.py +++ b/numpy/core/tests/test_ufunc.py @@ -288,27 +288,96 @@ class TestUfunc(object): """ pass + # from include/numpy/ufuncobject.h + size_inferred = 2 + can_ignore = 4 def test_signature0(self): # the arguments to test_signature are: nin, nout, core_signature - # pass - enabled, num_dims, ixs = umt.test_signature(2, 1, "(i),(i)->()") + enabled, num_dims, ixs, flags, sizes = umt.test_signature( + 2, 1, "(i),(i)->()") assert_equal(enabled, 1) assert_equal(num_dims, (1, 1, 0)) assert_equal(ixs, (0, 0)) + assert_equal(flags, (self.size_inferred,)) + assert_equal(sizes, (-1,)) def test_signature1(self): # empty core signature; treat as plain ufunc (with trivial core) - enabled, num_dims, ixs = umt.test_signature(2, 1, "(),()->()") + enabled, num_dims, ixs, flags, sizes = umt.test_signature( + 2, 1, "(),()->()") assert_equal(enabled, 0) assert_equal(num_dims, (0, 0, 0)) assert_equal(ixs, ()) + assert_equal(flags, ()) + assert_equal(sizes, ()) def test_signature2(self): # more complicated names for variables - enabled, num_dims, ixs = umt.test_signature(2, 1, "(i1,i2),(J_1)->(_kAB)") + enabled, num_dims, ixs, flags, sizes = umt.test_signature( + 2, 1, "(i1,i2),(J_1)->(_kAB)") assert_equal(enabled, 1) assert_equal(num_dims, (2, 1, 1)) assert_equal(ixs, (0, 1, 2, 3)) + assert_equal(flags, (self.size_inferred,)*4) + assert_equal(sizes, (-1, -1, -1, -1)) + + def test_signature3(self): + enabled, num_dims, ixs, flags, sizes = umt.test_signature( + 2, 1, u"(i1, i12), (J_1)->(i12, i2)") + assert_equal(enabled, 1) + assert_equal(num_dims, (2, 1, 2)) + assert_equal(ixs, (0, 1, 2, 1, 3)) + assert_equal(flags, (self.size_inferred,)*4) + assert_equal(sizes, (-1, -1, -1, -1)) + + def test_signature4(self): + # matrix_multiply signature from _umath_tests + enabled, num_dims, ixs, flags, sizes = umt.test_signature( + 2, 1, "(n,k),(k,m)->(n,m)") + assert_equal(enabled, 1) + assert_equal(num_dims, (2, 2, 2)) + assert_equal(ixs, (0, 1, 1, 2, 0, 2)) + assert_equal(flags, (self.size_inferred,)*3) + assert_equal(sizes, (-1, -1, -1)) + + def test_signature5(self): + # matmul signature from _umath_tests + enabled, num_dims, ixs, flags, sizes = umt.test_signature( + 2, 1, "(n?,k),(k,m?)->(n?,m?)") + assert_equal(enabled, 1) + assert_equal(num_dims, (2, 2, 2)) + assert_equal(ixs, (0, 1, 1, 2, 0, 2)) + assert_equal(flags, (self.size_inferred | self.can_ignore, + self.size_inferred, + self.size_inferred | self.can_ignore)) + assert_equal(sizes, (-1, -1, -1)) + + def test_signature6(self): + enabled, num_dims, ixs, flags, sizes = umt.test_signature( + 1, 1, "(3)->()") + assert_equal(enabled, 1) + assert_equal(num_dims, (1, 0)) + assert_equal(ixs, (0,)) + assert_equal(flags, (0,)) + assert_equal(sizes, (3,)) + + def test_signature7(self): + enabled, num_dims, ixs, flags, sizes = umt.test_signature( + 3, 1, "(3),(03,3),(n)->(9)") + assert_equal(enabled, 1) + assert_equal(num_dims, (1, 2, 1, 1)) + assert_equal(ixs, (0, 0, 0, 1, 2)) + assert_equal(flags, (0, self.size_inferred, 0)) + assert_equal(sizes, (3, -1, 9)) + + def test_signature8(self): + enabled, num_dims, ixs, flags, sizes = umt.test_signature( + 3, 1, "(3?),(3?,3?),(n)->(9)") + assert_equal(enabled, 1) + assert_equal(num_dims, (1, 2, 1, 1)) + assert_equal(ixs, (0, 0, 0, 1, 2)) + assert_equal(flags, (self.can_ignore, self.size_inferred, 0)) + assert_equal(sizes, (3, -1, 9)) def test_signature_failure0(self): # in the following calls, a ValueError should be raised because @@ -874,6 +943,89 @@ class TestUfunc(object): w = np.array([], dtype='f8') assert_array_equal(umt.innerwt(a, b, w), np.sum(a*b*w, axis=-1)) + def test_cross1d(self): + """Test with fixed-sized signature.""" + a = np.eye(3) + assert_array_equal(umt.cross1d(a, a), np.zeros((3, 3))) + out = np.zeros((3, 3)) + result = umt.cross1d(a[0], a, out) + assert_(result is out) + assert_array_equal(result, np.vstack((np.zeros(3), a[2], -a[1]))) + assert_raises(ValueError, umt.cross1d, np.eye(4), np.eye(4)) + assert_raises(ValueError, umt.cross1d, a, np.arange(4.)) + assert_raises(ValueError, umt.cross1d, a, np.arange(3.), np.zeros((3, 4))) + + def test_can_ignore_signature(self): + # Comparing the effects of ? in signature: + # matrix_multiply: (m,n),(n,p)->(m,p) # all must be there. + # matmul: (m?,n),(n,p?)->(m?,p?) # allow missing m, p. + mat = np.arange(12).reshape((2, 3, 2)) + single_vec = np.arange(2) + col_vec = single_vec[:, np.newaxis] + col_vec_array = np.arange(8).reshape((2, 2, 2, 1)) + 1 + # matrix @ single column vector with proper dimension + mm_col_vec = umt.matrix_multiply(mat, col_vec) + # matmul does the same thing + matmul_col_vec = umt.matmul(mat, col_vec) + assert_array_equal(matmul_col_vec, mm_col_vec) + # matrix @ vector without dimension making it a column vector. + # matrix multiply fails -> missing core dim. + assert_raises(ValueError, umt.matrix_multiply, mat, single_vec) + # matmul mimicker passes, and returns a vector. + matmul_col = umt.matmul(mat, single_vec) + assert_array_equal(matmul_col, mm_col_vec.squeeze()) + # Now with a column array: same as for column vector, + # broadcasting sensibly. + mm_col_vec = umt.matrix_multiply(mat, col_vec_array) + matmul_col_vec = umt.matmul(mat, col_vec_array) + assert_array_equal(matmul_col_vec, mm_col_vec) + # As above, but for row vector + single_vec = np.arange(3) + row_vec = single_vec[np.newaxis, :] + row_vec_array = np.arange(24).reshape((4, 2, 1, 1, 3)) + 1 + # row vector @ matrix + mm_row_vec = umt.matrix_multiply(row_vec, mat) + matmul_row_vec = umt.matmul(row_vec, mat) + assert_array_equal(matmul_row_vec, mm_row_vec) + # single row vector @ matrix + assert_raises(ValueError, umt.matrix_multiply, single_vec, mat) + matmul_row = umt.matmul(single_vec, mat) + assert_array_equal(matmul_row, mm_row_vec.squeeze()) + # row vector array @ matrix + mm_row_vec = umt.matrix_multiply(row_vec_array, mat) + matmul_row_vec = umt.matmul(row_vec_array, mat) + assert_array_equal(matmul_row_vec, mm_row_vec) + # Now for vector combinations + # row vector @ column vector + col_vec = row_vec.T + col_vec_array = row_vec_array.swapaxes(-2, -1) + mm_row_col_vec = umt.matrix_multiply(row_vec, col_vec) + matmul_row_col_vec = umt.matmul(row_vec, col_vec) + assert_array_equal(matmul_row_col_vec, mm_row_col_vec) + # single row vector @ single col vector + assert_raises(ValueError, umt.matrix_multiply, single_vec, single_vec) + matmul_row_col = umt.matmul(single_vec, single_vec) + assert_array_equal(matmul_row_col, mm_row_col_vec.squeeze()) + # row vector array @ matrix + mm_row_col_array = umt.matrix_multiply(row_vec_array, col_vec_array) + matmul_row_col_array = umt.matmul(row_vec_array, col_vec_array) + assert_array_equal(matmul_row_col_array, mm_row_col_array) + # Finally, check that things are *not* squeezed if one gives an + # output. + out = np.zeros_like(mm_row_col_array) + out = umt.matrix_multiply(row_vec_array, col_vec_array, out=out) + assert_array_equal(out, mm_row_col_array) + out[:] = 0 + out = umt.matmul(row_vec_array, col_vec_array, out=out) + assert_array_equal(out, mm_row_col_array) + # And check one cannot put missing dimensions back. + out = np.zeros_like(mm_row_col_vec) + assert_raises(ValueError, umt.matrix_multiply, single_vec, single_vec, + out) + # But fine for matmul, since it is just a broadcast. + out = umt.matmul(single_vec, single_vec, out) + assert_array_equal(out, mm_row_col_vec.squeeze()) + def test_matrix_multiply(self): self.compare_matrix_multiply_results(np.long) self.compare_matrix_multiply_results(np.double) diff --git a/numpy/core/tests/test_umath.py b/numpy/core/tests/test_umath.py index c15ce83f6..bd7985dfb 100644 --- a/numpy/core/tests/test_umath.py +++ b/numpy/core/tests/test_umath.py @@ -1327,21 +1327,18 @@ class TestMinMax(object): assert_equal(d.max(), d[0]) assert_equal(d.min(), d[0]) - def test_reduce_warns(self): + def test_reduce_reorder(self): # gh 10370, 11029 Some compilers reorder the call to npy_getfloatstatus # and put it before the call to an intrisic function that causes - # invalid status to be set. Also make sure warnings are emitted + # invalid status to be set. Also make sure warnings are not emitted for n in (2, 4, 8, 16, 32): for dt in (np.float32, np.float16, np.complex64): - with suppress_warnings() as sup: - sup.record(RuntimeWarning) - for r in np.diagflat(np.array([np.nan] * n, dtype=dt)): - assert_equal(np.min(r), np.nan) - assert_equal(len(sup.log), n) - - def test_minimize_warns(self): - # gh 11589 - assert_warns(RuntimeWarning, np.minimum, np.nan, 1) + for r in np.diagflat(np.array([np.nan] * n, dtype=dt)): + assert_equal(np.min(r), np.nan) + + def test_minimize_no_warns(self): + a = np.minimum(np.nan, 1) + assert_equal(a, np.nan) class TestAbsoluteNegative(object): diff --git a/numpy/distutils/misc_util.py b/numpy/distutils/misc_util.py index 073e841e8..eba0d9ba1 100644 --- a/numpy/distutils/misc_util.py +++ b/numpy/distutils/misc_util.py @@ -13,7 +13,6 @@ import multiprocessing import distutils from distutils.errors import DistutilsError -from distutils.msvccompiler import get_build_architecture try: from threading import local as tlocal except ImportError: @@ -2336,3 +2335,9 @@ def msvc_version(compiler): raise ValueError("Compiler instance is not msvc (%s)"\ % compiler.compiler_type) return compiler._MSVCCompiler__version + +def get_build_architecture(): + # Importing distutils.msvccompiler triggers a warning on non-Windows + # systems, so delay the import to here. + from distutils.msvccompiler import get_build_architecture + return get_build_architecture() diff --git a/numpy/doc/broadcasting.py b/numpy/doc/broadcasting.py index 6c3a4bc75..0bdb6ae7d 100644 --- a/numpy/doc/broadcasting.py +++ b/numpy/doc/broadcasting.py @@ -3,6 +3,12 @@ Broadcasting over arrays ======================== +.. note:: + See `this article + <https://numpy.org/devdocs/user/theory.broadcasting.html>`_ + for illustrations of broadcasting concepts. + + The term broadcasting describes how numpy treats arrays with different shapes during arithmetic operations. Subject to certain constraints, the smaller array is "broadcast" across the larger array so that they @@ -172,8 +178,5 @@ Here the ``newaxis`` index operator inserts a new axis into ``a``, making it a two-dimensional ``4x1`` array. Combining the ``4x1`` array with ``b``, which has shape ``(3,)``, yields a ``4x3`` array. -See `this article <https://scipy.github.io/old-wiki/pages/EricsBroadcastingDoc>`_ -for illustrations of broadcasting concepts. - """ from __future__ import division, absolute_import, print_function diff --git a/numpy/f2py/src/test/foomodule.c b/numpy/f2py/src/test/foomodule.c index d7ecc2519..733fab0be 100644 --- a/numpy/f2py/src/test/foomodule.c +++ b/numpy/f2py/src/test/foomodule.c @@ -116,8 +116,6 @@ static PyMethodDef foo_module_methods[] = { void initfoo() { int i; PyObject *m, *d, *s; - PyTypeObject *t; - PyObject *f; import_array(); m = Py_InitModule("foo", foo_module_methods); diff --git a/numpy/fft/fftpack.py b/numpy/fft/fftpack.py index d88990373..de675936f 100644 --- a/numpy/fft/fftpack.py +++ b/numpy/fft/fftpack.py @@ -35,10 +35,12 @@ from __future__ import division, absolute_import, print_function __all__ = ['fft', 'ifft', 'rfft', 'irfft', 'hfft', 'ihfft', 'rfftn', 'irfftn', 'rfft2', 'irfft2', 'fft2', 'ifft2', 'fftn', 'ifftn'] +import functools + from numpy.core import (array, asarray, zeros, swapaxes, shape, conjugate, take, sqrt) from numpy.core.multiarray import normalize_axis_index -from numpy.core.overrides import array_function_dispatch +from numpy.core import overrides from . import fftpack_lite as fftpack from .helper import _FFTCache @@ -46,6 +48,10 @@ _fft_cache = _FFTCache(max_size_in_mb=100, max_item_count=32) _real_fft_cache = _FFTCache(max_size_in_mb=100, max_item_count=32) +array_function_dispatch = functools.partial( + overrides.array_function_dispatch, module='numpy.fft') + + def _raw_fft(a, n=None, axis=-1, init_function=fftpack.cffti, work_function=fftpack.cfftf, fft_cache=_fft_cache): a = asarray(a) diff --git a/numpy/fft/helper.py b/numpy/fft/helper.py index 4b698bb4d..e65883651 100644 --- a/numpy/fft/helper.py +++ b/numpy/fft/helper.py @@ -24,7 +24,7 @@ def _fftshift_dispatcher(x, axes=None): return (x,) -@array_function_dispatch(_fftshift_dispatcher) +@array_function_dispatch(_fftshift_dispatcher, module='numpy.fft') def fftshift(x, axes=None): """ Shift the zero-frequency component to the center of the spectrum. @@ -81,7 +81,7 @@ def fftshift(x, axes=None): return roll(x, shift, axes) -@array_function_dispatch(_fftshift_dispatcher) +@array_function_dispatch(_fftshift_dispatcher, module='numpy.fft') def ifftshift(x, axes=None): """ The inverse of `fftshift`. Although identical for even-length `x`, the diff --git a/numpy/lib/arraypad.py b/numpy/lib/arraypad.py index f76ad456f..d27a3918f 100644 --- a/numpy/lib/arraypad.py +++ b/numpy/lib/arraypad.py @@ -995,7 +995,7 @@ def _pad_dispatcher(array, pad_width, mode, **kwargs): return (array,) -@array_function_dispatch(_pad_dispatcher) +@array_function_dispatch(_pad_dispatcher, module='numpy') def pad(array, pad_width, mode, **kwargs): """ Pads an array. diff --git a/numpy/lib/arraysetops.py b/numpy/lib/arraysetops.py index ec62cd7a6..850e20123 100644 --- a/numpy/lib/arraysetops.py +++ b/numpy/lib/arraysetops.py @@ -27,8 +27,14 @@ To do: Optionally return indices analogously to unique for all functions. """ from __future__ import division, absolute_import, print_function +import functools + import numpy as np -from numpy.core.overrides import array_function_dispatch +from numpy.core import overrides + + +array_function_dispatch = functools.partial( + overrides.array_function_dispatch, module='numpy') __all__ = [ diff --git a/numpy/lib/financial.py b/numpy/lib/financial.py index d1a0cd9c0..e1e297492 100644 --- a/numpy/lib/financial.py +++ b/numpy/lib/financial.py @@ -13,9 +13,14 @@ otherwise stated. from __future__ import division, absolute_import, print_function from decimal import Decimal +import functools import numpy as np -from numpy.core.overrides import array_function_dispatch +from numpy.core import overrides + + +array_function_dispatch = functools.partial( + overrides.array_function_dispatch, module='numpy') __all__ = ['fv', 'pmt', 'nper', 'ipmt', 'ppmt', 'pv', 'rate', diff --git a/numpy/lib/format.py b/numpy/lib/format.py index e25868236..1ef3dca47 100644 --- a/numpy/lib/format.py +++ b/numpy/lib/format.py @@ -161,7 +161,9 @@ import sys import io import warnings from numpy.lib.utils import safe_eval -from numpy.compat import asbytes, asstr, isfileobj, long, basestring +from numpy.compat import ( + asbytes, asstr, isfileobj, long, os_fspath + ) from numpy.core.numeric import pickle @@ -706,7 +708,7 @@ def open_memmap(filename, mode='r+', dtype=None, shape=None, Parameters ---------- - filename : str + filename : str or path-like The name of the file on disk. This may *not* be a file-like object. mode : str, optional @@ -747,9 +749,9 @@ def open_memmap(filename, mode='r+', dtype=None, shape=None, memmap """ - if not isinstance(filename, basestring): - raise ValueError("Filename must be a string. Memmap cannot use" - " existing file handles.") + if isfileobj(filename): + raise ValueError("Filename must be a string or a path-like object." + " Memmap cannot use existing file handles.") if 'w' in mode: # We are creating the file, not reading it. @@ -767,7 +769,7 @@ def open_memmap(filename, mode='r+', dtype=None, shape=None, shape=shape, ) # If we got here, then it should be safe to create the file. - fp = open(filename, mode+'b') + fp = open(os_fspath(filename), mode+'b') try: used_ver = _write_array_header(fp, d, version) # this warning can be removed when 1.9 has aged enough @@ -779,7 +781,7 @@ def open_memmap(filename, mode='r+', dtype=None, shape=None, fp.close() else: # Read the header of the file first. - fp = open(filename, 'rb') + fp = open(os_fspath(filename), 'rb') try: version = read_magic(fp) _check_version(version) diff --git a/numpy/lib/function_base.py b/numpy/lib/function_base.py index c52ecdbd8..fae6541bc 100644 --- a/numpy/lib/function_base.py +++ b/numpy/lib/function_base.py @@ -6,6 +6,7 @@ try: import collections.abc as collections_abc except ImportError: import collections as collections_abc +import functools import re import sys import warnings @@ -26,7 +27,7 @@ from numpy.core.fromnumeric import ( ravel, nonzero, partition, mean, any, sum ) from numpy.core.numerictypes import typecodes -from numpy.core.overrides import array_function_dispatch +from numpy.core import overrides from numpy.core.function_base import add_newdoc from numpy.lib.twodim_base import diag from .utils import deprecate @@ -44,6 +45,11 @@ if sys.version_info[0] < 3: else: import builtins + +array_function_dispatch = functools.partial( + overrides.array_function_dispatch, module='numpy') + + # needed in this module for compatibility from numpy.lib.histograms import histogram, histogramdd diff --git a/numpy/lib/index_tricks.py b/numpy/lib/index_tricks.py index 26243d231..ff2e00d3e 100644 --- a/numpy/lib/index_tricks.py +++ b/numpy/lib/index_tricks.py @@ -1,5 +1,6 @@ from __future__ import division, absolute_import, print_function +import functools import sys import math @@ -9,14 +10,17 @@ from numpy.core.numeric import ( ) from numpy.core.numerictypes import find_common_type, issubdtype -from . import function_base import numpy.matrixlib as matrixlib from .function_base import diff from numpy.core.multiarray import ravel_multi_index, unravel_index -from numpy.core.overrides import array_function_dispatch +from numpy.core import overrides, linspace from numpy.lib.stride_tricks import as_strided +array_function_dispatch = functools.partial( + overrides.array_function_dispatch, module='numpy') + + __all__ = [ 'ravel_multi_index', 'unravel_index', 'mgrid', 'ogrid', 'r_', 'c_', 's_', 'index_exp', 'ix_', 'ndenumerate', 'ndindex', 'fill_diagonal', @@ -341,7 +345,7 @@ class AxisConcatenator(object): step = 1 if isinstance(step, complex): size = int(abs(step)) - newobj = function_base.linspace(start, stop, num=size) + newobj = linspace(start, stop, num=size) else: newobj = _nx.arange(start, stop, step) if ndmin > 1: diff --git a/numpy/lib/nanfunctions.py b/numpy/lib/nanfunctions.py index 279c4c5c4..d73d84467 100644 --- a/numpy/lib/nanfunctions.py +++ b/numpy/lib/nanfunctions.py @@ -22,10 +22,15 @@ Functions """ from __future__ import division, absolute_import, print_function +import functools import warnings import numpy as np from numpy.lib import function_base -from numpy.core.overrides import array_function_dispatch +from numpy.core import overrides + + +array_function_dispatch = functools.partial( + overrides.array_function_dispatch, module='numpy') __all__ = [ diff --git a/numpy/lib/npyio.py b/numpy/lib/npyio.py index 62fc9c5b3..6fbb7e805 100644 --- a/numpy/lib/npyio.py +++ b/numpy/lib/npyio.py @@ -12,6 +12,7 @@ import numpy as np from . import format from ._datasource import DataSource from numpy.core.multiarray import packbits, unpackbits +from numpy.core.overrides import array_function_dispatch from numpy.core._internal import recursive from ._iotools import ( LineSplitter, NameValidator, StringConverter, ConverterError, @@ -21,7 +22,7 @@ from ._iotools import ( from numpy.compat import ( asbytes, asstr, asunicode, asbytes_nested, bytes, basestring, unicode, - is_pathlib_path + os_fspath, os_PathLike ) from numpy.core.numeric import pickle @@ -104,8 +105,8 @@ def zipfile_factory(file, *args, **kwargs): pathlib.Path objects. `args` and `kwargs` are passed to the zipfile.ZipFile constructor. """ - if is_pathlib_path(file): - file = str(file) + if not hasattr(file, 'read'): + file = os_fspath(file) import zipfile kwargs['allowZip64'] = True