特征工程(八)特征工程案例分析(1)—面部识别
1、加载面部识别数据集
from sklearn.datasets import fetch_lfw_people
import numpy as np
from sklearn.decomposition import PCA
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import GridSearchCV
from sklearn.metrics import confusion_matrix, accuracy_score
from sklearn.pipeline import Pipeline
import matplotlib as mpl
# 解决中文乱码
mpl.rcParams['font.sans-serif'] = [u'SimHei']
mpl.rcParams['axes.unicode_minus'] = False
%matplotlib inline
'''
数据
'''
# 加载数据，每个人至少有70个人脸数据
lfw_people = fetch_lfw_people(min_faces_per_person=70, resize=0.4)
如果加载失败，可以参考sklearn导入人脸图片fetch_lfw_people出错如何解决？
2、数据探索
'''
探索性数据分析
'''
# 画出一个样本的图像
plt.imshow(X[0].reshape(50, 37), cmap=plt.cm.gray)
lfw_people.target_names[y[0]]
# 将特征缩放后，再次画出图像
from sklearn.preprocessing import StandardScaler
plt.imshow(StandardScaler().fit_transform(X)[0].reshape(50, 37), cmap=plt.cm.gray)
lfw_people.target_names[y[0]]
# 可以看见，图像略有不同，脸部周围的像素变暗了
n_classes = lfw_people.target_names.shape[0]
n_samples = X.shape[0]
n_features = X.shape[1]
print('类别数目:{}'.format(n_classes))
print('样本的数目:{}'.format(n_samples))
print('特征数目:{}'.format(n_features))
3、应用面部识别
'''
应用面部识别
'''
# 将数据分割为训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=1)
# 在数据集上进行主成分分析(PCA).
# PCA实例化
pca = PCA(n_components=200, whiten=True)
print("Extracting the top %d eigenfaces from %d faces" % (200, X_train.shape[0]))
# 创建流水线
pca_pipe = Pipeline([
('scale', StandardScaler()),
('pca', pca)
])
# 拟合流水线
pca_pipe.fit_transform(X_train)
# 从流水线取PCA
extracted_pca = pca_pipe.steps[1][1]
# 创建函数，绘制PCA的主成分
components = extracted_pca.components_
def plot_pca_components(images, n_col, n_row):
plt.figure(figsize=(2.0 * n_col, 2.26 * n_row))
plt.suptitle("pca_components", size=16)
for i, comp in enumerate(images):
plt.subplot(n_row, n_col, i + 1)
plt.imshow(
comp.reshape((50, 37)),
cmap=plt.cm.gray,
vmin=comp.min(),
vmax=comp.max()
)
plt.xticks(())
plt.yticks(())
plt.subplots_adjust(0.01, 0.05, 0.99, 0.93, 0.04, 0.0)
plt.show()
# 绘制前16个
plot_pca_components(components[:16], 4, 4)
# 可以看到每行每列的PCA主成分
# 每个主成分包括了可以区分不同人脸的重要信息
import itertools
# 绘制混淆矩阵
def plot_confusion_matrix(cm, classes,
normalize=False,
title='Confusion matrix',
cmap=plt.cm.Blues):
"""
This function prints a more readable confusion matrix with heat labels and options for noramlization
Normalization can be applied by setting `normalize=True`.
"""
plt.imshow(cm, interpolation='nearest', cmap=cmap)
plt.title(title)
plt.colorbar()
tick_marks = np.arange(len(classes))
plt.xticks(tick_marks, classes, rotation=45)
plt.yticks(tick_marks, classes)
thresh = cm.max() / 2.
for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):
plt.text(j, i, cm[i, j],
horizontalalignment="center",
color="white" if cm[i, j] > thresh else "black")
plt.ylabel('True label')
plt.xlabel('Predicted label')
'''
不使用PCA，查看一下差异
'''
lr = LogisticRegression()
param = {
'C':[1e-2, 1e-1, 1e0, 1e1, 1e2]
}
grid = GridSearchCV(
lr,
param
)
grid.fit(X_train, y_train)
best_clf = grid.best_estimator_
# 测试集进行预测
y_pred = best_clf.predict(X_test)
target_names = lfw_people.target_names
print("精确率:{}".format(accuracy_score(y_pred, y_test)))
print(
plot_confusion_matrix(
confusion_matrix(y_test, y_pred, labels=range(n_classes)) , target_names
)
)
# 不使用pca达到了81.9%的准确率
'''
使用PCA，查看一下差异
'''
lr = LogisticRegression()
pca_pipe = Pipeline(
[
('pca',PCA(n_components=200)),
('lr', lr)
]
)
pipe_param = {
'lr__C':[1e-2, 1e-1, 1e0, 1e1, 1e2]
}
grid = GridSearchCV(
pca_pipe,
pipe_param
)
grid.fit(X_train, y_train)
best_clf = grid.best_estimator_
# 测试集进行预测
y_pred = best_clf.predict(X_test)
target_names = lfw_people.target_names
print("精确率:{}".format(accuracy_score(y_pred, y_test)))
print(
plot_confusion_matrix(
confusion_matrix(y_test, y_pred, labels=range(n_classes)) , target_names
)
)
# 可以看到准确率下降了
'''
做一个网格搜索，寻找最佳模型和准确率
'''
def get_best_model_and_accuracy(model, params, X, y):
grid = GridSearchCV(model, # 要搜索的模型
params, # 要尝试的参数
error_score=0.0 # 如果报错，结果为0
)
# 拟合模型和参数
grid.fit(X, y)
# 经典的性能指标
print('最佳的准确率为：{}'.format(grid.best_score_))
# 得到最佳准确率的最佳参数
print('得到最佳准确率的最佳参数：{}'.format(grid.best_params_))
# 拟合的平均时间
print('拟合的平均时间：{} 秒'.format(round(grid.cv_results_['mean_fit_time'].mean(), 3)))
# 预测的平均时间
print('预测的平均时间：{} 秒'.format(round(grid.cv_results_['mean_score_time'].mean(), 3)))
# 创建网格流水线
face_params = {'lr__C':[1e-2, 1e-1, 1e0, 1e1, 1e2],
'preprocessing__pca__n_components':[100, 150, 200, 250, 300],
'preprocessing__pca__whiten':[True, False],
'preprocessing__lda__n_components':range(1, 7)
# [1, 2, 3, 4, 5, 6] recall the max allowed is n_classes-1
}
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
pca = PCA()
lda = LinearDiscriminantAnalysis()
preprocessing = Pipeline([
('scale', StandardScaler()),
('pca', pca),
('lda', lda)
])
face_pipeline = Pipeline(
[
('preprocessing', preprocessing),
('lr', LogisticRegression())
]
)
get_best_model_and_accuracy(face_pipeline, face_params, X, y)
# 可以看到准确率提高了，而且预测速度很快
