X-Git-Url: https://code.communitydata.science/coldcallbot-discord.git/blobdiff_plain/3bd4c9c2a60797346868989dd63341e48e87da70..d6b74612e3a2f01112fa14c6c86bec9c20093ed3:/assessment_and_tracking/compute_final_case_grades.R

diff --git a/assessment_and_tracking/compute_final_case_grades.R b/assessment_and_tracking/compute_final_case_grades.R
index b26270b..93d6d1f 100644
--- a/assessment_and_tracking/compute_final_case_grades.R
+++ b/assessment_and_tracking/compute_final_case_grades.R
@@ -1,72 +1,148 @@
 ## load in the data
 #################################
+myuw <- read.csv("../data/2022_winter_COM_481_A_students.csv", stringsAsFactors=FALSE)
 
-myuw <- read.csv("myuw-COMMLD_570_A_spring_2021_students.csv", stringsAsFactors=FALSE)
+current.dir <- getwd()
+source("../assessment_and_tracking/track_participation.R")
+setwd(current.dir)
+
+rownames(d) <- d$unique.name
+call.list$timestamp <- as.Date(call.list$timestamp)
 
 ## class-level variables
-question.grades <- c("GOOD"=100, "FAIR"=100-(50/3.3), "WEAK"=100-(50/(3.3)*2))
+gpa.point.value <- 50/(4 - 0.7)
+question.grades <- c("PLUS"=100, "CHECK"=100-gpa.point.value, "MINUS"=100-(gpa.point.value*2))
+missed.question.penalty <- gpa.point.value * 0.2 ## 1/5 of a full point on the GPA scale
 
-source("../assessment_and_tracking/track_participation.R")
-setwd("case_grades")
+## inspect set the absence threashold
+ggplot(d) + aes(x=absences) + geom_histogram(binwidth=1, fill="white",color="black")
+absence.threshold <- median(d$absences)
 
-rownames(d) <- d$unique.name
+
+## inspect and set the questions cutoff
+## questions.cutoff <- median(d$num.calls)
+## median(d$num.calls)
+## questions.cutoff <- nrow(call.list) / nrow(d) ## TODO talk about this
+## this is the 95% percentile based on simulation in simulation.R
+questions.cutoff <- 4
 
 ## show the distribution of assessments
 table(call.list$assessment)
 prop.table(table(call.list$assessment))
-table(call.list$answered)
-prop.table(table(call.list$answered))
+
+table(call.list.full$answered)
+prop.table(table(call.list.full$answered))
 
 total.questions.asked <- nrow(call.list)
 
-## generate grades
-##########################################################
+## find out how man questions folks have present/absent for.
+## 
+## NOTE: this is currently only for informational purposes and is NOT
+## being used to compute grants in any way.
+########################################################################
+calls.per.day <- data.frame(day=as.Date(names(table(call.list$timestamp))),
+                            questions.asked=as.numeric(table(call.list$timestamp)))
+
+## function to return the numbers of calls present for or zero if they
+## were absent
+calls.for.student.day <- function (day, student.id) {
+    if (any(absence$unique.name == student.id & absence$date.absent == day)) {
+        return(0)
+    } else {
+        return(calls.per.day$questions.asked[calls.per.day$day == day])
+    }
+}
+
+compute.questions.present.for.student <- function (student.id) {
+    sum(unlist(lapply(unique(calls.per.day$day), calls.for.student.day, student.id)))
+}
 
-d$part.grade <- NA
+## create new column with number of questions present
+d$q.present <- unlist(lapply(d$unique.name, compute.questions.present.for.student))
+d$prop.asked <- d$num.calls / d$q.present
+
+## generate statistics using these new variables
+prop.asks.quantiles <- quantile(d$prop.asked, probs=seq(0,1, 0.01))
+prop.asks.quantiles <- prop.asks.quantiles[!duplicated(prop.asks.quantiles)]
+
+d$prop.asked.quant <- cut(d$prop.asked, right=FALSE, breaks=c(prop.asks.quantiles, 1),
+    labels=names(prop.asks.quantiles)[1:(length(prop.asks.quantiles))])
+
+## generate grades
+########################################################################
 
