Implement AR features for iOS

Co-authored-by: JulioV <juliovhz@gmail.com>

Snakefile

@@ -42,8 +42,8 @@ rule all:
         expand("data/processed/{pid}/bluetooth_{segment}.csv",
                             pid=config["PIDS"], 
                             segment = config["BLUETOOTH"]["DAY_SEGMENTS"]),
-        expand("data/processed/{pid}/google_activity_recognition_{segment}.csv",pid=config["PIDS"], 
+        expand("data/processed/{pid}/activity_recognition_{segment}.csv",pid=config["PIDS"], 
-                            segment = config["GOOGLE_ACTIVITY_RECOGNITION"]["DAY_SEGMENTS"]),
+                            segment = config["ACTIVITY_RECOGNITION"]["DAY_SEGMENTS"]),
         expand("data/processed/{pid}/battery_{day_segment}.csv",
                             pid = config["PIDS"],
                             day_segment = config["BATTERY"]["DAY_SEGMENTS"]),

config.yaml

@@ -1,5 +1,5 @@
 # Valid database table names
-SENSORS: [applications_crashes, applications_foreground, applications_notifications, battery, bluetooth, calls, locations, messages, plugin_ambient_noise, plugin_device_usage, plugin_google_activity_recognition, screen]
+SENSORS: [applications_crashes, applications_foreground, applications_notifications, battery, bluetooth, calls, locations, messages, plugin_ambient_noise, plugin_device_usage, plugin_google_activity_recognition, plugin_ios_activity_recognition, screen]
 
 FITBIT_TABLE: [fitbit_data]
 FITBIT_SENSORS: [heartrate, steps, sleep, calories]
@@ -78,7 +78,7 @@ BLUETOOTH:
   DAY_SEGMENTS: *day_segments
   FEATURES: ["countscans", "uniquedevices", "countscansmostuniquedevice"]
 
-GOOGLE_ACTIVITY_RECOGNITION:
+ACTIVITY_RECOGNITION:
   DAY_SEGMENTS: *day_segments
   FEATURES: ['count','mostcommonactivity','countuniqueactivities','activitychangecount','sumstationary','summobile','sumvehicle']
 
@@ -132,7 +132,7 @@ PARAMS_FOR_ANALYSIS:
   GROUNDTRUTH_TABLE: participant_info
   SOURCES: &sources ["phone_features", "fitbit_features", "phone_fitbit_features"]
   DAY_SEGMENTS: *day_segments
-  PHONE_FEATURES: [accelerometer, applications_foreground, battery, call_incoming, call_missed, call_outgoing, google_activity_recognition, light, location_barnett, screen, sms_received, sms_sent]
+  PHONE_FEATURES: [accelerometer, applications_foreground, battery, call_incoming, call_missed, call_outgoing, activity_recognition, light, location_barnett, screen, sms_received, sms_sent]
   FITBIT_FEATURES: [fitbit_heartrate, fitbit_step]
   PHONE_FITBIT_FEATURES: "" # This array is merged in the input_merge_features_of_single_participant function in models.snakefile
   DEMOGRAPHIC_FEATURES: [age, gender, inpatientdays]

rules/features.snakefile

@@ -1,3 +1,14 @@
+def optional_ar_input(wildcards):
+    with open("data/external/"+wildcards.pid, encoding="ISO-8859-1") as external_file:
+        external_file_content = external_file.readlines()
+    platform = external_file_content[1].strip()
+    if platform == "android":
+        return ["data/raw/{pid}/plugin_google_activity_recognition_with_datetime_unified.csv",
+                "data/processed/{pid}/plugin_google_activity_recognition_deltas.csv"]
+    else:
+        return ["data/raw/{pid}/plugin_ios_activity_recognition_with_datetime_unified.csv",
+                "data/processed/{pid}/plugin_ios_activity_recognition_deltas.csv"]
+
 rule sms_features:
     input: 
         "data/raw/{pid}/messages_with_datetime.csv"
@@ -41,11 +52,19 @@ rule screen_deltas:
 
 rule google_activity_recognition_deltas:
     input:
-        "data/raw/{pid}/plugin_google_activity_recognition_with_datetime.csv"
+        "data/raw/{pid}/plugin_google_activity_recognition_with_datetime_unified.csv"
     output:
         "data/processed/{pid}/plugin_google_activity_recognition_deltas.csv"
     script:
-        "../src/features/google_activity_recognition_deltas.R"
+        "../src/features/activity_recognition_deltas.R"
+
+rule ios_activity_recognition_deltas:
+    input:
+        "data/raw/{pid}/plugin_ios_activity_recognition_with_datetime_unified.csv"
+    output:
+        "data/processed/{pid}/plugin_ios_activity_recognition_deltas.csv"
+    script:
+        "../src/features/activity_recognition_deltas.R"
 
