From 81db90928d3b7dd712e47f0b0b138b873d3e768a Mon Sep 17 00:00:00 2001
From: Kohei Watanabe <watanabe.kohei@gmail.com>
Date: Fri, 12 Apr 2024 22:19:00 +0900
Subject: [PATCH] Update for qunteda v4.0 (#85)

dfm.character() is deprecated in v4.0
---
 vignettes/overview.Rmd | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/vignettes/overview.Rmd b/vignettes/overview.Rmd
index 34836b5..10a2fe6 100644
--- a/vignettes/overview.Rmd
+++ b/vignettes/overview.Rmd
@@ -162,7 +162,7 @@ The test makes more sense if more than one coder is involved. A suggested workfl
 Preprocess and create a document-feature matrix
 
 ```{r, eval = FALSE}
-dfm(abstracts$text, tolower = TRUE, stem = TRUE, remove = stopwords('english'), remove_punct = TRUE, remove_numbers = TRUE, remove_symbols = TRUE, remove_hyphens = TRUE) %>% dfm_trim(min_docfreq = 3, max_docfreq = 500) %>% dfm_select(min_nchar = 3, pattern = "^[a-zA-Z]+$", valuetype = "regex") -> abstracts_dfm
+tokens(abstracts$text, remove_punct = TRUE, remove_symbols = TRUE, remove_numbers = TRUE, remove_url = TRUE, spilit_hyphens = TRUE) %>% tokens_wordstem %>% tokens_remove(stopwords("en")) %>% dfm(tolower = TRUE) %>% dfm_trim(min_docfreq = 3, max_docfreq = 500) %>% dfm_select(min_nchar = 3, pattern = "^[a-zA-Z]+$", valuetype = "regex") -> abstracts_dfm
 ```
 
 Train a topic model.