R: wordcloud - Revision history

Onnowpurbo: /* Text Mining */

2018-11-04T09:26:33Z

Text Mining

← Older revision		Revision as of 09:26, 4 November 2018
Line 49:		Line 49:
	# specify your stopwords as a character vector		# specify your stopwords as a character vector
	docs <- tm_map(docs, removeWords, c("blabla1", "blabla2"))		docs <- tm_map(docs, removeWords, c("blabla1", "blabla2"))
			docs <- tm_map(docs, removeWords, c("tingkat", "bangun", "kembang", "laksana", "sasar"))
	# Remove punctuations		# Remove punctuations
	docs <- tm_map(docs, removePunctuation)		docs <- tm_map(docs, removePunctuation)

Onnowpurbo: /* Text Mining */

2018-11-04T09:22:51Z

Text Mining

← Older revision		Revision as of 09:22, 4 November 2018
Line 44:		Line 44:
	# Remove english common stopwords		# Remove english common stopwords
	docs <- tm_map(docs, removeWords, stopwords("english"))		docs <- tm_map(docs, removeWords, stopwords("english"))
			# Remove Indonesia common stopwords
			docs <- tm_map(docs, removeWords, stopwords::stopwords("id", source = "stopwords-iso"))
	# Remove your own stop word		# Remove your own stop word
	# specify your stopwords as a character vector		# specify your stopwords as a character vector

Onnowpurbo: /* Install Packages */

2018-11-04T09:18:59Z

Install Packages

← Older revision		Revision as of 09:18, 4 November 2018
Line 20:		Line 20:
	library("wordcloud")		library("wordcloud")
	library("RColorBrewer")		library("RColorBrewer")
			library(readtext)

	==Text Mining==		==Text Mining==

Onnowpurbo: /* Text Mining */

2018-11-01T04:55:30Z

Text Mining

← Older revision		Revision as of 04:55, 1 November 2018
Line 25:		Line 25:
	# dari file		# dari file
	text <- readLines(file.choose())		text <- readLines(file.choose())
	text <- ~~read.delim~~("out.txt")		text <- readtext("out.txt")

	# Read the text file from internet		# Read the text file from internet

Onnowpurbo: /* Wordcloud */

2018-11-01T04:40:56Z

Wordcloud

← Older revision		Revision as of 04:40, 1 November 2018
Line 67:		Line 67:
	max.words=200, random.order=FALSE, rot.per=0.35,		max.words=200, random.order=FALSE, rot.per=0.35,
	colors=brewer.pal(8, "Dark2"))		colors=brewer.pal(8, "Dark2"))


			==Pranala Menarik==

			* [[R]]

Onnowpurbo at 04:12, 1 November 2018

2018-11-01T04:12:25Z

← Older revision		Revision as of 04:12, 1 November 2018
Line 52:		Line 52:
	# Text stemming		# Text stemming
	# docs <- tm_map(docs, stemDocument)		# docs <- tm_map(docs, stemDocument)

			==Term Document Matrix==

			dtm <- TermDocumentMatrix(docs)
			m <- as.matrix(dtm)
			v <- sort(rowSums(m),decreasing=TRUE)
			d <- data.frame(word = names(v),freq=v)
			head(d, 10)

			==Wordcloud==

			set.seed(1234)
			wordcloud(words = d$word, freq = d$freq, min.freq = 1,
			max.words=200, random.order=FALSE, rot.per=0.35,
			colors=brewer.pal(8, "Dark2"))

Onnowpurbo: Created page with "The 5 main steps to create word clouds in R # Create a text file # Install and load the required packages # Text mining # Build a term-document matrix # Generate the Word clo..."

2018-11-01T04:08:26Z

Created page with "The 5 main steps to create word clouds in R # Create a text file # Install and load the required packages # Text mining # Build a term-document matrix # Generate the Word clo..."

New page

The 5 main steps to create word clouds in R

# Create a text file
# Install and load the required packages
# Text mining
# Build a term-document matrix
# Generate the Word cloud

==Install Packages==

# Install
install.packages("tm") # for text mining
install.packages("SnowballC") # for text stemming
install.packages("wordcloud") # word-cloud generator
install.packages("RColorBrewer") # color palettes
# Load
library("tm")
library("SnowballC")
library("wordcloud")
library("RColorBrewer")

==Text Mining==

# dari file
text <- readLines(file.choose())
text <- read.delim("out.txt")

# Read the text file from internet
filePath <- "http://www.sthda.com/sthda/RDoc/example-files/martin-luther-king-i-have-a-dream-speech.txt"
text <- readLines(filePath)

# Load the data as a corpus
docs <- Corpus(VectorSource(text))
inspect(docs)

Clean up

# Convert the text to lower case
docs <- tm_map(docs, content_transformer(tolower))
# Remove numbers
docs <- tm_map(docs, removeNumbers)
# Remove english common stopwords
docs <- tm_map(docs, removeWords, stopwords("english"))
# Remove your own stop word
# specify your stopwords as a character vector
docs <- tm_map(docs, removeWords, c("blabla1", "blabla2"))
# Remove punctuations
docs <- tm_map(docs, removePunctuation)
# Eliminate extra white spaces
docs <- tm_map(docs, stripWhitespace)
# Text stemming
# docs <- tm_map(docs, stemDocument)