#本例為人臉識別的SVM演算法
#首先fetch_lfw_people匯入資料
#其次對資料進行處理，首先得到X,y,分割資料集為訓練集和測試集,PCA降維,然後訓練
#最後檢視正確率，classification_report以及confusion_matrix 以及繪製出特徵圖和預測結果
from __future__ import print_function

from time import time
import logging#程式進展資訊
import matplotlib.pyplot as plt

import PIL
from sklearn.model_selection import train_test_split#分割資料集
#from sklearn.cross_validation import train_test_split
from sklearn.datasets import fetch_lfw_people#下載資料集
from sklearn.model_selection import GridSearchCV
#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.decomposition import PCA
from sklearn.svm import SVC


print(__doc__)#輸出檔案開頭註釋的內容"""  """

# Display progress logs on stdout
logging.basicConfig(level=logging.INFO, format='%(asctime)s %(message)s')


###############################################################################
# Download the data, if not already on disk and load it as numpy arrays

lfw_people = fetch_lfw_people(min_faces_per_person=70, resize=0.4)
#print(lfw_people)
# introspect the images arrays to find the shapes (for plotting)
n_samples, h, w = lfw_people.images.shape#影象矩陣的行h,列w
#print(n_samples,h,w)

# for machine learning we use the 2 data directly (as relative pixel
# positions info is ignored by this model)
X = lfw_people.data#圖片資料
n_features = X.shape[1]#特徵點資料

# the label to predict is the id of the person
y = lfw_people.target#y是label,有7個目標時，0-6之間取值
target_names = lfw_people.target_names#實際有哪些名字,這個是一個字串
n_classes = target_names.shape[0]#shape[0]--行維數 shape[1]--列維數
#print(target_names)

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


###############################################################################
# Split into a training set and a test set using a stratified k fold

# split into a training and testing set
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.25)


###############################################################################
# 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)
pca =PCA(svd_solver='randomized',n_components=n_components,whiten=True)
pca.fit(X,y)#訓練如何降維
print("done in %0.3fs" % (time() - t0))


eigenfaces = pca.components_.reshape((n_components,h,w))#三維
#eigenfaces = pca.components_.reshape((n_components, h, w))


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


###############################################################################
# Train a SVM classification model

print("Fitting the classifier to the training set")
t0 = time()
param_grid = {'C': [1e3, 998, 1001, 999, 1002],
              'gamma': [0.0025, 0.003, 0.0035], }#不停縮小範圍
#clf = GridSearchCV(SVC(kernel='rbf', class_weight='auto'), param_grid)
clf=GridSearchCV(SVC(kernel='rbf',class_weight=None),param_grid)#GridSearchCV()第一個引數是分類器
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_)


###############################################################################
# Quantitative 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)))

###############################################################################
# Qualitative 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(())

# 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)

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)

# 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()