diff options
Diffstat (limited to 'numpy/lib/npyio.py')
| -rw-r--r-- | numpy/lib/npyio.py | 68 |
1 files changed, 36 insertions, 32 deletions
diff --git a/numpy/lib/npyio.py b/numpy/lib/npyio.py index 096f1a3a4..b109d65e1 100644 --- a/numpy/lib/npyio.py +++ b/numpy/lib/npyio.py @@ -475,9 +475,7 @@ def save(file, arr, allow_pickle=True, fix_imports=True): Notes ----- - For a description of the ``.npy`` format, see the module docstring - of `numpy.lib.format` or the NumPy Enhancement Proposal - http://numpy.github.io/neps/npy-format.html + For a description of the ``.npy`` format, see :py:mod:`numpy.lib.format`. Examples -------- @@ -561,9 +559,7 @@ def savez(file, *args, **kwds): The ``.npz`` file format is a zipped archive of files named after the variables they contain. The archive is not compressed and each file in the archive contains one variable in ``.npy`` format. For a - description of the ``.npy`` format, see `numpy.lib.format` or the - NumPy Enhancement Proposal - http://numpy.github.io/neps/npy-format.html + description of the ``.npy`` format, see :py:mod:`numpy.lib.format`. When opening the saved ``.npz`` file with `load` a `NpzFile` object is returned. This is a dictionary-like object which can be queried for @@ -642,9 +638,9 @@ def savez_compressed(file, *args, **kwds): The ``.npz`` file format is a zipped archive of files named after the variables they contain. The archive is compressed with ``zipfile.ZIP_DEFLATED`` and each file in the archive contains one variable - in ``.npy`` format. For a description of the ``.npy`` format, see - `numpy.lib.format` or the NumPy Enhancement Proposal - http://numpy.github.io/neps/npy-format.html + in ``.npy`` format. For a description of the ``.npy`` format, see + :py:mod:`numpy.lib.format`. + When opening the saved ``.npz`` file with `load` a `NpzFile` object is returned. This is a dictionary-like object which can be queried for @@ -758,7 +754,7 @@ def _getconv(dtype): elif issubclass(typ, np.floating): return floatconv elif issubclass(typ, complex): - return lambda x: complex(asstr(x)) + return lambda x: complex(asstr(x).replace('+-', '-')) elif issubclass(typ, np.bytes_): return asbytes elif issubclass(typ, np.unicode_): @@ -791,8 +787,8 @@ def loadtxt(fname, dtype=float, comments='#', delimiter=None, the data-type. comments : str or sequence of str, optional The characters or list of characters used to indicate the start of a - comment. For backwards compatibility, byte strings will be decoded as - 'latin1'. The default is '#'. + comment. None implies no comments. For backwards compatibility, byte + strings will be decoded as 'latin1'. The default is '#'. delimiter : str, optional The string used to separate values. For backwards compatibility, byte strings will be decoded as 'latin1'. The default is whitespace. @@ -859,18 +855,18 @@ def loadtxt(fname, dtype=float, comments='#', delimiter=None, Examples -------- >>> from io import StringIO # StringIO behaves like a file object - >>> c = StringIO("0 1\\n2 3") + >>> c = StringIO(u"0 1\\n2 3") >>> np.loadtxt(c) array([[ 0., 1.], [ 2., 3.]]) - >>> d = StringIO("M 21 72\\nF 35 58") + >>> d = StringIO(u"M 21 72\\nF 35 58") >>> np.loadtxt(d, dtype={'names': ('gender', 'age', 'weight'), ... 