Nandini_Agarwal_Assignment08
Nandini
2024-03-22
library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.3 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ ggplot2 3.4.4 ✔ tibble 3.2.1
## ✔ lubridate 1.9.2 ✔ 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 errorslibrary(ggplot2)
library(dplyr)airlines = read.csv("~/Desktop/BANA 4137/airlines.csv", header = TRUE, stringsAsFactors = FALSE, na.strings = "")
airports = read.csv("~/Desktop/BANA 4137/airports.csv", header = TRUE, stringsAsFactors = FALSE, na.strings = "")
CVG_Flights = read.csv("~/Desktop/BANA 4137/CVG_Flights.csv", header = TRUE, stringsAsFactors = FALSE, na.strings = "")QUESTION 1:
cat("CVG_Flights.csv - Variables:", length(names(CVG_Flights)), "\n")## CVG_Flights.csv - Variables: 27cat("CVG_Flights.csv - Observations:", nrow(CVG_Flights), "\n")## CVG_Flights.csv - Observations: 7763missing_values <- colSums(is.na(CVG_Flights))
if (any(missing_values > 0)) {
cat("\nMissing Values in CVG_Flights.csv:\n")
print(missing_values[missing_values > 0])
} else {
cat("\nNo missing values in CVG_Flights.csv\n")
}##
## Missing Values in CVG_Flights.csv:
## DEPARTURE_TIME DEPARTURE_DELAY TAXI_OUT WHEELS_OFF
## 370 370 378 378
## ELAPSED_TIME AIR_TIME WHEELS_ON TAXI_IN
## 392 392 381 381
## ARRIVAL_TIME ARRIVAL_DELAY CANCELLATION_REASON AIR_SYSTEM_DELAY
## 381 392 7385 5814
## SECURITY_DELAY AIRLINE_DELAY LATE_AIRCRAFT_DELAY WEATHER_DELAY
## 5814 5814 5814 5814QUESTION 2:
summary_stats <- summary(CVG_Flights)
summary_stats## FLIGHT_DATE AIRLINE FLIGHT_NUMBER ORIGIN_AIRPORT
## Length:7763 Length:7763 Min. : 62 Length:7763
## Class :character Class :character 1st Qu.:1908 Class :character
## Mode :character Mode :character Median :3246 Mode :character
## Mean :3194
## 3rd Qu.:4536
## Max. :6297
##
## DESTINATION_AIRPORT SCHEDULED_DEPARTURE DEPARTURE_TIME DEPARTURE_DELAY
## Length:7763 Length:7763 Length:7763 Min. :-24.00
## Class :character Class :character Class :character 1st Qu.: -5.00
## Mode :character Mode :character Mode :character Median : -1.00
## Mean : 12.35
## 3rd Qu.: 12.00
## Max. :708.00
## NA's :370
## TAXI_OUT WHEELS_OFF SCHEDULED_TIME ELAPSED_TIME
## Min. : 1.00 Length:7763 Min. : 60.0 Min. : 49.0
## 1st Qu.: 12.00 Class :character 1st Qu.: 85.0 1st Qu.: 83.0
## Median : 15.00 Mode :character Median :126.0 Median :123.0
## Mean : 18.52 Mean :128.1 Mean :127.3
## 3rd Qu.: 21.00 3rd Qu.:156.0 3rd Qu.:152.0
## Max. :122.00 Max. :313.0 Max. :340.0
## NA's :378 NA's :392
## AIR_TIME DISTANCE WHEELS_ON TAXI_IN
## Min. : 36.0 Min. : 229.0 Length:7763 Min. : 1.000
## 1st Qu.: 56.0 1st Qu.: 308.0 Class :character 1st Qu.: 5.000
## Median : 99.0 Median : 589.0 Mode :character Median : 6.000
## Mean :100.4 Mean : 675.9 Mean : 8.448
## 3rd Qu.:125.0 3rd Qu.: 871.0 3rd Qu.: 9.000
## Max. :319.0 Max. :2036.0 Max. :128.000
## NA's :392 NA's :381
## SCHEDULED_ARRIVAL ARRIVAL_TIME ARRIVAL_DELAY DIVERTED
## Length:7763 Length:7763 Min. :-56.00 Min. :0.000000
## Class :character Class :character 1st Qu.:-12.00 1st Qu.:0.000000
## Mode :character Mode :character Median : -2.00 Median :0.000000
## Mean : 10.65 Mean :0.001803
## 3rd Qu.: 16.00 3rd Qu.:0.000000
## Max. :716.00 Max. :1.000000
## NA's :392
## CANCELLED CANCELLATION_REASON AIR_SYSTEM_DELAY SECURITY_DELAY
## Min. :0.00000 Length:7763 Min. : 0.00 Min. :0.00
## 1st Qu.:0.00000 Class :character 1st Qu.: 0.00 1st Qu.:0.00
## Median :0.00000 Mode :character Median : 10.00 Median :0.00
## Mean :0.04869 Mean : 16.35 Mean :0.01
## 3rd Qu.:0.00000 3rd Qu.: 23.00 3rd Qu.:0.00
## Max. :1.00000 Max. :258.00 Max. :9.00
## NA's :5814 NA's :5814
## AIRLINE_DELAY LATE_AIRCRAFT_DELAY WEATHER_DELAY
## Min. : 0.00 Min. : 0.00 Min. : 0.000
## 1st Qu.: 0.00 1st Qu.: 0.00 1st Qu.: 0.000
## Median : 0.00 Median : 2.00 Median : 0.000
## Mean : 17.06 Mean : 23.24 Mean : 3.873
## 3rd Qu.: 18.00 3rd Qu.: 30.00 3rd Qu.: 0.000
## Max. :435.00 Max. :435.00 Max. :638.000
## NA's :5814 NA's :5814 NA's :5814ggplot(CVG_Flights, aes(x = DEPARTURE_DELAY)) +
geom_histogram(binwidth = 10, fill = "pink", color = "black") +
labs(title = "Distribution of Departure Time",
x = "Departure Time (minutes)",
y = "Frequency")## Warning: Removed 370 rows containing non-finite values (`stat_bin()`).
ggplot(CVG_Flights, aes(x = AIR_TIME)) +
geom_histogram(binwidth = 10, fill = "darkred", color = "black") +
labs(title = "Distribution of Air Time",
x = "Air Time (minutes)",
y = "Frequency")## Warning: Removed 392 rows containing non-finite values (`stat_bin()`).
QUESTION 3:
ggplot(CVG_Flights, aes(x = AIR_TIME, y = DEPARTURE_DELAY)) +
geom_point() +
labs(title = "Association between Departure Time and Air Time",
x = "Air Time (minutes)",
y = "Departure Time (minutes)")## Warning: Removed 392 rows containing missing values (`geom_point()`).
QUESTION 4:
ggplot(CVG_Flights, aes(x = AIRLINE, y = ORIGIN_AIRPORT)) +
geom_point() +
labs(title = "Association between Delay Time, Air Time, and Distance (conditional on Origin Airport)",
x = "Air Time (minutes)",
y = "Delay Time (minutes)",
color = "Distance")
QUESTION 5:
merge_airlines <- left_join(CVG_Flights, airlines, by = c("AIRLINE" = "IATA_CODE"))
merge_origins <- left_join(merge_airlines, airports, by = c("ORIGIN_AIRPORT" = "IATA_CODE"))
flights_merged <- left_join(merge_origins, airports, by = c("DESTINATION_AIRPORT" = "IATA_CODE"))QUESTION 6:
Question 1: Which airlines operate the most flights from CVG airport?
airline_counts <- flights_merged %>%
group_by(AIRLINE.y) %>%
summarise(Flight_Count = n()) %>%
arrange(desc(Flight_Count))
ggplot(airline_counts, aes(x = reorder(AIRLINE.y, -Flight_Count), y = Flight_Count)) +
geom_bar(stat = "identity", fill = "purple") +
labs(title = "Number of Flights by Airline from CVG Airport",
x = "Airline",
y = "Flight Count")+
theme(axis.text.x = element_text(angle = 30, hjust = 1))
Question 2: What are the most common destinations for flights departing from CVG airport?
destination_counts <- flights_merged %>%
group_by(AIRPORT.y) %>%
summarise(Flight_Count = n()) %>%
arrange(desc(Flight_Count)) %>%
top_n(10)## Selecting by Flight_Countggplot(destination_counts, aes(x = reorder(AIRPORT.y, -Flight_Count), y = Flight_Count)) +
geom_bar(stat = "identity", fill = "brown") +
labs(title = "Top 10 Destinations from CVG Airport",
x = "Destination Airport",
y = "Flight Count") +
theme(axis.text.x = element_text(angle = 90, hjust = 1))
Question 3: What is the distribution of departure delays for flights departing from CVG airport?
flights_merged_filtered <- flights_merged[!is.na(flights_merged$DEPARTURE_DELAY), ]
ggplot(flights_merged_filtered, aes(x = DEPARTURE_DELAY)) +
geom_histogram(fill = "hotpink", color = "black", bins = 30) +
labs(title = "Distribution of Departure Delays from CVG Airport",
x = "Departure Delay (minutes)",
y = "Frequency")
Question 4: How does the number of flights departing from CVG airport vary over time?
flights_merged$FLIGHT_DATE <- as.Date(flights_merged$FLIGHT_DATE, format = "%m/%d/%Y")
flight_counts_by_date <- flights_merged %>%
group_by(FLIGHT_DATE) %>%
summarise(Flight_Count = n())
ggplot(flight_counts_by_date, aes(x = FLIGHT_DATE, y = Flight_Count)) +
geom_line(color = "darkblue") +
labs(title = "Number of Flights Departing from CVG Airport Over Time",
x = "Date",
y = "Flight Count")