python机器学习应用案例---PCA

因为之前也没有见过什么数据，所以就将数据集打印到文件，新手可以一起看一看，高手就不用在看了。

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

data = load_iris()
y = data.target
x = data.data
f = open("./iris_data.txt", "w+") #输入到文件,打开文件
print("%d"%len(x))
sum_lst = []
for i in range(len(x)):
    lst = []
    lst.append(x[i])
    lst.append(y[i])
    sum_lst.append(lst)           #将data and label 配成一对
    print(lst, file=f)            #逐对打出
print(sum_lst, file=f)            #一次性打出来
f.close()                         #关闭文件
pca = PCA(n_components=2)
reduced_x = pca.fit_transform(x)

red_x, red_y = [], []
blue_x, blue_y = [], []
green_x, green_y = [], []

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])

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()