File size: 20,488 Bytes
7885a28 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 |
"""Base class for sparse matrice with a .data attribute
subclasses must provide a _with_data() method that
creates a new matrix with the same sparsity pattern
as self but with a different data array
"""
import math
import numpy as np
from ._base import _spbase, sparray, _ufuncs_with_fixed_point_at_zero
from ._sputils import isscalarlike, validateaxis
__all__ = []
# TODO implement all relevant operations
# use .data.__methods__() instead of /=, *=, etc.
class _data_matrix(_spbase):
def __init__(self, arg1, *, maxprint=None):
_spbase.__init__(self, arg1, maxprint=maxprint)
@property
def dtype(self):
return self.data.dtype
@dtype.setter
def dtype(self, newtype):
self.data.dtype = newtype
def _deduped_data(self):
if hasattr(self, 'sum_duplicates'):
self.sum_duplicates()
return self.data
def __abs__(self):
return self._with_data(abs(self._deduped_data()))
def __round__(self, ndigits=0):
return self._with_data(np.around(self._deduped_data(), decimals=ndigits))
def _real(self):
return self._with_data(self.data.real)
def _imag(self):
return self._with_data(self.data.imag)
def __neg__(self):
if self.dtype.kind == 'b':
raise NotImplementedError('negating a boolean sparse array is not '
'supported')
return self._with_data(-self.data)
def __imul__(self, other): # self *= other
if isscalarlike(other):
self.data *= other
return self
return NotImplemented
def __itruediv__(self, other): # self /= other
if isscalarlike(other):
recip = 1.0 / other
self.data *= recip
return self
else:
return NotImplemented
def astype(self, dtype, casting='unsafe', copy=True):
dtype = np.dtype(dtype)
if self.dtype != dtype:
matrix = self._with_data(
self.data.astype(dtype, casting=casting, copy=True),
copy=True
)
return matrix._with_data(matrix._deduped_data(), copy=False)
elif copy:
return self.copy()
else:
return self
astype.__doc__ = _spbase.astype.__doc__
def conjugate(self, copy=True):
if np.issubdtype(self.dtype, np.complexfloating):
return self._with_data(self.data.conjugate(), copy=copy)
elif copy:
return self.copy()
else:
return self
conjugate.__doc__ = _spbase.conjugate.__doc__
def copy(self):
return self._with_data(self.data.copy(), copy=True)
copy.__doc__ = _spbase.copy.__doc__
def power(self, n, dtype=None):
"""
This function performs element-wise power.
Parameters
----------
n : scalar
n is a non-zero scalar (nonzero avoids dense ones creation)
If zero power is desired, special case it to use `np.ones`
dtype : If dtype is not specified, the current dtype will be preserved.
Raises
------
NotImplementedError : if n is a zero scalar
If zero power is desired, special case it to use
``np.ones(A.shape, dtype=A.dtype)``
"""
if not isscalarlike(n):
raise NotImplementedError("input is not scalar")
if not n:
raise NotImplementedError(
"zero power is not supported as it would densify the matrix.\n"
"Use `np.ones(A.shape, dtype=A.dtype)` for this case."
)
data = self._deduped_data()
if dtype is not None:
data = data.astype(dtype)
return self._with_data(data ** n)
###########################
# Multiplication handlers #
###########################
def _mul_scalar(self, other):
return self._with_data(self.data * other)
# Add the numpy unary ufuncs for which func(0) = 0 to _data_matrix.
for npfunc in _ufuncs_with_fixed_point_at_zero:
name = npfunc.__name__
def _create_method(op):
def method(self):
result = op(self._deduped_data())
return self._with_data(result, copy=True)
method.__doc__ = (f"Element-wise {name}.\n\n"
f"See `numpy.{name}` for more information.")
method.__name__ = name
return method
setattr(_data_matrix, name, _create_method(npfunc))
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
class _minmax_mixin:
"""Mixin for min and max methods.
These are not implemented for dia_matrix, hence the separate class.
