Add google activity recognition deltas

Snakefile

@@ -9,6 +9,7 @@ rule all:
         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}/screen_deltas.csv", pid=config["PIDS"]),
+        expand("data/processed/{pid}/google_activity_recognition_deltas.csv", pid=config["PIDS"]),
         expand("data/interim/{pid}/phone_valid_sensed_days.csv", pid=config["PIDS"]),
         expand("data/processed/{pid}/sms_{sms_type}_{day_segment}.csv",
                             pid=config["PIDS"],

rules/features.snakefile

@@ -38,6 +38,14 @@ rule screen_deltas:
     script:
         "../src/features/screen_deltas.R"
 
+rule google_activity_recognition_deltas:
+    input:
+        "data/raw/{pid}/plugin_google_activity_recognition_with_datetime.csv"
+    output:
+        "data/processed/{pid}/google_activity_recognition_deltas.csv"
+    script:
+        "../src/features/google_activity_recognition_deltas.R"
+
 rule location_barnett_metrics:
     input:
         "data/raw/{pid}/locations_with_datetime.csv"
@@ -62,7 +70,8 @@ rule bluetooth_metrics:
         
 rule activity_metrics:
     input:
-        "data/raw/{pid}/plugin_google_activity_recognition_with_datetime.csv"
+        "data/raw/{pid}/plugin_google_activity_recognition_with_datetime.csv",
+        "data/raw/{pid}/plugin_google_activity_recognition_deltas.csv"
     params:
         segment = "{day_segment}",
         metrics = config["GOOGLE_ACTIVITY_RECOGNITION"]["METRICS"]

src/features/google_activity_recognition_deltas.R

@@ -0,0 +1,33 @@
+source("packrat/init.R")
+
+library("tidyverse")
+
+gar <- read.csv(snakemake@input[[1]])
+
+if(nrow(gar) > 0){
+  activity_episodes <-
+    gar %>%
+    mutate(activity_episode = cumsum(c(1, head(activity_type, -1) != tail(activity_type, -1)))) %>% 
+    group_by(activity_episode) %>%
+    filter(n() > 1) %>%
+    summarize(episode = first(activity_name),
+              time_diff = (last(timestamp) - first(timestamp)) / (1000 * 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),
+              local_start_day_segment = first(local_day_segment),
+              local_end_day_segment = last(local_day_segment)) %>%
+    select(-activity_episode)
+} else {
+  activity_episodes <- data.frame(episode = character(), 
+                            time_diff = numeric(),
+                            local_start_date_time = character(),
+                            local_end_date_time = character(),
+                            local_start_date = character(),
+                            local_end_date = character(),
+                            local_start_day_segment = character(),
+                            local_end_day_segment = character())
+}
+
+write.csv(activity_episodes, snakemake@output[[1]], row.names = FALSE)