機器學習:線性迴歸和嶺迴歸入門程式碼
阿新 • • 發佈:2018-12-16
機器學習中運用python進行對房子價格的預測程式碼,資料庫直接使用sklearn自帶的boston,使用三種方法進行預測,分別是:線性迴歸直接預測、梯度下降預測、嶺迴歸預測
from sklearn.datasets import load_boston from sklearn.linear_model import LinearRegression, SGDRegressor,Ridge from sklearn.model_selection import train_test_split from sklearn.preprocessing import StandardScaler from sklearn.metrics import mean_squared_error def mylinear(): """ 線性迴歸直接預測房子價格 :return: None """ # 獲取資料 lb = load_boston() # 分割資料集到訓練集和測試集 x_train, x_test, y_train, y_test = train_test_split(lb.data, lb.target, test_size=0.25) # print(y_train, y_test) # 進行標準化處理(?)目標值處理? # 特徵值和目標值都必須進行標準化處理,例項化兩個標準化API std_x = StandardScaler() x_train = std_x.fit_transform(x_train) x_test = std_x.transform(x_test) # 目標值 std_y = StandardScaler() y_train = std_y.fit_transform(y_train.reshape(-1, 1)) y_test = std_y.transform(y_test.reshape(-1, 1)) # estimator預測 # 正規方程求解方式預測結果 lr = LinearRegression() lr.fit(x_train, y_train) print(lr.coef_) # 預測測試集房子價格 y_lr_predict = std_y.inverse_transform(lr.predict(x_test)) print("測試集裡面每個房子的預測價格:", y_lr_predict) print("正規方程的均方誤差:",mean_squared_error(std_y.inverse_transform(y_test), y_lr_predict)) # 梯度下降去預測房價 sgd = SGDRegressor() sgd.fit(x_train, y_train) print(sgd.coef_) # 預測測試集房子價格 y_sgd_predict = std_y.inverse_transform(sgd.predict(x_test)) print("測試集裡面每個房子的預測價格:", y_sgd_predict) print("梯度下降方程的均方誤差:", mean_squared_error(std_y.inverse_transform(y_test), y_sgd_predict)) # 嶺迴歸去預測房價 rd = Ridge() rd.fit(x_train, y_train) print(rd.coef_) # 預測測試集房子價格 y_rd_predict = std_y.inverse_transform(rd.predict(x_test)) print("測試集裡面每個房子的預測價格:", y_rd_predict) print("嶺迴歸方程的均方誤差:", mean_squared_error(std_y.inverse_transform(y_test), y_rd_predict)) return None if __name__ == '__main__': mylinear()