formula 1 export.Rmd

---
title: |-
  F1 results
   \vspace{0.5in}
author:
- name: Christoffer Trier Månsson
output:
  BiocStyle::html_document:
    toc: yes
    toc_depth: 2
    number_sections: yes
    highlight: haddock
date: "`r format(Sys.time(), '%d %b %Y')`"
---

```{r, include = FALSE}
knitr::opts_chunk$set(
    tidy.opts = list(width.cutoff=100),
    tidy = FALSE,
    message = FALSE,
    collapse = TRUE,
    comment = "#>",
    root.dir = "C:/Users/chris/OneDrive/1PhD/formula1/formula1/archive"
)
knitr::opts_knit$set(root.dir = "C:/Users/chris/OneDrive/1PhD/formula1/formula1/archive")
```
\newpage
# Bets
<img src="download.png" width="200" align="right">

```{r, echo=FALSE,warning=F}
library(dplyr)
`%ni%` <- Negate(`%in%`)
bet_df <- function(Christoffer, Emil, Mikkel){
    drivers <- df_drivers_2022 <- read.csv("C:/Users/chris/OneDrive/1PhD/formula1/formula1/archive/drivers.csv") %>% select(driverId, forename, surname)
    if(any(Christoffer %ni% drivers$surname)){
        stop("Én eller flere af Christoffers bud er ikke gyldige")
    }
    if(any(Emil %ni% drivers$surname)){
        stop("Én eller flere af Emils bud er ikke gyldige")
    }
    if(any(Mikkel %ni% drivers$surname)){
        stop("Én eller flere af Mikkels bud er ikke gyldige")
    }
    if(length(unique(Christoffer[1:3]))!= 3){
        stop("Christoffer har ikke givet 3 forskellige bud")
    }
    if(length(unique(Emil[1:3]))!= 3){
        stop("Emil har ikke givet 3 forskellige bud")
    }
    if(length(unique(Mikkel[1:3]))!= 3){
        stop("Mikkel har ikke givet 3 forskellige bud")
    }
    df <- data.frame(Bets = c("Vinder", "Andenplads", "Tredjeplads","Joker"),
               Christoffer = Christoffer,
               Emil = Emil,
               Mikkel = Mikkel)
    return(df)
}

bet_df_w <- bet_df(Christoffer = c("Verstappen", "Alonso", "Sainz","Pérez"),
                   Emil = c("Verstappen","Alonso","Hamilton", "Pérez"),
                   Mikkel = c("Verstappen", "Russell", "Alonso","Pérez"))

```



## Seneste top 10

Her præsenterer jeg seneste løbs top 10. 

```{r, echo=FALSE,warning=F}
library(dplyr)
library(ggplot2)
library(viridis)
library(RCurl)

df_race <- read.csv("C:/Users/chris/OneDrive/1PhD/formula1/formula1/formula1_dataset/Formula1_2023season_raceResults.csv")
df_race <- df_race[nrow(df_race),]
df_results <- read.csv("C:/Users/chris/OneDrive/1PhD/formula1/formula1/formula1_dataset/Formula1_2023season_raceResults.csv") %>% filter(Track == df_race$Track) %>% 
    filter(Points > 0) %>% 
    arrange(Points)
df_results <- df_results %>%
    mutate(Driver = factor(Driver, levels = df_results$Drive))
ggplot(df_results,aes(x = Driver, y = Points,
           fill = Driver)) +
    scale_fill_viridis("magma",discrete = T)+ 
    geom_bar(stat = "identity")+
    theme_minimal()+
    labs(x = "",
         y = "Points",
         title = paste(df_race$name,df_race$date))+ 
    theme(axis.text.x = element_text(angle = 45, vjust = 1, hjust=1, 
                                     size = 12, face = "bold"),
          legend.background = element_rect(),
    plot.title = element_text(angle = 0, size = 16, face = 'bold', vjust = 1),
    plot.caption = element_text(angle = 0, size = 10, vjust = 1, hjust = 0.37),
    axis.text.y = element_text(angle = 0, size = 12),
    axis.title = element_text(size = 14, face = 'bold'),
    axis.title.x = element_text(size = 14, face = 'bold'),
    axis.title.y = element_text(size = 14, face = 'bold'),
    legend.text = element_text(size = 12), 
    title = element_text(size = 14, face = "bold"),
    panel.grid.major.x = element_blank())+
    guides(fill="none")

```

## Seneste bet resultat
```{r, echo=FALSE,warning=F}
library(dplyr)
point_calculator <- function(bet_df){
    df_race <- read.csv("C:/Users/chris/OneDrive/1PhD/formula1/formula1/formula1_dataset/Formula1_2023season_raceResults.csv")
df_race <- df_race[nrow(df_race),]
df_results <- read.csv("C:/Users/chris/OneDrive/1PhD/formula1/formula1/formula1_dataset/Formula1_2023season_raceResults.csv") %>% filter(Track == df_race$Track)
df_drivers <-  read.csv("C:/Users/chris/OneDrive/1PhD/formula1/formula1/archive/drivers.csv") %>% 
        mutate(tot_name = paste(forename, surname)) %>% 
        select(tot_name, surname) %>% 
        mutate(new_names = ifelse(surname == "Pérez","Sergio Perez",tot_name)) %>%
        mutate(new_names = ifelse(surname == "Hülkenberg","Nico Hulkenberg",new_names)) %>% 
        mutate(new_names = ifelse(surname == "de Vries","Nyck De Vries",new_names))
    df_results <- df_results %>% left_join(df_drivers, by = c("Driver" = "new_names"))
    #Christoffer
    bet_Christoffer <- bet_df %>% select(Christoffer)
    res_Christoffer <- match(bet_Christoffer$Christoffer[1:3], df_results$surname) 
    for(i in 1:length(res_Christoffer)){
        ddf <- df_results[res_Christoffer[i],]
        if(ddf$Time.Retired == "DNF"){
            res_Christoffer[i] <- 20
        }
    }
    Christoffer_points <- sum(abs(res_Christoffer-c(1,2,3)))
    joker_Christoffer <- df_results %>% 
        filter(surname == bet_Christoffer$Christoffer[4])
    joker_res_Christoffer <- ifelse(joker_Christoffer$Time.Retired == "DNF",
                                    20-joker_Christoffer$Starting.Grid,
                                    as.numeric(joker_Christoffer$Position)-
                                                   joker_Christoffer$Starting.Grid)
    bet_Emil <- bet_df %>% select(Emil)
    res_Emil <- match(bet_Emil$Emil[1:3], df_results$surname)
    joker_Emil <- df_results %>% 
        filter(surname == bet_Emil$Emil[4])
    joker_res_Emil <- ifelse(joker_Emil$Time.Retired == "DNF",
                                    20-joker_Emil$Starting.Grid,
                                    as.numeric(joker_Emil$Position)-
                                                   joker_Emil$Starting.Grid)
    for(i in 1:length(res_Emil)){
        ddf <- df_results[res_Emil[i],]
        if(ddf$Time.Retired == "DNF"){
            res_Emil[i] <- 20
        }
    }
    Emil_points <- sum(abs(res_Emil-c(1,2,3)))
    #Mikkel
    bet_Mikkel <- bet_df %>% select(Mikkel)
    res_Mikkel <- match(bet_Mikkel$Mikkel[1:3], df_results$surname) 
    for(i in 1:length(res_Mikkel)){
        ddf <- df_results[res_Mikkel[i],]
        if(ddf$Time.Retired == "DNF"){
            res_Mikkel[i] <- 20
        }
    }
    Mikkel_points <- sum(abs(res_Mikkel-c(1,2,3)))
    joker_Mikkel <- df_results %>% 
        filter(surname == bet_Mikkel$Mikkel[4])
    joker_res_Mikkel <- ifelse(joker_Mikkel$Time.Retired == "DNF",
                                    20-joker_Mikkel$Starting.Grid,
                                    as.numeric(joker_Mikkel$Position)-
                                                   joker_Mikkel$Starting.Grid)
    collected_points <- c(Christoffer_points,Emil_points,Mikkel_points)
    if(any(collected_points == 0)){
        if(sum(collected_points == 0) == 1){
            winner_all3 <- colnames(bet_df)[c(2,3,4)][collected_points == 0]
            
        }
    }
    else{
        winner_all3 <- NULL
    }
    collected_winners <- c(res_Christoffer[1]-1,res_Emil[1]-1,res_Mikkel[1]-1)
    if(is.null(winner_all3)){
        if(any(collected_winners == 0)){
            if(sum(collected_winners == 0) == 1){
                winner <- colnames(bet_df)[c(2,3,4)][collected_winners == 0]
            }
            else{
                winner <- NULL
            }
        }
        else{
            winner <- NULL
        }
    }
    else{
            winner <- NULL
        }
    res_df <- data.frame(Bets = "Point",
                         Christoffer = Christoffer_points,
                         Emil = Emil_points,
                         Mikkel = Mikkel_points)
    if(!is.null(winner_all3)){
        res_df[winner_all3] <- -15
    }
    if(!is.null(winner)){
        res_df[winner] <- -5
    }
    res_df$Christoffer <- res_df$Christoffer + joker_res_Christoffer
    res_df$Emil <- res_df$Emil + joker_res_Emil
    res_df$Mikkel <- res_df$Mikkel + joker_res_Mikkel
    df <- rbind(bet_df,res_df)
    return(df)
}
```

Her kan man se hvor mange point vi fik efter seneste grandprix. 

```{r, echo = F,warning=F}
library(dplyr)
df_race <- read.csv("C:/Users/chris/OneDrive/1PhD/formula1/formula1/formula1_dataset/Formula1_2023season_raceResults.csv")
df_race <- df_race[nrow(df_race),]

print(paste(df_race$Track))

print(point_calculator(bet_df_w))
```

## Seneste Joker resultat

Her kan man se hvordan jokeren har spillet ind på resultatet

```{r, echo = FALSE,warning=F}

joker_plot <- function(bet_df){
    library(ggrepel)
    library(viridis)
    df_race <- read.csv("C:/Users/chris/OneDrive/1PhD/formula1/formula1/formula1_dataset/Formula1_2023season_raceResults.csv")
df_race <- df_race[nrow(df_race),]
    df_results <- read.csv("C:/Users/chris/OneDrive/1PhD/formula1/formula1/formula1_dataset/Formula1_2023season_raceResults.csv") %>% filter(Track == df_race$Track) 
    df_drivers <-  
        read.csv("C:/Users/chris/OneDrive/1PhD/formula1/formula1/archive/drivers.csv") %>% 
        mutate(tot_name = paste(forename, surname)) %>% 
        select(tot_name, surname) %>% 
        mutate(new_names = ifelse(surname == "Pérez","Sergio Perez",tot_name)) %>%
        mutate(new_names = ifelse(surname == "Hülkenberg","Nico Hulkenberg",new_names)) %>% 
        mutate(new_names = ifelse(surname == "de Vries","Nyck De Vries",new_names))
    df_results <- df_results %>% left_join(df_drivers, by = c("Driver" = "new_names"))
    bet_Christoffer <- bet_df %>% select(Christoffer)
    bet_Emil <- bet_df %>% select(Emil)
    bet_Mikkel <- bet_df %>% select(Mikkel)
    joker_Christoffer <- df_results %>% 
        filter(surname == bet_Christoffer$Christoffer[4])
    joker_res_Christoffer <- ifelse(joker_Christoffer$Time.Retired == "DNF",
                                    20-joker_Christoffer$Starting.Grid,
                                    as.numeric(joker_Christoffer$Position)-
                                                   joker_Christoffer$Starting.Grid)
    joker_Emil <- df_results %>% 
        filter(surname == bet_Emil$Emil[4])
    joker_res_Emil <- ifelse(joker_Emil$Time.Retired == "DNF",
                                    20-joker_Emil$Starting.Grid,
                                    as.numeric(joker_Emil$Position)-
                                                   joker_Emil$Starting.Grid)
    joker_Mikkel <- df_results %>% 
        filter(surname == bet_Mikkel$Mikkel[4])
    joker_res_Mikkel <- ifelse(joker_Mikkel$Time.Retired == "DNF",
                                    20-joker_Mikkel$Starting.Grid,
                                    as.numeric(joker_Mikkel$Position)-
                                                   joker_Mikkel$Starting.Grid)
    df <- data.frame(person = c(rep("Christoffer",2),
                                rep("Emil",2),
                                rep("Mikkel",2)),
                     type = factor(rep(c("Start","Slut"),3),
                                   levels = c("Start","Slut")),
                     Position = c(as.numeric(joker_Christoffer$Starting.Grid),
                                  ifelse(joker_Christoffer$Time.Retired == "DNF",
                                         20,
                                         as.numeric(joker_Christoffer$Position)),
                                  as.numeric(joker_Emil$Starting.Grid),
                                  ifelse(joker_Emil$Time.Retired == "DNF",
                                         20,
                                         as.numeric(joker_Emil$Position)),
                                  as.numeric(joker_Mikkel$Starting.Grid),
                                  ifelse(joker_Mikkel$Time.Retired == "DNF",
                                         20,
                                         as.numeric(joker_Mikkel$Position))),
                     driver = c(rep(bet_Christoffer$Christoffer[4],2),
                                rep(bet_Emil$Emil[4],2),
                                rep(bet_Mikkel$Mikkel[4],2)),
                     result = c(rep(joker_res_Christoffer,2),
                                rep(joker_res_Emil,2),
                                rep(joker_res_Mikkel,2)))
    gg <- ggplot(df, aes(x = type,y = Position,group = person,
                         color = person))+
        geom_point(size = 5)+
        geom_line(linewidth = 1.5)+
        scale_color_viridis("cividis",discrete = T)+
        theme_minimal()+
        labs(title = paste("Joker -",df_race$Track),
             x = "",
             y = "Placering")+
        scale_y_continuous(limits = c(0,20))+
        geom_label_repel(aes(label=ifelse(type == "Slut",
                                          paste(driver,result),"")),
                  nudge_x = 0.25,
                  na.rm = TRUE,
                  label.size = NA,
                  size = 3.5,
                  fill = alpha(c("white"),0),
                  parse = F,
                 max.overlaps = 100)+
            theme(axis.text.x = element_text(angle = 45, vjust = 1, hjust=1, 
                                     size = 12, face = "bold"),
            legend.background = element_rect(),
            plot.title = element_text(angle = 0, size = 16, face = 'bold', vjust = 1),
            plot.caption = element_text(angle = 0, size = 10, vjust = 1, hjust = 0.37),
            axis.text.y = element_text(angle = 0, size = 12),
            axis.title = element_text(size = 14, face = 'bold'),
            axis.title.x = element_text(size = 14, face = 'bold'),
            axis.title.y = element_text(size = 14, face = 'bold'),
            legend.text = element_text(size = 12), 
            title = element_text(size = 14, face = "bold"),
            panel.grid.major.x = element_blank(),
            legend.title = element_blank())+
        guides(color = guide_legend(override.aes = aes(label = ""))) 
    
    return(gg)
    
}
joker_plot(bet_df_w)
```


## Løbende udvikling for bets

Her kan man se hvordan det går i vores interne konkurrence efter hvert
grandprix. Først efter 4. løb vil jeg tage de værste 3 løb ud fra vores 
totale antal point. 

```{r, echo = FALSE,warning=F}
df_race <- read.csv("C:/Users/chris/OneDrive/1PhD/formula1/formula1/formula1_dataset/Formula1_2023season_raceResults.csv")
df_race <- df_race[nrow(df_race),]
path <- "C:/Users/chris/OneDrive/1PhD/formula1/formula1/formula1_dataset/bet_results"
recent_results <- point_calculator(bet_df_w)
saveRDS(recent_results,file = paste0(path,"/",df_race$Track,".rds"))

```

```{r, echo = FALSE,warning=F}
library(tidyverse)
setwd("C:/Users/chris/OneDrive/1PhD/formula1/formula1/formula1_dataset/bet_results")
list_of_files <- list.files(path = "C:/Users/chris/OneDrive/1PhD/formula1/formula1/formula1_dataset/bet_results")
df_1 <- readRDS("C:/Users/chris/OneDrive/1PhD/formula1/formula1/formula1_dataset/bet_results/Bahrain.rds") %>% filter(Bets != "date")
df_2 <- readRDS("C:/Users/chris/OneDrive/1PhD/formula1/formula1/formula1_dataset/bet_results/Saudi Arabia.rds")
df_3 <- readRDS("C:/Users/chris/OneDrive/1PhD/formula1/formula1/formula1_dataset/bet_results/Australia.rds")
####Change 1####
df_race <- read.csv("C:/Users/chris/OneDrive/1PhD/formula1/formula1/formula1_dataset/Formula1_2023season_raceResults.csv")
df_results <- rbind(df_1,df_2,df_3)####Change 2####
res_df <- df_results %>% filter(Bets == "Point")
res_df$place <- c("Bahrain", "Saudi Arabia", "Australia") ####Change 3####
res_df$Christoffer <- as.numeric(res_df$Christoffer)
res_df$Emil <- as.numeric(res_df$Emil)
res_df$Mikkel <- as.numeric(res_df$Mikkel)
res_df_gg <- data.frame(place = rep(res_df$place,3),
                        player = c(rep(colnames(res_df)[2],3),####Change 4####
                                   rep(colnames(res_df)[3],3),####Change 5####
                                   rep(colnames(res_df)[4],3)),####Change 6####
                        result = c(as.numeric(res_df$Christoffer),
                                   as.numeric(res_df$Emil),
                                   as.numeric(res_df$Mikkel))) %>% 
    group_by(player) %>% 
    summarise(sum_result = cumsum(result),
              place = place)
res_df_gg <- res_df_gg %>% 
  mutate(place = factor(place, levels = unique(res_df_gg$place)))
ggplot(res_df_gg,aes(x = place,y = sum_result,group = player,
                 color = player))+
        geom_point(size = 5)+
        geom_line(linewidth = 1.5)+
        scale_color_viridis("cividis",discrete = T)+
        theme_minimal()+
        labs(title = paste("Standings"),
             x = "Race",
             y = "Accumulated points")+
            theme(axis.text.x = element_text(angle = 45, vjust = 1, hjust=1, 
                                     size = 12, face = "bold"),
            legend.background = element_rect(),
            plot.title = element_text(angle = 0, size = 16, face = 'bold', vjust = 1),
            plot.caption = element_text(angle = 0, size = 10, vjust = 1, hjust = 0.37),
            axis.text.y = element_text(angle = 0, size = 12),
            axis.title = element_text(size = 14, face = 'bold'),
            axis.title.x = element_text(size = 14, face = 'bold'),
            axis.title.y = element_text(size = 14, face = 'bold'),
            legend.text = element_text(size = 12), 
            title = element_text(size = 14, face = "bold"),
            panel.grid.major.x = element_blank(),
            legend.title = element_blank())
    
```


# Kørernes resultater

## Kørernes udvikling
Her kan man se hvem der fører løbet og hvordan de har fået point gennem sæsonen
Jeg viser top10 + Magnussen
```{r, echo = FALSE,warning=F}

df_race <- read.csv("C:/Users/chris/OneDrive/1PhD/formula1/formula1/formula1_dataset/Formula1_2023season_raceResults.csv") %>%
    group_by(Driver) %>% 
    reframe(.groups = "Driver",
              cum_sums = cumsum(Points),
              place = Track) %>% 
    group_by(Driver) %>% 
    reframe(.groups = "Driver",
            cum_sums = cum_sums,
              sums = max(cum_sums),
              place = place)
    
top_10 <- df_race %>% 
    group_by(Driver) %>% 
    slice(1) %>% 
    arrange(desc(sums)) %>% 
    ungroup() %>% 
    dplyr::slice(1:10)

df_race_gg <- df_race %>% 
    filter(Driver %in% top_10$Driver | Driver == "Kevin Magnussen") %>% 
    mutate(label = ifelse(place == unique(df_race$place)[length(unique(df_race$place))],Driver,NA))
df_race_gg <- df_race_gg %>% 
  mutate(place = factor(place, levels = unique(df_race_gg$place)))

ggplot(df_race_gg, aes(x = place,
                            y = cum_sums,
                            colour = Driver,
                            group = Driver))+
    geom_point()+
    scale_color_viridis("magma",discrete = T)+ 
    geom_line()+
    theme_minimal()+
    labs(y = "Points",
         x = "",
         title = "2023 drivers")+
    geom_label_repel(aes(label=label),
                  nudge_x = 0.5,
                  na.rm = TRUE,
                  label.size = NA,
                  size = 3.5,
                  fill = alpha(c("white"),0),
                  parse = F,
                 max.overlaps = 100)+
    theme(axis.text.x = element_text(angle = 45, vjust = 1, hjust=1,size = 8),
          legend.background = element_rect(),
    plot.title = element_text(angle = 0, size = 16, face = 'bold', vjust = 1),
    plot.caption = element_text(angle = 0, size = 10, vjust = 1, hjust = 0.37),
    axis.text.y = element_text(angle = 0, size = 12),
    axis.title = element_text(size = 14, face = 'bold'),
    axis.title.x = element_text(size = 14, face = 'bold'),
    axis.title.y = element_text(size = 14, face = 'bold'),
    legend.text = element_text(size = 12), 
    title = element_text(size = 14, face = "bold"))+
   guides(color="none")

```

## Teamets udvikling

Her kan man se hvordan de enkelte teams scorer point samlet. Her forventer vi
jo en klar sejr til Haas ;) 

```{r, echo = FALSE,warning=F}

df_race <- read.csv("C:/Users/chris/OneDrive/1PhD/formula1/formula1/formula1_dataset/Formula1_2023season_raceResults.csv") %>%
    group_by(Team,Track)
df_race <- df_race %>%
    mutate(Track = factor(Track, levels = unique(df_race$Track))) %>% 
    reframe(.groups = "Team",
              team_sums = sum(Points)) %>% 
    group_by(Team) %>% 
    reframe(.groups = "Team",
            cum_sums = cumsum(team_sums),
            place = Track) %>% 
    group_by(Team) %>% 
    reframe(.groups = "Team",
            cum_sums = cum_sums,
              sums = max(cum_sums),
              place = place)
df_race <- df_race %>% mutate(label = ifelse(place == unique(df_race$place)[length(unique(df_race$place))],Team,NA)) 

ggplot(df_race, aes(x = place,
                            y = cum_sums,
                            colour = Team,
                            group = Team))+
    geom_point()+
    scale_color_viridis("magma",discrete = T)+ 
    geom_line()+
    theme_minimal()+
    labs(y = "Points",
         x = "",
         title = "2023 teams")+
    geom_label_repel(aes(label=label),
                  nudge_x = 0.5,
                  na.rm = TRUE,
                  label.size = NA,
                  size = 3.5,
                  fill = alpha(c("white"),0),
                  parse = F,
                 max.overlaps = 100)+
    theme(axis.text.x = element_text(angle = 45, vjust = 1, hjust=1,size = 8),
          legend.background = element_rect(),
    plot.title = element_text(angle = 0, size = 16, face = 'bold', vjust = 1),
    plot.caption = element_text(angle = 0, size = 10, vjust = 1, hjust = 0.37),
    axis.text.y = element_text(angle = 0, size = 12),
    axis.title = element_text(size = 14, face = 'bold'),
    axis.title.x = element_text(size = 14, face = 'bold'),
    axis.title.y = element_text(size = 14, face = 'bold'),
    legend.text = element_text(size = 12), 
    title = element_text(size = 14, face = "bold"))+
   guides(color="none")

```

## Fold difference from teammate

Det her plot viser hvor mange point den førerne kører fra hvert team har scoret
i forhold til hans holdkammerat. Størrelsen på cirklen indikerer 
hvor mange på point køren har fået. På Y-aksen samt på farven
kan man se hvor mange point
han har fået i forhold til sin holdkammerat. Navnet på hans hold og teammate kan
ses på X-aksen. 

```{r, echo = FALSE,fig.height= 6,warning=F}
df_race <- read.csv("C:/Users/chris/OneDrive/1PhD/formula1/formula1/formula1_dataset/Formula1_2023season_raceResults.csv") %>%
    group_by(Driver) %>%
    reframe(.groups = "Driver",
            sums = sum(Points),
            Team = Team,
            Driver = Driver) %>% 
    group_by(Driver) %>% 
    slice(1) %>% 
    group_by(Team) %>% 
    reframe(.groups = "Driver",
            lowest = Driver[which.min(sums)],
            Driver = Driver,
            sums = sums+1) %>% 
    group_by(Team) %>% 
    reframe(fold = ifelse(Driver == lowest,NA,sums/min(sums)),
            Driver = Driver,
            Points = sums-1,
            Team = Team,
            lowest = lowest,
            team_driver = paste0(Team,", ",lowest)) %>% 
    filter(!is.na(fold))
    
ggplot(df_race, aes(x = team_driver,
                            y = fold,
                            color = fold,
                            size = Points))+
    geom_point()+
    geom_label_repel(aes(label=Driver),
                  nudge_x = 0.5,
                  na.rm = TRUE,
                  label.size = NA,
                  size = 3.5,
                  fill = alpha(c("white"),0),
                  parse = F,
                 max.overlaps = 100)+
    scale_color_gradient(low = "#6a00fc", high = "#ffa10c")+ 
    theme_minimal()+
    labs(y = "Fold points compared to teammate",
         x = "Teams",
         title = "Driver comparisons")+
    theme(axis.text.x = element_text(angle = 90, vjust = 1, hjust=1,size = 8),
          legend.background = element_rect(),
    plot.title = element_text(angle = 0, size = 16, face = 'bold', vjust = 1),
    plot.caption = element_text(angle = 0, size = 10, vjust = 1, hjust = 0.37),
    axis.text.y = element_text(angle = 0, size = 12),
    axis.title = element_text(size = 14, face = 'bold'),
    axis.title.x = element_text(size = 14, face = 'bold'),
    axis.title.y = element_text(size = 14, face = 'bold'),
    legend.text = element_text(size = 12), 
    title = element_text(size = 14, face = "bold"))+
    guides(fill = guide_legend(title="Points"))

``` 


# Regler for spillet

Reglerne er simple. Efter kvallen, men inden løbsdagen skal man have sendt til 
Christoffer i chatgruppen, **Formula1**, hvilke 3 kører man forventer bliver
nummer 1, 2 og 3 i det kommende løb.

**Alle hjælper alle med at huske at der skal indsendes bud på det kommende løb!**

Glemmer man at give noget bud får man 50 point i straf. 

Efter hvert løb bliver det beregnet hvor mange pladser ens kører er væk fra den
plads man gættede på, at køren blev. Hvis en kører udgår 
anses det at han slutter sidst og får position 20. 
Altså kan man minimalt få 0 point (før bonuser og joker), mens 
man maximalt kan få 54 point (20-1 + 20-2 + 20-3 = 19+18+17 = 54).

Slutter ens kører bedre end man har budt får man stadig plus point

I formel1 sæsonen køres 23 løb. For at give lidt sikkerhed medregnes ens 3
dårligste bud ikke i regnskabet og derfor er hver spillers score baseret på
i alt 20 løb til slut i sæsonen.

## Bonus

Der udlådes bonus på to måder. 

1) Er man den eneste der har løbets vinder gives -5 point

2) Er man den eneste der har løbets top 3 gives -15 point

Har man kun eks. løbets nummer 1 og 2 gives -5 point.

Har man kun løbets nummer 2 og 3 gives ingen bonus. 

## Joker

Hver uge giver man også et bud på en joker. Det er den kører man forventer 
vil køre flest placeringer frem i forhold til startpositionen. 
De placeringer ens joker kører frem trækkes fra ens point. 
For eksempel vælger man en joker der starter som nummer 17 og der slutter 
som nummer 10 får man -7 joker point
Altså scorer man 10 point på ens top 3 og ens joker går fra 17 til 10 slutter 
man på 3 point (10 - 7 = 3). 

Ender ens joker dårligere end han startede lægger man differencen oven i 
pointene fra top 3. Altså havde han sluttet som nummer 20 (eller udgået) fra 
forrige eksempel havde man fået 3 point oveni og ville altså ende på 13 point.

## Præmie

Det er blevet besluttet at vi alle skal en tur ud at køre gokart når sæsonen
er slut. Her skal nummer 2 og 3 i bettingspillet betale udgifter for
nummer 1. **Plus ham der slutter sidst giver en øl i fredagsbaren! ;)** 

# Resultaterne for 2022 sæsonen

Her finder man et lille overblik over hvordan 2022 sæsonen gik. 

## Slut resultat

```{r, echo=FALSE,warning=F}
library(dplyr)

df_races_2022 <- read.csv("C:/Users/chris/OneDrive/1PhD/formula1/formula1/archive/races.csv") %>% filter(year == 2022)
df_drivers_2022 <- read.csv("C:/Users/chris/OneDrive/1PhD/formula1/formula1/archive/drivers.csv") %>% select(driverId, forename, surname)
df_results_2022 <- read.csv("C:/Users/chris/OneDrive/1PhD/formula1/formula1/archive/results.csv") %>% filter(raceId %in% df_races_2022$raceId) %>% 
    group_by(driverId) %>% 
    summarise(.groups = "keep",
              cumulativePoints = cumsum(points),
              raceId = raceId,
              totPoints = sum(points))
totResult <- abs(sort(-unique(df_results_2022$totPoints)))
df_results_2022 <- df_results_2022 %>%  
    left_join(df_drivers_2022, by = "driverId") %>% 
    left_join(df_races_2022 %>% select(raceId,name,date), by = "raceId") %>% 
    mutate(driverName = paste(forename, surname)) %>% 
    mutate(isTop10 = ifelse(totPoints %in% totResult[1:10] | surname == "Magnussen","Yes","No")) %>% 
    filter(isTop10 == "Yes") %>% 
    mutate(place = factor(name, level = unique(name))) %>% 
    mutate(label = ifelse(raceId == max(raceId), 
                          ifelse(isTop10 == "Yes", as.character(surname),NA_character_),
                          NA_character_))

```

Sidste års klare vinder var Max Verstappen, men det var meget tæt mellem nummer
2 og 3. 

```{r, echo=FALSE,warning=F}
library(ggplot2)
library(viridis)
library(ggrepel)
res <- df_results_2022 %>% filter(raceId == 1074) %>%
    arrange(totPoints)
res <- res %>% mutate(driverName = factor(driverName, levels = res$driverName))
ggplot(res, aes(x = driverName,
           y = totPoints,
           fill = driverName))+
    scale_fill_viridis("magma",discrete = T)+ 
    geom_bar(stat = "identity")+
    theme_minimal()+
    labs(x = "",
         y = "Accumulated points",
         title = "2022")+ 
    theme(axis.text.x = element_text(angle = 45, vjust = 1, hjust=1, 
                                     size = 12, face = "bold"),
          legend.background = element_rect(),
    plot.title = element_text(angle = 0, size = 16, face = 'bold', vjust = 1),
    plot.caption = element_text(angle = 0, size = 10, vjust = 1, hjust = 0.37),
    axis.text.y = element_text(angle = 0, size = 12),
    axis.title = element_text(size = 14, face = 'bold'),
    axis.title.x = element_text(size = 14, face = 'bold'),
    axis.title.y = element_text(size = 14, face = 'bold'),
    legend.text = element_text(size = 12), 
    title = element_text(size = 14, face = "bold"),
    panel.grid.major.x = element_blank())+
    guides(fill="none")

