Visualization of European basketball data
Guillermo Vinue
February 17, 2019
This document contains all the needed R code to reproduce the results described in the paper A web application for interactive visualization of European basketball data, which presents the dashboard available at https://www.uv.es/vivigui/AppEuroACB.html.
# Firstly, load BAwiR and other packages that will be used in the paper:
library(BAwiR) # 1.2
library(tidyverse) # 1.2.1
library(FSA) # 0.8.22
library(gridExtra) # 2.3# Code for Figure 1:
# Load the data_app_acb file with the ACB games from the 1985-1986 season to the 2017-2018 season:
load(url("http://www.uv.es/vivigui/softw/data_app_acb.RData"))
title <- " Number of Spanish and foreign players along the ACB seasons \n Data from www.acb.com"
get_pop_pyramid(data_app_acb, title, "eng")
# Create the data with games and players' info, add the advanced stats and compute the total numbers:
df0 <- do_join_games_bio("ACB", acb_games_1718, acb_players_1718)
df1 <- do_add_adv_stats(df0)
df2 <- do_stats(df1, "Total", "2017-2018", "ACB", "Regular Season")# Code for Figure 2:
df3 <- df2[which(df2$Position == "Center"), c("MP", "PTS", "Name", "CombinID")]
df3 <- df3[df3$MP > 100,]
ggplot(df3, aes(x = c(df3[,1])[[1]], y = c(df3[,2])[[1]], group = Name)) +
geom_point() +
geom_text(aes(label = Name), size = 2, vjust = -0.8) +
labs(x = colnames(df3)[1], y = colnames(df3)[2],
title = "ACB 2017-2018, Regular Season. Total stats. Centers.")
# Code for Table 2:
df4 <- df3 %>%
mutate(Player_info = paste("http://www.acb.com/jugador.php?id=", CombinID, sep = "")) %>%
select(-CombinID)
df5 <- df4[order(df4[,1][[1]], decreasing = TRUE),]
headtail(df5, 3)## MP PTS Name Player_info
## 1 499 271 Kelly, Ryan http://www.acb.com/jugador.php?id=54V
## 2 475 209 Thompson, Deon http://www.acb.com/jugador.php?id=54C
## 3 433 162 Abromaitis, Tim http://www.acb.com/jugador.php?id=FOI
## 76 116 56 Arteaga, Victor http://www.acb.com/jugador.php?id=768
## 77 108 34 Niang, Mamadou http://www.acb.com/jugador.php?id=SHU
## 78 104 16 Vucetic, Vasilije http://www.acb.com/jugador.php?id=51G# Code for Figure 3:
stats <- c("GP", "MP", "PTS", "FGPerc", "FTPerc", "TRB", "AST", "TOV", "PlusMinus", "PIR")
descr_stats <- c("Games played", "Minutes played", "Points", "Field goals percentage",
"Free throws percentage", "Total rebounds", "Assists", "Turnovers",
"Plus/minus", "Performance index rating")
df2_1 <- df2 %>%
select(1:5, stats, 46:49)
perc_plot_doncid <- get_bubble_plot(df2_1, "Doncic, Luka", descr_stats, 3, 7, 8) +
theme(strip.text.x = element_blank()) +
ggtitle(label = "Doncic, Luka",
subtitle = "ACB 2017-2018, Regular Season. Total stats.") +
theme(plot.title = element_text(size = 20))
perc_plot_abalde <- get_bubble_plot(df2_1, "Abalde, Alberto", descr_stats, 3, 7, 8) +
theme(strip.text.x = element_blank()) +
ggtitle(label = "Abalde, Alberto",
subtitle = "ACB 2017-2018, Regular Season. Total stats.") +
theme(plot.title = element_text(size = 20))
grid.arrange(perc_plot_doncid, perc_plot_abalde, ncol = 2)
# Code for Figure 4:
months <- c(df0 %>% distinct(Month))$Month
months_order <- c("September", "October", "November", "December", "January",
"February", "March", "April", "May", "June")
months_plot <- match(months_order, months)
months_plot1 <- months_plot[!is.na(months_plot)]
months_plot2 <- months[months_plot1]
df1_m <- df1 %>%
filter(Player.x %in% c("Doncic, Luka", "Abalde, Alberto")) %>%
group_by(Month) %>%
do(do_stats(., "Average", "2017-2018", "ACB", "Regular Season")) %>%
ungroup() %>%
mutate(Month = factor(Month, levels = months_plot2)) %>%
arrange(Month)
df1_m1 <- df1_m %>%
select(1:5, stats, 46:50) %>%
select(-EPS)
max_val <- max(df1_m1[,colnames(df1_m1) %in% stats])
min_val <- min(df1_m1[,colnames(df1_m1) %in% stats])
get_barplot_monthly_stats(df1_m1, "ACB 2017-2018, Regular Season. Monthly average stats.", 3) +
scale_y_continuous(limits = c(min_val - 10, max_val + 10))
# Code for Figure 5:
df0$Compet <- "ACB"
plot_yearly <- get_stats_seasons(df0, "ACB", c("Doncic, Luka", "Abalde, Alberto"),
stats[1:4], "Regular Season", TRUE, FALSE)
plot_yearly$gg +
labs(title = "ACB 2017-2018, Regular Season. Yearly average stats.") +
theme(strip.text.x = element_text(size = 15))
# Code for Figure 6:
levels_stats <- list("Offensive" = c("PTS", "FG", "FGA", "FGPerc",
"TwoP", "TwoPA", "TwoPPerc",
"ThreeP", "ThreePA", "ThreePPerc",
"FT", "FTA", "FTPerc", "ORB", "AST"),
"Defensive" = c("DRB", "STL", "PF"),
"Other" = c("GP", "MP", "TRB", "PlusMinus", "PIR"),
"Advanced" = c("EFGPerc", "PPS"))
get_heatmap_bb(df2, "Real_Madrid", levels_stats, "PlusMinus", 9,
paste("ACB", "2017-2018, Regular Season.", "Total stats.", sep = " "))
# Code for Figure 7:
get_shooting_plot(df2, "Real_Madrid", 3, 1, "ACB 2017-2018, Regular Season.", "en") +
theme(plot.title = element_text(size = 15))
# Code for Figure 8:
df1_10 <- df1 %>%
filter(Day <= 10)
teams <- as.character(rev(sort(unique(df2$Team))))
df_four_factors <- do_four_factors_df(df1_10, teams)
get_four_factors_plot(df_four_factors$df_rank, df_four_factors$df_no_rank,
c("Real_Madrid", "Valencia"), "en") +
ggtitle("ACB 2017-2018, Regular Season.")
# Code for Figure 9:
df0$Compet <- "ACB"
gg <- get_table_results(df0, "ACB", "2017-2018")
gg$plot_teams
# Code for Figure 10:
get_map_nats(df2) +
ggtitle("ACB 2017-2018, Regular Season.")
sessionInfo()## R version 3.4.4 (2018-03-15)
## Platform: x86_64-redhat-linux-gnu (64-bit)
## Running under: Fedora 27 (Workstation Edition)
##
## Matrix products: default
## BLAS/LAPACK: /usr/lib64/R/lib/libRblas.so
##
## locale:
## [1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C
## [3] LC_TIME=en_US.UTF-8 LC_COLLATE=en_US.UTF-8
## [5] LC_MONETARY=en_US.UTF-8 LC_MESSAGES=en_US.UTF-8
## [7] LC_PAPER=en_US.UTF-8 LC_NAME=C
## [9] LC_ADDRESS=C LC_TELEPHONE=C
## [11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C
##
## attached base packages:
## [1] stats graphics grDevices utils datasets methods base
##
## other attached packages:
## [1] bindrcpp_0.2.2 gridExtra_2.3 FSA_0.8.22 forcats_0.2.0
## [5] stringr_1.3.1 dplyr_0.7.8 purrr_0.2.4 readr_1.1.1
## [9] tidyr_0.8.0 tibble_1.4.2 ggplot2_3.1.0 tidyverse_1.2.1
## [13] BAwiR_1.2
##
## loaded via a namespace (and not attached):
## [1] nlme_3.1-131.1 archetypes_2.2-0 lubridate_1.7.2
## [4] httr_1.3.1 rprojroot_1.3-2 hunspell_2.9
## [7] tools_3.4.4 backports_1.1.2 R6_2.2.2
## [10] lazyeval_0.2.1 colorspace_1.3-2 withr_2.1.2
## [13] sp_1.2-7 mnormt_1.5-5 tidyselect_0.2.3
## [16] compiler_3.4.4 extrafontdb_1.0 flexclust_1.3-4
## [19] cli_1.0.0 rvest_0.3.2 xml2_1.1.1
## [22] labeling_0.3 scales_1.0.0 nnls_1.4
## [25] mvtnorm_1.0-6 psych_1.7.8 digest_0.6.18
## [28] foreign_0.8-69 rworldmap_1.3-6 rmarkdown_1.8
## [31] pkgconfig_2.0.1 htmltools_0.3.6 extrafont_0.17
## [34] maps_3.2.0 readxl_1.0.0 htmlwidgets_1.3
## [37] rlang_0.3.0.1 ggthemes_3.4.0 rstudioapi_0.7
## [40] circular_0.4-93 FNN_1.1 shiny_1.2.0
## [43] bindr_0.1.1 Anthropometry_1.10 jsonlite_1.5
## [46] crosstalk_1.0.0 magrittr_1.5 modeltools_0.2-21
## [49] dotCall64_0.9-5.2 Rcpp_1.0.0 munsell_0.5.0
## [52] biclust_1.2.0 abind_1.4-5 scatterplot3d_0.3-40
## [55] stringi_1.2.3 yaml_2.1.16 MASS_7.3-49
## [58] plyr_1.8.4 grid_3.4.4 maptools_0.9-2
## [61] hrbrthemes_0.1.0 parallel_3.4.4 promises_1.0.1
## [64] depth_2.1-1 crayon_1.3.4 lattice_0.20-35
## [67] haven_1.1.1 hms_0.4.1 knitr_1.19
## [70] pillar_1.1.0 boot_1.3-20 reshape2_1.4.3
## [73] stats4_3.4.4 glue_1.2.0 evaluate_0.10.1
## [76] modelr_0.1.1 spam_2.1-2 httpuv_1.4.5.1
## [79] cellranger_1.1.0 Rttf2pt1_1.3.5 ICGE_0.3
## [82] gtable_0.2.0 assertthat_0.2.0 mime_0.5
## [85] xtable_1.8-2 broom_0.4.3 later_0.7.5
## [88] shapes_1.2.3 fields_9.6 cluster_2.0.6
## [91] rgl_0.99.9