NYC Flights Revised Assignment

Use the Dataset NYC Flights23 to Explore Airline Carriers On-Time Performance

# Library and data loading
library(tidyverse)

── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ dplyr     1.1.4     ✔ readr     2.1.5
✔ forcats   1.0.0     ✔ stringr   1.5.1
✔ ggplot2   3.5.2     ✔ tibble    3.2.1
✔ lubridate 1.9.4     ✔ tidyr     1.3.1
✔ purrr     1.0.4     
── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()
ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

library(nycflights23)
data("flights")
data("airlines")

data(flights)
data(airlines)

glimpse(flights)

Rows: 435,352
Columns: 19
$ year           <int> 2023, 2023, 2023, 2023, 2023, 2023, 2023, 2023, 2023, 2…
$ month          <int> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1…
$ day            <int> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1…
$ dep_time       <int> 1, 18, 31, 33, 36, 503, 520, 524, 537, 547, 549, 551, 5…
$ sched_dep_time <int> 2038, 2300, 2344, 2140, 2048, 500, 510, 530, 520, 545, …
$ dep_delay      <dbl> 203, 78, 47, 173, 228, 3, 10, -6, 17, 2, -10, -9, -7, -…
$ arr_time       <int> 328, 228, 500, 238, 223, 808, 948, 645, 926, 845, 905, …
$ sched_arr_time <int> 3, 135, 426, 2352, 2252, 815, 949, 710, 818, 852, 901, …
$ arr_delay      <dbl> 205, 53, 34, 166, 211, -7, -1, -25, 68, -7, 4, -13, -14…
$ carrier        <chr> "UA", "DL", "B6", "B6", "UA", "AA", "B6", "AA", "UA", "…
$ flight         <int> 628, 393, 371, 1053, 219, 499, 996, 981, 206, 225, 800,…
$ tailnum        <chr> "N25201", "N830DN", "N807JB", "N265JB", "N17730", "N925…
$ origin         <chr> "EWR", "JFK", "JFK", "JFK", "EWR", "EWR", "JFK", "EWR",…
$ dest           <chr> "SMF", "ATL", "BQN", "CHS", "DTW", "MIA", "BQN", "ORD",…
$ air_time       <dbl> 367, 108, 190, 108, 80, 154, 192, 119, 258, 157, 164, 1…
$ distance       <dbl> 2500, 760, 1576, 636, 488, 1085, 1576, 719, 1400, 1065,…
$ hour           <dbl> 20, 23, 23, 21, 20, 5, 5, 5, 5, 5, 5, 6, 5, 6, 6, 6, 6,…
$ minute         <dbl> 38, 0, 44, 40, 48, 0, 10, 30, 20, 45, 59, 0, 59, 0, 0, …
$ time_hour      <dttm> 2023-01-01 20:00:00, 2023-01-01 23:00:00, 2023-01-01 2…

glimpse(airlines)

Rows: 14
Columns: 2
$ carrier <chr> "9E", "AA", "AS", "B6", "DL", "F9", "G4", "HA", "MQ", "NK", "O…
$ name    <chr> "Endeavor Air Inc.", "American Airlines Inc.", "Alaska Airline…

Data clean up

# removal of remove na's for distance, arr_delay, departure delay
flights_nona <- flights |>
  filter(!is.na(distance) & !is.na(arr_delay) & !is.na(dep_delay))  

Join the delay_punctuality dataset with the airlines dataset including removal of “Inc.” or “Co.” from the Carrier Name

flights2 <- left_join(flights_nona, airlines, by = "carrier")
flights2$name <- gsub("Inc\\.|Co\\.", "", flights2$name)

Plot visualizing distribution of late arrivals flights (arrival delay > 0 minutes) by carrier and airport of origin

# Load ggplot2
library(ggplot2)

# Filter data for late arrival
late_arrivals <- flights |>
filter(arr_delay > 0) |>
group_by(carrier, origin) |>
summarise(count = n(), .groups = "drop")

# Plot distribution of late arrivals
ggplot(late_arrivals, aes(x = carrier, y = count, fill = origin)) +
  geom_bar(stat = "identity", position = "dodge") +
  labs(
    title = "Distribution of Late Arrivals by Carrier and Airport of Origin",
    x = "Carrier",
    y = "Number of Late Arrivals",
    fill = "Origin Airport",
    caption = "Data Source: nycflights13 package"
  ) +
  theme_minimal()

# # used previous class notes and videos