diff options
Diffstat (limited to 'numpy/lib/npyio.py')
| -rw-r--r-- | numpy/lib/npyio.py | 80 |
1 files changed, 52 insertions, 28 deletions
diff --git a/numpy/lib/npyio.py b/numpy/lib/npyio.py index af259cfef..42a539f78 100644 --- a/numpy/lib/npyio.py +++ b/numpy/lib/npyio.py @@ -285,21 +285,22 @@ def load(file, mmap_mode=None): Parameters ---------- file : file-like object or string - The file to read. It must support ``seek()`` and ``read()`` methods. - If the filename extension is ``.gz``, the file is first decompressed. + The file to read. File-like objects must support the + ``seek()`` and ``read()`` methods. Pickled files require that the + file-like object support the ``readline()`` method as well. mmap_mode : {None, 'r+', 'r', 'w+', 'c'}, optional - If not None, then memory-map the file, using the given mode - (see `numpy.memmap` for a detailed description of the modes). - A memory-mapped array is kept on disk. However, it can be accessed - and sliced like any ndarray. Memory mapping is especially useful for - accessing small fragments of large files without reading the entire - file into memory. + If not None, then memory-map the file, using the given mode (see + `numpy.memmap` for a detailed description of the modes). A + memory-mapped array is kept on disk. However, it can be accessed + and sliced like any ndarray. Memory mapping is especially useful + for accessing small fragments of large files without reading the + entire file into memory. Returns ------- result : array, tuple, dict, etc. - Data stored in the file. For ``.npz`` files, the returned instance of - NpzFile class must be closed to avoid leaking file descriptors. + Data stored in the file. For ``.npz`` files, the returned instance + of NpzFile class must be closed to avoid leaking file descriptors. Raises ------ @@ -308,7 +309,7 @@ def load(file, mmap_mode=None): See Also -------- - save, savez, loadtxt + save, savez, savez_compressed, loadtxt memmap : Create a memory-map to an array stored in a file on disk. Notes @@ -319,13 +320,14 @@ def load(file, mmap_mode=None): - If the file is a ``.npz`` file, then a dictionary-like object is returned, containing ``{filename: array}`` key-value pairs, one for each file in the archive. - - If the file is a ``.npz`` file, the returned value supports the context - manager protocol in a similar fashion to the open function:: + - If the file is a ``.npz`` file, the returned value supports the + context manager protocol in a similar fashion to the open function:: with load('foo.npz') as data: a = data['a'] - The underlying file descriptor is closed when exiting the 'with' block. + The underlying file descriptor is closed when exiting the 'with' + block. Examples -------- @@ -549,6 +551,7 @@ def savez_compressed(file, *args, **kwds): See Also -------- numpy.savez : Save several arrays into an uncompressed ``.npz`` file format + numpy.load : Load the files created by savez_compressed. """ _savez(file, args, kwds, True) @@ -668,6 +671,7 @@ def loadtxt(fname, dtype=float, comments='#', delimiter=None, The returned array will have at least `ndmin` dimensions. Otherwise mono-dimensional axes will be squeezed. Legal values: 0 (default), 1 or 2. + .. versionadded:: 1.6.0 Returns @@ -840,6 +844,11 @@ def loadtxt(fname, dtype=float, comments='#', delimiter=None, continue if usecols: vals = [vals[i] for i in usecols] + if len(vals) != N: + line_num = i + skiprows + 1 + raise ValueError("Wrong number of columns at line %d" + % line_num) + # Convert each value according to its column and store items = [conv(val) for (conv, val) in zip(converters, vals)] # Then pack it according to the dtype's nesting @@ -906,22 +915,26 @@ def savetxt(fname, X, fmt='%.18e', delimiter=' ', newline='\n', header='', and imaginary part must have separate specifiers, e.g. `['%.3e + %.3ej', '(%.15e%+.15ej)']` for 2 columns delimiter : str, optional - Character separating columns. + String or character separating columns. newline : str, optional + String or character separating lines. + .. versionadded:: 1.5.0 header : str, optional String that will be written at the beginning of the file. + .. versionadded:: 1.7.0 footer : str, optional String that will be written at the end of the file. + .. versionadded:: 1.7.0 comments : str, optional String that will be prepended to the ``header`` and ``footer`` strings, to mark them as comments. Default: '# ', as expected by e.g. ``numpy.loadtxt``. + .. versionadded:: 1.7.0 - Character separating lines. See Also -------- @@ -1191,14 +1204,20 @@ def genfromtxt(fname, dtype=float, comments='#', delimiter=None, The string used to separate values. By default, any consecutive whitespaces act as delimiter. An integer or sequence of integers can also be provided as width(s) of each field. + skip_rows : int, optional + `skip_rows` was deprecated in numpy 1.5, and will be removed in + numpy 2.0. Please use `skip_header` instead. skip_header : int, optional - The numbers of lines to skip at the beginning of the file. + The number of lines to skip at the beginning of the file. skip_footer : int, optional - The numbers of lines to skip at the end of the file + The number of lines to skip at the end of the file. converters : variable, optional The set of functions that convert the data of a column to a value. The converters can also be used to provide a default value for missing data: ``converters = {3: lambda s: float(s or 0)}``. + missing : variable, optional + `missing` was deprecated in numpy 1.5, and will be removed in + numpy 2.0. Please use `missing_values` instead. missing_values : variable, optional The set of strings corresponding to missing data. filling_values : variable, optional @@ -1236,6 +1255,8 @@ def genfromtxt(fname, dtype=float, comments='#', delimiter=None, usemask : bool, optional If True, return a masked array. If False, return a regular array. + loose : bool, optional + If True, do not raise errors for invalid values. invalid_raise : bool, optional If True, an exception is raised if an inconsistency is detected in the number of columns. @@ -1840,7 +1861,7 @@ def recfromtxt(fname, **kwargs): array will be determined from the data. """ - kwargs.update(dtype=kwargs.get('dtype', None)) + kwargs.setdefault("dtype", None) usemask = kwargs.get('usemask', False) output = genfromtxt(fname, **kwargs) if usemask: @@ -1867,17 +1888,20 @@ def recfromcsv(fname, **kwargs): -------- numpy.genfromtxt : generic function to load ASCII data. + Notes + ----- + By default, `dtype` is None, which means that the data-type of the output + array will be determined from the data. + """ - case_sensitive = kwargs.get('case_sensitive', "lower") or "lower" - names = kwargs.get('names', True) - if names is None: - names = True - kwargs.update(dtype=kwargs.get('update', None), - delimiter=kwargs.get('delimiter', ",") or ",", - names=names, - case_sensitive=case_sensitive) - usemask = kwargs.get("usemask", False) + # Set default kwargs for genfromtxt as relevant to csv import. + kwargs.setdefault("case_sensitive", "lower") + kwargs.setdefault("names", True) + kwargs.setdefault("delimiter", ",") + kwargs.setdefault("dtype", None) output = genfromtxt(fname, **kwargs) + + usemask = kwargs.get("usemask", False) if usemask: from numpy.ma.mrecords import MaskedRecords output = output.view(MaskedRecords) |