Lab 1: Exploring Numerical Data
Ella Buono
4/12/2022
Exercise 1:
names(nycflights) ## [1] "year" "month" "day" "dep_time" "dep_delay" "arr_time"
## [7] "arr_delay" "carrier" "tailnum" "flight" "origin" "dest"
## [13] "air_time" "distance" "hour" "minute"glimpse(nycflights)## Rows: 32,735
## Columns: 16
## $ year <int> 2013, 2013, 2013, 2013, 2013, 2013, 2013, 2013, 2013, 2013, ~
## $ month <int> 6, 5, 12, 5, 7, 1, 12, 8, 9, 4, 6, 11, 4, 3, 10, 1, 2, 8, 10~
## $ day <int> 30, 7, 8, 14, 21, 1, 9, 13, 26, 30, 17, 22, 26, 25, 21, 23, ~
## $ dep_time <int> 940, 1657, 859, 1841, 1102, 1817, 1259, 1920, 725, 1323, 940~
## $ dep_delay <int> 15, -3, -1, -4, -3, -3, 14, 85, -10, 62, 5, 5, -2, 115, -4, ~
## $ arr_time <int> 1216, 2104, 1238, 2122, 1230, 2008, 1617, 2032, 1027, 1549, ~
## $ arr_delay <int> -4, 10, 11, -34, -8, 3, 22, 71, -8, 60, -4, -2, 22, 91, -6, ~
## $ carrier <chr> "VX", "DL", "DL", "DL", "9E", "AA", "WN", "B6", "AA", "EV", ~
## $ tailnum <chr> "N626VA", "N3760C", "N712TW", "N914DL", "N823AY", "N3AXAA", ~
## $ flight <int> 407, 329, 422, 2391, 3652, 353, 1428, 1407, 2279, 4162, 20, ~
## $ origin <chr> "JFK", "JFK", "JFK", "JFK", "LGA", "LGA", "EWR", "JFK", "LGA~
## $ dest <chr> "LAX", "SJU", "LAX", "TPA", "ORF", "ORD", "HOU", "IAD", "MIA~
## $ air_time <int> 313, 216, 376, 135, 50, 138, 240, 48, 148, 110, 50, 161, 87,~
## $ distance <int> 2475, 1598, 2475, 1005, 296, 733, 1411, 228, 1096, 820, 264,~
## $ hour <int> 9, 16, 8, 18, 11, 18, 12, 19, 7, 13, 9, 13, 8, 20, 12, 20, 6~
## $ minute <int> 40, 57, 59, 41, 2, 17, 59, 20, 25, 23, 40, 20, 9, 54, 17, 24~The unit of observation is an individual flight (32735 flights total)
Exercise 2:
ggplot(data = nycflights, aes(x = dep_delay)) +
geom_histogram() ## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
ggplot(data = nycflights, aes(x = dep_delay)) +
geom_histogram(binwidth = 15)
ggplot(data = nycflights, aes(x = dep_delay)) +
geom_histogram(binwidth = 150)
lax_flights <- nycflights %>%
filter(dest == "LAX")
glimpse(lax_flights)## Rows: 1,583
## Columns: 16
## $ year <int> 2013, 2013, 2013, 2013, 2013, 2013, 2013, 2013, 2013, 2013, ~
## $ month <int> 6, 12, 7, 8, 3, 6, 11, 3, 9, 3, 1, 10, 4, 9, 2, 3, 3, 4, 12,~
## $ day <int> 30, 8, 5, 22, 27, 9, 26, 24, 17, 5, 8, 4, 8, 26, 7, 31, 24, ~
## $ dep_time <int> 940, 859, 920, 1108, 1158, 1914, 1545, 2005, 1437, 1153, 185~
## $ dep_delay <int> 15, -1, 5, -7, -2, -2, 0, 5, -8, -7, -6, -3, -10, -2, -4, -2~
## $ arr_time <int> 1216, 1238, 1204, 1352, 1455, 2234, 1900, 2248, 1736, 1526, ~
## $ arr_delay <int> -4, 11, -6, -12, -16, 9, -20, -37, -22, 15, -27, -11, -3, -1~
## $ carrier <chr> "VX", "DL", "AA", "UA", "DL", "UA", "AA", "UA", "UA", "DL", ~
## $ tailnum <chr> "N626VA", "N712TW", "N328AA", "N597UA", "N721TW", "N26208", ~
## $ flight <int> 407, 422, 1, 703, 863, 1439, 133, 1466, 841, 863, 21, 398, 3~
## $ origin <chr> "JFK", "JFK", "JFK", "JFK", "JFK", "EWR", "JFK", "EWR", "JFK~
## $ dest <chr> "LAX", "LAX", "LAX", "LAX", "LAX", "LAX", "LAX", "LAX", "LAX~
## $ air_time <int> 313, 376, 302, 292, 336, 317, 334, 315, 325, 343, 337, 323, ~
## $ distance <int> 2475, 2475, 2475, 2475, 2475, 2454, 2475, 2454, 2475, 2475, ~
## $ hour <int> 9, 8, 9, 11, 11, 19, 15, 20, 14, 11, 18, 11, 11, 10, 5, 13, ~
## $ minute <int> 40, 59, 20, 8, 58, 14, 45, 5, 37, 53, 59, 22, 50, 58, 57, 23~ggplot(data = lax_flights, aes(x = dep_delay)) +
geom_histogram()## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
lax_flights %>%
summarize(mean_dd = mean(dep_delay), median_dd = median(dep_delay), sample_size = n())## mean_dd median_dd sample_size
## 1 9.782059 -1 1583sfo_feb_flights <- nycflights %>%
filter(dest == "SFO", month == 2)
sfo_feb_flights %>% summarise(
mean_ad = mean(arr_delay),
median_ad = median(arr_delay),
sample_size = n()