'formats': ('S1', 'i4', 'f4')}) array([('M', 21, 72.0), ('F', 35, 58.0)], dtype=[('gender', '|S1'), ('age', '<i4'), ('weight', '<f4')]) - >>> c = StringIO("1,0,2\\n3,0,4") + >>> c = StringIO(u"1,0,2\\n3,0,4") >>> x, y = np.loadtxt(c, delimiter=',', usecols=(0, 2), unpack=True) >>> x array([ 1., 3.]) @@ -936,7 +932,7 @@ def loadtxt(fname, dtype=float, comments='#', delimiter=None, if encoding is not None: fencoding = encoding # we must assume local encoding - # TOOD emit portability warning? + # TODO emit portability warning? elif fencoding is None: import locale fencoding = locale.getpreferredencoding() @@ -1104,11 +1100,16 @@ def loadtxt(fname, dtype=float, comments='#', delimiter=None, nshape = list(X.shape) pos = nshape[0] nshape[0] += len(x) - X.resize(nshape) + X.resize(nshape, refcheck=False) X[pos:, ...] = x finally: if fown: fh.close() + # recursive closures have a cyclic reference to themselves, which + # requires gc to collect (gh-10620). To avoid this problem, for + # performance and PyPy friendliness, we break the cycle: + flatten_dtype_internal = None + pack_items = None if X is None: X = np.array([], dtype) @@ -1161,13 +1162,14 @@ def savetxt(fname, X, fmt='%.18e', delimiter=' ', newline='\n', header='', multi-format string, e.g. 'Iteration %d -- %10.5f', in which case `delimiter` is ignored. For complex `X`, the legal options for `fmt` are: - a) a single specifier, `fmt='%.4e'`, resulting in numbers formatted - like `' (%s+%sj)' % (fmt, fmt)` - b) a full string specifying every real and imaginary part, e.g. - `' %.4e %+.4ej %.4e %+.4ej %.4e %+.4ej'` for 3 columns - c) a list of specifiers, one per column - in this case, the real - and imaginary part must have separate specifiers, - e.g. `['%.3e + %.3ej', '(%.15e%+.15ej)']` for 2 columns + + * a single specifier, `fmt='%.4e'`, resulting in numbers formatted + like `' (%s+%sj)' % (fmt, fmt)` + * a full string specifying every real and imaginary part, e.g. + `' %.4e %+.4ej %.4e %+.4ej %.4e %+.4ej'` for 3 columns + * a list of specifiers, one per column - in this case, the real + and imaginary part must have separate specifiers, + e.g. `['%.3e + %.3ej', '(%.15e%+.15ej)']` for 2 columns delimiter : str, optional String or character separating columns. newline : str, optional @@ -1372,7 +1374,8 @@ def savetxt(fname, X, fmt='%.18e', delimiter=' ', newline='\n', header='', for number in row: row2.append(number.real) row2.append(number.imag) - fh.write(format % tuple(row2) + newline) + s = format % tuple(row2) + newline + fh.write(s.replace('+-', '-')) else: for row in X: try: @@ -1460,9 +1463,9 @@ def fromregex(file, regexp, dtype, encoding=None): dtype = np.dtype(dtype) content = file.read() - if isinstance(content, bytes) and not isinstance(regexp, bytes): + if isinstance(content, bytes) and isinstance(regexp, np.unicode): regexp = asbytes(regexp) - elif not isinstance(content, bytes) and isinstance(regexp, bytes): + elif isinstance(content, np.unicode) and isinstance(regexp, bytes): regexp = asstr(regexp) if not hasattr(regexp, 'match'): @@ -1625,7 +1628,7 @@ def genfromtxt(fname, dtype=float, comments='#', delimiter=None, Comma delimited file with mixed dtype - >>> s = StringIO("1,1.3,abcde") + >>> s = StringIO(u"1,1.3,abcde") >>> data = np.genfromtxt(s, dtype=[('myint','i8'),('myfloat','f8'), ... ('mystring','S5')], delimiter=",") >>> data @@ -1652,7 +1655,7 @@ def genfromtxt(fname, dtype=float, comments='#', delimiter=None, An example with fixed-width columns - >>> s = StringIO("11.3abcde") + >>> s = StringIO(u"11.3abcde") >>> data = np.genfromtxt(s, dtype=None, names=['intvar','fltvar','strvar'], ... delimiter=[1,3,5]) >>> data @@ -1714,7 +1717,7 @@ def genfromtxt(fname, dtype=float, comments='#', delimiter=None, try: while not first_values: first_line = _decode_line(next(fhd), encoding) - if names is True: + if (names is True) and (comments is not None): if comments in first_line: first_line = ( ''.join(first_line.split(comments)[1:])) @@ -1728,8 +1731,9 @@ def genfromtxt(fname, dtype=float, comments='#', delimiter=None, # Should we take the first values as names ? if names is True: fval = first_values[0].strip() - if fval in comments: - del first_values[0] + if comments is not None: + if fval in comments: + del first_values[0] # Check the columns to use: make sure `usecols` is a list if usecols is not None: |