基于SVM的人脸识别

#!/usr/bin/python
# -*- coding: utf-8 -*-
import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import fetch_lfw_people
import seaborn as sns; sns.set()
faces = fetch_lfw_people(min_faces_per_person=60)
#print(faces.head())
print(faces.target_names)
print(faces.images.shape)

fig, ax = plt.subplots(3, 5)
for i, axi in enumerate(ax.flat):
    axi.imshow(faces.images[i], cmap='bone')
    axi.set(xticks=[], yticks=[],
            xlabel=faces.target_names[faces.target[i]])
plt.show()

from sklearn.svm import SVC
#from sklearn.decomposition import RandomizedPCA
from sklearn.decomposition import PCA
from sklearn.pipeline import make_pipeline
#利用PCA技术将特征降到150维
pca = PCA(n_components=150, whiten=True, random_state=42)
svc = SVC(kernel='rbf', class_weight='balanced')
model = make_pipeline(pca, svc)
print(model)
from sklearn.model_selection import train_test_split
Xtrain, Xtest, ytrain, ytest = train_test_split(faces.data, faces.target,
                                                random_state=42)

#使用grid search cross-validation来选择我们的参数
from sklearn.grid_search import GridSearchCV
param_grid = {'svc__C': [1, 5, 10],
              'svc__gamma': [0.0001, 0.0005, 0.001]}
grid = GridSearchCV(model, param_grid=param_grid,cv=5)
grid.fit(Xtrain,ytrain)
print(grid.best_params_)


model = grid.best_estimator_
yfit = model.predict(Xtest)
print(yfit.shape)

fig, ax = plt.subplots(4, 6)
for i, axi in enumerate(ax.flat):
    axi.imshow(Xtest[i].reshape(62, 47), cmap='bone')
    axi.set(xticks=[], yticks=[])
    axi.set_ylabel(faces.target_names[yfit[i]].split()[-1],
                   color='black' if yfit[i] == ytest[i] else 'red')
fig.suptitle('Predicted Names; Incorrect Labels in Red', size=14)
plt.show()
from sklearn.metrics import classification_report
print(classification_report(ytest, yfit,
                            target_names=faces.target_names))
#精度(precision) = 正确预测的个数(TP)/被预测正确的个数(TP+FP)
#召回率(recall)=正确预测的个数(TP)/预测个数(TP+FN)
#F1 = 2精度召回率/(精度+召回率)
from sklearn.metrics import confusion_matrix
mat = confusion_matrix(ytest, yfit)
sns.heatmap(mat.T, square=True, annot=True, fmt='d', cbar=False,
            xticklabels=faces.target_names,
            yticklabels=faces.target_names)
plt.xlabel('true label')
plt.ylabel('predicted label')
plt.show()