##install.packages("dplyr")
##install.packages("readr")
##Name: nombre del jugador
##Club: club en el que juega
##Nationality: nacionalidad del jugador
##Position: posicion en el campo del jugador
##Age: edad del jugador
##Matches: partidos jugados
##Starts: partifos jugados desde el incio
##Mins: minutos jugados
##Goals: goles realizador por el jugador
##Assists: asistencia realizadas por el jugador
##Passes_Attempted: pases realizados
##Perc_Passes_Completed: pases completados correctamente
##Penalty_Goals: goles de penales
##Penalty_Attempted: penales lanzados
##xG
##xA
##Yellow_Cards: tarjetas amarillas
##Red_Cards: tarjetas rojas
##variables cuantitativas: Age, Matches, Starts, Mins, Goals, Assists, Passes_Attempted, Perc_Passes_Completed, Penalty_Goals, Penalty_Attempted, xG, xA, Yellow_Cards, Red_Cards
##variables cualitativas: Name, Club, Nationality, Position
library(dplyr)
##
## Adjuntando el paquete: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(readr)
library(dslabs)
library(viridisLite)
library(RColorBrewer)
library(ggplot2)
library(plotly)
##
## Adjuntando el paquete: 'plotly'
## The following object is masked from 'package:ggplot2':
##
## last_plot
## The following object is masked from 'package:stats':
##
## filter
## The following object is masked from 'package:graphics':
##
## layout
# Carga de archivo EPL_20_21.csv
statsPremier <- read.csv("EPL_20_21.csv")
head(statsPremier)
## Name Club Nationality Position Age Matches Starts Mins Goals
## 1 Mason Mount Chelsea ENG MF,FW 21 36 32 2890 6
## 2 Edouard Mendy Chelsea SEN GK 28 31 31 2745 0
## 3 Timo Werner Chelsea GER FW 24 35 29 2602 6
## 4 Ben Chilwell Chelsea ENG DF 23 27 27 2286 3
## 5 Reece James Chelsea ENG DF 20 32 25 2373 1
## 6 César Azpilicueta Chelsea ESP DF 30 26 24 2188 1
## Assists Passes_Attempted Perc_Passes_Completed Penalty_Goals
## 1 5 1881 82.3 1
## 2 0 1007 84.6 0
## 3 8 826 77.2 0
## 4 5 1806 78.6 0
## 5 2 1987 85.0 0
## 6 2 2015 87.5 0
## Penalty_Attempted xG xA Yellow_Cards Red_Cards
## 1 1 0.21 0.24 2 0
## 2 0 0.00 0.00 2 0
## 3 0 0.41 0.21 2 0
## 4 0 0.10 0.11 3 0
## 5 0 0.06 0.12 3 0
## 6 0 0.03 0.11 5 1
#se realiza el factor sobre la variable Position
graVar <- levels(factor(statsPremier$Position))
print(graVar)
## [1] "DF" "DF,FW" "DF,MF" "FW" "FW,DF" "FW,MF" "GK" "MF" "MF,DF"
## [10] "MF,FW"
##se crea tabla statsPremierGK para identificar que jugadores son arqueros, donde
##su posicion dea GK pondra si para el resto pondra no
statsPremierGK <- statsPremier %>%
mutate(Position = ifelse(Position == "GK", "SI", "NO"))
head(statsPremierGK)
## Name Club Nationality Position Age Matches Starts Mins Goals
## 1 Mason Mount Chelsea ENG NO 21 36 32 2890 6
## 2 Edouard Mendy Chelsea SEN SI 28 31 31 2745 0
## 3 Timo Werner Chelsea GER NO 24 35 29 2602 6
## 4 Ben Chilwell Chelsea ENG NO 23 27 27 2286 3
## 5 Reece James Chelsea ENG NO 20 32 25 2373 1
## 6 César Azpilicueta Chelsea ESP NO 30 26 24 2188 1
## Assists Passes_Attempted Perc_Passes_Completed Penalty_Goals
## 1 5 1881 82.3 1
## 2 0 1007 84.6 0
## 3 8 826 77.2 0
## 4 5 1806 78.6 0
## 5 2 1987 85.0 0
## 6 2 2015 87.5 0
## Penalty_Attempted xG xA Yellow_Cards Red_Cards
## 1 1 0.21 0.24 2 0
## 2 0 0.00 0.00 2 0
## 3 0 0.41 0.21 2 0
## 4 0 0.10 0.11 3 0
## 5 0 0.06 0.12 3 0
## 6 0 0.03 0.11 5 1
tabla_GK <- table(statsPremierGK$Position)
#Crear grafica de barras
colores <- c("red", "orange")
bp_GK <- barplot(tabla_GK,
main="Arqueros en los equipos de la premier league",
ylab="Frecuencia",
xlab="arqueros",
ylim = c(0, max(tabla_GK) * 1.2),
col = colores)
text(bp_GK, tabla_GK, labels = tabla_GK, pos = 3, cex = 0.8, col = "black")
#grafico circular
group_GK <- statsPremierGK %>% group_by(Position) %>%
summarise(cantidad = n())
totalce <- sum(group_GK$cantidad)
stats1 <- (group_GK$cantidad/totalce) * 100
