298 lines
9.7 KiB
Python
298 lines
9.7 KiB
Python
"""Compatibility fixes for older version of python, numpy and scipy
|
|
|
|
If you add content to this file, please give the version of the package
|
|
at which the fixe is no longer needed.
|
|
"""
|
|
# Authors: Emmanuelle Gouillart <emmanuelle.gouillart@normalesup.org>
|
|
# Gael Varoquaux <gael.varoquaux@normalesup.org>
|
|
# Fabian Pedregosa <fpedregosa@acm.org>
|
|
# Lars Buitinck
|
|
#
|
|
# License: BSD 3 clause
|
|
|
|
import warnings
|
|
import os
|
|
import errno
|
|
|
|
import numpy as np
|
|
import scipy.sparse as sp
|
|
import scipy
|
|
|
|
try:
|
|
from inspect import signature
|
|
except ImportError:
|
|
from ..externals.funcsigs import signature
|
|
|
|
|
|
def _parse_version(version_string):
|
|
version = []
|
|
for x in version_string.split('.'):
|
|
try:
|
|
version.append(int(x))
|
|
except ValueError:
|
|
# x may be of the form dev-1ea1592
|
|
version.append(x)
|
|
return tuple(version)
|
|
|
|
|
|
euler_gamma = getattr(np, 'euler_gamma',
|
|
0.577215664901532860606512090082402431)
|
|
|
|
np_version = _parse_version(np.__version__)
|
|
sp_version = _parse_version(scipy.__version__)
|
|
|
|
|
|
# Remove when minimum required NumPy >= 1.10
|
|
try:
|
|
if (not np.allclose(np.divide(.4, 1, casting="unsafe"),
|
|
np.divide(.4, 1, casting="unsafe", dtype=np.float64))
|
|
or not np.allclose(np.divide(.4, 1), .4)):
|
|
raise TypeError('Divide not working with dtype: '
|
|
'https://github.com/numpy/numpy/issues/3484')
|
|
divide = np.divide
|
|
|
|
except TypeError:
|
|
# Compat for old versions of np.divide that do not provide support for
|
|
# the dtype args
|
|
def divide(x1, x2, out=None, dtype=None):
|
|
out_orig = out
|
|
if out is None:
|
|
out = np.asarray(x1, dtype=dtype)
|
|
if out is x1:
|
|
out = x1.copy()
|
|
else:
|
|
if out is not x1:
|
|
out[:] = x1
|
|
if dtype is not None and out.dtype != dtype:
|
|
out = out.astype(dtype)
|
|
out /= x2
|
|
if out_orig is None and np.isscalar(x1):
|
|
out = np.asscalar(out)
|
|
return out
|
|
|
|
|
|
try:
|
|
with warnings.catch_warnings(record=True):
|
|
# Don't raise the numpy deprecation warnings that appear in
|
|
# 1.9, but avoid Python bug due to simplefilter('ignore')
|
|
warnings.simplefilter('always')
|
|
sp.csr_matrix([1.0, 2.0, 3.0]).max(axis=0)
|
|
except (TypeError, AttributeError):
|
|
# in scipy < 14.0, sparse matrix min/max doesn't accept an `axis` argument
|
|
# the following code is taken from the scipy 0.14 codebase
|
|
|
|
def _minor_reduce(X, ufunc):
|
|
major_index = np.flatnonzero(np.diff(X.indptr))
|
|
value = ufunc.reduceat(X.data, X.indptr[major_index])
|
|
return major_index, value
|
|
|
|
def _min_or_max_axis(X, axis, min_or_max):
|
|
N = X.shape[axis]
|
|
if N == 0:
|
|
raise ValueError("zero-size array to reduction operation")
|
|
M = X.shape[1 - axis]
|
|
mat = X.tocsc() if axis == 0 else X.tocsr()
|
|
mat.sum_duplicates()
|
|
major_index, value = _minor_reduce(mat, min_or_max)
|
|
not_full = np.diff(mat.indptr)[major_index] < N
|
|
value[not_full] = min_or_max(value[not_full], 0)
|
|
mask = value != 0
