From 89c5369ad9bbefda1053caa99b9dca4e06f18f28 Mon Sep 17 00:00:00 2001
From: Benjamin Mako Hill <mako@atdot.cc>
Date: Wed, 5 Jan 2022 17:52:29 +0900
Subject: [PATCH 01/16] work to build a much better manual version of the
 script

one thing that is clear to me is that the preferred name logic should
really be removed entirely from the coldcall.py program and moved into
the coldcall.py file. I'm currently ignoring that functionality in the
coldcallbot-manual.py but I haven't yet fully removed it from the other.
---
 coldcall.py           | 22 ++++++++++++--------
 coldcallbot-manual.py | 48 ++++++++++++++++++++++++++++++++++++++-----
 2 files changed, 56 insertions(+), 14 deletions(-)

diff --git a/coldcall.py b/coldcall.py
index 1ba96a5..cc5504b 100644
--- a/coldcall.py
+++ b/coldcall.py
@@ -10,7 +10,7 @@ import os.path
 import re
 
 class ColdCall():
-    def __init__ (self, record_attendance=True):
+    def __init__ (self, record_attendance=True, preferred_name_field=None):
         self.today = str(datetime.date(datetime.now()))
         # how much less likely should it be that a student is called upon?
         self.weight = 2
@@ -20,8 +20,12 @@ class ColdCall():
         self.__fn_studentinfo = "data/student_information.tsv"
         self.__fn_daily_calllist = f"data/call_list-{self.today}.tsv"
         self.__fn_daily_attendance = f"data/attendance-{self.today}.tsv"
+        self.__preferred_name_field = preferred_name_field
 
-        self.preferred_names = self.__get_preferred_names()
+        if preferred_name_field != None:
+            self.preferred_names = self.__get_preferred_names()
+        else:
+            self.preferred_names = None
         
     def __load_prev_questions(self):
         previous_questions = defaultdict(int)
@@ -42,7 +46,7 @@ class ColdCall():
         preferred_names = {}
         with open(self.__fn_studentinfo, 'r') as f:
             for row in DictReader(f, delimiter="\t"):
-                preferred_names[row["Your username on the class Teams server"]] = row["Name you'd like to go by in class"]
+                row["Your UW student number"] = row[self.__preferred_name_field]
 
         return(preferred_names)
         
@@ -52,7 +56,7 @@ 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
@@ -67,7 +71,7 @@ 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:
@@ -79,7 +83,7 @@ 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:
@@ -91,12 +95,12 @@ class ColdCall():
                              "MISSING", "MISSING"]), 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)
 
-- 
2.39.5


From b30b0b6c68999107f92b2ae73c0d6b73b7c8b289 Mon Sep 17 00:00:00 2001
From: Benjamin Mako Hill <mako@atdot.cc>
Date: Wed, 5 Jan 2022 17:59:46 +0900
Subject: [PATCH 02/16] updated enrollment tracking code (just filenames)

---
 assessment_and_tracking/track_enrolled.R | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

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,]
-- 
2.39.5


From a59b6b86ffa275cfa425210a9e6b5e3007c7b518 Mon Sep 17 00:00:00 2001
From: Benjamin Mako Hill <mako@atdot.cc>
Date: Sun, 23 Jan 2022 17:16:36 -0800
Subject: [PATCH 03/16] updated track participation code to see how we're doing

---
 assessment_and_tracking/track_participation.R | 118 +++++++++++++++++-
 1 file changed, 112 insertions(+), 6 deletions(-)

diff --git a/assessment_and_tracking/track_participation.R b/assessment_and_tracking/track_participation.R
index 28b8a4e..c2b1ef9 100644
--- a/assessment_and_tracking/track_participation.R
+++ b/assessment_and_tracking/track_participation.R
@@ -1,25 +1,131 @@
 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)
+
+ggplot(data=d) +
+    aes(x=as.factor(num.calls), y=absences) +
+    geom_violin()
+
+## 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 asked") +
+    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 asked as of 2020-02-12") +
+    scale_y_continuous("Number of students") +
+    theme_bw() +
+    facet_wrap(.~absences, ncol=5, labeller="absence.labeller")
 
-- 
2.39.5


From 0738f9791a7f0ae2bc03869edf060d035b2dd0b6 Mon Sep 17 00:00:00 2001
From: Benjamin Mako Hill <mako@atdot.cc>
Date: Mon, 24 Jan 2022 18:53:04 -0800
Subject: [PATCH 04/16] clean up the plots being generated

