https://blog.csdn.net/weixin_40123108/article/details/84378202
In [5]:
from time import time
import logging #程序进展信息
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split #分割数据集
# from sklearn.cross_validation import train_test_split
from sklearn.datasets import fetch_lfw_people #下载数据集
from sklearn.model_selection import GridSearchCV
# from sklearn.grid_search import GridSearchCV
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
# from sklearn.decomposition import RandomizedPCA
from sklearn.decomposition import PCA
from sklearn.svm import SVC
In [7]:
lfw_people = fetch_lfw_people(min_faces_per_person=70, resize=0.4)
In [8]:
print(lfw_people)
In [9]:
# for machine learning we use the 2 data directly (as relative pixel
# positions info is ignored by this model)
n_samples, h, w = lfw_people.images.shape # 图像矩阵的行h,列w
print(n_samples, h, w) # 1288 50 37
In [12]:
X = lfw_people.data #图片数据
X.shape
Out[12]:
In [13]:
n_features = X.shape[1] # 矩阵列数特征点数据1850
n_features
Out[13]:
In [14]:
# the label to predict is the id of the person
y = lfw_people.target # y是label,目标代号0,1,2,3，......
y
Out[14]:
In [16]:
target_names = lfw_people.target_names # 实际有哪些名字,这个是一个字符串
target_names
Out[16]:
In [18]:
n_classes = target_names.shape[0] #shape[0]--行维数 shape[1]--列维数
n_classes
Out[18]:
In [19]:
print("Total dataset size:")
print("n_samples: %d\nn_features: %d\nn_classes: %d" % (n_samples, n_features, n_classes))
In [20]:
# Split into a training set and a test set using a stratified k fold
# split into a training and testing set
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25)
print(X_train.shape, y_train.shape, X_test.shape, y_test.shape)
In [21]:
# Compute a PCA (eigenfaces) on the face dataset (treated as unlabeled
# dataset): unsupervised feature extraction / dimensionality reduction
n_components = 150
print("Extracting the top %d eigenfaces from %d faces"
% (n_components, X_train.shape[0]))
In [22]:
t0 = time()
# pca = RandomizedPCA(n_components=n_components, whiten=True).fit(X_train)
pca = PCA(svd_solver='randomized', n_components=n_components, whiten=True) #降低维度，提取特征，（此处特征值位度较高）
pca.fit(X, y) # 训练如何降维
print("done in %0.3fs" % (time() - t0))
In [23]:
eigenfaces = pca.components_.reshape((n_components, h, w)) # 三维
# eigenfaces = pca.components_.reshape((n_components, h, w))
In [24]:
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))
In [35]:
# Train a SVM classification model
print("Fitting the classifier to the training set")
t0 = time()
param_grid = {'C': [1e3, 998, 1001, 999, 1002],
'gamma': [0.0001, 0.003, 0.0035, 0.004, 0.0045], } # 不停缩小范围
# clf = GridSearchCV(SVC(kernel='rbf', class_weight='auto'), param_grid)
clf = GridSearchCV(SVC(kernel='rbf', class_weight=None), param_grid) # GridSearchCV()第一个参数是分类器
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_)
In [33]:
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)))
# Qualitative evaluation of the predictions using matplotlib
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(())
# plot the result of the prediction on a portion of the test set
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)
# plot the gallery of the most significative eigenfaces
eigenface_titles = ["eigenface %d" % i for i in range(eigenfaces.shape[0])]
plot_gallery(eigenfaces, eigenface_titles, h, w)
plt.show()
In [ ]:
