决策树算法的python实现

import numpy as np 
import pandas as pd
def calEnt(dataSet) : 
    n = dataSet.shape[0] # 数据集总行数 
    iset = dataSet.iloc[: , -1] . value_counts() # 标签的所有类别 
    p = iset/n # 每一类标签所占比 
    ent = (-p*np.log2(p)).sum() # 计算信息熵 
    return ent
def createDataSet() : 
    row_data = { 'no surfacing' : [ 1, 1, 1,0,0] , 'flippers' : [1, 1, 0,1,1] , 'fish' : [ 'yes' , 'yes' , 'no' , 'no' , 'no']} 
    dataSet = pd.DataFrame(row_data) 
    return dataSet
dataSet = createDataSet()
print(calEnt(dataSet))
def bestSplit(dataSet) : 
    baseEnt = calEnt(dataSet) # 计算原始熵 
    bestGain = 0 # 初始化信息增益 
    axis = -1
    for i in range(dataSet.shape[1]-1): # 对特征的每一列进行循环 
        levels= dataSet.iloc[: , i ] . value_counts().index # 提取出当前列的所有取值 
        ents = 0
        for j in levels: # 对当前列的每一个取值进 行循环 
            childSet = dataSet[dataSet.iloc[: , i ] ==j] # 某一个子节点的 
            ent = calEnt(childSet)
            ents += (childSet.shape[0]/dataSet.shape[0])*ent
        infoGain = baseEnt-ents
        if (infoGain > bestGain): 
            bestGain = infoGain # 选择最大信息增益 
            axis = i
    return axis
print(bestSplit(dataSet))
def mySplit(dataSet,axis,value): 
    col = dataSet.columns[axis] 
    redataSet = dataSet.loc[dataSet[col]==value, : ] . drop(col , axis=1) 
    return redataSet
print(mySplit(dataSet,0,1))
def createTree(dataSet): 
    featlist = list(dataSet.columns) # 提取出数据集所有的列 
    classlist = dataSet.iloc[: , -1] . value_counts()
    if classlist[0]==dataSet.shape[0] or dataSet.shape[1] == 1: 
        return classlist.index[0]
    axis = bestSplit(dataSet)
    bestfeat = featlist[axis]
    myTree = {bestfeat:{}}
    del featlist[axis] # 删除当前特征 
    valuelist = set(dataSet.iloc[: , axis])
    for value in valuelist:
        myTree[bestfeat] [value] = createTree(mySplit(dataSet,axis,value))
    return myTree
np.save('myTree.npy' , createTree(dataSet)) # 树的读取 
read_myTree = np.load('myTree.npy',allow_pickle=True).item()
print(read_myTree)
def classify(inputTree,labels, testVec): 
    firstStr = next(iter(inputTree)) # 获取决策树第一个节点 
    secondDict = inputTree[firstStr] # 下一个字典 
    featIndex = labels.index(firstStr)
    for key in secondDict.keys():
        if testVec[featIndex] == key:
            if type(secondDict[key]) == dict :
                classLabel = classify(secondDict[key] , labels, testVec)
            else:
                classLabel = secondDict[key]
    return classLabel
def acc_classify(train,test) :
    inputTree = createTree(train) # 根据测试集生成一棵树 
    labels = list(train.columns) # 数据集所有的列名称 
    result = []
    for i in range(test.shape[0]) :
        testVec = test.iloc[i , : -1] # 测试集中的一个实例 
        classLabel = classify(inputTree,labels,testVec) # 预测该实例的分类 
        result.append(classLabel)
    test['predict']=result # 将预测结果追加到测试集最后一 列 
    acc = (test.iloc[: , -1]==test.iloc[: , -2]) . mean() # 计算准确率 
    print(f' 模型预测准确率为 {acc}') 
    return test
train = dataSet 
test = dataSet.iloc[:3, : ] 
acc_classify(train,test)