The flights dataset contains 336,776 observations and 19 variables.
glimpse(flights)
## Rows: 336,776
## Columns: 19
## $ year <int> 2013, 2013, 2013, 2013, 2013, 2013, 2013, 2013, 2013, 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> 517, 533, 542, 544, 554, 554, 555, 557, 557, 558, 558, …
## $ sched_dep_time <int> 515, 529, 540, 545, 600, 558, 600, 600, 600, 600, 600, …
## $ dep_delay <dbl> 2, 4, 2, -1, -6, -4, -5, -3, -3, -2, -2, -2, -2, -2, -1…
## $ arr_time <int> 830, 850, 923, 1004, 812, 740, 913, 709, 838, 753, 849,…
## $ sched_arr_time <int> 819, 830, 850, 1022, 837, 728, 854, 723, 846, 745, 851,…
## $ arr_delay <dbl> 11, 20, 33, -18, -25, 12, 19, -14, -8, 8, -2, -3, 7, -1…
## $ carrier <chr> "UA", "UA", "AA", "B6", "DL", "UA", "B6", "EV", "B6", "…
## $ flight <int> 1545, 1714, 1141, 725, 461, 1696, 507, 5708, 79, 301, 4…
## $ tailnum <chr> "N14228", "N24211", "N619AA", "N804JB", "N668DN", "N394…
## $ origin <chr> "EWR", "LGA", "JFK", "JFK", "LGA", "EWR", "EWR", "LGA",…
## $ dest <chr> "IAH", "IAH", "MIA", "BQN", "ATL", "ORD", "FLL", "IAD",…
## $ air_time <dbl> 227, 227, 160, 183, 116, 150, 158, 53, 140, 138, 149, 1…
## $ distance <dbl> 1400, 1416, 1089, 1576, 762, 719, 1065, 229, 944, 733, …
## $ hour <dbl> 5, 5, 5, 5, 6, 5, 6, 6, 6, 6, 6, 6, 6, 6, 6, 5, 6, 6, 6…
## $ minute <dbl> 15, 29, 40, 45, 0, 58, 0, 0, 0, 0, 0, 0, 0, 0, 0, 59, 0…
## $ time_hour <dttm> 2013-01-01 05:00:00, 2013-01-01 05:00:00, 2013-01-01 0…
summary(flights)
## year month day dep_time sched_dep_time
## Min. :2013 Min. : 1.000 Min. : 1.00 Min. : 1 Min. : 106
## 1st Qu.:2013 1st Qu.: 4.000 1st Qu.: 8.00 1st Qu.: 907 1st Qu.: 906
## Median :2013 Median : 7.000 Median :16.00 Median :1401 Median :1359
## Mean :2013 Mean : 6.549 Mean :15.71 Mean :1349 Mean :1344
## 3rd Qu.:2013 3rd Qu.:10.000 3rd Qu.:23.00 3rd Qu.:1744 3rd Qu.:1729
## Max. :2013 Max. :12.000 Max. :31.00 Max. :2400 Max. :2359
## NA's :8255
## dep_delay arr_time sched_arr_time arr_delay
## Min. : -43.00 Min. : 1 Min. : 1 Min. : -86.000
## 1st Qu.: -5.00 1st Qu.:1104 1st Qu.:1124 1st Qu.: -17.000
## Median : -2.00 Median :1535 Median :1556 Median : -5.000
## Mean : 12.64 Mean :1502 Mean :1536 Mean : 6.895
## 3rd Qu.: 11.00 3rd Qu.:1940 3rd Qu.:1945 3rd Qu.: 14.000
## Max. :1301.00 Max. :2400 Max. :2359 Max. :1272.000
## NA's :8255 NA's :8713 NA's :9430
## carrier flight tailnum origin
## Length:336776 Min. : 1 Length:336776 Length:336776
## Class :character 1st Qu.: 553 Class :character Class :character
## Mode :character Median :1496 Mode :character Mode :character
## Mean :1972
## 3rd Qu.:3465
## Max. :8500
##
## dest air_time distance hour
## Length:336776 Min. : 20.0 Min. : 17 Min. : 1.00
## Class :character 1st Qu.: 82.0 1st Qu.: 502 1st Qu.: 9.00
## Mode :character Median :129.0 Median : 872 Median :13.00
## Mean :150.7 Mean :1040 Mean :13.18
## 3rd Qu.:192.0 3rd Qu.:1389 3rd Qu.:17.00
## Max. :695.0 Max. :4983 Max. :23.00
## NA's :9430
## minute time_hour
## Min. : 0.00 Min. :2013-01-01 05:00:00
## 1st Qu.: 8.00 1st Qu.:2013-04-04 13:00:00
## Median :29.00 Median :2013-07-03 10:00:00
## Mean :26.23 Mean :2013-07-03 05:22:54
## 3rd Qu.:44.00 3rd Qu.:2013-10-01 07:00:00
## Max. :59.00 Max. :2013-12-31 23:00:00
##
dim(flights)
## [1] 336776 19
nrow(flights)
## [1] 336776
ncol(flights)
## [1] 19
We can identify the flight with the largest departure delay by finding the maximum value or sorting the dataset in descending order.
# Option C
maxdep <- max(flights$dep_delay, na.rm = TRUE)
maxdep_id <- which(
flights$dep_delay == maxdep
)
flights[maxdep_id, 10:12]
## # A tibble: 1 × 3
## carrier flight tailnum
## <chr> <int> <chr>
## 1 HA 51 N384HA
# Show complete flight information
flights[maxdep_id, ]
## # A tibble: 1 × 19
## year month day dep_time sched_dep_time dep_delay arr_time sched_arr_time
## <int> <int> <int> <int> <int> <dbl> <int> <int>
## 1 2013 1 9 641 900 1301 1242 1530
## # ℹ 11 more variables: arr_delay <dbl>, carrier <chr>, flight <int>,
## # tailnum <chr>, origin <chr>, dest <chr>, air_time <dbl>, distance <dbl>,
## # hour <dbl>, minute <dbl>, time_hour <dttm>
# Option D
sortf <- arrange(flights, desc(dep_delay))
select(
sortf,
carrier,
flight,
tailnum,
everything()
) %>%
head(10)
## # A tibble: 10 × 19
## carrier flight tailnum year month day dep_time sched_dep_time dep_delay
## <chr> <int> <chr> <int> <int> <int> <int> <int> <dbl>
## 1 HA 51 N384HA 2013 1 9 641 900 1301
## 2 MQ 3535 N504MQ 2013 6 15 1432 1935 1137
## 3 MQ 3695 N517MQ 2013 1 10 1121 1635 1126
## 4 AA 177 N338AA 2013 9 20 1139 1845 1014
## 5 MQ 3075 N665MQ 2013 7 22 845 1600 1005
## 6 DL 2391 N959DL 2013 4 10 1100 1900 960
## 7 DL 2119 N927DA 2013 3 17 2321 810 911
## 8 DL 2007 N3762Y 2013 6 27 959 1900 899
## 9 DL 2047 N6716C 2013 7 22 2257 759 898
## 10 AA 172 N5DMAA 2013 12 5 756 1700 896
## # ℹ 10 more variables: arr_time <int>, sched_arr_time <int>, arr_delay <dbl>,
## # origin <chr>, dest <chr>, air_time <dbl>, distance <dbl>, hour <dbl>,
## # minute <dbl>, time_hour <dttm>
Missing values must be removed or ignored when calculating average departure delays.
# Option A: Remove cancelled flights
not_cancelled <- flights %>%
filter(!is.na(dep_delay))
not_cancelled %>%
group_by(year, month, day) %>%
summarise(
mean = mean(dep_delay),
.groups = "drop"
)
## # A tibble: 365 × 4
## year month day mean
## <int> <int> <int> <dbl>
## 1 2013 1 1 11.5
## 2 2013 1 2 13.9
## 3 2013 1 3 11.0
## 4 2013 1 4 8.95
## 5 2013 1 5 5.73
## 6 2013 1 6 7.15
## 7 2013 1 7 5.42
## 8 2013 1 8 2.55
## 9 2013 1 9 2.28
## 10 2013 1 10 2.84
## # ℹ 355 more rows
# Option B: Ignore missing values
flights %>%
group_by(year, month, day) %>%
summarise(
mean = mean(dep_delay, na.rm = TRUE),
.groups = "drop"
)
## # A tibble: 365 × 4
## year month day mean
## <int> <int> <int> <dbl>
## 1 2013 1 1 11.5
## 2 2013 1 2 13.9
## 3 2013 1 3 11.0
## 4 2013 1 4 8.95
## 5 2013 1 5 5.73
## 6 2013 1 6 7.15
## 7 2013 1 7 5.42
## 8 2013 1 8 2.55
## 9 2013 1 9 2.28
## 10 2013 1 10 2.84
## # ℹ 355 more rows
First, calculate the average arrival delay for each tail number. Then, arrange the results from lowest to highest.
