Anscombe's quartet

val df =
    DataFrame.readCSV(
        "https://gist.githubusercontent.com/ericbusboom/b2ac1d366c005cd2ed8c/raw/c92c66e43d144fa9c29dbd602d5af6988e8db533/anscombes.csv",
        parserOptions = ParserOptions(locale = Locale.ENGLISH)
    )

df.head()

id	dataset	x	y
0	I	10	8.04
1	I	8	6.95
2	I	13	7.58
3	I	9	8.81
4	I	11	8.33

df.describe()

name	type	count	unique	top	freq	mean	std	min	median	max
id	Int	44	44	0	1	21.5	12.845	0	21	43
dataset	String	44	4	I	11	null	null	I	II	IV
x	Double	44	12	8.0	13	9	3.199	4.0	8.0	19.0
y	Double	44	43	8.84	2	7.501	1.959	3.1	7.52	12.74

df.plot {
    points {
        x("x") {
            scale = continuous(0.0..20.0)
        }
        y("y") {
            scale = continuous(0.0..20.0)
        }
        color(dataset)
        size = 5.0
    }

    abLine {
        slope.constant(0.5)
        intercept.constant(3)

        width = 1.7
        alpha = 0.7
    }

    facetWrap(nCol = 2) {
        facet(dataset)
    }
}

Last modified: 13 May 2024