|
|
major_index = np.compress(mask, major_index)
|
|
value = np.compress(mask, value)
|
|
|
|
from scipy.sparse import coo_matrix
|
|
if axis == 0:
|
|
res = coo_matrix((value, (np.zeros(len(value)), major_index)),
|
|
dtype=X.dtype, shape=(1, M))
|
|
else:
|
|
res = coo_matrix((value, (major_index, np.zeros(len(value)))),
|
|
dtype=X.dtype, shape=(M, 1))
|
|
return res.A.ravel()
|
|
|
|
def _sparse_min_or_max(X, axis, min_or_max):
|
|
if axis is None:
|
|
if 0 in X.shape:
|
|
raise ValueError("zero-size array to reduction operation")
|
|
zero = X.dtype.type(0)
|
|
if X.nnz == 0:
|
|
return zero
|
|
m = min_or_max.reduce(X.data.ravel())
|
|
if X.nnz != np.product(X.shape):
|
|
m = min_or_max(zero, m)
|
|
return m
|
|
if axis < 0:
|
|
axis += 2
|
|
if (axis == 0) or (axis == 1):
|
|
return _min_or_max_axis(X, axis, min_or_max)
|
|
else:
|
|
raise ValueError("invalid axis, use 0 for rows, or 1 for columns")
|
|
|
|
def sparse_min_max(X, axis):
|
|
return (_sparse_min_or_max(X, axis, np.minimum),
|
|
_sparse_min_or_max(X, axis, np.maximum))
|
|
|
|
else:
|
|
def sparse_min_max(X, axis):
|
|
return (X.min(axis=axis).toarray().ravel(),
|
|
X.max(axis=axis).toarray().ravel())
|
|
|
|
|
|
if sp_version < (0, 15):
|
|
# Backport fix for scikit-learn/scikit-learn#2986 / scipy/scipy#4142
|
|
from ._scipy_sparse_lsqr_backport import lsqr as sparse_lsqr
|
|
else:
|
|
from scipy.sparse.linalg import lsqr as sparse_lsqr # noqa
|
|
|
|
|
|
try: # SciPy >= 0.19
|
|
from scipy.special import comb, logsumexp
|
|
except ImportError:
|
|
from scipy.misc import comb, logsumexp # noqa
|
|
|
|
|
|
if sp_version >= (0, 19):
|
|
def _argmax(arr_or_spmatrix, axis=None):
|
|
return arr_or_spmatrix.argmax(axis=axis)
|
|
else:
|
|
# Backport of argmax functionality from scipy 0.19.1, can be removed
|
|
# once support for scipy 0.18 and below is dropped
|
|
|
|
def _find_missing_index(ind, n):
|
|
for k, a in enumerate(ind):
|
|
if k != a:
|
|
return k
|
|
|
|
k += 1
|
|
if k < n:
|
|
return k
|
|
else:
|
|
return -1
|
|
|
|
def _arg_min_or_max_axis(self, axis, op, compare):
|
|
if self.shape[axis] == 0:
|
|
raise ValueError("Can't apply the operation along a zero-sized "
|
|
"dimension.")
|
|
|
|
if axis < 0:
|
|
axis += 2
|
|
|
|
zero = self.dtype.type(0)
|
|
|
|
mat = self.tocsc() if axis == 0 else self.tocsr()
|
|
mat.sum_duplicates()
|
|
|
|
ret_size, line_size = mat._swap(mat.shape)
|
|
ret = np.zeros(ret_size, dtype=int)
|
|
|
|
nz_lines, = np.nonzero(np.diff(mat.indptr))
|
|
for i in nz_lines:
|
|
p, q = mat.indptr[i:i + 2]
|
|
data = mat.data[p:q]
|
|
indices = mat.indices[p:q]
|
|
am = op(data)
|
|
m = data[am]
|
|
if compare(m, zero) or q - p == line_size:
|
|
ret[i] = indices[am]
|
|
else:
|
|
zero_ind = _find_missing_index(indices, line_size)
|
|
if m == zero:
|
|
ret[i] = min(am, zero_ind)
|
|
else:
|
|
ret[i] = zero_ind
|
|
|
|
if axis == 1:
|
|
ret = ret.reshape(-1, 1)
|
|
|
|
return np.asmatrix(ret)
|
|
|
|
def _arg_min_or_max(self, axis, out, op, compare):
|
|
if out is not None:
|
|
raise ValueError("Sparse matrices do not support "
|
|
"an 'out' parameter.")
