From: Benjamin Mako Hill <mako@atdot.cc>
Date: Wed, 5 Jan 2022 04:52:27 +0000 (+0900)
Subject: Merge branch 'master' of code.communitydata.science:coldcallbot-discord
X-Git-Url: https://code.communitydata.science/coldcallbot-discord.git/commitdiff_plain/92e65de7715056ee39c923e1d51fb8c777e64afd?hp=d77f32f5c1deaa19c4ebb5ac931a7f7844a46368

Merge branch 'master' of code.communitydata.science:coldcallbot-discord
---

diff --git a/README b/README
index 611926e..733a2e8 100644
--- a/README
+++ b/README
@@ -1,7 +1,7 @@
 Setting up the Discord Bot
 ======================================
 
-I run the Discord boy from my laptop. It requires the discord Python
+I run the Discord bot from my laptop. It requires the discord Python
 module available in PyPi and installable like:
 
     $ pip3 install discord
@@ -44,7 +44,7 @@ Daily Process
 
 You need to start the bot from the laptop each day. I do that by:
 
-  $ ./coldcallboy.py
+  $ ./coldcallbot.py
 
 The bot will run in the terminal, print out data as it works including
 detailed weights as it goes, and it will record data into files in the
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_enrolled.R b/assessment_and_tracking/track_enrolled.R
index 563384d..f0d0fcb 100644
--- a/assessment_and_tracking/track_enrolled.R
+++ b/assessment_and_tracking/track_enrolled.R
@@ -1,4 +1,4 @@
-myuw <- read.csv("myuw-COM_482_A_autumn_2020_students.csv")
+myuw <- read.csv("myuw-COMMLD_570_A_spring_2021_students.csv")
 gs <- read.delim("student_information.tsv")
 
 ## these are students who dropped the class (should be empty)
@@ -10,14 +10,14 @@ myuw[!myuw$StudentNo %in% gs$Your.UW.student.number,]
 ## read all the folks who have been called and see who is missing from
 ## the google sheet
 
-call.list <- unlist(lapply(list.files(".", pattern="^attendance-.*tsv$"), function (x) {
-    d <- read.delim(x)
-    strsplit(d[[2]], ",")
-})
-)
-present <- unique(call.list)
-present[!present %in% gs[["Your.username.on.the.class.Discord.server"]]]
+## call.list <- unlist(lapply(list.files(".", pattern="^attendance-.*tsv$"), function (x) {
+##    d <- read.delim(x)
+##    strsplit(d[[2]], ",")
+## })
+## )
+## present <- unique(call.list)
+## present[!present %in% gs[["Your.username.on.the.class.Discord.server"]]]
 
 ## and never attended class..
-gs[["Your.username.on.the.class.Discord.server"]][!gs[["Your.username.on.the.class.Discord.server"]] %in% present]
+## gs[["Your.username.on.the.class.Discord.server"]][!gs[["Your.username.on.the.class.Discord.server"]] %in% present]
 
diff --git a/assessment_and_tracking/track_participation.R b/assessment_and_tracking/track_participation.R
index 9a51084..28b8a4e 100644
--- a/assessment_and_tracking/track_participation.R
+++ b/assessment_and_tracking/track_participation.R
@@ -1,109 +1,25 @@
+setwd("~/online_communities/coldcallbot/data/")
+
 library(ggplot2)
 library(data.table)
 
 gs <- read.delim("student_information.tsv")
-d <- gs[,c(2,5)]
-colnames(d) <- c("student.num", "discord.name")
+d <- gs[,c(2,4)]
+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]}))
 
-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))
 
-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$discord.name))
-colnames(call.counts) <- c("discord.name", "num.calls")
-
-d <- merge(d, call.counts, all.x=TRUE, all.y=TRUE, by="discord.name"); d
-
-## set anything that's missing to zero
-d$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
 
diff --git a/coldcall.py b/coldcall.py
index 1905844..1ba96a5 100644
--- a/coldcall.py
+++ b/coldcall.py
@@ -8,19 +8,21 @@ from csv import DictReader
 
 import os.path
 import re
-import discord
 
 class ColdCall():
-    def __init__ (self):
+    def __init__ (self, record_attendance=True):
         self.today = str(datetime.date(datetime.now()))
         # how much less likely should it be that a student is called upon?
-        self.weight = 2 
+        self.weight = 2
+        self.record_attendance = record_attendance
 
