PCA主成分分析_特征创建(数据挖掘入门与实践-实验8)

##############################数据处理
#数据导入 $$ 数据转换
import os
import numpy as np
import pandas as pd
from collections import defaultdict

def convert_number():
    try:
        return float(x)
    except ValueError:
        return np.nan

converters=defaultdict(convert_number)
converters[1558]=lambda x: 1 if x.strip() == "ad." else 0

#问号处理
for i in range(0,1558):
    converters[i]=lambda x: np.nan if x.strip() == "?" else x
ads=pd.read_csv("ad.data",header=None,converters=converters)
ads.head()

#特征抽取
ads.dropna(inplace=True)
X=ads.drop(1558,axis=1).values
y=ads[1558]
X[:5]

#############################主成分分析
from sklearn.decomposition import PCA
pca=PCA(n_components=5)
Xd=pca.fit_transform(X)

np.set_printoptions(precision=3,suppress=True)
pca.explained_variance_ratio_

##PCA评估
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import cross_val_score
clf=DecisionTreeClassifier()
scores_reduced=cross_val_score(clf,Xd,y,scoring='accuracy')
print("the accuracy is {0:.1f}%".format(100*np.mean(scores_reduced)))

#作图
%matplotlib inline
from matplotlib import pyplot as plt
#类别获取
classes=set(y)
#颜色指定
colors=['red','green']
for cur_class,color in zip(classes,colors):
    mask=(y==cur_class).values
    plt.scatter(Xd[mask,0], Xd[mask,1], marker='o', color=color, label=int(cur_class))
plt.legend() 
plt.show()