return zipfile.ZipFile(file, *args, **kwargs) @@ -399,15 +400,12 @@ def load(file, mmap_mode=None, allow_pickle=True, fix_imports=True, pickle_kwargs = {} # TODO: Use contextlib.ExitStack once we drop Python 2 - if isinstance(file, basestring): - fid = open(file, "rb") - own_fid = True - elif is_pathlib_path(file): - fid = file.open("rb") - own_fid = True - else: + if hasattr(file, 'read'): fid = file own_fid = False + else: + fid = open(os_fspath(file), "rb") + own_fid = True try: # Code to distinguish from NumPy binary files and pickles. @@ -447,6 +445,11 @@ def load(file, mmap_mode=None, allow_pickle=True, fix_imports=True, fid.close() +def _save_dispatcher(file, arr, allow_pickle=None, fix_imports=None): + return (arr,) + + +@array_function_dispatch(_save_dispatcher) def save(file, arr, allow_pickle=True, fix_imports=True): """ Save an array to a binary file in NumPy ``.npy`` format. @@ -497,18 +500,14 @@ def save(file, arr, allow_pickle=True, fix_imports=True): """ own_fid = False - if isinstance(file, basestring): + if hasattr(file, 'read'): + fid = file + else: + file = os_fspath(file) if not file.endswith('.npy'): file = file + '.npy' fid = open(file, "wb") own_fid = True - elif is_pathlib_path(file): - if not file.name.endswith('.npy'): - file = file.parent / (file.name + '.npy') - fid = file.open("wb") - own_fid = True - else: - fid = file if sys.version_info[0] >= 3: pickle_kwargs = dict(fix_imports=fix_imports) @@ -525,6 +524,14 @@ def save(file, arr, allow_pickle=True, fix_imports=True): fid.close() +def _savez_dispatcher(file, *args, **kwds): + for a in args: + yield a + for v in kwds.values(): + yield v + + +@array_function_dispatch(_savez_dispatcher) def savez(file, *args, **kwds): """ Save several arrays into a single file in uncompressed ``.npz`` format. @@ -604,6 +611,14 @@ def savez(file, *args, **kwds): _savez(file, args, kwds, False) +def _savez_compressed_dispatcher(file, *args, **kwds): + for a in args: + yield a + for v in kwds.values(): + yield v + + +@array_function_dispatch(_savez_compressed_dispatcher) def savez_compressed(file, *args, **kwds): """ Save several arrays into a single file in compressed ``.npz`` format. @@ -673,12 +688,10 @@ def _savez(file, args, kwds, compress, allow_pickle=True, pickle_kwargs=None): # component of the so-called standard library. import zipfile - if isinstance(file, basestring): + if not hasattr(file, 'read'): + file = os_fspath(file) if not file.endswith('.npz'): file = file + '.npz' - elif is_pathlib_path(file): - if not file.name.endswith('.npz'): - file = file.parent / (file.name + '.npz') namedict = kwds for i, val in enumerate(args): @@ -926,8 +939,8 @@ def loadtxt(fname, dtype=float, comments='#', delimiter=None, fown = False try: - if is_pathlib_path(fname): - fname = str(fname) + if isinstance(fname, os_PathLike): + fname = os_fspath(fname) if _is_string_like(fname): fh = np.lib._datasource.open(fname, 'rt', encoding=encoding) fencoding = getattr(fh, 'encoding', 'latin1') @@ -1154,6 +1167,13 @@ def loadtxt(fname, dtype=float, comments='#', delimiter=None, return X +def _savetxt_dispatcher(fname, X, fmt=None, delimiter=None, newline=None, + header=None, footer=None, comments=None, + encoding=None): + return (X,) + + +@array_function_dispatch(_savetxt_dispatcher) def savetxt(fname, X, fmt='%.18e', delimiter=' ', newline='\n', header='', footer='', comments='# ', encoding=None): """ @@ -1315,8 +1335,8 @@ def savetxt(fname, X, fmt='%.18e', delimiter=' ', newline='\n', header='', self.write = self.write_bytes own_fh = False - if is_pathlib_path(fname): - fname = str(fname) + if isinstance(fname, os_PathLike): + fname = os_fspath(fname) if _is_string_like(fname): # datasource doesn't support creating a new file ... open(fname, 'wt').close() @@ -1699,8 +1719,8 @@ def genfromtxt(fname, dtype=float, comments='#', delimiter=None, # Initialize the filehandle, the LineSplitter and the NameValidator own_fhd = False try: - if is_pathlib_path(fname): - fname = str(fname) + if isinstance(fname, os_PathLike): + fname = os_fspath(fname) if isinstance(fname, basestring): fhd = iter(np.lib._datasource.open(fname, 'rt', encoding=encoding)) own_fhd = True diff --git a/numpy/lib/polynomial.py b/numpy/lib/polynomial.py index 9f3b84732..c2702f0a7 100644 --- a/numpy/lib/polynomial.py +++ b/numpy/lib/polynomial.py @@ -8,17 +8,24 @@ __all__ = ['poly', 'roots', 'polyint', 'polyder', 'polyadd', 'polysub', 'polymul', 'polydiv', 'polyval', 'poly1d', 'polyfit', 'RankWarning'] +import functools import re import warnings import numpy.core.numeric as NX from numpy.core import (isscalar, abs, finfo, atleast_1d, hstack, dot, array, ones) +from numpy.core import overrides from numpy.lib.twodim_base import diag, vander from numpy.lib.function_base import trim_zeros from numpy.lib.type_check import iscomplex, real, imag, mintypecode from numpy.linalg import eigvals, lstsq, inv + +array_function_dispatch = functools.partial( + overrides.array_function_dispatch, module='numpy') + + class RankWarning(UserWarning): """ Issued by `polyfit` when the Vandermonde matrix is rank deficient. @@ -29,6 +36,12 @@ class RankWarning(UserWarning): """ pass + +def _poly_dispatcher(seq_of_zeros): + return seq_of_zeros + + +@array_function_dispatch(_poly_dispatcher) def poly(seq_of_zeros): """ Find the coefficients of a polynomial with the given sequence of roots. @@ -145,6 +158,12 @@ def poly(seq_of_zeros): return a + +def _roots_dispatcher(p): + return p + + +@array_function_dispatch(_roots_dispatcher) def roots(p): """ Return the roots of a polynomial with coefficients given in p. @@ -229,6 +248,12 @@ def roots(p): roots = hstack((roots, NX.zeros(trailing_zeros, roots.dtype))) return roots + +def _polyint_dispatcher(p, m=None, k=None): + return (p,) + + +@array_function_dispatch(_polyint_dispatcher) def polyint(p, m=1, k=None): """ Return an antiderivative (indefinite integral) of a polynomial. @@ -322,6 +347,12 @@ def polyint(p, m=1, k=None): return poly1d(val) return val + +def _polyder_dispatcher(p, m=None): + return (p,) + + +@array_function_dispatch(_polyder_dispatcher) def polyder(p, m=1): """ Return the derivative of the specified order of a polynomial. @@ -390,6 +421,12 @@ def polyder(p, m=1): val = poly1d(val) return val + +def _polyfit_dispatcher(x, y, deg, rcond=None, full=None, w=None, cov=None): + return (x, y, w) + + +@array_function_dispatch(_polyfit_dispatcher) def polyfit(x, y, deg, rcond=None, full=False, w=None, cov=False): """ Least squares polynomial fit. @@ -610,6 +647,11 @@ def polyfit(x, y, deg, rcond=None, full=False, w=None, cov=False): return c +def _polyval_dispatcher(p, x): + return (p, x) + + +@array_function_dispatch(_polyval_dispatcher) def polyval(p, x): """ Evaluate a polynomial at specific values. @@ -679,6 +721,12 @@ def polyval(p, x): y = y * x + p[i] return y + +def _binary_op_dispatcher(a1, a2): + return (a1, a2) + + +@array_function_dispatch(_binary_op_dispatcher) def polyadd(a1, a2): """ Find the sum of two polynomials. @@ -739,6 +787,8 @@ def polyadd(a1, a2): val = poly1d(val) return val + +@array_function_dispatch(_binary_op_dispatcher) def polysub(a1, a2): """ Difference (subtraction) of two polynomials. @@ -786,6 +836,7 @@ def polysub(a1, a2): return val +@array_function_dispatch(_binary_op_dispatcher) def polymul(a1, a2): """ Find the product of two polynomials. @@ -842,6 +893,12 @@ def polymul(a1, a2): val = poly1d(val) return val + +def _polydiv_dispatcher(u, v): + return (u, v) + + +@array_function_dispatch(_polydiv_dispatcher) def polydiv(u, v): """ Returns the quotient and remainder of polynomial division. diff --git a/numpy/lib/recfunctions.py b/numpy/lib/recfunctions.py index b6453d5a2..53a586f56 100644 --- a/numpy/lib/recfunctions.py +++ b/numpy/lib/recfunctions.py @@ -14,6 +14,7 @@ import numpy.ma as ma from numpy import ndarray, recarray from numpy.ma import MaskedArray from numpy.ma.mrecords import MaskedRecords +from numpy.core.overrides import array_function_dispatch from numpy.lib._iotools import _is_string_like from numpy.compat import basestring @@ -31,6 +32,11 @@ __all__ = [ ] +def _recursive_fill_fields_dispatcher(input, output): + return (input, output) + + +@array_function_dispatch(_recursive_fill_fields_dispatcher) def recursive_fill_fields(input, output): """ Fills fields from output with fields from input, @@ -189,6 +195,11 @@ def flatten_descr(ndtype): return tuple(descr) +def _zip_dtype_dispatcher(seqarrays, flatten=None): + return seqarrays + + +@array_function_dispatch(_zip_dtype_dispatcher) def zip_dtype(seqarrays, flatten=False): newdtype = [] if flatten: @@ -205,6 +216,7 @@ def zip_dtype(seqarrays, flatten=False): return np.dtype(newdtype) +@array_function_dispatch(_zip_dtype_dispatcher) def zip_descr(seqarrays, flatten=False): """ Combine the dtype description of a series of arrays. @@ -297,6 +309,11 @@ def _izip_fields(iterable): yield element +def _izip_records_dispatcher(seqarrays, fill_value=None, flatten=None): + return seqarrays + + +@array_function_dispatch(_izip_records_dispatcher) def izip_records(seqarrays, fill_value=None, flatten=True): """ Returns an iterator of concatenated items from a sequence of arrays. @@ -357,6 +374,12 @@ def _fix_defaults(output, defaults=None): return output +def _merge_arrays_dispatcher(seqarrays, fill_value=None, flatten=None, + usemask=None, asrecarray=None): + return seqarrays + + +@array_function_dispatch(_merge_arrays_dispatcher) def merge_arrays(seqarrays, fill_value=-1, flatten=False, usemask=False, asrecarray=False): """ @@ -494,6 +517,11 @@ def merge_arrays(seqarrays, fill_value=-1, flatten=False, return output +def _drop_fields_dispatcher(base, drop_names, usemask=None, asrecarray=None): + return (base,) + + +@array_function_dispatch(_drop_fields_dispatcher) def drop_fields(base, drop_names, usemask=True, asrecarray=False): """ Return