文本分类中朴素贝叶斯的R交叉验证

Question

我正在尝试使用R检查朴素贝叶斯分类的准确性。目前，我可以对数据集进行随机化，并生成50％的数据用于训练和50％的数据用于测试。根据评论，分类器必须预测标签0或1

我需要实施相同的交叉验证，而不是将数据手动划分为训练和测试目的，以便获得10个案例的平均准确性。

我的数据集的快照如下：

，R代码如下：

 # Load required libraries
    library(tm)
    library(RTextTools)
    library(e1071)
    library(dplyr)
    library(caret)
    #Library for parallel processing
    #install.packages("doMC", repos="http://R-Forge.R-project.org")
    library(doMC)
    registerDoMC(cores=detectCores())  # Use all available cores
    # Load Data
    setwd("C:/Users/malsa876/Desktop/RTest")
    df<- read.csv("mytracks_NaiveBayes_Filter.csv", stringsAsFactors = FALSE)
    glimpse(df)
    #Randomizing Dataset
    df <- df[sample(nrow(df)), ]
    df <- df[sample(nrow(df)), ]
    glimpse(df)
    # Convert the 'class' variable from character to factor.
    df$class <- as.factor(df$Label)
    corpus <- Corpus(VectorSource(df$Review))
    # Inspect the corpus
    corpus
    inspect(corpus[1:3])
    dtm <- DocumentTermMatrix(corpus)
    # Inspect the dtm
    inspect(dtm[40:50, 10:15])
    #Data Partitinoning
    df.train <- df[1:500,]
    df.test <- df[501:1000,]
    dtm.train <- dtm[1:500,]
    dtm.test <- dtm[501:1000,]
    corpus.clean.train <- corpus[1:500] #clean
    corpus.clean.test <- corpus[501:1000] #clean
    dim(dtm.train)
    #fivefreq <- findFreqTerms(dtm.train, 2)
    #length((fivefreq))
    dtm.train.nb <- DocumentTermMatrix(corpus.clean.train)#, control=list(dictionary = fivefreq))
    dim(dtm.train.nb)
    dtm.test.nb <- DocumentTermMatrix(corpus.clean.test)#, control=list(dictionary = fivefreq))
    dim(dtm.train.nb)
    # Function to convert the word frequencies to yes (presence) and no (absence) labels
    convert_count <- function(x) {
      y <- ifelse(x > 0, 1,0)
      y <- factor(y, levels=c(0,1), labels=c("No", "Yes"))
      y
    }
    trainNB <- apply(dtm.train.nb, 2, convert_count)
    testNB <- apply(dtm.test.nb, 2, convert_count)
    # Train the classifier
    system.time( classifier <- naiveBayes(trainNB, df.train$class, laplace = 1) )
    system.time( pred <- predict(classifier, newdata=testNB) )
    table("Predictions"= pred,  "Actual" = df.test$class)
    conf.mat <- confusionMatrix(pred, df.test$class)
    conf.mat
    conf.mat$byClass
    conf.mat$overall
    conf.mat$overall['Accuracy']