6.4:动手实现决策树
import numpy as np
def calcInfoEntropy(label):
'''
label(narray):样本标签
'''
label_set = set(label)
result = 0
for l in label_set:
count = 0
for j in range(len(label)):
if label[j] == l:
count += 1
p = count / len(label)
result -= p * np.log2(p)
return result
def calcHDA(feature,label,index,value):
'''
input:
feature(ndarray):样本特征
label(ndarray):样本标签
index(int):需要使用的特征列索引
value(int):index所表示的特征列中需要考察的特征值
output:
HDA(float):信息熵
'''
count = 0
sub_feature = []
sub_label = []
for i in range(len(feature)):
if feature[i][index] == value:
count += 1
sub_feature.append(feature[i])
sub_label.append(label[i])
pHA = count / len(feature)
e = calcInfoEntropy(sub_label)
HDA = pHA * e
return HDA
def calcInfoGain(feature, label, index):
'''
input:
feature(ndarry):测试用例中字典里的feature
label(ndarray):测试用例中字典里的label
index(int):测试用例中字典里的index,即feature部分特征列的索引。该索引指的是feature中第几个特征,如index:0表示使用第一个特征来计算信息增益。
output:
InfoGain(float):信息增益
'''
base_e = calcInfoEntropy(label)
f = np.array(feature)
f_set = set(f[:, index])
sum_HDA = 0
for value in f_set:
sum_HDA += calcHDA(feature, label, index, value)
InfoGain = base_e - sum_HDA
return InfoGain
def getBestFeature(feature, label):
'''
input:
feature(ndarray):样本特征
label(ndarray):样本标签
output:
best_feature(int):信息增益最高的特征
'''
max_infogain = 0
best_feature = 0
for i in range(len(feature[0])):
infogain = calcInfoGain(feature, label, i)
if infogain > max_infogain:
max_infogain = infogain
best_feature = i
return best_feature
def createTree(feature, label):
'''
input:
feature(ndarray):训练样本特征
label(ndarray):训练样本标签
output:
tree(dict):决策树模型
'''
if len(set(label)) == 1:
return label[0]
if len(feature[0]) == 1 or len(np.unique(feature, axis=0)) == 1:
vote = {}
for l in label:
if l in vote.keys():
vote[l] += 1
else:
vote[l] = 1
max_count = 0
vote_label = None
for k, v in vote.items():
if v > max_count:
max_count = v
vote_label = k
return vote_label
best_feature = getBestFeature(feature, label)
tree = {best_feature: {}}
f = np.array(feature)
f_set = set(f[:, best_feature])
for v in f_set:
sub_feature = []
sub_label = []
for i in range(len(feature)):
if feature[i][best_feature] == v:
sub_feature.append(feature[i])
sub_label.append(label[i])
tree[best_feature][v] = createTree(sub_feature, sub_label)
return tree
def dt_clf(train_feature,train_label,test_feature):
'''
input:
train_feature(ndarray):训练样本特征
train_label(ndarray):训练样本标签
test_feature(ndarray):测试样本特征
output:
predict(ndarray):测试样本预测标签
'''
tree = createTree(train_feature,train_label)
result = []
def classify(tree,test_feature):
if not isinstance(tree,dict):
return tree
t_index,t_value = list(tree.items())[0]
f_value = test_feature[t_index]
if isinstance(t_value,dict):
classLabel = classify(tree[t_index][f_value],test_feature)
return classLabel
else:
return t_value
for f in test_feature:
result.append(classify(tree,f))
predict = np.array(result)
return predict