{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "08641fd2",
   "metadata": {},
   "source": [
    "Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.\n",
    "\n",
    "SPDX-License-Identifier: Apache-2.0"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "aee7eb47",
   "metadata": {},
   "source": [
    "# Train and Predict Wifi Data Using GDN\n",
    "\n",
    "This notebook contains the steps to\n",
    "   1. Find/Load the preprocess data for training using GDN  \n",
    "   2. Train the model  \n",
    "   3. Model inference-- Visualize the trained graph and results  "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4cf931c1",
   "metadata": {},
   "source": [
    "# Loading the Preprocessed Data For Training\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c0624c7e",
   "metadata": {},
   "outputs": [],
   "source": [
    "import sys \n",
    "sys.path.append('../../src/anomaly_detection_spatial_temporal_data/')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "4a9dc61b",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import yaml\n",
    "from model.GDN.GDNTrainer import GDNTrainer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "81e57bfa",
   "metadata": {},
   "outputs": [],
   "source": [
    "data_dir = \"../../data/03_primary/wifi/gdn\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "95b8eced",
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(f\"{data_dir}/wifi_sensor_list.txt\", \"r\") as f:\n",
    "    sensors = f.read().split(\"\\n\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "7f4f4a44",
   "metadata": {},
   "outputs": [],
   "source": [
    "print(f\"Number of sensors: {len(sensors)}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b3f2b2fb",
   "metadata": {},
   "outputs": [],
   "source": [
    "print(sensors)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "91f2ad9f",
   "metadata": {},
   "outputs": [],
   "source": [
    "train_df = pd.read_csv(f\"{data_dir}/wifi_gdn_train.csv\")\n",
    "test_df = pd.read_csv(f\"{data_dir}/wifi_gdn_test.csv\")\n",
    "\n",
    "print(train_df.shape)\n",
    "print(test_df.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "aa086b4c",
   "metadata": {},
   "outputs": [],
   "source": [
    "model_config_file = \"../../conf/base/parameters/gdn.yml\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "3cff5843",
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(model_config_file, \"r\") as stream:\n",
    "    try:\n",
    "        model_config = yaml.safe_load(stream)\n",
    "        print(model_config)\n",
    "    except yaml.YAMLError as exc:\n",
    "        print(exc)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "95d3cf40",
   "metadata": {},
   "outputs": [],
   "source": [
    "train_config = model_config[\"train_config\"]\n",
    "env_config = model_config[\"env_config_wifi\"]\n",
    "\n",
    "env_config[\"checkpoint_save_dir\"] = \"../../data/07_model_output/gdn-wifi-notebook\""
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c7891669",
   "metadata": {},
   "source": [
    "## Train Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ca23601a",
   "metadata": {},
   "outputs": [],
   "source": [
    "trainer = GDNTrainer(\n",
    "    sensors, train_df, test_df, \n",
    "    train_config, env_config\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e2d27450",
   "metadata": {},
   "outputs": [],
   "source": [
    "trainer.run()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d24db616",
   "metadata": {},
   "source": [
    "## Model Inference"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "3830eca1",
   "metadata": {},
   "outputs": [],
   "source": [
    "pred, labels = trainer.predict()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b106e028",
   "metadata": {},
   "outputs": [],
   "source": [
    "pred"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "7147954a",
   "metadata": {},
   "outputs": [],
   "source": [
    "pred.shape\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "458d9bee",
   "metadata": {},
   "outputs": [],
   "source": [
    "np.array(labels).shape\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9607775f",
   "metadata": {},
   "source": [
    "# References\n",
    "\n",
    "Anisa Allahdadi and Ricardo Morla. 2017. 802.11 Wireless Access Point Usage Simulation and Anomaly Detection. CoRR abs/1707.02933, (2017). Retrieved from http://arxiv.org/abs/1707.02933 \n",
    "\n",
    "Ailin Deng and Bryan Hooi. 2021. Graph Neural Network-Based Anomaly Detection in Multivariate Time Series. CoRR abs/2106.06947, (2021). Retrieved from https://arxiv.org/abs/2106.06947 "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2261a987",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "kedro-gdn-venv",
   "language": "python",
   "name": "kedro-gdn-venv"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}