Running all unsupervised model types on a dataset with Driverless AI.

dai_unsupervised.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "5b16e7cb",
   "metadata": {},
   "source": [
    "# Driverless AI for Unsupervised Models"
   ]
  },
  {
   "cell_type": "raw",
   "id": "56657e4b-5af1-4a4f-8e47-8d797bd86b88",
   "metadata": {},
   "source": [
    "from getpass import getpass\n",
    "\n",
    "from h2o_ai_cloud import token_provider, steam_client\n",
    "from h2osteam.clients import DriverlessClient"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "8dca2fde",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Visit https://cloud-internal.h2o.ai/auth/get-platform-token to get your platform token\n"
     ]
    },
    {
     "name": "stdin",
     "output_type": "stream",
     "text": [
      "Enter your platform token:  ···········································································································································································································································································································································································································································································································································································································································································································································································································\n"
     ]
    }
   ],
   "source": [
    "steam = steam_client(token_provider())"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2069f13a",
   "metadata": {},
   "source": [
    "### Connect to Driverless AI\n",
    "We'll create a connection object called dai that we will use to interact with the platform."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "cfbc936e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "622 \t default-driverless-kubernetes \t stopped \t dai-quickstart\n"
     ]
    }
   ],
   "source": [
    "# List all instances I own\n",
    "for instance in steam.get_driverless_instances():\n",
    "    print(instance[\"id\"], \"\\t\", instance[\"profile_name\"], \"\\t\", instance[\"status\"], \"\\t\", instance[\"name\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "5c2eb80b-ff2b-4d40-85fa-be5cd861ba36",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Driverless AI instance is starting, please wait...\n",
      "Driverless AI instance is running\n"
     ]
    }
   ],
   "source": [
    "# Turn a machine on\n",
    "dai_machine = DriverlessClient(steam).get_instance(name=\"dai-quickstart\")\n",
    "dai_machine.start()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "86a54d4a-6a85-4fb4-8544-ea57bc5adb18",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Connect with Driverelss AI\n",
    "dai = dai_machine.connect()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "50b37ee6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'https://steam.cloud-internal.h2o.ai:443/oidc-login-start?forward=/proxy/driverless/622/openid/callback'"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Login to the UI as needed\n",
    "dai_machine.openid_login_url()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "26d4bbca",
   "metadata": {},
   "source": [
    "### List Existing Datasets"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "120f71ab",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "    | Type    | Key                                  | Name\n",
      "----+---------+--------------------------------------+-------------------\n",
      "  0 | Dataset | 4c4a1534-fcc6-11ec-aab1-36f210f733cb | Telco_Churn\n",
      "  1 | Dataset | 48a52cdc-f8db-11ec-8618-9e7cf9db9673 | telco_churn_test\n",
      "  2 | Dataset | 48a50cd4-f8db-11ec-8618-9e7cf9db9673 | telco_churn_train\n",
      "  3 | Dataset | 472e4bcc-f8db-11ec-8618-9e7cf9db9673 | Fancy New Name\n"
     ]
    }
   ],
   "source": [
    "print(dai.datasets.list(start_index=0, count=4))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "79c5de39-70a9-40eb-9c4d-8f654b6527f6",
   "metadata": {},
   "outputs": [],
   "source": [
    "dataset = dai.datasets.get(key=\"4c4a1534-fcc6-11ec-aab1-36f210f733cb\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fd347d51",
   "metadata": {},
   "source": [
    "## Unsupervised Models"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "ba42073b-31d2-41cb-80cb-c5c9d6af550f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['IsolationForestAnomaly',\n",
       " 'KMeans',\n",
       " 'KMeansFreq',\n",
       " 'KMeansOHE',\n",
       " 'TruncSVD',\n",
       " 'Unsupervised']"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# All unsupervised model types\n",
    "unsupervised_models = [m.name for m in dai.recipes.models.list() if m.is_unsupervised]\n",
    "unsupervised_models"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "21db3828",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Experiment launched at: https://steam.cloud-internal.h2o.ai:443/proxy/driverless/622/#/experiment?key=1092955c-0261-11ed-9bbc-2abf4ebade94\n",
      "Experiment launched at: https://steam.cloud-internal.h2o.ai:443/proxy/driverless/622/#/experiment?key=11305436-0261-11ed-9bbc-2abf4ebade94\n",
      "Experiment launched at: https://steam.cloud-internal.h2o.ai:443/proxy/driverless/622/#/experiment?key=11ce36ba-0261-11ed-9bbc-2abf4ebade94\n",
      "Experiment launched at: https://steam.cloud-internal.h2o.ai:443/proxy/driverless/622/#/experiment?key=127c0eac-0261-11ed-9bbc-2abf4ebade94\n",
      "Experiment launched at: https://steam.cloud-internal.h2o.ai:443/proxy/driverless/622/#/experiment?key=13245ee0-0261-11ed-9bbc-2abf4ebade94\n",
      "Experiment launched at: https://steam.cloud-internal.h2o.ai:443/proxy/driverless/622/#/experiment?key=13cd0e8c-0261-11ed-9bbc-2abf4ebade94\n"
     ]
    }
   ],
   "source": [
    "for algo in unsupervised_models:\n",
    "    dai.experiments.create_async(\n",
    "        train_dataset=dataset,\n",
    "        name=f'Telco Churn - {algo}', \n",
    "        task='unsupervised',\n",
    "        models=[algo],\n",
    "        target_column='',\n",
    "        force=True\n",
    "    )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5facf437",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Driverless AI instance is stopping, please wait...\n"
     ]
    }
   ],
   "source": [
    "dai_machine.stop()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b9298dc5",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python3 (H2O AI Cloud)",
   "language": "python",
   "name": "haic"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.12"
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": true,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {
    "height": "calc(100% - 180px)",
    "left": "10px",
    "top": "150px",
    "width": "336px"
   },
   "toc_section_display": true,
   "toc_window_display": true
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}