python randomforesttree_python RandomForest跑feature重要性

其实呢，就是直接调用一个函数的事情。。。

#coding=utf-8

from sklearn.tree import DecisionTreeClassifier

from matplotlib.pyplot import *

from sklearn.cross_validation import train_test_split

from sklearn.ensemble import RandomForestClassifier

from sklearn.externals.joblib import Parallel, delayed

from sklearn.tree import export_graphviz

final = open('full_train.csv','r')

print "open good!"

data = [line.strip().split(',') for line in final]

feature = [[float(x) for x in row[1:]] for row in data]

target = [int(row[0]) for row in data]

print "del good!"

#拆分训练集和测试集

feature_train, feature_test, target_train, target_test = train_test_split(feature, target, test_size=0.1, random_state=42)

#分类型决策树

clf = RandomForestClassifier(n_estimators = 8)

print "train good"

#训练模型

s = clf.fit(feature_train , target_train)

print s

print "fuck high"

#评估模型准确率

r = clf.score(feature_test , target_test)

print r

print '判定结果：%s' % clf.predict(feature_test[0])

#print clf.predict_proba(feature_test[0])

print '所有的树:%s' % clf.estimators_

print clf.classes_

print clf.n_classes_

print '各feature的重要性：%s' % clf.feature_importances_

print clf.n_outputs_