Indexing

library(tidyverse)
## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.1 ──
## ✓ ggplot2 3.3.5     ✓ purrr   0.3.4
## ✓ tibble  3.1.6     ✓ dplyr   1.0.8
## ✓ tidyr   1.2.0     ✓ stringr 1.4.0
## ✓ readr   2.1.2     ✓ forcats 0.5.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()
abalone <- read_csv("abalone.csv")
## Rows: 300 Columns: 9
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## dbl (9): row.names, Length, Diameter, Height, Whole.wt, Shucked.wt, Viscera....
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

Vector indexing

my_vec <- c(1, 3, 4)
my_vec
## [1] 1 3 4
length(my_vec)
## [1] 3
my_vec[3]
## [1] 4
my_vec[c(1,2)]
## [1] 1 3

List indexing

Recall a data frame is a list under the hood, with entries that are the columns.

abalone
## # A tibble: 300 × 9
##    row.names Length Diameter Height Whole.wt Shucked.wt Viscera.wt Shell.wt
##        <dbl>  <dbl>    <dbl>  <dbl>    <dbl>      <dbl>      <dbl>    <dbl>
##  1      1942  0.625    0.47   0.145    0.984     0.475      0.2       0.265
##  2       503  0.62     0.47   0.225    1.12      0.378      0.214     0.36 
##  3       312  0.56     0.44   0.14     0.971     0.443      0.204     0.265
##  4       655  0.37     0.28   0.11     0.230     0.0945     0.0465    0.075
##  5      1004  0.595    0.455  0.15     1.04      0.518      0.220     0.27 
##  6      2522  0.54     0.42   0.12     0.812     0.392      0.146     0.224
##  7      1558  0.425    0.325  0.11     0.317     0.135      0.048     0.09 
##  8      2622  0.695    0.525  0.175    1.74      0.696      0.389     0.505
##  9      3122  0.55     0.425  0.14     0.952     0.490      0.194     0.218
## 10       607  0.345    0.27   0.09     0.195     0.078      0.0455    0.059
## # … with 290 more rows, and 1 more variable: Rings <dbl>
length(abalone)
## [1] 9
abalone[[1]]
##   [1] 1942  503  312  655 1004 2522 1558 2622 3122  607  205 3065   30 2652 1474
##  [16] 3043 2108 2850  343 1850 1593 1555  660  617  685 3123 2904 2762 2535 2270
##  [31]  649  521 1042 1611  426 2393 1184  963 1872  717 1573 1359  196 1258  891
##  [46] 1121 2490  844 2595 1916 2815  135   21 1983 1956 2593 1438  842  322 1200
##  [61] 2180 2632 2911 1166 1204 1312  801 1362 1731  812 2233 2418 1387  455 2168
##  [76] 1485 3042 2171  122 2906 1378 2085  754 3110 1207  350 1063 2199 2373 2504
##  [91] 2597 2726 2095 2112   52 2173  987 2339  526  653 2128  663  762 1001 2858
## [106]  715 2889 1856 1431 2881 2297 1727 2246  810 2094  352 2728 2463 2975  576
## [121] 3029  536 2608  918 2239 2617 2494 1903 3062 1578  454 1299 2861  433 2408
## [136]  674 1669  193 