Last active
August 29, 2015 14:03
-
-
Save not-for-me/f0e269015e5681ec56ab to your computer and use it in GitHub Desktop.
topicmodel_with_r
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Library Load | |
library(tm) | |
# Set file Paths | |
otFilePath <- "~/Documents/mining/project/old" | |
ntFilePath <- "~/Documents/mining/project/new" | |
# Import txt to TextCorpus | |
oldTextCorpus <- Corpus(DirSource(otFilePath), readerControl = list(reader = readPlain, language = "en")) | |
newTextCorpus <- Corpus(DirSource(ntFilePath), readerControl = list(reader = readPlain, language = "en")) | |
summary(oldTextCorpus) | |
summary(newTextCorpus) | |
# Text Preprocessing | |
oldTextCorpus <- tm_map(oldTextCorpus, content_transformer(tolower)) | |
oldTextCorpus <- tm_map(oldTextCorpus, removeWords, stopwords("english")) | |
myStopWords <- c("also", "among", "like", "may", "must", "shall", "take", "went", "will") | |
oldTextCorpus <- tm_map(oldTextCorpus, removeWords, myStopWords ) | |
oldTextCorpus <- tm_map(oldTextCorpus, removeNumbers) | |
oldTextCorpus <- tm_map(oldTextCorpus, removePunctuation) | |
oldTextCorpus <- tm_map(oldTextCorpus, stripWhitespace) | |
library(SnowballC) | |
oldTextCorpus <- tm_map(oldTextCorpus, stemDocument) | |
newTextCorpus <- tm_map(newTextCorpus, content_transformer(tolower)) | |
newTextCorpus <- tm_map(newTextCorpus, removeWords, stopwords("english")) | |
myStopWords <- c("also", "among", "like", "may", "must", "shall", "take", "went", "will") | |
newTextCorpus <- tm_map(newTextCorpus, removeWords, myStopWords ) | |
newTextCorpus <- tm_map(newTextCorpus, removeNumbers) | |
newTextCorpus <- tm_map(newTextCorpus, removePunctuation) | |
newTextCorpus <- tm_map(newTextCorpus, stripWhitespace) | |
newTextCorpus <- tm_map(newTextCorpus, stemDocument) | |
bibleCorpus <- c(oldTextCorpus, newTextCorpus) | |
old_dtm <-DocumentTermMatrix(oldTextCorpus) | |
dim(old_dtm) | |
new_dtm <-DocumentTermMatrix(newTextCorpus) | |
dim(new_dtm) | |
bible_dtm <-DocumentTermMatrix(bibleCorpus) | |
dim(bible_dtm) | |
set.seed(1102) | |
library(topicmodels) | |
LDA <- LDA(bible_dtm, control = list(alpha = 0.1), k = 3) | |
topics <- get_terms(LDA, 100) | |
topics[1:100, 1] | |
topics[1:100, 2] | |
topics[1:100, 3] |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment