This page documents and implements the data processing workflow for bootcamp registration.
We load some packages into memory for convenience.
suppressPackageStartupMessages(library('tidyverse'))
suppressPackageStartupMessages(library('ggplot2'))
suppressPackageStartupMessages(library('dplyr'))
suppressPackageStartupMessages(library('tidyr'))
suppressPackageStartupMessages(library('stringr'))
suppressPackageStartupMessages(library('lubridate'))The Google Form generates a Google Sheet that we download to a protected directory (include/csv) that is not synched to GitHub.
This is because the sheet contains personally identifying information.
if (!dir.exists(params$csv_dir)) {
message("Creating missing `include/csv/`.")
dir.create(params$csv_dir)
}
options(gargle_oauth_email = Sys.getenv("GMAIL_SURVEY"))
googledrive::drive_auth()
googledrive::drive_download(
params$sheets_fn,
path = file.path(params$csv_dir, "registrations-2025.csv"),
type = "csv",
overwrite = TRUE
)We reimport the saved CSV file and then clean it.
registrations <- readr::read_csv(file.path(params$csv_dir, "registrations-2025.csv"),
show_col_types = FALSE)
names(registrations) [1] "Timestamp"
[2] "Email Address"
[3] "Which days of the bootcamp will you attend?"
[4] "What is your name?"
[5] "What is your department or unit?"
[6] "What is your current position?"
[7] "Any comments?"
[8] "Are you interested in registering for the 2.5 day bootcamp or the Keynote address(es)?"
[9] "Which Keynote address(es) are you interested in attending?"
[10] "presenter" Google Forms conveniently returns the questions as variable names at the top of each column. These are handy for creating a data dictionary, but awkward for data processing. We rename these for our convenience. We also export a data dictionary.
reqistrations_qs <- names(registrations)
registrations_clean <- registrations |>
dplyr::rename(
timestamp = "Timestamp",
attend_days = "Which days of the bootcamp will you attend?",
name = "What is your name?",
psu_email = "Email Address",
dept = "What is your department or unit?",
position = "What is your current position?",
comments = "Any comments?",
bootcamp_keynote = "Are you interested in registering for the 2.5 day bootcamp or the Keynote address(es)?",
which_keynotes = "Which Keynote address(es) are you interested in attending?"
)
registrations_short <- c(
"timestamp",
"psu_email",
"attend_days",
"name",
"dept",
"position",
"bootcamp_keynote",
"which_keynotes",
"comments",
"presenter"
)
registrations_pid <- c(FALSE, FALSE, FALSE, TRUE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE)
registrations_dd <- data.frame(qs = reqistrations_qs, qs_short = registrations_short, pid = registrations_pid)
registrations_dd |>
knitr::kable(format = 'html')
readr::write_csv(registrations_dd,
file = file.path(params$csv_dir, "registrations-2025-data-dict.csv"))| qs | qs_short | pid |
|---|---|---|
| Timestamp | timestamp | FALSE |
| Email Address | psu_email | FALSE |
| Which days of the bootcamp will you attend? | attend_days | FALSE |
| What is your name? | name | TRUE |
| What is your department or unit? | dept | FALSE |
| What is your current position? | position | FALSE |
| Any comments? | bootcamp_keynote | FALSE |
| Are you interested in registering for the 2.5 day bootcamp or the Keynote address(es)? | which_keynotes | FALSE |
| Which Keynote address(es) are you interested in attending? | comments | FALSE |
| presenter | presenter | FALSE |
We eliminate duplicate registrations.
gilmore_dup <- registrations_clean$timestamp != "6/20/2025 9:36:33" & registrations_clean$name == "Rick Gilmore"
eyal_dup <- registrations_clean$name == "Eyal Ben-Yehuda" & registrations_clean$psu_email == "eyalby@psu.edu"
registrations_clean <- registrations_clean |>
dplyr::filter(!gilmore_dup | !eyal_dup) |>
dplyr::mutate(timestamp = lubridate::mdy_hms(timestamp, tz = "America/New_York"))registrations_yes <- registrations_clean |>
dplyr::mutate(registered = TRUE)
keynotes_only <- registrations_clean |>
dplyr::mutate(keynotes = stringr::str_detect(string = bootcamp_keynote, pattern = "address"))As of 2025-07-31, we have n=89 registered attendees and presenters. That is 118.7% of our target registration/attendance limit of n=75.
