2020-05-02 01:46:04 +02:00
|
|
|
source("renv/activate.R")
|
2019-10-25 16:21:09 +02:00
|
|
|
|
|
|
|
library(dplyr)
|
|
|
|
library(entropy)
|
|
|
|
library(robustbase)
|
|
|
|
|
2019-11-06 20:47:33 +01:00
|
|
|
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))
|
|
|
|
}
|
|
|
|
|
2019-11-11 21:15:20 +01:00
|
|
|
Mode <- function(v) {
|
|
|
|
uniqv <- unique(v)
|
|
|
|
uniqv[which.max(tabulate(match(v, uniqv)))]
|
|
|
|
}
|
|
|
|
|
2020-04-08 17:51:18 +02:00
|
|
|
compute_call_feature <- function(calls, requested_feature, day_segment){
|
|
|
|
if(requested_feature == "countmostfrequentcontact"){
|
2019-11-12 21:40:48 +01:00
|
|
|
# Get the most frequent contact
|
|
|
|
calls <- calls %>% group_by(trace) %>%
|
|
|
|
mutate(N=n()) %>%
|
|
|
|
ungroup() %>%
|
|
|
|
filter(N == max(N))
|
|
|
|
|
|
|
|
return(calls %>%
|
|
|
|
filter_by_day_segment(day_segment) %>%
|
2020-04-08 17:51:18 +02:00
|
|
|
summarise(!!paste("call", type, day_segment, requested_feature, sep = "_") := n()))
|
2019-11-12 21:40:48 +01:00
|
|
|
} else {
|
|
|
|
calls <- calls %>% filter_by_day_segment(day_segment)
|
2020-04-08 17:51:18 +02:00
|
|
|
feature <- switch(requested_feature,
|
|
|
|
"count" = calls %>% summarise(!!paste("call", type, day_segment, requested_feature, sep = "_") := n()),
|
|
|
|
"distinctcontacts" = calls %>% summarise(!!paste("call", type, day_segment, requested_feature, sep = "_") := n_distinct(trace)),
|
|
|
|
"meanduration" = calls %>% summarise(!!paste("call", type, day_segment, requested_feature, sep = "_") := mean(call_duration)),
|
|
|
|
"sumduration" = calls %>% summarise(!!paste("call", type, day_segment, requested_feature, sep = "_") := sum(call_duration)),
|
|
|
|
"minduration" = calls %>% summarise(!!paste("call", type, day_segment, requested_feature, sep = "_") := min(call_duration)),
|
|
|
|
"maxduration" = calls %>% summarise(!!paste("call", type, day_segment, requested_feature, sep = "_") := max(call_duration)),
|
|
|
|
"stdduration" = calls %>% summarise(!!paste("call", type, day_segment, requested_feature, sep = "_") := sd(call_duration)),
|
|
|
|
"modeduration" = calls %>% summarise(!!paste("call", type, day_segment, requested_feature, sep = "_") := Mode(call_duration)),
|
|
|
|
"hubermduration" = calls %>% summarise(!!paste("call", type, day_segment, requested_feature, sep = "_") := huberM(call_duration)$mu),
|
|
|
|
"varqnduration" = calls %>% summarise(!!paste("call", type, day_segment, requested_feature, sep = "_") := Qn(call_duration)),
|
|
|
|
"entropyduration" = calls %>% summarise(!!paste("call", type, day_segment, requested_feature, sep = "_") := entropy.MillerMadow(call_duration)),
|
|
|
|
"timefirstcall" = calls %>% summarise(!!paste("call", type, day_segment, requested_feature, sep = "_") := first(local_hour) + (first(local_minute)/60)),
|
|
|
|
"timelastcall" = calls %>% summarise(!!paste("call", type, day_segment, requested_feature, sep = "_") := last(local_hour) + (last(local_minute)/60)))
|
2019-11-12 21:54:12 +01:00
|
|
|
return(feature)
|
2019-11-12 21:40:48 +01:00
|
|
|
}
|
2019-11-06 20:47:33 +01:00
|
|
|
}
|
|
|
|
|
|
|
|
calls <- read.csv(snakemake@input[[1]], stringsAsFactors = FALSE)
|
2019-10-25 16:21:09 +02:00
|
|
|
day_segment <- snakemake@params[["day_segment"]]
|
2020-04-08 17:51:18 +02:00
|
|
|
requested_features <- snakemake@params[["features"]]
|
2019-10-25 16:21:09 +02:00
|
|
|
type <- snakemake@params[["call_type"]]
|
2019-11-06 20:47:33 +01:00
|
|
|
features = data.frame(local_date = character(), stringsAsFactors = FALSE)
|
2019-10-25 16:21:09 +02:00
|
|
|
|
2019-11-06 20:47:33 +01:00
|
|
|
calls <- calls %>% filter(call_type == ifelse(type == "incoming", "1", ifelse(type == "outgoing", "2", "3")))
|
2019-10-25 16:21:09 +02:00
|
|
|
|
2020-04-08 17:51:18 +02:00
|
|
|
for(requested_feature in requested_features){
|
|
|
|
feature <- compute_call_feature(calls, requested_feature, day_segment)
|
2019-11-06 20:47:33 +01:00
|
|
|
features <- merge(features, feature, by="local_date", all = TRUE)
|
2019-10-25 16:21:09 +02:00
|
|
|
}
|
|
|
|
|
2020-04-08 17:51:18 +02:00
|
|
|
if("countmostfrequentcontact" %in% requested_features)
|
2020-03-12 16:18:32 +01:00
|
|
|
features <- features %>% mutate_at(vars(contains('countmostfrequentcontact')), funs(ifelse(is.na(.), 0, .)))
|
|
|
|
|
2019-11-06 20:47:33 +01:00
|
|
|
write.csv(features, snakemake@output[[1]], row.names = FALSE)
|