Source

numpypy / numpypy / lib / arraysetops.py

  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
"""
Set operations for 1D numeric arrays based on sorting.

:Contains:
  ediff1d,
  unique,
  intersect1d,
  setxor1d,
  in1d,
  union1d,
  setdiff1d

:Notes:

For floating point arrays, inaccurate results may appear due to usual round-off
and floating point comparison issues.

Speed could be gained in some operations by an implementation of
sort(), that can provide directly the permutation vectors, avoiding
thus calls to argsort().

To do: Optionally return indices analogously to unique for all functions.

:Author: Robert Cimrman
"""
__all__ = ['ediff1d', 'intersect1d', 'setxor1d', 'union1d', 'setdiff1d',
           'unique', 'in1d']

import numpy as np
from numpy.lib.utils import deprecate

def ediff1d(ary, to_end=None, to_begin=None):
    """
    The differences between consecutive elements of an array.

    Parameters
    ----------
    ary : array_like
        If necessary, will be flattened before the differences are taken.
    to_end : array_like, optional
        Number(s) to append at the end of the returned differences.
    to_begin : array_like, optional
        Number(s) to prepend at the beginning of the returned differences.

    Returns
    -------
    ed : ndarray
        The differences. Loosely, this is ``ary.flat[1:] - ary.flat[:-1]``.

    See Also
    --------
    diff, gradient

    Notes
    -----
    When applied to masked arrays, this function drops the mask information
    if the `to_begin` and/or `to_end` parameters are used.

    Examples
    --------
    >>> x = np.array([1, 2, 4, 7, 0])
    >>> np.ediff1d(x)
    array([ 1,  2,  3, -7])

    >>> np.ediff1d(x, to_begin=-99, to_end=np.array([88, 99]))
    array([-99,   1,   2,   3,  -7,  88,  99])

    The returned array is always 1D.

    >>> y = [[1, 2, 4], [1, 6, 24]]
    >>> np.ediff1d(y)
    array([ 1,  2, -3,  5, 18])

    """
    ary = np.asanyarray(ary).flat
    ed = ary[1:] - ary[:-1]
    arrays = [ed]
    if to_begin is not None:
        arrays.insert(0, to_begin)
    if to_end is not None:
        arrays.append(to_end)

    if len(arrays) != 1:
        # We'll save ourselves a copy of a potentially large array in
        # the common case where neither to_begin or to_end was given.
        ed = np.hstack(arrays)

    return ed

def unique(ar, return_index=False, return_inverse=False):
    """
    Find the unique elements of an array.

    Returns the sorted unique elements of an array. There are two optional
    outputs in addition to the unique elements: the indices of the input array
    that give the unique values, and the indices of the unique array that
    reconstruct the input array.

    Parameters
    ----------
    ar : array_like
        Input array. This will be flattened if it is not already 1-D.
    return_index : bool, optional
        If True, also return the indices of `ar` that result in the unique
        array.
    return_inverse : bool, optional
        If True, also return the indices of the unique array that can be used
        to reconstruct `ar`.

    Returns
    -------
    unique : ndarray
        The sorted unique values.
    unique_indices : ndarray, optional
        The indices of the unique values in the (flattened) original array.
        Only provided if `return_index` is True.
    unique_inverse : ndarray, optional
        The indices to reconstruct the (flattened) original array from the
        unique array. Only provided if `return_inverse` is True.

    See Also
    --------
    numpy.lib.arraysetops : Module with a number of other functions for
                            performing set operations on arrays.