---
 assessment_and_tracking/track_participation.R | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/assessment_and_tracking/track_participation.R b/assessment_and_tracking/track_participation.R
index c2b1ef9..4381b78 100644
--- a/assessment_and_tracking/track_participation.R
+++ b/assessment_and_tracking/track_participation.R
@@ -96,17 +96,13 @@ color.gradient <- scales::seq_gradient_pal("yellow", "magenta", "Lab")(seq(0,1,l
 
 table(d$num.calls, d$absences)
 
-ggplot(data=d) +
-    aes(x=as.factor(num.calls), y=absences) +
-    geom_violin()
-
 ## 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 asked") +
+    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) +
@@ -124,7 +120,7 @@ ggplot(d) +
     aes(x=as.factor(num.calls)) +
     geom_bar() +
     stat_count() +
-    scale_x_discrete("Number of questions asked as of 2020-02-12") +
+    scale_x_discrete("Number of questions answered") +
     scale_y_continuous("Number of students") +
     theme_bw() +
     facet_wrap(.~absences, ncol=5, labeller="absence.labeller")
-- 
2.39.5


From 35bf83e9f6168af66d16196bf6b455954acaa3e6 Mon Sep 17 00:00:00 2001
From: Benjamin Mako Hill <mako@atdot.cc>
Date: Wed, 9 Feb 2022 18:57:09 -0800
Subject: [PATCH 05/16] generate better imges

---
 assessment_and_tracking/track_participation.R | 20 +++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/assessment_and_tracking/track_participation.R b/assessment_and_tracking/track_participation.R
index 4381b78..37898e7 100644
--- a/assessment_and_tracking/track_participation.R
+++ b/assessment_and_tracking/track_participation.R
@@ -96,7 +96,7 @@ color.gradient <- scales::seq_gradient_pal("yellow", "magenta", "Lab")(seq(0,1,l
 
 table(d$num.calls, d$absences)
 
-## png("questions_absence_histogram_combined.png", units="px", width=600, height=400)
+png("questions_absence_histogram_combined.png", units="px", width=600, height=400)
 
 ggplot(d) +
     aes(x=as.factor(num.calls), fill=as.factor(absences)) +
@@ -108,7 +108,7 @@ ggplot(d) +
     scale_fill_manual("Absences", values=color.gradient) +
     theme_bw()
 
-## dev.off()
+dev.off()
 
 absence.labeller <- function (df) {
     lapply(df, function (x) { paste("Absences:", x) })
@@ -116,12 +116,12 @@ absence.labeller <- function (df) {
 
 ## 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")
+## 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")
 
-- 
2.39.5


From 78ac188f0487ba413244246181ad90b9a73451d8 Mon Sep 17 00:00:00 2001
From: Benjamin Mako Hill <mako@atdot.cc>
Date: Sat, 5 Mar 2022 20:51:15 -0800
Subject: [PATCH 06/16] code to create final case discussion grades

This still needs to be check over but this is new code to build the
final grades. Current threshold for minimum questions comes from 1000
simulated classes (simulation.R).
---
 .../compute_final_case_grades.R               | 135 ++++++++++++++----
 assessment_and_tracking/simulation.R          |  24 ++++
 .../student_report_template.Rmd               |  15 +-
 3 files changed, 135 insertions(+), 39 deletions(-)
 create mode 100644 assessment_and_tracking/simulation.R

diff --git a/assessment_and_tracking/compute_final_case_grades.R b/assessment_and_tracking/compute_final_case_grades.R
index b26270b..22dae47 100644
--- a/assessment_and_tracking/compute_final_case_grades.R
+++ b/assessment_and_tracking/compute_final_case_grades.R
@@ -1,72 +1,147 @@
 ## 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))
+question.grades <- c("PLUS"=100, "CHECK"=100-(50/3.3), "MINUS"=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")
+## inspect set the absence threashold
+ggplot(d) + aes(x=absences) + geom_histogram(binwidth=1, fill="white",color="black")
+## absence.threshold <- median(d$absences)
+absence.threshold <- 4 ## TODO talk about this
 
-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
+## first these are the people were were not called simply because they got unlucky
+
+ ## 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
 ##########################################################
+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
+
+## apply the penality for number of days we called on them and they were gone
+d$part.grade <- d$base.grade - d$missing.in.class.days * missed.question.penalty
+d$part.grade.orig <- d$part.grade
+
+## first we handle the zeros
+## step 1: first double check the people who have zeros and ensure that they didn't "just" get unlucky"
+d[d$num.calls == 0,]
+
+## set those people to 0 :(
+d[d$num.calls == 0]
+d$part.grade[d$num.calls == 0] <- 0
 
-d[as.character(tmp$unique.name), "part.grade"] <- tmp$part.grade
+## step 2: identify the people who were were not asked "enough" questions but were unlucky/lucky
+## penalized.unique.names <- d$unique.name[d$num.calls < median(d$num.calls) & d$absences > median(d$absences)]
 
