Difference between revisions of "R: tidytext RPJP BAPPENAS"
Jump to navigation
Jump to search
Onnowpurbo (talk | contribs) (Created page with " install.packages("pdftools") library(pdftools) rpjp2005 <- pdf_text("RPJP_2005-2025.pdf") %>% strsplit(split = "\n") original_rpjp2005 <- rpjp2005 %>% group_by(book...") |
Onnowpurbo (talk | contribs) |
||
| (13 intermediate revisions by the same user not shown) | |||
| Line 1: | Line 1: | ||
| + | install.packages("rJava") | ||
| + | install.packages("xlsx") | ||
| + | install.packages("tm") | ||
| + | install.packages("wordcloud") | ||
| + | install.packages("ggplot2") | ||
| + | install.packages("RWeka") | ||
| + | |||
| + | library(xlsx) | ||
| + | library(tm) | ||
| + | library(wordcloud) | ||
| + | library(ggplot2) | ||
| + | library(tidyverse) | ||
| + | library(tidytext) | ||
| + | library(RWeka) | ||
| + | library(tm) | ||
| + | directory <- "data-pdf" | ||
| + | |||
| + | # create corpus from pdfs | ||
| + | docs <- VCorpus(DirSource(directory), readerControl = list(reader = readPDF)) | ||
| − | + | # docs <- VCorpus(DirSource("data", recursive=TRUE)) | |
| − | + | # Get the document term matrices | |
| − | |||
| + | # dengan Stemming | ||
| + | # | ||
| + | BigramTokenizer <- function(x) NGramTokenizer(x, Weka_control(min = 2, max = 2)) | ||
| + | dtm_unigram <- DocumentTermMatrix(docs, control = list(tokenize="words", | ||
| + | removePunctuation = TRUE, | ||
| + | stopwords = c(stopwords::stopwords("id", source = "stopwords-iso"),"tabel","pada","dan"), | ||
| + | stemming = TRUE)) | ||
| + | dtm_bigram <- DocumentTermMatrix(docs, control = list(tokenize = BigramTokenizer, | ||
| + | removePunctuation = TRUE, | ||
| + | stopwords = c(stopwords::stopwords("id", source = "stopwords-iso"),"tabel","pada","dan"), | ||
| + | stemming = TRUE)) | ||
| − | + | # tanpa Stemming | |
| − | + | # | |
| − | + | BigramTokenizer <- function(x) NGramTokenizer(x, Weka_control(min = 2, max = 2)) | |
| − | + | dtm_unigram <- DocumentTermMatrix(docs, control = list(tokenize="words", | |
| − | + | removePunctuation = TRUE, | |
| − | + | stopwords = c(stopwords::stopwords("id", source = "stopwords-iso"),"tabel","pada","dan"))) | |
| − | + | dtm_bigram <- DocumentTermMatrix(docs, control = list(tokenize = BigramTokenizer, | |
| + | removePunctuation = TRUE, | ||
| + | stopwords = c(stopwords::stopwords("id", source = "stopwords-iso"),"tabel","pada","dan"))) | ||
| + | |||
| + | inspect(dtm_unigram) | ||
| + | inspect(dtm_bigram) | ||
Latest revision as of 12:20, 26 November 2019
install.packages("rJava")
install.packages("xlsx")
install.packages("tm")
install.packages("wordcloud")
install.packages("ggplot2")
install.packages("RWeka")
library(xlsx)
library(tm)
library(wordcloud)
library(ggplot2)
library(tidyverse) library(tidytext) library(RWeka) library(tm) directory <- "data-pdf" # create corpus from pdfs docs <- VCorpus(DirSource(directory), readerControl = list(reader = readPDF))
# docs <- VCorpus(DirSource("data", recursive=TRUE))
# Get the document term matrices
# dengan Stemming
#
BigramTokenizer <- function(x) NGramTokenizer(x, Weka_control(min = 2, max = 2))
dtm_unigram <- DocumentTermMatrix(docs, control = list(tokenize="words",
removePunctuation = TRUE,
stopwords = c(stopwords::stopwords("id", source = "stopwords-iso"),"tabel","pada","dan"),
stemming = TRUE))
dtm_bigram <- DocumentTermMatrix(docs, control = list(tokenize = BigramTokenizer,
removePunctuation = TRUE,
stopwords = c(stopwords::stopwords("id", source = "stopwords-iso"),"tabel","pada","dan"),
stemming = TRUE))
# tanpa Stemming
#
BigramTokenizer <- function(x) NGramTokenizer(x, Weka_control(min = 2, max = 2))
dtm_unigram <- DocumentTermMatrix(docs, control = list(tokenize="words",
removePunctuation = TRUE,
stopwords = c(stopwords::stopwords("id", source = "stopwords-iso"),"tabel","pada","dan")))
dtm_bigram <- DocumentTermMatrix(docs, control = list(tokenize = BigramTokenizer,
removePunctuation = TRUE,
stopwords = c(stopwords::stopwords("id", source = "stopwords-iso"),"tabel","pada","dan")))
inspect(dtm_unigram) inspect(dtm_bigram)