NFL

Data-Driven Mastery: Unlocking Business Potential

Author

Andrew Cox

1 NFL

Question Answers

Q2a= NFL2022_stuffs <- NFL2022_stuffs[!is.na(NFL2022_stuffs$posteam), ]

Q2b summary_df <- NFL2022_stuffs %>% filter(wp > 0.2 & wp < 0.75 & down <= 2 & half_seconds_remaining > 120) %>% group_by(posteam) %>% summarise(mean_pass = mean(pass, na.rm = TRUE))

Q2c Ggplot(data=NFL2022_stuffs)+ Geom_point(mapping=aes(x=percentage of pass plays, y=Team with possession))

Q2d NFL2022_epa <- read_csv(‘https://bcdanl.github.io/data/NFL2022_epa.csv’)

NFL2022_stuffs_EPA <- NFL2022_stuffs %>% left_join(NFL2022_epa[, c(“play_id”, “passer”, “receiver”, “epa”)], by = “play_id”) %>% filter(!is.na(passer))

Q2e

ggplot(NFL2022_stuffs_EPA, aes(x = week, y = epa, group = passer, color = passer)) + geom_line() + labs(title = “J.Allen v.s. P.Mahomes weekly epa”, x = “Week”, y = “Mean EPA”)

Q2f:

epa_diff <- NFL2022_stuffs_EPA %>% filter(passer %in% c(“J.Allen”, “P.Mahomes”)) %>% group_by(week, passer) %>% summarise(epa_diff = mean(epa)) %>% spread(passer, epa_diff) %>% mutate(diff = J.Allen - P.Mahomes)

Q2g: passers_summary <- NFL2022_stuffs_EPA %>% group_by(posteam, passer) %>% summarise(mean_epa = mean(epa), n_pass = n()) %>% group_by(passer) %>% filter(n_pass >= quantile(n_pass, 0.75)) %>% top_n(10, wt = mean_epa)