From: Benjamin Mako Hill Date: Sat, 28 Sep 2024 23:27:12 +0000 (-0700) Subject: Merge branch 'COM481-2024Q4' X-Git-Url: https://code.communitydata.science/coldcallbot-discord.git/commitdiff_plain/d6b74612e3a2f01112fa14c6c86bec9c20093ed3?hp=3c9c64edc856e6c8656614b5106b1f3f67704621 Merge branch 'COM481-2024Q4' --- 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$unique.name == id], + sep="")) +} diff --git a/assessment_and_tracking/simulation.R b/assessment_and_tracking/simulation.R new file mode 100644 index 0000000..7134bef --- /dev/null +++ b/assessment_and_tracking/simulation.R @@ -0,0 +1,24 @@ +weight.fac <- 2 +num.calls <- 373 +num.students <- 76 + +gen.calls.per.students <- function (x) { + raw.weights <<- rep(1, num.students) + names(raw.weights) <- seq(1, num.students) + + table(sapply(1:num.calls, function (i) { + probs <- raw.weights / sum(raw.weights) + selected <- sample(names(raw.weights), 1, prob=probs) + ## update the raw.weights + raw.weights[selected] <<- raw.weights[selected] / weight.fac + #print(raw.weights) + return(selected) + })) +} + + +simulated.call.list <- unlist(lapply(1:1000, gen.calls.per.students)) +hist(simulated.call.list) + +quantile(simulated.call.list, probs=seq(0,1,by=0.01)) +quantile(simulated.call.list, probs=0.05) diff --git a/assessment_and_tracking/student_report_template.Rmd b/assessment_and_tracking/student_report_template.Rmd index a0b2145..866b1e0 100644 --- a/assessment_and_tracking/student_report_template.Rmd +++ b/assessment_and_tracking/student_report_template.Rmd @@ -1,22 +1,19 @@ -**Student Name:** `r paste(d.print[d.print$discord.name == x.discord.name, c("FirstName", "LastName")])` +**Student Name:** `r paste(d.print[d.print$unique.name == id, c("LastName", "FirstName")])` (`r id`) -**Discord Name:** `r d.print[d.print$discord.name == x.discord.name, c("discord.name")]` +**Participation grade:** `r d.print$part.4point[d.print$unique.name == id]` -**Participation grade:** `r d.print$part.4point[d.print$discord.name == x.discord.name]` +**Questions asked:** `r d.print[d$unique.name == id, "num.calls"]` -**Questions asked:** `r d.print[d$discord.name == x.discord.name, "prev.questions"]` +**Days Absent:** `r d.print[d.print$unique.name == id, "absences"]` / `r length(unique(as.Date(unique(call.list$timestamp))))` -**Days Absent:** `r d.print[d.print$discord.name == x.discord.name, "days.absent"]` / `r case.sessions` +**Missing in class days:** `r d.print[d$unique.name == id, "missing.in.class.days"]` (base grade lowered by 0.2 per day) **List of questions:** ```{r echo=FALSE} -call.list[call.list$discord.name == x.discord.name,] +call.list[call.list$unique.name == id,] ``` -**Luckiness:** `r d.print[d.print$discord.name == x.discord.name, "prop.asked.quant"]` - -If you a student has a luckiness over 50% that means that they were helped by the weighting of the system and/or got lucky. We did not penalize *any* students with a luckiness under 50% for absences. diff --git a/assessment_and_tracking/track_enrolled.R b/assessment_and_tracking/track_enrolled.R index f0d0fcb..47e50c2 100644 --- a/assessment_and_tracking/track_enrolled.R +++ b/assessment_and_tracking/track_enrolled.R @@ -1,5 +1,5 @@ -myuw <- read.csv("myuw-COMMLD_570_A_spring_2021_students.csv") -gs <- read.delim("student_information.tsv") +myuw <- read.csv("../data/2022_winter_COM_481_A_students.csv") +gs <- read.delim("../data/student_information.tsv") ## these are students who dropped the class (should be empty) gs[!gs$Your.UW.student.number %in% myuw$StudentNo,] diff --git a/assessment_and_tracking/track_participation.R b/assessment_and_tracking/track_participation.R index 28b8a4e..37898e7 100644 --- a/assessment_and_tracking/track_participation.R +++ b/assessment_and_tracking/track_participation.R @@ -1,25 +1,127 @@ setwd("~/online_communities/coldcallbot/data/") -library(ggplot2) library(data.table) -gs <- read.delim("student_information.tsv") -d <- gs[,c(2,4)] -colnames(d) <- c("student.num", "unique.name") +################################################ +## LOAD call_list TSV data +################################################ call.list <- do.call("rbind", lapply(list.files(".", pattern="^call_list-.