From b795d1a0223444edfbe721eabd480299a92e26f2 Mon Sep 17 00:00:00 2001
From: Meng Li <34143965+Meng6@users.noreply.github.com>
Date: Wed, 24 Jun 2020 15:46:27 -0400
Subject: [PATCH] Refactor wifi features

---
 src/features/wifi/wifi_base.R | 45 +++++++++++++++++++++++++++++++++++
 src/features/wifi_features.R  | 41 +++++++------------------------
 2 files changed, 53 insertions(+), 33 deletions(-)
 create mode 100644 src/features/wifi/wifi_base.R

diff --git a/src/features/wifi/wifi_base.R b/src/features/wifi/wifi_base.R
new file mode 100644
index 00000000..7e8eff6c
--- /dev/null
+++ b/src/features/wifi/wifi_base.R
@@ -0,0 +1,45 @@
+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()))
+  }
+}
+
+base_wifi_features <- function(wifi_data, day_segment, requested_features){
+    # Output dataframe
+    features = data.frame(local_date = character(), stringsAsFactors = FALSE)
+
+    # The name of the features this function can compute
+    base_features_names  <- c("countscans", "uniquedevices", "countscansmostuniquedevice")
+
+    # The subset of requested features this function can compute
+    features_to_compute  <- intersect(base_features_names, requested_features)
+
+    for(feature_name in features_to_compute){
+    feature <- compute_wifi_feature(wifi_data, feature_name, day_segment)
+    features <- merge(features, feature, by="local_date", all = TRUE)
+    }
+
+    return(features)
+}
diff --git a/src/features/wifi_features.R b/src/features/wifi_features.R
index 7c6e5697..fb3964b0 100644
--- a/src/features/wifi_features.R
+++ b/src/features/wifi_features.R
@@ -1,41 +1,16 @@
 source("renv/activate.R")
-
+source("src/features/wifi/wifi_base.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)
+wifi_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)
-}
+# Compute base wifi features
+features <- merge(features, base_wifi_features(wifi_data, day_segment, requested_features), by="local_date", all = TRUE)
 
-write.csv(features, snakemake@output[[1]], row.names = FALSE)
\ No newline at end of file
+if(ncol(features) != length(requested_features) + 1)
+  stop(paste0("The number of features in the output dataframe (=", ncol(features),") does not match the expected value (=", length(requested_features)," + 1). Verify your wifi feature extraction functions"))
+
+write.csv(features, snakemake@output[[1]], row.names = FALSE)