Created
March 2, 2018 23:45
-
-
Save benmarwick/d47393820adceb3e9bf50eb09e36bd16 to your computer and use it in GitHub Desktop.
Use a character vector to count occurrences per row, in a data frame with rows of text, like a dictionary lookup, but with a very specific custom dictionary
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
library(usdanutrients) | |
library(tidyverse) | |
foods_simple <- | |
food %>% | |
separate(food, into = str_glue('V{1:11}'), sep = ",") %>% | |
distinct(V1) %>% | |
mutate(V1 = tolower(V1)) %>% | |
mutate(V1 = str_replace_all(V1, "[[:punct:]]", "")) %>% | |
rename(food = V1) | |
words_about_foods <- | |
data_frame(item = 1:2, | |
words = c("You should eat chocolate, candies and, cake infrequently", | |
"You should each spinach, potatoes, and broccoli often") | |
) | |
xx <- | |
words_about_foods %>% | |
nest(-item) %>% | |
mutate(word = map(data, ~unlist(str_split(.x$words, " ")))) %>% | |
unnest(word) %>% | |
mutate(word = tolower(str_replace_all(word, "[[:punct:]]", ""))) %>% | |
inner_join(foods_simple, by = c("word" = "food")) %>% | |
group_by(item, word) %>% | |
tally() %>% | |
spread(item, n) | |
# A tibble: 6 x 3 | |
word `1` `2` | |
<chr> <int> <int> | |
1 broccoli NA 1 | |
2 cake 1 NA | |
3 candies 1 NA | |
4 chocolate 1 NA | |
5 potatoes NA 1 | |
6 spinach NA 1 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment