Last active
December 13, 2017 19:21
-
-
Save Athospd/a92ae0f80482fb44e97ffd269289ad5c to your computer and use it in GitHub Desktop.
This file contains 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
| library(readr) | |
| library(stringr) | |
| library(tidyr) | |
| library(dplyr) | |
| library(purrr) | |
| library(tokenizers) | |
| library(forcats) | |
| reviews <- read_lines("finefoods.txt.gz") | |
| reviews <- reviews[str_sub(reviews, 1, 12) == "review/text:"] | |
| reviews <- str_sub(reviews, start = 14) | |
| reviews <- tokenize_words(reviews) | |
| reviews <- tibble(review_id = 1:length(reviews), review = reviews) | |
| vocab <- reviews$review %>% | |
| unlist() %>% | |
| table() %>% | |
| sort(decreasing = TRUE) %>% | |
| names() %>% | |
| head(49999) | |
| vocab <- tibble(vocab = vocab, vocab_id = 1:length(vocab)) | |
| reviews_final <- reviews %>% | |
| unnest %>% | |
| left_join(vocab, by = c("review" = "vocab")) %>% | |
| select(review_id, vocab_id) %>% | |
| nest(vocab_id) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment