library(RTextTools)
data <- read_data(system.file("data/NYTimes.csv.gz",package="RTextTools"),type="csv")
data <- data[sample(1:3100,size=100,replace=FALSE),]
matrix <- create_matrix(cbind(data$Title,data$Subject), language="english",
removeNumbers=TRUE, stemWords=FALSE, weighting=weightTfIdf)
corpus <- create_corpus(matrix,data$Topic.Code,trainSize=1:75, testSize=76:100,
virgin=FALSE)
corpus@training_matrix
corpus@training_codes
corpus@classification_matrix
corpus@testing_codes
corpus@column_names
corpus@virgin
Run the code above in your browser using DataLab