ESTUDIOS WHOTS
Christian Tabilo
2025-01-07
EXERCICIO
library(rvest)
library(stringr)
library(jsonlite)
library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ purrr 1.0.2
## ✔ forcats 1.0.0 ✔ readr 2.1.5
## ✔ ggplot2 3.5.1 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ purrr::flatten() masks jsonlite::flatten()
## ✖ readr::guess_encoding() masks rvest::guess_encoding()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errorslibrary(ggsoccer)
library(ggrepel)
("~/Downloads/Wolves 0-3 Nottingham Forest - Premier League 2024:2025 Live.html")## [1] "~/Downloads/Wolves 0-3 Nottingham Forest - Premier League 2024:2025 Live.html"# Defina o diretório onde você deseja procurar arquivos HTML
diretorio <- "~/Downloads/"
# Liste todos os arquivos com a extensão .html
arquivos_html <- list.files(path = diretorio, pattern = "\\.html$", full.names = TRUE)
# Exibir a lista de arquivos HTML
print(arquivos_html)## [1] "/Users/christiantabilojr/Downloads//aula-1-10.html"
## [2] "/Users/christiantabilojr/Downloads//aula-1-11.html"
## [3] "/Users/christiantabilojr/Downloads//aula-1-12.html"
## [4] "/Users/christiantabilojr/Downloads//aula-1-13.html"
## [5] "/Users/christiantabilojr/Downloads//aula-1-14.html"
## [6] "/Users/christiantabilojr/Downloads//aula-1-2.html"
## [7] "/Users/christiantabilojr/Downloads//aula-1-3.html"
## [8] "/Users/christiantabilojr/Downloads//aula-1-4.html"
## [9] "/Users/christiantabilojr/Downloads//aula-1-5.html"
## [10] "/Users/christiantabilojr/Downloads//aula-1-6.html"
## [11] "/Users/christiantabilojr/Downloads//aula-1-7.html"
## [12] "/Users/christiantabilojr/Downloads//aula-1-8.html"
## [13] "/Users/christiantabilojr/Downloads//aula-1-9.html"
## [14] "/Users/christiantabilojr/Downloads//aula-1.html"
## [15] "/Users/christiantabilojr/Downloads//nose.html"
## [16] "/Users/christiantabilojr/Downloads//plano-de-ensino.html"
## [17] "/Users/christiantabilojr/Downloads//principais-funções-R.html"
## [18] "/Users/christiantabilojr/Downloads//tra vs rsj.html"
## [19] "/Users/christiantabilojr/Downloads//Wolves 0-3 Nottingham Forest - Premier League 2024:2025 Live.html"# jogo 1 | johos disponiveis em que eu baixei# Define o caminho para o arquivo HTML
html_path <- "/Users/christiantabilojr/Downloads//Wolves 0-3 Nottingham Forest - Premier League 2024:2025 Live.html"# Lê o conteúdo do arquivo HTML
html_content <- read_html(html_path)
# Extrai o conteúdo de texto bruto do HTML
html_text <- html_content %>% html_text()
# Encontra o JSON usando regex
regex_pattern <- '(?<=require\\.config\\.params\\["args"\\].=.)[\\s\\S]*?;'
data_txt <- str_extract(html_text, regex_pattern)
# Faz substituições necessárias para parsear como JSON
data_txt <- gsub("matchId", '"matchId"', data_txt)
data_txt <- gsub("matchCentreData", '"matchCentreData"', data_txt)
data_txt <- gsub("matchCentreEventTypeJson", '"matchCentreEventTypeJson"', data_txt)
data_txt <- gsub("formationIdNameMappings", '"formationIdNameMappings"', data_txt)
# Remove o final }; e substitui por }
data_txt <- gsub("};$", '}', data_txt)
# Converte o texto JSON em um objeto R
data_list <- fromJSON(data_txt)
# Extrair os dados de eventos e jogadores
events <- data_list$matchCentreData$events
players <- data_list$matchCentreData$playerIdNameDictionary
# Converte em data frame
events_df <- as.data.frame(events)
players_df <- as.data.frame(players)
# inserir player df com nomes ao lado da coluna playerid
players_df <- stack(players)
events_df <- merge(events_df, players_df, by.x = "playerId", by.y = "ind", all.x = TRUE)
#names(events_df) #names sirve para ver las planillas de datos que tiene el evento