-## generate the baseline participation grades as per the process above
+## first these are the people were were not called simply because they got unlucky
+d[d$num.calls < questions.cutoff & d$absences < absence.threshold,]
 
+## first these are the people were were not called simply because they got unlucky
+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"] <- ((
+    (questions.cutoff - d[as.character(penalized.unique.names),"num.calls"] * 0) +
+    (d[as.character(penalized.unique.names),"num.calls"] * d[as.character(penalized.unique.names),"part.grade"]) )
+    / questions.cutoff)
+
+d[as.character(penalized.unique.names),]
+
+## 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 / (50/3.3)) - 2.6, 2)
+d$part.4point <- round((d$part.grade / (50/3.3)) - 2.6, 2)
 
-d[sort.list(d$part.4point),]
+d[sort.list(d$part.4point, decreasing=TRUE),
+  c("unique.name", "short.name", "num.calls", "absences", "part.4point")]
 
 
-## writing out data
+## 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.
 
 
 
-- 
2.39.5


From a50468cac2f57d05f7c6a4066e34f82b02fa2693 Mon Sep 17 00:00:00 2001
From: Benjamin Mako Hill <mako@atdot.cc>
Date: Sat, 5 Mar 2022 22:48:40 -0800
Subject: [PATCH 07/16] fix an ordering bug with grade creation

---
 .../compute_final_case_grades.R               | 50 ++++++++++---------
 1 file changed, 26 insertions(+), 24 deletions(-)

diff --git a/assessment_and_tracking/compute_final_case_grades.R b/assessment_and_tracking/compute_final_case_grades.R
index 22dae47..1c25538 100644
--- a/assessment_and_tracking/compute_final_case_grades.R
+++ b/assessment_and_tracking/compute_final_case_grades.R
@@ -10,21 +10,20 @@ rownames(d) <- d$unique.name
 call.list$timestamp <- as.Date(call.list$timestamp)
 
 ## class-level variables
-question.grades <- c("PLUS"=100, "CHECK"=100-(50/3.3), "MINUS"=100-(50/(3.3)*2))
-missed.question.penalty <- (50/3.3) * 0.2 ## 1/5 of a full point on the GPA scale
+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
 
 ## inspect set the absence threashold
 ggplot(d) + aes(x=absences) + geom_histogram(binwidth=1, fill="white",color="black")
-## absence.threshold <- median(d$absences)
-absence.threshold <- 4 ## TODO talk about this
+absence.threshold <- median(d$absences)
+
 
 ## 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
-## first these are the people were were not called simply because they got unlucky
-
- ## this is the 95% percentile based on simulation in simulation.R
+## this is the 95% percentile based on simulation in simulation.R
 questions.cutoff <- 4
 
 ## show the distribution of assessments
@@ -36,8 +35,11 @@ prop.table(table(call.list.full$answered))
 
 total.questions.asked <- nrow(call.list)
 
-## find out how man questions folks have present/absent for
-##########################################################
+## 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)))
 
@@ -67,7 +69,7 @@ d$prop.asked.quant <- cut(d$prop.asked, right=FALSE, breaks=c(prop.asks.quantile
     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
@@ -92,45 +94,44 @@ gen.part.grade <- function (x.unique.name) {
 tmp <- do.call("rbind", lapply(d$unique.name, gen.part.grade))
 d <- merge(d, tmp)
 rownames(d) <- d$unique.name
-
-## apply the penality for number of days we called on them and they were gone
-d$part.grade <- d$base.grade - d$missing.in.class.days * missed.question.penalty
-d$part.grade.orig <- d$part.grade
+d$part.grade <- d$base.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,]
 
 ## set those people to 0 :(
-d[d$num.calls == 0]
 d$part.grade[d$num.calls == 0] <- 0
 
-## step 2: identify the people who were were not asked "enough" questions but were unlucky/lucky
-## penalized.unique.names <- d$unique.name[d$num.calls < median(d$num.calls) & d$absences > median(d$absences)]
+## step 2: identify the people who were were not asked "enough"
+## questions but were unlucky/lucky
 
-## first these are the people were were not called simply because they got unlucky
+## 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,]
 
-## first these are the people were were not called simply because they got unlucky
+## 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"] <- ((
-    (questions.cutoff - d[as.character(penalized.unique.names),"num.calls"] * 0) +
-    (d[as.character(penalized.unique.names),"num.calls"] * d[as.character(penalized.unique.names),"part.grade"]) )
+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[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$missing.in.class.days * missed.question.penalty
+
 ## TODO ensure this is right. i think it is
 ## map part grades back to 4.0 letter scale and points
-d$part.4point <- round((d$part.grade / (50/3.3)) - 2.6, 2)
+d$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="unique.name", by.y="StudentNo")
@@ -145,3 +146,4 @@ for (id in d$unique.name) {
                              d.print$unique.name[d.print$unique.name == id],
                              sep=""))
 }
+k
-- 
2.39.5


