#-- coding:utf-8 --
from future import print_function#解決python2中的print問題
from time import time#記錄每段處理花費的時間
import logging#記錄進展的狀況
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split#分割資料集
from sklearn.model_selection import GridSearchCV
from sklearn.metrics import classification_report
from sklearn.datasets import fetch_lfw_people#用來下載下傳資料
from sklearn.metrics import confusion_matrix
from sklearn.decomposition import PCA
from sklearn.svm import SVC#支援向量機
print(doc)#輸出檔案開頭注釋的内容
logging.basicConfig(level=logging.INFO,format=’%(asctime)s%(message)s’)#INFO是指日志按照預處理進行 asctime指進展時間 message指進展内容
lfw_people=fetch_lfw_people(min_faces_per_person=70,resize=0.6)#下載下傳并導入資料
n_samples,h,w=lfw_people.images.shape
#print(lfw_people)
#print(n_samples)#樣本大小
print(h)#圖檔的多少
print(w)#次元
X=lfw_people.data#資料矩陣
#print(X)#
n_features=X.shape[1]#次元大小
#print(n_features)
Y=lfw_people.target#不同人的身份
target_names=lfw_people.target_names#特征向量的類别名 也就是對應的人名
n_class=target_names.shape[0]#有幾個人要區分識别
print(Y)
print(target_names)
print(n_class)
X_train,X_test,Y_train,Y_test=train_test_split(#train_test_split是sklearn自帶的一種劃分資料的函數
X,Y,test_size=0.65,random_state=49
)#訓練集 測試集 訓練集的label 測試集的label
print(X_train)
print(X_test)
print(Y_train)
print(Y_test)
#PCA降維
n_components=150#設定一個參數來進行降維炒作
print(“Extracting the top %d eigenfaces from %d faces”
% (n_components, X_train.shape[0]))
t0=time()
pca=PCA(n_components=n_components,svd_solver=‘randomized’,
whiten=True).fit(X_train)#降維并建立訓練集模型
print(“done in %0.3fs” % (time() - t0))#該過程花費多少時間
#print(pca)
eigenfaces=pca.components_.reshape((n_components,h,w))#人臉上的一些特征值
print(“Projecting the input data on the eigenfaces orthonormal basis”)
t0=time()
X_train_pca=pca.transform(X_train)#訓練集轉低維訓練集
X_test_pca=pca.transform(X_test)#測試集轉低維測試集
print(“done in %0.3fs” % (time() - t0))
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], }#gamma特征函數來建立不同的比例的核函數 對分類的精度來對比嘗試來組成的精度
clf=GridSearchCV(SVC(kernel=‘rbf’,class_weight=‘balanced’),
param_grid,cv=5)#rbf用來處理圖像的特征點,class_weight權重 param_grid核函數
#print(“clf:”,clf)
clf=clf.fit(X_train_pca,Y_train)#高次元模組化
print(“done in %0.3fs” % (time() - t0))
print(“Best estimator found by grid search:”)
print(clf.best_estimator_)
#進行預測和真實值之間的比較
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_class)))
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(())
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)
eigenface_titles=[“eigenface %d” % i for i in range(eigenfaces.shape[0])]
plot_gallery(eigenfaces,eigenface_titles,h,w)
plt.show()