1252  945 1404 1699 1449 1827  973 1889  367 1142 2685 2639
## [151] 1050  400 1518 2566 1497 2973   28 2869 1921 1066  432 1137 3027 1788 2117
## [166]  423 1012 1661  862 2078  759   25 1127 1178 1756 1554 1978 1301  445  959
## [181] 2875 1549 2539  413 1837  108 1335  241  873 2301 1919 1747  670 1071  860
## [196] 1757 1817 1524 2213 2147 2043 2583 1337 2241 2864  372  251 2695 1533  867
## [211] 1196 1302   18 2319 2498 1692 2374  281 2665  431 2810 1496 1219 2081 2447
## [226] 2540  277 1386 1380 2259 2589   60 1310 2386 1297  577 2456  995  198 3082
## [241] 2521 2114 2051 2367  941  467 1250  417 3006 2205  447 3086  805 1246 1659
## [256] 2698 1742 1346  737 2314 1735  389 2612 2915 1232 2190  573 2207  519 1397
## [271]   51 2248 1537 2523  516 2345  133   36 2725 1572  336 1577  905 1191  316
## [286] 1529 1910 2417  777 2944  282  769 1429 1724 2670 1873  186  136 2404 1408
abalone[1]
## # A tibble: 300 × 1
##    row.names
##        <dbl>
##  1      1942
##  2       503
##  3       312
##  4       655
##  5      1004
##  6      2522
##  7      1558
##  8      2622
##  9      3122
## 10       607
## # … with 290 more rows
abalone[[1]][3]
## [1] 312
abalone$Length
##   [1] 0.625 0.620 0.560 0.370 0.595 0.540 0.425 0.695 0.550 0.345 0.420 0.635
##  [13] 0.575 0.510 0.550 0.575 0.675 0.630 0.620 0.485 0.525 0.410 0.585 0.470
##  [25] 0.510 0.560 0.575 0.550 0.640 0.570 0.460 0.210 0.675 0.545 0.580 0.330
##  [37] 0.665 0.505 0.530 0.290 0.480 0.605 0.500 0.430 0.695 0.545 0.490 0.505
##  [49] 0.595 0.600 0.275 0.265 0.355 0.720 0.645 0.590 0.400 0.495 0.190 0.720
##  [61] 0.595 0.375 0.580 0.615 0.730 0.550 0.460 0.605 0.665 0.490 0.560 0.310
##  [73] 0.630 0.645 0.370 0.590 0.575 0.285 0.385 0.575 0.620 0.690 0.580 0.380
##  [85] 0.750 0.610 0.280 0.270 0.405 0.300 0.600 0.395 0.405 0.455 0.400 0.215
##  [97] 0.570 0.655 0.175 0.470 0.400 0.415 0.550 0.595 0.665 0.350 0.510 0.500
## [109] 0.230 0.475 0.535 0.660 0.460 0.520 0.505 0.585 0.405 0.440 0.745 0.610
## [121] 0.515 0.465 0.625 0.410 0.460 0.650 0.420 0.575 0.630 0.490 0.565 0.530
## [133] 0.720 0.565 0.625 0.490 0.610 0.580 0.405 0.465 0.650 0.630 0.440 0.310
## [145] 0.525 0.565 0.580 0.575 0.625 0.460 0.715 0.585 0.665 0.450 0.620 0.720
## [157] 0.590 0.335 0.605 0.315 0.600 0.575 0.495 0.545 0.310 0.490 0.625 0.600
## [169] 0.595 0.610 0.570 0.615 0.560 0.645 0.720 0.390 0.700 0.530 0.410 0.500
## [181] 0.425 0.385 0.660 0.580 0.415 0.500 0.575 0.565 0.620 0.480 0.600 0.700
## [193] 0.450 0.375 0.595 0.725 0.675 0.690 0.595 0.465 0.385 0.530 0.575 0.415
## [205] 0.740 0.660 0.330 0.650 0.285 0.605 0.705 0.535 0.440 