pacman::p_load(nycflights13, dplyr)
# view basic info
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…
# check dimensions
dim(flights)
## [1] 336776 19
# 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
# Option D
sortf <- arrange(flights, desc(dep_delay))
select(sortf, carrier, flight, tailnum, everything()) %>% head()
## # A tibble: 6 × 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
## # 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>
# B: specify na.rm = TRUE
flights %>%
group_by(year, month, day) %>%
summarise(mean = mean(dep_delay, na.rm = TRUE))
## `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 11.5
## 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
# C: filter not cancelled (remove NA in both dep_delay & arr_delay)
not_cancelled <- flights %>%
filter(!is.na(dep_delay), !is.na(arr_delay))
# D: similar fix, only using dep_delay
not_cancelled <- flights %>%
filter(!is.na(dep_delay))
not_cancelled %>%
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 11.5
## 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(arr_delay))
lowest_arr_delay <- not_cancelled %>%
group_by(tailnum) %>%
summarise(avg_arr_delay = mean(arr_delay)) %>%
arrange(avg_arr_delay)
lowest_arr_delay %>% head()
## # A tibble: 6 × 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
library(nycflights13)
library(dplyr)
# Remove flights with missing arrival delay
not_cancelled <- flights %>%
filter(!is.na(arr_delay))
# Step 1: Average arrival delay for each plane
avg_delay_per_tailnum <- not_cancelled %>%
group_by(tailnum) %>%
summarise(avg_arr_delay = mean(arr_delay))
# View the first few results
head(avg_delay_per_tailnum)
## # A tibble: 6 × 2
## tailnum avg_arr_delay
## <chr> <dbl>
## 1 D942DN 31.5
## 2 N0EGMQ 9.98
## 3 N10156 12.7
## 4 N102UW 2.94
## 5 N103US -6.93
## 6 N104UW 1.80
not_cancelled %>%
group_by(year, month, day) %>%
summarise(
first = min(dep_time),
last = max(dep_time)
) %>%
arrange(desc(last)) %>%
head()
## `summarise()` has grouped output by 'year', 'month'. You can override using the
## `.groups` argument.
## # A tibble: 6 × 5
## # Groups: year, month [3]
## 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
flights %>%
mutate(over_hour = dep_delay > 60) %>%
group_by(month) %>%
summarise(prop_over_hour = mean(over_hour, na.rm = TRUE)) %>%
arrange(desc(prop_over_hour))
## # A tibble: 12 × 2
## month prop_over_hour
## <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
flights %>%
group_by(dest) %>%
summarise(n_carriers = n_distinct(carrier)) %>%
arrange(desc(n_carriers)) %>%
head(10)
## # A tibble: 10 × 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
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")
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
flights %>%
filter(!is.na(arr_delay)) %>% # Step 1: Remove cancelled flights
group_by(tailnum) %>% # Step 1: Group by plane (tailnum)
summarise(avg_delay = mean(arr_delay)) %>% # Step 1: Calculate average delay
arrange(avg_delay) %>% # Step 2: Sort by average delay (ascending for lowest)
head(1) # Step 2: Take the top row
## # A tibble: 1 × 2
## tailnum avg_delay
## <chr> <dbl>
## 1 N560AS -53