实验三：朴素贝叶斯算法
【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 |
创建数据：
不使用sk-learn包
1.
#encoding:utf-8
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_excel('D:\\课程\\机器学习\\西瓜.xlsx', header=None,engine='openpyxl')
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]))
使用sk-learn包
1.导入数据
#导入相关库
import pandas as pd
import graphviz
from sklearn.model_selection import train_test_split
from sklearn import tree
data = pd.read_excel('D:\\课程\\机器学习\\西瓜.xlsx')
x = data[["色泽","根蒂","敲声","纹理","脐部","触感"]].copy()
y = data['好瓜'].copy()
print(data)
2.特征值数值化
#将特征值数值化
x = x.copy()
for i in ["色泽","根蒂","敲声","纹理","脐部","触感"]:
for j in range(len(x)):
if(x[i][j] == "青绿" or x[i][j] == "蜷缩" or data[i][j] == "浊响" \
or x[i][j] == "清晰" or x[i][j] == "凹陷" or x[i][j] == "硬滑"):
x[i][j] = 1
elif(x[i][j] == "乌黑" or x[i][j] == "稍蜷" or data[i][j] == "沉闷" \
or x[i][j] == "稍糊" or x[i][j] == "稍凹" or x[i][j] == "软粘"):
x[i][j] = 2
else:
x[i][j] = 3
y = y.copy()
for i in range(len(y)):
if(y[i] == "是"):
y[i] = int(1)
else:
y[i] = int(-1)
#需要将数据x，y转化好格式，数据框dataframe，否则格式报错
x = pd.DataFrame(x).astype(int)
y = pd.DataFrame(y).astype(int)
print(x)
print(y)
3.x值
x_train, x_test, y_train, y_test = train_test_split(x,y,test_size=0.2) print(x_train)
4.决策树实例
#决策树学习 clf = tree.DecisionTreeClassifier(criterion="entropy") #实例化 clf = clf.fit(x_train, y_train) score = clf.score(x_test, y_test) print(score)
朴树贝叶斯应用场景：1.文本分类
2.垃圾文本过滤
3.情感判别
浙公网安备 33010602011771号