87 lines
3.0 KiB
R
87 lines
3.0 KiB
R
library(ggplot2)
|
|
|
|
gs <- read.delim("student_information.tsv")
|
|
d <- gs[,c(2,5)]
|
|
colnames(d) <- c("student.num", "discord.name")
|
|
|
|
call.list <- do.call("rbind", lapply(list.files(".", pattern="^call_list-.*tsv$"), function (x) {read.delim(x)[,1:3]}))
|
|
colnames(call.list) <- gsub("_", ".", colnames(call.list))
|
|
|
|
call.list$day <- as.Date(call.list$timestamp)
|
|
|
|
call.counts <- data.frame(table(call.list$discord.name))
|
|
colnames(call.counts) <- c("discord.name", "num.calls")
|
|
|
|
d <- merge(d, call.counts, all.x=TRUE, all.y=TRUE, by="discord.name"); d
|
|
|
|
## set anything that's missing to zero
|
|
d$num.calls[is.na(d$num.calls)] <- 0
|
|
|
|
attendance <- unlist(lapply(list.files(".", pattern="^attendance-.*tsv$"), function (x) {d <- read.delim(x); strsplit(d[[2]], ",")}))
|
|
|
|
|
|
file.to.attendance.list <- function (x) {
|
|
tmp <- read.delim(x)
|
|
d.out <- data.frame(discord.name=unlist(strsplit(tmp[[2]], ",")))
|
|
d.out$day <- rep(as.Date(tmp[[1]][1]), nrow(d.out))
|
|
return(d.out)
|
|
}
|
|
|
|
attendance <- do.call("rbind",
|
|
lapply(list.files(".", pattern="^attendance-.*tsv$"),
|
|
file.to.attendance.list))
|
|
|
|
attendance.counts <- data.frame(table(attendance$discord.name))
|
|
colnames(attendance.counts) <- c("discord.name", "num.present")
|
|
|
|
d <- merge(d, attendance.counts,
|
|
all.x=TRUE, all.y=TRUE,
|
|
by="discord.name")
|
|
|
|
days.list <- lapply(unique(attendance$day), function (day) {
|
|
day.total <- table(call.list$day == day)[["TRUE"]]
|
|
lapply(d$discord.name, function (discord.name) {
|
|
num.present <- nrow(attendance[attendance$day == day & attendance$discord.name == discord.name,])
|
|
data.frame(discord.name=discord.name,
|
|
days.present=(num.present/day.total))
|
|
})
|
|
})
|
|
|
|
days.tmp <- do.call("rbind", lapply(days.list, function (x) do.call("rbind", x)))
|
|
|
|
days.tbl <- tapply(days.tmp$days.present, days.tmp$discord.name, sum)
|
|
|
|
attendance.days <- data.frame(discord.name=names(days.tbl),
|
|
days.present=days.tbl,
|
|
days.absent=length(list.files(".", pattern="^attendance-.*tsv$"))-days.tbl)
|
|
|
|
d <- merge(d, attendance.days,
|
|
all.x=TRUE, all.y=TRUE, by="discord.name")
|
|
d[sort.list(d$days.absent), c("discord.name", "num.calls", "days.absent")]
|
|
|
|
## make some visualizations of whose here/not here
|
|
#######################################################
|
|
|
|
png("questions_absence_histogram_combined.png", units="px", width=800, height=600)
|
|
|
|
ggplot(d) +
|
|
aes(x=as.factor(num.calls), fill=days.absent, group=days.absent) +
|
|
geom_bar(color="black") +
|
|
scale_x_discrete("Number of questions asked") +
|
|
scale_y_continuous("Number of students") +
|
|
scale_fill_continuous("Days absent", low="red", high="blue")+
|
|
theme_bw()
|
|
|
|
dev.off()
|
|
|
|
png("questions_absenses_boxplots.png", units="px", width=800, height=600)
|
|
|
|
ggplot(data=d) +
|
|
aes(x=as.factor(num.calls), y=days.absent) +
|
|
geom_boxplot() +
|
|
scale_x_discrete("Number of questions asked") +
|
|
scale_y_continuous("Days absent")
|
|
|
|
dev.off()
|
|
|