ggplot2 Assignment

The data used for this assignment is data from the 2021 College Football season and provides an general statistics about each team. Statistics include win percentages, offensive points per game, defensive points per game, strength of schedule and a rating based on schedule and margin of victory. The data was collected from sports-reference.com and has data for each team and season. For this assignment, I used data strictly from the 2021-22 season.

head(ncaaf_standings)

##   Rank               School Conference Overall_Wins Overall_Loses
## 2    1          Wake Forest       ACC            11             3
## 3    2              Clemson       ACC            10             3
## 4    3 North Carolina State       ACC             9             3
## 5    4           Louisville       ACC             6             7
## 6    5        Florida State       ACC             5             7
## 7    6       Boston College       ACC             6             6
##   Overall_WinPerc Conf_Wins Conf_Loses Conf_WinPerc Off_PPG Def_PPG   SRS   SOS
## 2           0.786         7          2        0.778    41.0    28.9 11.28  0.99
## 3           0.769         6          2        0.750    26.3    14.8 11.43  2.66
## 4           0.750         6          2        0.750    33.1    19.7 10.22  0.39
## 5           0.462         4          4        0.500    31.6    27.3  4.03  2.88
## 6           0.417         4          4        0.500    27.6    26.5  0.64  2.22
## 7           0.500         2          6        0.250    24.7    22.2 -1.00 -1.50
##    Bowl
## 2  TRUE
## 3  TRUE
## 4  TRUE
## 5  TRUE
## 6 FALSE
## 7  TRUE

offense = ggplot(data = ncaaf_standings, 
                  aes(x = Off_PPG, y = Overall_WinPerc, color = Conference)) +
  theme_minimal() + 
  geom_point() + 
  scale_color_viridis(discrete = TRUE) + 
  xlab("Points Scored per Game") + ylab("Win Percentage") +
  xlim(10, 50) + ylim(0, 1) +
  plot_annotation(
    title = "Average Number of Points Scored and Overall Win Percentage",
    subtitle = "Comparing the average number of points scored for each FBS football team and 
        their overall win percentage for the 2021-22 season",
    caption = "Data from Sports Reference"
  ) +
  ggrepel::geom_label_repel(data = . %>% filter(School == "Colorado State"),
                    aes(label = "CSU"), 
                    color = "darkgreen", show.legend = FALSE, fill = alpha(c("white"), 0),
                    nudge_y = 0.05, nudge_x = 3.5)

offense

defense = ggplot(data = ncaaf_standings, 
                  aes(x = Def_PPG, y = Overall_WinPerc, color = Conference)) +
  theme_minimal() + 
  geom_point() + 
  scale_color_viridis(discrete = TRUE) + 
  xlab("Points Allowed per Game") + ylab("Win Percentage") +
  xlim(10, 50) + ylim(0, 1) +
  plot_annotation(
    title = "Average Number of Points Allowed and Overall Win Percentage",
    subtitle = "Comparing the average number of points allowed for each FBS football team and 
        their overall win percentage for the 2021 season",
    caption = "Data from Sports Reference"
  ) +
  ggrepel::geom_label_repel(data = . %>% filter(School == "Colorado State"),
                    aes(label = "CSU"), 
                    color = "darkgreen", show.legend = FALSE, fill = alpha(c("white"), 0),
                    nudge_y = -0.1)

defense

ncaaf = ggplot(data = ncaaf_standings, 
                  aes(x = Off_PPG, y = Def_PPG, color = Conference)) +
  theme_minimal() + 
  geom_point() + 
  xlab("Points Scored per Game") + ylab("Points Allowed Per Game") +
  scale_color_viridis(discrete = TRUE) +
  xlim(10, 50) + ylim(5, 50) +
  theme(legend.position = "right") +
  ggrepel::geom_label_repel(data = . %>% filter(School == "Alabama"),
                    aes(label = "Alabama"), 
                    color = "red", show.legend = FALSE, fill = alpha(c("white"), 0),
                    nudge_x = 5,) +
  ggrepel::geom_label_repel(data = . %>% filter(School == "Cincinnati"),
                    aes(label = "Cincinnati"), 
                    color = "grey10", show.legend = FALSE, fill = alpha(c("white"), 0),
                    nudge_x = 0, nudge_y = -4) +
  ggrepel::geom_label_repel(data = . %>% filter(School == "Georgia"),
                    aes(label = "Georgia"), 
                    color = "black", show.legend = FALSE, fill = alpha(c("white"), 0),
                    nudge_y = -1, nudge_x = 5) +
  ggrepel::geom_label_repel(data = . %>% filter(School == "Michigan"),
                    aes(label = "Michigan"), 
                    color = "blue", show.legend = FALSE, fill = alpha(c("white"), 0),
                    nudge_y = -2, nudge_x = -5) +
  plot_annotation(
    title = "Average Points Scored vs Points Allowed for 2021-22 Season",
    subtitle = "The four teams labeled played in the 2022 College Football Playoff 
    and were considered the best four teams in college football.  Georgia defeated 
    Alabama in the championship game.",
    caption = "Data from Sports Reference"
  )

ncaaf

ncaaf1 = ggplot(data = ncaaf_standings, 
                  aes(x = Off_PPG, y = Def_PPG, color = Bowl)) +
  theme_minimal() + 
  geom_point() + 
  facet_wrap(. ~ Conference) +
  guides(color=guide_legend(title="Bowl Game?")) +
  xlab("Points Scored per Game") + ylab("Points Allowed Per Game") +
  scale_color_viridis(discrete = TRUE) +
  xlim(10, 50) + ylim(5, 50) +
  plot_annotation(
    title = "Average Points Scored vs Points Allowed for 2021-22 Season",
    subtitle = "",
    caption = "Data from Sports Reference"
  )


ncaaf1