Add wifi features
parent
8cc93c8791
commit
010114c1aa
|
@ -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"],
|
||||
|
|
|
@ -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"]
|
||||
|
|
|
@ -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"
|
|
@ -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)
|
Loading…
Reference in New Issue