Compare commits

..

No commits in common. "master" and "update_libs" have entirely different histories.

6 changed files with 26 additions and 1095 deletions

3
.gitignore vendored
View File

@ -100,9 +100,6 @@ data/external/*
!/data/external/wiki_tz.csv
!/data/external/main_study_usernames.csv
!/data/external/timezone.csv
!/data/external/play_store_application_genre_catalogue.csv
!/data/external/play_store_categories_count.csv
data/raw/*
!/data/raw/.gitkeep

View File

@ -26,7 +26,7 @@ TIME_SEGMENTS: &time_segments
INCLUDE_PAST_PERIODIC_SEGMENTS: TRUE # Only relevant if TYPE=PERIODIC, see docs
TAILORED_EVENTS: # Only relevant if TYPE=EVENT
COMPUTE: True
SEGMENTING_METHOD: "30_before" # 30_before, 90_before, stress_event
SEGMENTING_METHOD: "stress_event" # 30_before, 90_before, stress_event
INTERVAL_OF_INTEREST: 10 # duration of event of interest [minutes]
IOI_ERROR_TOLERANCE: 5 # interval of interest erorr tolerance (before and after IOI) [minutes]
@ -104,9 +104,9 @@ PHONE_APPLICATIONS_CRASHES:
CONTAINER: applications_crashes
APPLICATION_CATEGORIES:
CATALOGUE_SOURCE: FILE # FILE (genres are read from CATALOGUE_FILE) or GOOGLE (genres are scrapped from the Play Store)
CATALOGUE_FILE: "data/external/play_store_application_genre_catalogue.csv"
UPDATE_CATALOGUE_FILE: False # if CATALOGUE_SOURCE is equal to FILE, whether to update CATALOGUE_FILE, if CATALOGUE_SOURCE is equal to GOOGLE all scraped genres will be saved to CATALOGUE_FILE
SCRAPE_MISSING_CATEGORIES: False # whether 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
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_CATEGORIES: 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
PROVIDERS: # None implemented yet but this sensor can be used in PHONE_DATA_YIELD
# See https://www.rapids.science/latest/features/phone-applications-foreground/
@ -114,32 +114,24 @@ PHONE_APPLICATIONS_FOREGROUND:
CONTAINER: applications
APPLICATION_CATEGORIES:
CATALOGUE_SOURCE: FILE # FILE (genres are read from CATALOGUE_FILE) or GOOGLE (genres are scrapped from the Play Store)
CATALOGUE_FILE: "data/external/play_store_application_genre_catalogue.csv"
# Refer to data/external/play_store_categories_count.csv for a list of categories (genres) and their frequency.
UPDATE_CATALOGUE_FILE: False # if CATALOGUE_SOURCE is equal to FILE, whether to update CATALOGUE_FILE, if CATALOGUE_SOURCE is equal to GOOGLE all scraped genres will be saved to CATALOGUE_FILE
SCRAPE_MISSING_CATEGORIES: False # whether 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
CATALOGUE_FILE: "data/external/stachl_application_genre_catalogue.csv"
PACKAGE_NAMES_HASHED: True
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_CATEGORIES: 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
PROVIDERS:
RAPIDS:
COMPUTE: True
INCLUDE_EPISODE_FEATURES: True
SINGLE_CATEGORIES: ["Productivity", "Tools", "Communication", "Education", "Social"]
SINGLE_CATEGORIES: ["all", "email"]
MULTIPLE_CATEGORIES:
games: ["Puzzle", "Card", "Casual", "Board", "Strategy", "Trivia", "Word", "Adventure", "Role Playing", "Simulation", "Board, Brain Games", "Racing"]
social: ["Communication", "Social", "Dating"]
productivity: ["Tools", "Productivity", "Finance", "Education", "News & Magazines", "Business", "Books & Reference"]
health: ["Health & Fitness", "Lifestyle", "Food & Drink", "Sports", "Medical", "Parenting"]
entertainment: ["Shopping", "Music & Audio", "Entertainment", "Travel & Local", "Photography", "Video Players & Editors", "Personalization", "House & Home", "Art & Design", "Auto & Vehicles", "Entertainment,Music & Video",
"Puzzle", "Card", "Casual", "Board", "Strategy", "Trivia", "Word", "Adventure", "Role Playing", "Simulation", "Board, Brain Games", "Racing" # Add all games.
]
maps_weather: ["Maps & Navigation", "Weather"]
social: ["socialnetworks", "socialmediatools"]
entertainment: ["entertainment", "gamingknowledge", "gamingcasual", "gamingadventure", "gamingstrategy", "gamingtoolscommunity", "gamingroleplaying", "gamingaction", "gaminglogic", "gamingsports", "gamingsimulation"]
CUSTOM_CATEGORIES:
SINGLE_APPS: []
EXCLUDED_CATEGORIES: ["System", "STRAW"]
# Note: A special option here is "is_system_app".
# This excludes applications that have is_system_app = TRUE, which is a separate column in the table.
# However, all of these applications have been assigned System category.
# I will therefore filter by that category, which is a superset and is more complete. JL
EXCLUDED_APPS: []
social_media: ["com.google.android.youtube", "com.snapchat.android", "com.instagram.android", "com.zhiliaoapp.musically", "com.facebook.katana"]
dating: ["com.tinder", "com.relance.happycouple", "com.kiwi.joyride"]
SINGLE_APPS: ["top1global", "com.facebook.moments", "com.google.android.youtube", "com.twitter.android"] # There's no entropy for single apps
EXCLUDED_CATEGORIES: []
EXCLUDED_APPS: ["com.fitbit.FitbitMobile", "com.aware.plugin.upmc.cancer"] # TODO list system apps?
FEATURES:
APP_EVENTS: ["countevent", "timeoffirstuse", "timeoflastuse", "frequencyentropy"]
APP_EPISODES: ["countepisode", "minduration", "maxduration", "meanduration", "sumduration"]
@ -753,6 +745,6 @@ PARAMS_FOR_ANALYSIS:
TARGET:
COMPUTE: True
LABEL: appraisal_stressfulness_event_mean
ALL_LABELS: [PANAS_positive_affect_mean, PANAS_negative_affect_mean, JCQ_job_demand_mean, JCQ_job_control_mean, JCQ_supervisor_support_mean, JCQ_coworker_support_mean, appraisal_stressfulness_period_mean]
ALL_LABELS: [appraisal_stressfulness_event_mean, appraisal_threat_mean, appraisal_challenge_mean]
# PANAS_positive_affect_mean, PANAS_negative_affect_mean, JCQ_job_demand_mean, JCQ_job_control_mean, JCQ_supervisor_support_mean,
# JCQ_coworker_support_mean, appraisal_stressfulness_period_mean, appraisal_stressfulness_event_mean, appraisal_threat_mean, appraisal_challenge_mean

