From cb2ee1ec821d9363095483a58ec5af0cad0784ab Mon Sep 17 00:00:00 2001
From: JulioV <JulioV@users.noreply.github.com>
Date: Mon, 9 Dec 2019 19:15:10 -0500
Subject: [PATCH] Add switch to barnet_locations.R to use all, all except fused
 or resample fused locations

---
 config.yaml                             |  3 ++-
 rules/features.snakefile                |  4 +++-
 src/features/location_barnett_metrics.R | 14 +++++++++++++-
 3 files changed, 18 insertions(+), 3 deletions(-)

diff --git a/config.yaml b/config.yaml
index a56c3ef4..ee89d16f 100644
--- a/config.yaml
+++ b/config.yaml
@@ -52,7 +52,8 @@ RESAMPLE_FUSED_LOCATION:
   TIMEZONE: *timezone
 
 BARNETT_LOCATION:
-  ACCURACY_LIMIT: 51 # filters location coordinates with an accuracy higher than this
+  LOCATIONS_TO_USE: ALL # ALL_EXCEPT_FUSED, RESAMPLE_FUSED
+  ACCURACY_LIMIT: 51 # meters, drops location coordinates with an accuracy higher than this. This number means there's a 68% probability the true location is within this radius
   TIMEZONE: *timezone
 
 BLUETOOTH:
diff --git a/rules/features.snakefile b/rules/features.snakefile
index 80d0427a..cfbde01c 100644
--- a/rules/features.snakefile
+++ b/rules/features.snakefile
@@ -48,8 +48,10 @@ rule google_activity_recognition_deltas:
 
 rule location_barnett_metrics:
     input:
-        "data/raw/{pid}/locations_with_datetime.csv"
+        raw = "data/raw/{pid}/locations_raw.csv",
+        fused = rules.resample_fused_location.output
     params:
+        locations_to_use = config["BARNETT_LOCATION"]["LOCATIONS_TO_USE"],
         accuracy_limit = config["BARNETT_LOCATION"]["ACCURACY_LIMIT"],
         timezone = config["BARNETT_LOCATION"]["TIMEZONE"]
     output:
diff --git a/src/features/location_barnett_metrics.R b/src/features/location_barnett_metrics.R
index 89e18bf3..bc643961 100644
--- a/src/features/location_barnett_metrics.R
+++ b/src/features/location_barnett_metrics.R
@@ -26,12 +26,24 @@ write_empty_file <- function(file_path){
 file.sources = list.files(c("src/features/location_barnett"), pattern="*.R$", full.names=TRUE, ignore.case=TRUE)
 sapply(file.sources,source,.GlobalEnv)
 
+locations_to_use <- snakemake@params[["locations_to_use"]]
 accuracy_limit <- snakemake@params[["accuracy_limit"]]
 timezone <- snakemake@params[["timezone"]]
 
-location <- read.csv(snakemake@input[[1]], stringsAsFactors = F) %>%
+# By deafult we use all raw locations: fused without resampling and not fused (gps, network)
+location <- read.csv(snakemake@input[["raw"]], stringsAsFactors = F) %>%
   select(timestamp, latitude = double_latitude, longitude = double_longitude, altitude = double_altitude, accuracy)
 
+if(locations_to_use == "ALL_EXCEPT_FUSED"){
+  location <- location %>% filter(provider != "fused")
+} else if (locations_to_use == "RESAMPLE_FUSED"){
+  location <- read.csv(snakemake@input[["fused"]], stringsAsFactors = F) %>%
+    select(timestamp, latitude = double_latitude, longitude = double_longitude, altitude = double_altitude, accuracy)
+} else if (locations_to_use != "ALL"){
+  print("Unkown filter, provide one of the following three: ALL, ALL_EXCEPT_FUSED, or RESAMPLE_FUSED")
+  quit(save = "no", status = 1, runLast = FALSE)
+}
+
 if (nrow(location) > 1){
     features <- MobilityFeatures(location, ACCURACY_LIM = accuracy_limit, tz = timezone)
     if(is.null(features)){