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")