From e7c79c1644a5f8bdaf10b98578117653b0d97e36 Mon Sep 17 00:00:00 2001
From: Benjamin Mako Hill <mako@atdot.cc>
Date: Sat, 12 Mar 2022 19:13:18 -0800
Subject: [PATCH 08/16] minor changes to finalize case grades

---
 assessment_and_tracking/compute_final_case_grades.R | 1 -
 1 file changed, 1 deletion(-)

diff --git a/assessment_and_tracking/compute_final_case_grades.R b/assessment_and_tracking/compute_final_case_grades.R
index 1c25538..93d6d1f 100644
--- a/assessment_and_tracking/compute_final_case_grades.R
+++ b/assessment_and_tracking/compute_final_case_grades.R
@@ -146,4 +146,3 @@ for (id in d$unique.name) {
                              d.print$unique.name[d.print$unique.name == id],
                              sep=""))
 }
-k
-- 
2.39.5


From 56fb61e8b00a0cde7cde1138c3f49b89b302e773 Mon Sep 17 00:00:00 2001
From: Benjamin Mako Hill <mako@atdot.cc>
Date: Sat, 28 Sep 2024 17:34:48 -0700
Subject: [PATCH 09/16] many new changes for the new quarter

- switched to using a configuration.json file
- reworked the download_student_info.py to fix bugs
- substantial change to the scripts to use the new config structure
- other small changes
- wrote a new README file based on the old readme and material I sent
  to Matt McGarrity
---
 README_daily             | 127 +++++++++++++++++++++++++++++++++++++++
 coldcall.py              |  10 ++-
 coldcallbot-manual.py    |  26 ++++----
 configuration.json       |  16 +++++
 download_student_info.py |   4 +-
 5 files changed, 165 insertions(+), 18 deletions(-)
 create mode 100644 README_daily
 create mode 100644 configuration.json

