File size: 2,041 Bytes
f888423 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 |
box::use(
quanteda[corpus, docnames, dfm, convert, dfm_tfidf, dfm_subset],
quanteda.textstats[textstat_simil],
utils[head],
spacyr[spacy_parse],
dplyr[mutate, filter, select],
)
create_ref_corpus <- function(data_tab) {
corp <- corpus(data_tab, text_field = "description")
docnames(corp) <- data_tab$title
return(corp)
}
spacy_pipeline <- function(corp) {
res <- corp |> spacy_parse()
res_tokens <- res |>
filter(
! pos %in% c("PUNCT", "PART", "NUM", "SYM")
) |>
mutate(
lemma = tolower(lemma)
) |>
as.tokens(
use_lemma = TRUE
) |>
tokens_remove(stopwords("en"))
corp_dfm <- res_tokens |> dfm()
saveRDS(corp_dfm, "./data/ref_corp_dfm.rds")
corp_tfidf <- corp_dfm |> dfm_tfidf()
saveRDS(corp_tfidf, "./data/ref_corp_tfidf.rds")
}
#' export
get_recommendations <- function(corp_dfm, query_book_titles, simil_method = "ejaccard", how_many) {
query_dfm <- dfm_subset(corp_dfm, docname_ %in% query_book_titles)
tstat <- textstat_simil(
query_dfm, corp_dfm,
margin = "documents",
method = simil_method
)
stat_list <- as.list(tstat)
ordered <- sort(unlist(stat_list), decreasing = TRUE)
top_n <- head(ordered, n = how_many)
names(top_n) <- names(top_n) |> gsub(pattern = "\\..*$", replacement = "")
return(names(top_n))
}
#' export
parse_recommendations <- function(rec_book_names, data_tab) {
subset_books <- data_tab |>
filter(
title %in% rec_book_names
) |>
select(
title, average_rating, description, url, image_url, genres, author_name
)
return(subset_books)
}
# hp3 <- dfm_subset(corp_dfm, docname_ %in% "A Game of Thrones (A Song of Ice and Fire, #1)")
# tstat <- textstat_simil(hp3, corp_dfm,
# margin = "documents", method = "ejaccard")
# stat_list <- as.list(tstat)
# ordered <- sort(unlist(stat_list), decreasing = TRUE)
# top_ten <- head(ordered, n = 10)
# names(top_ten) <- names(top_ten) |> gsub(pattern = "\\..*$", replacement = "")
# top_ten
|