source("_common.r")
list.files("funs", full.names = TRUE) |>
purrr::walk(source)
options(digits = 3)
options(tinytable_tt_digits = 2)Challenge 05 – Solution
“Eine Hackathon-Variante zur Evaluation der Klickdaten des KI-Tools ‘HaNS’”
Betrachten Sie dazu die Targets-Datei auf Github.
1 Setup
1.1 Libs
1.2 Other setup
1.3 Load Targets
tar_load(c(data_prepped, time_spent, course_and_uni_per_visit))2 Challenge 6
n_actions_searches_interactions <-
data_prepped |>
select(
idvisit,
fingerprint,
any_of(c(
"searches",
"actions",
"interactions",
"referrertype",
"referrername",
"language",
"devicetype",
"devicemodel",
"operatingsystem",
"browsername"
))
)2.1 Berechnen Sie die Anzahl der Aktionen pro Visit und pro fingerprint
2.1.1 idvisit und fingerprint jeweils unique
n_actions_searches_interactions |>
as.data.frame() |>
summarise(
idvisit_n = length(unique(idvisit)),
fingerprint_n = length(unique(fingerprint)),
actions_mean = mean(as.integer(actions), na.rm = TRUE),
searches_mean = mean(as.integer(searches), na.rm = TRUE)
) |>
gt()| idvisit_n | fingerprint_n | actions_mean | searches_mean |
|---|---|---|---|
| 291 | 127 | 137 | 0.206 |
2.1.2 Actions pro idvisit und pro fingerprint
n_actions_searches_interactions_summarized <-
n_actions_searches_interactions |>
group_by(idvisit) |>
summarise(actions_mean = mean(as.integer(actions), na.rm = TRUE))
n_actions_searches_interactions_summarized |>
gghistostats(x = actions_mean)
https://indrajeetpatil.github.io/ggstatsplot/reference/gghistostats.html
n_actions_searches_interactions_summarized |>
plot_hist_descriptive(actions_mean)
Hinweis
Es gibt etwa doppelt so viele Besucher wie unique Nutzer.
2.2 User Specs
2.2.1 Referrer Type pro Visit
n_actions_searches_interactions |>
count(referrertype, sort = TRUE)2.2.2 Referrer Type Name pro Visit
n_actions_searches_interactions |>
count(referrername, sort = TRUE) |>
knitr::kable()| referrername | n |
|---|---|
| elearning.ohmportal.de | 206 |
| NA | 40 |
| moodle.hswt.de | 30 |
| statics.teams.cdn.office.net | 14 |
| hans.th-nuernberg.de | 1 |
2.2.3 devicemodel
n_actions_searches_interactions |>
count(devicemodel, sort = TRUE) |>
slice_head(n = 10)2.2.4 operatingsystem
n_actions_searches_interactions |>
count(operatingsystem, sort = TRUE) |>
slice_head(n = 10) |>
tinytable::tt()| operatingsystem | n |
|---|---|
| Windows 11 | 94 |
| Mac 10.15 | 76 |
| Windows 10 | 46 |
| iOS 18.5 | 27 |
| Mac 15.5 | 18 |
| Android 15.0 | 14 |
| Android 13.0 | 5 |
| GNU/Linux | 3 |
| iOS 18.1 | 3 |
| Android 14.0 | 1 |
2.2.5 browsername
n_actions_searches_interactions |>
count(browsername, sort = TRUE) |>
slice_head(n = 10) |>
tinytable::tt()| browsername | n |
|---|---|
| Safari | 74 |
| Chrome | 64 |
| Microsoft Edge | 63 |
| Mobile Safari | 27 |
| Opera GX | 21 |
| Chrome Webview | 14 |
| Firefox | 13 |
| Chrome Mobile iOS | 3 |
| Google Search App | 3 |
| Opera | 3 |
Die Mac-User scheinen besonders aktiv zu sein auf HaNS.
