def _dump(self, file, protocol=2):
if hasattr(file, "write"):
ctx = contextlib_nullcontext(file)
else:
ctx = open(os_fspath(file), "wb")
with ctx as f:
pickle.dump(self, f, protocol=protocol)
def __new__(subtype,
filename,
dtype=uint8,
mode='r+',
offset=0,
shape=None,
order='C'):
# Import here to minimize 'import numpy' overhead
import mmap
import os.path
try:
mode = mode_equivalents[mode]
except KeyError as e:
if mode not in valid_filemodes:
raise ValueError("mode must be one of {!r} (got {!r})".format(
valid_filemodes + list(mode_equivalents.keys()),
mode)) from None
if mode == 'w+' and shape is None:
raise ValueError("shape must be given")
if hasattr(filename, 'read'):
f_ctx = contextlib_nullcontext(filename)
else:
f_ctx = open(os_fspath(filename),
('r' if mode == 'c' else mode) + 'b')
with f_ctx as fid:
fid.seek(0, 2)
flen = fid.tell()
descr = dtypedescr(dtype)
_dbytes = descr.itemsize
if shape is None:
bytes = flen - offset
if bytes % _dbytes:
raise ValueError("Size of available data is not a "
"multiple of the data-type size.")
size = bytes // _dbytes
shape = (size, )
else:
if not isinstance(shape, tuple):
shape = (shape, )
size = np.intp(
1) # avoid default choice of np.int_, which might overflow
for k in shape:
size *= k
bytes = int(offset + size * _dbytes)
if mode in ('w+', 'r+') and flen < bytes:
fid.seek(bytes - 1, 0)
fid.write(b'\0')
fid.flush()
if mode == 'c':
acc = mmap.ACCESS_COPY
elif mode == 'r':
acc = mmap.ACCESS_READ
else:
acc = mmap.ACCESS_WRITE
start = offset - offset % mmap.ALLOCATIONGRANULARITY
bytes -= start
array_offset = offset - start
mm = mmap.mmap(fid.fileno(), bytes, access=acc, offset=start)
self = ndarray.__new__(subtype,
shape,
dtype=descr,
buffer=mm,
offset=array_offset,
order=order)
self._mmap = mm
self.offset = offset
self.mode = mode
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()
elif hasattr(fid, "name") and isinstance(fid.name, str):
# 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
return self
def __new__(subtype, filename, dtype=uint8, mode='r+', offset=0,
shape=None, order='C'):
# Import here to minimize 'import numpy' overhead
import mmap
import os.path
try:
mode = mode_equivalents[mode]
except KeyError:
if mode not in valid_filemodes:
raise ValueError("mode must be one of %s" %
(valid_filemodes + list(mode_equivalents.keys())))
if mode == 'w+' and shape is None:
raise ValueError("shape must be given")
if hasattr(filename, 'read'):
f_ctx = contextlib_nullcontext(filename)
else:
f_ctx = open(os_fspath(filename), ('r' if mode == 'c' else mode)+'b')
with f_ctx as fid:
fid.seek(0, 2)
flen = fid.tell()
descr = dtypedescr(dtype)
_dbytes = descr.itemsize
if shape is None:
bytes = flen - offset
if bytes % _dbytes:
raise ValueError("Size of available data is not a "
"multiple of the data-type size.")
size = bytes // _dbytes
shape = (size,)
else:
if not isinstance(shape, tuple):
shape = (shape,)
size = np.intp(1) # avoid default choice of np.int_, which might overflow
for k in shape:
size *= k
bytes = long(offset + size*_dbytes)
if mode == 'w+' or (mode == 'r+' and flen < bytes):
fid.seek(bytes - 1, 0)
fid.write(b'\0')
fid.flush()
if mode == 'c':
acc = mmap.ACCESS_COPY
elif mode == 'r':
acc = mmap.ACCESS_READ
else:
acc = mmap.ACCESS_WRITE
start = offset - offset % mmap.ALLOCATIONGRANULARITY
bytes -= start
array_offset = offset - start
mm = mmap.mmap(fid.fileno(), bytes, access=acc, offset=start)
self = ndarray.__new__(subtype, shape, dtype=descr, buffer=mm,
offset=array_offset, order=order)
self._mmap = mm
self.offset = offset
self.mode = mode
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()
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
return self
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
Parameters
----------
fd : str or file type
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).
dtype : data-type, optional
valid dtype for all arrays
shape : int or tuple of ints, optional
shape of each array.
offset : int, optional
Position in the file to start reading from.
formats, names, titles, aligned, byteorder :
If `dtype` is ``None``, these arguments are passed to
`numpy.format_parser` to construct a dtype. See that function for
detailed documentation
Returns
-------
np.recarray
record array consisting of data enclosed in file.
