library(dplyr)
pacman::p_load(nycflights13)

head(flights) 
## # A tibble: 6 × 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     1      517            515         2      830            819
## 2  2013     1     1      533            529         4      850            830
## 3  2013     1     1      542            540         2      923            850
## 4  2013     1     1      544            545        -1     1004           1022
## 5  2013     1     1      554            600        -6      812            837
## 6  2013     1     1      554            558        -4      740            728
## # 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>
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 05:00:00.00  
##  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  
## 

Q1 Does this dataset contain 336,776 flights records and 19 fields?

dim(flights)
## [1] 336776     19

Q2 Question 2 Which of the following codes show the flight has the largest departure delay? Check all that apply.

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
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>

Q3 Which of the following codes do you think will help him find the average departure delay per date.

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

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

Q4 Write the code to get the tailnum that has the lowest average arrival delay?

flights %>%
  filter(tailnum %in% c("N427SW", "N844MH", "N928DN")) %>%
  group_by(tailnum) %>%
  summarise(avg_delay = mean(arr_delay, na.rm = TRUE)) %>%
  arrange(avg_delay)
## # A tibble: 3 × 2
##   tailnum avg_delay
##   <chr>       <dbl>
## 1 N427SW        157
## 2 N928DN        201
## 3 N844MH        320

Q5 Does each day’s last flight leave by 12am?

not_cancelled %>% 
  group_by(year, month, day) %>% 
  summarise(
    first = min(dep_time),
    last = max(dep_time)
  ) %>%
  arrange(desc(last))
## # 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

Q6 Write the code to obtain what proportion of flights have departure delays of more than an hour for each months.Could we conclude that June and July show a higher proportion of departure delays than other months?

flights %>%
  group_by(month) %>%
  summarise(
    prop_delay_1hr = mean(dep_delay > 60, na.rm = TRUE)
  ) %>%
  arrange(desc(prop_delay_1hr))
## # A tibble: 12 × 2
##    month prop_delay_1hr
##    <int>          <dbl>
##  1     7         0.134 
##  2     6         0.128 
##  3    12         0.0942
##  4     4         0.0916
##  5     3         0.0837
##  6     5         0.0818
##  7     8         0.0796
##  8     2         0.0698
##  9     1         0.0688
## 10     9         0.0490
## 11    10         0.0469
## 12    11         0.0402

Q7 Given that the n_distinct() function can count the number of dinstict (unique) values, could you find out which destinations have the most carriers? Check all that apply.

flights %>%
  group_by(dest) %>%
  summarise(n_carriers = n_distinct(carrier)) %>%
  arrange(desc(n_carriers))
## # A tibble: 105 × 2
##    dest  n_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 95 more rows

Q9 Does the code achieve the similar goal with the above question except for missing the plotting step?

delays <- flights %>% 

 group_by(dest) %>% 

 summarise(

  count = n(),

  dist = mean(distance, na.rm = TRUE),

  delay = mean(arr_delay, na.rm = TRUE)

 ) %>% 

 filter(count > 20, dest != "HNL")