数据预处理PCA，标准化

Posted 2021-02-07 chengziaichiyu

1.PCA

from sklearn.decomposition import RandomizedPCA

# 100维度
n_components = 100
pca = RandomizedPCA(n_components=n_components, whiten=True).fit(x_train) 


# 将降维的再调回去
eigenfaces = pca.components_.reshape((n_components, h, w))

# 特征提取
x_train_pca = pca.transform(x_train)
x_test_pca = pca.transform(x_test)

 

2.标准化

from sklearn import preprocessing
import numpy as np
X = np.array([[ 1., -1.,  2.],[ 2.,  0.,  0.],[ 0.,  1., -1.]])
scaler= preprocessing.MinMaxScaler(feature_range=(-1, 1)).fit(X)
X_scaled = scaler.transform(X)

# 将标准化的数据转化为原数据
X1=scaler.inverse_transform(X_scaled)