机器学习实战-决策树预测隐形眼镜类型

我们将用递归来构建分类器并使用 Matplotlib 绘制。分类器获取隐形眼镜处方的数据，并用尝试预测人们需要什么镜片。
需要用到的库

# -*- coding: utf-8 -*-

from math import log
import operator
import matplotlib.pyplot as plt

主要代码

def calcShannonEnt(dataSet):
    numEntries = len(dataSet)
    labelCounts = {
   }
    for featVec in dataSet:
        currentLabel = featVec[-1]
        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 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


def chooseBestFeatureToSplit(dataSet):
    numFeatures = len(dataSet[0]) - 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


def majorityCnt(classList):
    classCount = {
   }
    for vote in classList:
        if vote not in classCount