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'))
suppressPackageStartupMessages(library('janitor'))The Google Form generates a Google Sheet that we download to a protected directory (private/csv) that is not synched to GitHub.
This is because the sheet contains personally identifying information.
To implement this, we add private to our .gitignore file in the project’s root directory. This omits all files in private/ from version control and keeps them local to the machine we render the site from.
x <- assertthat::is.string(params$csv_dir)
if (!dir.exists(params$csv_dir)) {
message("Creating missing `include/csv/`.")
dir.create(params$csv_dir)
}
x <- assertthat::is.writeable(params$csv_dir)
# options(gargle_oauth_email = Sys.getenv("GMAIL_SURVEY"))
# googledrive::drive_auth()
x <- assertthat::is.string(params$psu_id)
googlesheets4::gs4_auth(email = params$psu_id)
x <- assertthat::is.string(params$sheets_id)
registrations <- googlesheets4::read_sheet(params$reg_sheets_id,
sheet = "Form Responses 1")
x <- assertthat::assert_that(is_tibble(registrations))
registration_full_fn <- file.path(params$csv_dir, params$registration_fn)
x <- assertthat::is.string(registration_full_fn)
readr::write_csv(registrations, file = registration_full_fn)Download presenter data, too.
presenters <- googlesheets4::read_sheet(params$reg_sheets_id,
sheet = "presenters")
x <- assertthat::assert_that(is_tibble(presenters))
x <- assertthat::is.string(params$presenters_fn)
presenters_full_fn <- file.path(params$csv_dir, params$presenters_fn)
readr::write_csv(presenters, file = presenters_full_fn)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.
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?",
email = "Email Address",
dept = "What is your department or unit?",
position = "What is your current position?",
comments = "Any comments?",
dropped_out = "drop-out"
)
registrations_short <- c(
"timestamp",
"email",
"attend_days",
"name",
"dept",
"position",
"comments",
"dropped_out"
)We also export a data dictionary.
registrations_pid <- c(FALSE, FALSE, FALSE, TRUE, FALSE, FALSE, FALSE, FALSE)
registrations_dd <- data.frame(qs = reqistrations_qs,
qs_short = registrations_short,
pid = registrations_pid)
registrations_dd |>
knitr::kable(format = 'html')| qs | qs_short | pid |
|---|---|---|
| Timestamp | timestamp | FALSE |
| Email Address | 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? | comments | FALSE |
| drop-out | dropped_out | FALSE |
data_dict_fn <- file.path(params$csv_dir, "registrations-2026-data-dict.csv")
x <- assertthat::is.string(data_dict_fn)
readr::write_csv(registrations_dd,
file = data_dict_fn)We drop some of responses that were used to test the workflow or who are presenters.
registrations_clean <- registrations_clean |>
dplyr::filter(email != "nittany.amateur.radio.club@gmail.com")
registrations_clean <- registrations_clean |>
dplyr::filter(name != "Koraly Pérez-Edgar") |>
dplyr::filter(name != "Carrie Brown")
registrations_clean <- registrations_clean |>
dplyr::mutate(name = if_else(name == "Maria A Sanchez Farran", "Maria Sanchez Farran", name))We normalize the dropped_out variable.
registrations_clean <- registrations_clean |>
dplyr::mutate(dropped_out = if_else(is.na(dropped_out), FALSE, TRUE))And normalize the presenter names.
presenters_clean <- janitor::clean_names(presenters)attendees_names <- registrations_clean$name
presenter_names <- presenters$nameWarning: Unknown or uninitialised column: `name`.all_names <- unique(c(attendees_names, presenter_names))
n_all <- length(all_names)
n_drop_outs <- sum(registrations_clean$dropped_out)As of 2026-05-12, we have n=91 registered attendees. We also have n=0 presenters. A handful of presenters also registered. Some people registered twice, and n = 9 have had to cancel, so we have n=76 unique attendees who plan to come.
That is 101.3% of our target registration/attendance target of n=75.
registrations_clean |>
dplyr::arrange(timestamp) |>
dplyr::mutate(resp_index = seq_along(timestamp)) |>
ggplot() +
aes(x = timestamp, y = resp_index) +
geom_point() +
geom_line() +
theme(axis.text.x = element_text(angle = 90)) +
labs(x = NULL, y = 'n registrations') +
theme(legend.position = "none")
registrations_clean |>
dplyr::filter(!is.na(position)) |>
dplyr::count(position, sort = TRUE) |>
dplyr::mutate(position = fct_reorder(position, n)) |>
ggplot() +
geom_bar(aes(x = position, y = n), fill = "#96BEE6", stat = "identity") +
scale_y_continuous(breaks = seq(0, 50, by = 5)) +
theme(legend.position = "right") +
theme(legend.title = element_blank()) +
xlab("") +
theme_classic() +
coord_flip()
Clean and recode.
select_this <- registrations_clean$name == "Parisa Osfoori"
registrations_clean$dept[select_this] <- "Communication Sciences & Disorders"
select_this <- registrations_clean$name == "Koraly Pérez-Edgar"
registrations_clean$dept[select_this] <- "Psychology"
select_this <- registrations_clean$name== "Keyana Enayati"
registrations_clean$dept[select_this] <- "PSU Harrisburg"Normalize department names; assign college/institute values.
registrations_clean <- registrations_clean |>
dplyr::mutate(
dept = dplyr::recode(
dept,
`Clinical Psychology` = "Psychology",
`Psychology (Cognitive)` = "Psychology",
`Psychology / SSRI` = "Psychology",
`Psychology (Developmental)` = "Psychology",
`Department of Psychology` = "Psychology",
`Cognitive Psychology` = "Psychology",
`Psychology, Developmental` = "Psychology",
`Developmental Psychology (CAT Lab)` = "Psychology",
`Developmental Psychology` = "Psychology",
`Psych` = "Psychology",
`College of Liberal Arts (psychology)` = "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 Arts and Sciences` = "Communication Arts & Sciences",
`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",
`Biobehavioral health` = "BBH",
`RPTM` = "Recreation, Park, & Tourism Management",
`Recreation, Park and Tourism Management` = "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",
`French and Francophone Studies` = "French & Francophone Studies",
`DEMOG` = "Demography",
`Germanic & Slavic Languages & Literatures` = "German & Slavic Languages",
`Germanic and Slavic Languages and Literatures` = "German & Slavic Languages",
`Nutrition` = "Nutritional Sciences",
`Department of Nutritional Sciences` = "Nutritional Sciences",
`Nurition` = "Nutritional Sciences",
`College of IST` = "IST",
`Statistics Department` = "Statistics",
`Department of Statistics` = "Statistics",
`stat` = "Statistics",
`statistic` = "Statistics",
`Math` = "Mathematics",
`Astronomy and Astrophysics` = "Astronomy & Astrophysics",
`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",
`EE` = "Electrical Engineering",
`College of Medicine / Clinical and Translational Science Institute` = "CTSI",
`College of Medicine, CTSI` = "CTSI",
`Mechanical engineering,Penn state Harrisburg` = "Mechanical Engineering (Harrisburg)",
`Smeal College of Business, Accounting` = "Accounting",
`School of Science, Engineering, and Technology` = "Sci, Engr, & Tech",
`institute for Computational and Data Sciences` = "ICDS",
`Plant Pathology and environmental microbiology` = "Plant Pathology & Environmental Microbiology",
`Meteorology and Atmospheric Sciences` = "Meteorology & Atmospheric Sciences",
`Department of Meteorology and Atmospheric Science` = "Meteorology & Atmospheric Sciences",
`School of Labor and Employment Relations` = "School of Labor & Employment Relations",
`PCD` = "Preservation Conservation & Digitization",
`Vazquez Lab/Eberly College of Science/Bio` = "Biology",
`Biology Department/ Vazquez lab` = "Biology",
`WORKFORCE EDUCATION AND DEVELOPMENT` = "Workforce Education & Development",
`Curriculum and Instructions` = "Curriculum & Instruction",
`Kinesiology, HHD` = "Kinesiology",
`BME` = "Biomedical Engineering",
`Computer Science` = "Computer Science & Engineering",
`Department of Computer Science and Engineering` = "Computer Science & Engineering",
`College of Engineering/Computer Science` = "Computer Science & Engineering",
`Ed Policy Studies` = "Education Policy Studies",
`CHE` = "Chemical Engineering",
`Agricultural and Biological Engineering` = "Agricultural & Biological Engineering",
`Mechanical` = "Mechanical Engineering",
`Health Administration` = "Health Policy & Administration",
`CMPEN` = "Computer Engineering",
`ESM/ REI` = "Engineering Science & Mechanics",
`Civil Eng` = "Civil Engineering",
`Meteorology and Atmospheric Science` = "Meteorology & Atmospheric Science",
`Meteorology and Atmospheric Sciences` = "Meteorology & Atmospheric Science",
`Department of Meteorology and Atmospheric Science` = "Meteorology & Atmospheric Science",
