实验三：朴素贝叶斯算法实验
|博客班级|https://edu.cnblogs.com/campus/czu/classof2020BigDataClass3-MachineLearning|
|----|----|----|
|作业要求|https://edu.cnblogs.com/campus/czu/classof2020BigDataClass3-MachineLearning/homework/12872|
|学号|201613302|
【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 |
实验内容及结果
实验代码及截图
一、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、
import pandas as pd import numpy as np
2、
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)
3、
dataset = [['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']
]
labels=['色泽','根蒂','敲声','纹理','脐部','触感','好瓜']
dataTrain=pd.DataFrame(dataset,columns=labels)
naiveBayes = NaiveBayes()
treeData = naiveBayes.fit(dataTrain)
4、
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、使用sklearn包编写朴素贝叶斯算法程序，对输入数据进行预测
1、
dataset=[['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']
]
#青绿:0 乌黑:1 浅白:2
# 蜷缩 0 稍蜷 1 硬挺 2
# 浊响 0 沉闷 1 清脆 2
# 清晰 0 稍糊 1 模糊 2
# 凹陷 0 稍凹 1 平坦 2
# 碍滑 0 软粘 1 硬滑 2
# 是 1 否 0
labels=['色泽','根蒂','敲声','纹理','脐部','触感','好瓜']
2、
import pandas as pd target = np.array([0,1,2,3,4,5,6],dtype='float32') data = np.array(dataset,dtype='float32')
3、
from sklearn.naive_bayes import GaussianNB from sklearn.model_selection import train_test_split x_train,x_test,y_train,y_test = train_test_split(data.T,target,random_state=1) #按比例分割数据 nb_clf = GaussianNB() #实例化模型 nb_clf.fit(x_train,y_train) #模型训练 a=nb_clf.predict(x_test) #预测 acc_score = nb_clf.score(x_test,y_test) #查看模型分数
4、
x_train
5、
x_test
三、朴素贝叶斯算法的应用场景
文字识别， 图像识别、文本分类、垃圾邮件的分类、信用评估、钓鱼网站检测等。
标签：self,蜷缩,贝叶斯,浊响,算法,实验,pd,硬滑 From： https://www.cnblogs.com/chenwenwen/p/16884963.html