tailnum_delays <- flights %>%
filter(
!is.na(tailnum),
!is.na(arr_delay)
) %>%
group_by(tailnum) %>%
summarise(
avg_arr_delay = mean(arr_delay),
.groups = "drop"
) %>%
arrange(avg_arr_delay)
# Display the lowest average arrival delay
head(tailnum_delays, 10)
## # A tibble: 10 × 2
## tailnum avg_arr_delay
## <chr> <dbl>
## 1 N560AS -53
## 2 N315AS -51
## 3 N517AS -40.5
## 4 N592AS -35.5
## 5 N7AYAA -35
## 6 N585AS -34.5
## 7 N915DN -34
## 8 N512AS -31.5
## 9 N594AS -31.3
## 10 N564AS -31
# Display the correct tail number
tailnum_delays %>%
slice_min(avg_arr_delay, n = 1)
## # A tibble: 1 × 2
## tailnum avg_arr_delay
## <chr> <dbl>
## 1 N560AS -53
# Compare the multiple-choice options
tailnum_delays %>%
filter(
tailnum %in% c(
"N844MH",
"N928DN",
"N427SW"
)
) %>%
arrange(avg_arr_delay)
## # A tibble: 3 × 2
## tailnum avg_arr_delay
## <chr> <dbl>
## 1 N427SW 157
## 2 N928DN 201
## 3 N844MH 320
Some flights depart after midnight, so not every day’s last recorded departure occurs before 12 AM.
daily_departures <- not_cancelled %>%
group_by(year, month, day) %>%
summarise(
first = min(dep_time),
last = max(dep_time),
.groups = "drop"
)
daily_departures %>%
arrange(desc(last)) %>%
head(20)
## # A tibble: 20 × 5
## year month day first last
## <int> <int> <int> <int> <int>
## 1 2013 2 7 27 2400
## 2 2013 2 11 1 2400
## 3 2013 3 15 11 2400
## 4 2013 3 22 37 2400
## 5 2013 3 25 13 2400
## 6 2013 4 2 9 2400
## 7 2013 4 4 14 2400
## 8 2013 4 20 7 2400
## 9 2013 5 21 110 2400
## 10 2013 6 17 2 2400
## 11 2013 7 7 4 2400
## 12 2013 7 13 19 2400
## 13 2013 7 17 2 2400
## 14 2013 7 28 1 2400
## 15 2013 8 10 13 2400
## 16 2013 8 20 54 2400
## 17 2013 9 2 8 2400
## 18 2013 9 12 2 2400
## 19 2013 10 30 455 2400
## 20 2013 11 27 28 2400
Calculate the proportion of flights with departure delays greater than 60 minutes for each month.
monthly_delays <- flights %>%
group_by(month) %>%
summarise(
total_flights = n(),
delayed_over_hour = sum(
dep_delay > 60,
na.rm = TRUE
),
proportion = mean(
dep_delay > 60,
na.rm = TRUE
),
percentage = proportion * 100,
.groups = "drop"
) %>%
arrange(desc(proportion))
monthly_delays
## # A tibble: 12 × 5
## month total_flights delayed_over_hour proportion percentage
## <int> <int> <int> <dbl> <dbl>
## 1 7 29425 3820 0.134 13.4
## 2 6 28243 3494 0.128 12.8
## 3 12 28135 2553 0.0942 9.42
## 4 4 28330 2535 0.0916 9.16
## 5 3 28834 2340 0.0837 8.37
## 6 5 28796 2309 0.0818 8.18
## 7 8 29327 2295 0.0796 7.96
## 8 2 24951 1654 0.0698 6.98
## 9 1 27004 1821 0.0688 6.88
## 10 9 27574 1330 0.0490 4.90
## 11 10 28889 1344 0.0469 4.69
## 12 11 27268 1086 0.0402 4.02
ggplot(
monthly_delays,
aes(x = factor(month), y = percentage)
) +
geom_col(fill = "steelblue") +
labs(
title = "Flights Delayed Over One Hour by Month",
x = "Month",
y = "Percentage of Flights"
) +
theme_minimal()
Count the number of unique airlines serving each destination.