Of these, n=2 plan to attend a keynote talk, n=20 are presenting, and n=67 plan to attend one or more sessions.
registrations_clean |>
dplyr::arrange(timestamp) |>
dplyr::mutate(resp_index = seq_along(timestamp)) |>
ggplot() +
aes(x = timestamp, y = resp_index) +
geom_point() +
geom_line() +
# facet_grid(~ registered) +
theme(axis.text.x = element_text(angle = 90)) +
labs(x = NULL, y = 'n registrations') +
# ylim(0, 45) +
scale_color_manual(breaks = c("No", "Yes"),
values=c("red", "green")) +
theme(legend.position = "none")
registrations_clean |>
dplyr::mutate(plan_wed = stringr::str_detect(attend_days, "Wed"),
plan_thu = stringr::str_detect(attend_days, "Thu"),
plan_fri = stringr::str_detect(attend_days, "Fri")) |>
dplyr::mutate(n_wed = sum(plan_wed, na.rm = TRUE),
n_thu = sum(plan_thu, na.rm = TRUE),
n_fri = sum(plan_fri, na.rm = TRUE)) |>
dplyr::select(n_wed, n_thu, n_fri) |>
dplyr::distinct() |>
knitr::kable(format = "html") |>
kableExtra::kable_classic()| n_wed | n_thu | n_fri |
|---|---|---|
| 74 | 78 | 67 |
Bootcamp registrations by day.
registrations_yes |>
dplyr::filter(!is.na(position)) |>
dplyr::count(position) |>
dplyr::arrange(n) |>
dplyr::mutate(position = factor(position, levels = position)) |>
ggplot() +
aes(x = position, fill = position) +
geom_bar(aes(y = n), stat = "identity") +
theme(legend.position = "none") +
coord_flip()
registrations_yes <- registrations_yes |>
dplyr::mutate(
dept = dplyr::recode(
dept,
`Clinical Psychology` = "Psychology",
`Psychology (Cognitive)` = "Psychology",
`Psychology / SSRI` = "Psychology",
`Department of Psychology` = "Psychology",
`Cognitive Psychology` = "Psychology",
`Psychology, Developmental` = "Psychology",
`Developmental Psychology (CAT Lab)` = "Psychology",
`Developmental Psychology` = "Psychology",
`Psych` = "Psychology",
`English language` = "English",
`english` = "English",
`English Language Teaching` = "English",
`English Department` = "English",
`Languages` = "Global Languages & Literatures",
`Languages and Literature` = "Global Languages & Literatures",
`Department of Foreign Languages` = "Global Languages & Literatures",
`Linguistics` = "Applied Linguistics",
`Department of Sociology and Criminology` = "Sociology & Criminology",
`Communication Sciences and Disorders` = "Communication Sciences & Disorders",
`CSD` = "Communication Sciences & Disorders",
`Human Development and Family Studies & Social Data Analytics` = "HDFS",
`Human Development and Family Studies` = "HDFS",
`Human Development and Family Studies (HDFS)` = "HDFS",
`Department of Human Development and Family Studies` = "HDFS",
`Human Development and Family Sciences` = "HDFS",
`HDFS/DEMO` = "HDFS",
`bbh` = "BBH",
`Biobehavioral Health` = "BBH",
`Biobehavioural Health` = "BBH",
`Biobehavioural Health` = "BBH",
`RPTM` = "Recreation, Park, & Tourism Management",
`Sociology and Social Data Analytics` = "Sociology",
`Spanish Italian and portuguese` = "Spanish, Italian, & Portuguese",
`Spanish, Italian, and Portuguese Department` = "Spanish, Italian, & Portuguese",
`Spanish Italian and Portuguese` = "Spanish, Italian, & Portuguese",
`Spanish, Italian, and Portuguese` = "Spanish, Italian, & Portuguese",
`DEMOG` = "Demography",
`Nutrition` = "Nutritional Sciences",
`College of IST` = "IST",
