Fork me on GitHub

Faces dataset decompositionsΒΆ

This example applies to The Olivetti faces dataset different unsupervised matrix decomposition (dimension reduction) methods from the module sklearn.decomposition (see the documentation chapter Decomposing signals in components (matrix factorization problems)) .

  • ../../_images/plot_faces_decomposition_001.png
  • ../../_images/plot_faces_decomposition_002.png
  • ../../_images/plot_faces_decomposition_003.png
  • ../../_images/plot_faces_decomposition_004.png
  • ../../_images/plot_faces_decomposition_005.png
  • ../../_images/plot_faces_decomposition_006.png
  • ../../_images/plot_faces_decomposition_007.png
  • ../../_images/plot_faces_decomposition_008.png
  • ../../_images/plot_faces_decomposition_009.png

Script output:

Dataset consists of 400 faces
Extracting the top 6 Eigenfaces - RandomizedPCA...
done in 0.327s
Extracting the top 6 Non-negative components - NMF...
done in 2.391s
Extracting the top 6 Independent components - FastICA...
done in 2.360s
Extracting the top 6 Sparse comp. - MiniBatchSparsePCA...
done in 1.537s
Extracting the top 6 MiniBatchDictionaryLearning...
done in 1.300s
Extracting the top 6 Cluster centers - MiniBatchKMeans...
done in 0.292s
Extracting the top 6 Factor Analysis components - FA...
done in 2.775s

Python source code: plot_faces_decomposition.py

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
dataset = fetch_olivetti_faces(shuffle=True, random_state=rng)
faces = dataset.data

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):
    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=plt.cm.gray,
                   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 - RandomizedPCA',
     decomposition.RandomizedPCA(n_components=n_components, 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=2),
     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_
    if hasattr(estimator, 'noise_variance_'):
        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()

Total running time of the example: 13.54 seconds ( 0 minutes 13.54 seconds)

Previous