实验三：朴素贝叶斯算法实验

【实验目的】

理解朴素贝叶斯算法原理，掌握朴素贝叶斯算法框架。

【实验内容】

针对下表中的数据，编写python程序实现朴素贝叶斯算法（不使用sklearn包），对输入数据进行预测；
熟悉sklearn库中的朴素贝叶斯算法，使用sklearn包编写朴素贝叶斯算法程序，对输入数据进行预测；

【实验报告要求】

对照实验内容，撰写实验过程、算法及测试结果；
代码规范化：命名规则、注释；
查阅文献，讨论朴素贝叶斯算法的应用场景。

色泽	根蒂	敲声	纹理	脐部	触感	好瓜
青绿	蜷缩	浊响	清晰	凹陷	碍滑	是
乌黑	蜷缩	沉闷	清晰	凹陷	碍滑	是
乌黑	蜷缩	浊响	清晰	凹陷	碍滑	是
青绿	蜷缩	沉闷	清晰	凹陷	碍滑	是
浅白	蜷缩	浊响	清晰	凹陷	碍滑	是
青绿	稍蜷	浊响	清晰	稍凹	软粘	是
乌黑	稍蜷	浊响	稍糊	稍凹	软粘	是
乌黑	稍蜷	浊响	清晰	稍凹	硬滑	是
乌黑	稍蜷	沉闷	稍糊	稍凹	硬滑	否
青绿	硬挺	清脆	清晰	平坦	软粘	否
浅白	硬挺	清脆	模糊	平坦	硬滑	否
浅白	蜷缩	浊响	模糊	平坦	软粘	否
青绿	稍蜷	浊响	稍糊	凹陷	硬滑	否
浅白	稍蜷	沉闷	稍糊	凹陷	硬滑	否
乌黑	稍蜷	浊响	清晰	稍凹	软粘	否
浅白	蜷缩	浊响	模糊	平坦	硬滑	否
青绿	蜷缩	沉闷	稍糊	稍凹	硬滑	否

一、针对下表中的数据，编写python程序实现朴素贝叶斯算法（不使用sklearn包），对输入数据进行预测；

（1）创建数据

import numpy as np
import pandas as pd
from math import exp, sqrt, pi
 
 
def getDataSet():
    dataSet = [
        ['青绿', '蜷缩', '浊响', '清晰', '凹陷', '硬滑', 0.697, 0.460, 1],
        ['乌黑', '蜷缩', '沉闷', '清晰', '凹陷', '硬滑', 0.774, 0.376, 1],
        ['乌黑', '蜷缩', '浊响', '清晰', '凹陷', '硬滑', 0.634, 0.264, 1],
        ['青绿', '蜷缩', '沉闷', '清晰', '凹陷', '硬滑', 0.608, 0.318, 1],
        ['浅白', '蜷缩', '浊响', '清晰', '凹陷', '硬滑', 0.556, 0.215, 1],
        ['青绿', '稍蜷', '浊响', '清晰', '稍凹', '软粘', 0.403, 0.237, 1],
        ['乌黑', '稍蜷', '浊响', '稍糊', '稍凹', '软粘', 0.481, 0.149, 1],
        ['乌黑', '稍蜷', '浊响', '清晰', '稍凹', '硬滑', 0.437, 0.211, 1],
        ['乌黑', '稍蜷', '沉闷', '稍糊', '稍凹', '硬滑', 0.666, 0.091, 0],
        ['青绿', '硬挺', '清脆', '清晰', '平坦', '软粘', 0.243, 0.267, 0],
        ['浅白', '硬挺', '清脆', '模糊', '平坦', '硬滑', 0.245, 0.057, 0],
        ['浅白', '蜷缩', '浊响', '模糊', '平坦', '软粘', 0.343, 0.099, 0],
        ['青绿', '稍蜷', '浊响', '稍糊', '凹陷', '硬滑', 0.639, 0.161, 0],
        ['浅白', '稍蜷', '沉闷', '稍糊', '凹陷', '硬滑', 0.657, 0.198, 0],
        ['乌黑', '稍蜷', '浊响', '清晰', '稍凹', '软粘', 0.360, 0.370, 0],
        ['浅白', '蜷缩', '浊响', '模糊', '平坦', '硬滑', 0.593, 0.042, 0],
        ['青绿', '蜷缩', '沉闷', '稍糊', '稍凹', '硬滑', 0.719, 0.103, 0]
    ]
 
    features = ['色泽', '根蒂', '敲声', '纹理', '脐部', '触感', '密度', '含糖量']