2.3 Berechnen Sie die Anzahl der Tage seit dem letzten Besuch (pro Visit und pro uniquen Besucher)
data_prepped |>
select(matches("days")) |>
mutate(across(everything(), ~ as.integer(.))) |>
describe_distribution() |>
tinytable::tt()| Variable | Mean | SD | IQR | Min | Max | Skewness | Kurtosis | n | n_Missing |
|---|---|---|---|---|---|---|---|---|---|
| dayssincefirstvisit | 27.6 | 40 | 54 | 0 | 132 | 1.2 | -0.062 | 291 | 0 |
| dayssincelastvisit | 5.5 | 18 | 0 | 0 | 106 | 4 | 16.294 | 291 | 0 |
data_prepped |>
select(matches("days")) |>
mutate(across(everything(), as.integer)) |>
imap(~ plot_hist_descriptive(tibble(value = .x), var = value, title = .y))
## $dayssincefirstvisit
##
## $dayssincelastvisit
2.4 Anzahl von Unis und Kursen
course_and_uni_per_visit |>
count(university) |>
tinytable::tt()| university | n |
|---|---|
| hnu | 3 |
| hswt | 19 |
| th-nuernberg | 170 |
| NA | 99 |
course_and_uni_per_visit |>
count(university) |>
drop_na() |>
ggplot(aes(y = reorder(university, n), x = n)) +
geom_col() +
theme_minimal() +
labs(
title = "TH Nürnberg hosts the most courses on HaNS by far.",
y = "University"
)
course_and_uni_per_visit |>
distinct(fingerprint, .keep_all = TRUE) |>
count(university) |>
ggplot(aes(y = reorder(university, n), x = n)) +
geom_col() +
theme_minimal() +
labs(
title = "TH Nürnberg hosts the most courses on HaNS by far.",
y = "University"
)
2.5 Berechnen Sie die Anzahl der Tage seit dem letzten Besuch pro Modul/Lehrveranstaltung (pro Visit und pro uniquen Besucher).
Pro idvisit:
course_and_uni_per_visit_dayssincelastvisit <-
course_and_uni_per_visit |>
select(idvisit, course, university) |>
mutate(idvisit = as.integer(idvisit)) |>
left_join(data_prepped |> select(idvisit, dayssincelastvisit), by = "idvisit") |>
mutate(dayssincelastvisit = as.integer(dayssincelastvisit))course_and_uni_per_visit_dayssincelastvisit |>
group_by(course) |>
describe_distribution(dayssincelastvisit) |>
print_md()| course | Variable | Mean | SD | IQR | Range | Skewness | Kurtosis | n | n_Missing |
|---|---|---|---|---|---|---|---|---|---|
| bare | dayssincelastvisit | 28.00 | 27.06 | 54.00 | (0.00, 54.00) | -0.33 | -1.50 | 3 | 0 |
| bio | dayssincelastvisit | 1.50 | 2.12 | 3.00 | (0.00, 3.00) | 0.00 | -2.00 | 2 | 0 |
| cta1 | dayssincelastvisit | 6.84 | 14.19 | 8.00 | (0.00, 58.00) | 2.96 | 9.75 | 19 | 0 |
| fodesoa | dayssincelastvisit | 17.60 | 36.87 | 19.75 | (0.00, 100.00) | 1.91 | 2.30 | 10 | 0 |
| fosaq | dayssincelastvisit | 5.80 | 7.95 | 14.50 | (0.00, 15.00) | 0.62 | -3.28 | 5 | 0 |
| gdi | dayssincelastvisit | 35.33 | 61.20 | 106.00 | (0.00, 106.00) | 1.73 | -1.50 | 3 | 0 |
| gesoa | dayssincelastvisit | 2.86 | 11.32 | 0.00 | (0.00, 99.00) | 5.88 | 40.97 | 142 | 0 |
| nlp | dayssincelastvisit | 0.00 | 0.00 | 0.00 | (0.00, 0.00) | 2 | 0 | ||
| softa | dayssincelastvisit | 1.50 | 1.73 | 3.00 | (0.00, 3.00) | 0.00 | -6.00 | 4 | 0 |
| thesoa | dayssincelastvisit | 0.00 | 0.00 | 0.00 | (0.00, 0.00) | 2 | 0 |
Pro fingerprint: analog.
