Proportion of Late Departures that Arrived Late or On-time/Early by Carrier

#Using the Flights dataset, I created a data visualization that shows the proportion of
#late departures that arrived at their
#destination either late or on-time/early. I chose to do this analysis because I was
#curious to see if airlines could make-up for
#the late departures by still getting the passengers to their destination 
#on-time or early. I selected only five popular airlines
#(Delta, Alaska Airlines, American Airlines, Frontier, and United Airlines) 
#to review in order to keep the data visualization digestible. 
#This analysis can give customers 
#an insight on their chances of early/on-time arrivals despite
#difficulties that may results in late departures. 

#PS: I am not surprised that Frontier is the lowest.

#Load in R packages and dataset

library(tidyverse)

── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ dplyr     1.1.2     ✔ readr     2.1.4
✔ forcats   1.0.0     ✔ stringr   1.5.0
✔ ggplot2   3.4.2     ✔ tibble    3.2.1
✔ lubridate 1.9.2     ✔ tidyr     1.3.0
✔ purrr     1.0.1     
── 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(nycflights13)
library(psych)

Attaching package: 'psych'

The following objects are masked from 'package:ggplot2':

    %+%, alpha

flights <- flights

#Remove and rename carrier codes

flights2 <- flights %>%
  filter(!(carrier %in% c("B6", "EV", "MQ", "US", "WN", "VX", "FL", "9E", "HA", "YV", "OO"))) %>%
  mutate(carrier = recode(carrier, "AA" = "American Airlines", "AS" = "Alaska Airlines",
                          "DL" = "Delta Airlines", "F9" = "Frontier Airlines", "UA" = "United Airlines"))

#Remove NAs from delay columns

flights3 <- flights2 %>%
  filter(!is.na(dep_delay) & !is.na(arr_delay))

#Flights that departed late but arrived early/on time

flights4 <- flights3[flights3$dep_delay > 0 & flights3$arr_delay <= 0,]

#Create column for arrival statuses (On-time/Early)

flights4ontime <- flights4 %>%
  mutate(Status = "On-time/Early")

#Flights that departed and arrived late

flights5 <- flights3[flights3$dep_delay > 0 & flights3$arr_delay > 0,]

#Create column for arrival statuses (Late)

flights5late <- flights5 %>%
  mutate(Status = "Late")

#merge on-time/early & late datasets

final <- rbind(flights4ontime, flights5late)

#create stacked bar chart

ggplot(data = final) +
 geom_bar(mapping = aes(x = carrier, fill = Status), position = "fill") +
  ggtitle("Proportion of Late Departures that Arrived Late or On-time/Early by Carrier") +
  theme(panel.background = element_rect(fill = "white")) +
  theme(plot.title = element_text(hjust = 0.5))