sklearn
- import cross_validation, metrics
- import matplotlib.pylab as plt
- %matplotlib inline
-
-
- train= pd.read_csv('C:\Users\86349\Desktop\train_modified\train_modified.csv')
- target='Disbursed'
- IDcol= 'ID'
- train['Disbursed'].value_counts()
-
-
- 0 19680
- 1 320
- Name:Disbursed, dtype: int64
-
-
- x_columns = [x for x in train.columns if x notin [target,IDcol]]
- X = train[x_columns]
- y = train['Disbursed']
-
-
- rf0 = RandomForestClassifier(oob_score=True, random_state=10)
- rf0.fit(X,y)
- print rf0.oob_score_
- y_predprob = rf0.predict_proba(X)[:,1]
- print"AUC Score (Train): %f" % metrics.roc_auc_score(y,y_predprob)
-
-
-
-
- param_test1= {'n_estimators':range(10,71,10)}
- 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_
-
- ([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)
-
-
- 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_
-
- ([mean:0.79379, std: 0.02347, params: {'min_samples_split': 50, 'max_depth': 3},
- mean: 0.79339, std: 0.02410, params:{'min_samples_split': 70, 'max_depth': 3},
- mean: 0.79350, std: 0.02462, params:{'min_samples_split': 90, 'max_depth': 3},
- mean: 0.79367, std: 0.02493, params:{'min_samples_split': 110, 'max_depth': 3},
- mean: 0.79387, std: 0.02521, params:{'min_samples_split': 130, 'max_depth': 3},
- mean: 0.79373, std: 0.02524, params:{'min_samples_split': 150, 'max_depth': 3},
- mean: 0.79378, std: 0.02532, params:{'min_samples_split': 170, 'max_depth': 3},
- mean: 0.79349, std: 0.02542, params:{'min_samples_split': 190, 'max_depth': 3},
- mean: 0.80960, std: 0.02602, params:{'min_samples_split': 50, 'max_depth': 5},
- mean: 0.80920, std: 0.02629, params:{'min_samples_split': 70, 'max_depth': 5},
- mean: 0.80888, std: 0.02522, params:{'min_samples_split': 90, 'max_depth': 5},
- mean: 0.80923, std: 0.02777, params:{'min_samples_split': 110, 'max_depth': 5},
- mean: 0.80823, std: 0.02634, params:{'min_samples_split': 130, 'max_depth': 5},
- mean: 0.80801, std: 0.02637, params:{'min_samples_split': 150, 'max_depth': 5},
- mean: 0.80792, std: 0.02685, params:{'min_samples_split': 170, 'max_depth': 5},
- mean: 0.80771, std: 0.02587, params:{'min_samples_split': 190, 'max_depth': 5},
- mean: 0.81688, std: 0.02996, params:{'min_samples_split': 50, 'max_depth': 7},
- mean: 0.81872, std: 0.02584, params:{'min_samples_split': 70, 'max_depth': 7},
- mean: 0.81501, std: 0.02857, params:{'min_samples_split': 90, 'max_depth': 7},
- mean: 0.81476, std: 0.02552, params:{'min_samples_split': 110, 'max_depth': 7},
- mean: 0.81557, std: 0.02791, params:{'min_samples_split': 130, 'max_depth': 7},
- mean: 0.81459, std: 0.02905, params:{'min_samples_split': 150, 'max_depth': 7},
- mean: 0.81601, std: 0.02808, params:{'min_samples_split': 170, 'max_depth': 7},
- mean: 0.81704, std: 0.02757, params:{'min_samples_split': 190, 'max_depth': 7},
- mean: 0.82090, std: 0.02665, params:{'min_samples_split': 50, 'max_depth': 9},
- mean: 0.81908, std: 0.02527, params:{'min_samples_split': 70, 'max_depth': 9},
- mean: 0.82036, std: 0.02422, params:{'min_samples_split': 90, 'max_depth': 9},
- mean: 0.81889, std: 0.02927, params:{'min_samples_split': 110, 'max_depth': 9},
- mean: 0.81991, std: 0.02868, params:{'min_samples_split': 130, 'max_depth': 9},
- mean: 0.81788, std: 0.02436, params:{'min_samples_split': 150, 'max_depth': 9},
- mean: 0.81898, std: 0.02588, params:{'min_samples_split': 170, 'max_depth': 9},
- mean: 0.81746, std: 0.02716, params:{'min_samples_split': 190, 'max_depth': 9},
- mean: 0.82395, std: 0.02454, params:{'min_samples_split': 50, 'max_depth': 11},
- mean: 0.82380, std: 0.02258, params:{'min_samples_split': 70, 'max_depth': 11},
- mean: 0.81953, std: 0.02552, params:{'min_samples_split': 90, 'max_depth': 11},
- mean: 0.82254, std: 0.02366, params:{'min_samples_split': 110, 'max_depth': 11},
- mean: 0.81950, std: 0.02768, params:{'min_samples_split': 130, 'max_depth': 11},
- mean: 0.81887, std: 0.02636, params:{'min_samples_split': 150, 'max_depth': 11},
- mean: 0.81910, std: 0.02734, params:{'min_samples_split': 170, 'max_depth': 11},
