Quick change

notebooks/demo.ipynb

@@ -0,0 +1,130 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%load_ext autoreload\n",
+    "%autoreload 2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import umap\n",
+    "from sklearn.datasets import fetch_openml\n",
+    "import matplotlib.pyplot as plt\n",
+    "import seaborn as sns\n",
+    "\n",
+    "sns.set(context=\"paper\", style=\"white\")\n",
+    "\n",
+    "mnist = fetch_openml(\"mnist_784\", version=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "reducer = umap.UMAP(verbose=True, n_jobs=1)\n",
+    "embedding = reducer.fit_transform(mnist.data)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "fig, ax = plt.subplots(figsize=(12, 10))\n",
+    "color = mnist.target.astype(int)\n",
+    "plt.scatter(embedding[:, 0], embedding[:, 1], c=color, cmap=\"Spectral\", s=0.1)\n",
+    "plt.setp(ax, xticks=[], yticks=[])\n",
+    "plt.title(\"MNIST data embedded into two dimensions by UMAP\", fontsize=18)\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import nano_umap\n",
+    "\n",
+    "nano_reducer = nano_umap.NanoUMAP(verbose=True, n_jobs=-1, n_epochs=500)\n",
+    "nano_embedding = nano_reducer.fit_transform(mnist.data)\n",
+    "\n",
+    "fig, ax = plt.subplots(figsize=(10, 10))\n",
+    "color = mnist.target.astype(int)\n",
+    "plt.scatter(nano_embedding[:, 0], nano_embedding[:, 1], c=color, cmap=\"Spectral\", s=0.1)\n",
+    "plt.setp(ax, xticks=[], yticks=[])\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "precomputed_umap_knn = nano_reducer._get_knn(mnist.data)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "nano_reducer = nano_umap.NanoUMAP(\n",
+    "    precomputed_knn=precomputed_umap_knn,\n",
+    "    learning_rate=2.0,\n",
+    "    n_jobs=-1,\n",
+    "    init=\"spectral\",\n",
+    "    verbose=True,\n",
+    ")\n",
+    "nano_embedding = nano_reducer.fit_transform(mnist.data)\n",
+    "fig, ax = plt.subplots(figsize=(7, 7))\n",
+    "color = mnist.target.astype(int)\n",
+    "plt.scatter(nano_embedding[:, 0], nano_embedding[:, 1], c=color, cmap=\"Spectral\", s=0.1)\n",
+    "plt.setp(ax, xticks=[], yticks=[])\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 131,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "ml3.11",
+   "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": "3.11.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}