- bokeh
- numpy
- pandas
- scikit-learn
import asyncio
import micropip
from io import StringIO
from js import fetch
await micropip.install(['panel==0.13.0rc9', 'altair'])
import altair as alt
import panel as pn
import pandas as pd
from panel.io.pyodide import show
from sklearn.cluster import KMeans
pn.config.sizing_mode = 'stretch_width'
data = await fetch('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2020/2020-07-28/penguins.csv')
penguins = pd.read_csv(StringIO(await data.text())).dropna()
cols = list(penguins.columns)[2:6]
x = pn.widgets.Select(name='x', options=cols, value='bill_depth_mm')
y = pn.widgets.Select(name='y', options=cols, value='bill_length_mm')
n_clusters = pn.widgets.IntSlider(name='n_clusters', start=1, end=5, value=3)
@pn.depends(x.param.value, y.param.value, n_clusters.param.value)
def get_clusters(x, y, n_clusters):
kmeans = KMeans(n_clusters=n_clusters)
est = kmeans.fit(penguins[cols].values)
df = penguins.copy()
df['labels'] = est.labels_.astype('str')
centers = df.groupby('labels').mean()
table.value = df
return (
alt.Chart(df)
.mark_point(size=100)
.encode(
x=alt.X(x, scale=alt.Scale(zero=False)),
y=alt.Y(y, scale=alt.Scale(zero=False)),
shape='labels',
color='species'
).properties(width=800) +
alt.Chart(centers)
.mark_point(size=200, shape='cross', color='black')
.encode(x=x+':Q', y=y+':Q')
)
table = pn.widgets.Tabulator(penguins, pagination='remote', page_size=10)
intro = """
This app provides an example of **building a simple dashboard using
Panel**.\n\nIt demonstrates how to take the output of **k-means
clustering on the Penguins dataset** using scikit-learn, parameterizing
the number of clusters and the variables to plot.\n\nThe entire
clustering and plotting pipeline is expressed as a **single reactive
function** that responsively returns an updated plot when one of the
widgets changes.\n\n The **`x` marks the center** of the cluster.
"""
await show(x, 'x-widget')
await show(y, 'y-widget')
await show(n_clusters, 'n-widget')
await show(intro, 'intro')
await show(get_clusters, 'cluster-plot')
await show(table, 'table')