Load necessary libraries and datasets

library(dplyr)
library(tidyverse)
pacman::p_load(nycflights13)
#View(flights) # this View() function opens lets you directly view the whole dataset
#glimpse(flights) # this glimpse() function provides a quick overview of the dataset
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 05:00:00.00  
##  1st Qu.: 8.00   1st Qu.:2013-04-04 13:00:00.00  
##  Median :29.00   Median :2013-07-03 10:00:00.00  
##  Mean   :26.23   Mean   :2013-07-03 05:22:54.64  
##  3rd Qu.:44.00   3rd Qu.:2013-10-01 07:00:00.00  
##  Max.   :59.00   Max.   :2013-12-31 23:00:00.00  
## 
Rows: 336,776 Columns: 19

Question 2a

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

Question 2b

sortf <- arrange(flights,desc(dep_delay)) 
select(sortf, carrier, flight, tailnum, everything())
## # A tibble: 336,776 × 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 336,766 more rows
## # 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>

Question 3a

not_cancelled <- flights %>%  
 filter(!is.na(dep_delay))  

not_cancelled %>%  
 group_by(year, month, day) %>%  
 summarise(mean = mean(dep_delay))
## # A tibble: 365 × 4
## # Groups:   year, month [12]
##     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

Question 3b

flights %>%  
 group_by(year, month, day) %>%  
 summarise(mean = mean(dep_delay, na.rm = TRUE))
## # A tibble: 365 × 4
## # Groups:   year, month [12]
##     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

Question 4

The average arrival delay per tail number

not_cancelled <- flights %>%  
  filter(!is.na(arr_delay))  

avg_delays <- not_cancelled %>%  
  group_by(tailnum) %>%  
  summarise(mean_arr_delay = mean(arr_delay, na.rm = TRUE))

Find the tail number that has lowest value of average arrival delay

lowest_delay_tailnum <- avg_delays %>%  
  arrange(mean_arr_delay) %>%  
  slice(1) %>%  
  pull(tailnum)
print(lowest_delay_tailnum)
## [1] "N560AS"

Question 5

not_cancelled %>%  
  group_by(year, month, day) %>%  
  summarise(
    first = min(dep_time, na.rm = TRUE),
    last = max(dep_time, na.rm = TRUE)
  ) %>%  
arrange(desc(last))  # Sort by latest departure time
## # A tibble: 365 × 5
## # Groups:   year, month [12]
##     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
## # ℹ 355 more rows

Question 6

not_cancelled %>%  
  group_by(month) %>%  
  summarise(
    total_flights = n(),
    delayed_flights = sum(dep_delay > 60, na.rm = TRUE),
    proportion_delayed = delayed_flights / total_flights
  ) %>%  
arrange(desc(proportion_delayed))
## # A tibble: 12 × 4
##    month total_flights delayed_flights proportion_delayed
##    <int>         <int>           <int>              <dbl>
##  1     7         28293            3765             0.133 
##  2     6         27075            3459             0.128 
##  3    12         27020            2528             0.0936
##  4     4         27564            2506             0.0909
##  5     3         27902            2322             0.0832
##  6     5         28128            2284             0.0812
##  7     8         28756            2283             0.0794
##  8     2         23611            1638             0.0694
##  9     1         26398            1808             0.0685
## 10     9         27010            1313             0.0486
## 11    10         28618            1341             0.0469
## 12    11         26971            1082             0.0401

Question 7

not_cancelled %>%  
  group_by(dest) %>%  
  summarise(num_carriers = n_distinct(carrier)) %>%  
  arrange(desc(num_carriers))
## # A tibble: 104 × 2
##    dest  num_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
## # ℹ 94 more rows