数据分析与挖掘 - R语言:贝叶斯分类算法(案例二)
2016-05-25 13:43 猎手家园 阅读(4240) 评论(0) 编辑 收藏 举报接着案例一,我们再使用另一种方法实例一个案例
直接上代码:
#!/usr/bin/Rscript library(plyr) library(reshape2) #1、根据训练集创建朴素贝叶斯分类器 #1.1、生成类别的概率 ##计算训练集合D中类别出现的概率,即P{c_i} ##输入:trainData 训练集,类型为数据框 ## strClassName 指明训练集中名称为 strClassName列为分类结果 ##输出:数据框,P{c_i}的集合,类别名称|概率(列名为 prob) class_prob <- function(trainData, strClassName){ #训练集样本数 #nrow返回行数 length.train <- nrow(trainData) dTemp <- ddply(trainData, strClassName, "nrow") dTemp <- ddply(dTemp, strClassName, mutate, prob = nrow/length.train) dTemp[,-2] } ##1.2、生成每个类别下,特征取不同值的概率 ##计算训练集合D中,生成每个类别下,特征取不同值的概率,即P{fi|c_i} ##输入:trainData 训练集,类型为数据框 ## strClassName 指明训练集中名称为strClassName列为分类结果,其余的全部列认为是特征值 ##输出:数据框,P{fi|c_i}的集合,类别名称|特征名称|特征取值|概率(列名为 prob) feature_class_prob <- function(trainData, strClassName){ # 横表转换为纵表 data.melt <- melt(trainData,id=c(strClassName)) # 统计频数 aa <- ddply(data.melt, c(strClassName,"variable","value"), "nrow") # 计算概率 bb <- ddply(aa, c(strClassName,"variable"), mutate, sum = sum(nrow), prob = nrow/sum) # 增加列名 colnames(bb) <- c("class.name", "feature.name", "feature.value", "feature.nrow", "feature.sum", "prob") # 返回结果 bb[,c(1,2,3,6)] } ## 以上创建完朴素贝叶斯分类器
## 2、使用生成的朴素贝叶斯分类器进行预测 ##使用生成的朴素贝叶斯分类器进行预测P{fi|c_i} ##输入:oneObs 数据框,待预测的样本,格式为 特征名称|特征值 ## pc 数据框,训练集合D中类别出现的概率,即P{c_i} 类别名称|概率 ## pfc 数据框,每个类别下,特征取不同值的概率,即P{fi|c_i} ## 类别名称|特征名称|特征值|概率 ##输出:数据框,待预测样本的分类对每个类别的概率,类别名称|后验概率(列名为 prob) pre_class <- function(oneObs, pc,pfc){ colnames(oneObs) <- c("feature.name", "feature.value") colnames(pc) <- c("class.name","prob") colnames(pfc) <- c("class.name","feature.name","feature.value","prob") # 取出特征的取值的条件概率 feature.all <- join(oneObs,pfc,by=c("feature.name","feature.value"),type="inner") # 取出特征取值的条件概率连乘 feature.prob <- ddply(feature.all,.(class.name),summarize,prob_fea=prod(prob)) #prod为连乘函数 #取出类别的概率 class.all <- join(feature.prob,pc,by="class.name",type="inner") #输出结果 ddply(class.all,.(class.name),mutate,pre_prob=prob_fea*prob)[,c(1,4)] } ##3、数据测试 ##用上面苹果的数据作为例子进行测试 #训练集 train.apple <-data.frame( size=c("大","小","大","大","小","小"), weight=c("轻","重","轻","轻","重","轻"), color=c("红","红","红","绿","红","绿"), taste=c("good","good","bad","bad","bad","good") ) #待预测样本 oneObs<-data.frame( feature.name =c("size", "weight", "color"), feature.value =c("大","重","红") ) #预测分类 pc <- class_prob(train.apple,"taste") pfc <- feature_class_prob(train.apple,"taste") pre_class(oneObs, pc, pfc)
预测结果为:
class.name pre_prob
1 bad 0.07407407
2 good 0.03703704
可见该苹果的口味为:bad
*********************************************这里是分割线****************************************************
我们使用这个方法再预测一下案例一中的数据集。
#数据集样本 data <- data.frame(c("sunny","hot","high","weak","no", "sunny","hot","high","strong","no", "overcast","hot","high","weak","yes", "rain","mild","high","weak","yes", "rain","cool","normal","weak","yes", "rain","cool","normal","strong","no", "overcast","cool","normal","strong","yes", "sunny","mild","high","weak","no", "sunny","cool","normal","weak","yes", "rain","mild","normal","weak","yes", "sunny","mild","normal","strong","yes", "overcast","mild","high","strong","yes", "overcast","hot","normal","weak","yes", "rain","mild","high","strong","no"), byrow = TRUE, dimnames = list(day = c(),condition = c("outlook","temperature","humidity","wind","playtennis")), nrow=14, ncol=5); #待预测样本 ddata<-data.frame( feature.name =c("outlook", "temperature","humidity","wind"), feature.value =c("overcast","mild","normal","weak") ) #预测分类 pc <- class_prob(data,"playtennis") pfc <- feature_class_prob(data,"playtennis") pre_class(ddata, pc, pfc)
预测结果为:
class.name pre_prob
1 no 0.02666667
2 yes 0.13168724
预测结果为:yes,可见与案例一的结果一样。
欢迎关注我的公众号:云栖语,不一样的研发视界。
云栖语微信公众号:change-1978