a new array with fields in `drop_names` dropped. @@ -583,6 +611,11 @@ def _keep_fields(base, keep_names, usemask=True, asrecarray=False): return _fix_output(output, usemask=usemask, asrecarray=asrecarray) +def _rec_drop_fields_dispatcher(base, drop_names): + return (base,) + + +@array_function_dispatch(_rec_drop_fields_dispatcher) def rec_drop_fields(base, drop_names): """ Returns a new numpy.recarray with fields in `drop_names` dropped. @@ -590,6 +623,11 @@ def rec_drop_fields(base, drop_names): return drop_fields(base, drop_names, usemask=False, asrecarray=True) +def _rename_fields_dispatcher(base, namemapper): + return (base,) + + +@array_function_dispatch(_rename_fields_dispatcher) def rename_fields(base, namemapper): """ Rename the fields from a flexible-datatype ndarray or recarray. @@ -629,6 +667,14 @@ def rename_fields(base, namemapper): return base.view(newdtype) +def _append_fields_dispatcher(base, names, data, dtypes=None, + fill_value=None, usemask=None, asrecarray=None): + yield base + for d in data: + yield d + + +@array_function_dispatch(_append_fields_dispatcher) def append_fields(base, names, data, dtypes=None, fill_value=-1, usemask=True, asrecarray=False): """ @@ -699,6 +745,13 @@ def append_fields(base, names, data, dtypes=None, return _fix_output(output, usemask=usemask, asrecarray=asrecarray) +def _rec_append_fields_dispatcher(base, names, data, dtypes=None): + yield base + for d in data: + yield d + + +@array_function_dispatch(_rec_append_fields_dispatcher) def rec_append_fields(base, names, data, dtypes=None): """ Add new fields to an existing array. @@ -732,6 +785,12 @@ def rec_append_fields(base, names, data, dtypes=None): return append_fields(base, names, data=data, dtypes=dtypes, asrecarray=True, usemask=False) + +def _repack_fields_dispatcher(a, align=None, recurse=None): + return (a,) + + +@array_function_dispatch(_repack_fields_dispatcher) def repack_fields(a, align=False, recurse=False): """ Re-pack the fields of a structured array or dtype in memory. @@ -811,6 +870,13 @@ def repack_fields(a, align=False, recurse=False): dt = np.dtype(fieldinfo, align=align) return np.dtype((a.type, dt)) + +def _stack_arrays_dispatcher(arrays, defaults=None, usemask=None, + asrecarray=None, autoconvert=None): + return arrays + + +@array_function_dispatch(_stack_arrays_dispatcher) def stack_arrays(arrays, defaults=None, usemask=True, asrecarray=False, autoconvert=False): """ @@ -897,6 +963,12 @@ def stack_arrays(arrays, defaults=None, usemask=True, asrecarray=False, usemask=usemask, asrecarray=asrecarray) +def _find_duplicates_dispatcher( + a, key=None, ignoremask=None, return_index=None): + return (a,) + + +@array_function_dispatch(_find_duplicates_dispatcher) def find_duplicates(a, key=None, ignoremask=True, return_index=False): """ Find the duplicates in a structured array along a given key @@ -951,8 +1023,15 @@ def find_duplicates(a, key=None, ignoremask=True, return_index=False): return duplicates +def _join_by_dispatcher( + key, r1, r2, jointype=None, r1postfix=None, r2postfix=None, + defaults=None, usemask=None, asrecarray=None): + return (r1, r2) + + +@array_function_dispatch(_join_by_dispatcher) def join_by(key, r1, r2, jointype='inner', r1postfix='1', r2postfix='2', - defaults=None, usemask=True, asrecarray=False): + defaults=None, usemask=True, asrecarray=False): """ Join arrays `r1` and `r2` on key `key`. @@ -1130,6 +1209,13 @@ def join_by(key, r1, r2, jointype='inner', r1postfix='1', r2postfix='2', return _fix_output(_fix_defaults(output, defaults), **kwargs) +def _rec_join_dispatcher( + key, r1, r2, jointype=None, r1postfix=None, r2postfix=None, + defaults=None): + return (r1, r2) + + +@array_function_dispatch(_rec_join_dispatcher) def rec_join(key, r1, r2, jointype='inner', r1postfix='1', r2postfix='2', defaults=None): """ diff --git a/numpy/lib/scimath.py b/numpy/lib/scimath.py index f1838fee6..9ca006841 100644 --- a/numpy/lib/scimath.py +++ b/numpy/lib/scimath.py @@ -20,6 +20,7 @@ from __future__ import division, absolute_import, print_function import numpy.core.numeric as nx import numpy.core.numerictypes as nt from numpy.core.numeric import asarray, any +from numpy.core.overrides import array_function_dispatch from numpy.lib.type_check import isreal @@ -94,6 +95,7 @@ def _tocomplex(arr): else: return arr.astype(nt.cdouble) + def _fix_real_lt_zero(x): """Convert `x` to complex if it has real, negative components. @@ -121,6 +123,7 @@ def _fix_real_lt_zero(x): x = _tocomplex(x) return x + def _fix_int_lt_zero(x): """Convert `x` to double if it has real, negative components. @@ -147,6 +150,7 @@ def _fix_int_lt_zero(x): x = x * 1.0 return x + def _fix_real_abs_gt_1(x): """Convert `x` to complex if it has real components x_i with abs(x_i)>1. @@ -173,6 +177,12 @@ def _fix_real_abs_gt_1(x): x = _tocomplex(x) return x + +def _unary_dispatcher(x): + return (x,) + + +@array_function_dispatch(_unary_dispatcher) def sqrt(x): """ Compute the square root of x. @@ -215,6 +225,8 @@ def sqrt(x): x = _fix_real_lt_zero(x) return nx.sqrt(x) + +@array_function_dispatch(_unary_dispatcher) def log(x): """ Compute the natural logarithm of `x`. @@ -261,6 +273,8 @@ def log(x): x = _fix_real_lt_zero(x) return nx.log(x) + +@array_function_dispatch(_unary_dispatcher) def log10(x): """ Compute the logarithm base 10 of `x`. @@ -309,6 +323,12 @@ def log10(x): x = _fix_real_lt_zero(x) return nx.log10(x) + +def _logn_dispatcher(n, x): + return (n, x,) + + +@array_function_dispatch(_logn_dispatcher) def logn(n, x): """ Take log base n of x. @@ -318,8 +338,8 @@ def logn(n, x): Parameters ---------- - n : int - The base in which the log is taken. + n : array_like + The integer base(s) in which the log is taken. x : array_like The value(s) whose log base `n` is (are) required. @@ -343,6 +363,8 @@ def logn(n, x): n = _fix_real_lt_zero(n) return nx.log(x)/nx.log(n) + +@array_function_dispatch(_unary_dispatcher) def log2(x): """ Compute the logarithm base 2 of `x`. @@ -389,6 +411,12 @@ def log2(x): x = _fix_real_lt_zero(x) return nx.log2(x) + +def _power_dispatcher(x, p): + return (x, p) + + +@array_function_dispatch(_power_dispatcher) def power(x, p): """ Return x to the power p, (x**p). @@ -432,6 +460,8 @@ def power(x, p): p = _fix_int_lt_zero(p) return nx.power(x, p) + +@array_function_dispatch(_unary_dispatcher) def arccos(x): """ Compute the inverse cosine of x. @@ -475,6 +505,8 @@ def arccos(x): x = _fix_real_abs_gt_1(x) return nx.arccos(x) + +@array_function_dispatch(_unary_dispatcher) def arcsin(x): """ Compute the inverse sine of x. @@ -519,6 +551,8 @@ def arcsin(x): x = _fix_real_abs_gt_1(x) return nx.arcsin(x) + +@array_function_dispatch(_unary_dispatcher) def arctanh(x): """ Compute the inverse hyperbolic tangent of `x`. diff --git a/numpy/lib/shape_base.py b/numpy/lib/shape_base.py index 66f534734..6e7cab3fa 100644 --- a/numpy/lib/shape_base.py +++ b/numpy/lib/shape_base.py @@ -1,5 +1,6 @@ from __future__ import division, absolute_import, print_function +import functools import warnings import numpy.core.numeric as _nx @@ -8,7 +9,9 @@ from numpy.core.numeric import ( ) from numpy.core.fromnumeric import product, reshape, transpose from numpy.core.multiarray import normalize_axis_index +from numpy.core import overrides from numpy.core import vstack, atleast_3d +from numpy.core.shape_base import _arrays_for_stack_dispatcher from numpy.lib.index_tricks import ndindex from numpy.matrixlib.defmatrix import matrix # this raises all the right alarm bells @@ -21,6 +24,10 @@ __all__ = [ ] +array_function_dispatch = functools.partial( + overrides.array_function_dispatch, module='numpy') + + def _make_along_axis_idx(arr_shape, indices, axis): # compute dimensions to iterate over if not _nx.issubdtype(indices.dtype, _nx.integer): @@ -44,6 +51,11 @@ def _make_along_axis_idx(arr_shape, indices, axis): return tuple(fancy_index) +def _take_along_axis_dispatcher(arr, indices, axis): + return (arr, indices) + + +@array_function_dispatch(_take_along_axis_dispatcher) def take_along_axis(arr, indices, axis): """ Take values from the input array by matching 1d index and data slices. @@ -160,6 +172,11 @@ def take_along_axis(arr, indices, axis): return arr[_make_along_axis_idx(arr_shape, indices, axis)] +def _put_along_axis_dispatcher(arr, indices, values, axis): + return (arr, indices, values) + + +@array_function_dispatch(_put_along_axis_dispatcher) def put_along_axis(arr, indices, values, axis): """ Put values into the destination array by matching 1d index and data slices. @@ -245,6 +262,11 @@ def put_along_axis(arr, indices, values, axis): arr[_make_along_axis_idx(arr_shape, indices, axis)] = values +def _apply_along_axis_dispatcher(func1d, axis, arr, *args, **kwargs): + return (arr,) + + +@array_function_dispatch(_apply_along_axis_dispatcher) def apply_along_axis(func1d, axis, arr, *args, **kwargs): """ Apply a function to 1-D slices along the given axis. @@ -392,6 +414,11 @@ def apply_along_axis(func1d, axis, arr, *args, **kwargs): return res.