From 010114c1aa421734f55d458bdc8cd0e7466ca336 Mon Sep 17 00:00:00 2001
From: JulioV <JulioV@users.noreply.github.com>
Date: Mon, 13 Apr 2020 13:24:52 -0400
Subject: [PATCH] Add wifi features

---
 Snakefile                    |  3 +++
 config.yaml                  |  4 ++++
 rules/features.snakefile     | 11 ++++++++++
 src/features/wifi_features.R | 41 ++++++++++++++++++++++++++++++++++++
 4 files changed, 59 insertions(+)
 create mode 100644 src/features/wifi_features.R

diff --git a/Snakefile b/Snakefile
index 06d323a6..7379de28 100644
--- a/Snakefile
+++ b/Snakefile
@@ -67,6 +67,9 @@ rule all:
         expand("data/processed/{pid}/fitbit_step_{day_segment}.csv",
                             pid = config["PIDS"],
                             day_segment = config["STEP"]["DAY_SEGMENTS"]),
+        expand("data/processed/{pid}/wifi_{segment}.csv",
+                            pid=config["PIDS"], 
+                            segment = config["WIFI"]["DAY_SEGMENTS"]),
         # Models
         expand("data/processed/{pid}/metrics_for_individual_model/{source}_{day_segment}_original.csv",
                                 pid = config["PIDS"],
diff --git a/config.yaml b/config.yaml
index 7220fc5d..068155e2 100644
--- a/config.yaml
+++ b/config.yaml
@@ -124,6 +124,10 @@ STEP:
   THRESHOLD_ACTIVE_BOUT: 10 # steps
   INCLUDE_ZERO_STEP_ROWS: True
 
+WIFI:
+  DAY_SEGMENTS: *day_segments
+  FEATURES: ["countscans", "uniquedevices", "countscansmostuniquedevice"]
+
 METRICS_FOR_ANALYSIS:
   GROUNDTRUTH_TABLE: participant_info
   SOURCES: &sources ["phone_metrics", "fitbit_metrics", "phone_fitbit_metrics"]
diff --git a/rules/features.snakefile b/rules/features.snakefile
index 9d937797..ce2f99d1 100644
--- a/rules/features.snakefile
+++ b/rules/features.snakefile
@@ -174,3 +174,14 @@ rule fitbit_step_features:
         "data/processed/{pid}/fitbit_step_{day_segment}.csv"
     script:
         "../src/features/fitbit_step_features.py"
+
+rule wifi_features:
+    input: 
+        "data/raw/{pid}/wifi_with_datetime.csv"
+    params:
+        day_segment = "{day_segment}",
+        features = config["WIFI"]["FEATURES"]
+    output:
+        "data/processed/{pid}/wifi_{day_segment}.csv"
+    script:
+        "../src/features/wifi_features.R"
\ No newline at end of file
diff --git a/src/features/wifi_features.R b/src/features/wifi_features.R
new file mode 100644
index 00000000..b2f11339
--- /dev/null
+++ b/src/features/wifi_features.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_wifi_feature <- function(data, feature, day_segment){
+  if(feature %in% c("countscans", "uniquedevices")){
+    data <- data %>% filter_by_day_segment(day_segment)
+    data <- switch(feature,
+              "countscans" = data %>% summarise(!!paste("wifi", day_segment, feature, sep = "_") := n()),
+              "uniquedevices" = data %>% summarise(!!paste("wifi", day_segment, feature, sep = "_") := n_distinct(bssid)))
+    return(data)
+   } else if(feature == "countscansmostuniquedevice"){
+     # Get the most scanned device
+    data <- data %>% group_by(bssid) %>% 
+      mutate(N=n()) %>% 
+      ungroup() %>%
+      filter(N == max(N))
+    return(data %>% 
+             filter_by_day_segment(day_segment) %>%
+             summarise(!!paste("wifi", day_segment, feature, sep = "_") := n()))
+  }
+}
+
+data <- read.csv(snakemake@input[[1]], stringsAsFactors = FALSE)
+day_segment <- snakemake@params[["day_segment"]]
+requested_features <-  snakemake@params[["features"]]
+features = data.frame(local_date = character(), stringsAsFactors = FALSE)
+
+for(requested_feature in requested_features){
+  feature <- compute_wifi_feature(data, requested_feature, 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