    Examples
    --------
    >>> np.unique([1, 1, 2, 2, 3, 3])
    array([1, 2, 3])
    >>> a = np.array([[1, 1], [2, 3]])
    >>> np.unique(a)
    array([1, 2, 3])

    Return the indices of the original array that give the unique values:

    >>> a = np.array(['a', 'b', 'b', 'c', 'a'])
    >>> u, indices = np.unique(a, return_index=True)
    >>> u
    array(['a', 'b', 'c'],
           dtype='|S1')
    >>> indices
    array([0, 1, 3])
    >>> a[indices]
    array(['a', 'b', 'c'],
           dtype='|S1')

    Reconstruct the input array from the unique values:

    >>> a = np.array([1, 2, 6, 4, 2, 3, 2])
    >>> u, indices = np.unique(a, return_inverse=True)
    >>> u
    array([1, 2, 3, 4, 6])
    >>> indices
    array([0, 1, 4, 3, 1, 2, 1])
    >>> u[indices]
    array([1, 2, 6, 4, 2, 3, 2])

    """
    try:
        ar = ar.flatten()
    except AttributeError:
        if not return_inverse and not return_index:
            items = sorted(set(ar))
            return np.asarray(items)
        else:
            ar = np.asanyarray(ar).flatten()

    if ar.size == 0:
        if return_inverse and return_index:
            return ar, np.empty(0, np.bool), np.empty(0, np.bool)
        elif return_inverse or return_index:
            return ar, np.empty(0, np.bool)
        else:
            return ar

    if return_inverse or return_index:
        perm = ar.argsort()
        aux = ar[perm]
        flag = np.concatenate(([True], aux[1:] != aux[:-1]))
        if return_inverse:
            iflag = np.cumsum(flag) - 1
            iperm = perm.argsort()
            if return_index:
                return aux[flag], perm[flag], iflag[iperm]
            else:
                return aux[flag], iflag[iperm]
        else:
            return aux[flag], perm[flag]

    else:
        ar.sort()
        flag = np.concatenate(([True], ar[1:] != ar[:-1]))
        return ar[flag]


def intersect1d(ar1, ar2, assume_unique=False):
    """
    Find the intersection of two arrays.

    Return the sorted, unique values that are in both of the input arrays.

    Parameters
    ----------
    ar1, ar2 : array_like
        Input arrays.
    assume_unique : bool
        If True, the input arrays are both assumed to be unique, which
        can speed up the calculation.  Default is False.

    Returns
    -------
    out : ndarray
        Sorted 1D array of common and unique elements.

    See Also
    --------
    numpy.lib.arraysetops : Module with a number of other functions for
                            performing set operations on arrays.

    Examples
    --------
    >>> np.intersect1d([1, 3, 4, 3], [3, 1, 2, 1])
    array([1, 3])

    """
    if not assume_unique:
        # Might be faster than unique( intersect1d( ar1, ar2 ) )?
        ar1 = unique(ar1)
        ar2 = unique(ar2)
    aux = np.concatenate( (ar1, ar2) )
    aux.sort()
    return aux[:-1][aux[1:] == aux[:-1]]

def setxor1d(ar1, ar2, assume_unique=False):
    """
    Find the set exclusive-or of two arrays.

    Return the sorted, unique values that are in only one (not both) of the
    input arrays.

    Parameters
    ----------
    ar1, ar2 : array_like
        Input arrays.
    assume_unique : bool
        If True, the input arrays are both assumed to be unique, which
        can speed up the calculation.  Default is False.

    Returns
    -------
    xor : ndarray
        Sorted 1D array of unique values that are in only one of the input
        arrays.

    Examples
    --------
    >>> a = np.array([1, 2, 3, 2, 4])
    >>> b = np.array([2, 3, 5, 7, 5])
    >>> np.setxor1d(a,b)
    array([1, 4, 5, 7])

    """
    if not assume_unique:
        ar1 = unique(ar1)
        ar2 = unique(ar2)

    aux = np.concatenate( (ar1, ar2) )
    if aux.size == 0:
        return aux

    aux.sort()
#    flag = ediff1d( aux, to_end = 1, to_begin = 1 ) == 0
    flag = np.concatenate( ([True], aux[1:] != aux[:-1], [True] ) )
#    flag2 = ediff1d( flag ) == 0
    flag2 = flag[1:] == flag[:-1]
    return aux[flag2]

def in1d(ar1, ar2, assume_unique=False):
    """
    Test whether each element of a 1-D array is also present in a second array.

