#本例为人脸识别的SVM算法#首先fetch_lfw_people导入数据#其次对数据进行处理，首先得到X,y,分割数据集为训练集和测试集,PCA降维,然后训练#最后查看正确率，classification_report以及confusion_matrix 以及绘制出特征图和预测结果from __future__ import print_functionfrom time import timeimport logging#程序进展信息import matplotlib.pyplot as pltimport PILfrom sklearn.model_selection import train_test_split#分割数据集#from sklearn.cross_validation import train_test_splitfrom sklearn.datasets import fetch_lfw_people#下载数据集from sklearn.model_selection import GridSearchCV#from sklearn.grid_search import GridSearchCVfrom sklearn.metrics import classification_reportfrom sklearn.metrics import confusion_matrix#from sklearn.decomposition import RandomizedPCAfrom sklearn.decomposition import PCAfrom sklearn.svm import SVCprint(__doc__)#输出文件开头注释的内容""" """# Display progress logs on stdoutlogging.basicConfig(level=logging.INFO, format='%(asctime)s %(message)s')################################################################################ Download the data, if not already on disk and load it as numpy arrayslfw_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#图像矩阵的行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#图片数据n_features = X.shape[1]#特征点数据# the label to predict is the id of the persony = lfw_people.target#y是label,有7个目标时，0-6之间取值target_names = lfw_people.target_names#实际有哪些名字,这个是一个字符串n_classes = target_names.shape[0]#shape[0]--行维数 shape[1]--列维数#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 setX_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 reductionn_components = 150print("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)#训练如何降维print("done in %0.3fs" % (time() - t0))eigenfaces = ponents_.reshape((n_components,h,w))#三维#eigenfaces = ponents_.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 modelprint("Fitting the classifier to the training set")t0 = time()param_grid = {'C': [1e3, 998, 1001, 999, 1002],'gamma': [0.0025, 0.003, 0.0035], }#不停缩小范围#clf = GridSearchCV(SVC(kernel='rbf', class_weight='auto'), param_grid)clf=GridSearchCV(SVC(kernel='rbf',class_weight=None),param_grid)#GridSearchCV()第一个参数是分类器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 setprint("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 matplotlibdef 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 setdef 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 eigenfaceseigenface_titles = ["eigenface %d" % i for i in range(eigenfaces.shape[0])]plot_gallery(eigenfaces, eigenface_titles, h, w)plt.show()
