import  matplotlib.pyplot as plt

from sklearn.decomposition import PCA

from sklearn.datasets import load_iris #加载鸢尾花数据集导入函数

data = load_iris()#加载数据，array([[5.1 3.5 1.4 0.2].....])

#print(data)

y = data.target #各50个 0,1,2 暂不明作用,

#print(y)

X = data.data

#print(X) #把array换成二维列表，数据不变

pca = PCA(n_components=2)#设置降维后主成分数目为2

reduce_X = pca.fit_transform(X) #对袁术数据进行降维[[-2.68412563  0.31939725]....]

print(reduce_X)

#按类别对降维后的数据进行保存

red_x, red_y = [], []

blue_x, blue_y = [], []

green_x, green_y = [], []

#按照鸢尾花的类别将降维后的数据点保存在不同的列表中

for i in range(len(reduce_X)):

    if y[i] == 0:

        red_x.append(reduce_X[i][0])

        red_y.append(reduce_X[i][1])

    elif y[i] == 1:

        blue_x.append(reduce_X[i][0])

        blue_y.append(reduce_X[i][1])

    else:

        green_x.append(reduce_X[i][0])

        green_y.append(reduce_X[i][1])

#可视化 散点图

plt.scatter(red_x, red_y, c='r', marker='x')

plt.scatter(blue_x, blue_y, c='b', marker='D')

plt.scatter(green_x, green_y, c='g', marker='.')

plt.show()