diff --git a/README_daily b/README_daily
new file mode 100644
index 0000000..ea666b9
--- /dev/null
+++ b/README_daily
@@ -0,0 +1,127 @@
+I keep my entire data directory in git and I'd recommend that you do
+too. Just make sure you don't commit and publish student records into
+the public git repository. I usually just keep a separate branch for
+classes.
+
+Daily Process
+================================
+
+1. Open your terminal (on Windows, this will likely be powershell in anaconda)
+
+2. Change into the directory with the coldcall scripts.
+
+3. Download new data with: `python download_student_info.py`
+
+   This will download the latest version of absence data into `data/optout_poll_data.tsv` as well as th student information into `data/student_information.tsv`.
+
+   If you noticed any changes you need to make (e.g., the same preferred names, incorrectly entered absences, etc) you should edit the Google sheets and then running the download again with the same script.
+
+4. When you're ready, fun the main script in the same directory: python coldcallbot-manual.py
+   
+   This will both:
+   
+   - output a paper list in terminal. I often redirect this to a file like: `python coldcallbot-manual.py > data/paper_call_list-2024-09-26.txt` or similar.
+   - Create the computed call list in the `data/` folder
+
+During case, I take notes on student answers on paper during class (typically I
+only note down non "GOOD" answers) and then add these to the sheet
+immediately after class.
+
+After class each day, you need to open up "call_list-YYYY-MM-DD.tsv"
+and edit the two columns in which you store the results of the
+case. The first columns `answered` means that the person responded and
+answered the question (i.e., they were present in the room but away
+from their computer and unresponsive). This is almost always TRUE but
+would be FALSE if the student were missing.
+
+The assessment column should be is "GOOD", "SATISFACTORY", "POOR", "NO
+MEANINGFUL ANSWER" or "ABSENT" but you can do whatever makes sense in
+this and we can work with it when it comes to grading. Just make sure
+you are consistent!
+
+Details on my rubric is here:
+
+https://wiki.communitydata.science/User:Benjamin_Mako_Hill/Assessment#Rubric_for_case_discussion_answers
+
+
+Assessment and Tracking
+======================================
+
+These scripts rely on a file in this repository called
+`data/student_information.csv` which I have set to be downloaded
+automatically from a Google form using the download script.
+
+I don't expect that these will necessary work without
+modification. It's a good idea to go line-by-line through these to
+make sure they are doing what *you* want and that you agree with the
+assessment logic built into this.
+
+For reference, that file has the following column labels (this is the
+full header, in order):
+
+    Timestamp
+    Your UW student number
+    Name you'd like to go by in class
+    Your Wikipedia username
+    Your username on the class Discord server
+    Preferred pronouns
+    Anything else you'd like me to know?
+
+The scripts in this directory are meant to be run or sourced *from*
+the data directory. As in:
+
+    $ cd ../data
+    $ R --no-save < ../assessment_and_tracking/track_participation.R
+
+There are three files in that directory:
+
+track_enrolled.R:
+
+    This file keeps track of who is in Discord, who is enrolled for
+    the class, etc. This helps me remove people from the
+    student_informaiton.csv spreadsheet who are have dropped the
+    class, deal with users who change their Discord name, and other
+    things that the scripts can't deal with automatically.
+
+    This all need to be dealt with manually, one way or
+    another. Sometimes by modifying the script, sometimes by modifying
+    the files in the data/ directory.
+
+    This requires an additional file called
+    `myuw-COM_482_A_autumn_2020_students.csv` which is just the saved
+    CSV from https://my.uw.edu which includes the full class list. I
+    download this one manually.
+
+track_participation.R:
+
+    This file generates histograms and other basic information about
+    the distribution of participation and absences. I've typically run
+    this weekly after a few weeks of the class and share these images
+    with students at least once or twice in the quarter.
+
+    This file is also sourced by compute_final_case_grades.R.
+
+compute_final_case_grades.R:
+
+    You can find a narrative summary of my assessment process here:
+
+    https://wiki.communitydata.science/User:Benjamin_Mako_Hill/Assessment#Overall_case_discussion_grade
+
+    This also requires the registration file (something like
+    `myuw-COM_482_A_autumn_2020_students.csv`) which is described
+    above.
+
+    To run this script, you will need to create the following subdirectories:
+
+    data/case_grades
+    data/case_grades/student_reports
+
+
+One final note: A bunch of things in these scripts assumes a UW 4.0
+grade scale. I don't think it should be hard to map these onto some
+other scale, but that's an exercise I'll leave up to those that want
+to do this.
+
+   
+ 5. after class, update the call list in the data folder to remove lines for any call that didn't happen (or you don't want to count) and update the assessments:
+ 
diff --git a/coldcall.py b/coldcall.py
index 37b4eb5..3fb79d6 100644
--- a/coldcall.py
+++ b/coldcall.py
@@ -16,6 +16,7 @@ class ColdCall():
             config = json.loads(config_file.read())
 
         self.today = str(datetime.date(datetime.now()))
+
         # how much less likely should it be that a student is called upon?
         self.weight = 2
         self.record_attendance = record_attendance
@@ -43,7 +44,7 @@ class ColdCall():
 
         return previous_questions
 
-    def __get_preferred_names(self):
+    def get_preferred_names(self):
         # translate the unique name into the preferred students name,
         # if possible, otherwise return the unique name
 
@@ -55,8 +56,9 @@ class ColdCall():
         return(preferred_names)
         
     def __get_preferred_name(self, selected_student):
-        if selected_student in self.preferred_names:
-            return self.preferred_names[selected_student]
+        preferred_names = self.get_preferred_names()
+        if selected_student in preferred_names:
+            return preferred_names[selected_student]
         else:
             return None
 
@@ -94,6 +96,8 @@ class ColdCall():
                 print("\t".join([self.unique_row, self.preferred_row, "answered", "assessment", "timestamp"]), file=f)
 
         preferred_name = self.__get_preferred_name(selected_student)
+        if preferred_name == None:
+            preferred_name = ""
 
         # open for appending the student
         with open(self.__fn_daily_calllist, "a") as f:
diff --git a/coldcallbot-manual.py b/coldcallbot-manual.py
index 6c128ba..75a88dc 100755
--- a/coldcallbot-manual.py
+++ b/coldcallbot-manual.py
@@ -3,39 +3,39 @@
 from coldcall import ColdCall
 from datetime import datetime
 from csv import DictReader
+import json
 
 current_time = datetime.today()
+with open("configuration.json") as config_file:
+    config = json.loads(config_file.read())
 
 ## create the coldcall object
-cc = ColdCall(record_attendance=False, preferred_name_field="Name you'd like to go by in class")
+cc = ColdCall(record_attendance=False)
 
 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:
+    with open(config["optout_file"], '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"])
+                yield(row[config["unique_name_rowname"]])
 
 full_names = {}
 registered_students = []
-with open("data/2022_winter_COM_481_A_students.csv", 'r') as f:
+with open(config["roster_file"], '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)
+        full_names[student_no] = f"{row[config['roster_firstname_rowname']]} {row[config['roster_lastname_rowname']]}"
+# print("Registered:", registered_students) # useful for debug
 
 missing_today = [x for x in get_missing(current_time)]
-## print("Missing Today: ", missing_today)
+# print("Missing Today: ", missing_today)  # useful for debug
 
