Add bluetooth features

replace/9f5cc9465c64a562c1754f378899037db5584ac8
JulioV 2019-11-06 12:19:30 -05:00
parent 58299a8869
commit 911e183c26
4 changed files with 61 additions and 2 deletions

View File

@ -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"]),

View File

@ -45,3 +45,7 @@ PHONE_VALID_SENSED_DAYS:
BARNETT_LOCATION:
ACCURACY_LIMIT: 51 # filters location coordinates with an accuracy higher than this
TIMEZONE: *timezone
BLUETOOTH:
DAY_SEGMENTS: *day_segments
METRICS: ["countscans", "uniquedevices", "countscansmostuniquedevice"]

View File

@ -40,3 +40,14 @@ rule location_barnett_metrics:
"data/processed/{pid}/location_barnett_metrics.csv"
script:
"../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"

View File

@ -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)