[HEAD]: initial commit

2026-08-04 19:19:24 +01:00
commit 2d9bfafbe6
39 changed files with 8905 additions and 0 deletions
@@ -0,0 +1,126 @@
+European_performance_data = read_csv('Data/European performance historical data.csv')
+Points_difference_data <- read_csv("Data/Points difference.csv")
+Players_used_data <- read_csv("Data/European clubs number of players used.csv")
+Top_goalscorers_data <- read_csv("Data/Average top scorers.csv")
+Market_value_data <- read_csv("Data/Market values.csv")
+gini_coeffecient_data <- Market_value_data %>%
+  select(-`Average market value of clubs`)
+all_seasons <- unique(European_performance_data$Season)
+
+overall_country_performance <- European_performance_data %>%
+  group_by(Country) %>%
+  summarise(total_performance = sum(European_performance, na.rm = TRUE)) %>%
+  arrange(desc(total_performance))
+
+#season by season performance
+country_performance_by_season <- European_performance_data %>%
+  filter(Country %in% c("Germany", "Spain", "England", "Portugal", "Italy", "France")) %>%
+  group_by(Country, Season) %>%
+  summarise(
+    European_performance = sum(European_performance, na.rm = TRUE),
+    .groups = "drop"
+  ) %>%
+  complete(Country, Season = all_seasons, fill = list(European_performance = 0))
+#season by season performance by competition
+country_performance_by_season_comp_breakdown <- European_performance_data %>%
+  filter(Country %in% c("Germany", "Spain", "England", "Portugal", "Italy", "France")) %>%
+  group_by(Country, Season) %>%
+  summarise(
+    CL = sum(European_performance[Competition == "CL"], na.rm = TRUE),
+    EL = sum(European_performance[Competition == "EL"], na.rm = TRUE),
+    .groups = "drop"
+  ) %>%
+  complete(Country, Season = all_seasons, fill = list(CL = 0, EL = 0)) %>%
+  pivot_longer(cols = c("CL", "EL"), names_to = "competition", values_to = "European_performance") %>%
+  mutate(European_performance = ifelse(competition == "CL", European_performance/2, European_performance)) #halving score for CL as had double weighting
+
+#join all metrics data together
+#impute missing Gini coefficient with average for league - assumed the same over time
+season_league_metrics_dataset <- Points_difference_data %>%
+  left_join(Players_used_data, by = c("Country", "Season")) %>%
+  left_join(Top_goalscorers_data, by = c("Country", "Season")) %>%
+  left_join(gini_coeffecient_data, by = c("Country", "Season")) %>%
+  mutate(season_start = as.integer(str_extract(Season, "^\\d{4}"))) %>%
+  group_by(Country) %>%
+  mutate(Gini_coefficient = coalesce(Gini_coefficient, mean(Gini_coefficient, na.rm = TRUE))) %>%
+  ungroup()
+
+#average country performance
+average_country_metrics <- season_league_metrics_dataset %>%
+  group_by(Country) %>%
+  summarise(across(!contains("eason"), mean, na.rm = TRUE))
+
+#scaling to min-max of variables
+average_country_metrics_scaled <- average_country_metrics
+average_country_metrics_scaled[,-1] <- lapply(average_country_metrics[,-1], function(x) {
+  (x - min(x)) / (max(x) - min(x))
+})
+
+#scaling metrics normally
+scaled_metrics_data <- season_league_metrics_dataset %>%
+  mutate(across(
+    c(First_and_second, First_and_CL, First_and_relegated, CL_and_relegated,
+      Winners_GD, Top_4_total_GD, Average_number_of_players,
+      Average_goals_by_top_3_players, Gini_coefficient),
+    ~ as.numeric(scale(.))
+  ))
+
+#join metrics data to European performance data
+#calculate European performance in next season as lead
+season_league_full_dataset <- season_league_metrics_dataset %>%
+  left_join(country_performance_by_season, by = c("Country", "Season")) %>%
+  arrange(Season, Country) %>%
+  group_by(Country) %>%
+  mutate(lead_european_performance = dplyr::lead(European_performance)) %>%
+  ungroup()
+
+#join metrics data to European performance data by competition
+#calculate European performance in next season as lead
+season_league_full_dataset_comp_breakdown <- season_league_metrics_dataset %>%
+  left_join(country_performance_by_season_comp_breakdown, by = c("Country", "Season")) %>%
+  arrange(Season, Country) %>%
+  group_by(Country, competition) %>%
+  mutate(lead_european_performance = dplyr::lead(European_performance)) %>%
+  ungroup()
+
+#full data scaled
+scaled_full_data <- scaled_metrics_data %>%
+  left_join(country_performance_by_season, by = c("Country", "Season")) %>%
+  arrange(Season, Country) %>%
+  group_by(Country) %>%
+  mutate(lead_european_performance = dplyr::lead(European_performance)) %>%
+  ungroup()
+
+#data by competition scaled
+scaled_full_data_comp_breakdown <- scaled_metrics_data %>%
+  left_join(country_performance_by_season_comp_breakdown, by = c("Country", "Season")) %>%
+  arrange(Season, Country) %>%
+  group_by(Country, competition) %>%
+  mutate(lead_european_performance = dplyr::lead(European_performance)) %>%
+  ungroup()
+
+#full dataset with competition breakdown and full
+pivoted_scaled_full_data_comp_breakdown <- scaled_full_data_comp_breakdown %>%
+  pivot_wider(names_from = competition, values_from = c(European_performance, lead_european_performance)) %>%
+  mutate(European_performance = 2*European_performance_CL + European_performance_EL,
+         lead_european_performance = 2*lead_european_performance_CL + lead_european_performance_EL)
+
+#basic profiling based on European performance
+quantile_splits <- scaled_full_data %>%
+  mutate(
+    performance_group = ntile(European_performance, 3)
+  )
+european_performance_groups_characteristics <- quantile_splits %>%
+  group_by(performance_group) %>%
+  summarise(across(where(is.numeric), mean, na.rm = TRUE)) %>%
+  select(-season_start) %>%
+  mutate(label = case_when(
+    performance_group == 1 ~ "Worst performing",
+    performance_group == 2 ~ "Middle performing",
+    performance_group == 3 ~ "Best performing"
+  )) %>%
+  mutate(performance_group = case_when(
+    label == "Worst performing" ~ 1,
+    label == "Middle performing" ~ 3,
+    label == "Best performing" ~ 2
+  ))