File diff suppressed because it is too large Load Diff

View File

@ -1,45 +0,0 @@
genre,n
System,261
Tools,96
Productivity,71
Health & Fitness,60
Finance,54
Communication,39
Music & Audio,39
Shopping,38
Lifestyle,33
Education,28
News & Magazines,24
Maps & Navigation,23
Entertainment,21
Business,18
Travel & Local,18
Books & Reference,16
Social,16
Weather,16
Food & Drink,14
Sports,14
Other,13
Photography,13
Puzzle,13
Video Players & Editors,12
Card,9
Casual,9
Personalization,8
Medical,7
Board,5
Strategy,4
House & Home,3
Trivia,3
Word,3
Adventure,2
Art & Design,2
Auto & Vehicles,2
Dating,2
Role Playing,2
STRAW,2
Simulation,2
"Board,Brain Games",1
"Entertainment,Music & Video",1
Parenting,1
Racing,1
1 genre n
2 System 261
3 Tools 96
4 Productivity 71
5 Health & Fitness 60
6 Finance 54
7 Communication 39
8 Music & Audio 39
9 Shopping 38
10 Lifestyle 33
11 Education 28
12 News & Magazines 24
13 Maps & Navigation 23
14 Entertainment 21
15 Business 18
16 Travel & Local 18
17 Books & Reference 16
18 Social 16
19 Weather 16
20 Food & Drink 14
21 Sports 14
22 Other 13
23 Photography 13
24 Puzzle 13
25 Video Players & Editors 12
26 Card 9
27 Casual 9
28 Personalization 8
29 Medical 7
30 Board 5
31 Strategy 4
32 House & Home 3
33 Trivia 3
34 Word 3
35 Adventure 2
36 Art & Design 2
37 Auto & Vehicles 2
38 Dating 2
39 Role Playing 2
40 STRAW 2
41 Simulation 2
42 Board,Brain Games 1
43 Entertainment,Music & Video 1
44 Parenting 1
45 Racing 1

View File

@ -248,7 +248,7 @@ rule empatica_readable_datetime:
output:
"data/raw/{pid}/empatica_{sensor}_with_datetime.csv"
resources:
mem_mb=50000
mem_mb=100000
script:
"../src/data/datetime/readable_datetime.R"

View File

@ -29,16 +29,23 @@ get_genre <- function(apps){
apps <- read.csv(snakemake@input[[1]], stringsAsFactors = F)
genre_catalogue <- data.frame()
catalogue_source <- snakemake@params[["catalogue_source"]]
package_names_hashed <- snakemake@params[["package_names_hashed"]]
update_catalogue_file <- snakemake@params[["update_catalogue_file"]]
scrape_missing_genres <- snakemake@params[["scrape_missing_genres"]]
apps_with_genre <- data.frame(matrix(ncol=length(colnames(apps)) + 1,nrow=0, dimnames=list(NULL, c(colnames(apps), "genre"))))
if (length(package_names_hashed) == 0) {package_names_hashed <- FALSE}
if(nrow(apps) > 0){
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 (package_names_hashed) {
apps_with_genre <- left_join(apps, genre_catalogue, by = "package_hash")
} else {
apps_with_genre <- left_join(apps, genre_catalogue, by = "package_name")
}
}
if(catalogue_source == "GOOGLE" || (catalogue_source == "FILE" && scrape_missing_genres)){