Decison Tree的註釋：畫圖部分不給註釋了

from math import log
import numpy
def calcShannonEnt(dataSet):
    numEntries = len(dataSet)
    labelCounts = {}

#這個是字典，｛a:1,b:2｝其中a，b是key，1，2是對應的value
    for featVec in dataSet:
        currentLabel = featVec[-1]

#-1代表最後一行，也就是類標
        if currentLabel not in labelCounts.keys():
            labelCounts[currentLabel] = 0
 
labelCounts[currentLabel] += 1
shannonEnt = 0.0
for key in labelCounts:
        prob = float(labelCounts[key])/numEntries
        shannonEnt -= prob * log(prob,2)
    return shannonEnt
def createDataSet():
    dataSet=[[1,1,'yes'],
             [1,1,'yes'],
             [1,0,'no'],
             [0,1,'yes'
 
],
             [0,1,'no']]
    labels=['no surfacing','flippers']
    return dataSet,labels
#依據特徵劃分資料集  axis代表第幾個特徵  value代表該特徵所對應的值  返回的是劃分後的資料集def splitDataSet(dataSet, axis, value):
    retDataSet = []
    for featVec in dataSet:
        if featVec[axis] == value:
            reducedFeatVec = featVec[:axis]

#這裡的featVec[:axis]，是指從第1（就是下標0）個數到第axis個，不包含
            reducedFeatVec.extend(featVec[axis+1:])

#同上，這裡的[axis+1,:]就是從最後到axis+1
            retDataSet.append(reducedFeatVec)

#extend,append都是擴充套件用的，a=[1,2],b=[3,4],a.append(b)=[1,2,[3,4]],a.extend(b)=[1,2,3,4]
    return retDataSet

#選擇最好的資料集(特徵)劃分方式  返回最佳特徵下標
def chooseBestFeatureToSplit(dataSet):
    numFeatures = len(dataSet[0]) - 1   #特徵個數
    baseEntropy = calcShannonEnt(dataSet)
    bestInfoGain = 0.0; bestFeature = -1
    for i in range(numFeatures):   #遍歷特徵 第i個
        featureSet = set([example[i] for example in dataSet])   #第i個特徵取值集合

#這一部分程式碼沒啥難度，跟matalb差不多，唯一就是這個set
        newEntropy= 0.0
        for value in featureSet:
            subDataSet = splitDataSet(dataSet, i, value)
            prob = len(subDataSet)/float(len(dataSet))
            newEntropy += prob * calcShannonEnt(subDataSet)   #該特徵劃分所對應的entropy
        infoGain = baseEntropy - newEntropy
        if infoGain > bestInfoGain:
            bestInfoGain = infoGain
            bestFeature = i
    return bestFeature

#建立樹的函式程式碼   python中用字典型別來儲存樹的結構 返回的結果是myTree-字典
def createTree(dataSet, labels):
    classList = [example[-1] for example in dataSet]
    if classList.count(classList[0]) == len(classList):    #類別完全相同則停止繼續劃分  返回類標籤-葉子節點
        return classList[0]
    if len(dataSet[0]) == 1:
        return majorityCnt(classList)       #遍歷完所有的特徵時返回出現次數最多的
    bestFeat = chooseBestFeatureToSplit(dataSet)
    bestFeatLabel = labels[bestFeat]
    myTree = {bestFeatLabel:{}}
    del(labels[bestFeat])
    featValues = [example[bestFeat] for example in dataSet]    #得到的列表包含所有的屬性值
    uniqueVals = set(featValues)
    for value in uniqueVals:
        subLabels = labels[:]
        myTree[bestFeatLabel][value] = createTree(splitDataSet(dataSet, bestFeat, value), subLabels)
    return myTree

#多數表決的方法決定葉子節點的分類 ----  當所有的特徵全部用完時仍屬於多類
def majorityCnt(classList):
    classCount = {}
    for vote in classList:
        if vote not in classCount.key():
            classCount[vote] = 0;
        classCount[vote] += 1
    sortedClassCount = sorted(classCount.iteritems(), key = operator.itemgetter(1), reverse = True)

#排序函式，至於怎麼用，help就好，裡面引數設定有詳細例子
    return sortedClassCount[0][0]

建立樹的函式程式碼   其實這一步應該放在上一步前面
def createTree(dataSet, labels):
    classList = [example[-1] for example in dataSet]
    if classList.count(classList[0]) == len(classList):    #類別完全相同則停止繼續劃分  返回類標籤-葉子節點
return classList[0]

#count是數數目的函式，a=[1,1,2] a.count[1]=2 len相當於matalb裡的length
    if len(dataSet[0]) == 1:
        return majorityCnt(classList)       #遍歷完所有的特徵時返回出現次數最多的
bestFeat = chooseBestFeatureToSplit(dataSet)
    bestFeatLabel = labels[bestFeat]
    myTree = {bestFeatLabel:{}}
    del(labels[bestFeat])
    featValues = [example[bestFeat] for example in dataSet]    #得到的列表包含所有的屬性值
uniqueVals = set(featValues)
    for value in uniqueVals:
        subLabels = labels[:]
        myTree[bestFeatLabel][value] = createTree(splitDataSet(dataSet, bestFeat, value), subLabels)

#這一步creteTree裡面又用了creatTree，遞迴呼叫，直到len(dataSet[0]) == 1:
    return myTree