sklearn中的pca

import numpy as np
import matplotlib.pyplot as plt

### scikit-learn中的PCA

from sklearn.decomposition import PCA


x = np.empty((100,2))
x[:,0] = np.random.uniform(0.,100,size = 100)
x[:,1] = 0.75 * x[:,0] + 3. + np.random.normal(0,10,size = 100)

pca = PCA(n_components=1)
pca.fit(x)


pca.components_

x_reduction = pca.transform(x)
x_reduction.shape

x_restore =  pca.inverse_transform(x_reduction)
x_restore.shape

plt.scatter(x[:,0],x[:,1],color = 'b')

plt.scatter(x_restore[:,0],x_restore[:,1],color = 'r')
plt.show()

%%time
#如果不知道n_components设置多少合适的话，可以直接传入0~1的数，表示pca.explained_variance_ratio_可以解释的范围
pca = PCA(0.95)
pca.fit(x_train)
x_train_reduction = pca.transform(x_train)
x_test_reduction = pca.transform(x_test)
knn = KNeighborsClassifier()
knn.fit(x_train_reduction,y_train)
print(pca.n_components)
knn.score(x_test_reduction,y_test)