-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)
+preferred_names = cc.get_preferred_names()
+# print("Preferred names:", preferred_names)  # useful for debug
 
 students_present = [s for s in registered_students if s not in missing_today]
-## print("Students present:", students_present)
+# print("Students present:", students_present)  # useful for debug
 
 for i in range(100):
     selected_student = cc.select_student_from_list(students_present)
diff --git a/configuration.json b/configuration.json
new file mode 100644
index 0000000..4ea79ab
--- /dev/null
+++ b/configuration.json
@@ -0,0 +1,16 @@
+{ 
+    "roster_file" : "data/FIXME.csv",
+    "roster_unique_rowname" : "StudentNo",
+    "roster_firstname_rowname" : "FirstName",
+    "roster_lastname_rowname" : "LastName",
+    "student_info_file" : "data/student_information.tsv",
+    "student_info_gsheet_id" : "FIXME",
+    "student_info_gsheet_gid" : 99999999,
+    "optout_file" : "data/optout_poll_data.tsv",
+    "optout_gsheet_id" : "FIXME",
+    "optout_gsheet_gid" : 99999999,
+    "daily_calllist_file" : "data/call_list-{date}.tsv",
+    "daily_attendance" : "data/attendance-{date}.tsv",
+    "unique_name_rowname" : "Your UW student number", 
+    "preferred_name_rowname" : "Name you'd like to go by in class"
+}
diff --git a/download_student_info.py b/download_student_info.py
index 0b6a98f..8a448b9 100755
--- a/download_student_info.py
+++ b/download_student_info.py
@@ -9,7 +9,7 @@ with open("configuration.json", 'r') as config_file:
 base_url = 'https://docs.google.com/spreadsheets/d/{id}/export?gid={gid}&format=tsv'
 
 student_info_url = base_url.format(id=config["student_info_gsheet_id"], gid=config["student_info_gsheet_gid"])
-subprocess.run(["wget", url, "-O", config["student_info_file"]], check=True)
+subprocess.run(["wget", student_info_url, "-O", config["student_info_file"]], check=True)
 
-optout_url = base_url.format(id=config["optout_info_gsheet_id"], gid=config["output_info_gsheet_gid"])
+optout_url = base_url.format(id=config["optout_gsheet_id"], gid=config["optout_gsheet_gid"])
 subprocess.run(["wget", optout_url, "-O", config["optout_file"]], check=True)
-- 
2.39.5


From 360a7e8ee059d7060c373abb453e29dba8cfc015 Mon Sep 17 00:00:00 2001
From: Benjamin Mako Hill <mako@atdot.cc>
Date: Sat, 28 Sep 2024 20:10:18 -0700
Subject: [PATCH 10/16] updated code to better figure out whose not registered

---
 assessment_and_tracking/track_enrolled.R | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/assessment_and_tracking/track_enrolled.R b/assessment_and_tracking/track_enrolled.R
index 47e50c2..06e4aba 100644
--- a/assessment_and_tracking/track_enrolled.R
+++ b/assessment_and_tracking/track_enrolled.R
@@ -1,5 +1,5 @@
-myuw <- read.csv("../data/2022_winter_COM_481_A_students.csv")
-gs <- read.delim("../data/student_information.tsv")
+myuw <- read.csv("data/2024_autumn_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,]
@@ -7,6 +7,12 @@ gs[!gs$Your.UW.student.number %in% myuw$StudentNo,]
 ## these are students who are in the class but didn't reply to the form
 myuw[!myuw$StudentNo %in% gs$Your.UW.student.number,]
 
+roster.merged <- merge(myuw, gs, by.x="StudentNo", by.y="Your.UW.student.number", all.x=TRUE, all.y=FALSE)
+
+roster.merged[,c("StudentNo", "Email", "FirstName", "LastName", "Your.username.on.the.class.Discord.server",  "checked.off.on.discord")][!roster.merged$StudentNo %in% gs$Your.UW.student.number,]
+## these are students who are in the class but didn't reply to the form
+
+
 ## read all the folks who have been called and see who is missing from
 ## the google sheet
 
-- 
2.39.5


From 3845559ac8f2298e30679c75edf78cdc26a90f38 Mon Sep 17 00:00:00 2001
From: Benjamin Mako Hill <mako@atdot.cc>
Date: Sat, 28 Sep 2024 20:10:44 -0700
Subject: [PATCH 11/16] print preferred pronouns in the call list

