【Python-ML】SKlearn库特征抽取-PCA

# -*- coding: utf-8 -*-
'''
Created on 2018年1月18日
@author: Jason.F
@summary: 特征抽取-PCA方法，无监督、线性
'''
import pandas as pd
import numpy as np
from sklearn.cross_validation import train_test_split
from sklearn.preprocessing import MinMaxScaler
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
import matplotlib.pyplot as plt
from matplotlib.colors import ListedColormap
from sklearn.decomposition import PCA
#定义绘制函数
def plot_decision_regions(X, y, classifier, resolution=0.02):

    # setup marker generator and color map
    markers = ('s', 'x', 'o', '^', 'v')
    colors = ('red', 'blue', 'lightgreen', 'gray', 'cyan')
    cmap = ListedColormap(colors[:len(np.unique(y))])

    # plot the decision surface
    x1_min, x1_max = X[:, 0].min() - 1, X[:, 0].max() + 1
    x2_min, x2_max = X[:, 1].min() - 1, X[:, 1].max() + 1
    xx1, xx2 = np.meshgrid(np.arange(x1_min, x1_max, resolution),
                           np.arange(x2_min, x2_max, resolution))
    Z = classifier.predict(np.array([xx1.ravel(), xx2.ravel()]).T)
    Z = Z.reshape(xx1.shape)
    plt.contourf(xx1, xx2, Z, alpha=0.4, cmap=cmap)
    plt.xlim(xx1.min(), xx1.max())
    plt.ylim(xx2.min(), xx2.max())

    # plot class samples
    for idx, cl in enumerate(np.unique(y)):
        plt.scatter(x=X[y == cl, 0], y=X[y == cl, 1],
                    alpha=0.8, c=cmap(idx),
                    marker=markers[idx], label=cl)
        
#第一步:导入数据，对原始d维数据集做标准化处理
df_wine = pd.read_csv('https://archive.ics.uci.edu/ml/machine-learning-databases/wine/wine.data',header=None)
df_wine.columns=['Class label','Alcohol','Malic acid','Ash','Alcalinity of ash','Magnesium','Total phenols','Flavanoids','Nonflavanoid phenols','Proanthocyanins','Color intensity','Hue','OD280/OD315 of diluted wines','Proline']
print ('class labels:',np.unique(df_wine['Class label']))
#print (df_wine.head(5))
#分割训练集合测试集
X,y=df_wine.iloc[:,1:].values,df_wine.iloc[:,0].values
X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.3,random_state=0)
#特征值缩放-标准化
stdsc=StandardScaler()
X_train_std=stdsc.fit_transform(X_train)
X_test_std=stdsc.fit_transform(X_test)
#第二步：PCA降维
pca=PCA(n_components=2)#参数设置选择前2个方差最大的特征
lr=LogisticRegression()
X_train_pca=pca.fit_transform(X_train_std)
X_test_pca=pca.fit_transform(X_test_std)
lr.fit(X_train_pca,y_train)
plot_decision_regions(X_train_pca,y_train,classifier=lr)
plt.xlabel('PC1')
plt.ylabel('PC2')
plt.legend(loc='lower left')
plt.show()
plot_decision_regions(X_test_pca,y_test,classifier=lr)
plt.xlabel('PC1')
plt.ylabel('PC2')
plt.legend(loc='lower left')
plt.show()

#观察不同主成分的防线贡献率
pca_all=PCA(n_components=None)#None值保留所有成分
X_train_pca_all=pca_all.fit_transform(X_train_std)
print (pca_all.explained_variance_ratio_)

结果：

('class labels:', array([1, 2, 3], dtype=int64))
[ 0.37329648  0.18818926  0.10896791  0.07724389  0.06478595  0.04592014
  0.03986936  0.02521914  0.02258181  0.01830924  0.01635336  0.01284271
  0.00642076]