"""
def _min_or_max_axis(self, axis, min_or_max, explicit):
N = self.shape[axis]
if N == 0:
raise ValueError("zero-size array to reduction operation")
M = self.shape[1 - axis]
idx_dtype = self._get_index_dtype(maxval=M)
mat = self.tocsc() if axis == 0 else self.tocsr()
mat.sum_duplicates()
major_index, value = mat._minor_reduce(min_or_max)
if not explicit:
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).astype(idx_dtype, copy=False)
value = np.compress(mask, value)
if isinstance(self, sparray):
coords = (major_index,)
shape = (M,)
return self._coo_container((value, coords), shape=shape, dtype=self.dtype)
if axis == 0:
return self._coo_container(
(value, (np.zeros(len(value), dtype=idx_dtype), major_index)),
dtype=self.dtype, shape=(1, M)
)
else:
return self._coo_container(
(value, (major_index, np.zeros(len(value), dtype=idx_dtype))),
dtype=self.dtype, shape=(M, 1)
)
def _min_or_max(self, axis, out, min_or_max, explicit):
if out is not None:
raise ValueError("Sparse arrays do not support an 'out' parameter.")
validateaxis(axis)
if self.ndim == 1:
if axis not in (None, 0, -1):
raise ValueError("axis out of range")
axis = None # avoid calling special axis case. no impact on 1d
if axis is None:
if 0 in self.shape:
raise ValueError("zero-size array to reduction operation")
zero = self.dtype.type(0)
if self.nnz == 0:
return zero
m = min_or_max.reduce(self._deduped_data().ravel())
if self.nnz != math.prod(self.shape) and not explicit:
m = min_or_max(zero, m)
return m
if axis < 0:
axis += 2
if (axis == 0) or (axis == 1):
return self._min_or_max_axis(axis, min_or_max, explicit)
else:
raise ValueError("axis out of range")
def _arg_min_or_max_axis(self, axis, argmin_or_argmax, compare, explicit):
if self.shape[axis] == 0:
raise ValueError("Cannot 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]
extreme_index = argmin_or_argmax(data)
extreme_value = data[extreme_index]
if explicit:
if q - p > 0:
ret[i] = indices[extreme_index]
else:
if compare(extreme_value, zero) or q - p == line_size:
ret[i] = indices[extreme_index]
else:
zero_ind = _find_missing_index(indices, line_size)
if extreme_value == zero:
ret[i] = min(extreme_index, zero_ind)
else:
ret[i] = zero_ind
if isinstance(self, sparray):
return ret
if axis == 1:
ret = ret.reshape(-1, 1)
return self._ascontainer(ret)
def _arg_min_or_max(self, axis, out, argmin_or_argmax, compare, explicit):
if out is not None:
raise ValueError("Sparse types do not support an 'out' parameter.")
validateaxis(axis)
if self.ndim == 1:
if axis not in (None, 0, -1):
raise ValueError("axis out of range")
axis = None # avoid calling special axis case. no impact on 1d
if axis is not None:
return self._arg_min_or_max_axis(axis, argmin_or_argmax, compare, explicit)
if 0 in self.shape:
raise ValueError("Cannot apply the operation to an empty matrix.")
if self.nnz == 0:
if explicit:
raise ValueError("Cannot apply the operation to zero matrix "
"when explicit=True.")
return 0
zero = self.dtype.type(0)
mat = self.tocoo()
# Convert to canonical form: no duplicates, sorted indices.
mat.sum_duplicates()
extreme_index = argmin_or_argmax(mat.data)
if explicit:
return extreme_index
extreme_value = mat.data[extreme_index]
num_col = mat.shape[-1]
# If the min value is less than zero, or max is greater than zero,
# then we do not need to worry about implicit zeros.
if compare(extreme_value, zero):
# cast to Python int to avoid overflow and RuntimeError
return int(mat.row[extreme_index]) * num_col + int(mat.col[extreme_index])
# Cheap test for the rare case where we have no implicit zeros.
size = math.prod(self.shape)
if size == mat.nnz:
return int(mat.row[extreme_index]) * num_col + int(mat.col[extreme_index])
