library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(ggplot2)
library(nycflights13)
Question 1
pacman::p_load(nycflights13)
#View(flights)
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
## 1st Qu.: 8.00 1st Qu.:2013-04-04 13:00:00
## Median :29.00 Median :2013-07-03 10:00:00
## Mean :26.23 Mean :2013-07-03 05:22:54
## 3rd Qu.:44.00 3rd Qu.:2013-10-01 07:00:00
## Max. :59.00 Max. :2013-12-31 23:00:00
##
dim(flights)
## [1] 336776 19
Question 2
# Option A
summarise(flights, delay=mean(dep_delay,na.rm=TRUE))
## # A tibble: 1 × 1
## delay
## <dbl>
## 1 12.6
# Option B
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 C
select(flights, starts_with("dep"))
## # A tibble: 336,776 × 2
## dep_time dep_delay
## <int> <dbl>
## 1 517 2
## 2 533 4
## 3 542 2
## 4 544 -1
## 5 554 -6
## 6 554 -4
## 7 555 -5
## 8 557 -3
## 9 557 -3
## 10 558 -2
## # ℹ 336,766 more rows
# Option D
pacman::p_load(dplyr, nycflights13)
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 3
# Option A
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
# Option B
not_cancelled <- flights %>%
filter(!is.na(dep_delay), !is.na(arr_delay))
# Option C
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
#Option D
delays <- not_cancelled %>%
group_by(tailnum) %>%
summarise(
delay = mean(arr_delay)
)
Question 4
not_cancelled <- flights %>%
filter(!is.na(arr_delay))
delays <- not_cancelled %>%
group_by(tailnum) %>%
summarise(avg_arr_delay = mean(arr_delay, na.rm = TRUE))
best_tailnum <- delays %>%
arrange(avg_arr_delay) %>%
slice(1)
best_tailnum
## # A tibble: 1 × 2
## tailnum avg_arr_delay
## <chr> <dbl>
## 1 N560AS -53
Question 5
not_cancelled %>%
group_by(year, month, day) %>%
summarise(
first = min(dep_time),
last = max(dep_time)
)
## `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 1 1 517 2356
## 2 2013 1 2 42 2354
## 3 2013 1 3 32 2349
## 4 2013 1 4 25 2358
## 5 2013 1 5 14 2357
## 6 2013 1 6 16 2355
## 7 2013 1 7 49 2359
## 8 2013 1 8 454 2351
## 9 2013 1 9 2 2252
## 10 2013 1 10 3 2320
## # ℹ 355 more rows
Question 6
library(dplyr)
library(nycflights13)
flights %>%
group_by(month) %>%
summarise(prop_delayed = mean(dep_delay > 60, na.rm = TRUE))
## # A tibble: 12 × 2
## month prop_delayed
## <int> <dbl>
## 1 1 0.0688
## 2 2 0.0698
## 3 3 0.0837
## 4 4 0.0916
## 5 5 0.0818
## 6 6 0.128
## 7 7 0.134
## 8 8 0.0796
## 9 9 0.0490
## 10 10 0.0469
## 11 11 0.0402
## 12 12 0.0942
Question 7
flights %>%
group_by(dest) %>%
summarise(num_carriers = n_distinct(carrier)) %>%
arrange(desc(num_carriers))
## # A tibble: 105 × 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 95 more rows
Question 8
Group flights by destination
by_dest <- group_by(flights, dest)
Summarize to compute distance, average delay, and number of
flights
delay <- summarise(
by_dest,
count = n(),
dist = mean(distance, na.rm = TRUE),
delay = mean(arr_delay, na.rm = TRUE)
)
Filter to remove noisy points and Honolulu airport, which is almost
twice as far away as the next closest airport.
delays <- not_cancelled %>%
group_by(dest) %>%
summarise(
count = n(),
delay = mean(arr_delay, na.rm = TRUE)
)
delay <- filter(delays, count > 20, dest != "HNL")
Plot the relationship between average delay and distance and find
out a pattern.
library(dplyr)
library(ggplot2)
library(nycflights13)
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")
ggplot(data = delays, aes(x = dist, y = delay)) +
geom_point(aes(size = count), alpha = 1/3) +
geom_smooth(se = FALSE)
## `geom_smooth()` using method = 'loess' and formula = 'y ~ x'
Question 9
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")