File: plot_faces_decomposition.py

package info (click to toggle)
scikit-learn 0.23.2-5
  • links: PTS, VCS
  • area: main
  • in suites: bookworm, bullseye, sid
  • size: 21,892 kB
  • sloc: python: 132,020; cpp: 5,765; javascript: 2,201; ansic: 831; makefile: 213; sh: 44
file content (193 lines) | stat: -rw-r--r-- 7,250 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
"""
============================
Faces dataset decompositions
============================

This example applies to :ref:`olivetti_faces_dataset` different unsupervised
matrix decomposition (dimension reduction) methods from the module
:py:mod:`sklearn.decomposition` (see the documentation chapter
:ref:`decompositions`) .

"""
print(__doc__)

# Authors: Vlad Niculae, Alexandre Gramfort
# License: BSD 3 clause

import logging
from time import time

from numpy.random import RandomState
import matplotlib.pyplot as plt

from sklearn.datasets import fetch_olivetti_faces
from sklearn.cluster import MiniBatchKMeans
from sklearn import decomposition

# Display progress logs on stdout
logging.basicConfig(level=logging.INFO,
                    format='%(asctime)s %(levelname)s %(message)s')
n_row, n_col = 2, 3
n_components = n_row * n_col
image_shape = (64, 64)
rng = RandomState(0)

# #############################################################################
# Load faces data
faces, _ = fetch_olivetti_faces(return_X_y=True, shuffle=True,
                                random_state=rng)
n_samples, n_features = faces.shape

# global centering
faces_centered = faces - faces.mean(axis=0)

# local centering
faces_centered -= faces_centered.mean(axis=1).reshape(n_samples, -1)

print("Dataset consists of %d faces" % n_samples)


def plot_gallery(title, images, n_col=n_col, n_row=n_row, cmap=plt.cm.gray):
    plt.figure(figsize=(2. * n_col, 2.26 * n_row))
    plt.suptitle(title, size=16)
    for i, comp in enumerate(images):
        plt.subplot(n_row, n_col, i + 1)
        vmax = max(comp.max(), -comp.min())
        plt.imshow(comp.reshape(image_shape), cmap=cmap,
                   interpolation='nearest',
                   vmin=-vmax, vmax=vmax)
        plt.xticks(())
        plt.yticks(())
    plt.subplots_adjust(0.01, 0.05, 0.99, 0.93, 0.04, 0.)

# #############################################################################
# List of the different estimators, whether to center and transpose the
# problem, and whether the transformer uses the clustering API.
estimators = [
    ('Eigenfaces - PCA using randomized SVD',
     decomposition.PCA(n_components=n_components, svd_solver='randomized',
                       whiten=True),
     True),

    ('Non-negative components - NMF',
     decomposition.NMF(n_components=n_components, init='nndsvda', tol=5e-3),
     False),

    ('Independent components - FastICA',
     decomposition.FastICA(n_components=n_components, whiten=True),
     True),

    ('Sparse comp. - MiniBatchSparsePCA',
     decomposition.MiniBatchSparsePCA(n_components=n_components, alpha=0.8,
                                      n_iter=100, batch_size=3,
                                      random_state=rng),
     True),

    ('MiniBatchDictionaryLearning',
        decomposition.MiniBatchDictionaryLearning(n_components=15, alpha=0.1,
                                                  n_iter=50, batch_size=3,
                                                  random_state=rng),
     True),

    ('Cluster centers - MiniBatchKMeans',
        MiniBatchKMeans(n_clusters=n_components, tol=1e-3, batch_size=20,
                        max_iter=50, random_state=rng),
     True),

    ('Factor Analysis components - FA',
     decomposition.FactorAnalysis(n_components=n_components, max_iter=20),
     True),
]


# #############################################################################
# Plot a sample of the input data

plot_gallery("First centered Olivetti faces", faces_centered[:n_components])

# #############################################################################
# Do the estimation and plot it

for name, estimator, center in estimators:
    print("Extracting the top %d %s..." % (n_components, name))
    t0 = time()
    data = faces
    if center:
        data = faces_centered
    estimator.fit(data)
    train_time = (time() - t0)
    print("done in %0.3fs" % train_time)
    if hasattr(estimator, 'cluster_centers_'):
        components_ = estimator.cluster_centers_
    else:
        components_ = estimator.components_

    # Plot an image representing the pixelwise variance provided by the
    # estimator e.g its noise_variance_ attribute. The Eigenfaces estimator,
    # via the PCA decomposition, also provides a scalar noise_variance_
    # (the mean of pixelwise variance) that cannot be displayed as an image
    # so we skip it.
    if (hasattr(estimator, 'noise_variance_') and
            estimator.noise_variance_.ndim > 0):  # Skip the Eigenfaces case
        plot_gallery("Pixelwise variance",
                     estimator.noise_variance_.reshape(1, -1), n_col=1,
                     n_row=1)
    plot_gallery('%s - Train time %.1fs' % (name, train_time),
                 components_[:n_components])

plt.show()

# #############################################################################
# Various positivity constraints applied to dictionary learning.
estimators = [
    ('Dictionary learning',
        decomposition.MiniBatchDictionaryLearning(n_components=15, alpha=0.1,
                                                  n_iter=50, batch_size=3,
                                                  random_state=rng),
     True),
    ('Dictionary learning - positive dictionary',
        decomposition.MiniBatchDictionaryLearning(n_components=15, alpha=0.1,
                                                  n_iter=50, batch_size=3,
                                                  random_state=rng,
                                                  positive_dict=True),
     True),
    ('Dictionary learning - positive code',
        decomposition.MiniBatchDictionaryLearning(n_components=15, alpha=0.1,
                                                  n_iter=50, batch_size=3,
                                                  fit_algorithm='cd',
                                                  random_state=rng,
                                                  positive_code=True),
     True),
    ('Dictionary learning - positive dictionary & code',
        decomposition.MiniBatchDictionaryLearning(n_components=15, alpha=0.1,
                                                  n_iter=50, batch_size=3,
                                                  fit_algorithm='cd',
                                                  random_state=rng,
                                                  positive_dict=True,
                                                  positive_code=True),
     True),
]


# #############################################################################
# Plot a sample of the input data

plot_gallery("First centered Olivetti faces", faces_centered[:n_components],
             cmap=plt.cm.RdBu)

# #############################################################################
# Do the estimation and plot it

for name, estimator, center in estimators:
    print("Extracting the top %d %s..." % (n_components, name))
    t0 = time()
    data = faces
    if center:
        data = faces_centered
    estimator.fit(data)
    train_time = (time() - t0)
    print("done in %0.3fs" % train_time)
    components_ = estimator.components_
    plot_gallery(name, components_[:n_components], cmap=plt.cm.RdBu)

plt.show()