In [43]:

    

%matplotlib inline
from __future__ import print_function

from time import time
import logging
import matplotlib.pyplot as plt

from sklearn.cross_validation import train_test_split
from sklearn.datasets import fetch_lfw_people
from sklearn.grid_search import GridSearchCV
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
from sklearn.decomposition import RandomizedPCA
from sklearn.svm import SVC

print(__doc__)


    

    




Automatically created module for IPython interactive environment

In [44]:

    

lfw_people = fetch_lfw_people(min_faces_per_person=70, resize=0.4)


    

In [45]:

    

n_samples, h, w = lfw_people.images.shape
n_samples, h, w


    

    
Out[45]:





(1288, 50, 37)

In [46]:

    

X = lfw_people.data
n_features = X.shape[1]


    

In [47]:

    

y = lfw_people.target
target_names = lfw_people.target_names
n_classes = target_names.shape[0]


    

In [48]:

    

print("Total dataset size:")
print("n_samples: %d" % n_samples)
print("n_features: %d" % n_features)
print("n_classes: %d" % n_classes)


    

    




Total dataset size:
n_samples: 1288
n_features: 1850
n_classes: 7

In [18]:

    

# split into a training set and a test set using K fold
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.25, random_state=42)


    

In [36]:

    

# compute a PCA(eigenfaces) on the face dataset (treated as unlabeled)
# dataset ; unsupervised feature extraction / dimensionality reduction

n_components = 150
print("Extracting the top %d eigenfaces from %d faces"
      % (n_components, X_train.shape[0]))
t0 = time()
pca = RandomizedPCA(n_components=n_components, whiten=True).fit(X_train)
print("done in %0.3fs" % (time() - t0))

eigenfaces = pca.components_.reshape((n_components, h, w))

print("Projecting the input data on the eigenfaces orthonormal basis")
# 좌표 변환
X_train_pca = pca.transform(X_train)
X_test_pca = pca.transform(X_test)
print("done in %0.3fs" % (time() - t0))


    

    




Extracting the top 150 eigenfaces from 966 faces
done in 0.343s
Projecting the input data on the eigenfaces orthonormal basis
done in 0.368s

In [30]:

    

eigenfaces.shape


    

    
Out[30]:





(150, 50, 37)

In [37]:

    

# Train a SVM classification model

print("Fitting the classifier to the training set")
t0 = time()
param_grid = {'C': [1e3, 5e3, 1e4, 5e4, 1e5],
              'gamma': [0.0001, 0.0005, 0.001, 0.005, 0.01, 0.1], }
clf = GridSearchCV(SVC(kernel='rbf', class_weight='balanced'), param_grid)
clf = clf.fit(X_train_pca, y_train)
print("done in %0.3fs" % (time() - t0))
print("Best estimator found by grid search:")
print(clf.best_estimator_)


    

    




Fitting the classifier to the training set
done in 21.898s
Best estimator found by grid search:
SVC(C=1000.0, cache_size=200, class_weight='balanced', coef0=0.0,
  decision_function_shape=None, degree=3, gamma=0.001, kernel='rbf',
  max_iter=-1, probability=False, random_state=None, shrinking=True,
  tol=0.001, verbose=False)

In [55]:

    

# Qualitative evaluation of the model quality on the test set

print("Predicting people's names on the test set")
t0 = time()
y_pred = clf.predict(X_test_pca)
print("done in %0.3fs" % (time() - t0))

print(classification_report(y_test, y_pred, target_names=target_names))
print(confusion_matrix(y_test, y_pred, labels=range(n_classes)))


    

    




Predicting people's names on the test set
done in 0.078s
                   precision    recall  f1-score   support

     Ariel Sharon       0.67      0.77      0.71        13
     Colin Powell       0.80      0.85      0.82        60
  Donald Rumsfeld       0.71      0.74      0.73        27
    George W Bush       0.85      0.88      0.86       146
Gerhard Schroeder       0.83      0.76      0.79        25
      Hugo Chavez       0.80      0.80      0.80        15
       Tony Blair       0.89      0.67      0.76        36

      avg / total       0.82      0.82      0.82       322

[[ 10   0   0   2   1   0   0]
 [  3  51   0   4   0   1   1]
 [  1   1  20   4   0   1   0]
 [  0   9   6 128   0   1   2]
 [  0   0   0   6  19   0   0]
 [  1   0   0   1   1  12   0]
 [  0   3   2   5   2   0  24]]

In [56]:

    

# Qualititative evaluation of the predictions using matplotlib

def plot_gallery(images, titles, h, w, n_row=3, n_col=4):
    """Helper function to plot a gallery of portraits"""
    plt.figure(figsize=(1.8 * n_col, 2.4 * n_row))
    plt.subplots_adjust(bottom=0, left=.01, right=.99, top=.90, hspace=.35)
    for i in range(n_row * n_col):
        plt.subplot(n_row, n_col, i + 1)
        plt.imshow(images[i].reshape((h, w)), cmap=plt.cm.gray)
        plt.title(titles[i], size=12)
        plt.xticks(())
        plt.yticks(())


    

In [63]:

    

# plot the result of the prediction on a portion of the test set

def title(y_pred, y_test, target_names, i):
    pred_name = target_names[y_pred[i]].rsplit(' ', 1)[-1]
    true_name = target_names[y_test[i]].rsplit(' ', 1)[-1]
    return 'predicted: %s\ntrue:      %s' % (pred_name, true_name)


    

In [67]:

    

prediction_titles = [title(y_pred, y_test, target_names, i)
                    for i in range(y_pred.shape[0])]

plot_gallery(X_test, prediction_titles, h, w)


    

In [71]:

    

# plot the gallery of the most significative eigenfaces

eigenface_titles = ["eigenface %d" % i for i in range(eigenfaces.shape[0])]
plot_gallery(eigenfaces, eigenface_titles, h, w)

plt.show()