123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596 |
- #-*- coding:utf-8 -*-
- import numpy as np
- from sklearn.ensemble import GradientBoostingClassifier,GradientBoostingRegressor
- from sklearn.model_selection import train_test_split
- from sklearn.datasets import load_wine,load_boston
- from sklearn import tree
- def read_data():
- boston = load_boston()
- Xtrain, Xtest, Ytrain, Ytest = train_test_split(boston.data, boston.target, test_size=0.3)
- return Xtrain, Xtest, Ytrain, Ytest
- def init(Ytrain):
- return np.average(Ytrain)
- def fit(Xtrain, Ytrain):
- print("init", Ytrain[:10])
- fx = []
- trees = []
- fx0 = np.ones(Ytrain.shape[0])*init(Ytrain)
- fx.append(fx0)
- print("0", fx0[:10])
- gx = Ytrain
- for i in range(55):
- # 求残差
- gx = gx - fx0
- print("第", i, '轮 残差', gx[:10])
- clf = tree.DecisionTreeRegressor(criterion="mse", max_features=5, max_depth=10, random_state=10)
- clf.fit(Xtrain, gx)
- trees.append(clf)
- fx0 = clf.predict(Xtrain)*0.7
- print("第", i, '轮 结果', fx0[:10])
- fx.append(fx0)
- gx = np.zeros(Ytrain.shape[0])
- for i in range(len(fx)):
- gx = gx + fx[i]
- print(gx[:10])
- sum = 0
- for i in range(Ytrain.shape[0]):
- sum = sum + (gx[i] - Ytrain[i])**2
- print("train mse", sum/Ytrain.shape[0])
- return trees, fx[0][0]
- def score(Xtest, Ytest, trees, fx0):
- gx = np.ones(Ytest.shape[0]) * fx0
- for i in range(len(trees)):
- gx = gx + trees[i].predict(Xtest)
- print(gx[:10])
- print(Ytest[:10])
- sum = 0
- for i in range(Ytest.shape[0]):
- sum = sum + (gx[i] - Ytest[i])**2
- print("test mse", sum/Ytest.shape[0])
- gx = trees[0].predict(Xtest)
- sum = 0
- for i in range(Ytest.shape[0]):
- sum = sum + (gx[i] - Ytest[i]) ** 2
- print("test mse0", sum / Ytest.shape[0])
- if __name__ == '__main__':
- Xtrain, Xtest, Ytrain, Ytest = read_data()
- trees, fx0 = fit(Xtrain, Ytrain)
- score(Xtest, Ytest, trees, fx0)
- gbm2 = GradientBoostingRegressor(n_estimators=55, max_depth=10, learning_rate=0.7,
- max_features='sqrt', random_state=10)
- gbm2.fit(Xtrain, Ytrain) # 分数越高越好
- print("gbdt1", gbm2.score(Xtest, Ytest))
- gx = gbm2.predict(Xtest)
- sum = 0
- for i in range(Ytest.shape[0]):
- sum = sum + (gx[i] - Ytest[i]) ** 2
- print(gx[:10])
- print(Ytest[:10])
- print("gbdt mse", sum / Ytest.shape[0])
|