From: Benjamin Mako Hill <mako@atdot.cc>
Date: Tue, 1 Jun 2021 00:06:09 +0000 (-0700)
Subject: updated grade code
X-Git-Url: https://code.communitydata.science/coldcallbot-discord.git/commitdiff_plain/3bd4c9c2a60797346868989dd63341e48e87da70?hp=-c

updated grade code

- COMMLD570A did not penalize/track absences at all so i cut this completely
---

3bd4c9c2a60797346868989dd63341e48e87da70
diff --git a/assessment_and_tracking/compute_final_case_grades.R b/assessment_and_tracking/compute_final_case_grades.R
index 60a60f3..b26270b 100644
--- a/assessment_and_tracking/compute_final_case_grades.R
+++ b/assessment_and_tracking/compute_final_case_grades.R
@@ -1,36 +1,23 @@
 ## load in the data
 #################################
 
-case.sessions  <- 15
-myuw <- read.csv("myuw-COM_482_A_autumn_2020_students.csv", stringsAsFactors=FALSE)
+myuw <- read.csv("myuw-COMMLD_570_A_spring_2021_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
+question.grades <- c("GOOD"=100, "FAIR"=100-(50/3.3), "WEAK"=100-(50/(3.3)*2))
 
 source("../assessment_and_tracking/track_participation.R")
 setwd("case_grades")
 
-rownames(d) <- d$discord.name
+rownames(d) <- d$unique.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))
+table(call.list$assessment)
+prop.table(table(call.list$assessment))
+table(call.list$answered)
+prop.table(table(call.list$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)])
+total.questions.asked <- nrow(call.list)
 
 ## generate grades
 ##########################################################
@@ -39,81 +26,47 @@ 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]]
+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$discord.name == x.discord.name,])
+    # missing.days <- nrow(missing.in.class[missing.in.class$unique.name == x.unique.name,])
 
     ## return the final score
-    data.frame(discord.name=x.discord.name,
-               part.grade=(base.score - missing.days * missed.question.penalty))
+    data.frame(unique.name=x.unique.name,
+               part.grade=(base.score))
 }
 
-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
+tmp <- do.call("rbind", lapply(d$unique.name, gen.part.grade))
 
-## 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$part.grade)]
+d[as.character(tmp$unique.name), "part.grade"] <- tmp$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")]
+d[sort.list(d$part.4point),]
 
 
 ## 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)
+## 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$discord.name == x.discord.name],
-                             sep=""))
-}
+## for (x.unique.name in d$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=""))
+## }
diff --git a/assessment_and_tracking/track_participation.R b/assessment_and_tracking/track_participation.R
index 698041c..28b8a4e 100644
--- a/assessment_and_tracking/track_participation.R
+++ b/assessment_and_tracking/track_participation.R
@@ -5,7 +5,7 @@ library(data.table)
 
 gs <- read.delim("student_information.tsv")
 d <- gs[,c(2,4)]
-colnames(d) <- c("student.num", "teams.name")
+colnames(d) <- c("student.num", "unique.name")
 
 call.list <- do.call("rbind", lapply(list.files(".", pattern="^call_list-.*tsv$"), function (x) {read.delim(x, stringsAsFactors=FALSE)[,1:4]}))
 
@@ -13,104 +13,13 @@ colnames(call.list) <- gsub("_", ".", colnames(call.list))
 
 table(call.list$unique_name[call.list$answered])
 
-exit()
-
-call.list$day <- as.Date(call.list$timestamp)
-
 ## 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,]
 
-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))
-
-## create list of folks who are missing in class 
-missing.in.class  <- call.list.full[is.na(call.list.full$answered) |
-                                    (!is.na(call.list.full$answered) & !call.list.full$answered),
-                                    c("discord.name", "day")]
-
-missing.in.class <- unique(missing.in.class)
-
-setDT(attendance)
-setkey(attendance, discord.name, day)
-setDT(missing.in.class)
-setkey(missing.in.class, discord.name, day)
-
-## drop presence for people on missing days
-attendance[missing.in.class,]
-attendance <- as.data.frame(attendance[!missing.in.class,])
-
-attendance.counts <- data.frame(table(attendance$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$day), function (day) {
-    day.total <- table(call.list.full$day == day)[["TRUE"]]
-    lapply(d$discord.name, function (discord.name) {
-        num.present <- nrow(attendance[attendance$day == day & attendance$discord.name == discord.name,])
-        if (num.present/day.total > 1) {print(day)}
-        data.frame(discord.name=discord.name,
-                   days.present=(num.present/day.total))
-    })
-})
-
-days.tmp <- do.call("rbind", lapply(days.list, function (x) do.call("rbind", x)))
-
-days.tbl <- tapply(days.tmp$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$days.absent), c("discord.name", "num.calls", "days.absent")]
-
-## make some visualizations of whose here/not here
-#######################################################
-
-png("questions_absence_histogram_combined.png", units="px", width=800, height=600)
-
-ggplot(d) +
-    aes(x=as.factor(num.calls), fill=days.absent, group=days.absent) +
-    geom_bar(color="black") +
-    scale_x_discrete("Number of questions asked") +
-    scale_y_continuous("Number of students") +
-    scale_fill_continuous("Days absent", low="red", high="blue")+
-    theme_bw()
-
-dev.off()
-
-png("questions_absenses_boxplots.png", units="px", width=800, height=600)
-
-ggplot(data=d) +
-    aes(x=as.factor(num.calls), y=days.absent) +
-    geom_boxplot() +
-    scale_x_discrete("Number of questions asked") +
-    scale_y_continuous("Days absent")
+call.counts <- data.frame(table(call.list$unique.name))
+colnames(call.counts) <- c("unique.name", "num.calls")
 
-dev.off()
+d <- merge(d, call.counts, all.x=TRUE, all.y=TRUE, by="unique.name"); d