算法梳理進階線性迴歸(三)

代碼實現

# -*- coding:utf-8 -*-

import sklearn.datasets as datasets
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score
from sklearn.model_selection import train_test_split
import numpy as np


class HousePrice:

    def data_split(self):
        # 載入數據集
        boston_data = datasets.load_boston()
        # 得到RM列的數據
        x = boston_data.data[:, 5]

        # 變爲一列
        x = x.reshape(-1, 1)
        y = boston_data.target
        y = y.reshape(-1, 1)

        # 分割數據集
        x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=0)

        # 創建線性迴歸模型
        lr = LinearRegression()
        lr.fit(x_train, y_train)

        # 得到預測結果
        y_pred = lr.predict(x_test)
        return y_pred, y_test


if __name__ == '__main__':
    hp = HousePrice()
    # 得到預測以及測試原本的結果
    y_pred, y_test = hp.data_split()

    # 計算評分指標
    mse_test = np.sum((y_pred - y_test) ** 2) / len(y_test)
    mae_test = np.sum(np.absolute(y_pred - y_test)) / len(y_test)

    rmse_test = mse_test ** 0.5
    r_score = 1 - (mse_test / np.var(y_test))
    print('自己實現')
    print("均方誤差:{0},平均絕對誤差:{1},均方根誤差:{2},可決係數:{3}".format(mse_test, mae_test, rmse_test, r2_score))

    # 調用函數得到
    # 調用函數獲得結果
    mse_test = mean_squared_error(y_test, y_pred)
    mae_test = mean_absolute_error(y_test, y_pred)
    rmse_test = mse_test ** 0.5
    r2_score = r2_score(y_test, y_pred)

    print('調用函數')
    print("均方誤差:{0},平均絕對誤差:{1},均方根誤差:{2},可決係數:{3}".format(mse_test, mae_test, rmse_test, r2_score))
    pass

效果