# At this stage, any implicit zero could be the min or max value.
# After sum_duplicates(), the `row` and `col` arrays are guaranteed to
# be sorted in C-order, which means the linearized indices are sorted.
linear_indices = mat.row * num_col + mat.col
first_implicit_zero_index = _find_missing_index(linear_indices, size)
if extreme_value == zero:
return min(first_implicit_zero_index, extreme_index)
return first_implicit_zero_index
def max(self, axis=None, out=None, *, explicit=False):
"""Return the maximum of the array/matrix or maximum along an axis.
By default, all elements are taken into account, not just the non-zero ones.
But with `explicit` set, only the stored elements are considered.
Parameters
----------
axis : {-2, -1, 0, 1, None} optional
Axis along which the sum is computed. The default is to
compute the maximum over all elements, returning
a scalar (i.e., `axis` = `None`).
out : None, optional
This argument is in the signature *solely* for NumPy
compatibility reasons. Do not pass in anything except
for the default value, as this argument is not used.
explicit : {False, True} optional (default: False)
When set to True, only the stored elements will be considered.
If a row/column is empty, the sparse.coo_array returned
has no stored element (i.e. an implicit zero) for that row/column.
.. versionadded:: 1.15.0
Returns
-------
amax : coo_array or scalar
Maximum of `a`. If `axis` is None, the result is a scalar value.
If `axis` is given, the result is a sparse.coo_array of dimension
``a.ndim - 1``.
See Also
--------
min : The minimum value of a sparse array/matrix along a given axis.
numpy.max : NumPy's implementation of 'max'
"""
return self._min_or_max(axis, out, np.maximum, explicit)
def min(self, axis=None, out=None, *, explicit=False):
"""Return the minimum of the array/matrix or maximum along an axis.
By default, all elements are taken into account, not just the non-zero ones.
But with `explicit` set, only the stored elements are considered.
Parameters
----------
axis : {-2, -1, 0, 1, None} optional
Axis along which the sum is computed. The default is to
compute the minimum over all elements, returning
a scalar (i.e., `axis` = `None`).
out : None, optional
This argument is in the signature *solely* for NumPy
compatibility reasons. Do not pass in anything except for
the default value, as this argument is not used.
explicit : {False, True} optional (default: False)
When set to True, only the stored elements will be considered.
If a row/column is empty, the sparse.coo_array returned
has no stored element (i.e. an implicit zero) for that row/column.
.. versionadded:: 1.15.0
Returns
-------
amin : coo_matrix or scalar
Minimum of `a`. If `axis` is None, the result is a scalar value.
If `axis` is given, the result is a sparse.coo_array of dimension
``a.ndim - 1``.
See Also
--------
max : The maximum value of a sparse array/matrix along a given axis.
numpy.min : NumPy's implementation of 'min'
"""
return self._min_or_max(axis, out, np.minimum, explicit)
def nanmax(self, axis=None, out=None, *, explicit=False):
"""Return the maximum, ignoring any Nans, along an axis.
Return the maximum, ignoring any Nans, of the array/matrix along an axis.
By default this takes all elements into account, but with `explicit` set,
only stored elements are considered.
.. versionadded:: 1.11.0
Parameters
----------
axis : {-2, -1, 0, 1, None} optional
Axis along which the maximum is computed. The default is to
compute the maximum over all elements, returning
a scalar (i.e., `axis` = `None`).
out : None, optional
This argument is in the signature *solely* for NumPy
compatibility reasons. Do not pass in anything except
for the default value, as this argument is not used.
explicit : {False, True} optional (default: False)
When set to True, only the stored elements will be considered.
If a row/column is empty, the sparse.coo_array returned
has no stored element (i.e. an implicit zero) for that row/column.
.. versionadded:: 1.15.0
Returns
-------
amax : coo_array or scalar
Maximum of `a`. If `axis` is None, the result is a scalar value.
