class: center, middle, inverse, title-slide .title[ # Sharing session #22: ] .subtitle[ ## Analysing Fantasy Premier League data in R ] .author[ ### Arif P. Sulistiono ] .date[ ### <br>Tuesday, 4 August 2022<br> <a href="https://www.instagram.com/mof.dac"> <i class="fa fa-instagram fa-fw"></i>mof.dac</a> ] --- <style>.xe__progress-bar__container { top:0; opacity: 1; position:absolute; right:0; left: 0; } .xe__progress-bar { height: 0.25em; background-color: orange; width: calc(var(--slide-current) / var(--slide-total) * 100%); } .remark-visible .xe__progress-bar { animation: xe__progress-bar__wipe 200ms forwards; animation-timing-function: cubic-bezier(.86,0,.07,1); } @keyframes xe__progress-bar__wipe { 0% { width: calc(var(--slide-previous) / var(--slide-total) * 100%); } 100% { width: calc(var(--slide-current) / var(--slide-total) * 100%); } }</style> # About me .center[  An employee of the Republic of Indonesia’s Ministry of Finance. Funded by the Indonesia Endowment Fund for Education ("Lembaga Pengelola Dana Pendidikan"), at the moment, on study leave to join a PhD program in the <a href="https://www.nottingham.ac.uk/economics/people/arif.sulistiono">School of Economics, the University of Nottingham</a> with research interests in Indonesia's government bonds market and their bondholders' behaviour. Also a research assistant at <a href="https://www.tracktheeconomy.ac.uk/arif-sulistiono">tracktheeconomy.ac.uk</a>. <br> <br> <a href="mailto:ap.sulistiono@gmail.com"><i class="fa fa-envelope fa-fw"></i></a></a> <a href="https://www.facebook.com/arifpras"> <i class="fa fa-facebook fa-fw"></i></a> <a href="https://github.com/arifpras"><i class="fa fa-github fa-fw"></i></a> <a href="https://www.instagram.com/arifpras"> <i class="fa fa-instagram fa-fw"></i></a> <a href="https://arifpras.medium.com/"> <i class="fa fa-medium fa-fw"></i></a> <a href="https://twitter.com/arifpras"> <i class="fa fa-twitter fa-fw"></i></a> <a href="https://arifpras.com"> <i class="fa fa-wordpress fa-fw"></i></a> ] --- # Limitations .panelset[ .panel[.panel-name[1: Data availability] * Historical statistics from previous seasons: 2020/2021 and 2021/2022 * Not included: + Pre-season matches + New players (i.e., Erling Haaland, Ivan Perišić, Kalidou Koulibaly, etc.) + New teams (i.e., Fulham, Bournemouth, Nottingham Forest) ] .panel[.panel-name[2: Specifications] * Software: RStudio 2022.07.1+554 "Spotted Wakerobin" Release for macOS + Alternative: Atom 1.60.0 x64 * Hardware: MBP 2020, chip M1, memory 16 GB. + Alternative: Cloud Computing Services - Amazon Web Services (AWS) + Multiple choices, depends on the price. ] ] .left[.footnote[.small[Source: https://www.rstudio.com/products/rstudio/download/; https://ec2instances.github.io/]]] --- # Today's session * Web scrapping + library: dplyr, jsonlite, rvest + functions: read_csv(), fromJSON(), read_html() * Data wrangling + library: dplyr + functions: mutate(), left_join(), right_join(), rename(), group_by() and ungroup(), select(), bind_rows(), etc. * Data visualisation + library: ggplot2, tidyr, viridis, ggrepel, ggsoccer + functions: geom_col(), reorder_within(), scale_fill_manual(), scale_fill_viridis, etc. * Basic statistics + library: dplyr, corrr + library: mean(), sum(), correlate(), combn(), choose(), etc. --- # Previous lessons: Data Wrangling and Visualisation <iframe src="https://arifpras.github.io/WranglingViz/" width="100%" height="400px" data-external="1"></iframe> .left[.footnote[.small[Source: https://arifpras.github.io/WranglingViz/]]] --- # Previous lessons: Basic Modelling <iframe