Assignment6!

options(repos = c(CRAN = "https://cran.rstudio.com/"))
library(nycflights13)
library(pacman)
library(dplyr)
pacman::p_load(nycflights13)

View(flights)
glimpse(flights)

summary(flights)



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())

These 2 methods would work

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



not_cancelled <- flights %>% 
  
  filter(!is.na(dep_delay))

not_cancelled %>% 
  
  group_by(year, month, day) %>% 
  
  summarise(mean = mean(dep_delay))




Tailnum_delay_avg <- flights %>% 
  
  group_by(tailnum) %>% 
  
  summarise(avg_arr_delay = mean(arr_delay))

summarise(Tailnum_delay_avg)

Sort chart by avg_arr_delay, tailnum is N560AS

flight_times <- flight_times %>%
  mutate(before_midnight = last <= 2400)
flight_times <- flight_times %>%
  arrange(last)
view(flight_times)


hourplus_delays <- flights %>%
  group_by(month) %>%
  summarise(total_flights = n(),
    delayed_flights = sum(dep_delay > 60, na.rm = TRUE))

        
hourplus_delays$delayed_flights/hourplus_delays$total_flights

carrier_number <- flights %>% group_by(dest) %>% summarize(carriers = n_distinct(carrier) %>% 
arrange(carriers))

view(carrier_number)

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")

delays