library(nycflights13)
library(tidyverse)
nc <- filter(flights, !is.na(dep_delay), !is.na(arr_delay))

Q1

dim(flights)
## [1] 336776     19

Q2

arrange(flights, -dep_delay)
## # A tibble: 336,776 × 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
##  2  2013     6    15     1432           1935      1137     1607           2120
##  3  2013     1    10     1121           1635      1126     1239           1810
##  4  2013     9    20     1139           1845      1014     1457           2210
##  5  2013     7    22      845           1600      1005     1044           1815
##  6  2013     4    10     1100           1900       960     1342           2211
##  7  2013     3    17     2321            810       911      135           1020
##  8  2013     6    27      959           1900       899     1236           2226
##  9  2013     7    22     2257            759       898      121           1026
## 10  2013    12     5      756           1700       896     1058           2020
## # ℹ 336,766 more rows
## # 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>

Q3

nc %>% group_by(year, month, day) %>% summarise(mean = mean(dep_delay))
## `summarise()` has grouped output by 'year', 'month'. You can override using the
## `.groups` argument.
## # A tibble: 365 × 4
## # Groups:   year, month [12]
##     year month   day  mean
##    <int> <int> <int> <dbl>
##  1  2013     1     1 11.4 
##  2  2013     1     2 13.7 
##  3  2013     1     3 10.9 
##  4  2013     1     4  8.97
##  5  2013     1     5  5.73
##  6  2013     1     6  7.15
##  7  2013     1     7  5.42
##  8  2013     1     8  2.56
##  9  2013     1     9  2.30
## 10  2013     1    10  2.84
## # ℹ 355 more rows

Q4

nc %>% group_by(tailnum) %>% summarise(d = mean(arr_delay)) %>% arrange(d)
## # A tibble: 4,037 × 2
##    tailnum     d
##    <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  
## # ℹ 4,027 more rows

Q5

nc %>% group_by(year, month, day) %>% summarise(first = min(dep_time), last = max(dep_time)) %>% arrange(last)
## `summarise()` has grouped output by 'year', 'month'. You can override using the
## `.groups` argument.
## # A tibble: 365 × 5
## # Groups:   year, month [12]
##     year month   day first  last
##    <int> <int> <int> <int> <int>
##  1  2013     2     8   458  1728
##  2  2013     9     7   452  2246
##  3  2013     1     9     2  2252
##  4  2013     8    26    13  2258
##  5  2013     9     4   446  2258
##  6  2013     1    11    11  2304
##  7  2013     9    21     8  2306
##  8  2013    10    18     9  2317
##  9  2013     1    10     3  2320
## 10  2013     3    17    17  2321
## # ℹ 355 more rows

Q6

nc %>% group_by(month) %>% summarise(p = mean(dep_delay > 60))
## # A tibble: 12 × 2
##    month      p
##    <int>  <dbl>
##  1     1 0.0685
##  2     2 0.0694
##  3     3 0.0832
##  4     4 0.0909
##  5     5 0.0812
##  6     6 0.128 
##  7     7 0.133 
##  8     8 0.0794
##  9     9 0.0486
## 10    10 0.0469
## 11    11 0.0401
## 12    12 0.0936

Q7

flights %>% group_by(dest) %>% summarise(n = n_distinct(carrier)) %>% arrange(-n)
## # A tibble: 105 × 2
##    dest      n
##    <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 95 more rows

Q8

d <- flights %>% group_by(dest) %>% summarise(count = n(), dist = mean(distance), delay = mean(arr_delay, na.rm = TRUE)) %>% filter(count > 20, dest != "HNL")
ggplot(d, aes(dist, delay)) + geom_point() + geom_smooth()
## `geom_smooth()` using method = 'loess' and formula = 'y ~ x'

Q9

d
## # A tibble: 96 × 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
##  7 BDL     443  116   7.05
##  8 BGR     375  378   8.03
##  9 BHM     297  866. 16.9 
## 10 BNA    6333  758. 11.8 
## # ℹ 86 more rows

Q10

Read R for Data Science to double check answers.