用python做主成分分析(PCA)

import相关工具箱：

from sklearn.decomposition import PCA
from sklearn.preprocessing import normalize

L2-normalization（可选）:

def l2_norm(data):
    for i in range(data.shape[0]):
        data[i, :] = normalize(data[i, :].reshape((1, -1)), norm='l2')  # L2归一化
    return data
train_annotated_feature = l2_norm(train_annotated_feature)
train_candidates_feature = l2_norm(train_candidates_feature)
test_annotated_feature = l2_norm(test_annotated_feature)
test_candidates_feature = l2_norm(test_candidates_feature)

用train_annotated_feature数据训练PCA模型，然后对其他数据进行主成分分析：

pca = PCA(n_components=300, copy=True, whiten=False)    # 降维到300dimensions
pca.fit(train_annotated_feature)

pca_train_annotated_feature = pca.transform(train_annotated_feature)
pca_train_candidates_feature = pca.transform(train_candidates_feature)
pca_test_annotated_feature = pca.transform(test_annotated_feature)
pca_test_candidates_feature = pca.transform(test_candidates_feature)