machine_learn/integr/my_ada_boost.py

# -*- encoding:utf-8 -*-
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
alpha = []
# 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(30):
    # 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)

    # my_tree.print_width([nodes], 1)
    # print("熵值", my_tree.calc_ent(Ytrain, w))
    Xpredit = my_tree.predict(Xtrain, Ytrain, nodes)
    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)
    ab = 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])
    sum_w = sum(w)
    w = w/sum_w

    alpha.append(ab)
    trees.append(nodes)

predicts = []
for tree in trees:
    predicts.append(my_tree.predict(Xtest, None, tree))

print(alpha)
# 结果加权
result = np.zeros(len(Xtest), float)
for p in predicts:
    r = 0
    for w_alpha in alpha:
        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(len([i for i in result == Ytest if i])/len(result))
# cmp = np.concatenate(([result], [Ytest]), axis=0)
# print(cmp)


clf = DecisionTreeClassifier(criterion="entropy", max_features=1, max_depth=1)
clf = clf.fit(Xtrain, Ytrain)
print(clf.score(Xtest, Ytest))