)## mean_ad median_ad sample_size
## 1 -4.5 -11 68The dataset included 68 flights headed to SFO in February.
Exercise 3:
ggplot(data = sfo_feb_flights, aes(x = arr_delay)) +
geom_histogram(binwidth = 60)
The distribtion is right-skewed (so mean is likely higher than median)
Exercise 4:
sfo_feb_flights %>%
summarise(
median_ad = median(arr_delay),
mean_ad = mean(arr_delay),
ad = n())## median_ad mean_ad ad
## 1 -11 -4.5 68Mean arrival delay is smaller than median arrival delay (which matches exercise 3 conclusion because the right skew predicted that the mean of the arrival delay would be right (more positive, therefore less late) of the median)
Exercise 5:
nycflights %>%
group_by(month) %>%
summarize(median_ad = median(arr_delay), n_flights = n()) %>%
arrange(desc(median_ad))## # A tibble: 12 x 3
## month median_ad n_flights
## <int> <dbl> <int>
## 1 12 4 2716
## 2 7 -1 2742
## 3 4 -2 2781
## 4 6 -2 2732
## 5 1 -3 2610
## 6 2 -3 2286
## 7 8 -5 2880
## 8 11 -5 2733
## 9 3 -6 2869
## 10 5 -7 2821
## 11 10 -7 2884
## 12 9 -12 2681December (12) has the longest median arrival delay because if the median is positive, than at least 50% of flights in December were delayed (4 min being the median)
Exercise 6:
nycflights %>%
group_by(carrier) %>%
summarize(mean_ad = mean(arr_delay), n_flights = n()) %>%
arrange(desc(mean_ad)) ## # A tibble: 16 x 3
## carrier mean_ad n_flights
## <chr> <dbl> <int>
## 1 HA 28.1 34
## 2 FL 19.6 307
## 3 OO 16.7 3
## 4 EV 16.2 5142
## 5 YV 15.1 53
## 6 F9 12.5 69
## 7 MQ 10.1 2507
## 8 B6 9.73 5376
## 9 WN 8.88 1261
## 10 9E 8.04 1696
## 11 UA 4.36 5770
## 12 VX 2.41 497
## 13 US 1.80 2015
## 14 AA 1.40 3188
## 15 DL 0.907 4751
## 16 AS -11.3 66# (group by, summarize by)Based on mean, Hawaiian Airlines (HA) has the longest arrival delays.
Exercise 7:
nycflights <- nycflights %>%
mutate(speed = distance/(air_time/60))
nycflights %>%
group_by(carrier) %>%
summarize(mean_speed = mean(speed), n_flights = n()) %>%
arrange(desc(mean_speed)) ## # A tibble: 16 x 3
## carrier mean_speed n_flights
## <chr> <dbl> <int>
## 1 HA 481. 34
## 2 VX 445. 497
## 3 AS 443. 66
## 4 F9 427. 69
## 5 UA 421. 5770
## 6 DL 419. 4751
## 7 AA 417. 3188
## 8 B6 400. 5376
## 9 WN 399. 1261
## 10 FL 392. 307
## 11 MQ 367. 2507
## 12 OO 364. 3
## 13 EV 362. 5142
## 14 9E 347. 1696
## 15 US 343. 2015
## 16 YV 332. 53Hawaiian Airlines (HA) operates flights with the highest speeds (according to this data).
Exercise 8:
nycflights %>%
ggplot(aes(x=distance, y=speed)) +
geom_point()
Travel distance and flight speed seem to have a positive monotonic
relationship based on this data.
Exercise 9
nycflights %>%
group_by(carrier) %>%
summarize(mean_distance = mean(distance), n_flights = n()) %>%
arrange(desc(mean_distance))## # A tibble: 16 x 3
## carrier mean_distance n_flights
## <chr> <dbl> <int>
## 1 HA 4983 34
## 2 VX 2501. 497
## 3 AS 2402 66
## 4 F9 1620 69
## 5 UA 1528. 5770
## 6 AA 1350. 3188
## 7 DL 1245. 4751
## 8 B6 1063. 5376
## 9 WN 995. 1261
## 10 FL 651. 307
## 11 OO 615. 3
## 12 MQ 565. 2507
## 13 EV 562. 5142
## 14 US 557. 2015
## 15 9E 538. 1696
## 16 YV 395. 53Hawaiian Airlines (HA) likely operates at the highest speeds because, on average, they’re the airline witht the most arrival delays, so flying faster hopefully compensates at least a little for late arrival