File: affinity_propagation_.py

package info (click to toggle)
scikit-learn 0.20.2%2Bdfsg-6
  • links: PTS, VCS
  • area: main
  • in suites: buster
  • size: 51,036 kB
  • sloc: python: 108,171; ansic: 8,722; cpp: 5,651; makefile: 192; sh: 40
file content (412 lines) | stat: -rw-r--r-- 14,644 bytes parent folder | download
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
"""Affinity Propagation clustering algorithm."""

# Author: Alexandre Gramfort alexandre.gramfort@inria.fr
#        Gael Varoquaux gael.varoquaux@normalesup.org

# License: BSD 3 clause

import numpy as np
import warnings

from sklearn.exceptions import ConvergenceWarning
from ..base import BaseEstimator, ClusterMixin
from ..utils import as_float_array, check_array
from ..utils.validation import check_is_fitted
from ..metrics import euclidean_distances
from ..metrics import pairwise_distances_argmin


def _equal_similarities_and_preferences(S, preference):
    def all_equal_preferences():
        return np.all(preference == preference.flat[0])

    def all_equal_similarities():
        # Create mask to ignore diagonal of S
        mask = np.ones(S.shape, dtype=bool)
        np.fill_diagonal(mask, 0)

        return np.all(S[mask].flat == S[mask].flat[0])

    return all_equal_preferences() and all_equal_similarities()


def affinity_propagation(S, preference=None, convergence_iter=15, max_iter=200,
                         damping=0.5, copy=True, verbose=False,
                         return_n_iter=False):
    """Perform Affinity Propagation Clustering of data

    Read more in the :ref:`User Guide <affinity_propagation>`.

    Parameters
    ----------

    S : array-like, shape (n_samples, n_samples)
        Matrix of similarities between points

    preference : array-like, shape (n_samples,) or float, optional
        Preferences for each point - points with larger values of
        preferences are more likely to be chosen as exemplars. The number of
        exemplars, i.e. of clusters, is influenced by the input preferences
        value. If the preferences are not passed as arguments, they will be
        set to the median of the input similarities (resulting in a moderate
        number of clusters). For a smaller amount of clusters, this can be set
        to the minimum value of the similarities.

    convergence_iter : int, optional, default: 15
        Number of iterations with no change in the number
        of estimated clusters that stops the convergence.

    max_iter : int, optional, default: 200
        Maximum number of iterations

    damping : float, optional, default: 0.5
        Damping factor between 0.5 and 1.

    copy : boolean, optional, default: True
        If copy is False, the affinity matrix is modified inplace by the
        algorithm, for memory efficiency

    verbose : boolean, optional, default: False
        The verbosity level

    return_n_iter : bool, default False
        Whether or not to return the number of iterations.

    Returns
    -------

    cluster_centers_indices : array, shape (n_clusters,)
        index of clusters centers

    labels : array, shape (n_samples,)
        cluster labels for each point

    n_iter : int
        number of iterations run. Returned only if `return_n_iter` is
        set to True.

    Notes
    -----
    For an example, see :ref:`examples/cluster/plot_affinity_propagation.py
    <sphx_glr_auto_examples_cluster_plot_affinity_propagation.py>`.

    When the algorithm does not converge, it returns an empty array as
    ``cluster_center_indices`` and ``-1`` as label for each training sample.

    When all training samples have equal similarities and equal preferences,
    the assignment of cluster centers and labels depends on the preference.
    If the preference is smaller than the similarities, a single cluster center
    and label ``0`` for every sample will be returned. Otherwise, every
    training sample becomes its own cluster center and is assigned a unique
    label.

    References
    ----------
    Brendan J. Frey and Delbert Dueck, "Clustering by Passing Messages
    Between Data Points", Science Feb. 2007
    """
    S = as_float_array(S, copy=copy)
    n_samples = S.shape[0]

    if S.shape[0] != S.shape[1]:
        raise ValueError("S must be a square array (shape=%s)" % repr(S.shape))

    if preference is None:
        preference = np.median(S)
    if damping < 0.5 or damping >= 1:
        raise ValueError('damping must be >= 0.5 and < 1')

    preference = np.array(preference)

    if (n_samples == 1 or
            _equal_similarities_and_preferences(S, preference)):
        # It makes no sense to run the algorithm in this case, so return 1 or
        # n_samples clusters, depending on preferences
        warnings.warn("All samples have mutually equal similarities. "
                      "Returning arbitrary cluster center(s).")
        if preference.flat[0] >= S.flat[n_samples - 1]:
            return ((np.arange(n_samples), np.arange(n_samples), 0)
                    if return_n_iter
                    else (np.arange(n_samples), np.arange(n_samples)))
        else:
            return ((np.array([0]), np.array([0] * n_samples), 0)
                    if return_n_iter
                    else (np.array([0]), np.array([0] * n_samples)))

    random_state = np.random.RandomState(0)

