Penguin Crossfilter

import numpy as np
import pandas as pd
import panel as pn

import holoviews as hv
import hvplot.pandas # noqa

pn.extension(template='fast')

pn.state.template.logo = 'https://github.com/allisonhorst/palmerpenguins/raw/main/man/figures/logo.png'

Introduction

welcome = "## Welcome and meet the Palmer penguins!"

penguins_art = pn.pane.PNG('https://raw.githubusercontent.com/allisonhorst/palmerpenguins/main/man/figures/palmerpenguins.png', height=160)

credit = "### Artwork by @allison_horst"

instructions = """
Use the box-select and lasso-select tools to select a subset of penguins
and reveal more information about the selected subgroup through the power
of cross-filtering.
"""

license = """
### License

Data are available by CC-0 license in accordance with the Palmer Station LTER Data Policy and the LTER Data Access Policy for Type I data."
"""

art = pn.Column(
    welcome, penguins_art, credit, instructions, license,
    sizing_mode='stretch_width'
).servable(area='sidebar')

art

Building some plots

Let us first load the Palmer penguin dataset (Gorman et al.) which contains measurements about a number of penguin species:

penguins = pd.read_csv('https://datasets.holoviz.org/penguins/v1/penguins.csv')
penguins = penguins[~penguins.sex.isnull()].reset_index().sort_values('species')

penguins.head()

	index	species	island	bill_length_mm	bill_depth_mm	flipper_length_mm	body_mass_g	sex	year
0	0	Adelie	Torgersen	39.1	18.7	181.0	3750.0	male	2007
94	100	Adelie	Biscoe	35.0	17.9	192.0	3725.0	female	2009
95	101	Adelie	Biscoe	41.0	20.0	203.0	4725.0	male	2009
96	102	Adelie	Biscoe	37.7	16.0	183.0	3075.0	female	2009
97	103	Adelie	Biscoe	37.8	20.0	190.0	4250.0	male	2009

Next we will set up a linked selections instance that will allow us to perform cross-filtering on the plots we will create in the next step:

ls = hv.link_selections.instance()

def count(selected):
    return f"## {len(selected)}/{len(penguins)} penguins selected"

selected = pn.pane.Markdown(
    pn.bind(count, ls.selection_param(penguins)),
    align='center', width=400, margin=(0, 100, 0, 0)
)

header = pn.Row(
    pn.layout.HSpacer(), selected,
    sizing_mode='stretch_width'
).servable(area='header')

selected

Now we can start plotting the data with hvPlot, which provides a familiar API to pandas .plot users but generates interactive plots and use the linked selections object to allow cross-filtering across the plots:

colors = {
    'Adelie': '#1f77b4',
    'Gentoo': '#ff7f0e',
    'Chinstrap': '#2ca02c'
}

scatter = penguins.hvplot.points(
    'bill_length_mm', 'bill_depth_mm', c='species',
    cmap=colors, responsive=True, min_height=300
)

histogram = penguins.hvplot.hist(
    'body_mass_g', by='species', color=hv.dim('species').categorize(colors),
    legend=False, alpha=0.5, responsive=True, min_height=300
)

bars = penguins.hvplot.bar(
    'species', 'index', c='species', cmap=colors,
    responsive=True, min_height=300, ylabel=''
).aggregate(function=np.count_nonzero)

violin = penguins.hvplot.violin(
    'flipper_length_mm', by=['species', 'sex'], cmap='Category20',
    responsive=True, min_height=300, legend='bottom_right'
).opts(split='sex')

plots = pn.pane.HoloViews(
    ls(scatter.opts(show_legend=False) + bars + histogram + violin).opts(sizing_mode='stretch_both').cols(2)
).servable(title='Palmer Penguins')

plots