机器学习---支持向量机(SVM)算法应用（下）

利用SVM进行人脸识别实例：

源码

# !/usr/bin/env python# -*- coding: utf-8 -*-# Author: Justin Chan#在python2.x版本中要使用Python3.x的特性,可以使用__future__模块导入相应的接口，减少对当前低版本影响#from __future__ import print_function#计时，程序运行时间from time import time#打印程序进展时的一些信息import logging#最后识别出来的人脸通过绘图打印出来import matplotlib.pyplot as plt#当import 一个模块比如如下模块cross_validation时，会有删除横线，表示该模块在当前版本可能已经被删除,在新版本中改为model_selection模块#DeprecationWarning: This module was deprecated in version 0.18 in favor of the model_selection module into which all the refactored classes and functions are moved. Also note that the interface of the new CV iterators are different from that of this module. This module will be removed in 0.20."This module will be removed in 0.20.", DeprecationWarning)#from sklearn.cross_validation import train_test_splitfrom sklearn.model_selection import train_test_splitfrom sklearn.datasets import fetch_lfw_people#grid_search已经被移除#from sklearn.grid_search import GridSearchCVfrom sklearn.model_selection import GridSearchCVfrom sklearn.metrics import classification_reportfrom sklearn.decomposition import RandomizedPCAfrom sklearn.svm import SVC#导入混淆矩阵模块confusion_matrix()from sklearn.metrics import confusion_matrixprint(__doc__)# Display progress logs on stdout程序进展的信息打印出来logging.basicConfig(level=logging.INFO, format='%(asctime)s %(message)s')################################################################################ Download the data, if not already on disk and load it as numpy arrays#下载人脸库 http://vis-www.cs.umass.edu/lfw/lfw_people = fetch_lfw_people(min_faces_per_person=70, resize=0.4)# introspect the images arrays to find the shapes (for plotting)n_samples, h, w = lfw_people.images.shape# for machine learning we use the 2 data directly (as relative pixel# positions info is ignored by this model)#获取特征向量矩阵X = lfw_people.data#特征向量的维度(列数)或者称特征点的个数n_features = X.shape[1]# the label to predict is the id of the person#返回每一组的特征标记y = lfw_people.targettarget_names = lfw_people.target_names#返回多少类(多少行)，也就是多少个人进行人脸识别n_classes = target_names.shape[0]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#将数据集拆分成四个部分X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25)################################################################################PCA降维方法，减少特征值，降低复杂度。# 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)print("done in %0.3fs" % (time() - t0))#提取特征值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 modelprint("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='auto'), param_grid)clf = GridSearchCV(SVC(kernel='rbf'), 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_)################################################################################ 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()

运行结果

NoneTotal dataset size:n_samples: 1288n_features: 1850n_classes: 7Extracting the top 150 eigenfaces from 966 faces/usr/local/lib/python3.5/dist-packages/sklearn/utils/deprecation.py:58: DeprecationWarning: Class RandomizedPCA is deprecated; RandomizedPCA was deprecated in 0.18 and will be removed in 0.20. Use PCA(svd_solver='randomized') instead. The new implementation DOES NOT store whiten ``components_``. Apply transform to get them.  warnings.warn(msg, category=DeprecationWarning)done in 0.077sProjecting the input data on the eigenfaces orthonormal basisdone in 0.010sFitting the classifier to the training setdone in 23.559sBest estimator found by grid search:SVC(C=1000.0, cache_size=200, class_weight=None, coef0=0.0,  decision_function_shape='ovr', degree=3, gamma=0.005, kernel='rbf',  max_iter=-1, probability=False, random_state=None, shrinking=True,  tol=0.001, verbose=False)Predicting people's names on the test setdone in 0.056s                   precision    recall  f1-score   support     Ariel Sharon       1.00      0.60      0.75        20     Colin Powell       0.80      0.85      0.82        55  Donald Rumsfeld       0.96      0.71      0.81        31    George W Bush       0.79      0.99      0.88       128Gerhard Schroeder       0.83      0.83      0.83        24      Hugo Chavez       1.00      0.59      0.74        27       Tony Blair       1.00      0.73      0.84        37      avg / total       0.86      0.84      0.84       322[[ 12   2   1   5   0   0   0] [  0  47   0   8   0   0   0] [  0   4  22   5   0   0   0] [  0   1   0 127   0   0   0] [  0   1   0   3  20   0   0] [  0   2   0   6   3  16   0] [  0   2   0   7   1   0  27]]

预测与真实结果

生成结果