    # Place preference on the diagonal of S
    S.flat[::(n_samples + 1)] = preference

    A = np.zeros((n_samples, n_samples))
    R = np.zeros((n_samples, n_samples))  # Initialize messages
    # Intermediate results
    tmp = np.zeros((n_samples, n_samples))

    # Remove degeneracies
    S += ((np.finfo(np.double).eps * S + np.finfo(np.double).tiny * 100) *
          random_state.randn(n_samples, n_samples))

    # Execute parallel affinity propagation updates
    e = np.zeros((n_samples, convergence_iter))

    ind = np.arange(n_samples)

    for it in range(max_iter):
        # tmp = A + S; compute responsibilities
        np.add(A, S, tmp)
        I = np.argmax(tmp, axis=1)
        Y = tmp[ind, I]  # np.max(A + S, axis=1)
        tmp[ind, I] = -np.inf
        Y2 = np.max(tmp, axis=1)

        # tmp = Rnew
        np.subtract(S, Y[:, None], tmp)
        tmp[ind, I] = S[ind, I] - Y2

        # Damping
        tmp *= 1 - damping
        R *= damping
        R += tmp

        # tmp = Rp; compute availabilities
        np.maximum(R, 0, tmp)
        tmp.flat[::n_samples + 1] = R.flat[::n_samples + 1]

        # tmp = -Anew
        tmp -= np.sum(tmp, axis=0)
        dA = np.diag(tmp).copy()
        tmp.clip(0, np.inf, tmp)
        tmp.flat[::n_samples + 1] = dA

        # Damping
        tmp *= 1 - damping
        A *= damping
        A -= tmp

        # Check for convergence
        E = (np.diag(A) + np.diag(R)) > 0
        e[:, it % convergence_iter] = E
        K = np.sum(E, axis=0)

        if it >= convergence_iter:
            se = np.sum(e, axis=1)
            unconverged = (np.sum((se == convergence_iter) + (se == 0))
                           != n_samples)
            if (not unconverged and (K > 0)) or (it == max_iter):
                if verbose:
                    print("Converged after %d iterations." % it)
                break
    else:
        if verbose:
            print("Did not converge")

    I = np.flatnonzero(E)
    K = I.size  # Identify exemplars

    if K > 0:
        c = np.argmax(S[:, I], axis=1)
        c[I] = np.arange(K)  # Identify clusters
        # Refine the final set of exemplars and clusters and return results
        for k in range(K):
            ii = np.where(c == k)[0]
            j = np.argmax(np.sum(S[ii[:, np.newaxis], ii], axis=0))
            I[k] = ii[j]

        c = np.argmax(S[:, I], axis=1)
        c[I] = np.arange(K)
        labels = I[c]
        # Reduce labels to a sorted, gapless, list
        cluster_centers_indices = np.unique(labels)
        labels = np.searchsorted(cluster_centers_indices, labels)
    else:
        warnings.warn("Affinity propagation did not converge, this model "
                      "will not have any cluster centers.", ConvergenceWarning)
        labels = np.array([-1] * n_samples)
        cluster_centers_indices = []

    if return_n_iter:
        return cluster_centers_indices, labels, it + 1
    else:
        return cluster_centers_indices, labels


###############################################################################

class AffinityPropagation(BaseEstimator, ClusterMixin):
    """Perform Affinity Propagation Clustering of data.

    Read more in the :ref:`User Guide <affinity_propagation>`.

    Parameters
    ----------
    damping : float, optional, default: 0.5
        Damping factor (between 0.5 and 1) is the extent to
        which the current value is maintained relative to
        incoming values (weighted 1 - damping). This in order
        to avoid numerical oscillations when updating these
        values (messages).

    max_iter : int, optional, default: 200
        Maximum number of iterations.

    convergence_iter : int, optional, default: 15
        Number of iterations with no change in the number
        of estimated clusters that stops the convergence.

    copy : boolean, optional, default: True
        Make a copy of input data.

    preference : array-like, shape (n_samples,) or float, optional
        Preferences for each point - points with larger values of
        preferences are more likely to be chosen as exemplars. The number
        of exemplars, ie of clusters, is influenced by the input
        preferences value. If the preferences are not passed as arguments,
        they will be set to the median of the input similarities.

    affinity : string, optional, default=``euclidean``
        Which affinity to use. At the moment ``precomputed`` and
        ``euclidean`` are supported. ``euclidean`` uses the
        negative squared euclidean distance between points.

    verbose : boolean, optional, default: False
        Whether to be verbose.