If `axis` is given, the result is a sparse.coo_array of dimension
``a.ndim - 1``.
See Also
--------
nanmin : The minimum value of a sparse array/matrix along a given axis,
ignoring NaNs.
max : The maximum value of a sparse array/matrix along a given axis,
propagating NaNs.
numpy.nanmax : NumPy's implementation of 'nanmax'.
"""
return self._min_or_max(axis, out, np.fmax, explicit)
def nanmin(self, axis=None, out=None, *, explicit=False):
"""Return the minimum, ignoring any Nans, along an axis.
Return the minimum, ignoring any Nans, of the array/matrix along an axis.
By default this takes all elements into account, but with `explicit` set,
only stored elements are considered.
.. versionadded:: 1.11.0
Parameters
----------
axis : {-2, -1, 0, 1, None} optional
Axis along which the minimum is computed. The default is to
compute the minimum over all elements, returning
a scalar (i.e., `axis` = `None`).
out : None, optional
This argument is in the signature *solely* for NumPy
compatibility reasons. Do not pass in anything except for
the default value, as this argument is not used.
explicit : {False, True} optional (default: False)
When set to True, only the stored elements will be considered.
If a row/column is empty, the sparse.coo_array returned
has no stored element (i.e. an implicit zero) for that row/column.
.. versionadded:: 1.15.0
Returns
-------
amin : coo_array or scalar
Minimum of `a`. If `axis` is None, the result is a scalar value.
If `axis` is given, the result is a sparse.coo_array of dimension
``a.ndim - 1``.
See Also
--------
nanmax : The maximum value of a sparse array/matrix along a given axis,
ignoring NaNs.
min : The minimum value of a sparse array/matrix along a given axis,
propagating NaNs.
numpy.nanmin : NumPy's implementation of 'nanmin'.
"""
return self._min_or_max(axis, out, np.fmin, explicit)
def argmax(self, axis=None, out=None, *, explicit=False):
"""Return indices of maximum elements along an axis.
By default, implicit zero elements are taken into account. If there are
several minimum values, the index of the first occurrence is returned.
If `explicit` is set, only explicitly stored elements will be considered.
Parameters
----------
axis : {-2, -1, 0, 1, None}, optional
Axis along which the argmax is computed. If None (default), index
of the maximum element in the flatten data is returned.
out : None, optional
This argument is in the signature *solely* for NumPy
compatibility reasons. Do not pass in anything except for
the default value, as this argument is not used.
explicit : {False, True} optional (default: False)
When set to True, only explicitly stored elements will be considered.
If axis is not None and a row/column has no stored elements, argmax
is undefined, so the index ``0`` is returned for that row/column.
.. versionadded:: 1.15.0
Returns
-------
ind : numpy.matrix or int
Indices of maximum elements. If matrix, its size along `axis` is 1.
"""
return self._arg_min_or_max(axis, out, np.argmax, np.greater, explicit)
def argmin(self, axis=None, out=None, *, explicit=False):
"""Return indices of minimum elements along an axis.
By default, implicit zero elements are taken into account. If there are
several minimum values, the index of the first occurrence is returned.
If `explicit` is set, only explicitly stored elements will be considered.
Parameters
----------
axis : {-2, -1, 0, 1, None}, optional
Axis along which the argmin is computed. If None (default), index
of the minimum element in the flatten data is returned.
out : None, optional
This argument is in the signature *solely* for NumPy
compatibility reasons. Do not pass in anything except for
the default value, as this argument is not used.
explicit : {False, True} optional (default: False)
When set to True, only explicitly stored elements will be considered.
If axis is not None and a row/column has no stored elements, argmin
is undefined, so the index ``0`` is returned for that row/column.
.. versionadded:: 1.15.0
Returns
-------
ind : numpy.matrix or int
Indices of minimum elements. If matrix, its size along `axis` is 1.
"""
return self._arg_min_or_max(axis, out, np.argmin, np.less, explicit)
|