数据挖掘-实验-SVM人脸识别


1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
#第1步:导入包

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

from sklearn.model_selection import train_test_split
from sklearn.model_selection import GridSearchCV
from sklearn.datasets import fetch_lfw_people
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
from sklearn.decomposition import PCA
from sklearn.svm import SVC

#第2步:输出进度日志

logging.basicConfig(level=logging.INFO, format='%(asctime)s %(message)s')

#第3步:下载数据并加载为numpy数组(如果是第一次运行,这一步需要花点儿时间去下载)

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

#第4步:获得图像数组的形状(用于绘图)

n_samples, h, w = lfw_people.images.shape
X = lfw_people.data
n_features = X.shape[1]
#预测的目标是人的ID
y = lfw_people.target
target_names = lfw_people.target_names
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)

#第5步:切分训练集和测试集

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=42)
t0 = time()
n_components = 150
pca = PCA(n_components=n_components, svd_solver='randomized',whiten=True).fit(X_train)
# 主成分分析进行降维(暂时不理解也没关系)
X_train_pca = pca.transform(X_train)
X_test_pca = pca.transform(X_test)
print("done in %0.3fs" % (time() - t0))

#第6步:训练SVM分类模型

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, cv=5, iid=False)
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_)

#第8步:在测试集上评估模型的量化效果

pca = PCA(n_components=n_components, svd_solver='randomized',whiten=True).fit(X_train)
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)))

#第9步:使用 matplotlib 定性分析预测结果

def plot_gallery(images, titles, h, w, n_row=3, n_col=4):
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(())

#第10步:绘制部分测试集的预测结果

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)

#第11步:几个最重要的特征脸的相册

plt.show()