CI: Improve example dataset usage (#3020)

* Convert regression plot docstrings to notebooks

* Convert matrix API exapmles to notebooks

* Remove dataset cache from test workflow and cache using git clone in doc build

Author: mwaskom

.github/workflows/ci.yaml

@@ -12,6 +12,7 @@ on:
 env:
   NB_KERNEL: python
   MPLBACKEND: Agg
+  SEABORN_DATA: ~/seaborn-data
 
 jobs:
   build-docs:
@@ -34,7 +35,8 @@ jobs:
           sudo apt-get install pandoc
 
       - name: Cache datasets
-        run: python ci/cache_datasets.py
+        run: |
+          git clone https://github.com/mwaskom/seaborn-data.git
 
       - name: Build docs
         env:
@@ -80,9 +82,6 @@ jobs:
           if [[ ${{matrix.deps }} == 'pinned' ]]; then DEPS='-r ci/deps_pinned.txt'; fi
           pip install .[dev$EXTRAS] $DEPS
 
-      - name: Cache datasets
-        run: python ci/cache_datasets.py
-
       - name: Run tests
         run: make ${{ matrix.target }}
 

doc/_docstrings/clustermap.ipynb

@@ -0,0 +1,184 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ffc1e1d9-fa74-4121-aa87-e1a8665e4c2b",
+   "metadata": {
+    "tags": [
+     "hide"
+    ]
+   },
+   "outputs": [],
+   "source": [
+    "import seaborn as sns\n",
+    "sns.set_theme()"
+   ]
+  },
+  {
+   "cell_type": "raw",
+   "id": "41b4f602-32af-44f8-bf1a-0f1695c9abbb",
+   "metadata": {},
+   "source": [
+    "Plot a heatmap with row and column clustering:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c715bd8f-cf5d-4caa-9244-336b3d0248a8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "iris = sns.load_dataset(\"iris\")\n",
+    "species = iris.pop(\"species\")\n",
+    "sns.clustermap(iris)"
+   ]
+  },
+  {
+   "cell_type": "raw",
+   "id": "1cc3134c-579a-442a-97d8-a878651ce90a",
+   "metadata": {},
+   "source": [
+    "Change the size and layout of the figure:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fd33cf4b-9589-4b9a-a246-0b95bad28c51",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sns.clustermap(\n",
+    "    iris,\n",
+    "    figsize=(7, 5),\n",
+    "    row_cluster=False,\n",
+    "    dendrogram_ratio=(.1, .2),\n",
+    "    cbar_pos=(0, .2, .03, .4)\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "raw",
+   "id": "c5d3408d-f5d6-4045-9d61-15573a981587",
+   "metadata": {},
+   "source": [
+    "Add colored labels to identify observations:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "79d3fe52-6146-4f33-a39a-1d4a47243ea5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "lut = dict(zip(species.unique(), \"rbg\"))\n",
+    "row_colors = species.map(lut)\n",
+    "sns.clustermap(iris, row_colors=row_colors)"
+   ]
+  },
+  {
+   "cell_type": "raw",
+   "id": "f2f944e2-36cd-4653-86b4-6d2affec13d6",
+   "metadata": {},
+   "source": [
+    "Use a different colormap and adjust the limits of the color range:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6137c7ad-db92-47b8-9d00-3228c4e1f7df",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sns.clustermap(iris, cmap=\"mako\", vmin=0, vmax=10)"
+   ]
+  },
+  {
+   "cell_type": "raw",
+   "id": "93f96d1c-9d04-464f-93c9-4319caa8504a",
+   "metadata": {},
+   "source": [
+    "Use differente clustering parameters:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f9e76bde-a222-4eca-971f-54f56ad53281",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sns.clustermap(iris, metric=\"correlation\", method=\"single\")"
+   ]
+  },
+  {
+   "cell_type": "raw",
+   "id": "ea6ed3fd-188d-4244-adac-ec0169c02205",
+   "metadata": {},
+   "source": [
+    "Standardize the data within the columns:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e5f744c4-b959-4ed1-b2cf-6046c9214568",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sns.clustermap(iris, standard_scale=1)"
+   ]
+  },
+  {
+   "cell_type": "raw",
+   "id": "7ca72242-4eb0-4f8e-b0c0-d1ef7166b738",
+   "metadata": {},
+   "source": [
+    "Normalize the data within rows:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "33815c4c-9bae-4226-bd11-3dfdb7ecab2b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sns.clustermap(iris, z_score=0, cmap=\"vlag\", center=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0f37d57a-b049-4665-9c24-4d5fbbca00ba",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "py310",
+   "language": "python",
+   "name": "py310"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.0"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}