         # filenames
         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_names = self.__get_preferred_names()
+        
     def __load_prev_questions(self):
         previous_questions = defaultdict(int)
 
@@ -29,21 +31,24 @@ class ColdCall():
                 with open(f"./data/{fn}", 'r') as f:
                     for row in DictReader(f, delimiter="\t"):
                         if not row["answered"] == "FALSE":
-                            previous_questions[row["discord_name"]] += 1
+                            previous_questions[row["unique_name"]] += 1
 
         return previous_questions
-    
-    def __get_preferred_name(self, selected_student):
-        # translate the discord name into the preferred students name,
-        # if possible, otherwise return the discord name
+
+    def __get_preferred_names(self):
+        # translate the unique name into the preferred students name,
+        # if possible, otherwise return the unique name
 
         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 Discord server"]] = row["Name you'd like to go by in class"]
+                preferred_names[row["Your username on the class Teams server"]] = row["Name you'd like to go by in class"]
 
-        if selected_student in preferred_names:
-            return preferred_names[selected_student]
+        return(preferred_names)
+        
+    def __get_preferred_name(self, selected_student):
+        if selected_student in self.preferred_names:
+            return self.preferred_names[selected_student]
         else:
             return None
 
@@ -59,7 +64,7 @@ class ColdCall():
                 weights[s] = weights[s] / self.weight
 
         # choose one student from the weighted list
-        print(weights)
+        # print(weights) # DEBUG LINE
         return choices(list(weights.keys()), weights=list(weights.values()), k=1)[0]
 
     def __record_attendance(self, students_present):
@@ -78,7 +83,7 @@ class ColdCall():
         # 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:
-                print("\t".join(["discord_name", "timestamp", "answered", "assessment"]), file=f)
+                print("\t".join(["unique_name", "timestamp", "answered", "assessment"]), file=f)
 
         # open for appending the student
         with open(self.__fn_daily_calllist, "a") as f:
@@ -89,7 +94,8 @@ class ColdCall():
         selected_student = self.__select_student_from_list(students_present)
 
         # record the called-upon student in the right place
-        self.__record_attendance(students_present)
+        if self.record_attendance:
+            self.__record_attendance(students_present)
         self.__record_coldcall(selected_student)
 
         preferred_name = self.__get_preferred_name(selected_student)
@@ -100,7 +106,7 @@ class ColdCall():
         return coldcall_message
 
 # cc = ColdCall()
- 
+
 # test_student_list = ["jordan", "Kristen Larrick", "Madison Heisterman", "Maria.Au20", "Laura (Alia) Levi", "Leona Aklipi", "anne", "emmaaitelli", "ashleylee", "allie_partridge", "Tiana_Cole", "Hamin", "Ella Qu", "Shizuka", "Ben Baird", "Kim Do", "Isaacm24", "Sam Bell", "Courtneylg"]
 # print(cc.coldcall(test_student_list))
 
diff --git a/coldcallbot-manual.py b/coldcallbot-manual.py
new file mode 100755
index 0000000..a4268ea
--- /dev/null
+++ b/coldcallbot-manual.py
@@ -0,0 +1,15 @@
+#!/usr/bin/env python3
+
+from coldcall import ColdCall
+import re
+
+## create the coldcall object
+cc = ColdCall(record_attendance=False)
+
+student_list = cc.preferred_names
+
+# print out 100 students
+
+for i in range(100):
+    print(f"{i + 1}. {cc.coldcall(student_list)} [ ] [ ]\n")
+
diff --git a/data/download_data.sh b/data/download_data.sh
new file mode 100755
index 0000000..8687509
--- /dev/null
+++ b/data/download_data.sh
@@ -0,0 +1,4 @@
+#!/bin/bash
+
+wget 'https://docs.google.com/spreadsheets/d/FIXME/export?gid=FIXME&format=tsv' -O 'student_information.tsv'
+