0.505 0.505 0.625
## [217] 0.500 0.535 0.570 0.570 0.710 0.620 0.315 0.645 0.550 0.675 0.660 0.630
## [229] 0.620 0.430 0.570 0.505 0.545 0.450 0.525 0.560 0.235 0.580 0.640 0.730
## [241] 0.525 0.385 0.450 0.695 0.460 0.670 0.395 0.630 0.680 0.420 0.565 0.255
## [253] 0.515 0.385 0.600 0.660 0.680 0.585 0.520 0.595 0.670 0.490 0.630 0.590
## [265] 0.365 0.490 0.590 0.290 0.325 0.645 0.520 0.470 0.335 0.545 0.270 0.670
## [277] 0.325 0.465 0.385 0.475 0.620 0.490 0.315 0.690 0.450 0.725 0.580 0.425
## [289] 0.505 0.630 0.360 0.550 0.815 0.655 0.590 0.530 0.620 0.425 0.290 0.655
abalone[["Length"]]
##   [1] 0.625 0.620 0.560 0.370 0.595 0.540 0.425 0.695 0.550 0.345 0.420 0.635
##  [13] 0.575 0.510 0.550 0.575 0.675 0.630 0.620 0.485 0.525 0.410 0.585 0.470
##  [25] 0.510 0.560 0.575 0.550 0.640 0.570 0.460 0.210 0.675 0.545 0.580 0.330
##  [37] 0.665 0.505 0.530 0.290 0.480 0.605 0.500 0.430 0.695 0.545 0.490 0.505
##  [49] 0.595 0.600 0.275 0.265 0.355 0.720 0.645 0.590 0.400 0.495 0.190 0.720
##  [61] 0.595 0.375 0.580 0.615 0.730 0.550 0.460 0.605 0.665 0.490 0.560 0.310
##  [73] 0.630 0.645 0.370 0.590 0.575 0.285 0.385 0.575 0.620 0.690 0.580 0.380
##  [85] 0.750 0.610 0.280 0.270 0.405 0.300 0.600 0.395 0.405 0.455 0.400 0.215
##  [97] 0.570 0.655 0.175 0.470 0.400 0.415 0.550 0.595 0.665 0.350 0.510 0.500
## [109] 0.230 0.475 0.535 0.660 0.460 0.520 0.505 0.585 0.405 0.440 0.745 0.610
## [121] 0.515 0.465 0.625 0.410 0.460 0.650 0.420 0.575 0.630 0.490 0.565 0.530
## [133] 0.720 0.565 0.625 0.490 0.610 0.580 0.405 0.465 0.650 0.630 0.440 0.310
## [145] 0.525 0.565 0.580 0.575 0.625 0.460 0.715 0.585 0.665 0.450 0.620 0.720
## [157] 0.590 0.335 0.605 0.315 0.600 0.575 0.495 0.545 0.310 0.490 0.625 0.600
## [169] 0.595 0.610 0.570 0.615 0.560 0.645 0.720 0.390 0.700 0.530 0.410 0.500
## [181] 0.425 0.385 0.660 0.580 0.415 0.500 0.575 0.565 0.620 0.480 0.600 0.700
## [193] 0.450 0.375 0.595 0.725 0.675 0.690 0.595 0.465 0.385 0.530 0.575 0.415
## [205] 0.740 0.660 0.330 0.650 0.285 0.605 0.705 0.535 0.440 0.505 0.505 0.625
## [217] 0.500 0.535 0.570 0.570 0.710 0.620 0.315 0.645 0.550 0.675 0.660 0.630
## [229] 0.620 0.430 0.570 0.505 0.545 0.450 0.525 0.560 0.235 0.580 0.640 0.730
## [241] 0.525 0.385 0.450 0.695 0.460 0.670 0.395 0.630 0.680 0.420 0.565 0.255
## [253] 0.515 0.385 0.600 0.660 0.680 0.585 0.520 0.595 0.670 0.490 0.630 0.590
## [265] 0.365 0.490 0.590 0.290 0.325 0.645 0.520 0.470 0.335 0.545 0.270 0.670
## [277] 0.325 0.465 0.385 0.475 0.620 0.490 0.315 0.690 0.450 0.725 0.580 0.425
## [289] 0.505 0.630 0.360 0.550 0.815 0.655 0.590 0.530 0.620 0.425 0.290 0.655

This is exactly equivalent to the $ notation.

abalone[c("Length", "Height")]
## # A tibble: 300 × 2
##    Length Height
##     <dbl>  <dbl>
##  1  0.625  0.145
##  2  0.62   0.225
##  3  0.56   0.14 
##  4  0.37   0.11 
##  5  0.595  0.15 
##  6  0.54   0.12 
##  7  0.425  0.11 
##  8  0.695  0.175
##  9  0.55   0.14 
## 10  0.345  0.09 
## # … with 290 more rows

Pipe operator

a %>% b() means: take value of a (any variable, e.g. a tibble/data frame), and call the function b(), using a as the first argument. Most commonly, a is a tibble, b is a dplyr verb.

?dplyr::select

select() can be used to index into tibbles - in particular to extract columns. Above we selected the length and height using abalone[c("Length", "Height")]. We can do the same with select():

select(abalone, Length, Height)
## # A tibble: 300 × 2
##    Length Height
##     <dbl>  <dbl>
##  1  0.625  0.145
##  2  0.62   0.225
##  3  0.56   0.14 
##  4  0.37   0.11 
##  5  0.595  0.15 
##  6  0.54   0.12 
##  7  0.425  0.11 
##  8  0.695  0.175
##  9  0.55   0.14 
## 10  0.345  0.09 
## # … with 290 more rows
abalone %>%
  select(Length, Height)
## # A tibble: 300 × 2
##    Length Height
##     <dbl>  <dbl>
##  1  0.625  0.145
##  2  0.62   0.225
##  3  0.56   0.14 
##  4  0.37   0.11 
##  5  0.595  0.15 
##  6  0.54   0.12 
##  7  0.425  0.11 
##  8  0.695  0.175
##  9  0.55   0.14 
## 10  0.345  0.09 
## # … with 290 more rows
summary(cars)
##      speed           dist       
##  Min.   : 4.0   Min.   :  2.00  
##  1st Qu.:12.0   1st Qu.: 26.00  
##  Median :15.0   Median : 36.00  
##  Mean   :15.4   Mean   : 42.98  
##  3rd Qu.:19.0   3rd Qu.: 56.00  
##  Max.   :25.0   Max.   :120.00
abalone %>%
  dplyr::filter(Length <= 0.5)
## # A tibble: 113 × 9
##    row.names Length Diameter Height Whole.wt Shucked.wt Viscera.wt Shell.wt
##        <dbl>  <dbl>    <dbl>  <dbl>    <dbl>      <dbl>      <dbl>    <dbl>
##  1       655  0.37     0.28   0.11    0.230      0.0945     0.0465   0.075 
##  2      1558  0.425    0.325  0.11    0.317      0.135      0.048    0.09  
##  3       607  0.345    0.27   0.09    0.195      0.078      0.0455   0.059 
##  4       205  0.42     0.335  0.115   0.369      0.171      0.071    0.12  
##  5      1850  0.485    0.385  0.13    0.568      0.250      0.178    0.154 
##  6      1555  0.41     0.3    0.09    0.304      0.129      0.071    0.0955
##  7       617  0.47     0.355  0.14    0.433      0.152      0.095    0.152 
##  8       649  0.46     0.35   0.12    0.488      0.193      0.105    0.155 
##  9       521  0.21     0.15   0.05    0.0385     0.0155     0.0085   0.01  
## 10      2393  0.33     0.25   0.09    0.197      0.085      0.041    0.0605
## # … with 103 more rows, and 1 more variable: Rings <dbl>
dplyr::filter(abalone, Length <= 0.5)
## # A tibble: 113 × 9
##    row.names Length Diameter Height Whole.wt Shucked.wt Viscera.wt Shell.wt
##        <dbl>  <dbl>    <dbl>  <dbl>    <dbl>      <dbl>      <dbl>    <dbl>
##  1       655  0.37     0.28   0.11    0.230      0.0945     0.0465   0.075 
##  2      1558  0.425    0.325  0.11    0.317      0.135      0.048    0.09  
##  3       607  0.345    0.27   0.09    0.195      0.078      0.0455   0.059 
##  4       205  0.42     0.335  0.115   0.369      0.171      0.071    0.12  
##  5      1850  0.485    0.385  0.13    0.568      0.250      0.178    0.154 
##  6      1555  0.41     0.3    0.09    0.304      0.129      0.071    0.0955
##  7       617  0.47     0.355  0.14    0.433      0.152      0.095    0.152 
##  8       649  0.46     0.35   0.12    0.488      0.193      0.105    0.155 
##  9       521  0.21     0.15   0.05    0.0385     0.0155     0.0085   0.01  
## 10      2393  0.33     0.25   0.09    0.197      0.085      0.041    0.0605
## # … with 103 more rows, and 1 more variable: Rings <dbl>
abalone %>%
  slice(c(4,6))
## # A tibble: 2 × 9
##   row.names Length Diameter Height Whole.wt Shucked.wt Viscera.wt Shell.wt Rings
##       <dbl>  <dbl>    <dbl>  <dbl>    <dbl>      <dbl>      <dbl>    <dbl> <dbl>
## 1       655   0.37     0.28   0.11    0.230     0.0945     0.0465    0.075    10
## 2      2522   0.54     0.42   0.12    0.812     0.392      0.146     0.224     9
abalone %>%
  select(c(2,7))
## # A tibble: 300 × 2
##    Length Viscera.wt
##     <dbl>      <dbl>
##  1  0.625     0.2   
##  2  0.62      0.214 
##  3  0.56      0.204 
##  4  0.37      0.0465
##  5  0.595     0.220 
##  6  0.54      0.146 
##  7  0.425     0.048 
##  8  0.695     0.389 
##  9  0.55      0.194 
## 10  0.345     0.0455
## # … with 290 more rows
abalone[c(4,6),]
## # A tibble: 2 × 9
##   row.names Length Diameter Height Whole.wt Shucked.wt Viscera.wt Shell.wt Rings
##       <dbl>  <dbl>    <dbl>  <dbl>    <dbl>      <dbl>      <dbl>    <dbl> <dbl>
## 1       655   0.37     0.28   0.11    0.230     0.0945     0.0465    0.075    10
## 2      2522   0.54     0.42   0.12    0.812     0.392      0.146     0.224     9
abalone[,c(2,7)]
## # A tibble: 300 × 2
##    Length Viscera.wt
##     <dbl>      <dbl>
##  1  0.625     0.2   
##  2  0.62      0.214 
##  3  0.56      0.204 
##  4  0.37      0.0465
##  5  0.595     0.220 
##  6  0.54      0.146 
##  7  0.425     0.048 
##  8  0.695     0.389 
##  9  0.55      0.194 
## 10  0.345     0.0455
## # … with 290 more rows

