From 911e183c265a6fd7fb2f0e6d41402c828e3e3b2b Mon Sep 17 00:00:00 2001
From: JulioV <JulioV@users.noreply.github.com>
Date: Wed, 6 Nov 2019 12:19:30 -0500
Subject: [PATCH] Add bluetooth features

---
 Snakefile                        |  3 +++
 config.yaml                      |  6 ++++-
 rules/features.snakefile         | 13 +++++++++-
 src/features/bluetooth_metrics.R | 41 ++++++++++++++++++++++++++++++++
 4 files changed, 61 insertions(+), 2 deletions(-)
 create mode 100644 src/features/bluetooth_metrics.R

diff --git a/Snakefile b/Snakefile
index 5976cc0a..26f4f1a2 100644
--- a/Snakefile
+++ b/Snakefile
@@ -25,6 +25,9 @@ rule all:
                             segment = config["COM_CALL"]["DAY_SEGMENTS"],
                             metric = config["COM_CALL"]["METRICS_TAKEN"]),
         expand("data/processed/{pid}/location_barnett_metrics.csv", pid=config["PIDS"]),
+        expand("data/processed/{pid}/bluetooth_{segment}.csv",
+                            pid=config["PIDS"], 
+                            segment = config["BLUETOOTH"]["DAY_SEGMENTS"]),
         # Reports
         expand("reports/figures/{pid}/{sensor}_heatmap_rows.html", pid=config["PIDS"], sensor=config["SENSORS"]),
         expand("reports/figures/{pid}/compliance_heatmap.html", pid=config["PIDS"], sensor=config["SENSORS"]),
diff --git a/config.yaml b/config.yaml
index 48ff0c3d..a1818aba 100644
--- a/config.yaml
+++ b/config.yaml
@@ -44,4 +44,8 @@ PHONE_VALID_SENSED_DAYS:
 
 BARNETT_LOCATION:
   ACCURACY_LIMIT: 51 # filters location coordinates with an accuracy higher than this
-  TIMEZONE: *timezone
\ No newline at end of file
+  TIMEZONE: *timezone
+
+BLUETOOTH:
+  DAY_SEGMENTS: *day_segments
+  METRICS: ["countscans", "uniquedevices", "countscansmostuniquedevice"]
\ No newline at end of file
diff --git a/rules/features.snakefile b/rules/features.snakefile
index 14544319..cfdb5097 100644
--- a/rules/features.snakefile
+++ b/rules/features.snakefile
@@ -39,4 +39,15 @@ rule location_barnett_metrics:
     output:
         "data/processed/{pid}/location_barnett_metrics.csv"
     script:
-        "../src/features/location_barnett_metrics.R"
\ No newline at end of file
+        "../src/features/location_barnett_metrics.R"
+
+rule bluetooth_metrics:
+    input: 
+        "data/raw/{pid}/bluetooth_with_datetime.csv"
+    params:
+        day_segment = "{day_segment}",
+        metrics = config["BLUETOOTH"]["METRICS"]
+    output:
+        "data/processed/{pid}/bluetooth_{day_segment}.csv"
+    script:
+        "../src/features/bluetooth_metrics.R"
\ No newline at end of file
diff --git a/src/features/bluetooth_metrics.R b/src/features/bluetooth_metrics.R
new file mode 100644
index 00000000..21200364
--- /dev/null
+++ b/src/features/bluetooth_metrics.R
@@ -0,0 +1,41 @@
+source("packrat/init.R")
+
+library(dplyr)
+
+filter_by_day_segment <- function(data, day_segment) {
+  if(day_segment %in% c("morning", "afternoon", "evening", "night"))
+    data <- data %>% filter(local_day_segment == day_segment)
+
+  return(data %>% group_by(local_date))
+}
+
+compute_bluetooth_metric <- function(data, metric, day_segment){
+  if(metric %in% c("countscans", "uniquedevices")){
+    data <- data %>% filter_by_day_segment(day_segment)
+    data <- switch(metric,
+              "countscans" = data %>% summarise(!!paste("bluetooth", day_segment, metric, sep = "_") := n()),
+              "uniquedevices" = data %>% summarise(!!paste("bluetooth", day_segment, metric, sep = "_") := n_distinct(bt_address)))
+    return(data)
+   } else if(metric == "countscansmostuniquedevice"){
+     # Get the most scanned device
+    data <- data %>% group_by(bt_address) %>% 
+      mutate(N=n()) %>% 
+      ungroup() %>%
+      filter(N == max(N))
+    return(data %>% 
+             filter_by_day_segment(day_segment) %>%
+             summarise(!!paste("bluetooth", day_segment, metric, sep = "_") := n()))
+  }
+}
+
+data <- read.csv(snakemake@input[[1]], stringsAsFactors = FALSE)
+day_segment <- snakemake@params[["day_segment"]]
+metrics <-  snakemake@params[["metrics"]]
+features = data.frame(local_date = character(), stringsAsFactors = FALSE)
+
+for(metric in metrics){
+  feature <- compute_bluetooth_metric(data, metric, day_segment)
+  features <- merge(features, feature, by="local_date", all = TRUE)
+}
+
+write.csv(features, snakemake@output[[1]], row.names = FALSE)
\ No newline at end of file