PCA-小麦分类预处理之降维

from sklearn.decomposition import PCA
from sklearn.linear_model import LogisticRegression
import matplotlib.pyplot as plt
import numpy 
import pandas as pd

fp=open('seeds_dataset.txt','r')
ls=[]
for line in fp:
    line=line.strip('\n')   #将\n去掉
    ls.append(line.split('\t'))   #将空格作为分隔符将一个字符切割成一个字符数组
fp.close()
ls=numpy.array(ls,dtype=float)   #将其转换成numpy的数组，并定义数据类型为float
print(ls)

# 将文件转为DataFrame表格
ls_pd = pd.DataFrame(ls)

ls_pd.loc[:,1:6]

y = ls_pd.loc[:,7]

from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
data_std = sc.fit_transform(ls_pd.loc[:,1:6])

pca = PCA(n_components = 2) #加载PCA算法，设置降维后主成分数目为2
reduced_x = pca.fit_transform(data_std) #对样本进行降维

reduced_x

red_x,red_y=[],[]
blue_x,blue_y=[],[]
green_x,green_y=[],[]
for i in range(len(reduced_x)):
    if y[i] == 1:
        red_x.append(reduced_x[i][0])
        red_y.append(reduced_x[i][1])
    elif y[i] == 2:
        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])

#可视化
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()