├── paw.png
├── MaleCat.png
├── FemaleCat.png
├── sCATterplot.Rmd
├── s-cat-terplot.png
└── README.md


/paw.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MangoTheCat/blog_scatterplot/master/paw.png


--------------------------------------------------------------------------------
/MaleCat.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MangoTheCat/blog_scatterplot/master/MaleCat.png


--------------------------------------------------------------------------------
/FemaleCat.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MangoTheCat/blog_scatterplot/master/FemaleCat.png


--------------------------------------------------------------------------------
/sCATterplot.Rmd:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MangoTheCat/blog_scatterplot/master/sCATterplot.Rmd


--------------------------------------------------------------------------------
/s-cat-terplot.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MangoTheCat/blog_scatterplot/master/s-cat-terplot.png


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
  1 | # sCATterplot
  2 | Clara Schartner, Data Scientist  
  3 | 
  4 | 
  5 | 
  6 | It will come as no surprise that cats and ggplot are among our favourite things here at mango. And there is an easy way to combine both:
  7 | 
  8 | ![](s-cat-terplot.png)
  9 | 
 10 | Using the function `annotation_custom` of the popular ggplot2 package it is possible to display images on a plot as points of a scatterplot. This way data can be displayed in a more fun, creative way.  
 11 | In keeping with the cat theme I have chosen a data set about cats and a cat icon based on Mango the cat. The `MASS` package provides a data set called cats which contains the body weight, heart weight and sex of adult cats.
 12 | 
 13 | 
 14 | However since the data has 144 observations only a subset is used for the plot.
 15 | 
 16 | 
 17 | ```r
 18 | library(MASS)
 19 | data(cats)
 20 | head(cats)
 21 | set.seed(1234)
 22 | cats <- cats[sample(1:144, size = 40),]
 23 | ```
 24 | 
 25 | First a normal scatterplot is defined on which the images will be plotted later: 
 26 | 
 27 | 
 28 | ```r
 29 | library(ggplot2)
 30 | sCATter <-ggplot(data = cats, aes(x = Bwt, y = Hwt)) +
 31 |   geom_point(size = 0, aes(group = Sex, colour = Sex)) +
 32 |   theme_classic() +
 33 |   xlab("Body weight") +
 34 |   ylab("Heart weight") +
 35 |   ggtitle("sCATterplot") +
 36 |   theme(plot.title = element_text(hjust = 0.5)) +
 37 |   # create a legend
 38 |   scale_color_manual(
 39 |     values = c("#999999", "#b35900" ),
 40 |     name = "Cat",
 41 |     labels = c("Male cat", "Female cat")
 42 |   ) +
 43 |   guides(colour = guide_legend(override.aes = list(size = 10)))
 44 | ```
 45 | 
 46 | Any png image can be used for the plot, however images with a transparent background are preferable.  
 47 | 
 48 | 
 49 | ```r
 50 | library(png)
 51 | library(grid)
 52 | mCat <- readPNG("MaleCat.png")
 53 | feCat<- readPNG("FemaleCat.png")
 54 | ```
 55 | 
 56 | In the last step the cats are iteratively plotted onto the plot using `annotation_custom`.
 57 | 
 58 | 
 59 | ```r
 60 | for (i in 1:nrow(cats)) {
 61 |   # distinguishing the sex of the cat
 62 |   if (cats$Sex[i] == "F") {
 63 |   image <- feCat
 64 |   } else{
 65 |   image <- mCat
 66 |   }
 67 |   sCATter = sCATter +
 68 |   annotation_custom(
 69 |     rasterGrob(image),
 70 |     xmin = cats$Bwt[i] - 0.6,
 71 |     xmax = cats$Bwt[i] + 0.6,
 72 |     ymin = cats$Hwt[i] - 0.6,
 73 |     ymax = cats$Hwt[i] + 0.6
 74 |   )
 75 | }
 76 | ```
 77 | 
 78 | 
 79 | 
 80 | The cat´s paw trail is displaying a linear regression of heart on body weight. This can easily be added by computing a linear Regression, defining a grid to calculate the expected values and plotting cats on top of this data.
 81 | 
 82 | 
 83 | ```r
 84 | LmCat <- lm(Hwt~Bwt, data = cats)
 85 | 
 86 | steps <- 20
 87 | Reg <- data.frame(Bwt = 
 88 |                     seq(from = min(cats$Bwt), 
 89 |                             to = max(cats$Bwt), 
 90 |                             length.out = steps))
 91 | Reg$Hwt <- predict(LmCat, newdata = Reg)
 92 | ```
 93 | 
 94 | 
 95 | ```r
 96 | sCATter <- sCATter + 
 97 |   geom_point(data = Reg, aes(Bwt, Hwt), size = 0)
 98 | 
 99 | paw <- readPNG("paw.png")
100 | for (i in 1:nrow(Reg)) {
101 |   sCATter = sCATter +
102 |   annotation_custom(
103 |     rasterGrob(paw),
104 |     xmin = Reg$Bwt[i] - 0.6,
105 |     xmax = Reg$Bwt[i] + 0.6,
106 |     ymin = Reg$Hwt[i] - 0.6,
107 |     ymax = Reg$Hwt[i] + 0.6
108 |   )
109 | }
110 | sCATter
111 | ```
112 | 


--------------------------------------------------------------------------------