特征重要性
#检测重要特征rf = RandomForestClassifier()
rf.fit(X, y)
f, ax = plt.subplots(figsize=(7, 5))
ax.bar(range(len(rf.feature_importances_)),rf.feature_importances_)
ax.set_title("Feature Importances")
f.show()
#每个例子属于哪个类的概率probs = rf.predict_proba(X)import pandas as pd
probs_df = pd.DataFrame(probs, columns=['0', '1'])
probs_df['was_correct'] = rf.predict(X) == yimport matplotlib.pyplot as plt
f, ax = plt.subplots(figsize=(7, 5))
probs_df.groupby('0').was_correct.mean().plot(kind='bar', ax=ax)
ax.set_title("Accuracy at 0 class probability")
ax.set_ylabel("% Correct")
ax.set_xlabel("% trees for 0")
f.show()
特征重要性
forest=RandomForestClassifier(n_estimators=10,n_jobs=-1,random_state=9)
forest.fit(x_train,y_train)
importances=forest.feature_importances_
print('每个维度对应的重要性因子：\n',importances)
indices = np.argsort(importances)[::-1]# a[::-1]让a逆序输出print('得到按维度重要性因子排序的维度的序号：\n',indices)
most_import = indices[:3]#取最总要的3个print(x_train[:,most_import])
特征重要性
from sklearn.datasets import load_boston
from sklearn.ensemble import RandomForestRegressor
import numpy as np
#Load boston housing dataset as an example
boston = load_boston()
X = boston["data"]
print type(X),X.shape
Y = boston["target"]
names = boston["feature_names"]
print names
rf = RandomForestRegressor()
rf.fit(X, Y)
print "Features sorted by their score:"
print sorted(zip(map(lambda x: round(x, 4), rf.feature_importances_), names), reverse=True)
参数调优
param_test1= {'n_estimators':list(range(10,71,10))} #对参数'n_estimators'进行网格调参
gsearch1= GridSearchCV(estimator = RandomForestClassifier(min_samples_split=100,min_samples_leaf=20,max_depth=8,max_features='sqrt' ,random_state=10), param_grid =param_test1, scoring='roc_auc',cv=5)
gsearch1.fit(X,y)
gsearch1.grid_scores_,gsearch1.best_params_, gsearch1.best_score_ #输出调参结果，并返回最优下的参数
#输出结果如下：
([mean:0.80681, std: 0.02236, params: {'n_estimators': 10},
mean: 0.81600, std: 0.03275, params:{'n_estimators': 20},
mean: 0.81818, std: 0.03136, params:{'n_estimators': 30},
mean: 0.81838, std: 0.03118, params:{'n_estimators': 40},
mean: 0.82034, std: 0.03001, params:{'n_estimators': 50},
mean: 0.82113, std: 0.02966, params:{'n_estimators': 60},
mean: 0.81992, std: 0.02836, params:{'n_estimators': 70}],
{'n_estimators':60}, 0.8211334476626017)
#多个特征的网格搜索，如下所示
param_test2= {'max_depth':list(range(3,14,2)),'min_samples_split':list(range(50,201,20))}
gsearch2= GridSearchCV(estimator = RandomForestClassifier(n_estimators= 60, min_samples_leaf=20,max_features='sqrt' ,oob_score=True,random_state=10), param_grid = param_test2,scoring='roc_auc',iid=False, cv=5)
gsearch2.fit(X,y)
gsearch2.grid_scores_,gsearch2.best_params_, gsearch2.best_score_
#通过查看袋外准确率（oob）来判别参数调整前后准确率的变化情况
rf1= RandomForestClassifier(n_estimators= 60, max_depth=13, min_samples_split=110, min_samples_leaf=20,max_features='sqrt' ,oob_score=True,random_state=10)
rf1.fit(X,y)
print(rf1.oob_score_)
#通过每次对1-3个特征进行网格搜索，重复此过程直到遍历每个特征，并得到最终的调参结果。