destination_carriers <- flights %>%
group_by(dest) %>%
summarise(
carriers = n_distinct(carrier),
.groups = "drop"
) %>%
arrange(desc(carriers))
# View the destinations with most carriers
head(destination_carriers, 20)
## # A tibble: 20 × 2
## dest carriers
## <chr> <int>
## 1 ATL 7
## 2 BOS 7
## 3 CLT 7
## 4 ORD 7
## 5 TPA 7
## 6 AUS 6
## 7 DCA 6
## 8 DTW 6
## 9 IAD 6
## 10 MSP 6
## 11 MSY 6
## 12 PIT 6
## 13 STL 6
## 14 BNA 5
## 15 CLE 5
## 16 DEN 5
## 17 IND 5
## 18 LAS 5
## 19 LAX 5
## 20 PBI 5
# Identify all destinations tied for the maximum
destination_carriers %>%
filter(carriers == max(carriers))
## # A tibble: 5 × 2
## dest carriers
## <chr> <int>
## 1 ATL 7
## 2 BOS 7
## 3 CLT 7
## 4 ORD 7
## 5 TPA 7
# Compare all multiple-choice options
destination_carriers %>%
filter(
dest %in% c(
"CLT",
"ORD",
"ATL",
"TPA",
"BOS"
)
) %>%
arrange(desc(carriers))
## # A tibble: 5 × 2
## dest carriers
## <chr> <int>
## 1 ATL 7
## 2 BOS 7
## 3 CLT 7
## 4 ORD 7
## 5 TPA 7
by_dest <- group_by(flights, dest)
delay <- summarise(
by_dest,
count = n(),
dist = mean(distance, na.rm = TRUE),
delay = mean(arr_delay, na.rm = TRUE)
)
head(delay)
## # A tibble: 6 × 4
## dest count dist delay
## <chr> <int> <dbl> <dbl>
## 1 ABQ 254 1826 4.38
## 2 ACK 265 199 4.85
## 3 ALB 439 143 14.4
## 4 ANC 8 3370 -2.5
## 5 ATL 17215 757. 11.3
## 6 AUS 2439 1514. 6.02
Remove destinations with 20 or fewer flights and exclude Honolulu.
delay <- filter(
delay,
count > 20,
dest != "HNL"
)
head(delay)
## # A tibble: 6 × 4
## dest count dist delay
## <chr> <int> <dbl> <dbl>
## 1 ABQ 254 1826 4.38
## 2 ACK 265 199 4.85
## 3 ALB 439 143 14.4
## 4 ATL 17215 757. 11.3
## 5 AUS 2439 1514. 6.02
## 6 AVL 275 584. 8.00
ggplot(
data = delay,
mapping = aes(x = dist, y = delay)
) +
geom_point(
aes(size = count),
alpha = 1/3
) +
geom_smooth(se = FALSE) +
labs(
title = "Distance vs. Average Arrival Delay",
x = "Average Flight Distance (Miles)",
y = "Average Arrival Delay (Minutes)"
) +
theme_minimal()
The following code performs the same data manipulation as Question 8, excluding the plotting step.
delays <- flights %>%
group_by(dest) %>%
summarise(
count = n(),
dist = mean(distance, na.rm = TRUE),
delay = mean(arr_delay, na.rm = TRUE),
.groups = "drop"
) %>%
filter(
count > 20,
dest != "HNL"
)
head(delays)
## # A tibble: 6 × 4
## dest count dist delay
## <chr> <int> <dbl> <dbl>
## 1 ABQ 254 1826 4.38
## 2 ACK 265 199 4.85
## 3 ALB 439 143 14.4
## 4 ATL 17215 757. 11.3
## 5 AUS 2439 1514. 6.02
## 6 AVL 275 584. 8.00
# Confirm both methods produce the same result
all.equal(
as.data.frame(delay),
as.data.frame(delays)
)
## [1] TRUE
The R for Data Science textbook can be used to verify the code and answers.
# Final verification of dataset dimensions
dim(flights)
## [1] 336776 19
# Verify monthly departure delays
monthly_delays
## # A tibble: 12 × 5
## month total_flights delayed_over_hour proportion percentage
## <int> <int> <int> <dbl> <dbl>
## 1 7 29425 3820 0.134 13.4
## 2 6 28243 3494 0.128 12.8
## 3 12 28135 2553 0.0942 9.42
## 4 4 28330 2535 0.0916 9.16
## 5 3 28834 2340 0.0837 8.37
## 6 5 28796 2309 0.0818 8.18
## 7 8 29327 2295 0.0796 7.96
## 8 2 24951 1654 0.0698 6.98
## 9 1 27004 1821 0.0688 6.88
## 10 9 27574 1330 0.0490 4.90
## 11 10 28889 1344 0.0469 4.69
## 12 11 27268 1086 0.0402 4.02
# Verify destinations with the most carriers
destination_carriers %>%
filter(carriers == max(carriers))
## # A tibble: 5 × 2
## dest carriers
## <chr> <int>
## 1 ATL 7
## 2 BOS 7
## 3 CLT 7
## 4 ORD 7
## 5 TPA 7
# Verify tail number with lowest arrival delay
tailnum_delays %>%
slice_min(avg_arr_delay, n = 1)
## # A tibble: 1 × 2
## tailnum avg_arr_delay
## <chr> <dbl>
## 1 N560AS -53
This assignment explored the NYC flights dataset using data manipulation and visualization techniques in R.
The analysis examined departure delays, arrival delays, airline carriers, destinations, and flight distances. Functions such as group_by(), summarise(), filter(), arrange(), and ggplot() were used to identify patterns and compare flight performance.