 ## print the median number of questions for (a) everybody and (b)
 ## people that have been present 75% of the time
 median(d$num.calls)
 
-questions.cutoff <- median(d$num.calls)
-
 ## helper function to generate average grade minus number of missing
 gen.part.grade <- function (x.unique.name) {
     q.scores <- question.grades[call.list$assessment[call.list$unique.name == x.unique.name]]
     base.score <- mean(q.scores, na.rm=TRUE)
 
     ## number of missing days
-    # missing.days <- nrow(missing.in.class[missing.in.class$unique.name == x.unique.name,])
+    missing.in.class.days <- nrow(missing.in.class[missing.in.class$unique.name == x.unique.name,])
 
     ## return the final score
     data.frame(unique.name=x.unique.name,
-               part.grade=(base.score))
+               base.grade=base.score,
+               missing.in.class.days=missing.in.class.days)
 }
 
 
+## create the base grades which do NOT include missing questions
 tmp <- do.call("rbind", lapply(d$unique.name, gen.part.grade))
+d <- merge(d, tmp)
+rownames(d) <- d$unique.name
+d$part.grade <- d$base.grade
 
-d[as.character(tmp$unique.name), "part.grade"] <- tmp$part.grade
+## 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,]
 
-## generate the baseline participation grades as per the process above
+## set those people to 0 :(
+d$part.grade[d$num.calls == 0] <- 0
 
-## map part grades back to 4.0 letter scale and points
-d$part.4point <-round((d$part.grade / (50/3.3)) - 2.6, 2)
+## step 2: identify the people who were were not asked "enough"
+## questions but were unlucky/lucky
+
+## first this just prints out are the people were were not called
+## simply because they got unlucky
+d[d$num.calls < questions.cutoff & d$absences < absence.threshold,]
+
+## these are the people were were not called simply unlucky (i.e.,
+## they were not in class very often)
+penalized.unique.names <- d$unique.name[d$num.calls < questions.cutoff & d$absences > absence.threshold]
+d[d$unique.name %in% penalized.unique.names,]
+
+## now add "zeros" for every questions that is below the normal
+d[as.character(penalized.unique.names),"part.grade"] <- (
+    (d[as.character(penalized.unique.names),"num.calls"] * d[as.character(penalized.unique.names),"part.grade"])
+    / questions.cutoff)
 
-d[sort.list(d$part.4point),]
+d[as.character(penalized.unique.names),]
 
+## apply the penality for number of days we called on them and they were gone
+d$part.grade <- d$part.grade - d$missing.in.class.days * missed.question.penalty
 
-## writing out data
+## TODO ensure this is right. i think it is
+## map part grades back to 4.0 letter scale and points
+d$part.4point <- round((d$part.grade / gpa.point.value) - ((100 / gpa.point.value) - 4), 2)
+
+d[sort.list(d$part.4point, decreasing=TRUE),
+  c("unique.name", "short.name", "num.calls", "absences", "part.4point")]
+
+## writing out data to CSV
 d.print <- merge(d, myuw[,c("StudentNo", "FirstName", "LastName", "UWNetID")],
-           by.x="student.num", by.y="StudentNo")
-write.csv(d.print, file="final_participation_grades.csv")
-
-## library(rmarkdown)
-
-## for (x.unique.name in d$unique.name) {
-##     render(input="../../assessment_and_tracking/student_report_template.Rmd",
-##            output_format="html_document",
-##            output_file=paste("../data/case_grades/student_reports/",
-##                              d.print$UWNetID[d.print$unique.name == x.unique.name],
-##                              sep=""))
-## }
+                 by.x="unique.name", by.y="StudentNo")
+write.csv(d.print, file="../data/final_participation_grades.csv")
+
+library(rmarkdown)
+
+for (id in d$unique.name) {
+    render(input="student_report_template.Rmd",
+           output_format="html_document",
+           output_file=paste("../data/case_grades/",
+                             d.print$unique.name[d.print$unique.name == id],
+                             sep=""))
+}