Add category (genre) to foreground apps

.gitignore

@@ -96,6 +96,7 @@ packrat/*
 # exclude data from source control by default
 data/external/*
 !/data/external/.gitkeep
+!/data/external/stachl_application_genre_catalogue.csv
 data/raw/*
 !/data/raw/.gitkeep
 data/interim/*

Snakefile

@@ -10,6 +10,7 @@ rule all:
         expand("data/raw/{pid}/{sensor}_raw.csv", pid=config["PIDS"], sensor=config["FITBIT_TABLE"]),
         expand("data/raw/{pid}/{sensor}_with_datetime.csv", pid=config["PIDS"], sensor=config["SENSORS"]),
         expand("data/processed/{pid}/battery_deltas.csv", pid=config["PIDS"]),
+        expand("data/interim/{pid}/applications_foreground_with_datetime_with_genre.csv", pid=config["PIDS"]),
         expand("data/processed/{pid}/screen_deltas.csv", pid=config["PIDS"]),
         expand("data/processed/{pid}/plugin_google_activity_recognition_deltas.csv", pid=config["PIDS"]),
         expand("data/interim/{pid}/phone_valid_sensed_days.csv", pid=config["PIDS"]),

config.yaml

@@ -44,6 +44,12 @@ CALLS:
     outgoing: [count, distinctcontacts, meanduration, sumduration, minduration, maxduration, stdduration, modeduration, hubermduration, varqnduration, entropyduration, timefirstcall, timelastcall, countmostfrequentcontact]
   DAY_SEGMENTS: *day_segments
 
+APPLICATION_GENRES:
+  CATALOGUE_SOURCE: FILE # FILE (genres are read from CATALOGUE_FILE) or GOOGLE (genres are scrapped from the Play Store)
+  CATALOGUE_FILE: "data/external/stachl_application_genre_catalogue.csv"
+  UPDATE_CATALOGUE_FILE: false # if CATALOGUE_SOURCE is equal to FILE, whether or not to update CATALOGUE_FILE, if CATALOGUE_SOURCE is equal to GOOGLE all scraped genres will be saved to CATALOGUE_FILE
+  SCRAPE_MISSING_GENRES: false # whether or not to scrape missing genres, only effective if CATALOGUE_SOURCE is equal to FILE. If CATALOGUE_SOURCE is equal to GOOGLE, all genres are scraped anyway
+
 PHONE_VALID_SENSED_DAYS:
   BIN_SIZE: 5 # (in minutes)
   MIN_VALID_HOURS: 20 # (out of 24)

rules/preprocessing.snakefile

@@ -69,6 +69,19 @@ rule resample_fused_location:
     script:
         "../src/data/resample_fused_location.R"
 
+rule application_genres:
+    input:
+        "data/raw/{pid}/applications_foreground_with_datetime.csv"
+    params:
+        catalogue_source = config["APPLICATION_GENRES"]["CATALOGUE_SOURCE"],
+        catalogue_file = config["APPLICATION_GENRES"]["CATALOGUE_FILE"],
+        update_catalogue_file = config["APPLICATION_GENRES"]["UPDATE_CATALOGUE_FILE"],
+        scrape_missing_genres = config["APPLICATION_GENRES"]["SCRAPE_MISSING_GENRES"]
+    output:
+        "data/interim/{pid}/applications_foreground_with_datetime_with_genre.csv"
+    script:
+        "../src/data/application_genres.R"
+
 rule fitbit_heartrate_with_datetime:
     input:
         "data/raw/{pid}/fitbit_data_raw.csv"
@@ -97,4 +110,5 @@ rule fitbit_sleep_with_datetime:
     output:
         "data/raw/{pid}/fitbit_sleep_with_datetime.csv"
     script:
-        "../src/data/fitbit_sleep_with_datetime.py"
+        "../src/data/fitbit_sleep_with_datetime.py"
+

src/data/application_genres.R

@@ -0,0 +1,57 @@
+source("packrat/init.R")
+
+library(tidyr)
+library(dplyr)
+library(stringr)
+library("rvest")
+
+get_genre <- function(apps){
+  urls = paste0("https://play.google.com/store/apps/details?id=", apps)
+  destfiles = paste0(apps,".html")
+  genres = vector("character", length(apps))
+
+  for(i in seq_along(urls)){
+    try_download <- try(download.file(urls[i], destfiles[i], quiet=TRUE), silent = T)
+    page_title <- read_html(destfiles[i]) %>% html_nodes("title") %>% html_text()
+
+    if(is(try_download,"try-error") || page_title == "Not Found"){
+      genres[i] <- "unknown"
+    }
+    else{
+      genres[i] <- read_html(destfiles[i]) %>% 
+        html_nodes(xpath = '//*[@itemprop="genre"]') %>%
+        html_text()
+      genres[i]  <- tolower(str_remove_all(genres[i], "[\\s&]+")) # removes white spaces or ampersands
+    }
+    file.remove(destfiles[i])
+  }
+  return(data.frame(package_name = apps, genre = genres, stringsAsFactors = F))
+}
+
+apps <- read.csv(snakemake@input[[1]], stringsAsFactors = F)
+genre_catalogue <- data.frame()
+catalogue_source <- snakemake@params[["catalogue_source"]]
+update_catalogue_file <- snakemake@params[["update_catalogue_file"]]
+scrape_missing_genres <- snakemake@params[["scrape_missing_genres"]]
+
+if(catalogue_source == "GOOGLE"){
+  apps_with_genre <- apps %>% mutate(genre = NA_character_)
+} else if(catalogue_source == "FILE"){
+  genre_catalogue <- read.csv(snakemake@params[["catalogue_file"]], colClasses = c("character", "character"))
+  apps_with_genre <- left_join(apps, genre_catalogue, by = "package_name")
+}
+
+if(catalogue_source == "GOOGLE" || (catalogue_source == "FILE" && scrape_missing_genres)){
+  apps_without_genre <- (apps_with_genre %>% filter(is.na(genre)) %>% distinct(package_name))$package_name
+  updated_apps <- get_genre(apps_without_genre)
+  apps_with_genre <- left_join(apps_with_genre, updated_apps, by = "package_name") %>%
+    mutate(genre = coalesce(genre.x, genre.y)) %>%
+    select(-genre.x, -genre.y)
+
+  if(update_catalogue_file){
+    genre_catalogue <- bind_rows(genre_catalogue, updated_apps) %>% distinct()
+    write.csv(genre_catalogue, file = snakemake@params[["catalogue_file"]], row.names = FALSE)
+  }
+}
+
+write.csv(apps_with_genre, snakemake@output[[1]], row.names = FALSE)