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.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]], ",")}))

attendance.counts <- data.frame(table(attendance))
colnames(attendance.counts) <- c("discord.name", "num.present")

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


color.gradient <- scales::seq_gradient_pal("yellow", "magenta", "Lab")(seq(0,1,length.out=length(unique(d$num.present))))

png("questions_absence_histogram_combined.png", units="px", width=800, height=600)

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

dev.off()