python3 学习机器学习api
使用了三种集成回归模型
git: https://github.com/linyi0604/MachineLearning
代码：
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.ensemble import RandomForestRegressor, ExtraTreesRegressor, GradientBoostingRegressor 5 from sklearn.metrics import r2_score, mean_squared_error, mean_absolute_error 6 import numpy as np 7 8 ''' 9 随机森林回归 10 极端随机森林回归 11 梯度提升回归 12 13 通常集成模型能够取得非常好的表现 14 ''' 15 16 # 1 准备数据 17 # 读取波士顿地区房价信息 18 boston = load_boston() 19 # 查看数据描述 20 # print(boston.DESCR) # 共506条波士顿地区房价信息，每条13项数值特征描述和目标房价 21 # 查看数据的差异情况 22 # print("最大房价：", np.max(boston.target)) # 50 23 # print("最小房价：",np.min(boston.target)) # 5 24 # print("平均房价：", np.mean(boston.target)) # 22.532806324110677 25 26 x = boston.data 27 y = boston.target 28 29 # 2 分割训练数据和测试数据 30 # 随机采样25%作为测试 75%作为训练 31 x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.25, random_state=33) 32 33 # 3 训练数据和测试数据进行标准化处理 34 ss_x = StandardScaler() 35 x_train = ss_x.fit_transform(x_train) 36 x_test = ss_x.transform(x_test) 37 38 ss_y = StandardScaler() 39 y_train = ss_y.fit_transform(y_train.reshape(-1, 1)) 40 y_test = ss_y.transform(y_test.reshape(-1, 1)) 41 42 # 4 三种集成回归模型进行训练和预测 43 # 随机森林回归 44 rfr = RandomForestRegressor() 45 # 训练 46 rfr.fit(x_train, y_train) 47 # 预测 保存预测结果 48 rfr_y_predict = rfr.predict(x_test) 49 50 # 极端随机森林回归 51 etr = ExtraTreesRegressor() 52 # 训练 53 etr.fit(x_train, y_train) 54 # 预测 保存预测结果 55 etr_y_predict = rfr.predict(x_test) 56 57 # 梯度提升回归 58 gbr = GradientBoostingRegressor() 59 # 训练 60 gbr.fit(x_train, y_train) 61 # 预测 保存预测结果 62 gbr_y_predict = rfr.predict(x_test) 63 64 # 5 模型评估 65 # 随机森林回归模型评估 66 print("随机森林回归的默认评估值为：", rfr.score(x_test, y_test)) 67 print("随机森林回归的R_squared值为：", r2_score(y_test, rfr_y_predict)) 68 print("随机森林回归的均方误差为:", mean_squared_error(ss_y.inverse_transform(y_test), 69 ss_y.inverse_transform(rfr_y_predict))) 70 print("随机森林回归的平均绝对误差为:", mean_absolute_error(ss_y.inverse_transform(y_test), 71 ss_y.inverse_transform(rfr_y_predict))) 72 73 # 极端随机森林回归模型评估 74 print("极端随机森林回归的默认评估值为：", etr.score(x_test, y_test)) 75 print("极端随机森林回归的R_squared值为：", r2_score(y_test, gbr_y_predict)) 76 print("极端随机森林回归的均方误差为:", mean_squared_error(ss_y.inverse_transform(y_test), 77 ss_y.inverse_transform(gbr_y_predict))) 78 print("极端随机森林回归的平均绝对误差为:", mean_absolute_error(ss_y.inverse_transform(y_test), 79 ss_y.inverse_transform(gbr_y_predict))) 80 81 # 梯度提升回归模型评估 82 print("梯度提升回归回归的默认评估值为：", gbr.score(x_test, y_test)) 83 print("梯度提升回归回归的R_squared值为：", r2_score(y_test, etr_y_predict)) 84 print("梯度提升回归回归的均方误差为:", mean_squared_error(ss_y.inverse_transform(y_test), 85 ss_y.inverse_transform(etr_y_predict))) 86 print("梯度提升回归回归的平均绝对误差为:", mean_absolute_error(ss_y.inverse_transform(y_test), 87 ss_y.inverse_transform(etr_y_predict))) 88 89 ''' 90 随机森林回归的默认评估值为： 0.8391590262557747 91 随机森林回归的R_squared值为： 0.8391590262557747 92 随机森林回归的均方误差为: 12.471817322834646 93 随机森林回归的平均绝对误差为: 2.4255118110236227 94 95 极端随机森林回归的默认评估值为： 0.783339502805047 96 极端随机森林回归的R_squared值为： 0.8391590262557747 97 极端随机森林回归的均方误差为: 12.471817322834646 98 极端随机森林回归的平均绝对误差为: 2.4255118110236227 99 100 GradientBoostingRegressor回归的默认评估值为： 0.8431187344932869 101 GradientBoostingRegressor回归的R_squared值为： 0.8391590262557747 102 GradientBoostingRegressor回归的均方误差为: 12.471817322834646 103 GradientBoostingRegressor回归的平均绝对误差为: 2.4255118110236227 104 '''