Examples
--------
>>> from tempfile import TemporaryFile
>>> a = np.empty(10,dtype='f8,i4,a5')
>>> a[5] = (0.5,10,'abcde')
>>>
>>> fd=TemporaryFile()
>>> a = a.newbyteorder('<')
>>> a.tofile(fd)
>>>
>>> _ = fd.seek(0)
>>> r=np.core.records.fromfile(fd, formats='f8,i4,a5', shape=10,
... byteorder='<')
>>> print(r[5])
(0.5, 10, 'abcde')
>>> r.shape
(10,)
"""
if dtype is None and formats is None:
raise TypeError("fromfile() needs a 'dtype' or 'formats' argument")
# NumPy 1.19.0, 2020-01-01
shape = _deprecate_shape_0_as_None(shape)
if shape is None:
shape = (-1, )
elif isinstance(shape, int):
shape = (shape, )
if hasattr(fd, 'readinto'):
# GH issue 2504. fd supports io.RawIOBase or io.BufferedIOBase interface.
# Example of fd: gzip, BytesIO, BufferedReader
# file already opened
ctx = contextlib_nullcontext(fd)
else:
# open file
ctx = open(os_fspath(fd), 'rb')
with ctx as fd:
if offset > 0:
fd.seek(offset, 1)
size = get_remaining_size(fd)
if dtype is not None:
descr = sb.dtype(dtype)
else:
descr = format_parser(formats, names, titles, aligned,
byteorder).dtype
itemsize = descr.itemsize
shapeprod = sb.array(shape).prod(dtype=nt.intp)
shapesize = shapeprod * itemsize
if shapesize < 0:
shape = list(shape)
shape[shape.index(-1)] = size // -shapesize
shape = tuple(shape)
shapeprod = sb.array(shape).prod(dtype=nt.intp)
nbytes = shapeprod * itemsize
if nbytes > size:
raise ValueError(
"Not enough bytes left in file for specified shape and type")
# create the array
_array = recarray(shape, descr)
nbytesread = fd.readinto(_array.data)
if nbytesread != nbytes:
raise IOError("Didn't read as many bytes as expected")
return _array
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 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')
>>> a[5] = (0.5,10,'abcde')
>>>
>>> fd=TemporaryFile()
>>> a = a.newbyteorder('<')
>>> a.tofile(fd)
>>>
>>> _ = fd.seek(0)
>>> r=np.core.records.fromfile(fd, formats='f8,i4,a5', shape=10,
... byteorder='<')
>>> print(r[5])
(0.5, 10, 'abcde')
>>> r.shape
(10,)
"""
if dtype is None and formats is None:
raise TypeError("fromfile() needs a 'dtype' or 'formats' argument")
# NumPy 1.19.0, 2020-01-01
shape = _deprecate_shape_0_as_None(shape)
if shape is None:
shape = (-1,)
elif isinstance(shape, (int, long)):
shape = (shape,)
if isfileobj(fd):
# file already opened
ctx = contextlib_nullcontext(fd)
else:
# open file
ctx = open(os_fspath(fd), 'rb')
with ctx as fd:
if (offset > 0):
fd.seek(offset, 1)
size = get_remaining_size(fd)
if dtype is not None:
descr = sb.dtype(dtype)
else:
descr = format_parser(formats, names, titles, aligned, byteorder)._descr
itemsize = descr.itemsize
shapeprod = sb.array(shape).prod(dtype=nt.intp)
shapesize = shapeprod * itemsize
if shapesize < 0:
shape = list(shape)
shape[shape.index(-1)] = size // -shapesize
shape = tuple(shape)
shapeprod = sb.array(shape).prod(dtype=nt.intp)
nbytes = shapeprod * itemsize
if nbytes > size:
raise ValueError(
"Not enough bytes left in file for specified shape and type")
# create the array
_array = recarray(shape, descr)
nbytesread = fd.readinto(_array.data)
if nbytesread != nbytes:
raise IOError("Didn't read as many bytes as expected")
return _array
def save_np_arrays(outfile, outdict):
from numpy.compat import contextlib_nullcontext
with contextlib_nullcontext(outfile) as f:
np.savez_compressed(f, **outdict)
