【无标题】

RandomForestClassifier算法对特征值筛选的应用

# -*- coding: utf-8 -*-
"""
Created on Tue Feb 15 22:07:32 2022

@author: 17584
随机森林
"""
import pandas as pd
url = 'http://archive.ics.uci.edu/ml/machine-learning-databases/wine/wine.data'
df = pd.read_csv(url,header= None) #读入csv文件
df.columns=map(str,[i for i in range(1,15)]) #对列名进行定义

from sklearn.model_selection import train_test_split 
from sklearn.ensemble import RandomForestClassifier
x,y = df.iloc[:,1:].values,df.iloc[:,0].values #x特征值 y目标值

x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=0.3,random_state=0)
#特征值变量的名称
feat_labels = df.columns[1:]
#生成随机森林
forest = RandomForestClassifier(n_estimators=10000,random_state=0,n_jobs=-1) #调整参数
forest.fit(x_train,y_train) 
#获取特征值的重要程度
importances = forest.feature_importances_

import numpy as np

np.unique(df['1'])
indices = np.argsort(importances)[::-1] #按重要度进行排序（降序）
for f in range(x_train.shape[1]):
   print('(%.2d)%-*s %f' % (f + 1,30,feat_labels[indices[f]],importances[indices[f]]))
   #按重要程度排序进行打印
import matplotlib.pyplot as plt #绘图
plt.title('Feature Importance') #标题
plt.bar(range(x_train.shape[1]),importances[indices],color='lightblue',align='center') #bar图
plt.xticks(range(x_train.shape[1]),feat_labels,rotation=90) #x轴
plt.xlim([-1,x_train.shape[1]]) #x轴最小值与最大值
plt.tight_layout()  #自动调整参数使图像布满整个区域
plt.show( )