library(tidyverse)
## -- Attaching packages --------------------------------------- tidyverse 1.3.0 --
## v ggplot2 3.3.3 v purrr 0.3.4
## v tibble 3.0.6 v dplyr 1.0.3
## v tidyr 1.1.2 v stringr 1.4.0
## v readr 1.4.0 v forcats 0.5.1
## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
library(nycflights13)
library(psych)
##
## Attaching package: 'psych'
## The following objects are masked from 'package:ggplot2':
##
## %+%, alpha
view(flights)
describe(flights)
## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf
## Warning in FUN(newX[, i], ...): no non-missing arguments to max; returning -Inf
## vars n mean sd median trimmed mad min max
## year 1 336776 2013.00 0.00 2013 2013.00 0.00 2013 2013
## month 2 336776 6.55 3.41 7 6.56 4.45 1 12
## day 3 336776 15.71 8.77 16 15.70 11.86 1 31
## dep_time 4 328521 1349.11 488.28 1401 1346.82 634.55 1 2400
## sched_dep_time 5 336776 1344.25 467.34 1359 1341.60 613.80 106 2359
## dep_delay 6 328521 12.64 40.21 -2 3.32 5.93 -43 1301
## arr_time 7 328063 1502.05 533.26 1535 1526.42 619.73 1 2400
## sched_arr_time 8 336776 1536.38 497.46 1556 1550.67 618.24 1 2359
## arr_delay 9 327346 6.90 44.63 -5 -1.03 20.76 -86 1272
## carrier* 10 336776 7.14 4.14 6 7.00 5.93 1 16
## flight 11 336776 1971.92 1632.47 1496 1830.51 1608.62 1 8500
## tailnum* 12 334264 1814.32 1199.75 1798 1778.21 1587.86 1 4043
## origin* 13 336776 1.95 0.82 2 1.94 1.48 1 3
## dest* 14 336776 50.03 28.12 50 49.56 32.62 1 105
## air_time 15 327346 150.69 93.69 129 140.03 75.61 20 695
## distance 16 336776 1039.91 733.23 872 955.27 569.32 17 4983
## hour 17 336776 13.18 4.66 13 13.15 5.93 1 23
## minute 18 336776 26.23 19.30 29 25.64 23.72 0 59
## time_hour 19 336776 NaN NA NA NaN NA Inf -Inf
## range skew kurtosis se
## year 0 NaN NaN 0.00
## month 11 -0.01 -1.19 0.01
## day 30 0.01 -1.19 0.02
## dep_time 2399 -0.02 -1.09 0.85
## sched_dep_time 2253 -0.01 -1.20 0.81
## dep_delay 1344 4.80 43.95 0.07
## arr_time 2399 -0.47 -0.19 0.93
## sched_arr_time 2358 -0.35 -0.38 0.86
## arr_delay 1358 3.72 29.23 0.08
## carrier* 15 0.36 -1.21 0.01
## flight 8499 0.66 -0.85 2.81
## tailnum* 4042 0.17 -1.24 2.08
## origin* 2 0.09 -1.50 0.00
## dest* 104 0.13 -1.08 0.05
## air_time 675 1.07 0.86 0.16
## distance 4966 1.13 1.19 1.26
## hour 22 0.00 -1.21 0.01
## minute 59 0.09 -1.24 0.03
## time_hour -Inf NA NA NA
average_dep_delay <-
filter(flights, dep_delay > 450 & (arr_time > 600 & arr_time < 1620) | dep_delay > 550)
flight_delay <- ggplot(flights) +
geom_point(mapping = aes(x = arr_time, y = dep_delay)) +
geom_point(data = average_dep_delay, mapping = aes(x = arr_time, y = dep_delay, color = origin))
flight_delay + ggtitle("flight delay") +
xlab("arrival time") +
ylab("departure delay") +
scale_color_manual(name = "departure location", labels = c("EWR", "JFK", "LGA"), values = c("orangered2", "slateblue2", "springgreen3"))
## Warning: Removed 8713 rows containing missing values (geom_point).
## Warning: Removed 1 rows containing missing values (geom_point).
average_dep_delay2 <-
filter(flights, carrier == "B6")
flight_delay2 <- ggplot(average_dep_delay2) +
geom_point(aes(x = arr_time, y = dep_delay, color = "gold2"), na.rm = TRUE) +
geom_point(data = flights, mapping = aes(x = arr_time, y = dep_delay), alpha = 1/20, na.rm = TRUE)
flight_delay2 + ggtitle("flight delay") +
xlab("arrival time") +
ylab("departure delay") +
scale_color_manual(name = "carrier", labels = c("BlueJet"), values = c("gold2"))
## Conclusion I made 2 graphs the first had the main purpose of the first graph is to show the outliers. I looked into those outliers and found that more of the outliers are from JFK airport than any other single airport but it still does not make up more than half of the outliers. After trying to figure out why JFK has so many outliers I looked up “why is JFK” and the sixth auto complete was “why is JFK airport so bad” which while not conclusive does show that JFK is notoriously bad. The second graph I made to illustrate something that I had noticed when I was trying to explain the outliers. I noticed that a lot of the flights from 3AM-6AM where the same carrier so I filtered out those points and placed them in yellow then I took the entire dataset and overlaid it with a greatly reduced opacity. after looking into it, “B6” is the name for JetBlue and I could not figure out why they might be so prevalent in the early morning.