    Attributes
    ----------
    cluster_centers_indices_ : array, shape (n_clusters,)
        Indices of cluster centers

    cluster_centers_ : array, shape (n_clusters, n_features)
        Cluster centers (if affinity != ``precomputed``).

    labels_ : array, shape (n_samples,)
        Labels of each point

    affinity_matrix_ : array, shape (n_samples, n_samples)
        Stores the affinity matrix used in ``fit``.

    n_iter_ : int
        Number of iterations taken to converge.

    Examples
    --------
    >>> from sklearn.cluster import AffinityPropagation
    >>> import numpy as np
    >>> X = np.array([[1, 2], [1, 4], [1, 0],
    ...               [4, 2], [4, 4], [4, 0]])
    >>> clustering = AffinityPropagation().fit(X)
    >>> clustering # doctest: +NORMALIZE_WHITESPACE
    AffinityPropagation(affinity='euclidean', convergence_iter=15, copy=True,
              damping=0.5, max_iter=200, preference=None, verbose=False)
    >>> clustering.labels_
    array([0, 0, 0, 1, 1, 1])
    >>> clustering.predict([[0, 0], [4, 4]])
    array([0, 1])
    >>> clustering.cluster_centers_
    array([[1, 2],
           [4, 2]])

    Notes
    -----
    For an example, see :ref:`examples/cluster/plot_affinity_propagation.py
    <sphx_glr_auto_examples_cluster_plot_affinity_propagation.py>`.

    The algorithmic complexity of affinity propagation is quadratic
    in the number of points.

    When ``fit`` does not converge, ``cluster_centers_`` becomes an empty
    array and all training samples will be labelled as ``-1``. In addition,
    ``predict`` will then label every sample as ``-1``.

    When all training samples have equal similarities and equal preferences,
    the assignment of cluster centers and labels depends on the preference.
    If the preference is smaller than the similarities, ``fit`` will result in
    a single cluster center and label ``0`` for every sample. Otherwise, every
    training sample becomes its own cluster center and is assigned a unique
    label.

    References
    ----------

    Brendan J. Frey and Delbert Dueck, "Clustering by Passing Messages
    Between Data Points", Science Feb. 2007
    """

    def __init__(self, damping=.5, max_iter=200, convergence_iter=15,
                 copy=True, preference=None, affinity='euclidean',
                 verbose=False):

        self.damping = damping
        self.max_iter = max_iter
        self.convergence_iter = convergence_iter
        self.copy = copy
        self.verbose = verbose
        self.preference = preference
        self.affinity = affinity

    @property
    def _pairwise(self):
        return self.affinity == "precomputed"

    def fit(self, X, y=None):
        """ Create affinity matrix from negative euclidean distances, then
        apply affinity propagation clustering.

        Parameters
        ----------

        X : array-like, shape (n_samples, n_features) or (n_samples, n_samples)
            Data matrix or, if affinity is ``precomputed``, matrix of
            similarities / affinities.

        y : Ignored

        """
        X = check_array(X, accept_sparse='csr')
        if self.affinity == "precomputed":
            self.affinity_matrix_ = X
        elif self.affinity == "euclidean":
            self.affinity_matrix_ = -euclidean_distances(X, squared=True)
        else:
            raise ValueError("Affinity must be 'precomputed' or "
                             "'euclidean'. Got %s instead"
                             % str(self.affinity))

        self.cluster_centers_indices_, self.labels_, self.n_iter_ = \
            affinity_propagation(
                self.affinity_matrix_, self.preference, max_iter=self.max_iter,
                convergence_iter=self.convergence_iter, damping=self.damping,
                copy=self.copy, verbose=self.verbose, return_n_iter=True)

        if self.affinity != "precomputed":
            self.cluster_centers_ = X[self.cluster_centers_indices_].copy()

        return self

    def predict(self, X):
        """Predict the closest cluster each sample in X belongs to.

        Parameters
        ----------
        X : {array-like, sparse matrix}, shape (n_samples, n_features)
            New data to predict.

        Returns
        -------
        labels : array, shape (n_samples,)
            Index of the cluster each sample belongs to.
        """
        check_is_fitted(self, "cluster_centers_indices_")
        if not hasattr(self, "cluster_centers_"):
            raise ValueError("Predict method is not supported when "
                             "affinity='precomputed'.")

        if self.cluster_centers_.size > 0:
            return pairwise_distances_argmin(X, self.cluster_centers_)
        else:
            warnings.warn("This model does not have any cluster centers "
                          "because affinity propagation did not converge. "
                          "Labeling every sample as '-1'.", ConvergenceWarning)
            return np.array([-1] * X.shape[0])