`Statistics Department` = "Statistics",
`Department of Statistics` = "Statistics",
`Math` = "Mathematics",
`Astronomy and Astrophysics` = "Astronomy & Astrophysics",
`Recreation, Park and Tourism Management` = "Recreation, Park, & Tourism Management",
`SHS` = "Student Health Svcs",
`Department of Chemical Engineering` = "Chemical Engineering",
`ESM` = "Engineering Science & Mechanics",
`Engineering Science` = "Engineering Science & Mechanics",
`Engineering Science and Mechanics` = "Engineering Science & Mechanics",
`EECS` = "Electrical Engineering & Comp Sci",
`Department of Food Science` = "Food Science",
`Libraries` = "University Libraries",
`University libraries` = "University Libraries",
`Ecosystem Science and Management` = "Ecosystem Science & Management",
`PRC` = "Population Research Center",
`TLT, PSU Libraries` = "University Libraries",
`Business and Economics` = "Business & Economics"
)
) |>
dplyr::mutate(
college = case_match(
dept,
"Statistics" ~ "ECoS",
"University of Kansas, Psychology" ~ "UKansas",
"Biology" ~ "ECoS",
"Psychology" ~ "CLA",
"Spanish, Italian, & Portuguese" ~ "CLA",
"Research Informatics and Publishing" ~ "Libraries",
"Political Science" ~ "CLA",
"Applied Linguistics" ~ "CLA",
"Global Languages & Literatures" ~ "CLA",
"Anthropology" ~ "CLA",
"Sociology" ~ "CLA",
"English" ~ "CLA",
"C-SoDA" ~ "CLA",
"Office of Digital Pedagogies and Initiatives" ~ "CLA",
"Asian Studies" ~ "CLA",
"Sociology & Criminology" ~ "CLA",
"IST" ~ "IST",
"Chemical Engineering" ~ "Engineering",
"Material Science and Engineering" ~ "Engineering",
"Engineering Science & Mechanics" ~ "Engineering",
"College of Engineering" ~ "Engineering",
"Biomedical Engineering" ~ "Engineering",
"Nutritional Sciences" ~ "HHD",
"HDFS" ~ "HHD",
"Kinesiology" ~ "HHD",
"Recreation, Park, & Tourism Management" ~ "HHD",
"BBH" ~ "HHD",
"College of Nursing" ~ "Nursing",
"Bellisario College of Communication" ~ "Comm",
"Mass Communications" ~ "Comm",
"Marketing" ~ "Smeal",
"Food Science" ~ "Ag",
"Neuroscience" ~ "Med",
"College of Human and Health Development" ~ "HHD",
"University Libraries" ~ "Libraries",
"ICDS" ~ "ICDS",
"EESI" ~ "EESI",
"ORP" ~ "OVPR",
"Astronomy & Astrophysics" ~ "ECoS",
"Chemistry" ~ "ECoS",
"Mathematics" ~ "ECoS",
"Entomology" ~ "AgSci",
"Ecosystem Science & Management" ~ "AgSci",
"Plant Biology" ~ "Huck",
"Biotechnology" ~ "Huck",
"Acoustics" ~ "Engineering",
"Communication Sciences & Disorders" ~ "HHD",
"Electrical Engineering & Comp Sci" ~ "Engineering",
"Population Research Center" ~ "SSRI",
"Psychology (Harrisburg)" ~ "PSU Harrisburg",
"Business & Economics" ~ "PSU Brandywine",
"Engineering" ~ "Engineering",
"LPS/LDT" ~ "Education",
"Demography" ~ "CLA",
"OVPR" ~ "OVPR"
),
.default = "Unknown",
.missing = "Unknown"
)registrations_yes |>
dplyr::filter(!is.na(dept),
dept != "University of Pennsylvania") |>
dplyr::count(dept, college, sort = TRUE) |>
dplyr::mutate(dept = fct_reorder(dept, n)) |>
ggplot() +
aes(x = dept, fill = college) +
geom_bar(aes(y = n), stat = "identity") +
scale_y_continuous(breaks = c(2, 4, 6, 8, 10, 12)) +
theme(legend.position = "right") +
theme(legend.title = element_blank()) +
coord_flip()
The bootcamp registrations represent n=40 departments and n=19 campuses, colleges, institutes, or administrative entities.