gbdt算法

integr/my_gbdt.py

@@ -0,0 +1,55 @@
+#-*- 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 = []
+
+    fx0 = np.ones(Ytrain.shape[0])*init(Ytrain)
+    fx.append(fx0)
+
+    print("0", fx0[:10])
+
+    gx = Ytrain
+
+    for i in range(20):
+        # 求残差
+        gx = gx - fx0
+        print("第", i, '轮 残差', gx[:10])
+        clf = tree.DecisionTreeRegressor(criterion="mse", max_features=1, max_depth=4)
+        clf.fit(Xtrain, gx)
+
+        fx0 = clf.predict(Xtrain)
+        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])*(gx[i] - Ytrain[i])
+
+    print(sum)
+
+if __name__ == '__main__':
+    Xtrain, Xtest, Ytrain, Ytest = read_data()
+    fit(Xtrain, Ytrain)