Completely remove PACKAGE_NAMES_HASHED and instead provide a differently structured file.

presentation/ApplicationCategories.R

@@ -48,12 +48,21 @@ df_app_categories %<>%
       }
     }(play_store_genre)
   ) %>%
-  rename(genre = play_store_genre)
+  select(-package_name) %>% 
+  rename(
+    genre = play_store_genre,
+    package_name = package_hash)
 
 table(df_app_categories$genre)
 
+df_app_categories %>% 
+  group_by(genre) %>% 
+  count() %>% 
+  arrange(desc(n)) %>%
+  write_csv("play_store_categories_count.csv")
+
 write_csv(
-  x = select(df_app_categories, c(package_hash, genre)),
+  x = select(df_app_categories, c(package_name, genre)),
   file = "play_store_application_genre_catalogue.csv"
 )
 

presentation/play_store_application_genre_catalogue.csv

@@ -1,4 +1,4 @@
-package_hash,genre
+package_name,genre
 98a5c1a9c7717f791cb4083199ff5c91a958df844a47dc89c7319b2bb824ac94,Personalization
 c9112978f6b1c96c767496a15a6dbb9c8dccabe847c31ecc9e5f706de24342a6,Communication
 650ab12d7007ee573df2291f3a9207442e3897a9a5b2f5068ad685c0d04751ea,Tools