SIDS Ch 1

tidyverse
R
Author

Colin Madland

Published

May 16, 2025

Ismay, C., Kim, A. Y., & Valdivia, A. (2025). Statistical Inference via Data Science: A ModernDive into R and the Tidyverse (2nd ed.). Chapman and Hall/CRC.

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(nycflights23)
library(knitr)
library(ggplot2)
flights
# A tibble: 435,352 × 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  2023     1     1        1           2038       203      328              3
 2  2023     1     1       18           2300        78      228            135
 3  2023     1     1       31           2344        47      500            426
 4  2023     1     1       33           2140       173      238           2352
 5  2023     1     1       36           2048       228      223           2252
 6  2023     1     1      503            500         3      808            815
 7  2023     1     1      520            510        10      948            949
 8  2023     1     1      524            530        -6      645            710
 9  2023     1     1      537            520        17      926            818
10  2023     1     1      547            545         2      845            852
# ℹ 435,342 more rows
# ℹ 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>
glimpse(flights)
Rows: 435,352
Columns: 19
$ year           <int> 2023, 2023, 2023, 2023, 2023, 2023, 2023, 2023, 2023, 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> 1, 18, 31, 33, 36, 503, 520, 524, 537, 547, 549, 551, 5…
$ sched_dep_time <int> 2038, 2300, 2344, 2140, 2048, 500, 510, 530, 520, 545, …
$ dep_delay      <dbl> 203, 78, 47, 173, 228, 3, 10, -6, 17, 2, -10, -9, -7, -…
$ arr_time       <int> 328, 228, 500, 238, 223, 808, 948, 645, 926, 845, 905, …
$ sched_arr_time <int> 3, 135, 426, 2352, 2252, 815, 949, 710, 818, 852, 901, …
$ arr_delay      <dbl> 205, 53, 34, 166, 211, -7, -1, -25, 68, -7, 4, -13, -14…
$ carrier        <chr> "UA", "DL", "B6", "B6", "UA", "AA", "B6", "AA", "UA", "…
$ flight         <int> 628, 393, 371, 1053, 219, 499, 996, 981, 206, 225, 800,…
$ tailnum        <chr> "N25201", "N830DN", "N807JB", "N265JB", "N17730", "N925…
$ origin         <chr> "EWR", "JFK", "JFK", "JFK", "EWR", "EWR", "JFK", "EWR",…
$ dest           <chr> "SMF", "ATL", "BQN", "CHS", "DTW", "MIA", "BQN", "ORD",…
$ air_time       <dbl> 367, 108, 190, 108, 80, 154, 192, 119, 258, 157, 164, 1…
$ distance       <dbl> 2500, 760, 1576, 636, 488, 1085, 1576, 719, 1400, 1065,…
$ hour           <dbl> 20, 23, 23, 21, 20, 5, 5, 5, 5, 5, 5, 6, 5, 6, 6, 6, 6,…
$ minute         <dbl> 38, 0, 44, 40, 48, 0, 10, 30, 20, 45, 59, 0, 59, 0, 0, …
$ time_hour      <dttm> 2023-01-01 20:00:00, 2023-01-01 23:00:00, 2023-01-01 2…
airlines
# A tibble: 14 × 2
   carrier name                  
   <chr>   <chr>                 
 1 9E      Endeavor Air Inc.     
 2 AA      American Airlines Inc.
 3 AS      Alaska Airlines Inc.  
 4 B6      JetBlue Airways       
 5 DL      Delta Air Lines Inc.  
 6 F9      Frontier Airlines Inc.
 7 G4      Allegiant Air         
 8 HA      Hawaiian Airlines Inc.
 9 MQ      Envoy Air             
10 NK      Spirit Air Lines      
11 OO      SkyWest Airlines Inc. 
12 UA      United Air Lines Inc. 
13 WN      Southwest Airlines Co.
14 YX      Republic Airline      
kable(airlines)
carrier name
9E Endeavor Air Inc.
AA American Airlines Inc.
AS Alaska Airlines Inc.
B6 JetBlue Airways
DL Delta Air Lines Inc.
F9 Frontier Airlines Inc.
G4 Allegiant Air
HA Hawaiian Airlines Inc.
MQ Envoy Air
NK Spirit Air Lines
OO SkyWest Airlines Inc.
UA United Air Lines Inc.
WN Southwest Airlines Co.
YX Republic Airline
airlines$name
 [1] "Endeavor Air Inc."      "American Airlines Inc." "Alaska Airlines Inc."  
 [4] "JetBlue Airways"        "Delta Air Lines Inc."   "Frontier Airlines Inc."
 [7] "Allegiant Air"          "Hawaiian Airlines Inc." "Envoy Air"             
[10] "Spirit Air Lines"       "SkyWest Airlines Inc."  "United Air Lines Inc." 
[13] "Southwest Airlines Co." "Republic Airline"      
glimpse(airports)
Rows: 1,255
Columns: 8
$ faa   <chr> "AAF", "AAP", "ABE", "ABI", "ABL", "ABQ", "ABR", "ABY", "ACK", "…
$ name  <chr> "Apalachicola Regional Airport", "Andrau Airpark", "Lehigh Valle…
$ lat   <dbl> 29.72750, 29.72250, 40.65210, 32.41130, 67.10630, 35.04020, 45.4…
$ lon   <dbl> -85.02750, -95.58830, -75.44080, -99.68190, -157.85699, -106.609…
$ alt   <dbl> 20, 79, 393, 1791, 334, 5355, 1302, 197, 47, 516, 221, 75, 18, 7…
$ tz    <dbl> -5, -6, -5, -6, -9, -7, -6, -5, -5, -6, -8, -5, -10, -6, -9, -6,…
$ dst   <chr> "A", "A", "A", "A", "A", "A", "A", "A", "A", "A", "A", "A", "A",…
$ tzone <chr> "America/New_York", "America/Chicago", "America/New_York", "Amer…
?flights