3 Debrief
3.1 Targets-Objekte
targets::tar_manifest() |>
select(name) |>
#print(n = Inf) |>
knitr::kable()| name |
|---|
| config_file |
| config |
| data_files_list |
| data_files_dupes_excluded |
| data_imported |
| data_prepped |
| data_all_fct |
| test_unique_idvisit |
| data_long |
| data_wide_slim |
| data_separated |
| n_visits |
| course_and_uni_per_visit |
| data_separated_filtered |
| n_action_fingerprint |
| n_action |
| n_action_lt_500_fingerprint |
| n_action_lt_500 |
3.2 Pipeline-Graph
tar_visnetwork(targets_only = TRUE,
outdated = TRUE)tar_glimpse()3.3 sessionInfo
sessioninfo::session_info()
## ─ Session info ───────────────────────────────────────────────────────────────
## setting value
## version R version 4.5.1 (2025-06-13)
## os Ubuntu 25.10
## system x86_64, linux-gnu
## ui X11
## language (EN)
## collate de_DE.UTF-8
## ctype de_DE.UTF-8
## tz Europe/Berlin
## date 2025-12-08
## pandoc 3.6.3 @ /snap/rstudio/25/resources/app/bin/quarto/bin/tools/x86_64/ (via rmarkdown)
## quarto 1.7.32 @ /snap/rstudio/25/resources/app/bin/quarto/bin/quarto
##
## ─ Packages ───────────────────────────────────────────────────────────────────
## package * version date (UTC) lib source
## backports 1.5.0 2024-05-23 [3] CRAN (R 4.4.1)
## base64url 1.4 2018-05-14 [3] CRAN (R 4.0.1)
## BayesFactor 0.9.12-4.7 2024-01-24 [3] CRAN (R 4.3.2)
## bayestestR * 0.17.0 2025-08-29 [1] RSPM (R 4.5.1)
## boot 1.3-31 2024-08-28 [4] CRAN (R 4.4.1)
## callr 3.7.6 2024-03-25 [3] CRAN (R 4.4.0)
## cli 3.6.5 2025-04-23 [1] CRAN (R 4.5.1)
## coda 0.19-4.1 2024-01-31 [1] RSPM
## codetools 0.2-20 2024-03-31 [4] CRAN (R 4.3.3)
## correlation * 0.8.8 2025-07-08 [1] RSPM (R 4.5.1)
## data.table 1.17.8 2025-07-10 [1] RSPM (R 4.5.1)
## datawizard * 1.3.0 2025-10-11 [1] RSPM (R 4.5.1)
## dichromat 2.0-0.1 2022-05-02 [3] CRAN (R 4.2.0)
## digest 0.6.39 2025-11-19 [1] CRAN (R 4.5.1)
## dplyr * 1.1.4 2023-11-17 [3] CRAN (R 4.4.2)
## easystats * 0.7.5 2025-07-11 [1] RSPM (R 4.5.1)
## effectsize * 1.0.1 2025-05-27 [1] RSPM (R 4.5.1)
## emmeans 1.10.7 2025-01-31 [3] CRAN (R 4.4.2)
## estimability 1.5.1 2024-05-12 [3] CRAN (R 4.4.2)
## evaluate 1.0.5 2025-08-27 [1] CRAN (R 4.5.1)
## farver 2.1.2 2024-05-13 [3] CRAN (R 