*tsv$"), function (x) {read.delim(x, stringsAsFactors=FALSE)[,1:4]})) colnames(call.list) <- gsub("_", ".", colnames(call.list)) -table(call.list$unique_name[call.list$answered]) +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,] +## show the distribution of assessments +prop.table(table(call.list$assessment)) + call.counts <- data.frame(table(call.list$unique.name)) colnames(call.counts) <- c("unique.name", "num.calls") -d <- merge(d, call.counts, all.x=TRUE, all.y=TRUE, by="unique.name"); d +## create list of folks who are missing in class w/o reporting it +absence.data.cols <- c("unique.name", "date.absent", "reported") + +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 <- FALSE +missing.in.class <- missing.in.class[,absence.data.cols] +missing.in.class <- unique(missing.in.class) + +################################################ +## LOAD absence data TSV data +################################################ + +absence.google <- read.delim("absence_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$reported <- TRUE +absence.google <- absence.google[,absence.data.cols] +absence.google <- unique(absence.google) + +## combine the two absence lists and then create a unique subset +absence <- rbind(missing.in.class[,absence.data.cols], + absence.google[,absence.data.cols]) + +## these are people that show up in both lists (i.e., probably they +## submitted too late but it's worth verifying before we penalize +## them. i'd actually remove them from the absence sheet to suppress +## this error +absence[duplicated(absence[,1:2]),] +absence <- absence[!duplicated(absence[,1:2]),] + +## print total questions asked and absences +absence.count <- data.frame(table(unique(absence[,c("unique.name", "date.absent")])[,"unique.name"])) +colnames(absence.count) <- c("unique.name", "absences") + + +## load up the full class list +gs <- read.delim("student_information.tsv") +d <- gs[,c("Your.UW.student.number", "Name.you.d.like.to.go.by.in.class")] +colnames(d) <- c("unique.name", "short.name") + +## merge in the call counts +d <- merge(d, call.counts, all.x=TRUE, all.y=FALSE, by="unique.name") +d <- merge(d, absence.count, by="unique.name", all.x=TRUE, all.y=FALSE) + +d + +## set anything that's missing to zero +d$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$num.calls, decreasing=TRUE),] + +################################################ +## build visualizations +################################################ + + +library(ggplot2) + +color.gradient <- scales::seq_gradient_pal("yellow", "magenta", "Lab")(seq(0,1,length.out=range(d$absences)[2]+1)) + +table(d$num.calls, d$absences) + +png("questions_absence_histogram_combined.png", units="px", width=600, height=400) + +ggplot(d) + + aes(x=as.factor(num.calls), fill=as.factor(absences)) + + geom_bar(color="black") + + stat_count() + + scale_x_discrete("Number of questions answered") + + scale_y_continuous("Number of students") + + ##scale_fill_brewer("Absences", palette="Blues") + + scale_fill_manual("Absences", values=color.gradient) + + theme_bw() + +dev.off() + +absence.labeller <- function (df) { + lapply(df, function (x) { paste("Absences:", x) }) +} + +## png("questions_absence_histogram_facets.png", units="px", width=600, height=400) + +## 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") diff --git a/coldcall.py b/coldcall.py index 2250fac..37b4eb5 100644 --- a/coldcall.py +++ b/coldcall.py @@ -26,9 +26,10 @@ class ColdCall(): self.__fn_daily_attendance = config["daily_attendance"].format(date=self.today) self.unique_row = config["unique_name_rowname"] - self.preferred_row = config["preferred_name_rowname"] - - self.preferred_names = self.