Create a wordcloud of your google search history

google_wordcloud.R

# Script to make a word cloud of your google searches.  Get your google search
# history at https://myactivity.google.com/more-activity .  This script assumes the JSON files
# exported are in a 'Searches' subfolder

library(jsonlite)
library(rlist)
library(magrittr)
library(stringi)
library(wordcloud)
library(tm)
library(SnowballC)

queries = lapply(list.files('Searches', full.names=TRUE), fromJSON, simplifyDataFrame=FALSE) %>%
  do.call("c", .) %>%
  do.call("c", .) %>%
  do.call("c", .) %>%
  list.mapv(.$query) %>%
  stri_trans_tolower %>%
  removeWords(stopwords("english")) %>%
#  removeWords(stopwords("german")) %>%
  `[`(., !grepl(pattern = '[-][>]',x = .)) # filter some gmaps stuff


words = stri_split_regex(queries, "\\s") %>%
  do.call("c", .) %>%
  `[`(., . != "")  %>%
  `[`(., !grepl(pattern = '[:]',x = .))# filter out google search paramters
# words %<>%  wordStem

word_table = table(words) %>%
  sort(decreasing = TRUE)


pal <- colorRampPalette(c("red","blue"))(10)
wordcloud(names(word_table), word_table, scale=c(3, 1), min.freq=10,colors=pal,random.order=TRUE, max.words=150)