4.4.1)
## fastmap 1.2.0 2024-05-15 [3] CRAN (R 4.4.1)
## forcats * 1.0.0 2023-01-29 [3] CRAN (R 4.2.2)
## fs 1.6.6 2025-04-12 [1] CRAN (R 4.5.1)
## generics 0.1.4 2025-05-09 [1] CRAN (R 4.5.1)
## ggplot2 * 4.0.1 2025-11-14 [1] RSPM (R 4.5.1)
## ggstatsplot * 0.13.3 2025-10-05 [1] RSPM
## glue 1.8.0 2024-09-30 [3] CRAN (R 4.4.2)
## gt * 1.1.0 2025-09-23 [1] RSPM (R 4.5.1)
## gtable 0.3.6 2024-10-25 [3] CRAN (R 4.4.2)
## hms 1.1.3 2023-03-21 [3] CRAN (R 4.3.1)
## htmltools 0.5.8.1 2024-04-04 [3] CRAN (R 4.4.0)
## htmlwidgets 1.6.4 2023-12-06 [3] CRAN (R 4.3.2)
## igraph 2.1.4 2025-01-23 [3] CRAN (R 4.5.0)
## insight * 1.4.2 2025-09-02 [1] RSPM (R 4.5.1)
## jsonlite 2.0.0 2025-03-27 [1] CRAN (R 4.5.1)
## knitr 1.50 2025-03-16 [3] CRAN (R 4.4.3)
## labeling 0.4.3 2023-08-29 [3] CRAN (R 4.3.1)
## lattice 0.22-7 2025-04-02 [4] CRAN (R 4.4.3)
## lifecycle 1.0.4 2023-11-07 [3] CRAN (R 4.3.2)
## lubridate * 1.9.4 2024-12-08 [3] CRAN (R 4.4.2)
## magrittr 2.0.4 2025-09-12 [1] CRAN (R 4.5.1)
## MASS 7.3-65 2025-02-28 [4] CRAN (R 4.4.3)
## Matrix 1.7-3 2025-03-11 [4] CRAN (R 4.4.3)
## MatrixModels 0.5-4 2025-03-26 [3] CRAN (R 4.4.3)
## modelbased * 0.13.0 2025-08-30 [1] RSPM (R 4.5.1)
## multcomp 1.4-28 2025-01-29 [3] CRAN (R 4.4.2)
## mvtnorm 1.3-3 2025-01-10 [1] RSPM
## paletteer 1.6.0 2024-01-21 [1] RSPM
## parameters * 0.28.2 2025-09-10 [1] RSPM (R 4.5.1)
## patchwork 1.3.2 2025-08-25 [1] RSPM (R 4.5.1)
## pbapply 1.7-2 2023-06-27 [3] CRAN (R 4.3.1)
## performance * 0.15.2 2025-10-06 [1] RSPM (R 4.5.1)
## pillar 1.11.1 2025-09-17 [1] CRAN (R 4.5.1)
## pkgconfig 2.0.3 2019-09-22 [3] CRAN (R 4.0.1)
## prettyunits 1.2.0 2023-09-24 [3] CRAN (R 4.3.1)
## processx 3.8.6 2025-02-21 [3] CRAN (R 4.4.3)
## ps 1.9.0 2025-02-18 [3] CRAN (R 4.4.3)
## purrr * 1.2.0 2025-11-04 [1] RSPM (R 4.5.1)
## R6 2.6.1 2025-02-15 [3] CRAN (R 4.4.3)
## RColorBrewer 1.1-3 2022-04-03 [3] CRAN (R 4.2.0)
## Rcpp 1.1.0 2025-07-02 [3] CRAN (R 4.5.1)
## RcppParallel 5.1.7 2023-02-27 [3] CRAN (R 4.5.0)
## readr * 2.1.6 2025-11-14 [1] RSPM
## rematch2 2.1.2 2020-05-01 [3] CRAN (R 4.0.1)
## report * 0.6.2 2025-11-03 [1] RSPM (R 4.5.1)
## rlang 1.1.6 2025-04-11 [1] CRAN (R 4.5.1)
## rmarkdown 2.30 2025-09-28 [1] RSPM (R 4.5.1)
## rstantools 2.4.0 2024-01-31 [3] CRAN (R 4.3.2)
## rstudioapi 0.17.1 2024-10-22 [3] CRAN (R 4.4.1)
## S7 0.2.1 2025-11-14 [1] RSPM (R 4.5.1)
## sandwich 3.1-1 2024-09-15 [3] CRAN (R 4.4.1)
## sass 0.4.10 2025-04-11 [1] RSPM (R 4.5.1)
## scales * 1.4.0 2025-04-24 [1] RSPM (R 4.5.1)
## secretbase 1.0.5 2025-03-04 [1] RSPM
## see * 0.12.0 2025-09-14 [1] RSPM (R 4.5.1)
## sessioninfo 1.2.3 2025-02-05 [3] CRAN (R 4.4.3)
## statsExpressions 1.7.1 2025-07-27 [1] RSPM
## stringi 1.8.7 2025-03-27 [1] CRAN (R 4.5.1)
## stringr * 1.6.0 2025-11-04 [1] CRAN (R 4.5.1)
## survival 3.8-3 2024-12-17 [4] CRAN (R 4.4.2)
## targets * 1.11.4 2025-09-13 [1] RSPM
## TH.data 1.1-3 2025-01-17 [3] CRAN (R 4.4.2)
## tibble * 3.3.0 2025-06-08 [1] CRAN (R 4.5.1)
## tidyr * 1.3.1 2024-01-24 [3] CRAN (R 4.3.2)
## tidyselect 1.2.1 2024-03-11 [3] CRAN (R 4.4.0)
## tidyverse * 2.0.0 2023-02-22 [3] CRAN (R 4.4.2)
## timechange 0.3.0 2024-01-18 [3] CRAN (R 4.4.3)
## tinytable 0.15.1 2025-11-02 [1] CRAN (R 4.5.1)
## tzdb 0.5.0 2025-03-15 [3] CRAN (R 4.4.3)
## vctrs 0.6.5 2023-12-01 [3] CRAN (R 4.3.2)
## visdat * 0.6.0 2023-02-02 [1] CRAN (R 4.5.1)
## visNetwork 2.1.2 2022-09-29 [3] CRAN (R 4.4.1)
## withr 3.0.2 2024-10-28 [3] CRAN (R 4.4.1)
## xfun 0.54 2025-10-30 [1] CRAN (R 4.5.1)
## xml2 1.5.0 2025-11-17 [1] CRAN (R 4.5.1)
## xtable 1.8-4 2019-04-21 [3] CRAN (R 4.0.1)
## yaml 2.3.10 2024-07-26 [3] CRAN (R 4.4.1)
## zeallot 0.2.0 2025-05-27 [1] RSPM
## zoo 1.8-14 2025-04-10 [3] CRAN (R 4.4.3)
##
## [1] /home/sebastian-sauer/R/x86_64-pc-linux-gnu-library/4.5
## [2] /usr/local/lib/R/site-library
## [3] /usr/lib/R/site-library
## [4] /usr/lib/R/library
## * ── Packages attached to the search path.
##
## ──────────────────────────────────────────────────────────────────────────────Wiederverwendung
MIT
Zitat
Mit BibTeX zitieren:
@online{sauer2026,
author = {Sauer, Sebastian},
title = {Challenge 05 -\/- Solution},
date = {2026-01-12},
url = {https://sebastiansauer.github.io/hans-hackathon2025/challenge05-solution.html},
langid = {de-DE}
}
Bitte zitieren Sie diese Arbeit als:
Sauer, Sebastian. 2026. “Challenge 05 -- Solution.” January
12, 2026. https://sebastiansauer.github.io/hans-hackathon2025/challenge05-solution.html.