Create a notebook comparing nx and cuGraph using synthetic data

notebooks/applications/gen_550M.ipynb

@@ -0,0 +1,138 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import gc\n",
+    "import os\n",
+    "from time import perf_counter\n",
+    "import numpy as np\n",
+    "import random\n",
+    "import math\n",
+    "\n",
+    "# rapids\n",
+    "import cugraph\n",
+    "import cudf\n",
+    "\n",
+    "# NetworkX libraries\n",
+    "import networkx as nx\n",
+    "\n",
+    "# RMAT data generator\n",
+    "from cugraph.generators import rmat\n",
+    "from datetime import datetime"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def generate_data(scale, edgefactor=16):\n",
+    "    _gdf = rmat(\n",
+    "        scale,\n",
+    "        (2 ** scale) * edgefactor,\n",
+    "        0.57,\n",
+    "        0.19,\n",
+    "        0.19,\n",
+    "        42,\n",
+    "        clip_and_flip=False,\n",
+    "        scramble_vertex_ids=True,\n",
+    "        create_using=None,  # return edgelist instead of Graph instance\n",
+    "        mg=False\n",
+    "        )\n",
+    "    print('Generating a dataframe of ' + str(len(_gdf)) + '...')\n",
+    "    return _gdf"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def gen_times(count, start_date, end_date):\n",
+    "    range_start = start_date.timestamp()\n",
+    "    range_end =  int(end_date.timestamp())\n",
+    "    random_list = []\n",
+    "    for i in range(count):\n",
+    "        random_list.append(random.randint(range_start,range_end))\n",
+    "    return cudf.Series(random_list,name='Date', dtype=int)\n",
+    "#    return [datetime.fromtimestamp(i) for i in random_list]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def gen_amounts(count,value_range):\n",
+    "    random_list = []\n",
+    "    for i in range(count):\n",
+    "        random_list.append(random.randint(0,value_range*100))\n",
+    "    return cudf.Series(random_list,name='amount', dtype=float).divide(100)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "start_time = '1/1/2022 01:00:00 AM'\n",
+    "end_time =   '7/1/2022 01:00:00 AM'\n",
+    "amount_range = 25000\n",
+    "d1 = datetime.strptime(start_time, '%m/%d/%Y %I:%M:%S %p')\n",
+    "d2 = datetime.strptime(end_time, '%m/%d/%Y %I:%M:%S %p')\n",
+    "\n",
+    "df = generate_data(15)\n",
+    "\n",
+    "dates = gen_times(len(df),d1, d2)\n",
+    "amounts = gen_amounts(len(df),amount_range)\n",
+    "df['amounts'] = amounts\n",
+    "df['date'] = dates\n",
+    "len(df)\n",
+    "df.head(4)\n",
+    "df.to_csv('../data/data_500m.csv') #append mode"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "cudfdev",
+   "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": "3.9.15"
+  },
+  "orig_nbformat": 4,
+  "vscode": {
+   "interpreter": {
+    "hash": "587ff963ecd34554a9da41c94362e2baa062d9a57502e220f049e10816826984"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}