whystea3

import pandas as pd from sklearn.model_selection import train_test_split from sklearn.linear_model import LogisticRegression,Ridge from sklearn.svm import SVC from sklearn.tree import DecisionTreeClassifier from sklearn.neighbors import KNeighborsClassifier from sklearn.metrics import roc_auc_score from sklearn.ensemble import RandomForestClassifier,BaggingClassifier,AdaBoostClassifier,GradientBoostingClassifier from sklearn.metrics import roc_curve from sklearn.model_selection import GridSearchCV path='data/data_loan.csv' data=pd.read_csv(path) data_x=data.drop(columns=['user_id','y']) data_y=data['y'] x,test_x,y,test_y=train_test_split(data_x,data_y,train_size=0.7) models=[LogisticRegression,Ridge,SVC,DecisionTreeClassifier,KNeighborsClassifier,roc_auc_score ,RandomForestClassifier,BaggingClassifier,AdaBoostClassifier,GradientBoostingClassifier] for cls in models: cls=LogisticRegression() cls.fit(x,y) pre_y=cls.predict_proba(test_x)[:,1] grid_param=[{'n_estimators':[50,100,200,300],'max_depth':[3,5,7]}] cls=RandomForestClassifier() searcher=GridSearchCV(cls,grid_param,cv=5,scoring='roc_auc',n_jobs=4) searcher.fit(x,y) best_cls=searcher.best_estimator_ pre_y=best_cls.predict_proba(test_x)[:,1]