---
 coldcallbot-manual.py | 20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/coldcallbot-manual.py b/coldcallbot-manual.py
index 75a88dc..ac46bc1 100755
--- a/coldcallbot-manual.py
+++ b/coldcallbot-manual.py
@@ -28,6 +28,13 @@ with open(config["roster_file"], 'r') as f:
         full_names[student_no] = f"{row[config['roster_firstname_rowname']]} {row[config['roster_lastname_rowname']]}"
 # print("Registered:", registered_students) # useful for debug
 
+# get pronouns
+with open(config["student_info_file"], 'r') as f:
+    preferred_pronouns = {}
+    for row in DictReader(f, delimiter="\t"):
+        preferred_pronouns[row[config["unique_name_rowname"]]] = row["Preferred pronouns"]
+print(preferred_pronouns)
+
 missing_today = [x for x in get_missing(current_time)]
 # print("Missing Today: ", missing_today)  # useful for debug
 
@@ -43,11 +50,14 @@ for i in range(100):
     try:
         preferred_name = preferred_names[selected_student]
     except KeyError:
-        preferred_name = "MISSING PREFERRED NAME"
+        preferred_name = "[unknown preferred name]"
+
+    if selected_student in preferred_pronouns:
+        pronouns = preferred_pronouns[selected_student]
+    else:
+        pronouns = "[unknown pronouns]"
+    
+    print(f"{i + 1}. {preferred_name} :: {pronouns} :: {full_names[selected_student]} :: {selected_student}")
 
-    print(f"{i + 1}.",
-          preferred_name, "::",
-          selected_student, "::",
-          full_names[selected_student])
     cc.record_coldcall(selected_student)
 
-- 
2.39.5


From 499ed62bce2e13aaf3e4395931b4683d05fcb473 Mon Sep 17 00:00:00 2001
From: Benjamin Mako Hill <mako@atdot.cc>
Date: Fri, 4 Oct 2024 11:00:26 -0700
Subject: [PATCH 12/16] removed print debug line

---
 coldcallbot-manual.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/coldcallbot-manual.py b/coldcallbot-manual.py
index ac46bc1..61c2010 100755
--- a/coldcallbot-manual.py
+++ b/coldcallbot-manual.py
@@ -33,7 +33,7 @@ with open(config["student_info_file"], 'r') as f:
     preferred_pronouns = {}
     for row in DictReader(f, delimiter="\t"):
         preferred_pronouns[row[config["unique_name_rowname"]]] = row["Preferred pronouns"]
-print(preferred_pronouns)
+# print(preferred_pronouns)
 
 missing_today = [x for x in get_missing(current_time)]
 # print("Missing Today: ", missing_today)  # useful for debug
-- 
2.39.5


From da93d3fd56f78a67c1f109f4c72f3fcf35fbc102 Mon Sep 17 00:00:00 2001
From: Benjamin Mako Hill <mako@atdot.cc>
Date: Mon, 7 Oct 2024 20:54:49 -0700
Subject: [PATCH 13/16] updated assessment code for new class

- fix a few bugs related to make scripts work with no students have been fully
  missing
- other smaller code fixes, path updates, etc
---
 assessment_and_tracking/track_participation.R | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/assessment_and_tracking/track_participation.R b/assessment_and_tracking/track_participation.R
index 37898e7..8b9f368 100644
--- a/assessment_and_tracking/track_participation.R
+++ b/assessment_and_tracking/track_participation.R
@@ -1,4 +1,4 @@
-setwd("~/online_communities/coldcallbot/data/")
+setwd("~/online_communities/coldcall_scripts-COM481-2024Q4/data/")
 
 library(data.table)
 
@@ -6,9 +6,11 @@ library(data.table)
 ## LOAD call_list TSV data
 ################################################
 
-call.list <- do.call("rbind", lapply(list.files(".", pattern="^call_list-.*tsv$"), function (x) {read.delim(x, stringsAsFactors=FALSE)[,1:4]}))
+call.list <- do.call("rbind", lapply(list.files(".", pattern="^call_list-.*tsv$"), function (x) {read.delim(x, stringsAsFactors=FALSE)[,1:5]}))
 
 colnames(call.list) <- gsub("_", ".", colnames(call.list))
+colnames(call.list)[1] <- "unique.name"
+colnames(call.list)[2] <- "preferred.name"
 
 table(call.list$unique.name[call.list$answered])
 
@@ -29,7 +31,7 @@ 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$reported <- rep(FALSE, nrow(missing.in.class))
 missing.in.class <- missing.in.class[,absence.data.cols]
 missing.in.class <- unique(missing.in.class)
 
@@ -37,7 +39,7 @@ missing.in.class <- unique(missing.in.class)
 ## LOAD absence data TSV data
 ################################################
 
