setwd("~/online_communities/coldcallbot/data/")

library(ggplot2)
library(data.table)

gs <- read.delim("student_information.tsv")
d <- gs[,c(2,4)]
colnames(d) <- c("student.num", "unique.name")

call.list <- do.call("rbind", lapply(list.files(".", pattern="^call_list-.*tsv$"), function (x) {read.delim(x, stringsAsFactors=FALSE)[,1:4]}))

colnames(call.list) <- gsub("_", ".", colnames(call.list))

table(call.list$unique_name[call.list$answered])

## drop calls where the person wasn't present
call.list.full <- call.list
call.list[!call.list$answered,]
call.list <- call.list[call.list$answered,]

call.counts <- data.frame(table(call.list$unique.name))
colnames(call.counts) <- c("unique.name", "num.calls")

d <- merge(d, call.counts, all.x=TRUE, all.y=TRUE, by="unique.name"); d