Clean up categories.

presentation/ApplicationCategories.R

@@ -2,32 +2,50 @@ library(conflicted)
 library(yaml)
 library(RPostgreSQL)
 library(tidyverse)
-conflicts_prefer(dplyr::filter, 
-                 dplyr::lag)
+conflicts_prefer(
+  dplyr::filter,
+  dplyr::lag
+)
 library(magrittr)
 
 # read the password from file
 credentials <- yaml.load_file("../rapids/credentials.yaml")
 pw <- credentials$PSQL_STRAW$password
 
-#load the PostgreSQL driver
+# load the PostgreSQL driver
 drv <- RPostgres::Postgres()
 
 # creates a connection to the postgres database
 # note that "con" will be used later in each connection to the database
-con <- RPostgres::dbConnect(drv, dbname = "staw",
-                            host = "eol.ijs.si", port = 5432,
-                            user = "staw_db", password = pw)
+con <- RPostgres::dbConnect(drv,
+  dbname = "staw",
+  host = "eol.ijs.si", port = 5432,
+  user = "staw_db", password = pw
+)
 
 rm(pw, credentials) # removes the password
 
 # check for the bluetooth table, an example
 dbExistsTable(con, "app_categories")
 
-df_app_categories <- tbl(con, "app_categories") %>% 
+df_app_categories <- tbl(con, "app_categories") %>%
   collect()
 
 head(df_app_categories)
 table(df_app_categories$play_store_genre)
 
+# Correct some mistakes
+df_app_categories %<>% mutate(
+  play_store_genre = {
+    function(x) {
+      case_when(
+        x == "Education,Education" ~ "Education",
+        x == "EducationEducation" ~ "Education",
+        x == "not_found" ~ "System",
+        .default = x
+      )
+    }
+  }(play_store_genre)
+)
+
 dbDisconnect(con)