(2)算法实现

import pandas as pd
import numpy  as np

class NaiveBayes:
    def __init__(self):
        self.model = {}#key 为类别名 val 为字典PClass表示该类的该类，PFeature:{}对应对于各个特征的概率
    def calEntropy(self, y): # 计算熵
        valRate = y.value_counts().apply(lambda x : x / y.size) # 频次汇总 得到各个特征对应的概率
        valEntropy = np.inner(valRate, np.log2(valRate)) * -1
        return valEntropy

    def fit(self, xTrain, yTrain = pd.Series()):
        if not yTrain.empty:#如果不传，自动选择最后一列作为分类标签
            xTrain = pd.concat([xTrain, yTrain], axis=1)
        self.model = self.buildNaiveBayes(xTrain) 
        return self.model
    def buildNaiveBayes(self, xTrain):
        yTrain = xTrain.iloc[:,-1]
        
        yTrainCounts = yTrain.value_counts()# 频次汇总 得到各个特征对应的概率

        yTrainCounts = yTrainCounts.apply(lambda x : (x + 1) / (yTrain.size + yTrainCounts.size)) #使用了拉普拉斯平滑
        retModel = {}
        for nameClass, val in yTrainCounts.items():
            retModel[nameClass] = {'PClass': val, 'PFeature':{}}

        propNamesAll = xTrain.columns[:-1]
        allPropByFeature = {}
        for nameFeature in propNamesAll:
            allPropByFeature[nameFeature] = list(xTrain[nameFeature].value_counts().index)
        #print(allPropByFeature)
        for nameClass, group in xTrain.groupby(xTrain.columns[-1]):
            for nameFeature in propNamesAll:
                eachClassPFeature = {}
                propDatas = group[nameFeature]
                propClassSummary = propDatas.value_counts()# 频次汇总 得到各个特征对应的概率
                for propName in allPropByFeature[nameFeature]:
                    if not propClassSummary.get(propName):
                        propClassSummary[propName] = 0#如果有属性灭有，那么自动补0
                Ni = len(allPropByFeature[nameFeature])
                propClassSummary = propClassSummary.apply(lambda x : (x + 1) / (propDatas.size + Ni))#使用了拉普拉斯平滑
                for nameFeatureProp, valP in propClassSummary.items():
                    eachClassPFeature[nameFeatureProp] = valP
                retModel[nameClass]['PFeature'][nameFeature] = eachClassPFeature

        return retModel
    def predictBySeries(self, data):
        curMaxRate = None
        curClassSelect = None
        for nameClass, infoModel in self.model.items():
            rate = 0
            rate += np.log(infoModel['PClass'])
            PFeature = infoModel['PFeature']
            
            for nameFeature, val in data.items():
                propsRate = PFeature.get(nameFeature)
                if not propsRate:
                    continue
                rate += np.log(propsRate.get(val, 0))#使用log加法避免很小的小数连续乘，接近零
                #print(nameFeature, val, propsRate.get(val, 0))
            #print(nameClass, rate)
            if curMaxRate == None or rate > curMaxRate:
                curMaxRate = rate
                curClassSelect = nameClass
            
        return curClassSelect
    def predict(self, data):
        if isinstance(data, pd.Series):
            return self.predictBySeries(data)
        return data.apply(lambda d: self.predictBySeries(d), axis=1)
dataTrain = pd.read_csv("D:/机器学习/data_word.csv", encoding = "gbk")

naiveBayes = NaiveBayes()
treeData = naiveBayes.fit(dataTrain)

import json
print(json.dumps(treeData, ensure_ascii=False))

pd = pd.DataFrame({'预测值':naiveBayes.predict(dataTrain), '正取值':dataTrain.iloc[:,-1]})
print(pd)
print('正确率:%f%%'%(pd[pd['预测值'] == pd['正取值']].shape[0] * 100.0 / pd.shape[0]))

二、熟悉sklearn库中的朴素贝叶斯算法，使用sklearn包编写朴素贝叶斯算法程序，对输入数据进行预测；

import numpy as np
import pandas as pd
from sklearn.naive_bayes import GaussianNB
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
datasets=[['0','0','0','0','0','0','1'],
['1','0','1','0','0','0','1'],
['1','0','0','0','0','0','1'],
['0','0','1','0','0','0','1'],
['2','0','0','0','0','0','1'],
['0','1','0','0','1','1','1'],
['1','1','0','1','1','1','1'],
['1','1','0','0','1','2','1'],
['1','1','1','1','1','2','0'],
['0','2','2','0','2','1','0'],
['2','2','2','2','2','2','0'],
['2','0','0','2','2','1','0'],
['0','1','0','1','0','2','0'],
['2','1','1','1','0','2','0'],
['1','1','0','0','1','1','0'],
['2','0','0','2','2','2','0'],
['0','0','1','1','1','2','0']
]
labels=['色泽','根蒂','敲声','纹理','脐部','触感','好瓜']
data=pd.DataFrame(datasets,columns=labels)
X=data.iloc[:,:-1]
y=data.iloc[:,-1]
x_train,x_test,y_train,y_test = train_test_split(X,y,test_size=1,random_state=None)
ga = GaussianNB() #实例化
ga.fit(x_train,y_train) #模型训练
y_pref=ga.predict(x_test) #预测
ga.score(x_test,y_test) #模型准确率