Advanced dplyr

library(nycflights13)
airports
## # A tibble: 1,458 × 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/…
##  2 06A   Moton Field Municipal Airport   32.5  -85.7   264    -6 A     America/…
##  3 06C   Schaumburg Regional             42.0  -88.1   801    -6 A     America/…
##  4 06N   Randall Airport                 41.4  -74.4   523    -5 A     America/…
##  5 09J   Jekyll Island Airport           31.1  -81.4    11    -5 A     America/…
##  6 0A9   Elizabethton Municipal Airport  36.4  -82.2  1593    -5 A     America/…
##  7 0G6   Williams County Airport         41.5  -84.5   730    -5 A     America/…
##  8 0G7   Finger Lakes Regional Airport   42.9  -76.8   492    -5 A     America/…
##  9 0P2   Shoestring Aviation Airfield    39.8  -76.6  1000    -5 U     America/…
## 10 0S9   Jefferson County Intl           48.1 -123.    108    -8 A     America/…
## # … with 1,448 more rows
airports_new <- airports %>%
  group_by(tzone) %>%
  summarise(mean_lon=mean(lon),
            mean_lat=mean(lat),
            n_obs=n())
airports_new
## # A tibble: 10 × 4
##    tzone               mean_lon mean_lat n_obs
##    <chr>                  <dbl>    <dbl> <int>
##  1 America/Anchorage     -153.      61.3   239
##  2 America/Chicago        -92.9     37.2   342
##  3 America/Denver        -108.      40.4   119
##  4 America/Los_Angeles   -120.      40.0   176
##  5 America/New_York       -79.4     37.6   519
##  6 America/Phoenix       -112.      33.8    38
##  7 America/Vancouver     -127.      55.0     2
##  8 Asia/Chongqing         115.      32.9     2
##  9 Pacific/Honolulu      -157.      20.8    18
## 10 <NA>                   -58.7     54.7     3
airports %>%
    summarise(mean_lon=mean(lon),
            mean_lat=mean(lat))
## # A tibble: 1 × 2
##   mean_lon mean_lat
##      <dbl>    <dbl>
## 1    -103.     41.6
flights
## # A tibble: 336,776 × 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>
airports
## # A tibble: 1,458 × 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/…
##  2 06A   Moton Field Municipal Airport   32.5  -85.7   264    -6 A     America/…
##  3 06C   Schaumburg Regional             42.0  -88.1   801    -6 A     America/…
##  4 06N   Randall Airport                 41.4  -74.4   523    -5 A     America/…
##  5 09J   Jekyll Island Airport           31.1  -81.4    11    -5 A     America/…
##  6 0A9   Elizabethton Municipal Airport  36.4  -82.2  1593    -5 A     America/…
##  7 0G6   Williams County Airport         41.5  -84.5   730    -5 A     America/…
##  8 0G7   Finger Lakes Regional Airport   42.9  -76.8   492    -5 A     America/…
##  9 0P2   Shoestring Aviation Airfield    39.8  -76.6  1000    -5 U     America/…
## 10 0S9   Jefferson County Intl           48.1 -123.    108    -8 A     America/…
## # … with 1,448 more rows
left_join(airports, flights, by=c("faa"="origin"))
