机器学习Python数据特征选定
16lz
2021-01-22
from pandas import read_csv
from numpy import set_printoptions
from sklearn.feature_selection import SelectKBest
from sklearn.feature_selection import chi2
from sklearn.feature_selection import RFE
from sklearn.linear_model import LogisticRegression
from sklearn.decomposition import PCA
from sklearn.ensemble import ExtraTreesClassifier
#本例数据集用的pima_Indians进行学习 下载地址 http://www.broadview.com.cn/33110
filename = 'pima_data.csv'
names = ['preg','plas','pres','skin','test','mass','pedi','age','class']
data = read_csv(filename,names = names)
array = data.values
X = array[:,0:8]
Y = array[:,8]
#单变量特征选定
test = SelectKBest(score_func=chi2,k=4)
fit = test.fit(X,Y)
set_printoptions(precision=3)
#print(fit.scores_)
features = fit.transform(X)
# print(features)
#RFR(递归特征消除)
'''使用一个基模型来进行多轮训练，每轮训练后消除若干权值系数的特征，再基于新的特征进行下一轮训练'''
model = LogisticRegression()
rfe = RFE(model,3)
fit = rfe.fit(X,Y)
# print("特征个数:")
# print(fit.n_features_)
# print("被选定的特征：")
# print(fit.support_)
# print("特征排名：")
# print(fit.ranking_)
#主成分分析
'''将原始的样本映射到维度更低的样本空间中，PCA让映射的样本具有更大的发散性，用于无监督降维'''
pca = PCA(n_components=3)
fit =pca.fit(X)
# print("解释方差：%s" %fit.explained_variance_ratio_)
# print(fit.components_)
#特征重要性
'''用extratressclassifier进行特征的重要性计算'''
model = ExtraTreesClassifier()
fit = model.fit(X,Y)
#输出每一个特征数据的得分
print(fit.feature_importances_)