和sklearn的比较下

integr/my_gbdt.py

@@ -31,7 +31,7 @@ def fit(Xtrain, Ytrain):
         # 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)
+        clf = tree.DecisionTreeRegressor(criterion="mse", max_features=5, max_depth=10, random_state=10)
         clf.fit(Xtrain, gx)
         trees.append(clf)
 
@@ -74,7 +74,22 @@ def score(Xtest, Ytest, trees, fx0):
         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)
+    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])
+

integr/my_gbdt_classic.py

@@ -87,4 +87,9 @@ def score(Xtest, Ytest, trees, fx0):
 if __name__ == '__main__':
     Xtrain, Xtest, Ytrain, Ytest = read_data()
     trees,fx0 = fit(Xtrain, Ytrain)
-    score(Xtest, Ytest, trees, fx0)
+    score(Xtest, Ytest, trees, fx0)
+
+    gbm1 = GradientBoostingClassifier(n_estimators=10, max_depth=1, learning_rate=0.7,
+                                      max_features='sqrt', random_state=10)
+    gbm1.fit(Xtrain, Ytrain)
+    print("gbdt", gbm1.score(Xtest, Ytest))