## # A tibble: 338,231 × 26
##    faa   name      lat    lon   alt    tz dst   tzone  year month   day dep_time
##    <chr> <chr>   <dbl>  <dbl> <dbl> <dbl> <chr> <chr> <int> <int> <int>    <int>
##  1 04G   Lansdo…  41.1  -80.6  1044    -5 A     Amer…    NA    NA    NA       NA
##  2 06A   Moton …  32.5  -85.7   264    -6 A     Amer…    NA    NA    NA       NA
##  3 06C   Schaum…  42.0  -88.1   801    -6 A     Amer…    NA    NA    NA       NA
##  4 06N   Randal…  41.4  -74.4   523    -5 A     Amer…    NA    NA    NA       NA
##  5 09J   Jekyll…  31.1  -81.4    11    -5 A     Amer…    NA    NA    NA       NA
##  6 0A9   Elizab…  36.4  -82.2  1593    -5 A     Amer…    NA    NA    NA       NA
##  7 0G6   Willia…  41.5  -84.5   730    -5 A     Amer…    NA    NA    NA       NA
##  8 0G7   Finger…  42.9  -76.8   492    -5 A     Amer…    NA    NA    NA       NA
##  9 0P2   Shoest…  39.8  -76.6  1000    -5 U     Amer…    NA    NA    NA       NA
## 10 0S9   Jeffer…  48.1 -123.    108    -8 A     Amer…    NA    NA    NA       NA
## # … with 338,221 more rows, and 14 more variables: sched_dep_time <int>,
## #   dep_delay <dbl>, arr_time <int>, sched_arr_time <int>, arr_delay <dbl>,
## #   carrier <chr>, flight <int>, tailnum <chr>, dest <chr>, air_time <dbl>,
## #   distance <dbl>, hour <dbl>, minute <dbl>, time_hour <dttm>
inner_join(airports, flights, by=c("faa"="origin"))
## # A tibble: 336,776 × 26
##    faa   name       lat   lon   alt    tz dst   tzone  year month   day dep_time
##    <chr> <chr>    <dbl> <dbl> <dbl> <dbl> <chr> <chr> <int> <int> <int>    <int>
##  1 EWR   Newark …  40.7 -74.2    18    -5 A     Amer…  2013     1     1      517
##  2 EWR   Newark …  40.7 -74.2    18    -5 A     Amer…  2013     1     1      554
##  3 EWR   Newark …  40.7 -74.2    18    -5 A     Amer…  2013     1     1      555
##  4 EWR   Newark …  40.7 -74.2    18    -5 A     Amer…  2013     1     1      558
##  5 EWR   Newark …  40.7 -74.2    18    -5 A     Amer…  2013     1     1      559
##  6 EWR   Newark …  40.7 -74.2    18    -5 A     Amer…  2013     1     1      601
##  7 EWR   Newark …  40.7 -74.2    18    -5 A     Amer…  2013     1     1      606
##  8 EWR   Newark …  40.7 -74.2    18    -5 A     Amer…  2013     1     1      607
##  9 EWR   Newark …  40.7 -74.2    18    -5 A     Amer…  2013     1     1      608
## 10 EWR   Newark …  40.7 -74.2    18    -5 A     Amer…  2013     1     1      615
## # … with 336,766 more rows, and 14 more variables: sched_dep_time <int>,
## #   dep_delay <dbl>, arr_time <int>, sched_arr_time <int>, arr_delay <dbl>,
## #   carrier <chr>, flight <int>, tailnum <chr>, dest <chr>, air_time <dbl>,
## #   distance <dbl>, hour <dbl>, minute <dbl>, time_hour <dttm>