twolayer_rf.py 文件源码

def run(result_csv_path):
    train_x,train_y = load_data(train_csv_path,True)
    test_x = load_data(test_csv_path,False)
    print('load data successfully.........')

    layer1_rf_paramters ={
            'max_depth':range(15,21),
            'max_features': [0.5,0.6,0.8],
            'min_samples_leaf':[1,3,10]
            }

    print('layer 1 train..........')
    layer1_rf = RandomForestRegressor(
            n_estimators = 2500,
            n_jobs = -1
            )
    layer1_gs_rf = GridSearchCV(layer1_rf,param_grid = layer1_rf_paramters)
    layer1_gs_rf.fit(train_x,train_y)
    ################# save model##################
    joblib.dump(layer1_gs_rf,'weights/layer1_'+Model_Name+'.m')

    #layer1_rf = joblib.load('weights/layer1_'+Model_Name+'.m')
    tr_pred = layer1_gs_rf.predict(train_x)
    train_x = feature_engineer(layer1_gs_rf,train_x,tr_pred)

    te_pred = layer1_gs_rf.predict(test_x)
    test_x = feature_engineer(layer1_gs_rf,test_x,te_pred)

    print('layer 2 train ............')
    layer2_rf = RandomForestRegressor(
            n_jobs = -1,
            n_estimators = 1000,
            max_features = 'sqrt',
            max_depth = 18,
            bootstrap = False
            )
    layer2_rf.fit(train_x,train_y)
    joblib.dump(layer2_rf,'weights/layer2_'+Model_Name+'.m')
    y_pred = layer2_rf.predict(test_x)

    ############ save_results ########################
    save_results(result_csv_path,y_pred)