I'm trying to create TermDocumentMatrix and I'm facing the following error:
Error in UseMethod("meta", x) : no applicable method for 'meta' applied to an object of class "character" In addition: Warning message: In mclapply(unname(content(x)), termFreq, control) : all scheduled cores encountered errors in user code
#Read in data
policy.HTML.page <- readLines("http://policy.unt.edu/policy/3-5")
#Obtain text and remove mark-up
policy.HTML.page[186:202]
id.1 <- 3 + which(policy.HTML.page == " TOTAL UNIVERSITY </div>")
id.2 <- id.1 + 5
text.data <- policy.HTML.page[id.1:id.2]
td.1 <- gsub(pattern = "<p>", replacement = "", x = text.data,
ignore.case = TRUE, perl = FALSE, fixed = FALSE, useBytes = FALSE)
td.2 <- gsub(pattern = "</p>", replacement = "", x = td.1, ignore.case = TRUE,
perl = FALSE, fixed = FALSE, useBytes = FALSE)
text.d <- td.2; rm(text.data, td.1, td.2)
#Create corpus and clean
library(tm)
library(SnowballC)
txt <- VectorSource(text.d); rm(text.d)
txt.corpus <- Corpus(txt)
txt.corpus <- tm_map(txt.corpus, tolower)
txt.corpus <- tm_map(txt.corpus, removeNumbers)
txt.corpus <- tm_map(txt.corpus, removePunctuation)
txt.corpus <- tm_map(txt.corpus, removeWords, stopwords("english"))
txt.corpus <- tm_map(txt.corpus, stripWhitespace); #inspect(docs[1])
txt.corpus <- tm_map(txt.corpus, stemDocument)
# NOTE ERROR WHEN CREATING TDM
tdm <- TermDocumentMatrix(txt.corpus)