pyrandom.py 文件源码

def create_model(list_of_features):

    n_estimators=10000 
    n_jobs=4 
    x_train=data_frame[list_of_features] 
    y_train=data_frame.iloc[:,-1]
    x_test=data_frame_test[list_of_features] 
    random_state=0

    forest=BaggingRegressor(base_estimator=DecisionTreeRegressor(),n_estimators=n_estimators,random_state=random_state, n_jobs=n_jobs)
    forest.fit(x_train[list_of_features],y_train)
    Y_pred=forest.predict(data_frame_test[list_of_features].as_matrix()) 

    i=0
    file=open('submission.csv','w')
    header="Id,SalePrice"
    header=header+'\n'
    file.write(header)
    for id in (data_frame_test['Id']):
        str="{},{}".format(id,Y_pred[i])
        str=str+'\n'
        file.write(str)
        i+=1