In this weeks Data Dive, we will take an introductory look into the data. This will entail creating primitive look into the numerical meaning of some of the data. After looking at the initial summary of data, we will create three novel questions to guide further investigation, and answering at least one. Lastly, we will create a visualization to better showcase and understand the data.
We begin by importing our libraries and data.
library(tidyverse) #loading libraries
## Warning: package 'tidyverse' was built under R version 4.3.2
## Warning: package 'ggplot2' was built under R version 4.3.2
## Warning: package 'tibble' was built under R version 4.3.2
## Warning: package 'tidyr' was built under R version 4.3.2
## Warning: package 'readr' was built under R version 4.3.2
## Warning: package 'purrr' was built under R version 4.3.2
## Warning: package 'dplyr' was built under R version 4.3.2
## Warning: package 'stringr' was built under R version 4.3.2
## Warning: package 'forcats' was built under R version 4.3.2
## Warning: package 'lubridate' was built under R version 4.3.2
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.4.4 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.0
## ✔ purrr 1.0.2
## ── 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(readr)
adc <- read_csv("ADC_2022_ed.csv")
## Rows: 20345 Columns: 18
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (2): carrier, airport
## dbl (16): month, arrived_flights, total_delayed, air_carrier_delay, weather_...
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
We will know take an initial look at the data. This data contains the flight information of all U.S. airports from October 2021 through October 2023. These dates are chosen as the information is provided by the FAA, the FAA has only provided this information through October 2023. The start date of October 2021 was chosen as this is when the impacts of travel from Covid was minimized.
Before we begin we must understand what a delayed flight is:
A flight is considered delayed when it arrived 15 or more minutes than the schedule. Delayed minutes are calculated for delayed flights only. When multiple causes are assigned to one delayed flight, each cause is prorated based on delayed minutes it is responsible for.
SOURCE: Bureau of Transportation Statistics, Airline Service Quality
Performance 234
When viewing the data the first questions that pops into the mind is if any airlines or airports have a greater number of delayed flight. We can look a this through filter through the airports/airlines and viewing the amount of delays.
We begin by looking at the different Airports and Airline in this data.
adc |>
select(airport) |> #We look at all the distinct Airports
distinct() |>
count()
## # A tibble: 1 × 1
## n
## <int>
## 1 373
adc |>
select(carrier) |> #We look at all the distinct airlines
distinct() |>
count()
## # A tibble: 1 × 1
## n
## <int>
## 1 17
There are 373 distinct airports and 17 distinct airlines.
We can now look at a basic summary of the data.
adc |>
select(where(is.numeric)) |>
summary()
## month arrived_flights total_delayed air_carrier_delay
## Min. : 1.000 Min. : 1.0 Min. : 0.00 Min. : 0.000
## 1st Qu.: 4.000 1st Qu.: 43.0 1st Qu.: 7.00 1st Qu.: 2.683
## Median : 6.000 Median : 90.0 Median : 17.00 Median : 7.370
## Mean : 6.487 Mean : 330.9 Mean : 67.73 Mean : 25.487
## 3rd Qu.: 9.000 3rd Qu.: 217.0 3rd Qu.: 47.00 3rd Qu.: 20.270
## Max. :12.000 Max. :18388.0 Max. :3479.00 Max. :1096.180
## NA's :7 NA's :16 NA's :7
## weather_delay national_aviation_system_delay security_delay
## Min. : 0.000 Min. : 0.00 Min. : 0.0000
## 1st Qu.: 0.000 1st Qu.: 0.75 1st Qu.: 0.0000
## Median : 0.520 Median : 3.10 Median : 0.0000
## Mean : 2.478 Mean : 16.24 Mean : 0.2072
## 3rd Qu.: 2.000 3rd Qu.: 9.56 3rd Qu.: 0.0000
## Max. :222.900 Max. :1391.74 Max. :58.6900
## NA's :7 NA's :7 NA's :7
## late_aircraft_delay cancelled diverted
## Min. : 0.00 Min. : 0.000 Min. : 0.0000
## 1st Qu.: 1.30 1st Qu.: 0.000 1st Qu.: 0.0000
## Median : 4.65 Median : 1.000 Median : 0.0000
## Mean : 23.28 Mean : 8.914 Mean : 0.7782
## 3rd Qu.: 14.41 3rd Qu.: 5.000 3rd Qu.: 1.0000
## Max. :1537.66 Max. :1565.000 Max. :153.0000
## NA's :7 NA's :7 NA's :7
## total_delayed_minutes air_carrier_delay_minutes weather_delay_minutes
## Min. : 0 Min. : 0 Min. : 0.0
## 1st Qu.: 380 1st Qu.: 134 1st Qu.: 0.0
## Median : 1084 Median : 448 Median : 22.0
## Mean : 4555 Mean : 1812 Mean : 252.9
## 3rd Qu.: 3053 3rd Qu.: 1348 3rd Qu.: 164.8
## Max. :323449 Max. :119425 Max. :24324.0
## NA's :7 NA's :7 NA's :7
## national_aviation_system_delay_minutes security_delay_minutes
## Min. : 0.0 Min. : 0.000
## 1st Qu.: 23.0 1st Qu.: 0.000
## Median : 122.0 Median : 0.000
## Mean : 765.4 Mean : 9.648
## 3rd Qu.: 411.0 3rd Qu.: 0.000
## Max. :84155.0 Max. :3551.000
## NA's :7 NA's :7
## late_aircraft_delay _minutes
## Min. : 0
## 1st Qu.: 69
## Median : 311
## Mean : 1715
## 3rd Qu.: 1089
## Max. :158653
## NA's :7
What we see is the quantile summary for the numeric data.
