python_adult_pca

#! /usr/bin/env python
#coding=utf-8
import pandas as pd
root="F:/Data/exe/3_adult/"#我没等网页全部加载出来就全选复制了，导致数据集未完整！！！！！！！！！！！！！
adult=pd.read_csv(root+"adult.data.txt",header=None)
adult.columns=(["Age","Work-Class","fnlwgt",
                "Education","Education-Num",
                "Matrital-Status","Occupation",
                "Relationship","Race","Sex",
                "Capital-gain","Capital-loss",
                "Hours-per-week","Native-Country","Earnings-Raw"])
#删除包含无效数字的行，inplace=True表示改动当前数据框而不是新建一个
adult.dropna(how="all",inplace=True)
#adult["Work-Class"].unique()#得到所有情况
adult["LongHours"]=adult["Hours-per-week"]>40
#应用了values得到的x和y就是矩阵和向量了，就可以按照矩阵和向量的数字法来取了
x=adult[["Age","Education-Num","Capital-gain","Capital-loss","Hours-per-week"]].values
y=(adult["Earnings-Raw"]==" >50K").values
from sklearn.feature_selection import SelectKBest
from sklearn.feature_selection import chi2
transformer=SelectKBest(score_func=chi2,k=3)
xt_chi2=transformer.fit_transform(x,y)#返回的是x的k个特征的列
#print transformer.scores_输出每个特征与y的相关性
#print type(xt_chi2)
#transformer.fit()得到的类型是SelectKBest这个类
#transformer.fit_transform()得到的类型是<type 'numpy.ndarray'>
#xt_chi2后面要带到cross_val_score()函数中，它对x的类型有要求
#用pearson相关系数判断相关性
#print x.shape[0]#shape[0]指行数，[1]指列数
from scipy.stats import pearsonr#pearsonr函数
import numpy as np
#pearsonr的参数为两个数组，返回的是相关系数和p值
def multivariate_pearsonr(x,y):
    scores,pvalues=[],[]#创建两个数组
    for column in range(x.shape[1]):
        cur_score,cur_p=pearsonr(x[:,column],y)
        scores.append(abs(cur_score))
        pvalues.append(cur_p)
    return np.array(scores),np.array(pvalues)
transformer=SelectKBest(score_func=multivariate_pearsonr,k=3)
xt_pearson=transformer.fit_transform(x,y)#返回的是x的k个特征的列
#print transformer.scores_
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import cross_val_score
clf=DecisionTreeClassifier(random_state=14)
scores_chi2=cross_val_score(clf,xt_chi2,y,scoring="accuracy")
print "精确度:{}".format(np.mean(scores_chi2))#精确度:0.828598676158
scores_pearson=cross_val_score(clf,xt_pearson,y,scoring="accuracy")
print "精确度:{}".format(np.mean(scores_pearson))#精确度:0.770645941597