[WIP] Distributed NearestNeighbors

.gitignore

@@ -127,3 +127,6 @@ dmypy.json
 
 # Pyre type checker
 .pyre/
+
+# dask
+.lock

distributed/README.md

@@ -0,0 +1,4 @@
+# Getting started
+1. Install Google Cloud CLI tool https://cloud.google.com/sdk/gcloud
+2. Enable Compute Engine API https://console.cloud.google.com/marketplace/product/google/compute.googleapis.com
+3. Install RAPIDS https://docs.rapids.ai/deployment/stable/cloud/gcp/gke/ 

distributed/distributed_knn.ipynb

@@ -0,0 +1,332 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Distributed Nearest Neighbors with cuML"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from dask_cuda import LocalCUDACluster\n",
+    "from dask.distributed import Client\n",
+    "\n",
+    "cluster = LocalCUDACluster()\n",
+    "client = Client(cluster)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "BlazingContext ready\n"
+     ]
+    }
+   ],
+   "source": [
+    "from blazingsql import BlazingContext\n",
+    "\n",
+    "bc = BlazingContext(dask_client=client, network_interface='lo')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import dask_cudf\n",
+    "\n",
+    "df = dask_cudf.read_csv('https://github.com/gumdropsteve/datasets/raw/master/iris.csv')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "bc.create_table('iris', df)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# df.tail()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# df.compute().to_pandas().plot(kind='scatter', x='sepal_length', y='petal_width', c='target', cmap=('spring'), sharex=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# df.species.compute().unique()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Nearest Neighbors\n",
+    "Nearest Neighbors enables the query of the k-nearest neighbors from a set of input samples."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from cuml.dask.neighbors import NearestNeighbors\n",
+    "\n",
+    "\"\"\"Multi-node Multi-GPU NearestNeighbors Model.\"\"\"\n",
+    "\n",
+    "nn = NearestNeighbors(client=client)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>sepal_length</th>\n",
+       "      <th>sepal_width</th>\n",
+       "      <th>petal_length</th>\n",
+       "      <th>petal_width</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>147</th>\n",
+       "      <td>6.5</td>\n",
+       "      <td>3.0</td>\n",
+       "      <td>5.2</td>\n",
+       "      <td>2.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>148</th>\n",
+       "      <td>6.2</td>\n",
+       "      <td>3.4</td>\n",
+       "      <td>5.4</td>\n",
+       "      <td>2.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>149</th>\n",
+       "      <td>5.9</td>\n",
+       "      <td>3.0</td>\n",
+       "      <td>5.1</td>\n",
+       "      <td>1.8</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "     sepal_length  sepal_width  petal_length  petal_width\n",
+       "147           6.5          3.0           5.2          2.0\n",
+       "148           6.2          3.4           5.4          2.3\n",
+       "149           5.9          3.0           5.1          1.8"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# X = df[['sepal_length', 'sepal_width', 'petal_length', 'petal_width']]\n",
+    "X = bc.sql('select sepal_length, sepal_width, petal_length, petal_width from iris')\n",
+    "\n",
+    "X.tail(3)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<cuml.dask.neighbors.nearest_neighbors.NearestNeighbors at 0x7fdbc80549d0>"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# pass features and labels into model\n",
+    "nn.fit(X)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "NearestNeighbors returns a tuple of distances and indices.\n",
+    "\n",
+    "distances: cuDF DataFrame or numpy ndarray\n",
+    "    The distances of the k-nearest neighbors for each column vector\n",
+    "    in X\n",
+    "\n",
+    "indices: cuDF DataFrame of numpy ndarray\n",
+    "    The indices of the k-nearest neighbors for each column vector in X"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "distances, indicies = nn.kneighbors(X, n_neighbors=3)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>0</th>\n",
+       "      <th>1</th>\n",
+       "      <th>2</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>147</th>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.223631</td>\n",
+       "      <td>0.346403</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>148</th>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.244975</td>\n",
+       "      <td>0.300019</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>149</th>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.282832</td>\n",
+       "      <td>0.316213</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       0         1         2\n",
+       "147  0.0  0.223631  0.346403\n",
+       "148  0.0  0.244975  0.300019\n",
+       "149  0.0  0.282832  0.316213"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "distances.tail(3)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# indicies.tail(3)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "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": "3.7.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}