stats1
## [1] 92.105263 7.894737
pie(tabla_GK, labels = paste0(group_GK$Position, "\n", round(stats1,1), "%"),col = rocket(4), main = "Diagrama circular", border = rocket(4))
legend("bottomright",legend = names(tabla_GK),cex = 0.75,fill=rocket(4))
# Top 10 de jugadores con mas goles
topGoleadores <- statsPremier %>%
select(Name, Goals) %>%
top_n(n =10, wt = Goals) %>%
arrange(desc(Goals))
topGoleadores$Goals <- as.numeric(gsub(",", "", topGoleadores$Goals))
topGoleadores
## Name Goals
## 1 Harry Kane 23
## 2 Mohamed Salah 22
## 3 Bruno Fernandes 18
## 4 Son Heung-min 17
## 5 Patrick Bamford 17
## 6 Dominic Calvert-Lewin 16
## 7 Jamie Vardy 15
## 8 Ollie Watkins 14
## 9 İlkay Gündoğan 13
## 10 Alexandre Lacazette 13
ggplot(topGoleadores, aes(x = reorder(Name, Goals), y = Goals)) +
geom_bar(stat = "identity", fill = "#4682B4") +
geom_text(aes(label = Goals), vjust = -0.3, size = 3) + # Agregar texto a las barras
coord_flip() +
labs(title = "Top 10 goleadores",
x = "jugador",
y = "goles") +
scale_y_continuous(labels = scales::comma) +
theme_minimal()
###Histograma para ver la distribución de la edad de los jugadores.
edadJugadores <- ggplot(statsPremier, aes(x = Age, fill = factor(Age))) +
geom_histogram(binwidth = 1) +
labs(title = "Distribución de Edades de los Jugadores",
fill = "Edad",
y = "Cantidad de Jugadores") +
scale_fill_brewer(palette = "Set3") +
scale_x_continuous(breaks = seq(0, max(statsPremier$Age), by = 1))
edadJugadoresGrapHisto <- ggplotly(edadJugadores)
## Warning in RColorBrewer::brewer.pal(n, pal): n too large, allowed maximum for palette Set3 is 12
## Returning the palette you asked for with that many colors
edadJugadoresGrapHisto
### pases completados por posicion
pasesComPos <- ggplot(statsPremier, aes(x = Position, y = Perc_Passes_Completed, fill = Position)) +
geom_bar(stat = "summary", fun = "mean") +
labs(title = "Porcentaje de Pases Completados por Posición",
x = "Posición",
y = "Porcentaje de Pases Completados (%)") +
theme_minimal() +
scale_fill_brewer(palette = "Set2") +
scale_y_continuous(limits = c(0, 100), expand = c(0, 0)) +
geom_text(stat = "summary", fun = "mean", aes(label = round(..y.., 2)), vjust = -0.5) #
grapasesComPos <- ggplotly(pasesComPos)
## Warning: The dot-dot notation (`..y..`) was deprecated in ggplot2 3.4.0.
## ℹ Please use `after_stat(y)` instead.
## ℹ The deprecated feature was likely used in the base package.
## Please report the issue to the authors.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
## Warning: Removed 2 rows containing non-finite outside the scale range
## (`stat_summary()`).
## Removed 2 rows containing non-finite outside the scale range
## (`stat_summary()`).
## Warning in RColorBrewer::brewer.pal(n, pal): n too large, allowed maximum for palette Set2 is 8
## Returning the palette you asked for with that many colors
grapasesComPos
##goles por minutos jugados de los delanteros
fw_stats <- statsPremier %>%
filter(Position %in% c("FW", "MF"))
golesMinutps <- ggplot(fw_stats, aes(x = Mins, y = Goals, color = Position, text = Name)) +
geom_point(size = 3, alpha = 0.7) + # Ajustar el tamaño y la transparencia de los puntos
labs(title = "Relación entre Minutos Jugados y Goles (FW y MF)",
x = "Minutos Jugados",
y = "Goles",
color = "Posición") +
theme_minimal() +
scale_color_brewer(palette = "Set1")
gragolesMinutps <- ggplotly(golesMinutps, tooltip = "text")
gragolesMinutps
##distribucion de goles por posicion
golesposi <- ggplot(statsPremier, aes(x = Position, y = Goals, fill = Position)) +
geom_boxplot() +
labs(title = "Distribución de Goles por Posición",
x = "Posición",
y = "Goles") +
theme_minimal() +
scale_fill_manual(values = c("FW" = "blue", "MF" = "green", "DF" = "red", "GK" = "purple"))
gragolesposi <- ggplotly(golesposi)
gragolesposi