`Meteorology & Atmospheric Sciences` = "Meteorology & Atmospheric Science"
)
) |>
dplyr::mutate(
college = recode_values(
dept,
"Agricultural & Biological Engineering" ~ "AgSci",
"Ecosystem Science & Management" ~ "AgSci",
"Entomology" ~ "AgSci",
"Food Science" ~ "AgSci",
"Plant Pathology & Environmental Microbiology" ~ "AgSci",
"Plant Science" ~ "AgSci",
"German & Slavic Languages" ~ "CLA",
"Psychology" ~ "CLA",
"Spanish, Italian, & Portuguese" ~ "CLA",
"Anthropology" ~ "CLA",
"Applied Linguistics" ~ "CLA",
"Asian Studies" ~ "CLA",
"C-SoDA" ~ "CLA",
"Demography" ~ "CLA",
"Communication Arts & Sciences" ~ "CLA",
"Economics" ~ "CLA",
"English" ~ "CLA",
"French & Francophone Studies" ~ "CLA",
"Global Languages & Literatures" ~ "CLA",
"Office of Digital Pedagogies and Initiatives" ~ "CLA",
"Political Science" ~ "CLA",
"Sociology" ~ "CLA",
"Sociology & Criminology" ~ "CLA",
"School of Labor & Employment Relations" ~ "CLA",
"Bellisario College of Communication" ~ "Comm",
"Mass Communications" ~ "Comm",
"Astronomy & Astrophysics" ~ "ECoS",
"Biology" ~ "ECoS",
"Chemistry" ~ "ECoS",
"Integrative Science" ~ "ECoS",
"Mathematics" ~ "ECoS",
"Statistics" ~ "ECoS",
"College of Education" ~ "Education",
"LPS/LDT" ~ "Education",
"Workforce Education & Development" ~ "Education",
"Curriculum & Instruction" ~ "Education",
"Education Policy Studies" ~ "Education",
"Meteorology & Atmospheric Science" ~ "EMS",
"Meteorology & Atmospheric Sciences" ~ "EMS",
"Acoustics" ~ "Engineering",
"Biomedical Engineering" ~ "Engineering",
"Chemical Engineering" ~ "Engineering",
"Chemical/Biomedical Engineering" ~ "Engineering",
"Civil Engineering" ~ "Engineering",
"College of Engineering" ~ "Engineering",
"Computer Engineering" ~ "Engineering",
"Computer Science & Engineering" ~ "Engineering",
"Electrical Engineering & Comp Sci" ~ "Engineering",
"Electrical Engineering" ~ "Engineering",
"Engineering" ~ "Engineering",
"Engineering Science & Mechanics" ~ "Engineering",
"Material Science and Engineering" ~ "Engineering",
"Mechanical Engineering" ~ "Engineering",
"College of Human and Health Development" ~ "HHD",
"Communication Sciences & Disorders" ~ "HHD",
"BBH" ~ "HHD",
"HDFS" ~ "HHD",
"Kinesiology" ~ "HHD",
"Nutritional Sciences" ~ "HHD",
"Recreation, Park, & Tourism Management" ~ "HHD",
"HHD" ~ "HHD",
"Health Policy & Administration" ~ "HHD",
"Biotechnology" ~ "Huck",
"Plant Biology" ~ "Huck",
"ICDS" ~ "ICDS",
"IST" ~ "IST",
"Data Analytics" ~ "IST",
"Cybersecurity" ~ "IST",
"Information Science and Technology" ~ "IST",
"Preservation Conservation & Digitization" ~ "Libraries",
"Research Informatics and Publishing" ~ "Libraries",
"University Libraries" ~ "Libraries",
"Neuroscience" ~ "Medicine",
"Medicine" ~ "Medicine",
"CTSI" ~ "Medicine",
"College of Nursing" ~ "Nursing",
"EESI" ~ "EESI",
"Psychology (Harrisburg)" ~ "PSU Harrisburg",
"PSU Harrisburg" ~ "PSU Harrisburg",
"Mechanical Engineering (Harrisburg)" ~ "PSU Harrisburg",
"PSU Harrisburg" ~ "PSU Harrisburg",
"Sci, Engr, & Tech" ~ "PSU Harrisburg",
"Business & Economics" ~ "PSU Brandywine",
"Schreyer Institute for Teaching Excellence" ~ "Old Main",
"OVPR" ~ "OVPR",
"ORP" ~ "OVPR",
"Population Research Center" ~ "SSRI",
"Accounting" ~ "Smeal",
"Marketing" ~ "Smeal",
"University of Kansas, Psychology" ~ "UKansas"
),
.default = "Unknown",
.missing = "Unknown"
)Plot.
registrations_clean |>
dplyr::filter(!is.na(college)) |>
dplyr::count(college, sort = TRUE) |>
dplyr::mutate(college = fct_reorder(college, n)) |>
ggplot() +
geom_bar(aes(x = college, y = n), fill = "#BF8226", stat = "identity") +
scale_y_continuous(breaks = seq(2, 24, by = 2)) +
theme(legend.position = "right") +
theme(legend.title = element_blank()) +
xlab("") +
theme_classic() +
coord_flip()
The bootcamp registrations represent n=45 departments and n=14 campuses, colleges, institutes, or administrative entities.
readr::write_csv(registrations_clean, file.path(params$csv_dir, "registrations-2026-clean.csv"))
readr::write_csv(presenters_clean, file.path(params$csv_dir, "presenters-2026-clean.csv"))