X-Git-Url: https://code.communitydata.science/coldcallbot-discord.git/blobdiff_plain/a59b6b86ffa275cfa425210a9e6b5e3007c7b518..f7270293f2febd56d1570fef67085223d5d91d33:/assessment_and_tracking/track_participation.R

diff --git a/assessment_and_tracking/track_participation.R b/assessment_and_tracking/track_participation.R
index c2b1ef9..71d3256 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("../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
@@ -96,23 +98,19 @@ 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)
+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) +
+    scale_fill_manual("Opt-outs", values=color.gradient) +
     theme_bw()
 
-## dev.off()
+dev.off()
 
 absence.labeller <- function (df) {
     lapply(df, function (x) { paste("Absences:", x) })
@@ -120,12 +118,12 @@ 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 asked as of 2020-02-12") +
-    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")