These questions will guide our initial approach and allow us to navigate into even deeper
Is there any airlines/airports that have an egregious amount of delays?
Which month is the worst for average delays compared to total flights.
What types of delays are most common through the different airlines/airports?
All these questions are basic, but can guide airlines and airports in improving flight scheduling by examining the delay trends.
We will focus on the first business questions. We want to know whether there is a specific airline or airport with a greater amount of delayed flights. We can view this by averaging the total delayed flights and group them by airports and airline. We compare the mean of delayed flights with the total flights to acquire a better picture.
adc |>
group_by(carrier, airport)|>
summarise(mean_flights = mean(arrived_flights),
mean_del_flights = mean(total_delayed),
total_flights = sum(arrived_flights),
total_del_flights = sum(total_delayed)) |>
arrange(desc(mean_del_flights))
## `summarise()` has grouped output by 'carrier'. You can override using the
## `.groups` argument.
## # A tibble: 1,945 × 6
## # Groups: carrier [17]
## carrier airport mean_flights mean_del_flights total_flights total_del_flights
## <chr> <chr> <dbl> <dbl> <dbl> <dbl>
## 1 DL ATL 17492. 2312 209902 27744
## 2 AA DFW 11911. 2305 142930 27660
## 3 AA CLT 8794. 1601. 105531 19209
## 4 WN DEN 6928. 1490. 83139 17886
## 5 WN LAS 6129. 1474. 73549 17686
## 6 WN MDW 5918. 1343 71013 16116
## 7 UA EWR 5132. 1335. 61582 16022
## 8 B6 JFK 3933. 1285. 47191 15421
## 9 WN DAL 5325. 1240. 63902 14886
## 10 UA DEN 6758. 1170. 81090 14042
## # ℹ 1,935 more rows
adc |>
group_by(airport) |>
summarise(mean_flights = mean(arrived_flights),
mean_del_flights = mean(total_delayed),
total_flights = sum(arrived_flights),
total_del_flights = sum(total_delayed)) |>
arrange(desc(mean_del_flights))
## # A tibble: 373 × 5
## airport mean_flights mean_del_flights total_flights total_del_flights
## <chr> <dbl> <dbl> <dbl> <dbl>
## 1 DEN 2225. 443. 271459 54028
## 2 DFW 1962. 382. 276711 53924
## 3 MCO 1359. 374. 146784 40360
## 4 DAL 1619. 372. 66378 15267
## 5 JFK 1453. 352. 136554 33132
## 6 ATL 1892. 300. 317910 50350
## 7 LAS 1219. 299. 175519 43040
## 8 MDW 1303. 295. 76882 17412
## 9 LGA 1283. 290. 169414 38226
## 10 ORD 1619. 286. 260587 46027
## # ℹ 363 more rows
adc |>
group_by(carrier) |>
summarise(mean_flights = mean(arrived_flights),
mean_del_flights = mean(total_delayed),
total_flights = sum(arrived_flights),
total_del_flights = sum(total_delayed)) |>
arrange(desc(mean_del_flights))
## # A tibble: 17 × 5
## carrier mean_flights mean_del_flights total_flights total_del_flights
## <chr> <dbl> <dbl> <dbl> <dbl>
## 1 WN 1018. 238. 1307149 305255
## 2 AA 645. 141. 874145 190872
## 3 B6 349. 109. 273058 85373
## 4 UA 479. 90.2 626473 118018
## 5 NK 343. 81.8 232400 55480
## 6 HA 283. 65.6 73865 17131
## 7 AS 234. 46.2 228384 45003
## 8 F9 142. 43.7 155482 47981
## 9 OH 193. 36.1 214450 40071
## 10 9E 195. 30.6 231941 36473
## 11 QX 157. 25.6 88791 14497
## 12 G4 77.5 25.4 116877 38373
## 13 DL NA NA NA NA
## 14 MQ NA NA NA NA
## 15 OO NA NA NA NA
## 16 YV NA NA NA NA
## 17 YX NA NA NA NA
Looking at the numeric summaries, we see Denver International has the largest average amount of delayed flights, but also has one of the largest number of flights within this data.
Looking at the carriers, Southwest Airlines has the largest average delayed flights , and one of the largest amount of total flights.
If we wanted to further divulge into this business question we could try and understand the type of delays within DEN airport and Southwest Airlines.
We will now look at a visual summary of the delayed flights. We can visualize the amount of delayed flights by each airline.
adc|>
group_by(month, carrier, airport) |>
ggplot() +
geom_bar(mapping = aes(x = carrier, fill = total_delayed)) +
labs(title = "Delayed Flights By Airline",
x = "Airline", y = "Total") +
scale_x_discrete(guide = guide_axis(angle = 90)) +
theme_classic()
## Warning: The following aesthetics were dropped during statistical transformation: fill
## ℹ This can happen when ggplot fails to infer the correct grouping structure in
## the data.
## ℹ Did you forget to specify a `group` aesthetic or to convert a numerical
## variable into a factor?
And now we can see the total amount of delayed minutes by month.
adc |>
group_by(month, carrier, airport) |>
ggplot() +
geom_col(mapping = aes(month, total_delayed_minutes)) +
theme_light()
## Warning: Removed 7 rows containing missing values (`position_stack()`).