完善

integr/my_ada_boost.py

@@ -3,99 +3,97 @@ from sklearn.datasets import load_wine, load_iris, load_breast_cancer
 from sklearn.model_selection import train_test_split
 from sklearn.tree import DecisionTreeClassifier
 import numpy as np
-from tree import my_tree
-
-wine = load_breast_cancer()
-Xtrain, Xtest, Ytrain, Ytest = train_test_split(wine.data,wine.target,test_size=0.3)
-
-# 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
-alphas = []
-# 决策树数组
-trees = []
-pn = 1/len(Ytrain)
-
-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
-print(Ytest)
-
-for i in range(20):
-    # 训练决策树
-    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
-
-    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 = clf.predict(Xtrain)
-    error = 0
-    p_error = 0
-    for j in range(len(Ytrain)):
-        if Xpredit[j] != Ytrain[j]:
-            error += w[j]
-            p_error += pn
-
-    if error > 0.5:
-        continue
-    if error == 0:
-        error = 0.001
-
-    print("第", i, "轮错误率", p_error, error)
-    alpha = 0.5*np.log2(1/error - 1)
-
-    # 更新权重
-    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
-
-    alphas.append(alpha)
-    trees.append(clf)
-
-predicts = []
-for tree in trees:
-    predicts.append(tree.predict(Xtrain))
-
-print(alphas)
-# 结果加权
-result = np.zeros(len(Xtrain), float)
-for p in predicts:
-    r = 0
-    for w_alpha in alphas:
-        r += w_alpha * p
-    result = result + r
-
-print("sign前:" , result)
-result = np.sign(result)
-print("sign后:", result)
-
-# print(1- sum(np.bitwise_xor(Ytest, result))/len(result))
-# print(result == Ytest)
-print()
-x = len([i for i in result == Ytrain if i])/len(result)
-x = x + 0.5*len([i for i in result if i==0])/len(result)
-print(x)
-# cmp = np.concatenate(([result], [Ytest]), axis=0)
-# print(cmp)
-
-
-# clf = DecisionTreeClassifier(criterion="entropy", max_features=1, max_depth=2)
-# 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 = trees[0].predict(Xtrain)
-error = 0
-for j in range(len(Xtrain)):
-    if Ypredit[j] != Ytrain[j]:
-        error += w[j]
-print(1-error)
+from tree.my_tree import MyDT
+
+
+def read_data():
+    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
+
+
+def fit(Xtrain, Ytrain):
+    # 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
+    alphas = []
+    # 决策树数组
+    trees = []
+    pn = 1/len(Ytrain)
+    print(Ytest)
+
+    for i in range(20):
+        # 训练决策树
+        clf = MyDT(criterion="entropy", max_features=1, max_depth=1,
+                                     )  # 实例化，criterion不写的话默认是基尼系数
+
+        clf.fit(Xtrain, Ytrain, w)
+        Xpredit = clf.predict(Xtrain)
+
+        error = np.dot([Xpredit != Ytrain], w)
+        p_error = sum(Xpredit != Ytrain)/Ytrain.shape[0]
+
+        if error > 0.5:
+            continue
+        if error == 0:
+            error = 0.001
+
+        print("第", i, "轮错误率", p_error, error)
+        alpha = 0.5*np.log2(1/error - 1)
+
+        # 更新权重
+        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
+
+        alphas.append(alpha)
+        trees.append(clf)
+    return trees, alphas
+
+
+def cmp_predict(trees, alphas, Xtrain, Ytrain):
+    predicts = []
+    for tree in trees:
+        predicts.append(tree.predict(Xtrain))
+
+    # 结果加权
+    result = np.zeros(len(Xtrain), float)
+    for p in predicts:
+        r = 0
+        for w_alpha in alphas:
+            r += w_alpha * p
+        result = result + r
+
+    # print("sign前:" , result)
+    result = np.sign(result)
+    # print("sign后:", result)
+
+    # print(1- sum(np.bitwise_xor(Ytest, result))/len(result))
+    # print(result == Ytest)
+    x = len([i for i in result == Ytrain if i])/len(result)
+    x = x + 0.5*len([i for i in result if i==0])/len(result)
+    print(x)
+
+    w = np.array([1/len(Xtrain) for i in range(len(Xtrain))])
+    Ypredit = trees[0].predict(Xtrain)
+    p_error = sum(Ypredit != Ytrain)/Ytrain.shape[0]
+    print(1-p_error)
+
+
+if __name__ == '__main__':
+    Xtrain, Xtest, Ytrain, Ytest = read_data()
+    trees, alphas = fit(Xtrain, Ytrain)
+
+    print(alphas)
+
+    print('训练集上比较')
+    cmp_predict(trees, alphas, Xtrain, Ytrain)
+    print('测试集上比较')
+    cmp_predict(trees, alphas, Xtest, Ytest)

tree/example.py

@@ -20,7 +20,7 @@ print(wine.target_names)
 Xtrain, Xtest, Ytrain, Ytest = train_test_split(wine.data,wine.target,test_size=0.3)
 numpy.savetxt("foo.csv", Xtrain, delimiter=",")
 
-clf = tree.DecisionTreeClassifier(criterion="entropy", max_features=1, max_depth=5)#实例化，criterion不写的话默认是基尼系数
+clf = tree.DecisionTreeClassifier(criterion="entropy", max_features=1, max_depth=1)#实例化，criterion不写的话默认是基尼系数
 # clf.n_features_ = 2
 clf = clf.fit(Xtrain, Ytrain)
 score = clf.score(Xtest, Ytest) #返回预测的准确度

tree/my_tree.py

@@ -304,7 +304,7 @@ class MyDT(object):
 
     root_node = None
 
-    def __init__(self, criterion, max_depth):
+    def __init__(self, criterion, max_depth, max_features=1):
         self.criterion = criterion
         self.max_depth = max_depth