-library(ggplot2)
+setwd("~/online_communities/coldcall_scripts-COM481-2024Q4/data/")
+
library(data.table)
-gs <- read.delim("student_information.tsv")
-d <- gs[,c(2,5)]
-colnames(d) <- c("student.num", "discord.name")
+################################################
+## LOAD call_list TSV data
+################################################
+
+call.list <- do.call("rbind", lapply(list.files(".", pattern="^call_list-.*tsv$"), function (x) {read.delim(x, stringsAsFactors=FALSE)[,1:5]}))
-call.list <- do.call("rbind", lapply(list.files(".", pattern="^call_list-.*tsv$"), function (x) {read.delim(x)[,1:4]}))
colnames(call.list) <- gsub("_", ".", colnames(call.list))
+colnames(call.list)[1] <- "unique.name"
+colnames(call.list)[2] <- "preferred.name"
-call.list$day <- as.Date(call.list$timestamp)
+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,]
-call.counts <- data.frame(table(call.list$discord.name))
-colnames(call.counts) <- c("discord.name", "num.calls")
+## show the distribution of assessments
+prop.table(table(call.list$assessment))
-d <- merge(d, call.counts, all.x=TRUE, all.y=TRUE, by="discord.name"); d
+call.counts <- data.frame(table(call.list$unique.name))
+colnames(call.counts) <- c("unique.name", "num.calls")
-## set anything that's missing to zero
-d$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$day <- rep(as.Date(tmp[[1]][1]), nrow(d.out))
- return(d.out)
-}
+## create list of folks who are missing in class w/o reporting it
+absence.data.cols <- c("unique.name", "date.absent", "reported")
-attendance <- do.call("rbind",
- lapply(list.files(".", pattern="^attendance-.*tsv$"),
- file.to.attendance.list))
+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)
-## 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$answered),
- c("discord.name", "day")]
+################################################
+## LOAD absence data TSV data
+################################################
-missing.in.class <- unique(missing.in.class)
+absence.google <- read.delim("optout_poll_data.tsv")
+colnames(absence.google) <- c("timestamp", "unique.name", "date.absent")
+absence.google$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)
-setDT(attendance)
-setkey(attendance, discord.name, day)
-setDT(missing.in.class)
-setkey(missing.in.class, discord.name, day)
+## combine the two absence lists and then create a unique subset
+absence <- rbind(missing.in.class[,absence.data.cols],
+ absence.google[,absence.data.cols])
-## drop presence for people on missing days
-attendance[missing.in.class,]
-attendance <- as.data.frame(attendance[!missing.in.class,])
+## 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]),]
-attendance.counts <- data.frame(table(attendance$discord.name))
-colnames(attendance.counts) <- c("discord.name", "num.present")
+## print total questions asked and absences
+absence.count <- data.frame(table(unique(absence[,c("unique.name", "date.absent")])[,"unique.name"]))
+colnames(absence.count) <- c("unique.name", "absences")
-d <- merge(d, attendance.counts,
- all.x=TRUE, all.y=TRUE,
- by="discord.name")
-days.list <- lapply(unique(attendance$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))
- })
-})
+## 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")
-days.tmp <- do.call("rbind", lapply(days.list, function (x) do.call("rbind", x)))
+## 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)
-days.tbl <- tapply(days.tmp$days.present, days.tmp$discord.name, sum)
+d
-attendance.days <- data.frame(discord.name=names(days.tbl),
- days.present=days.tbl,
- days.absent=length(list.files(".", pattern="^attendance-.*tsv$"))-days.tbl)
+## set anything that's missing to zero
+d$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$num.calls, decreasing=TRUE),]
-d <- merge(d, attendance.days,
- all.x=TRUE, all.y=TRUE, by="discord.name")
+################################################
+## build visualizations
+################################################
-d[sort.list(d$days.absent), c("discord.name", "num.calls", "days.absent")]
-## make some visualizations of whose here/not here
-#######################################################
+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=800, height=600)
+png("questions_absence_histogram_combined.png", units="px", width=600, height=400)
ggplot(d) +
- aes(x=as.factor(num.calls), fill=days.absent, group=days.absent) +
+ aes(x=as.factor(num.calls), fill=as.factor(absences)) +
geom_bar(color="black") +
- scale_x_discrete("Number of questions asked") +
+ stat_count() +
+ scale_x_discrete("Number of questions answered") +
scale_y_continuous("Number of students") +
- scale_fill_continuous("Days absent", low="red", high="blue")+
+ ##scale_fill_brewer("Absences", palette="Blues") +
+ scale_fill_manual("Opt-outs", values=color.gradient) +
theme_bw()
dev.off()
-png("questions_absenses_boxplots.png", units="px", width=800, height=600)
+absence.labeller <- function (df) {
+ lapply(df, function (x) { paste("Absences:", x) })
+}
-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")
+## png("questions_absence_histogram_facets.png", units="px", width=600, height=400)
-dev.off()
+## 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")
projects / coldcallbot-discord.git / blobdiff