python3學習使用api

線性回歸，和 隨機參數回歸

git: https://github.com/linyi0604/MachineLearning

 1 from sklearn.datasets import load_boston
 2 from sklearn.cross_validation import train_test_split
 3 from sklearn.preprocessing import StandardScaler
 4 from sklearn.linear_model import LinearRegression, SGDRegressor
 5
 
 from sklearn.metrics import r2_score, mean_squared_error, mean_absolute_error
 6 import numpy as np
 7 
 8 # 1 準備數據
 9 # 讀取波士頓地區房價信息
10 boston = load_boston()
11 # 查看數據描述
12 # print(boston.DESCR)   # 共506條波士頓地區房價信息，每條13項數值特征描述和目標房價
13 # 查看數據的差異情況
14 # print("最大房價：", np.max(boston.target))   # 50
15 # print("最小房價：",np.min(boston.target))    # 5
 

16 # print("平均房價：", np.mean(boston.target))   # 22.532806324110677
17 
18 x = boston.data
19 y = boston.target
20 
21 # 2 分割訓練數據和測試數據
22 # 隨機采樣25%作為測試 75%作為訓練
23 x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.25, random_state=33)
24 
25 
26 # 3 訓練數據和測試數據進行標準化處理
27 ss_x = StandardScaler()
 
28 x_train = ss_x.fit_transform(x_train)
29 x_test = ss_x.transform(x_test)
30 
31 ss_y = StandardScaler()
32 y_train = ss_y.fit_transform(y_train.reshape(-1, 1))
33 y_test = ss_y.transform(y_test.reshape(-1, 1))
34 
35 # 4 使用兩種線性回歸模型進行訓練和預測
36 # 初始化LinearRegression線性回歸模型
37 lr = LinearRegression()
38 # 訓練
39 lr.fit(x_train, y_train)
40 # 預測 保存預測結果
41 lr_y_predict = lr.predict(x_test)
42 
43 # 初始化SGDRRegressor隨機梯度回歸模型
44 sgdr = SGDRegressor()
45 # 訓練
46 sgdr.fit(x_train, y_train)
47 # 預測 保存預測結果
48 sgdr_y_predict = sgdr.predict(x_test)
49 
50 # 5 模型評估
51 # 對Linear模型評估
52 lr_score = lr.score(x_test, y_test)
53 print("Linear的默認評估值為：", lr_score)
54 lr_R_squared = r2_score(y_test, lr_y_predict)
55 print("Linear的R_squared值為：", lr_R_squared)
56 lr_mse = mean_squared_error(ss_y.inverse_transform(y_test),ss_y.inverse_transform(lr_y_predict))
57 print("Linear的均方誤差為:", lr_mse)
58 lr_mae = mean_absolute_error(ss_y.inverse_transform(y_test),ss_y.inverse_transform(lr_y_predict))
59 print("Linear的平均絕對誤差為:", lr_mae)
60 
61 # 對SGD模型評估
62 sgdr_score = sgdr.score(x_test, y_test)
63 print("SGD的默認評估值為：", sgdr_score)
64 sgdr_R_squared = r2_score(y_test, sgdr_y_predict)
65 print("SGD的R_squared值為：", sgdr_R_squared)
66 sgdr_mse = mean_squared_error(ss_y.inverse_transform(y_test), ss_y.inverse_transform(sgdr_y_predict))
67 print("SGD的均方誤差為:", sgdr_mse)
68 sgdr_mae = mean_absolute_error(ss_y.inverse_transform(y_test), ss_y.inverse_transform(sgdr_y_predict))
69 print("SGD的平均絕對誤差為:", sgdr_mae)
70 
71 ‘‘‘
72 Linear的默認評估值為： 0.6763403830998702
73 Linear的R_squared值為： 0.6763403830998701
74 Linear的均方誤差為: 25.09698569206773
75 Linear的平均絕對誤差為: 3.5261239963985433
76 
77 SGD的默認評估值為： 0.659795654161198
78 SGD的R_squared值為： 0.659795654161198
79 SGD的均方誤差為: 26.379885392159494
80 SGD的平均絕對誤差為: 3.5094445431026413
81 ‘‘‘

機器學習之路: python 線性回歸LinearRegression, 隨機參數回歸SGDRegressor 預測波士頓房價