clf.fit(Xtrain, Ytrain, w)

integr/my_ada_boost.py

@@ -11,7 +11,7 @@ Xtrain, Xtest, Ytrain, Ytest = train_test_split(wine.data,wine.target,test_size=
 # 设置数据初始权重
 w = np.array([1/len(Ytrain) for i in range(len(Ytrain))])
 # 决策树权重
-alpha = []
+alphas = []
 # 决策树数组
 trees = []
 pn = 1/len(Ytrain)
@@ -24,15 +24,18 @@ for i in range(len(Ytest)):
         Ytest[i] = -1
 print(Ytest)
 
-for i in range(15):
+for i in range(20):
     # 训练决策树
-    # clf = DecisionTreeClassifier(criterion="entropy", max_features=1, max_depth=1,
-    #                              class_weight={0:w0, 1:1-w0})  # 实例化，criterion不写的话默认是基尼系数
-    nodes = my_tree.fit(Xtrain, Ytrain, None, 0, w)
+    clf = DecisionTreeClassifier(criterion="entropy", max_features=1, max_depth=1,
+                                 )  # 实例化，criterion不写的话默认是基尼系数
 
-    my_tree.print_width([nodes], 1)
+    clf.fit(Xtrain, Ytrain, w)
+    # nodes = my_tree.fit(Xtrain, Ytrain, None, 0, w)
+
+    # my_tree.print_width([nodes], 1)
     # print("熵值", my_tree.calc_ent(Ytrain, w))
-    Xpredit = my_tree.predict(Xtrain, Ytrain, nodes)
+    # Xpredit = my_tree.predict(Xtrain, Ytrain, nodes)
+    Xpredit = clf.predict(Xtrain)
     error = 0
     p_error = 0
     for j in range(len(Ytrain)):
@@ -46,27 +49,27 @@ for i in range(15):
         error = 0.001
 
     print("第", i, "轮错误率", p_error, error)
-    ab = 0.5*np.log2(1/error - 1)
+    alpha = 0.5*np.log2(1/error - 1)
 
     # 更新权重
-    for j in range(len(Ytrain)):
-        w[j] = w[j]*np.exp(-ab*Ytrain[j]*Xpredit[j])
+    for j in range(Ytrain.shape[0]):
+        w[j] = w[j]*np.exp(-alpha*Ytrain[j]*Xpredit[j])
     sum_w = sum(w)
     w = w/sum_w
 
-    alpha.append(ab)
-    trees.append(nodes)
+    alphas.append(alpha)
+    trees.append(clf)
 
 predicts = []
 for tree in trees:
-    predicts.append(my_tree.predict(Xtrain, None, tree))
+    predicts.append(tree.predict(Xtrain))
 
-print(alpha)
+print(alphas)
 # 结果加权
 result = np.zeros(len(Xtrain), float)
 for p in predicts:
     r = 0
-    for w_alpha in alpha:
+    for w_alpha in alphas:
         r += w_alpha * p
     result = result + r
 
@@ -88,9 +91,9 @@ print(x)
 # clf = clf.fit(Xtrain, Ytrain)
 # print(clf.score(Xtest, Ytest))
 
-w = np.array([1/len(Xtrain) for i in range(len(Xtrain))])
-my_tree_0 = trees[0]
-Ypredit = my_tree.predict(Xtrain, None, my_tree_0)
+# w = np.array([1/len(Xtrain) for i in range(len(Xtrain))])
+# my_tree_0 = trees[0]
+Ypredit = trees[0].predict(Xtrain)
 error = 0
 for j in range(len(Xtrain)):
     if Ypredit[j] != Ytrain[j]: