# Load the package
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.5.1 ✔ tibble 3.2.1
## ✔ lubridate 1.9.4 ✔ tidyr 1.3.1
## ✔ purrr 1.0.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
# Load the dataset
students <- read_delim("https://raw.githubusercontent.com/MarcoKuehne/marcokuehne.github.io/main/data/Viadrina/viadrina_students_2013_2025.csv",
delim = ";",
escape_double = FALSE,
trim_ws = TRUE)
## Rows: 12 Columns: 7
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ";"
## chr (1): term
## dbl (6): students, female, male, german, foreign, year
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
# Create the plot
students %>%
ggplot(aes(x = year, y = students)) + # Map year to x-axis and student numbers to y-axis
geom_point() + # Add data points to the plot
geom_smooth(method = "gam") + # Add a smooth curve using a generalized additive model
scale_x_continuous(breaks = scales::pretty_breaks(n = 9)) + # Adjust x-axis to show readable year labels
labs(title = "Student Numbers at Viadrina",
x = "Year (Winter Semester)",
y = "Student Numbers") + # Add a title and axis labels
theme_minimal() + # Use a clean, minimal theme for the plot
geom_vline(xintercept = 2020.5, # Add a vertical line at 2020.5 to indicate the Corona shock
colour = "grey",
linetype = "solid",
lwd = 1.3) +
geom_text(aes(x = 2020.7, y = 6500,
label = "Corona"),
colour = "red",
angle = 90,
vjust = 1) # Add a label for the vertical line
## Warning in geom_text(aes(x = 2020.7, y = 6500, label = "Corona"), colour = "red", : All aesthetics have length 1, but the data has 12 rows.
## ℹ Please consider using `annotate()` or provide this layer with data containing
## a single row.
## `geom_smooth()` using formula = 'y ~ s(x, bs = "cs")'
