From d6eea0fc00c2cd77b8c131f64bc05ddd35aafcd7 Mon Sep 17 00:00:00 2001
From: junos <junos.lukan@ijs.si>
Date: Wed, 19 Apr 2023 10:54:46 +0200
Subject: [PATCH] Completely classify unknown applications.

---
 presentation/ApplicationCategories.R | 33 +++++++++++++++++++++++++++-
 1 file changed, 32 insertions(+), 1 deletion(-)

diff --git a/presentation/ApplicationCategories.R b/presentation/ApplicationCategories.R
index 3e47b23..ca44067 100644
--- a/presentation/ApplicationCategories.R
+++ b/presentation/ApplicationCategories.R
@@ -71,6 +71,37 @@ rows_os_manufacturer <- grepl(grep_pattern, df_app_categories$package_name)
 df_app_categories[!rows_os_manufacturer, ] %>%
   filter(play_store_genre == "not_found")
 
+# Manually classify apps
+df_app_categories %<>% 
+  mutate(
+    play_store_genre = 
+      case_when(
+        str_detect(str_to_lower(package_name), grep_pattern) ~ "System",
+        str_detect(str_to_lower(package_name), "straw") ~ "STRAW",
+        str_detect(str_to_lower(package_name), "chromium") ~ "Communication", # Same as chrome.
+        str_detect(str_to_lower(package_name), "skype") ~ "Communication", # Skype Lite not classified.
+        str_detect(str_to_lower(package_name), "imsservice") ~ "Communication", # IP Multimedia Subsystem
+        str_detect(str_to_lower(package_name), paste(c("covid", "empatica"), collapse = "|")) ~ "Medical",
+        str_detect(str_to_lower(package_name), paste(c("libri", "tachiyomi"), collapse = "|")) ~ "Books & Reference",
+        str_detect(str_to_lower(package_name), paste(c("bricks", "chess"), collapse = "|")) ~ "Casual",
+        str_detect(str_to_lower(package_name), "weather") ~ "Weather",
+        str_detect(str_to_lower(package_name), "excel") ~ "Productivity",
+        str_detect(str_to_lower(package_name), paste(c("qr", "barcode", "archimedes", "mixplorer", "winrar", "filemanager", "shot", "faceunlock", "signin", "milink"), collapse = "|")) ~ "Tools",
+        str_detect(str_to_lower(package_name), "stupeflix") ~ "Photography",
+        str_detect(str_to_lower(package_name), "anyme") ~ "Entertainment",
+        str_detect(str_to_lower(package_name), "vanced") ~ "Video Players & Editors",
+        str_detect(str_to_lower(package_name), paste(c("music", "radio", "dolby"), collapse = "|")) ~ "Music & Audio",
+        str_detect(str_to_lower(package_name), paste(c("tensorflow", "object_detection"), collapse = "|")) ~ "Education",
+        .default = play_store_genre
+      )
+  )
+
+# Explore what remains after classifying above.
+df_app_categories %>%
+  filter(play_store_genre == "not_found")
+
+# After this, 13 applications remain, which I will classify as "Other".
+
 # Correct some mistakes
 # And classify 'not_found'
 df_app_categories %<>%
@@ -80,7 +111,7 @@ df_app_categories %<>%
         case_when(
           x == "Education,Education" ~ "Education",
           x == "EducationEducation" ~ "Education",
-          x == "not_found" ~ "System",
+          x == "not_found" ~ "Other",
           .default = x
         )
       }