Wordcloud with R

1. Loading file and data

# Read the text file 
filePath <- "../example.txt"
text <- readLines(filePath)

# Load the data as a tibble
library(dplyr)

Attaching package: ‘dplyr’

The following objects are masked from ‘package:stats’:

    filter, lag

The following objects are masked from ‘package:base’:

    intersect, setdiff, setequal, union

text_df <- tibble(line = 1:15, text = text)

2. Tokenizing

library(tidytext)

token_df <- text_df %>%
            unnest_tokens(word, text)

token_df

3. Removing generic stopwords

data(stop_words)

clean_df <- token_df %>%
  anti_join(stop_words, by = c("word" = "word"))

4. Removing stopwords defined by me

mystop <- read.csv("../stop.csv", header = TRUE)

cleaner_df <- clean_df %>%
  anti_join(mystop, by = c("word" = "text"))

cleaner_df

5. Getting word count

frequency <- cleaner_df %>%
              count(word, sort = TRUE) 

6. Plotting

Version A

library(wordcloud)

frequency %>%
 with(wordcloud(word, n, min.freq = 4, max.words = 100, random.order=FALSE, rot.per=0.35, colors=brewer.pal(8, "Dark2")))

Version B

library(wordcloud2)

Registered S3 method overwritten by 'htmlwidgets':
  method           from         
  print.htmlwidget tools:rstudio

  wordcloud2(data=frequency, size=1.6, color='random-dark')