 rule location_barnett_features:
     input:
@@ -75,15 +94,14 @@ rule bluetooth_features:
 
 rule activity_features:
     input:
-        gar_events = "data/raw/{pid}/plugin_google_activity_recognition_with_datetime.csv",
+        optional_ar_input
-        gar_deltas = "data/processed/{pid}/plugin_google_activity_recognition_deltas.csv"
     params:
         segment = "{day_segment}",
-        features = config["GOOGLE_ACTIVITY_RECOGNITION"]["FEATURES"]
+        features = config["ACTIVITY_RECOGNITION"]["FEATURES"]
     output:
-        "data/processed/{pid}/google_activity_recognition_{day_segment}.csv"
+        "data/processed/{pid}/activity_recognition_{day_segment}.csv"
     script:
-        "../src/features/google_activity_recognition.py"
+        "../src/features/activity_recognition.py"
 
 rule battery_features:
     input:

src/data/unify_ios_android.R

@@ -1,6 +1,7 @@
 source("packrat/init.R")
 
 library(dplyr)
+library(stringr)
 
 unify_ios_battery <- function(ios_battery){
     # We only need to unify battery data for iOS client V1. V2 does it out-of-the-box
@@ -64,6 +65,50 @@ unify_ios_calls <- function(ios_calls){
     return(ios_calls)
 }
 
+clean_ios_activity_column <- function(ios_gar){
+    ios_gar <- ios_gar %>%
+        mutate(activities = str_replace_all(activities, pattern = '("|\\[|\\])', replacement = ""))
+
+    existent_multiple_activities <- ios_gar %>%
+        filter(str_detect(activities, ",")) %>% 
+        group_by(activities) %>%
+        summarise(mutiple_activities = unique(activities)) %>% 
+        pull(mutiple_activities)
+
+    known_multiple_activities <- c("stationary,automotive")
+    unkown_multiple_actvities <- setdiff(existent_multiple_activities, known_multiple_activities)
+    if(length(unkown_multiple_actvities) > 0){
+        stop(paste0("There are unkwown combinations of ios activities, you need to implement the decision of the ones to keep: ", unkown_multiple_actvities))
+    }
+
+    ios_gar <- ios_gar %>%
+        mutate(activities = str_replace_all(activities, pattern = "stationary,automotive", replacement = "automotive"))
+    
+    return(ios_gar)
+}
+
+unify_ios_gar <- function(ios_gar){
+    # We only need to unify Google Activity Recognition data for iOS
+    # discard rows where activities column is blank
+    ios_gar <- ios_gar[-which(ios_gar$activities == ""), ]
+    # clean "activities" column of ios_gar
+    ios_gar <- clean_ios_activity_column(ios_gar)
+
+    # make it compatible with android version: generate "activity_name" and "activity_type" columns
+    ios_gar  <-  ios_gar %>% 
+        mutate(activity_name = case_when(activities == "automotive" ~ "in_vehicle",
+                                         activities == "cycling" ~ "on_bicycle",
+                                         activities == "walking" | activities == "running" ~ "on_foot",
+                                         activities == "stationary" ~ "still"),
+               activity_type = case_when(activities == "automotive" ~ 0,
+                                         activities == "cycling" ~ 1,
+                                         activities == "walking" | activities == "running" ~ 2,
+                                         activities == "stationary" ~ 3,
+                                         activities == "unknown" ~ 4))
+    
+    return(ios_gar)
+}
+
 
 sensor_data <- read.csv(snakemake@input[["sensor_data"]], stringsAsFactors = FALSE)
 participant_info <- snakemake@input[["participant_info"]]
@@ -80,5 +125,7 @@ if(sensor == "calls"){
         sensor_data = unify_ios_battery(sensor_data)
     }
     # android battery remains unchanged
+} else if(sensor == "plugin_ios_activity_recognition"){
+    sensor_data = unify_ios_gar(sensor_data)
 }
 write.csv(sensor_data, snakemake@output[[1]], row.names = FALSE)

src/features/activity_recognition.py

@@ -7,8 +7,8 @@ day_segment = snakemake.params["segment"]
 features = snakemake.params["features"]
 
 #Read csv into a pandas dataframe
-data = pd.read_csv(snakemake.input['gar_events'],parse_dates=['local_date_time'])
+data = pd.read_csv(snakemake.input[0],parse_dates=["local_date_time"])
-ar_deltas = pd.read_csv(snakemake.input['gar_deltas'],parse_dates=["local_start_date_time", "local_end_date_time", "local_start_date", "local_end_date"])
+ar_deltas = pd.read_csv(snakemake.input[1],parse_dates=["local_start_date_time", "local_end_date_time", "local_start_date", "local_end_date"])
 columns = list("ar_" + str(day_segment) + "_" + column for column in features)
 
 if data.empty: