#Load packages

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   3.5.2     ✔ tibble    3.3.0
## ✔ lubridate 1.9.4     ✔ tidyr     1.3.1
## ✔ purrr     1.1.0     
## ── 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
library(tidytuesdayR)
library(janitor)
## 
## Attaching package: 'janitor'
## 
## The following objects are masked from 'package:stats':
## 
##     chisq.test, fisher.test
tuesdata <- tidytuesdayR::tt_load(2025, week = 40)
## ---- Compiling #TidyTuesday Information for 2025-10-07 ----
## --- There is 1 file available ---
## 
## 
## ── Downloading files ───────────────────────────────────────────────────────────
## 
##   1 of 1: "euroleague_basketball.csv"
eurov <- tuesdata$euroleague_basketball
view(eurov)

#Which countries are most represented in the EuroLeague?

eurov |> 
  count(Country) 
## # A tibble: 11 × 2
##    Country                  n
##    <chr>                <int>
##  1 France                   2
##  2 Germany                  1
##  3 Greece                   2
##  4 Israel                   2
##  5 Italy                    2
##  6 Lithuania                1
##  7 Monaco                   1
##  8 Serbia                   2
##  9 Spain                    4
## 10 Turkey                   2
## 11 United Arab Emirates     1
#Spain

#How do arena capacities compare across teams and countries? In R, the readr::parse_number() function might be helpful here. #Some cities have two arenas in the column #separate_longer_delim(items, delim = “,”) #parse_number to get the capacity

eurov_sep <- eurov |> 
  separate_longer_delim(Capacity, delim = ", ") 
  
view(eurov_sep)

eurov_sep$capacity <- parse_number(eurov_sep$Capacity)

#by country
eurov_sep |> 
  ggplot(aes(x = Country, y = capacity))+
  geom_bar(stat = "identity")

#by team
eurov_sep |> 
  ggplot(aes(x = Team, y = capacity))+
  geom_bar(stat = "identity")

#Which clubs have been the most successful historically?

eurov_sep |> 
  ggplot(aes(x = Team, y = FinalFour_Appearances))+
  geom_bar(stat = "identity")

#to filter out the columns with zero

ggplot(
  eurov_sep[eurov_sep$FinalFour_Appearances > 0,],
  aes(x = Team, y = FinalFour_Appearances))+
  geom_bar(stat = "identity")

#Olympiacos and Panathinaikos