I have a data frame with only one column "text"
"text"
"User Interfaces"
"Twitter"
"Text Normalization"
"Term weighting"
"Teenagers"
"Team member replacement"
I would like to take a dataframe with the frequency of every phrase, like this:
"User Interfaces",1
"Twitter",1
"Text Normalization",1
"Term weighting",1
"Teenagers",1
"Team member replacement",1
in order to make it I use this:
library(tm)
df <- read.csv("C:/Users/acel/Desktop/myphr.csv", header=TRUE, sep=",")
corpusD <- Corpus(VectorSource(df$text))
corpusD <- tm_map(corpusD, tolower)
corpusD <- tm_map(corpusD, removeWords, stopwords('english'))
corpusD <- tm_map(corpusD, removeNumbers)
corpusD <- tm_map(corpusD, stripWhitespace)
corpusD <- tm_map(corpusD, PlainTextDocument)
corpusD <- tm_map(corpusD, stemDocument, language = "english")
corpusC <- Corpus(VectorSource(corpusD))
matrixD <- TermDocumentMatrix(corpusC)
matrixD <- removeSparseTerms(matrixD, 0.75)
MatrixDfreq <- rowSums(as.matrix(matrixD))
MatrixDfreq<-sort(MatrixDfreq, decreasing = TRUE)
MatrixDtop30<- MatrixDfreq [1:30]
but when I check the result from MatrixDtop30 I see one word counted like user,1 and interface,1 instead of seeing "user interface",1
Any idea why this is happening?
I think this would be a lot easier using data.table operations.
library(data.table)
df = data.frame(text = c("test", "test" ,"test" , "test2", "test3", "test2"))
> df
text
1 test
2 test
3 test
4 test2
5 test3
6 test2
setDT(df)
df = df[ , .(Number = .N), by = .(text)]
> df
text Number
1: test 3
2: test2 2
3: test3 1
Edit
We can include stemming with this
library(data.table)
library(SnowballC)
df = data.frame(text = c("test", "testing" ,"test" , "test2", "test3", "test2"))
> df
text
1 test
2 testing
3 test
4 test2
5 test3
6 test2
df$text = wordStem(df$text, language = "porter")
> df
text
1 test
2 test
3 test
4 test2
5 test3
6 test2
setDT(df)
df = df[ , .(Number = .N), by = .(text)]
> df
text Number
1: test 3
2: test2 2
3: test3 1