用自己写的弱分类器训练就是有问题

integr/my_ada_boost.py

@@ -20,13 +20,13 @@ def read_data():
 
 def fit(Xtrain, Ytrain):
     # 设置数据初始权重
-    w = np.array([1/len(Ytrain) for i in range(len(Ytrain))])
+    w = np.ones(len(Ytrain))/Ytrain.shape[0]
     # 决策树权重
     alphas = []
     # 决策树数组
     trees = []
     pn = 1/len(Ytrain)
-    print(Ytest)
+    # print(Ytest)
 
     for i in range(20):
         # 训练决策树
@@ -34,10 +34,10 @@ def fit(Xtrain, Ytrain):
                                      )  # 实例化，criterion不写的话默认是基尼系数
 
         clf.fit(Xtrain, Ytrain, w)
-        Xpredit = clf.predict(Xtrain)
+        Ypredit = clf.predict(Xtrain)
 
-        error = np.dot([Xpredit != Ytrain], w)
-        p_error = sum(Xpredit != Ytrain)/Ytrain.shape[0]
+        error = np.dot(Ypredit != Ytrain, w)
+        p_error = sum(Ypredit != Ytrain)/Ytrain.shape[0]
 
         if error > 0.5:
             continue
@@ -49,7 +49,7 @@ def fit(Xtrain, Ytrain):
 
         # 更新权重
         for j in range(Ytrain.shape[0]):
-            w[j] = w[j]*np.exp(-alpha*Ytrain[j]*Xpredit[j])
+            w[j] = w[j]*np.exp(-alpha*Ytrain[j]*Ypredit[j])
         sum_w = sum(w)
         w = w/sum_w
 

tree/my_tree.py

@@ -1,6 +1,6 @@
 #!/usr/bin/python
 # -*- coding: UTF-8 -*-
-from sklearn.datasets import load_wine
+from sklearn.datasets import load_wine,load_breast_cancer
 from sklearn.model_selection import train_test_split
 import numpy as np
 
@@ -367,8 +367,20 @@ class MyDT(object):
         print_width([nodes], 1, feature_names, class_names)
 
 
+def read_data_1():
+    wine = load_breast_cancer()
+    Xtrain, Xtest, Ytrain, Ytest = train_test_split(wine.data,wine.target,test_size=0.3)
+    for i in range(len(Ytrain)):
+        if Ytrain[i] == 0:
+            Ytrain[i] = -1
+    for i in range(len(Ytest)):
+        if Ytest[i] == 0:
+            Ytest[i] = -1
+    return Xtrain, Xtest, Ytrain, Ytest
+
+
 if __name__ == '__main__':
-    Xtrain, Xtest, Ytrain, Ytest = read_data()
+    Xtrain, Xtest, Ytrain, Ytest = read_data_1()
     print(calc_ent1(Ytrain))
 
     weights = np.ones(len(Ytrain))/Ytrain.shape[0]
@@ -386,6 +398,6 @@ if __name__ == '__main__':
 
     print(clf.predict(Xtest))
 
-    print(clf.score(Xtest, Ytest))
-    print(clf.score(Xtrain, Ytrain))
+    print("测试集", clf.score(Xtest, Ytest))
+    print("训练集", clf.score(Xtrain, Ytrain))
     MyDT.export(clf, feature_name, class_names)