anscombe quartet plotting and summarizing

anscombe_quartet.md

library(ggplot2)
library(patchwork)
library(tidyr)
library(magrittr)
library(dplyr)

datasets::anscombe
#>    x1 x2 x3 x4    y1   y2    y3    y4
#> 1  10 10 10  8  8.04 9.14  7.46  6.58
#> 2   8  8  8  8  6.95 8.14  6.77  5.76
#> 3  13 13 13  8  7.58 8.74 12.74  7.71
#> 4   9  9  9  8  8.81 8.77  7.11  8.84
#> 5  11 11 11  8  8.33 9.26  7.81  8.47
#> 6  14 14 14  8  9.96 8.10  8.84  7.04
#> 7   6  6  6  8  7.24 6.13  6.08  5.25
#> 8   4  4  4 19  4.26 3.10  5.39 12.50
#> 9  12 12 12  8 10.84 9.13  8.15  5.56
#> 10  7  7  7  8  4.82 7.26  6.42  7.91
#> 11  5  5  5  8  5.68 4.74  5.73  6.89

plot_fn = function(x,y){
  maxx=max(anscombe[[x]])
  maxy=max(anscombe[[y]])
  ggplot(anscombe, aes(eval(get(x)), eval(get(y)))) +
    geom_point(color='red', size=2.3) +
    geom_smooth(method='lm', se=FALSE) +
    labs(x=x,y=y) +
    scale_x_continuous(limits = c(0,maxx + 2), expand=c(0,0)) +
    scale_y_continuous(limits = c(0, maxy + 2), expand=c(0,0)) +
    theme_classic()
}

p1 = plot_fn('x1', 'y1')
p2 = plot_fn('x2', 'y2')
p3 = plot_fn('x3', 'y3')
p4 = plot_fn('x4', 'y4')
(p1 + p2)/(p3 + p4) + plot_annotation(title = 'Anscombe Quartet',
                                      theme = theme(plot.title = element_text(hjust=0.5)))

anscombe %>%
  pivot_longer(cols=everything(),
               names_to='variables',
               values_to='values') %>%
  group_by(variables) %>%
  summarise('mean'=mean(values), 'variance'=var(values)) 
#> # A tibble: 8 x 3
#>   variables  mean variance
#>   <chr>     <dbl>    <dbl>
#> 1 x1         9       11   
#> 2 x2         9       11   
#> 3 x3         9       11   
#> 4 x4         9       11   
#> 5 y1         7.50     4.13
#> 6 y2         7.50     4.13
#> 7 y3         7.5      4.12
#> 8 y4         7.50     4.12