- mean: 0.81564, std: 0.02622, params:{'min_samples_split': 190, 'max_depth': 11},
- mean: 0.82291, std: 0.02092, params:{'min_samples_split': 50, 'max_depth': 13},
- mean: 0.82177, std: 0.02513, params:{'min_samples_split': 70, 'max_depth': 13},
- mean: 0.82415, std: 0.02480, params:{'min_samples_split': 90, 'max_depth': 13},
- mean: 0.82420, std: 0.02417, params:{'min_samples_split': 110, 'max_depth': 13},
- mean: 0.82209, std: 0.02481, params:{'min_samples_split': 130, 'max_depth': 13},
- mean: 0.81852, std: 0.02227, params:{'min_samples_split': 150, 'max_depth': 13},
- mean: 0.81955, std: 0.02885, params:{'min_samples_split': 170, 'max_depth': 13},
- mean: 0.82092, std: 0.02600, params:{'min_samples_split': 190, 'max_depth': 13}],
- {'max_depth':13, 'min_samples_split': 110},
- 0.8242016800050813)
-
-
- 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)
- printrf1.oob_score_
-
-
-
-
- param_test3= {'min_samples_split':range(80,150,20), 'min_samples_leaf':range(10,60,10)}
- gsearch3= GridSearchCV(estimator = RandomForestClassifier(n_estimators= 60,max_depth=13,
- max_features='sqrt' ,oob_score=True, random_state=10),
- param_grid = param_test3,scoring='roc_auc',iid=False, cv=5)
- gsearch3.fit(X,y)
- gsearch3.grid_scores_,gsearch2.best_params_, gsearch2.best_score_
-
- ([mean:0.82093, std: 0.02287, params: {'min_samples_split': 80, 'min_samples_leaf':10},
- mean: 0.81913, std: 0.02141, params:{'min_samples_split': 100, 'min_samples_leaf': 10},
- mean: 0.82048, std: 0.02328, params:{'min_samples_split': 120, 'min_samples_leaf': 10},
- mean: 0.81798, std: 0.02099, params:{'min_samples_split': 140, 'min_samples_leaf': 10},
- mean: 0.82094, std: 0.02535, params:{'min_samples_split': 80, 'min_samples_leaf': 20},
- mean: 0.82097, std: 0.02327, params:{'min_samples_split': 100, 'min_samples_leaf': 20},
- mean: 0.82487, std: 0.02110, params:{'min_samples_split': 120, 'min_samples_leaf': 20},
- mean: 0.82169, std: 0.02406, params:{'min_samples_split': 140, 'min_samples_leaf': 20},
- mean: 0.82352, std: 0.02271, params:{'min_samples_split': 80, 'min_samples_leaf': 30},
- mean: 0.82164, std: 0.02381, params:{'min_samples_split': 100, 'min_samples_leaf': 30},
- mean: 0.82070, std: 0.02528, params:{'min_samples_split': 120, 'min_samples_leaf': 30},
- mean: 0.82141, std: 0.02508, params:{'min_samples_split': 140, 'min_samples_leaf': 30},
- mean: 0.82278, std: 0.02294, params:{'min_samples_split': 80, 'min_samples_leaf': 40},
- mean: 0.82141, std: 0.02547, params:{'min_samples_split': 100, 'min_samples_leaf': 40},
- mean: 0.82043, std: 0.02724, params:{'min_samples_split': 120, 'min_samples_leaf': 40},
- mean: 0.82162, std: 0.02348, params:{'min_samples_split': 140, 'min_samples_leaf': 40},
- mean: 0.82225, std: 0.02431, params:{'min_samples_split': 80, 'min_samples_leaf': 50},
- mean: 0.82225, std: 0.02431, params:{'min_samples_split': 100, 'min_samples_leaf': 50},
- mean: 0.81890, std: 0.02458, params:{'min_samples_split': 120, 'min_samples_leaf': 50},
- mean: 0.81917, std: 0.02528, params:{'min_samples_split': 140, 'min_samples_leaf': 50}],
- {'min_samples_leaf':20, 'min_samples_split': 120},
- 0.8248650279471544)
-
-
- param_test4= {'max_features':range(3,11,2)}
- gsearch4= GridSearchCV(estimator = RandomForestClassifier(n_estimators= 60,max_depth=13, min_samples_split=120,
- min_samples_leaf=20 ,oob_score=True, random_state=10),
- param_grid = param_test4,scoring='roc_auc',iid=False, cv=5)
- gsearch4.fit(X,y)
- gsearch4.grid_scores_,gsearch4.best_params_, gsearch4.best_score_
-
- ([mean:0.81981, std: 0.02586, params: {'max_features': 3},
- mean: 0.81639, std: 0.02533, params:{'max_features': 5},
- mean: 0.82487, std: 0.02110, params:{'max_features': 7},
- mean: 0.81704, std: 0.02209, params:{'max_features': 9}],
- {'max_features':7},
- 0.8248650279471544)
-
-
- rf2= RandomForestClassifier(n_estimators= 60, max_depth=13, min_samples_split=120,
- min_samples_leaf=20,max_features=7 ,oob_score=True, random_state=10)
- rf2.fit(X,y)
- printrf2.oob_score_
-
-
来源: http://www.taocms.org/1126.html