Created
August 8, 2018 04:14
-
-
Save RodriguezGoldstein/c9801f7545bc9008d95bd1a353fefa94 to your computer and use it in GitHub Desktop.
This file contains hidden or 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
| unnest_reg <- "([^A-Za-z_\\d#@']|'(?![A-Za-z_\\d#@]))" | |
| replace_reg <- '(.*.)\\.com(.*.)\\S+\\s|[^[:alnum:]]|(http|https)\\S+\\s*|(#|@)\\S+\\s*|\\n|\\"' | |
| #type_visited = "Visited" | |
| #type_searched = "Searched" | |
| #search_data[search_data$type == type_visited, ]$search | |
| search <- search_data$search %>% | |
| str_replace_all(pattern = replace_reg, replacement = " ") %>% | |
| iconv(from = "ASCII", to = "UTF-8", sub = " ") %>% | |
| tolower() %>% | |
| trimws() | |
| search <- tibble(text = search) %>% | |
| unnest_tokens(word, text, token = "regex", pattern = unnest_reg) %>% | |
| filter(!word %in% stop_words$word, str_detect(word, "[a-z]")) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment