Data management

library(data.table)
library(dplyr)
library(readr)
library(forcats)

rg2013.dt <- fread("FrenchOpen-men-2013.csv")
rg2013.dt

rg2013.df <- read.table("FrenchOpen-men-2013.csv",sep=",",header=TRUE)
rg2013.tb <- tibble(rg2013.dt)

rg2013.tb <- read_csv("FrenchOpen-men-2013.csv")

rg2013.tb |>
  filter(Round==6) |>
  select(Player1,Player2)

rg2013.tb |>
  filter(Player1=='Roger Federer' | Player2=='Roger Federer')

rg2013.tb |>
  distinct(Player2)

rg2013.tb |>
  mutate(nb_points=TPW.1+TPW.2) |>
  summarise(nb_points_moy=mean(nb_points))

rg2013.tb |>
  mutate(nb_points=TPW.1+TPW.2) |>
  select(Player1,Player2,nb_points)

rg2013.tb |> mutate(nb_ace=ACE.1+ACE.2) |>
  group_by(Round) |>
  summarise(min=min(nb_ace),max=max(nb_ace),moy=mean(nb_ace))

rg2013.tb |> mutate(dbf=DBF.1+DBF.2) |>
  summarize(tot.df=sum(dbf,na.rm=TRUE))

rg2013.tb |> mutate(dbf=DBF.1+DBF.2) |>
  ggplot() +
  aes(x=dbf) +
  geom_histogram(bins=10) +
  theme_classic()

rg2013.tb |>
  mutate(dbf=DBF.1+DBF.2) |>
  group_by(Round) |>
  summarize(dbf=mean(dbf,na.rm=TRUE)) |>
  ggplot() +
  aes(x=Round,y=dbf) +
  geom_bar(stat="identity",fill="red") +
  theme_classic()

rg2013.tb |>
  select(Result, FSP.1, FSP.2) |>
  mutate(FSW=if_else(Result==1,FSP.1,FSP.2),FSL=if_else(Result==0,FSP.1,FSP.2)) |>
  select(FSW,FSL) |>
  ggplot() +
  geom_boxplot(aes(x = "Winner", y = FSW)) +
  geom_boxplot(aes(x = "Loser", y = FSL)) +
  labs(title = "First serve percentage", ylab="")+
  theme_minimal()