吴裕雄 python 机器学习-DMT（1）

import numpy as np
import operator as op

from math import log

def createDataSet():
    dataSet = [[1, 1, 'yes'],
               [1, 1, 'yes'],
               [1, 0, 'no'],
               [0, 1, 'no'],
               [0, 1, 'no']]
    labels = ['no surfacing','flippers']
    return dataSet, labels

dataSet,labels = createDataSet()
print(dataSet)
print(labels)

def calcShannonEnt(dataSet):
    labelCounts = {}
    for featVec in dataSet:
        currentLabel = featVec[-1]
        if(currentLabel not in labelCounts.keys()):
            labelCounts[currentLabel] = 0
        labelCounts[currentLabel] += 1
    shannonEnt = 0.0
    rowNum = len(dataSet)
    for key in labelCounts:
        prob = float(labelCounts[key])/rowNum
        shannonEnt -= prob * log(prob,2)
    return shannonEnt

shannonEnt = calcShannonEnt(dataSet)
print(shannonEnt)

def splitDataSet(dataSet, axis, value):
    retDataSet = []
    for featVec in dataSet:
        if(featVec[axis] == value):
            reducedFeatVec = featVec[:axis]
            reducedFeatVec.extend(featVec[axis+1:])
            retDataSet.append(reducedFeatVec)
    return retDataSet

retDataSet = splitDataSet(dataSet,1,1)
print(np.array(retDataSet))
retDataSet = splitDataSet(dataSet,1,0)
print(retDataSet)

def chooseBestFeatureToSplit(dataSet):
    numFeatures = np.shape(dataSet)[1]-1
    baseEntropy = calcShannonEnt(dataSet)
    bestInfoGain = 0.0
    bestFeature = -1
    for i in range(numFeatures):
        featList = [example[i] for example in dataSet]
        uniqueVals = set(featList)
        newEntropy = 0.0
        for value in uniqueVals:
            subDataSet = splitDataSet(dataSet, i, value)
            prob = len(subDataSet)/float(len(dataSet))
            newEntropy += prob * calcShannonEnt(subDataSet)
        infoGain = baseEntropy - newEntropy
        if (infoGain > bestInfoGain):
            bestInfoGain = infoGain
            bestFeature = i
    return bestFeature 

bestFeature = chooseBestFeatureToSplit(dataSet)
print(bestFeature)

def majorityCnt(classList):
    classCount={}
    for vote in classList:
        if(vote not in classCount.keys()):
            classCount[vote] = 0
        classCount[vote] += 1
    sortedClassCount = sorted(classCount.items(), key=op.itemgetter(1), reverse=True)
    return sortedClassCount[0][0]

def createTree(dataSet,labels):
    classList = [example[-1] for example in dataSet]
    if(classList.count(classList[0]) == len(classList)):
        return classList[0]
    if len(dataSet[0]) == 1:
        return majorityCnt(classList)
    bestFeat = chooseBestFeatureToSplit(dataSet)
    bestFeatLabel = labels[bestFeat]
    myTree = {bestFeatLabel:{}}
    del(labels[bestFeat])
    featValues = [example[bestFeat] for example in dataSet]
    uniqueVals = set(featValues)
    for value in uniqueVals:
        subLabels = labels[:]
        myTree[bestFeatLabel][value] = createTree(splitDataSet(dataSet, bestFeat, value),subLabels)
    return myTree

myTree = createTree(dataSet,labels)
print(myTree)

def classify(inputTree,featLabels,testVec):
    for i in inputTree.keys():
        firstStr = i
        break
    secondDict = inputTree[firstStr]
    featIndex = featLabels.index(firstStr)
    key = testVec[featIndex]
    valueOfFeat = secondDict[key]
    if isinstance(valueOfFeat, dict):
        classLabel = classify(valueOfFeat, featLabels, testVec)
    else:
        classLabel = valueOfFeat
    return classLabel

featLabels = ['no surfacing', 'flippers']
classLabel = classify(myTree,featLabels,[1,1])
print(classLabel)

import pickle

def storeTree(inputTree,filename):
    fw = open(filename,'wb')
    pickle.dump(inputTree,fw)
    fw.close()

def grabTree(filename):
    fr = open(filename,'rb')
    return pickle.load(fr)

filename = "D:\\mytree.txt"
storeTree(myTree,filename)
mySecTree = grabTree(filename)
print(mySecTree)

featLabels = ['no surfacing', 'flippers']
classLabel = classify(mySecTree,featLabels,[0,0])
print(classLabel)