    Returns a boolean array the same length as `ar1` that is True
    where an element of `ar1` is in `ar2` and False otherwise.

    Parameters
    ----------
    ar1 : array_like, shape (M,)
        Input array.
    ar2 : array_like
        The values against which to test each value of `ar1`.
    assume_unique : bool, optional
        If True, the input arrays are both assumed to be unique, which
        can speed up the calculation.  Default is False.

    Returns
    -------
    mask : ndarray of bools, shape(M,)
        The values `ar1[mask]` are in `ar2`.

    See Also
    --------
    numpy.lib.arraysetops : Module with a number of other functions for
                            performing set operations on arrays.

    Notes
    -----
    `in1d` can be considered as an element-wise function version of the
    python keyword `in`, for 1-D sequences. ``in1d(a, b)`` is roughly
    equivalent to ``np.array([item in b for item in a])``.

    .. versionadded:: 1.4.0

    Examples
    --------
    >>> test = np.array([0, 1, 2, 5, 0])
    >>> states = [0, 2]
    >>> mask = np.in1d(test, states)
    >>> mask
    array([ True, False,  True, False,  True], dtype=bool)
    >>> test[mask]
    array([0, 2, 0])

    """
    # This code is significantly faster when the condition is satisfied.
    if len(ar2) < 10 * len(ar1) ** 0.145:
        mask = np.zeros(len(ar1), dtype=np.bool)
        for a in ar2:
            mask |= (ar1 == a)
        return mask

    # Otherwise use sorting
    if not assume_unique:
        ar1, rev_idx = np.unique(ar1, return_inverse=True)
        ar2 = np.unique(ar2)

    ar = np.concatenate( (ar1, ar2) )
    # We need this to be a stable sort, so always use 'mergesort'
    # here. The values from the first array should always come before
    # the values from the second array.
    order = ar.argsort(kind='mergesort')
    sar = ar[order]
    equal_adj = (sar[1:] == sar[:-1])
    flag = np.concatenate( (equal_adj, [False] ) )
    indx = order.argsort(kind='mergesort')[:len( ar1 )]

    if assume_unique:
        return flag[indx]
    else:
        return flag[indx][rev_idx]

def union1d(ar1, ar2):
    """
    Find the union of two arrays.

    Return the unique, sorted array of values that are in either of the two
    input arrays.

    Parameters
    ----------
    ar1, ar2 : array_like
        Input arrays. They are flattened if they are not already 1D.

    Returns
    -------
    union : ndarray
        Unique, sorted union of the input arrays.

    See Also
    --------
    numpy.lib.arraysetops : Module with a number of other functions for
                            performing set operations on arrays.

    Examples
    --------
    >>> np.union1d([-1, 0, 1], [-2, 0, 2])
    array([-2, -1,  0,  1,  2])

    """
    return unique( np.concatenate( (ar1, ar2) ) )

def setdiff1d(ar1, ar2, assume_unique=False):
    """
    Find the set difference of two arrays.

    Return the sorted, unique values in `ar1` that are not in `ar2`.

    Parameters
    ----------
    ar1 : array_like
        Input array.
    ar2 : array_like
        Input comparison array.
    assume_unique : bool
        If True, the input arrays are both assumed to be unique, which
        can speed up the calculation.  Default is False.

    Returns
    -------
    difference : ndarray
        Sorted 1D array of values in `ar1` that are not in `ar2`.

    See Also
    --------
    numpy.lib.arraysetops : Module with a number of other functions for
                            performing set operations on arrays.

    Examples
    --------
    >>> a = np.array([1, 2, 3, 2, 4, 1])
    >>> b = np.array([3, 4, 5, 6])
    >>> np.setdiff1d(a, b)
    array([1, 2])

    """
    if not assume_unique:
        ar1 = unique(ar1)
        ar2 = unique(ar2)
    aux = in1d(ar1, ar2, assume_unique=True)
    if aux.size == 0:
        return aux
    else:
        return np.asarray(ar1)[aux == 0]