PYTHON

pca python

import numpy as np
from sklearn.decomposition import PCA

pca = PCA(n_components = 3) # Choose number of components
pca.fit(X) # fit on X_train if train/test split applied

print(pca.explained_variance_ratio_)

pca python

from sklearn.decomposition import PCA
pca = PCA(n_components=2)
X_train = pca.fit_transform(X_train)
X_test = pca.transform(X_test)

pca python

from sklearn.decomposition import PCA

pca = PCA(n_components=3)
pca.fit(features)
features_pca = pca.transform(features)
print("original shape:   ", features.shape)
print("transformed shape:", features_pca.shape)
print(pca.explained_variance_)
print(pca.explained_variance_ratio_)

pca in python

def pca(data, n):
    data = np.array(data)

    # 均值
    mean_vector = np.mean(data, axis=0)

    # 协方差
    cov_mat = np.cov(data - mean_vector, rowvar=0)

    # 特征值 特征向量
    fvalue, fvector = np.linalg.eig(cov_mat)

    # 排序
    fvaluesort = np.argsort(-fvalue)

    # 取前几大的序号
    fValueTopN = fvaluesort[:n]

    # 保留前几大的数值
    newdata = fvector[:, fValueTopN]

    new = np.dot(data, newdata)

    return new