Distribusi Delay

library(nycflights13)
library(tidyverse)

## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.0 ──

## ✓ ggplot2 3.3.3     ✓ purrr   0.3.4
## ✓ tibble  3.1.0     ✓ dplyr   1.0.5
## ✓ tidyr   1.1.3     ✓ stringr 1.4.0
## ✓ readr   1.4.0     ✓ forcats 0.5.1

## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

airports

## # A tibble: 1,458 x 8
##    faa   name                       lat    lon   alt    tz dst   tzone          
##    <chr> <chr>                    <dbl>  <dbl> <dbl> <dbl> <chr> <chr>          
##  1 04G   Lansdowne Airport         41.1  -80.6  1044    -5 A     America/New_Yo…
##  2 06A   Moton Field Municipal A…  32.5  -85.7   264    -6 A     America/Chicago
##  3 06C   Schaumburg Regional       42.0  -88.1   801    -6 A     America/Chicago
##  4 06N   Randall Airport           41.4  -74.4   523    -5 A     America/New_Yo…
##  5 09J   Jekyll Island Airport     31.1  -81.4    11    -5 A     America/New_Yo…
##  6 0A9   Elizabethton Municipal …  36.4  -82.2  1593    -5 A     America/New_Yo…
##  7 0G6   Williams County Airport   41.5  -84.5   730    -5 A     America/New_Yo…
##  8 0G7   Finger Lakes Regional A…  42.9  -76.8   492    -5 A     America/New_Yo…
##  9 0P2   Shoestring Aviation Air…  39.8  -76.6  1000    -5 U     America/New_Yo…
## 10 0S9   Jefferson County Intl     48.1 -123.    108    -8 A     America/Los_An…
## # … with 1,448 more rows

flights

## # A tibble: 336,776 x 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
##  7  2013     1     1      555            600        -5      913            854
##  8  2013     1     1      557            600        -3      709            723
##  9  2013     1     1      557            600        -3      838            846
## 10  2013     1     1      558            600        -2      753            745
## # … with 336,766 more rows, and 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>

flights %>% 
  semi_join(airports, c("dest" = "faa")) %>%
  group_by(dest) %>% 
  summarise(delay = mean(arr_delay, na.rm=TRUE)) %>% 
  left_join(airports, by = c("dest"="faa")) %>% 
  ggplot(aes(lon, lat)) +
  borders("state") +
  geom_point(aes(colour = delay)) +
  coord_quickmap()+
  # see chapter 28 for information on scales
  scale_color_gradient2(low = "green", high = "red")

Daftar Pustaka: https://r4ds.had.co.nz/relational-data.html