#events_df # solo la da la tabla especifica de lo que estamos buscando.analisis de datos es la información que se consigue atraves de bases de datos y se va desarollando atravez de ejecuciones de los mismos para tener información o recopilar informacion sobre un tema que queremos aprender o hacer una hipotesis
visitante = events_df%>%
filter(teamId=="174") # esto da para elegir los jugadores y las serie con el nombre del jugador sea visitante o local
#names(visitante)
EAD = visitante$type$displayName
table(EAD)## EAD
## Aerial BallRecovery BallTouch BlockedPass Card
## 26 42 33 4 2
## Challenge Clearance CornerAwarded Dispossessed End
## 4 35 8 6 3
## Error FormationChange FormationSet Foul Goal
## 2 2 1 18 3
## Interception KeeperPickup MissedShots OffsideGiven OffsidePass
## 10 7 6 4 4
## OffsideProvoked Pass Punch Save SavedShot
## 1 389 3 11 2
## ShieldBallOpp Smother Start SubstitutionOff SubstitutionOn
## 1 1 2 5 5
## Tackle TakeOn
## 18 13# Asegúrate de extraer correctamente los nombres de los eventos
visitante <- visitante %>%
mutate(displayName = unlist(type$displayName)) # Extraer nombres si es necesario
# Crear tabla resumen por jugador
summary_table <- visitante %>%
group_by(values, displayName) %>% # Agrupar por jugador y tipo de evento
summarise(event_count = n(), .groups = "drop") %>% # Contar eventos
pivot_wider(names_from = displayName, values_from = event_count, values_fill = 0) # Crear columnas para cada evento
# Mostrar tabla
print(summary_table)## # A tibble: 17 × 33
## values Aerial BallRecovery BallTouch BlockedPass CornerAwarded Dispossessed
## <chr> <int> <int> <int> <int> <int> <int>
## 1 Anthony… 1 1 3 1 1 2
## 2 Callum … 1 6 3 0 0 0
## 3 Chris W… 3 0 2 0 0 0
## 4 Elliot … 2 9 5 0 2 0
## 5 James W… 1 0 0 0 0 0
## 6 Jota Si… 1 0 2 0 0 0
## 7 Matz Se… 1 0 0 0 2 0
## 8 Morato 1 0 0 0 0 0
## 9 Morgan … 5 2 4 0 0 2
## 10 Murillo 0 4 3 0 2 1
## 11 Neco Wi… 1 5 5 1 0 0
## 12 Nicolás… 0 2 1 2 0 0
## 13 Nikola … 5 2 0 0 0 0
## 14 Ola Aina 1 9 3 0 1 0
## 15 Ryan Ya… 0 2 0 0 0 1
## 16 Taiwo A… 3 0 2 0 0 0
## 17 <NA> 0 0 0 0 0 0
## # ℹ 26 more variables: Foul <int>, OffsideGiven <int>, Pass <int>,
## # SubstitutionOff <int>, Tackle <int>, TakeOn <int>, MissedShots <int>,
## # Goal <int>, OffsidePass <int>, Card <int>, Clearance <int>, Error <int>,
## # Interception <int>, SavedShot <int>, SubstitutionOn <int>, Challenge <int>,
## # KeeperPickup <int>, Punch <int>, Save <int>, Smother <int>,
## # OffsideProvoked <int>, ShieldBallOpp <int>, End <int>,
## # FormationChange <int>, FormationSet <int>, Start <int>hist(summary_table$Aerial)
names(summary_table)## [1] "values" "Aerial" "BallRecovery" "BallTouch"
## [5] "BlockedPass" "CornerAwarded" "Dispossessed" "Foul"
## [9] "OffsideGiven" "Pass" "SubstitutionOff" "Tackle"
## [13] "TakeOn" "MissedShots" "Goal" "OffsidePass"
## [17] "Card" "Clearance" "Error" "Interception"
## [21] "SavedShot" "SubstitutionOn" "Challenge" "KeeperPickup"
## [25] "Punch" "Save" "Smother" "OffsideProvoked"
## [29] "ShieldBallOpp" "End" "FormationChange" "FormationSet"
## [33] "Start"events = BallRecovery
ggplot(summary_table, aes(x = BallRecovery,
y =values))+
geom_point(color="purple",
size = 4 )+
theme_minimal()
ggplot(summary_table, aes(x = Interception,
y =values))+
geom_point(color="purple",
size = 4 )+
geom_text(aes(label=Interception),vjust = -1, size = 3)+
theme_minimal()+labs(title="Wolves 0-3 Nottingham Forest",subtitle = "Partido Premier League",caption = "Christian Tabilo")
ggplot(summary_table, aes(x = Goal,
y =values))+
geom_point(color="purple",
size = 4 )+
geom_text(aes(label=Goal),vjust = -1, size = 3)+
theme_minimal()+labs(title="Wolves 0-3 Nottingham Forest",subtitle = "Partido Premier League",caption = "Christian Tabilo")