setwd("~/online_communities/coldcall_scripts-COM481-2024Q4/data/")

library(data.table)

################################################
## LOAD call_list TSV data
################################################

call.list <- do.call("rbind", lapply(list.files(".", pattern="^call_list-.*tsv$"), function (x) {read.delim(x, stringsAsFactors=FALSE)[,1:5]}))

colnames(call.list) <- gsub("_", ".", colnames(call.list))
colnames(call.list)[1] <- "unique.name"
colnames(call.list)[2] <- "preferred.name"

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,]

## show the distribution of assessments
prop.table(table(call.list$assessment))

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

## create list of folks who are missing in class w/o reporting it
absence.data.cols <- c("unique.name", "date.absent", "reported")

missing.in.class <- call.list.full[!call.list.full$answered,
                                   c("unique.name", "timestamp")]
missing.in.class$date.absent <- as.Date(missing.in.class$timestamp)
missing.in.class$reported <- rep(FALSE, nrow(missing.in.class))
missing.in.class <- missing.in.class[,absence.data.cols]
missing.in.class <- unique(missing.in.class)

################################################
## LOAD absence data TSV data
################################################

absence.google <- read.delim("optout_poll_data.tsv")
colnames(absence.google) <- c("timestamp", "unique.name", "date.absent")
absence.google$date.absent <- as.Date(absence.google$date.absent, format="%m/%d/%Y")
absence.google$reported <- TRUE
absence.google <- absence.google[,absence.data.cols]
absence.google <- unique(absence.google)

## combine the two absence lists and then create a unique subset
absence <- rbind(missing.in.class[,absence.data.cols],
                 absence.google[,absence.data.cols])

## these are people that show up in both lists (i.e., probably they
## submitted too late but it's worth verifying before we penalize
## them. i'd actually remove them from the absence sheet to suppress
## this error
absence[duplicated(absence[,1:2]),]
absence <- absence[!duplicated(absence[,1:2]),]

## print total questions asked and absences
absence.count <- data.frame(table(unique(absence[,c("unique.name", "date.absent")])[,"unique.name"]))
colnames(absence.count) <- c("unique.name", "absences")


## load up the full class list
gs <- read.delim("student_information.tsv")
d <- gs[,c("Your.UW.student.number", "Name.you.d.like.to.go.by.in.class")]
colnames(d) <- c("unique.name", "short.name")

## merge in the call counts
d <- merge(d, call.counts, all.x=TRUE, all.y=FALSE, by="unique.name")
d <- merge(d, absence.count, by="unique.name", all.x=TRUE, all.y=FALSE)

d

## set anything that's missing to zero
d$num.calls[is.na(d$num.calls)] <- 0
d$absences[is.na(d$absences)] <- 0

################################################
## list people who have been absent often or called on a lot
################################################


## list students sorted in terms of (a) absences and (b) prev questions
d[sort.list(d$absences),]

d[sort.list(d$num.calls, decreasing=TRUE),]

################################################
## build visualizations
################################################


library(ggplot2)

color.gradient <- scales::seq_gradient_pal("yellow", "magenta", "Lab")(seq(0,1,length.out=range(d$absences)[2]+1))

table(d$num.calls, d$absences)

png("questions_absence_histogram_combined.png", units="px", width=600, height=400)

ggplot(d) +
    aes(x=as.factor(num.calls), fill=as.factor(absences)) +
    geom_bar(color="black") +
    stat_count() +
    scale_x_discrete("Number of questions answered") +
    scale_y_continuous("Number of students") +
    ##scale_fill_brewer("Absences", palette="Blues") +
    scale_fill_manual("Absences", values=color.gradient) +
    theme_bw()

dev.off()

absence.labeller <- function (df) {
    lapply(df, function (x) { paste("Absences:", x) })
}

## png("questions_absence_histogram_facets.png", units="px", width=600, height=400)

## ggplot(d) +
##     aes(x=as.factor(num.calls)) +
##     geom_bar() +
##     stat_count() +
##     scale_x_discrete("Number of questions answered") +
##     scale_y_continuous("Number of students") +
##     theme_bw() +
##     facet_wrap(.~absences, ncol=5, labeller="absence.labeller")