```

## Udviklingen gennem 2022

Verstappen havde en dårligere start på sæsonen end nogen af hans konkurrenter
Herimod havde Magnussen en meget stille sidste halvdel af sæsonen. 
```{r, echo=FALSE,fig.height= 6,warning=F}
library(ggplot2)
library(viridis)
library(ggrepel)
ggplot(df_results_2022, aes(x = place,
                            y = cumulativePoints,
                            colour = driverName,
                            group = driverName))+
    geom_point()+
    scale_color_viridis("magma",discrete = T)+ 
    geom_line()+
    theme_minimal()+
    labs(y = "Points",
         x = "",
         title = "2022")+
    geom_label_repel(aes(label=label),
                  nudge_x = 2,
                  na.rm = TRUE,
                  label.size = NA,
                  size = 3.5,
                  fill = alpha(c("white"),0),
                  parse = F,
                 max.overlaps = 100)+
    theme(axis.text.x = element_text(angle = 45, vjust = 1, hjust=1,size = 8),
          legend.background = element_rect(),
    plot.title = element_text(angle = 0, size = 16, face = 'bold', vjust = 1),
    plot.caption = element_text(angle = 0, size = 10, vjust = 1, hjust = 0.37),
    axis.text.y = element_text(angle = 0, size = 12),
    axis.title = element_text(size = 14, face = 'bold'),
    axis.title.x = element_text(size = 14, face = 'bold'),
    axis.title.y = element_text(size = 14, face = 'bold'),
    legend.text = element_text(size = 12), 
    title = element_text(size = 14, face = "bold"))+
   guides(color="none")
```

## Team ranking i 2022

Red Bull med Perez (samlet nummer 3) og Verstappen (samlet vinder) blev en 
rimelig klar vinder af team konkurrencen. Kampen om andepladsen var tæt mellem
Mercedes (Russell (4) og Hamilton (5)) og Ferrari (Leclerc (2) og Sainz (6)).
Williams slutter sidst med bare 7 point på en hel sæson! Det er sgu en ommer!

```{r, echo=FALSE,fig.height= 6,warning=FALSE}
library(dplyr)
library(scales)
df_constructors <- read.csv("C:/Users/chris/OneDrive/1PhD/formula1/formula1/archive/constructors.csv") %>% select(constructorId, name)
df_results_2022_teams <- read.csv("C:/Users/chris/OneDrive/1PhD/formula1/formula1/archive/results.csv") %>% filter(raceId %in% df_races_2022$raceId) %>% 
    group_by(constructorId) %>% 
    summarise(.groups = "keep",
              raceId = raceId,
              totPoints = sum(points)) %>% 
        left_join(df_constructors, by = "constructorId") %>% 
    filter(raceId == "1095") %>% 
    arrange(totPoints) %>% 
    distinct()
df_results_2022_teams %>% 
    mutate(name = factor(name, levels = unique(df_results_2022_teams$name))) %>% 
    ggplot(aes(x = name, y = totPoints,
           fill = name)) +
    scale_fill_viridis("magma",discrete = T)+ 
    geom_bar(stat = "identity")+
    theme_minimal()+
    scale_y_continuous(trans = "log10",
                       labels = label_comma())+
    labs(x = "",
         y = "Accumulated points",
         title = "2022")+ 
    theme(axis.text.x = element_text(angle = 45, vjust = 1, hjust=1, 
                                     size = 12, face = "bold"),
          legend.background = element_rect(),
    plot.title = element_text(angle = 0, size = 16, face = 'bold', vjust = 1),
    plot.caption = element_text(angle = 0, size = 10, vjust = 1, hjust = 0.37),
    axis.text.y = element_text(angle = 0, size = 12),
    axis.title = element_text(size = 14, face = 'bold'),
    axis.title.x = element_text(size = 14, face = 'bold'),
    axis.title.y = element_text(size = 14, face = 'bold'),
    legend.text = element_text(size = 12), 
    title = element_text(size = 14, face = "bold"),
    panel.grid.major.x = element_blank())+
    guides(fill="none")
```

# Information om data

Data er taget fra følgende side <https://www.kaggle.com/datasets/rohanrao/formula-1-world-championship-1950-2020?resource=download> samt <https://github.com/toUpperCase78/formula1-datasets> som løbende opdaterer den seneste data fra hele F1

Koden til dette dokument er frit tilgængelig gennem <https://github.com/CTrierMaansson/formula1> hvor der også vil komme løbende
opdateringer. Jeg henviser til **issues** fanen for bugs og andre problemer 
man kan have med dokumentet. Her kan man også rette forslag til statistik
man ønsker skal være en del af dokumentet.