#here is my code
library(data.table)
library(dplyr)
library(ggplot2)

Introduction

Here is an intro section. Here you can explain at a high level what you did to determine who is the best kicker.

Description of Project

Talk about your data. Go into detail on what you did to subset your data, what type of results you considered, etc.

Data Visualization

Talk about your visualizations, what they show, and what you conclude. If you need to print stuff out on the screen to show the top kicker(s), talk about that also.

setwd("C:/Users/jason/Desktop/F24 Classes/IS470")

library(ggplot2)
library(data.table)
library(dplyr)
library(scales)
library(tidytext)
library(RColorBrewer)
library(kableExtra)

df <- fread("Data/NFLBDB2022/GamesGithub.csv")

df1 <- df %>%
  select(season, away_team, home_team, away_score, home_score) %>%
  filter(season != 2024) %>%
  mutate( away_team = recode(away_team, "OAK" = "LV", "SD" = "LAC", "STL" = "LA"),
          home_team = recode(home_team, "OAK" = "LV", "SD" = "LAC", "STL" = "LA"),
          winner = ifelse(away_score > home_score, away_team, home_team),
          loser  = ifelse(away_score < home_score, away_team, home_team),
          won_by = ifelse(winner == home_team, home_score - away_score, away_score - home_score)) %>%
  arrange(winner) %>%
  data.frame()

winners <- df1 %>%
  group_by(season, winner) %>%
  summarise( games_won = n(),
             tot_won_by = sum(won_by), .groups = "keep" ) %>%
  arrange(winner, season) %>%
  data.frame()

losers <- df1 %>%
  group_by(season, loser) %>%
  summarise( games_lost = n(),
             tot_lost_by = sum(won_by), .groups = "keep" ) %>%
  arrange(loser, season) %>%
  data.frame()

wins_df <- winners %>%
  inner_join(losers, by = c("season" = "season", "winner" = "loser")) %>%
  group_by(winner) %>%
  summarise( n_wins = sum(games_won),
             n_losses = sum(games_lost),
             point_diff = sum(tot_won_by) - sum(tot_lost_by),
             winrate = n_wins / (n_wins + n_losses) ) %>%
  arrange(-winrate) %>%
  data.frame()

  knitr::kable(head(wins_df, 10), caption = 'Top 10 NFL Teams by Win Rate') %>%
  kable_styling(bootstrap_options = c("striped", "hover"))
Top 10 NFL Teams by Win Rate
winner n_wins n_losses point_diff winrate
NE 304 141 3043 0.6831461
PIT 268 164 1462 0.6203704
GB 265 171 1554 0.6077982
IND 256 174 920 0.5953488
BAL 257 176 1892 0.5935335
PHI 250 184 1287 0.5760369
KC 242 187 1000 0.5641026
SEA 242 189 917 0.5614849
NO 233 189 920 0.5521327
DAL 222 196 635 0.5311005

Visualization 1: A graph that shows …

# vertical bar chart
ggplot(data = wins_df, aes(x = reorder(winner, -n_wins), y = n_wins, fill = winrate)) +
  geom_bar(stat = "identity") +
  labs(x = "Teams", y = "Number of Wins", title = "Win Rates by Team (1999 to 2024)", fill = "Win %") +
  geom_text(aes( label =  label_percent(accuracy = 1L) (winrate)), vjust = -0.5 ) +
  scale_fill_continuous(breaks = seq(.1, 1, 0.2),
                        limits = c(0, 1),
                        labels = paste0(100*seq(.1, 1, 0.2), "%"),
                        low = "red",
                        high = "forestgreen") +
  theme(plot.title = element_text(hjust = 0.50, face="bold", size=18),
        axis.text.x=element_text(size=12),
        axis.text.y=element_text(size=15),
        axis.title=element_text(size=18,face="bold"))