__get_preferred_names() + if "preferred_name_rowname" in config: + self.preferred_row = config["preferred_name_rowname"] + else: + self.preferred_row = None def __load_prev_questions(self): previous_questions = defaultdict(int) @@ -59,7 +60,7 @@ class ColdCall(): else: return None - def __select_student_from_list (self, students_present): + def select_student_from_list(self, students_present): prev_questions = self.__load_prev_questions() # created a weighted list by starting out with everybody 1 @@ -74,7 +75,7 @@ class ColdCall(): # print(weights) # DEBUG LINE return choices(list(weights.keys()), weights=list(weights.values()), k=1)[0] - def __record_attendance(self, students_present): + def record_attendance(self, students_present): # if it's the first one of the day, write it out if not os.path.exists(self.__fn_daily_attendance): with open(self.__fn_daily_attendance, "w") as f: @@ -86,7 +87,7 @@ class ColdCall(): ",".join(students_present)]), file=f) - def __record_coldcall(self, selected_student): + def record_coldcall(self, selected_student): # if it's the first one of the day, write it out if not os.path.exists(self.__fn_daily_calllist): with open(self.__fn_daily_calllist, "w") as f: @@ -100,12 +101,12 @@ class ColdCall(): "MISSING", "MISSING", str(datetime.now())]), file=f) def coldcall(self, students_present): - selected_student = self.__select_student_from_list(students_present) + selected_student = self.select_student_from_list(students_present) # record the called-upon student in the right place if self.record_attendance: - self.__record_attendance(students_present) - self.__record_coldcall(selected_student) + self.record_attendance(students_present) + self.record_coldcall(selected_student) preferred_name = self.__get_preferred_name(selected_student) if preferred_name: diff --git a/coldcallbot-manual.py b/coldcallbot-manual.py index a4268ea..6c128ba 100755 --- a/coldcallbot-manual.py +++ b/coldcallbot-manual.py @@ -1,15 +1,53 @@ #!/usr/bin/env python3 from coldcall import ColdCall -import re +from datetime import datetime +from csv import DictReader + +current_time = datetime.today() ## create the coldcall object -cc = ColdCall(record_attendance=False) +cc = ColdCall(record_attendance=False, preferred_name_field="Name you'd like to go by in class") + +def get_missing(d=current_time): + date_string = f'{d.month}/{d.day}/{d.year}' + with open("data/absence_poll_data.tsv", 'r') as f: + for row in DictReader(f, delimiter="\t"): + if row["Date of class session you will be absent"] == date_string: + yield(row["Your UW student number"]) + +full_names = {} +registered_students = [] +with open("data/2022_winter_COM_481_A_students.csv", 'r') as f: + for row in DictReader(f, delimiter=","): + student_no = row["StudentNo"].strip() + registered_students.append(student_no) + full_names[student_no] = f"{row['FirstName']} {row['LastName']}" +## print("Registered:", registered_students) -student_list = cc.preferred_names +missing_today = [x for x in get_missing(current_time)] +## print("Missing Today: ", missing_today) -# print out 100 students +preferred_names = {} +with open("data/student_information.tsv", 'r') as f: + for row in DictReader(f, delimiter="\t"): + preferred_names[row["Your UW student number"]] = row["Name you'd like to go by in class"] +## print("Preferred names:", preferred_names) + +students_present = [s for s in registered_students if s not in missing_today] +## print("Students present:", students_present) for i in range(100): - print(f"{i + 1}. {cc.coldcall(student_list)} [ ] [ ]\n") + selected_student = cc.select_student_from_list(students_present) + + try: + preferred_name = preferred_names[selected_student] + except KeyError: + preferred_name = "MISSING PREFERRED NAME" + + print(f"{i + 1}.", + preferred_name, "::", + selected_student, "::", + full_names[selected_student]) + cc.record_coldcall(selected_student)