Assignment 6

Olivia Thompson

# Q1
install.packages("pacman")
pacman::p_load(nycflights13)
View(flights)
summary(flights)

# Q2
maxdep <- max(flights$dep_delay, na.rm=TRUE)
maxdep_id <- which(flights$dep_delay==maxdep)
flights[maxdep_id, 10:12]

sortf <- arrange(flights,desc(dep_delay)) 
select(sortf, carrier, flight, tailnum, everything())

install.packages("dplyr")
library(dplyr)
sortf <- arrange(flights,desc(dep_delay)) 
select(sortf, carrier, flight, tailnum, everything())

# Q3
flights %>% 
group_by(year, month, day) %>% 
  summarise(mean = mean(dep_delay))
  
not_cancelled <- flights %>% 
  filter(!is.na(dep_delay))
not_cancelled %>% 
  group_by(year, month, day) %>% 
  summarise(mean = mean(dep_delay))


flights %>% 
  group_by(year, month, day) %>% 
  summarise(mean = mean(dep_delay, na.rm = TRUE))

# Q4
avg_arrival_delay <- flights %>%
  filter(!is.na(arr_delay)) %>%  
  group_by(tailnum) %>%
  summarise(avg_arr_delay = mean(arr_delay, na.rm = TRUE))

lowest_avg_delay_tailnum <- avg_arrival_delay %>%
  arrange(avg_arr_delay) %>%  
  slice(1) %>%                
  pull(tailnum)               

lowest_avg_delay_tailnum

# Q5
not_cancelled %>% 
  group_by(year, month, day) %>% 
  summarise(first = min(dep_time),last = max(dep_time))

not_cancelled %>% 
 group_by(year, month, day) %>% 
 summarise(
  first = min(dep_time),
  last = max(dep_time)
)

# Q6
monthly_delay_proportion <- flights %>%
  mutate(dep_delay_over_60 = dep_delay > 60) %>%  
  group_by(month) %>%
  summarise(proportion_delayed = mean(dep_delay_over_60, na.rm = TRUE)) 
monthly_delay_proportion

## Q7 
dest_carrier_counts <- flights %>%
  group_by(dest) %>%
  summarise(num_carriers = n_distinct(carrier)) %>%
  arrange(desc(num_carriers))
max_carriers <- max(dest_carrier_counts$num_carriers)

most_carriers_destinations <- dest_carrier_counts %>%
  filter(num_carriers == max_carriers)
print(most_carriers_destinations)

Q8

see blackboard

# Q9
delays <- flights %>% 
 group_by(dest) %>% 
 summarise(
  count = n(),
  dist = mean(distance, na.rm = TRUE),
  delay = mean(arr_delay, na.rm = TRUE)
 ) %>% 
 filter(count > 20, dest != "HNL")

ran - same as code from above question except for missing the plotting step