Visualization 2: A graph that shows …

# horizontal bar chart
ggplot(data = wins_df, aes(x = reorder(winner, n_wins), y = n_wins, fill = winrate)) +
  geom_bar(stat = "identity") +
  labs(x = "Teams", y = "Number of Wins", title = "Win Rates by Team (1999 to 2024)", fill = "Win %") +
  coord_flip() +
  geom_text(aes( label =  label_percent(accuracy = 1L) (winrate)), hjust = -0.2 ) +
  scale_fill_continuous(breaks = seq(.1, 1, 0.2),
                        limits = c(0, 1),
                        labels = paste0(100*seq(.1, 1, 0.2), "%"),
                        low = "red",
                        high = "forestgreen") +
  theme(plot.title = element_text(hjust = 0.50, face="bold", size=18),
        axis.text.x=element_text(size=12),
        axis.text.y=element_text(size=15),
        axis.title=element_text(size=18,face="bold"))

Visualization 3: A graph that shows …

wins_yr_df <- winners %>%
  inner_join(losers, by = c("season" = "season", "winner" = "loser")) %>%
  filter(season >= 2021) %>%
  group_by(winner, season) %>%
  summarise( n_wins = sum(games_won),
             n_losses = sum(games_lost),
             point_diff = sum(tot_won_by) - sum(tot_lost_by),
             winrate = n_wins / (n_wins + n_losses) ) %>%
  arrange(season, -winrate) %>%
  data.frame()

ggplot(data = wins_yr_df, aes(x = reorder_within(winner, -n_wins, season), y = n_wins, fill = winrate)) +
  geom_bar(stat = "identity") +
  labs(x = "Teams", y = "Number of Wins", title = "Win Rates by Team by Year", fill = "Win %") +
  geom_text(aes( label =  label_percent(accuracy = 1L) (winrate)), vjust = -0.5 ) +
  scale_fill_continuous(breaks = seq(.1, 1, 0.2),
                        limits = c(0, 1),
                        labels = paste0(100*seq(.1, 1, 0.2), "%"),
                        low = "red",
                        high = "forestgreen") +
  theme(plot.title = element_text(hjust = 0.50)) +
  scale_y_continuous(limits = c(0, 20)) +
  scale_x_reordered() +
  facet_wrap(~season, scales = "free", ncol=1) +
  theme(plot.title = element_text(hjust = 0.50, face="bold", size=18),
        axis.text.x=element_text(size=12),
        axis.text.y=element_text(size=15),
        axis.title=element_text(size=18,face="bold"),
        strip.text = element_text(size = 18))

Visualization 4: A graph that shows …

# create a bump chart
ranking_df <- wins_yr_df %>%
  group_by(season) %>%
  mutate(rank = rank(-winrate, ties.method = "random")) %>%
  data.frame()

cols <- colorRampPalette( brewer.pal(8, "Set2") )
myPal <- cols(32)

ggplot(ranking_df, aes(x = season, y = rank, group = winner)) +
  geom_line(aes(color = winner), linewidth = 2) +
  geom_point(shape = 21, size = 4, fill = "white") +
  scale_y_reverse(breaks = seq(32, 1, -1) ) +
  geom_text(data = ranking_df %>% filter(season == min(ranking_df$season)),
            aes(x = season, y = rank, label = winner),
            size = 3,
            hjust = 1.5) +
  geom_text(data = ranking_df %>% filter(season == max(ranking_df$season)),
            aes(x = season, y = rank, label = winner),
            size = 3,
            hjust = -0.5) +
  scale_x_continuous(breaks = min(ranking_df$season):max(ranking_df$season),
                     labels = as.character(min(ranking_df$season):max(ranking_df$season))) +
  scale_color_manual(values = myPal) +
  labs(x = "Season",
       y = "Ranking",
       title = "Team Ranking by Win Rates over Time",
       colour = "Teams") +
  theme(plot.title = element_text(hjust = 0.50, face="bold", size=18),
        axis.text.x=element_text(size=12),
        axis.text.y=element_text(size=15),
        axis.title=element_text(size=18,face="bold"))

Conclusion

Here are some general takeaways from your project.

Note

You can add captions at the bottom of images. To add a caption, include the words fig.cap=“blah blah” inside the {….} at the top of the RMarkdown code you are using to include the image. You will notice here that I can also add lines of HTML code directly into the text. Here’s something bold, something italics, something underline, and something blue.