Add battery deltas

Snakefile

@@ -7,6 +7,7 @@ rule all:
     input:
         expand("data/raw/{pid}/{sensor}_raw.csv", pid=config["PIDS"], sensor=config["SENSORS"]),
         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/processed/{pid}/com_sms_{sms_type}_{day_segment}_{metric}.csv",
                             pid=config["PIDS"],
                             sms_type = config["COM_SMS"]["SMS_TYPES"],

config.yaml

@@ -1,5 +1,5 @@
 # Valid database table names
-SENSORS: [messages, calls]
+SENSORS: [messages, calls, battery]
 
 # Participants to include in the analysis
 # You must create a file for each participant

rules/features.snakefile

@@ -20,4 +20,12 @@ rule communication_call_metrics:
     output:
         "data/processed/{pid}/com_call_{call_type}_{day_segment}_{metric}.csv"
     script:
-        "../src/features/communication_call_metrics.R"
+        "../src/features/communication_call_metrics.R"
+
+rule battery_deltas:
+    input:
+        "data/raw/{pid}/battery_with_datetime.csv"
+    output:
+        "data/processed/{pid}/battery_deltas.csv"
+    script:
+        "../src/features/battery_deltas.R"

src/features/battery_deltas.R

@@ -0,0 +1,21 @@
+source("packrat/init.R")
+
+library("tidyverse")
+
+battery <- read.csv(snakemake@input[[1]])
+
+consumption <- battery %>%
+    mutate(group = ifelse(lag(battery_status) != battery_status, 1, 0) %>% coalesce(0),
+            group_id = cumsum(group) + 1) %>%
+    filter(battery_status == 3) %>%
+    group_by(group_id) %>%
+    summarize(battery_diff = first(battery_level) - last(battery_level),
+            time_diff = (last(timestamp) - first(timestamp)) / (1000 * 60 * 60),
+            local_start_date_time = first(local_date_time),
+            local_end_date_time = last(local_date_time),
+            local_start_date = first(local_date),
+            local_end_date = last(local_date)) %>%
+    select(-group_id) %>%
+    filter(time_diff > 0.1) # Avoids including quick discharge cycles
+
+write.csv(consumption, snakemake@output[[1]])