__array_wrap__(out_arr) +def _apply_over_axes_dispatcher(func, a, axes): + return (a,) + + +@array_function_dispatch(_apply_over_axes_dispatcher) def apply_over_axes(func, a, axes): """ Apply a function repeatedly over multiple axes. @@ -474,9 +501,15 @@ def apply_over_axes(func, a, axes): val = res else: raise ValueError("function is not returning " - "an array of the correct shape") + "an array of the correct shape") return val + +def _expand_dims_dispatcher(a, axis): + return (a,) + + +@array_function_dispatch(_expand_dims_dispatcher) def expand_dims(a, axis): """ Expand the shape of an array. @@ -554,8 +587,15 @@ def expand_dims(a, axis): # axis = normalize_axis_index(axis, a.ndim + 1) return a.reshape(shape[:axis] + (1,) + shape[axis:]) + row_stack = vstack + +def _column_stack_dispatcher(tup): + return _arrays_for_stack_dispatcher(tup) + + +@array_function_dispatch(_column_stack_dispatcher) def column_stack(tup): """ Stack 1-D arrays as columns into a 2-D array. @@ -597,6 +637,12 @@ def column_stack(tup): arrays.append(arr) return _nx.concatenate(arrays, 1) + +def _dstack_dispatcher(tup): + return _arrays_for_stack_dispatcher(tup) + + +@array_function_dispatch(_dstack_dispatcher) def dstack(tup): """ Stack arrays in sequence depth wise (along third axis). @@ -649,6 +695,7 @@ def dstack(tup): """ return _nx.concatenate([atleast_3d(_m) for _m in tup], 2) + def _replace_zero_by_x_arrays(sub_arys): for i in range(len(sub_arys)): if _nx.ndim(sub_arys[i]) == 0: @@ -657,6 +704,12 @@ def _replace_zero_by_x_arrays(sub_arys): sub_arys[i] = _nx.empty(0, dtype=sub_arys[i].dtype) return sub_arys + +def _array_split_dispatcher(ary, indices_or_sections, axis=None): + return (ary, indices_or_sections) + + +@array_function_dispatch(_array_split_dispatcher) def array_split(ary, indices_or_sections, axis=0): """ Split an array into multiple sub-arrays. @@ -712,7 +765,12 @@ def array_split(ary, indices_or_sections, axis=0): return sub_arys -def split(ary,indices_or_sections,axis=0): +def _split_dispatcher(ary, indices_or_sections, axis=None): + return (ary, indices_or_sections) + + +@array_function_dispatch(_split_dispatcher) +def split(ary, indices_or_sections, axis=0): """ Split an array into multiple sub-arrays. @@ -789,6 +847,12 @@ def split(ary,indices_or_sections,axis=0): res = array_split(ary, indices_or_sections, axis) return res + +def _hvdsplit_dispatcher(ary, indices_or_sections): + return (ary, indices_or_sections) + + +@array_function_dispatch(_hvdsplit_dispatcher) def hsplit(ary, indices_or_sections): """ Split an array into multiple sub-arrays horizontally (column-wise). @@ -851,6 +915,8 @@ def hsplit(ary, indices_or_sections): else: return split(ary, indices_or_sections, 0) + +@array_function_dispatch(_hvdsplit_dispatcher) def vsplit(ary, indices_or_sections): """ Split an array into multiple sub-arrays vertically (row-wise). @@ -902,6 +968,8 @@ def vsplit(ary, indices_or_sections): raise ValueError('vsplit only works on arrays of 2 or more dimensions') return split(ary, indices_or_sections, 0) + +@array_function_dispatch(_hvdsplit_dispatcher) def dsplit(ary, indices_or_sections): """ Split array into multiple sub-arrays along the 3rd axis (depth). @@ -971,6 +1039,12 @@ def get_array_wrap(*args): return wrappers[-1][-1] return None + +def _kron_dispatcher(a, b): + return (a, b) + + +@array_function_dispatch(_kron_dispatcher) def kron(a, b): """ Kronecker product of two arrays. @@ -1070,6 +1144,11 @@ def kron(a, b): return result +def _tile_dispatcher(A, reps): + return (A, reps) + + +@array_function_dispatch(_tile_dispatcher) def tile(A, reps): """ Construct an array by repeating A the number of times given by reps. diff --git a/numpy/lib/stride_tricks.py b/numpy/lib/stride_tricks.py index ca13738c1..0dc36e41c 100644 --- a/numpy/lib/stride_tricks.py +++ b/numpy/lib/stride_tricks.py @@ -8,6 +8,7 @@ NumPy reference guide. from __future__ import division, absolute_import, print_function import numpy as np +from numpy.core.overrides import array_function_dispatch __all__ = ['broadcast_to', 'broadcast_arrays'] @@ -135,6 +136,11 @@ def _broadcast_to(array, shape, subok, readonly): return result +def _broadcast_to_dispatcher(array, shape, subok=None): + return (array,) + + +@array_function_dispatch(_broadcast_to_dispatcher, module='numpy') def broadcast_to(array, shape, subok=False): """Broadcast an array to a new shape. @@ -195,6 +201,11 @@ def _broadcast_shape(*args): return b.shape +def _broadcast_arrays_dispatcher(*args, **kwargs): + return args + + +@array_function_dispatch(_broadcast_arrays_dispatcher, module='numpy') def broadcast_arrays(*args, **kwargs): """ Broadcast any number of arrays against each other. diff --git a/numpy/lib/tests/test_function_base.py b/numpy/lib/tests/test_function_base.py index 40cca1dbb..0c789e012 100644 --- a/numpy/lib/tests/test_function_base.py +++ b/numpy/lib/tests/test_function_base.py @@ -3114,3 +3114,29 @@ class TestAdd_newdoc(object): assert_equal(np.core.flatiter.index.__doc__[:len(tgt)], tgt) assert_(len(np.core.ufunc.identity.__doc__) > 300) assert_(len(np.lib.index_tricks.mgrid.__doc__) > 300) + +class TestSortComplex(object): + + @pytest.mark.parametrize("type_in, type_out", [ + ('l', 'D'), + ('h', 'F'), + ('H', 'F'), + ('b', 'F'), + ('B', 'F'), + ('g', 'G'), + ]) + def test_sort_real(self, type_in, type_out): + # sort_complex() type casting for real input types + a = np.array([5, 3, 6, 2, 1], dtype=type_in) + actual = np.sort_complex(a) + expected = np.sort(a).astype(type_out) + assert_equal(actual, expected) + assert_equal(actual.dtype, expected.dtype) + + def test_sort_complex(self): + # sort_complex() handling of complex input + a = np.array([2 + 3j, 1 - 2j, 1 - 3j, 2 + 1j], dtype='D') + expected = np.array([1 - 3j, 1 - 2j, 2 + 1j, 2 + 3j], dtype='D') + actual = np.sort_complex(a) + assert_equal(actual, expected) + assert_equal(actual.dtype, expected.dtype) diff --git a/numpy/lib/tests/test_histograms.py b/numpy/lib/tests/test_histograms.py index fa6ad989f..1b5a71d0e 100644 --- a/numpy/lib/tests/test_histograms.py +++ b/numpy/lib/tests/test_histograms.py @@ -249,6 +249,12 @@ class TestHistogram(object): assert_raises(ValueError, histogram, vals, range=[np.nan,0.75]) assert_raises(ValueError, histogram, vals, range=[0.25,np.inf]) + def test_invalid_range(self): + # start of range must be < end of range + vals = np.linspace(0.0, 1.0, num=100) + with assert_raises_regex(ValueError, "max must be larger than"): + np.histogram(vals, range=[0.1, 0.01]) + def test_bin_edge_cases(self): # Ensure that floating-point computations correctly place edge cases. arr = np.array([337, 404, 739, 806, 1007, 1811, 2012]) @@ -265,6 +271,13 @@ class TestHistogram(object): hist, edges = np.histogram(arr, bins=30, range=(-0.5, 5)) assert_equal(hist[-1], 1) + def test_bin_array_dims(self): + # gracefully handle bins object > 1 dimension + vals = np.linspace(0.0, 1.0, num=100) + bins = np.array([[0, 0.5], [0.6, 1.0]]) + with assert_raises_regex(ValueError, "must be 1d"): + np.histogram(vals, bins=bins) + def test_unsigned_monotonicity_check(self): # Ensures ValueError is raised if bins not increasing monotonically # when bins contain unsigned values (see #9222) diff --git a/numpy/lib/tests/test_index_tricks.py b/numpy/lib/tests/test_index_tricks.py index 76d9b403e..3246f68ff 100644 --- a/numpy/lib/tests/test_index_tricks.py +++ b/numpy/lib/tests/test_index_tricks.py @@ -226,6 +226,11 @@ class TestConcatenator(object): g = r_[-10.1, np.array([1]), np.array([2, 3, 4]), 10.0] assert_(g.dtype == 'f8') + def test_complex_step(self): + # Regression test for #12262 + g = r_[0:36:100j] + assert_(g.shape == (100,)) + def test_2d(self): b = np.random.rand(5, 5) c = np.random.rand(5, 5) diff --git a/numpy/lib/tests/test_io.py b/numpy/lib/tests/test_io.py index 08800ff97..b746937b9 100644 --- a/numpy/lib/tests/test_io.py +++ b/numpy/lib/tests/test_io.py @@ -2295,11 +2295,35 @@ class TestPathUsage(object): assert_array_equal(x, a) def test_save_load(self): - # Test that pathlib.Path instances can be used with savez. + # Test that pathlib.Path instances can be used with save. + with temppath(suffix='.npy') as path: + path = Path(path) + a = np.array([[1, 2], [3, 4]], int) + np.save(path, a) + data = np.load(path) + assert_array_equal(data, a) + + def test_save_load_memmap(self): + # Test that pathlib.Path instances can be loaded mem-mapped. + with temppath(suffix='.npy') as path: + path = Path(path) + a = np.array([[1, 2], [3, 4]], int) + np.save(path, a) + data = np.load(path, mmap_mode='r') + assert_array_equal(data, a) + # close the mem-mapped file + del data + + def test_save_load_memmap_readwrite(self): + # Test that pathlib.Path instances can be written mem-mapped. with temppath(suffix='.npy') as path: path = Path(path) a = np.array([[1, 2], [3, 4]], int) np.save(path, a) + b = np.load(path, mmap_mode='r+') + a[0][0] = 5 + b[0][0] = 5 + del b # closes the file data = np.load(path) assert_array_equal(data, a) diff --git a/numpy/lib/tests/test_shape_base.py b/numpy/lib/tests/test_shape_base.py index 6e4cd225d..e338467f9 100644 --- a/numpy/lib/tests/test_shape_base.py +++ b/numpy/lib/tests/test_shape_base.py @@ -457,10 +457,35 @@ class TestSplit(object): a = np.arange(10) assert_raises(ValueError, split, a, 3) + class TestColumnStack(object): def test_non_iterable(self): assert_raises(TypeError, column_stack, 1) + def test_1D_arrays(self): + # example from docstring + a = np.array((1, 2, 3)) + b = np.array((2, 3, 4)) + expected = np.array([[1, 2], + [2, 3], + [3, 4]]) + actual = np.column_stack((a, b)) + assert_equal(actual, expected) + + def test_2D_arrays(self): + # same as hstack 2D docstring example + a = np.array([[1], [2], [3]]) + b = np.array([[2], [3], [4]]) + expected = np.array([[1, 2], + [2, 3], + [3, 4]]) + actual = np.column_stack((a, b)) + assert_equal(actual, expected) + + def test_generator(self): + with assert_warns(FutureWarning): + column_stack((np.arange(3) for _ in range(2))) + class TestDstack(object): def test_non_iterable(self): @@ -494,6 +519,10 @@ class TestDstack(object): desired = np.array([[[1, 1], [2, 2]]]) assert_array_equal(res, desired) + def test_generator(self): + with assert_warns(FutureWarning): + dstack((np.arange(3) for _ in range(2))) + # array_split has more comprehensive test of splitting. # only do simple test on hsplit, vsplit, and dsplit diff --git a/numpy/lib/twodim_base.py b/numpy/lib/twodim_base.py index 98efba191..a05e68375 100644 --- a/numpy/lib/twodim_base.py +++ b/numpy/lib/twodim_base.py @@ -3,11 +3,14 @@ """ from __future__ import division, absolute_import, print_function +import functools + from numpy.core.numeric import ( absolute, asanyarray, arange, zeros, greater_equal, multiply, ones, asarray, where, int8, int16, int32, int64, empty, promote_types, diagonal, nonzero ) +from numpy.core import overrides from numpy.core import iinfo, transpose @@ -17,6 +20,10 @@ __all__ = [ 'tril_indices_from', 'triu_indices', 'triu_indices_from', ] +array_function_dispatch = functools.partial( + overrides.array_function_dispatch, module='numpy') + + i1 = iinfo(int8) i2 = iinfo(int16) i4 = iinfo(int32) @@ -33,6 +40,11 @@ def _min_int(low, high): return int64 +def _flip_dispatcher(m): + return (m,) + + +@array_function_dispatch(_flip_dispatcher) def fliplr(m): """ Flip array in the left/right direction. @@ -83,6 +95,7 @@ def fliplr(m): return m[:, ::-1] +@array_function_dispatch(_flip_dispatcher) def flipud(m): """ Flip array in the up/down direction. @@ -194,6 +207,11 @@ def eye(N, M=None, k=0, dtype=float, order='C'): return m +def _diag_dispatcher(v, k=None): + return (v,) + + +@array_function_dispatch(_diag_dispatcher) def diag(v, k=0): """ Extract a diagonal or construct a diagonal array. @@ -265,6 +283,7 @@ def diag(v, k=0): raise ValueError("Input must be 1- or 2-d.") +@array_function_dispatch(_diag_dispatcher) def diagflat(v, k=0): """ Create a two-dimensional array with the flattened input as a diagonal. @@ -373,6 +392,11 @@ def tri(N, M=None, k=0, dtype=float): return m +def _trilu_dispatcher(m, k=None): + return (m,) + + +@array_function_dispatch(_trilu_dispatcher) def tril(m, k=0): """ Lower triangle of an array. @@ -411,6 +435,7 @@ def tril(m, k=0): return where(mask, m, zeros(1, m.dtype)) +@array_function_dispatch(_trilu_dispatcher) def triu(m, k=0): """ Upper triangle of an array. @@ -439,7 +464,12 @@ def triu(m, k=0): return where(mask, zeros(1, m.dtype), m) +def _vander_dispatcher(x, N=None, increasing=None): + return (x,) + + # Originally borrowed from John Hunter and matplotlib +@array_function_dispatch(_vander_dispatcher) def vander(x, N=None, increasing=False): """ Generate a Vandermonde matrix. @@ -530,6 +560,12 @@ def vander(x, N=None, increasing=False): return v +def _histogram2d_dispatcher(x, y, bins=None, range=None, normed=None, + weights=None, density=None): + return (x, y, bins, weights) + + +@array_function_dispatch(_histogram2d_dispatcher) def histogram2d(x, y, bins=10, range=None, normed=None, weights=None, density=None): """ @@ -812,6 +848,11 @@ def tril_indices(n, k=0, m=None): return nonzero(tri(n, m, k=k, dtype=bool)) +def _trilu_indices_form_dispatcher(arr, k=None): + return (arr,) + + +@array_function_dispatch(_trilu_indices_form_dispatcher) def tril_indices_from(arr, k=0): """ Return the indices for the lower-triangle of arr. @@ -922,6 +963,7 @@ def triu_indices(n, k=0, m=None): return nonzero(~tri(n, m, k=k-1, dtype=bool)) +@array_function_dispatch(_trilu_indices_form_dispatcher) def triu_indices_from(arr, k=0): """ Return the indices for the upper-triangle of arr. diff --git a/numpy/lib/type_check.py b/numpy/lib/type_check.py index 603da8567..9153e1692 100644 --- a/numpy/lib/type_check.py +++ b/numpy/lib/type_check.py @@ -2,6 +2,7 @@ """ from __future__ import division, absolute_import, print_function +import functools import warnings __all__ = ['iscomplexobj', 'isrealobj', 'imag', 'iscomplex', @@ -11,10 +12,17 @@ __all__ = ['iscomplexobj', 'isrealobj', 'imag', 'iscomplex', import numpy.core.numeric as _nx from numpy.core.numeric import asarray, asanyarray, array, isnan, zeros +from numpy.core import overrides from .ufunclike import isneginf, isposinf + +array_function_dispatch = functools.partial( + overrides.array_function_dispatch, module='numpy') + + _typecodes_by_elsize = 'GDFgdfQqLlIiHhBb?' + def mintypecode(typechars,typeset='GDFgdf',default='d'): """ Return the character for the minimum-size type to which given types can @@ -104,6 +112,11 @@ def asfarray(a, dtype=_nx.float_): return asarray(a, dtype=dtype) +def _real_dispatcher(val): + return (val,) + + +@array_function_dispatch(_real_dispatcher) def real(val): """ Return the real part of the complex argument. @@ -145,6 +158,11 @@ def real(val): return asanyarray(val).real +def _imag_dispatcher(val): + return (val,) + + +@array_function_dispatch(_imag_dispatcher) def imag(val): """ Return the imaginary part of the complex argument. @@ -183,6 +201,11 @@ def imag(val): return asanyarray(val).imag +def _is_type_dispatcher(x): + return (x,) + + +@array_function_dispatch(_is_type_dispatcher) def iscomplex(x): """ Returns a bool array, where True if input element is complex. @@ -218,6 +241,8 @@ def iscomplex(x): res = zeros(ax.shape, bool) return res[()] # convert to scalar if needed + +@array_function_dispatch(_is_type_dispatcher) def isreal(x): """ Returns a bool array, where True if input element is real. @@ -248,6 +273,8 @@ def isreal(x): """ return imag(x) == 0 + +@array_function_dispatch(_is_type_dispatcher) def iscomplexobj(x): """ Check for a complex type or an array of complex numbers. @@ -288,6 +315,7 @@ def iscomplexobj(x): return issubclass(type_, _nx.complexfloating) +@array_function_dispatch(_is_type_dispatcher) def isrealobj(x): """ Return True if x is a not complex type or an array of complex numbers. @@ -329,6 +357,12 @@ def _getmaxmin(t): f = getlimits.finfo(t) return f.max, f.min + +def _nan_to_num_dispatcher(x, copy=None): + return (x,) + + +@array_function_dispatch(_nan_to_num_dispatcher) def nan_to_num(x, copy=True): """ Replace NaN with zero and infinity with large finite numbers. @@ -411,7 +445,12 @@ def nan_to_num(x, copy=True): #----------------------------------------------------------------------------- -def real_if_close(a,tol=100): +def _real_if_close_dispatcher(a, tol=None): + return (a,) + + +@array_function_dispatch(_real_if_close_dispatcher) +def real_if_close(a, tol=100): """ If complex input returns a real array if complex parts are close to zero. @@ -466,6 +505,11 @@ def real_if_close(a,tol=100): return a +def _asscalar_dispatcher(a): + return (a,) + + +@array_function_dispatch(_asscalar_dispatcher) def asscalar(a): """ Convert an array of size 1 to its scalar equivalent. @@ -586,6 +630,13 @@ array_precision = {_nx.half: 0, _nx.csingle: 1, _nx.cdouble: 2, _nx.clongdouble: 3} + + +def _common_type_dispatcher(*arrays): + return arrays + + +@array_function_dispatch(_common_type_dispatcher) def common_type(*arrays): """ Return a scalar type which is common to the input arrays. diff --git a/numpy/lib/ufunclike.py b/numpy/lib/ufunclike.py index 6259c5445..ac0af0b37 100644 --- a/numpy/lib/ufunclike.py +++ b/numpy/lib/ufunclike.py @@ -8,6 +8,7 @@ from __future__ import division, absolute_import, print_function __all__ = ['fix', 'isneginf', 'isposinf'] import numpy.core.numeric as nx +from numpy.core.overrides import array_function_dispatch import warnings import functools @@ -37,7 +38,30 @@ def _deprecate_out_named_y(f): return func +def _fix_out_named_y(f): + """ + Allow the out argument to be passed as the name `y` (deprecated) + + This decorator should only be used if _deprecate_out_named_y is used on + a corresponding dispatcher fucntion. + """ + @functools.wraps(f) + def func(x, out=None, **kwargs): + if 'y' in kwargs: + # we already did error checking in _deprecate_out_named_y + out = kwargs.pop('y') + return f(x, out=out, **kwargs) + + return func + + @_deprecate_out_named_y +def _dispatcher(x, out=None): + return (x, out) + + +@array_function_dispatch(_dispatcher, verify=False, module='numpy') +@_fix_out_named_y def fix(x, out=None): """ Round to nearest integer towards zero. @@ -83,7 +107,8 @@ def fix(x, out=None): return res -@_deprecate_out_named_y +@array_function_dispatch(_dispatcher, verify=False, module='numpy') +@_fix_out_named_y def isposinf(x, out=None): """ Test element-wise for positive infinity, return result as bool array. @@ -151,7 +176,8 @@ def isposinf(x, out=None): return nx.logical_and(is_inf, signbit, out) -@_deprecate_out_named_y +@array_function_dispatch(_dispatcher, verify=False, module='numpy') +@_fix_out_named_y def isneginf(x, out=None): """ Test element-wise for negative infinity, return result as bool array. diff --git a/numpy/linalg/linalg.py b/numpy/linalg/linalg.py index 59923f3c5..771481e8e 100644 --- a/numpy/linalg/linalg.py +++ b/numpy/linalg/linalg.py @@ -16,6 +16,7 @@ __all__ = ['matrix_power', 'solve', 'tensorsolve', 'tensorinv', 'inv', 'svd', 'eig', 'eigh', 'lstsq', 'norm', 'qr', 'cond', 'matrix_rank', 'LinAlgError', 'multi_dot'] +import functools import operator import warnings @@ -28,10 +29,15 @@ from numpy.core import ( swapaxes, divide, count_nonzero, isnan ) from numpy.core.multiarray import normalize_axis_index -from numpy.core.overrides import array_function_dispatch +from numpy.core import overrides from numpy.lib.twodim_base import triu, eye from numpy.linalg import lapack_lite, _umath_linalg + +array_function_dispatch = functools.partial( + overrides.array_function_dispatch, module='numpy.linalg') + + # For Python2/3 compatibility _N = b'N' _V = b'V' diff --git a/numpy/linalg/tests/test_linalg.py b/numpy/linalg/tests/test_linalg.py index 19e214e2d..905f3a549 100644 --- a/numpy/linalg/tests/test_linalg.py +++ b/numpy/linalg/tests/test_linalg.py @@ -1924,3 +1924,44 @@ class TestMultiDot(object): def test_too_few_input_arrays(self): assert_raises(ValueError, multi_dot, []) assert_raises(ValueError, multi_dot, [np.random.random((3, 3))]) + + +class TestTensorinv(object): + + @pytest.mark.parametrize("arr, ind", [ + (np.ones((4, 6, 8, 2)), 2), + (np.ones((3, 3, 2)), 1), + ]) + def test_non_square_handling(self, arr, ind): + with assert_raises(LinAlgError): + linalg.tensorinv(arr, ind=ind) + + @pytest.mark.parametrize("shape, ind", [ + # examples from docstring + ((4, 6, 8, 3), 2), + ((24, 8, 3), 1), + ]) + def test_tensorinv_shape(self, shape, ind): + a = np.eye(24) + a.shape = shape + ainv = linalg.tensorinv(a=a, ind=ind) + expected = a.shape[ind:] + a.shape[:ind] + actual = ainv.shape + assert_equal(actual, expected) + + @pytest.mark.parametrize("ind", [ + 0, -2, + ]) + def test_tensorinv_ind_limit(self, ind): + a = np.eye(24) + a.shape = (4, 6, 8, 3) + with assert_raises(ValueError): + linalg.tensorinv(a=a, ind=ind) + + def test_tensorinv_result(self): + # mimic a docstring example + a = np.eye(24) + a.shape = (24, 8, 3) + ainv = linalg.tensorinv(a, ind=1) + b = np.ones(24) + assert_allclose(np.tensordot(ainv, b, 1), np.linalg.tensorsolve(a, b)) diff --git a/numpy/ma/core.py b/numpy/ma/core.py index 85a830661..9ee44e9ff 100644 --- a/numpy/ma/core.py +++ b/numpy/ma/core.py @@ -446,6 +446,7 @@ def _check_fill_value(fill_value, ndtype): If fill_value is not None, its value is forced to the given dtype. The result is always a 0d array. + """ ndtype = np.dtype(ndtype) fields = ndtype.fields @@ -465,17 +466,19 @@ def _check_fill_value(fill_value, ndtype): dtype=ndtype) else: if isinstance(fill_value, basestring) and (ndtype.char not in 'OSVU'): + # Note this check doesn't work if fill_value is not a scalar err_msg = "Cannot set fill value of string with array of dtype %s" raise TypeError(err_msg % ndtype) else: # In case we want to convert 1e20 to int. + # Also in case of converting string arrays. try: fill_value = np.array(fill_value, copy=False, dtype=ndtype) - except OverflowError: - # Raise TypeError instead of OverflowError. OverflowError - # is seldom used, and the real problem here is that the - # passed fill_value is not compatible with the ndtype. - err_msg = "Fill value %s overflows dtype %s" + except (OverflowError, ValueError): + # Raise TypeError instead of OverflowError or ValueError. + # OverflowError is seldom used, and the real problem here is + # that the passed fill_value is not compatible with the ndtype. + err_msg = "Cannot convert fill_value %s to dtype %s" raise TypeError(err_msg % (fill_value, ndtype)) return np.array(fill_value) @@ -3008,11 +3011,13 @@ class MaskedArray(ndarray): except (TypeError, AttributeError): # When _mask.shape is not writable (because it's a void) pass - # Finalize the fill_value for structured arrays - if self.dtype.names is not None: - if self._fill_value is None: - self._fill_value = _check_fill_value(None, self.dtype) - return + + # Finalize the fill_value + if self._fill_value is not None: + self._fill_value = _check_fill_value(self._fill_value, self.dtype) + elif self.dtype.names is not None: + # Finalize the default fill_value for structured arrays + self._fill_value = _check_fill_value(None, self.dtype) def __array_wrap__(self, obj, context=None): """ @@ -4012,6 +4017,16 @@ class MaskedArray(ndarray): check = check.view(type(self)) check._update_from(self) check._mask = mask + + # Cast fill value to bool_ if needed. If it cannot be cast, the + # default boolean fill value is used. + if check._fill_value is not None: + try: + fill = _check_fill_value(check._fill_value, np.bool_) + except (TypeError, ValueError): + fill = _check_fill_value(None, np.bool_) + check._fill_value = fill + return check def __eq__(self, other): diff --git a/numpy/ma/tests/test_core.py b/numpy/ma/tests/test_core.py index aa7672daa..8a015e609 100644 --- a/numpy/ma/tests/test_core.py +++ b/numpy/ma/tests/test_core.py @@ -60,6 +60,11 @@ suppress_copy_mask_on_assignment.filter( "setting an item on a masked array which has a shared mask will not copy") +# For parametrized numeric testing +num_dts = [np.dtype(dt_) for dt_ in '?bhilqBHILQefdgFD'] +num_ids = [dt_.char for dt_ in num_dts] + + class TestMaskedArray(object): # Base test class for MaskedArrays. @@ -1415,23 +1420,34 @@ class TestMaskedArrayArithmetic(object): # Test the equality of structured arrays ndtype = [('A', int), ('B', int)] a = array([(1, 1), (2, 2)], mask=[(0, 1), (0, 0)], dtype=ndtype) + test = (a == a) assert_equal(test.data, [True, True]) assert_equal(test.mask, [False, False]) + assert_(test.fill_value == True) + test = (a == a[0]) assert_equal(test.data, [True, False]) assert_equal(test.mask, [False, False]) + assert_(test.fill_value == True) + b = array([(1, 1), (2, 2)], mask=[(1, 0), (0, 0)], dtype=ndtype) test = (a == b) assert_equal(test.data, [False, True]) assert_equal(test.mask, [True, False]) + assert_(test.fill_value == True) + test = (a[0] == b) assert_equal(test.data, [False, False]) assert_equal(test.mask, [True, False]) + assert_(test.fill_value == True) + b = array([(1, 1), (2, 2)], mask=[(0, 1), (1, 0)], dtype=ndtype) test = (a == b) assert_equal(test.data, [True, True]) assert_equal(test.mask, [False, False]) + assert_(test.fill_value == True) + # complicated dtype, 2-dimensional array. ndtype = [('A', int), ('B', [('BA', int), ('BB', int)])] a = array([[(1, (1, 1)), (2, (2, 2))], @@ -1441,28 +1457,40 @@ class TestMaskedArrayArithmetic(object): test = (a[0, 0] == a) assert_equal(test.data, [[True, False], [False, False]]) assert_equal(test.mask, [[False, False], [False, True]]) + assert_(test.fill_value == True) def test_ne_on_structured(self): # Test the equality of structured arrays ndtype = [('A', int), ('B', int)] a = array([(1, 1), (2, 2)], mask=[(0, 1), (0, 0)], dtype=ndtype) + test = (a != a) assert_equal(test.data, [False, False]) assert_equal(test.mask, [False, False]) + assert_(test.fill_value == True) + test = (a != a[0]) assert_equal(test.data, [False, True]) assert_equal(test.mask, [False, False]) + assert_(test.fill_value == True) + b = array([(1, 1), (2, 2)], mask=[(1, 0), (0, 0)], dtype=ndtype) test = (a != b) assert_equal(test.data, [True, False]) assert_equal(test.mask, [True, False]) + assert_(test.fill_value == True) + test = (a[0] != b) assert_equal(test.data, [True, True]) assert_equal(test.mask, [True, False]) + assert_(test.fill_value == True) + b = array([(1, 1), (2, 2)], mask=[(0, 1), (1, 0)], dtype=ndtype) test = (a != b) assert_equal(test.data, [False, False]) assert_equal(test.mask, [False, False]) + assert_(test.fill_value == True) + # complicated dtype, 2-dimensional array. ndtype = [('A', int), ('B', [('BA', int), ('BB', int)])] a = array([[(1, (1, 1)), (2, (2, 2))], @@ -1472,6 +1500,7 @@ class TestMaskedArrayArithmetic(object): test = (a[0, 0] != a) assert_equal(test.data, [[False, True], [True, True]]) assert_equal(test.mask, [[False, False], [False, True]]) + assert_(test.fill_value == True) def test_eq_ne_structured_extra(self): # ensure simple examples are symmetric and make sense. @@ -1507,6 +1536,120 @@ class TestMaskedArrayArithmetic(object): el_by_el = [m1[name] != m2[name] for name in dt.names] assert_equal(array(el_by_el, dtype=bool).any(), ne_expected) + @pytest.mark.parametrize('dt', ['S', 'U']) + @pytest.mark.parametrize('fill', [None, 'A']) + def test_eq_for_strings(self, dt, fill): + # Test the equality of structured arrays + a = array(['a', 'b'], dtype=dt, mask=[0, 1], fill_value=fill) + + test = (a == a) + assert_equal(test.data, [True, True]) + assert_equal(test.mask, [False, True]) + assert_(test.fill_value == True) + + test = (a == a[0]) + assert_equal(test.data, [True, False]) + assert_equal(test.mask, [False, True]) + assert_(test.fill_value == True) + + b = array(['a', 'b'], dtype=dt, mask=[1, 0], fill_value=fill) + test = (a == b) + assert_equal(test.data, [False, False]) + assert_equal(test.mask, [True, True]) + assert_(test.fill_value == True) + + # test = (a[0] == b) # doesn't work in Python2 + test = (b == a[0]) + assert_equal(test.data, [False, False]) + assert_equal(test.mask, [True, False]) + assert_(test.fill_value == True) + + @pytest.mark.parametrize('dt', ['S', 'U']) + @pytest.mark.parametrize('fill', [None, 'A']) + def test_ne_for_strings(self, dt, fill): + # Test the equality of structured arrays + a = array(['a', 'b'], dtype=dt, mask=[0, 1], fill_value=fill) + + test = (a != a) + assert_equal(test.data, [False, False]) + assert_equal(test.mask, [False, True]) + assert_(test.fill_value == True) + + test = (a != a[0]) + assert_equal(test.data, [False, True]) + assert_equal(test.mask, [False, True]) + assert_(test.fill_value == True) + + b = array(['a', 'b'], dtype=dt, mask=[1, 0], fill_value=fill) + test = (a != b) + assert_equal(test.data, [True, True]) + assert_equal(test.mask, [True, True]) + assert_(test.fill_value == True) + + # test = (a[0] != b) # doesn't work in Python2 + test = (b != a[0]) + assert_equal(test.data, [True, True]) + assert_equal(test.mask, [True, False]) + assert_(test.fill_value == True) + + @pytest.mark.parametrize('dt1', num_dts, ids=num_ids) + @pytest.mark.parametrize('dt2', num_dts, ids=num_ids) + @pytest.mark.parametrize('fill', [None, 1]) + def test_eq_for_numeric(self, dt1, dt2, fill): + # Test the equality of structured arrays + a = array([0, 1], dtype=dt1, mask=[0, 1], fill_value=fill) + + test = (a == a) + assert_equal(test.data, [True, True]) + assert_equal(test.mask, [False, True]) + assert_(test.fill_value == True) + + test = (a == a[0]) + assert_equal(test.data, [True, False]) + assert_equal(test.mask, [False, True]) + assert_(test.fill_value == True) + + b = array([0, 1], dtype=dt2, mask=[1, 0], fill_value=fill) + test = (a == b) + assert_equal(test.data, [False, False]) + assert_equal(test.mask, [True, True]) + assert_(test.fill_value == True) + + # test = (a[0] == b) # doesn't work in Python2 + test = (b == a[0]) + assert_equal(test.data, [False, False]) + assert_equal(test.mask, [True, False]) + assert_(test.fill_value == True) + + @pytest.mark.parametrize('dt1', num_dts, ids=num_ids) + @pytest.mark.parametrize('dt2', num_dts, ids=num_ids) + @pytest.mark.parametrize('fill', [None, 1]) + def test_ne_for_numeric(self, dt1, dt2, fill): + # Test the equality of structured arrays + a = array([0, 1], dtype=dt1, mask=[0, 1], fill_value=fill) + + test = (a != a) + assert_equal(test.data, [False, False]) + assert_equal(test.mask, [False, True]) + assert_(test.fill_value == True) + + test = (a != a[0]) + assert_equal(test.data, [False, True]) + assert_equal(test.mask, [False, True]) + assert_(test.fill_value == True) + + b = array([0, 1], dtype=dt2, mask=[1, 0], fill_value=fill) + test = (a != b) + assert_equal(test.data, [True, True]) + assert_equal(test.mask, [True, True]) + assert_(test.fill_value == True) + + # test = (a[0] != b) # doesn't work in Python2 + test = (b != a[0]) + assert_equal(test.data, [True, True]) + assert_equal(test.mask, [True, False]) + assert_(test.fill_value == True) + def test_eq_with_None(self): # Really, comparisons with None should not be done, but check them # anyway. Note that pep8 will flag these tests. @@ -4985,7 +5128,7 @@ def test_ufunc_with_out_varied(): assert_equal(res_pos.data, expected.data) -def test_astype(): +def test_astype_mask_ordering(): descr = [('v', int, 3), ('x', [('y', float)])] x = array([ [([1, 2, 3], (1.0,)), ([1, 2, 3], (2.0,))], @@ -5017,6 +5160,25 @@ def test_astype(): assert_(x_f2.mask.flags.f_contiguous) +@pytest.mark.parametrize('dt1', num_dts, ids=num_ids) +@pytest.mark.parametrize('dt2', num_dts, ids=num_ids) +@pytest.mark.filterwarnings('ignore::numpy.ComplexWarning') +def test_astype_basic(dt1, dt2): + # See gh-12070 + src = np.ma.array(ones(3, dt1), fill_value=1) + dst = src.astype(dt2) + + assert_(src.fill_value == 1) + assert_(src.dtype == dt1) + assert_(src.fill_value.dtype == dt1) + + assert_(dst.fill_value == 1) + assert_(dst.dtype == dt2) + assert_(dst.fill_value.dtype == dt2) + + assert_equal(src, dst) + + def test_fieldless_void(): dt = np.dtype([]) # a void dtype with no fields x = np.empty(4, dt) diff --git a/numpy/testing/_private/utils.py b/numpy/testing/_private/utils.py index a3832fcde..20a7dfd0b 100644 --- a/numpy/testing/_private/utils.py +++ b/numpy/testing/_private/utils.py @@ -19,7 +19,7 @@ from warnings import WarningMessage import pprint from numpy.core import( - float32, empty, arange, array_repr, ndarray, isnat, array) + bool_, float32, empty, arange, array_repr, ndarray, isnat, array) from numpy.lib.utils import deprecate if sys.version_info[0] >= 3: @@ -352,7 +352,7 @@ def assert_equal(actual, desired, err_msg='', verbose=True): # XXX: catch ValueError for subclasses of ndarray where iscomplex fail try: usecomplex = iscomplexobj(actual) or iscomplexobj(desired) - except ValueError: + except (ValueError, TypeError): usecomplex = False if usecomplex: @@ -692,6 +692,9 @@ def assert_array_compare(comparison, x, y, err_msg='', verbose=True, x = array(x, copy=False, subok=True) y = array(y, copy=False, subok=True) + # original array for output formating + ox, oy = x, y + def isnumber(x): return x.dtype.char in '?bhilqpBHILQPefdgFDG' @@ -705,15 +708,20 @@ def assert_array_compare(comparison, x, y, err_msg='', verbose=True, at the same locations. """ - # Both the != True comparison here and the cast to bool_ at the end are - # done to deal with `masked`, which cannot be compared usefully, and - # for which np.all yields masked. The use of the function np.all is - # for back compatibility with ndarray subclasses that changed the - # return values of the all method. We are not committed to supporting - # such subclasses, but some used to work. x_id = func(x) y_id = func(y) - if npall(x_id == y_id) != True: + # We include work-arounds here to handle three types of slightly + # pathological ndarray subclasses: + # (1) all() on `masked` array scalars can return masked arrays, so we + # use != True + # (2) __eq__ on some ndarray subclasses returns Python booleans + # instead of element-wise comparisons, so we cast to bool_() and + # use isinstance(..., bool) checks + # (3) subclasses with bare-bones __array_function__ implemenations may + # not implement np.all(), so favor using the .all() method + # We are not committed to supporting such subclasses, but it's nice to + # support them if possible. + if bool_(x_id == y_id).all() != True: msg = build_err_msg([x, y], err_msg + '\nx and y %s location mismatch:' % (hasval), verbose=verbose, header=header, @@ -721,9 +729,9 @@ def assert_array_compare(comparison, x, y, err_msg='', verbose=True, raise AssertionError(msg) # If there is a scalar, then here we know the array has the same # flag as it everywhere, so we should return the scalar flag. - if x_id.ndim == 0: + if isinstance(x_id, bool) or x_id.ndim == 0: return bool_(x_id) - elif y_id.ndim == 0: + elif isinstance(x_id, bool) or y_id.ndim == 0: return bool_(y_id) else: return y_id @@ -780,10 +788,10 @@ def assert_array_compare(comparison, x, y, err_msg='', verbose=True, # do not trigger a failure (np.ma.masked != True evaluates as # np.ma.masked, which is falsy). if cond != True: - match = 100-100.0*reduced.count(1)/len(reduced) - msg = build_err_msg([x, y], + mismatch = 100.0 * reduced.count(0) / ox.size + msg = build_err_msg([ox, oy], err_msg - + '\n(mismatch %s%%)' % (match,), + + '\n(mismatch %s%%)' % (mismatch,), verbose=verbose, header=header, names=('x', 'y'), precision=precision) raise AssertionError(msg) diff --git a/numpy/testing/tests/test_utils.py b/numpy/testing/tests/test_utils.py index e0d3414f7..e54fbc390 100644 --- a/numpy/testing/tests/test_utils.py +++ b/numpy/testing/tests/test_utils.py @@ -158,6 +158,44 @@ class TestArrayEqual(_GenericTest): self._test_equal(a, b) self._test_equal(b, a) + def test_subclass_that_overrides_eq(self): + # While we cannot guarantee testing functions will always work for + # subclasses, the tests should ideally rely only on subclasses having + # comparison operators, not on them being able to store booleans + # (which, e.g., astropy Quantity cannot usefully do). See gh-8452. + class MyArray(np.ndarray): + def __eq__(self, other): + return bool(np.equal(self, other).all()) + + def __ne__(self, other): + return not self == other + + a = np.array([1., 2.]).view(MyArray) + b = np.array([2., 3.]).view(MyArray) + assert_(type(a == a), bool) + assert_(a == a) + assert_(a != b) + self._test_equal(a, a) + self._test_not_equal(a, b) + self._test_not_equal(b, a) + + def test_subclass_that_does_not_implement_npall(self): + # While we cannot guarantee testing functions will always work for + # subclasses, the tests should ideally rely only on subclasses having + # comparison operators, not on them being able to store booleans + # (which, e.g., astropy Quantity cannot usefully do). See gh-8452. + class MyArray(np.ndarray): + def __array_function__(self, *args, **kwargs): + return NotImplemented + + a = np.array([1., 2.]).view(MyArray) + b = np.array([2., 3.]).view(MyArray) + with assert_raises(TypeError): + np.all(a) + self._test_equal(a, a) + self._test_not_equal(a, b) + self._test_not_equal(b, a) + class TestBuildErrorMessage(object): @@ -469,7 +507,8 @@ class TestAlmostEqual(_GenericTest): self._test_not_equal(x, z) def test_error_message(self): - """Check the message is formatted correctly for the decimal value""" + """Check the message is formatted correctly for the decimal value. + Also check the message when input includes inf or nan (gh12200)""" x = np.array([1.00000000001, 2.00000000002, 3.00003]) y = np.array([1.00000000002, 2.00000000003, 3.00004]) @@ -493,6 +532,19 @@ class TestAlmostEqual(_GenericTest): # remove anything that's not the array string assert_equal(str(e).split('%)\n ')[1], b) + # Check the error message when input includes inf or nan + x = np.array([np.inf, 0]) + y = np.array([np.inf, 1]) + try: + self._assert_func(x, y) + except AssertionError as e: + msgs = str(e).split('\n') + # assert error percentage is 50% + assert_equal(msgs[3], '(mismatch 50.0%)') + # assert output array contains inf + assert_equal(msgs[4], ' x: array([inf, 0.])') + assert_equal(msgs[5], ' y: array([inf, 1.])') + def test_subclass_that_cannot_be_bool(self): # While we cannot guarantee testing functions will always work for # subclasses, the tests should ideally rely only on subclasses having @@ -1077,7 +1129,7 @@ class TestStringEqual(object): assert_raises(AssertionError, lambda: assert_string_equal("foo", "hello")) - + def test_regex(self): assert_string_equal("a+*b", "a+*b") diff --git a/tools/travis-test.sh b/tools/travis-test.sh index 2a16b37a3..3b56f1162 100755 --- a/tools/travis-test.sh +++ b/tools/travis-test.sh @@ -101,8 +101,8 @@ setup_chroot() # install needed packages sudo chroot $DIR bash -c "apt-get install -qq -y \ - libatlas-base-dev gfortran python-dev python-nose python-pip cython \ - python-pytest" + libatlas-base-dev gfortran python3-dev python3-pip \ + cython python3-pytest" } run_test() @@ -112,7 +112,7 @@ run_test() fi if [ -n "$RUN_COVERAGE" ]; then - pip install pytest-cov + $PIP install pytest-cov COVERAGE_FLAG=--coverage fi @@ -191,11 +191,11 @@ if [ -n "$USE_WHEEL" ] && [ $# -eq 0 ]; then . venv-for-wheel/bin/activate # Move out of source directory to avoid finding local numpy pushd dist - pip install --pre --no-index --upgrade --find-links=. numpy - pip install nose pytest + $PIP install --pre --no-index --upgrade --find-links=. numpy + $PIP install nose pytest if [ -n "$INSTALL_PICKLE5" ]; then - pip install pickle5 + $PIP install pickle5 fi popd @@ -215,10 +215,10 @@ elif [ -n "$USE_SDIST" ] && [ $# -eq 0 ]; then . venv-for-wheel/bin/activate # Move out of source directory to avoid finding local numpy pushd dist - pip install numpy* - pip install nose pytest + $PIP install numpy* + $PIP install nose pytest if [ -n "$INSTALL_PICKLE5" ]; then - pip install pickle5 + $PIP install pickle5 fi popd @@ -229,9 +229,9 @@ elif [ -n "$USE_CHROOT" ] && [ $# -eq 0 ]; then # the chroot'ed environment will not have the current locale, # avoid any warnings which may disturb testing export LANG=C LC_ALL=C - # run again in chroot with this time testing + # run again in chroot with this time testing with python3 sudo linux32 chroot $DIR bash -c \ - "cd numpy && PYTHON=python PIP=pip IN_CHROOT=1 $0 test" + "cd numpy && PYTHON=python3 PIP=pip3 IN_CHROOT=1 $0 test" else setup_base run_test |