src="https://arifpras.github.io/BasicModelling/" width="100%" height="400px" data-external="1"></iframe> .left[.footnote[.small[Source: https://arifpras.github.io/BasicModelling/]]] --- # General rules * Budget constraints = £100.0 for 15 players + 2 goalkeepers + 5 defenders + 5 midfielders + 3 forwards * Chips + Bench boost: once a season, bench players' points included in the total points. + Free hit: once a season, unlimited transfers for a single Gameweek. + Triple captain: once a season, tripled the captain's points instead of doubled. + Wild card: twice a season, Gameweek 1 to 16 and Gameweek 17 to 38. * Gameweek 1 deadline: Friday, 5 Aug 18:30 BST * Total managers (as of 3 August 2022): 5,592,326 managers --- # Initial budgeting plan and data sources ## Allocating the budget * Goalkeepers: £9.0 for 2 players. * Outfield players: £91.0 for 13 players. + Defenders: £35.0 for 5 players. + Midfielders: £35.0 for 5 players. + Forwards: £21.0 for 3 players. * Left £0.00 in the bank (less flexibility) ## Data sources: * vaastav's Github: https://github.com/vaastav/Fantasy-Premier-League/ * FPL data set: https://fantasy.premierleague.com/api/bootstrap-static/ * Fixtures: https://fixturedownload.com/results/epl-2022 --- # Another consideration <iframe src="https://pbs.twimg.com/media/FZHCGpIWQAE2DeV?format=jpg" width="100%" height="400px" data-external="1"></iframe> .left[.footnote[.small[Source: https://twitter.com/HollyShand/status/1554523674140495872]]] --- class: center, inverse, middle .center[  ] .large[<span style="color:orange"> Let's practice! </span>] <br> .small[open "BelutListik.qmd" in RStudio] --- # Disclaimers * Based on the previous seasons' statistics. + Re-run the codes after several matches in the next season. + The data set needs to be updated frequently (i.e., every two Gameweeks). * The Summer 2022 Transfer Window for Premier League clubs will close at 23:00 BST on 1 September 2022. + A possible move of Mark Cucurella (BHA, £5.0) to Chelsea. * Limitations in the computer memory make the analysis could not cover all possible choices: Use a higher specifications (memory >60 GB). * World Cup 2022: Including players involved in the competition or not? * Belut Listrik's statistics in the last season: + Overall points: 2,414 + Overall rank: 272,435 of 9,167,407 teams --- class: center, inverse, middle .large[ <span style="color:orange"> **Invite me to your mini league, maybe?** </span> ] **or you could join** @standupindo_kemenkeu X @ajikpurnomoputro: <span style="color:white">**hwf84k**</span> --- class: center, middle, clear .center[  ] .large[ Thank you for listening. ] .small[**All teaching materials will be available on https://github.com/arifpras/BelutListrik**] .small[ Slides created via the R packages: [**xaringan**](https://github.com/yihui/xaringan) and [gadenbuie/xaringanthemer](https://github.com/gadenbuie/xaringanthemer). <br> The chakra comes from [remark.js](https://remarkjs.com), [**knitr**](http://yihui.name/knitr), and [R Markdown](https://rmarkdown.rstudio.com). ] --- # Acknowledgements * Grolemund, G., & Wickham, H. (2017). R for Data Science. O’Reilly Media. * R Core Team (2019). R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. URL https://www.R-project.org/ * Wickham et al., (2019). Welcome to the tidyverse. Journal of Open Source Software, 4(43), 1686, https://doi.org/10.21105/joss.01686 * Claus O. Wilke: Data Visualization in R, https://wilkelab.org/SDS375/ * Cedric Scherer's personal blog: https://www.cedricscherer.com/ * ...and other sources i.e. stackoverflow.com, github.com, etc.