Marginal Plots¶

A marginal plot is a scatterplot (sometimes a density plot or other bivariate plot) that has histograms, boxplots, or other distribution visualization layers in the margins of the x- and y-axes.

It allows studying the relationship between 2 numeric variables.

You can use the ggmarginal() function to add marginal layers to a plot.

In [1]:

import numpy as np
import pandas as pd

from lets_plot import *
from lets_plot.mapping import as_discrete
LetsPlot.setup_html()

In [2]:

# The default plot theme and palette.
LetsPlot.set_theme(theme_light())
palette = scale_color_manual(values=["#394449", "#F7C443"]) + scale_fill_manual(values=["#394449", "#F7C443"])

In [3]:

np.random.seed(0)

cov0=[[1, -.8], 
     [-.8, 1]]     
cov1=[[ 10, .1],
       [.1, .1]]

x0, y0 = np.random.multivariate_normal(mean=[-2,0], cov=cov0, size=200).T
x1, y1 = np.random.multivariate_normal(mean=[0,1], cov=cov1, size=200).T

data = dict(
    x = np.concatenate((x0,x1)),
    y = np.concatenate((y0,y1)),
    c = ["A"]*200 + ["B"]*200
)

In [4]:

p = ggplot(data, aes("x", "y", color="c", fill="c")) + geom_point() + palette
p

Out[4]:

In [5]:

# Add marginal layers to any side on the plot: 
# - [l]eft 
# - [r]ight 
# - [t]op 
# - [b]ottom 

p + ggmarginal("tr", layer=geom_histogram(color="white")) \
  + ggmarginal("lb", layer=geom_density(size=0))

Out[5]:

In [6]:

# Set constant colors to disable the grouping.

p_hist = (p 
          + ggmarginal("tr", layer=geom_histogram(fill="gray", color="white"))
          + ggmarginal("tr", layer=geom_density(fill="rgba(0,0,0,0)", color="red")))
p_hist

Out[6]:

In [7]:

# Add marginal boxplots.
# Make margins smaller using the parameter `size`.

p_hist + ggmarginal("lb", size=0.03, layer=geom_boxplot(fill="white", color="black")) 

Out[7]:

In [8]:

# Combine marginal violin and boxplot.
# Make margins much larger.

p + ggmarginal("rb", size=0.4, layer=geom_violin(trim=False, color="black")) \
  + ggmarginal("rb", layer=geom_boxplot(aes(group="c"), fill="white", color="white", 
                                        alpha=.25, outlier_color="red", width=.2))

Out[8]:

In [9]:

# Show marginal densities on a 2D-density plot.

ggplot(data, aes("x", "y")) + geom_density2df(aes(fill="..level..")) + coord_cartesian() \
 + ggmarginal("tr", layer=geom_area(stat="density"))

Out[9]: