{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"tags": [
"hide-input"
]
},
"outputs": [],
"source": [
"import panel as pn\n",
"\n",
"import pandas as pd\n",
"import holoviews as hv\n",
"\n",
"from sklearn.cluster import KMeans\n",
"\n",
"penguins = pd.read_csv('https://raw.githubusercontent.com/mwaskom/seaborn-data/master/penguins.csv')\n",
"cols = list(penguins.columns)[:-1]\n",
"\n",
"pn.extension('ace')\n",
"\n",
"import hvplot.pandas"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"tags": [
"hide-input"
]
},
"outputs": [],
"source": [
"slider = pn.widgets.IntSlider(start=0, end=10)\n",
"\n",
"img = pn.pane.JPG(f\"https://picsum.photos/800/300?image=0\", embed=False, height=300)\n",
"\n",
"slider.jscallback(args={'img': img}, value=\"\"\"\n",
"img.text = ''\n",
"\"\"\")\n",
"\n",
"app = pn.Column(slider, img)\n",
"\n",
"ace = pn.widgets.Ace(readonly=True, width=800, height=200, language='python', theme='monokai', value=\\\n",
"\"\"\"slider = pn.widgets.IntSlider(start=0, end=10)\n",
"\n",
"def slideshow(index):\n",
" url = f\"https://picsum.photos/800/300?image={index}\"\n",
" return pn.pane.JPG(url)\n",
"\n",
"output = pn.bind(slideshow, slider)\n",
"\n",
"app = pn.Column(slider, output)\"\"\")\n",
"\n",
"app1 = pn.Tabs(('Output', app), ('Code', ace))\n",
"\n",
"penguins = pd.read_csv('https://raw.githubusercontent.com/mwaskom/seaborn-data/master/penguins.csv').dropna()\n",
"cols = list(penguins.columns)[2:6]\n",
"\n",
"x = pn.widgets.Select(name='x', options=cols)\n",
"y = pn.widgets.Select(name='y', options=cols, value='bill_depth_mm')\n",
"n_clusters = pn.widgets.IntSlider(name='n_clusters', start=2, end=5, value=3)\n",
"\n",
"def cluster(data, n_clusters):\n",
" kmeans = KMeans(n_clusters=n_clusters)\n",
" est = kmeans.fit(data)\n",
" return est.labels_.astype('str')\n",
"\n",
"def plot(x, y, n_clusters):\n",
" penguins['labels'] = cluster(penguins.iloc[:, 2:6].values, n_clusters)\n",
" centers = penguins.groupby('labels').mean()\n",
" return (penguins.sort_values('labels').hvplot.scatter(\n",
" x, y, c='labels', hover_cols=['species'], line_width=1, size=60, frame_width=400, frame_height=400\n",
" ).opts(marker=hv.dim('species').categorize({'Adelie': 'square', 'Chinstrap': 'circle', 'Gentoo': 'triangle'})) * centers.hvplot.scatter(\n",
" x, y, marker='x', color='black', size=400, padding=0.1, line_width=5\n",
" ))\n",
"\n",
"explanation = pn.pane.Markdown(\"\"\"\n",
"This app applies k-means clustering on the Palmer Penguins dataset using scikit-learn, parameterizing the number of clusters and the variables to plot.\n",
"
\n",
"Each cluster is denoted by one color while the penguin species is indicated using markers: \n",
"
\n",
"● - Adelie, ▲ - Gentoo, ■ - Chinstrap\n",
"
\n",
"By comparing the two we can assess the performance of the clustering algorithm.\n",
"
\n",
"\"\"\")\n",
"\n",
"code = pn.widgets.Ace(language='python', theme='monokai', height=360, value=\\\n",
"\"\"\"x = pn.widgets.Select(name='x', options=cols)\n",
"y = pn.widgets.Select(name='y', options=cols, value='bill_depth_mm')\n",
"n_clusters = pn.widgets.IntSlider(name='n_clusters', start=2, end=5, value=3)\n",
"explanation = pn.pane.Markdown(...)\n",
"\n",
"def plot_clusters(x, y, n_clusters):\n",
" ...\n",
" \n",
"pn.Row(\n",
" pn.WidgetBox(x, y, n_clusters, explanation), \n",
" pn.bind(plot, x, y, n_clusters)\n",
")\"\"\", width=800)\n",
"\n",
"app2 = pn.Tabs(\n",
" ('Output', pn.Column(\n",
" pn.Row(\n",
" pn.WidgetBox(x, y, n_clusters, explanation), \n",
" pn.bind(plot, x, y, n_clusters)\n",
" )\n",
" )),\n",
" ('Code', code)\n",
")\n",
"\n",
"pn.Row(pn.layout.HSpacer(), pn.Tabs(\n",
" ('Penguin K-Means Clustering', app2),\n",
" ('Slideshow', app1)\n",
"), pn.layout.HSpacer(), sizing_mode='stretch_width').embed(max_opts=4, json=True, json_prefix='json')"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.10"
},
"toc-autonumbering": false,
"toc-showcode": true,
"toc-showmarkdowntxt": true,
"toc-showtags": true,
"widgets": {
"application/vnd.jupyter.widget-state+json": {
"state": {},
"version_major": 2,
"version_minor": 0
}
}
},
"nbformat": 4,
"nbformat_minor": 4
}