|
|
|
|
# validateaxis(axis)
|
|
|
|
if axis is None:
|
|
if 0 in self.shape:
|
|
raise ValueError("Can't apply the operation to "
|
|
"an empty matrix.")
|
|
|
|
if self.nnz == 0:
|
|
return 0
|
|
else:
|
|
zero = self.dtype.type(0)
|
|
mat = self.tocoo()
|
|
mat.sum_duplicates()
|
|
am = op(mat.data)
|
|
m = mat.data[am]
|
|
|
|
if compare(m, zero):
|
|
return mat.row[am] * mat.shape[1] + mat.col[am]
|
|
else:
|
|
size = np.product(mat.shape)
|
|
if size == mat.nnz:
|
|
return am
|
|
else:
|
|
ind = mat.row * mat.shape[1] + mat.col
|
|
zero_ind = _find_missing_index(ind, size)
|
|
if m == zero:
|
|
return min(zero_ind, am)
|
|
else:
|
|
return zero_ind
|
|
|
|
return _arg_min_or_max_axis(self, axis, op, compare)
|
|
|
|
def _sparse_argmax(self, axis=None, out=None):
|
|
return _arg_min_or_max(self, axis, out, np.argmax, np.greater)
|
|
|
|
def _argmax(arr_or_matrix, axis=None):
|
|
if sp.issparse(arr_or_matrix):
|
|
return _sparse_argmax(arr_or_matrix, axis=axis)
|
|
else:
|
|
return arr_or_matrix.argmax(axis=axis)
|
|
|
|
|
|
def parallel_helper(obj, methodname, *args, **kwargs):
|
|
"""Workaround for Python 2 limitations of pickling instance methods"""
|
|
return getattr(obj, methodname)(*args, **kwargs)
|
|
|
|
|
|
if 'exist_ok' in signature(os.makedirs).parameters:
|
|
makedirs = os.makedirs
|
|
else:
|
|
def makedirs(name, mode=0o777, exist_ok=False):
|
|
"""makedirs(name [, mode=0o777][, exist_ok=False])
|
|
|
|
Super-mkdir; create a leaf directory and all intermediate ones. Works
|
|
like mkdir, except that any intermediate path segment (not just the
|
|
rightmost) will be created if it does not exist. If the target
|
|
directory already exists, raise an OSError if exist_ok is False.
|
|
Otherwise no exception is raised. This is recursive.
|
|
|
|
"""
|
|
|
|
try:
|
|
os.makedirs(name, mode=mode)
|
|
except OSError as e:
|
|
if (not exist_ok or e.errno != errno.EEXIST
|
|
or not os.path.isdir(name)):
|
|
raise
|
|
|
|
|
|
if np_version < (1, 12):
|
|
class MaskedArray(np.ma.MaskedArray):
|
|
# Before numpy 1.12, np.ma.MaskedArray object is not picklable
|
|
# This fix is needed to make our model_selection.GridSearchCV
|
|
# picklable as the ``cv_results_`` param uses MaskedArray
|
|
def __getstate__(self):
|
|
"""Return the internal state of the masked array, for pickling
|
|
purposes.
|
|
|
|
"""
|
|
cf = 'CF'[self.flags.fnc]
|
|
data_state = super(np.ma.MaskedArray, self).__reduce__()[2]
|
|
return data_state + (np.ma.getmaskarray(self).tostring(cf),
|
|
self._fill_value)
|
|
else:
|
|
from numpy.ma import MaskedArray # noqa
|