## load in the data
#################################

case.sessions  <- 15
myuw <- read.csv("myuw-COM_482_A_autumn_2020_students.csv", stringsAsFactors=FALSE)

## class-level variables
question.grades <- c("GOOD"=100, "FAIR"=100-(50/3.3), "BAD"=100-(50/(3.3)*2))
missed.question.penalty <- (50/3.3) * 0.2 ## 1/5 of a full point on the GPA scale

source("../assessment_and_tracking/track_participation.R")
setwd("case_grades")

rownames(d) <- d$discord.name

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

total.questions.asked <- nrow(call.list.full)

## create new column with number of questions present
d$prop.asked <- d$num.calls / d$num.present

## generate statistics using these new variables
prop.asks.quantiles <- quantile(d$prop.asked, probs=seq(0,1, 0.01))
prop.asks.quantiles <- prop.asks.quantiles[!duplicated(prop.asks.quantiles)]

## this is generating broken stuff but it's not used for anything
d$prop.asked.quant <- cut(d$prop.asked, breaks=prop.asks.quantiles,
    labels=names(prop.asks.quantiles)[1:(length(prop.asks.quantiles)-1)])

## generate grades
##########################################################

d$part.grade <- NA

## print the median number of questions for (a) everybody and (b)
## people that have been present 75% of the time
median(d$num.calls[d$days.absent < 0.25*case.sessions])
median(d$num.calls)

questions.cutoff <- median(d$num.calls)

## helper function to generate average grade minus number of missing
gen.part.grade <- function (x.discord.name) {
    q.scores <- question.grades[call.list$assessment[call.list$discord.name == x.discord.name]]
    base.score <- mean(q.scores, na.rm=TRUE)

    ## number of missing days
    missing.days <- nrow(missing.in.class[missing.in.class$discord.name == x.discord.name,])

    ## return the final score
    data.frame(discord.name=x.discord.name,
               part.grade=(base.score - missing.days * missed.question.penalty))
}

tmp <- do.call("rbind", lapply(d$discord.name[d$num.calls >= questions.cutoff], gen.part.grade))

d[as.character(tmp$discord.name), "part.grade"] <- tmp$part.grade

## next handle the folks *under* the median

## first we handle the zeros
## step 1: first double check the people who have zeros and ensure that they didn't "just" get unlucky"
d[d$num.calls == 0,]

## set those people to 0 :(
d$part.grade[d$num.calls == 0] <- 0

## step 2 is to handle folks who got unlucky in the normal way
tmp <- do.call("rbind", lapply(d$discord.name[is.na(d$part.grade) & d$prop.asked <= median(d$prop.asked)], gen.part.grade))
d[as.character(tmp$discord.name), "part.grade"] <- tmp$part.grade

## the people who are left are lucky and still undercounted so we'll penalize them
d[is.na(d$part.grade),]
penalized.discord.names <- d$discord.name[is.na(d$part.grade)]

## generate the baseline participation grades as per the process above
tmp <- do.call("rbind", lapply(penalized.discord.names, gen.part.grade))
d[as.character(tmp$discord.name), "part.grade"] <- tmp$part.grade

## now add "zeros" for every questions that is below the normal
d[as.character(penalized.discord.names),"part.grade"] <- ((
    (questions.cutoff - d[as.character(penalized.discord.names),"num.calls"] * 0) +
    (d[as.character(penalized.discord.names),"num.calls"] * d[as.character(penalized.discord.names),"part.grade"]) )
    / questions.cutoff)

d[as.character(penalized.discord.names),]

## map part grades back to 4.0 letter scale and points
d$part.4point <-round((d$part.grade / (50/3.3)) - 2.6, 2)

d[sort.list(d$prop.asked), c("discord.name", "num.calls", "num.present",
                             "prop.asked", "prop.asked.quant", "part.grade", "part.4point",
                             "days.absent")]

d[sort.list(d$part.4point), c("discord.name", "num.calls", "num.present",
                             "prop.asked", "prop.asked.quant", "part.grade", "part.4point",
                             "days.absent")]


## writing out data
quantile(d$num.calls, probs=(0:100*0.01))
d.print <- merge(d, myuw[,c("StudentNo", "FirstName", "LastName", "UWNetID")],
           by.x="student.num", by.y="StudentNo")
write.csv(d.print, file="final_participation_grades.csv")

library(rmarkdown)

for (x.discord.name in d$discord.name) {
    render(input="../../assessment_and_tracking/student_report_template.Rmd",
           output_format="html_document",
           output_file=paste("../data/case_grades/student_reports/",
                             d.print$UWNetID[d.print$discord.name == x.discord.name],
                             sep=""))
}