mooc机器学习第四天-降维pca（主成分分析）

from sklearn.decomposition import PCA
from sklearn.datasets import load_iris
import matplotlib.pyplot as plt
from pylab import mpl

mpl.rcParams[‘font.sans-serif‘] = [‘SimHei‘] # 设置matplotlib可以显示汉语
mpl.rcParams[‘axes.unicode_minus‘] = False

def pca():
    data=load_iris() #载入数据到字典
    y = data.target  #数据属性
    X = data.data    #具体数值


    pca = PCA(n_components=2)  #主成分为2（降维二）
    reduced_x = pca.fit_transform(X)

    #分三类鸢尾花存值
    red_x,red_y=[],[]
    blue_x,blue_y=[],[]
    green_x,green_y=[],[]

    #把降维后的数据按target存值
    for i in range(len(reduced_x)):
        if y[i]==0:
            red_x.append(reduced_x[i][0])
            red_y.append(reduced_x[i][1])
        elif y[i]==1:
            blue_x.append(reduced_x[i][0])
            blue_y.append(reduced_x[i][1])
        else:
            green_x.append(reduced_x[i][0])
            green_y.append(reduced_x[i][1])


    #散点图绘制
    plt.scatter(red_x,red_y,c=‘r‘,marker=‘d‘)

    plt.scatter(blue_x,blue_y,c=‘b‘,marker=‘+‘)

    plt.scatter(green_x,green_y,c=‘g‘,marker=‘o‘)
    plt.title(‘鸢尾花PCA降维分析‘)
    plt.legend(loc=‘best‘)
    plt.show()


if __name__ == ‘__main__‘:
    pca()