-absence.google <- read.delim("absence_poll_data.tsv")
+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
-- 
2.39.5


From 1103b95c378b2904c4b72b260bbaa46429a15b70 Mon Sep 17 00:00:00 2001
From: Benjamin Mako Hill <mako@atdot.cc>
Date: Wed, 16 Oct 2024 16:29:48 -0700
Subject: [PATCH 14/16] changed from absenses to opt-out since that matches
 syllabus

---
 assessment_and_tracking/track_participation.R | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/assessment_and_tracking/track_participation.R b/assessment_and_tracking/track_participation.R
index 8b9f368..b8b6e1c 100644
--- a/assessment_and_tracking/track_participation.R
+++ b/assessment_and_tracking/track_participation.R
@@ -107,7 +107,7 @@ ggplot(d) +
     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) +
+    scale_fill_manual("Opt-outs", values=color.gradient) +
     theme_bw()
 
 dev.off()
-- 
2.39.5


From 44868248dba6471a1180c3f1c6b51ef5af91091a Mon Sep 17 00:00:00 2001
From: Benjamin Mako Hill <mako@atdot.cc>
Date: Tue, 22 Oct 2024 17:11:42 -0700
Subject: [PATCH 15/16] change to relative path which will work for all future
 classes

---
 assessment_and_tracking/track_participation.R | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/assessment_and_tracking/track_participation.R b/assessment_and_tracking/track_participation.R
index b8b6e1c..71d3256 100644
--- a/assessment_and_tracking/track_participation.R
+++ b/assessment_and_tracking/track_participation.R
@@ -1,4 +1,4 @@
-setwd("~/online_communities/coldcall_scripts-COM481-2024Q4/data/")
+setwd("../data/")
 
 library(data.table)
 
-- 
2.39.5


From f7270293f2febd56d1570fef67085223d5d91d33 Mon Sep 17 00:00:00 2001
From: Benjamin Mako Hill <mako@atdot.cc>
Date: Sun, 27 Oct 2024 15:59:14 -0700
Subject: [PATCH 16/16] updated cold call script to do a pure shuffle

- this will just just produce the students present for the day, in random order
---
 coldcallbot-manual.py | 39 +++++++++++++++++++++++++++++++++++----
 1 file changed, 35 insertions(+), 4 deletions(-)

diff --git a/coldcallbot-manual.py b/coldcallbot-manual.py
index 61c2010..985ada0 100755
--- a/coldcallbot-manual.py
+++ b/coldcallbot-manual.py
@@ -3,7 +3,19 @@
 from coldcall import ColdCall
 from datetime import datetime
 from csv import DictReader
+from random import sample
 import json
+import argparse
+
+parser = argparse.ArgumentParser(description='run the coldcall bot manually to create a coldcall list')
+
+parser.add_argument('-n', '--num', dest="num_calls", default=100, const=100, type=int, nargs='?',
+                    help="how many students should be called")
+
+parser.add_argument('-s', '--shuffle', dest="shuffle_roster", action="store_true",
+                    help="select without replacement (i.e., call each person once with n equal to the group size)")
+
+args = parser.parse_args()
 
 current_time = datetime.today()
 with open("configuration.json") as config_file:
@@ -44,8 +56,12 @@ preferred_names = cc.get_preferred_names()
 students_present = [s for s in registered_students if s not in missing_today]
 # print("Students present:", students_present)  # useful for debug
 
-for i in range(100):
-    selected_student = cc.select_student_from_list(students_present)
+def print_selected(selected_student):
+    if "print_index" in globals():
+        global print_index
+    else:
+        global print_index
+        print_index = 1
 
     try:
         preferred_name = preferred_names[selected_student]
@@ -56,8 +72,23 @@ for i in range(100):
         pronouns = preferred_pronouns[selected_student]
     else:
         pronouns = "[unknown pronouns]"
-    
-    print(f"{i + 1}. {preferred_name} :: {pronouns} :: {full_names[selected_student]} :: {selected_student}")
+
+    print(f"{print_index}. {preferred_name} :: {pronouns} :: {full_names[selected_student]} :: {selected_student}")
 
     cc.record_coldcall(selected_student)
+    print_index += 1 ## increase the index
+
+# if we're in suffle mode
+shuffle = args.shuffle_roster
+
+print_index = 1
+
+if shuffle:
+    for selected_student in sample(students_present, len(students_present)):
+        print_selected(selected_student)
+else:
+    num_calls = args.num_calls
 
+    for i in range(num_calls):
+        selected_student = cc.select_student_from_list(students_present)
+        print_selected(selected_student)
-- 
2.39.5