soccer.R

library(dplyr)
library(ggplot2)
library(httr)


setwd("C:/Dropbox/Projects/20160206_Soccer_Scores")
if (!file.exists("20160206_Soccer_Scores.csv.gz")) {
  cat("must reread")
}

if (!file.exists("20160206_Soccer_Scores.csv.gz"))
{
  cat("Reading data from server\n")
  STARTYEAR = 1993
  STOPYEAR = 2015 #Stop at 2015 to get 2015-2016 data
  yearstrings = vector(mode = "character", length = STOPYEAR - STARTYEAR +
                         1)
  for (i in STARTYEAR:STOPYEAR) {
    yearstrings[i - STARTYEAR + 1] =
      paste(
        substr(as.character(i), start = 3, stop = 4),
        substr(as.character(i + 1), start = 3, stop = 4),
        sep = ""
      )
  }
  
  reslist = vector(mode = "list", length = 1000)
  i = 1
  for (yearstring in yearstrings) {
    for (confstring in c("E0", "E1", "E2", "E3", "EC")) {
      aurl = paste(
        "http://www.football-data.co.uk/mmz4281/",
        yearstring,
        "/",
        confstring,
        ".csv",
        sep = ""
      )
      if (http_status(GET(aurl))$category == "Success")
      {
        reslist[[i]] = read.csv(url(aurl))
        i = i + 1
      } else {
        cat("Failed: ", aurl, "\n")
      }
    }
  }
  if (exists("reslist2")) {
    rm(reslist2)
  }
  reslist2 = vector(mode = "list", length = 50)
  for (i in 1:(5 * (STOPYEAR - STARTYEAR + 1))) {
    reslist2[[i]] = reslist[[i]][, c(1:6)]
  }
  df = do.call(rbind, reslist2)
  df = subset(df, !is.na(FTHG))
  write.csv(df,
            file = gzfile("20160206_Soccer_Scores.csv.gz"),
            row.names = FALSE)
}

get_neighbors = function(low, high) {
  #returns own score plus neighbors
  if (high < low)
    stop("high > low in get_neighbors")
  rbind(expand.grid(a = (low - 1):(low + 1), b = high),
        expand.grid(a = low, b = (high - 1):(high + 1))) %>%
    filter(a >= 0 &
             b >= 0 &
             b >= a) %>%
    mutate(neighbor = paste(b, a, sep = "-"),
           neighbor_group = paste(high, low, sep = "-")) %>%
    group_by(neighbor_group, neighbor) %>%
    summarise()
}

#create the neighbor data frame ndf
curr = 1
reslist = vector(mode = "list", length = 1000)
for (i in 0:11) {
  for (j in i:11) {
    reslist[[curr]] = get_neighbors(i, j)
    curr = curr + 1
  }
}

ndf = do.call('rbind', reslist)
ndf_summ = ndf %>% group_by(neighbor_group) %>% summarise(count = length(neighbor)) %>% arrange(-count) %>% ungroup()


df = read.csv("20160206_Soccer_Scores.csv.gz")

df = df %>%
  mutate(
    Low = ifelse(FTHG < FTAG, FTHG, FTAG),
    High = ifelse(FTHG < FTAG, FTAG, FTHG),
    Total = FTHG + FTAG
  )

#Total points scored hist
p = ggplot(df, aes(x = Total))
p = p + geom_bar(
  stat = "bin",
  binwidth = 1,
  fill = "green",
  color = "black",
  width = 2,
  alpha = .2
)
p = p + scale_x_continuous(breaks = seq(-.5, 12.5, by = 1),
                           labels = c("", 0:12))
p = p + coord_cartesian(xlim = c(0.1, 12))
p = p + labs(x = "Total Goals", y = "Matches", title = "Distribution of Total Goals / Match \n(N = 52,017 Matches)")
p = p + theme(panel.grid = element_blank())
p
ggsave(
  plot = p,
  file = "Total_Points_Scored.png",
  width = 4,
  height = 4
)

matcher =
  rbind(expand.grid(1, 1:3),
        expand.grid(0:2, 2))[-5, ] %>%
  mutate(match = TRUE)
names(matcher) = c("Low", "High", "Match")

df = left_join(df, matcher) %>%
  mutate(Score = paste(High, Low, sep = "-"))

df_summ = df %>% group_by(Score) %>%
  summarise(Count = n(),
            Goals = Low[1] + High[1]) %>% ungroup()

df_summ = df_summ %>%
  arrange(-Count) %>%
  mutate(CumProp = cumsum(Count) / sum(Count),
         Prop = Count / sum(Count))

df_summ2 = df_summ %>%
  group_by(Goals) %>%
  summarise(Proportion = sum(Prop)) %>%
  ungroup() %>%
  mutate(TotalProp = cumsum(Proportion))

p = ggplot(df_summ %>% filter(CumProp < .95), aes(y = 100 * Prop, x = reorder(Score, Prop))) +
  geom_bar(
    stat = 'identity',
    fill = "green",
    color = "black",
    alpha = .2
  ) +
  coord_flip() +
  labs(x = "Score", y = "Percentage of Games", title = "Most Common Final Scores") +
  theme(legend.position = "bottom")
p = p + theme(panel.grid.major = element_blank())
p
ggsave(
  plot = p,
  file = "Most_Common_Scores.png",
  width = 4,
  height = 4
)
###NOW JUST JOIN df_summ and NDF by x=Score y=neighbor


#Games within 1 point hist
plot_data = left_join(ndf, df_summ, by = c("neighbor" = "Score")) %>% select(-CumProp) %>%
  group_by(neighbor_group) %>%
  summarise(
    group_count = sum(Count, na.rm = TRUE),
    group_prop = sum(Prop, na.rm = TRUE),
    obs = n()
  ) %>%
  arrange(-group_count) %>%
  ungroup() %>%
  filter(group_count > 0) %>%
  filter(group_prop > .1)

plot_data$score = factor(plot_data$neighbor_group, levels = as.character(plot_data$neighbor_group))

p = ggplot(plot_data, aes(x = score, y = 100 * group_prop))
p = p + geom_bar(
  stat = "identity",
  fill = "green",
  color = "black",
  alpha = .2
)
p = p + labs(x = "Score", y = "% of Matches Within 1 Point of Score",
             title = "% of Matches Within 1 Point \nof Various Scores")
p = p + scale_y_continuous(breaks = seq(0, 55, by = 5))
p = p + theme(panel.grid.major = element_blank())
p
ggsave(
  plot = p,
  file = "Within_One_Point.png",
  width = 4,
  height = 4
)

#show all the games within 1 of a given score
plot_data = left_join(ndf, df_summ, by = c("neighbor" = "Score"))
plot_data = subset(plot_data, neighbor_group %in% c("2-1", "2-0", "1-0", "1-1"))
plot_data$neighbor_group = factor(plot_data$neighbor_group, levels = c("2-1", "2-0", "1-0", "1-1"))
p = ggplot(plot_data, aes(x = neighbor, y = Count))
p = p + geom_bar(
  stat = "identity",
  fill = "green",
  color = "black",
  alpha = .2
)
p = p + labs(x = "Scores in Score Group", y = "Number of Matches", title =
               "Frequency of Scores Within Score Groups")
p = p + facet_grid(neighbor_group ~ .)
p
ggsave(
  plot = p,
  file = "Breakdown.png",
  width = 4,
  height = 4
)