from sklearn.ensemble import RandomForestClassifier
forest = RandomForestClassifier(n_estimators=10000, random_state=0, n_jobs=-1)
importances = forest.feature_importances_
#样例的输出结果如下所示
 1) Alcohol                        0.1824832) Malic acid                     0.1586103) Ash                            0.1509484) Alcalinity of ash              0.1319875) Magnesium                      0.1065896) Total phenols                  0.0782437) Flavanoids                     0.0607188) Nonflavanoid phenols           0.0320339) Proanthocyanins                0.025400
10) Color intensity                0.022351
11) Hue                            0.022078
12) OD280/OD315 of diluted wines   0.014645
13) Proline                        0.013916

from sklearn.datasets import load_iris
from sklearn.ensemble import RandomForestClassifier
import pandas as pd
import numpy as np
iris = load_iris()
df = pd.DataFrame(iris.data, columns=iris.feature_names)
df['is_train'] = np.random.uniform(0, 1, len(df)) <= .75
df['species'] = pd.Categorical.from_codes(iris.target, iris.target_names)
df.head()
train, test = df[df['is_train']==True], df[df['is_train']==False]
features = df.columns[:4]
clf = RandomForestClassifier(n_jobs=2)
y, _ = pd.factorize(train['species'])
clf.fit(train[features], y)
preds = iris.target_names[clf.predict(test[features])]
pd.crosstab(test['species'], preds, rownames=['actual'], colnames=['preds'])
clf.feature_importances_#返回特征重要性的结果：[ 0.085598  ,  0.01877088,  0.45324092,  0.4423902 ]

1、sklearn.metrics.roc_curve(true_y. pred_proba_score, pos_labal)
#返回roc曲线的3个属性：fpr, tpr,和阈值
import numpy as np
from sklearn.metrics import roc_curve
y = np.array([1,1,2,2])
pred = np.array([0.1, 0.4, 0.35, 0.8])
fpr, tpr, thresholds = roc_curve(y, pred, pos_label=2)
fpr      # array([ 0. ,  0.5,  0.5,  1. ])
tpr      # array([ 0.5,  0.5,  1. ,  1. ])
thresholds      #array([ 0.8 ,  0.4 ,  0.35,  0.1 ])
from sklearn.metrics import auc
metrics.auc(fpr, tpr) 2、sklearn.metrics.auc(x, y, reorder=False)
#计算AUC值，其中x，y分别为数组形式，根据（xi，yi）在坐标上的点，生成的曲线，计算AUC值3、sklearn.metrics.roc_auc_score(true_y, pred_proba_y)
#直接根据真实值（必须是二值）、预测值（可以是0/1，或是prob）计算出auc值

param_test1= {'n_estimators':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':range(3,14,2),'min_samples_split':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。