linear_model.py 文件源码

def GDBT_regression(X=train_split,Y=y):
    est = GradientBoostingRegressor(n_estimators=75,max_depth=3,learning_rate=0.1)
    X_train,X_test,Y_train,Y_test = train_test_split(X,Y,test_size=0.3,random_state=0)
    est.fit(X_train,Y_train)
    y_train_pred = est.predict(X_test)
    plt.scatter(y_train_pred,y_train_pred - Y_test,c = 'blue',marker='s', label='error on training data')

    plt.title("Linear regression with  GDBT")
    plt.xlabel("Predicted values")
    plt.ylabel("Residuals")
    plt.legend(loc="upper left")
    plt.hlines(y=0, xmin=10.5, xmax=13.5, color="red")
    plt.show()
    # Plot predictions
    plt.scatter(Y_test, y_train_pred, c="blue", marker="s", label="Training data")

    plt.title("Linear regression with  GDBT")
    plt.xlabel("Predicted values")
    plt.ylabel("Real values")
    plt.legend(loc="upper left")
    plt.plot([10.5, 13.5], [10.5, 13.5], c="red")
    plt.show()
    print('rmse value:',rmsle(Y_test,y_train_pred))

    return est


# linear_regression()
# ridge_regression()
# Lasso_regression()
#model = Elasticnet_regression()
# '''
#         predict final result
#  '''
#
#
# coefs,lasso = Lasso_regression()
# selected_features = coefs[coefs['value'] != 0].index.values
# train_new = train_split[selected_features]