{
 "cells": [
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "eb84f2fd",
   "metadata": {},
   "source": [
    "# AutoGluon Tabular with Deep Learning Containers on SageMaker"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "a389c40c",
   "metadata": {},
   "source": [
    "---\n",
    "\n",
    "This notebook's CI test result for us-west-2 is as follows. CI test results in other regions can be found at the end of the notebook. \n",
    "\n",
    "![This us-west-2 badge failed to load. Check your device's internet connectivity, otherwise the service is currently unavailable](https://h75twx4l60.execute-api.us-west-2.amazonaws.com/sagemaker-nb/us-west-2/advanced_functionality|autogluon-tabular-containers|AutoGluon_Tabular_SageMaker_Containers.ipynb)\n",
    "\n",
    "---"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "775e84ba",
   "metadata": {},
   "source": [
    "[AutoGluon](https://github.com/awslabs/autogluon) automates machine learning tasks enabling you to easily achieve strong predictive performance in your applications. With just a few lines of code, you can train and deploy high-accuracy deep learning models on tabular, image, and text data.\n",
    "This example shows how to use AutoGluon-Tabular with Amazon SageMaker by applying [pre-built deep learning containers](https://github.com/aws/deep-learning-containers/blob/master/available_images.md#autogluon-training-containers)."
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "f4992c4f",
   "metadata": {},
   "source": [
    "# Prerequisites"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9ea8f68a",
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "# Ensure autogluon the most recent images information is available in SageMaker Python SDK\n",
    "!pip install -q -U 'sagemaker>=2.126.0'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "faf25796",
   "metadata": {},
   "outputs": [],
   "source": [
    "import sagemaker\n",
    "import pandas as pd\n",
    "from ag_model import (\n",
    "    AutoGluonSagemakerEstimator,\n",
    "    AutoGluonNonRepackInferenceModel,\n",
    "    AutoGluonSagemakerInferenceModel,\n",
    "    AutoGluonRealtimePredictor,\n",
    "    AutoGluonBatchPredictor,\n",
    ")\n",
    "from sagemaker import utils\n",
    "from sagemaker.serializers import CSVSerializer\n",
    "import os\n",
    "import boto3\n",
    "\n",
    "role = sagemaker.get_execution_role()\n",
    "sagemaker_session = sagemaker.session.Session()\n",
    "region = sagemaker_session._region_name\n",
    "\n",
    "bucket = sagemaker_session.default_bucket()\n",
    "s3_prefix = f\"autogluon_sm/{utils.sagemaker_timestamp()}\"\n",
    "output_path = f\"s3://{bucket}/{s3_prefix}/output/\""
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "2c006dc0",
   "metadata": {},
   "source": [
    "### Get the data\n",
    "We'll be using the [Adult Census dataset](https://archive.ics.uci.edu/ml/datasets/adult) for this exercise. \n",
    "This data was extracted from the [1994 Census bureau database](http://www.census.gov/en.html) by Ronny Kohavi and Barry Becker (Data Mining and Visualization, Silicon Graphics), with the task being to predict if an individual person makes over 50K a year. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d00074fc",
   "metadata": {},
   "outputs": [],
   "source": [
    "!mkdir -p data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a102722b",
   "metadata": {},
   "outputs": [],
   "source": [
    "columns = [\n",
    "    \"age\",\n",
    "    \"workclass\",\n",
    "    \"fnlwgt\",\n",
    "    \"education\",\n",
    "    \"education-num\",\n",
    "    \"marital-status\",\n",
    "    \"occupation\",\n",
    "    \"relationship\",\n",
    "    \"race\",\n",
    "    \"sex\",\n",
    "    \"capital-gain\",\n",
    "    \"capital-loss\",\n",
    "    \"hours-per-week\",\n",
    "    \"native-country\",\n",
    "    \"class\",\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5f1218fa",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Download the data - needed for examples; in notebooks, S3 URL can be directly used for loading from S3\n",
    "s3 = boto3.client(\"s3\")\n",
    "s3.download_file(\n",
    "    f\"sagemaker-example-files-prod-{region}\",\n",
    "    \"datasets/tabular/uci_adult/adult.data\",\n",
    "    \"data/adult.data\",\n",
    ")\n",
    "s3.download_file(\n",
    "    f\"sagemaker-example-files-prod-{region}\",\n",
    "    \"datasets/tabular/uci_adult/adult.test\",\n",
    "    \"data/adult.test\",\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c242a5f8",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_train = pd.read_csv(\"data/adult.data\", header=None, names=columns)\n",
    "df_train.to_csv(\"data/train.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9f2888ae",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_test = pd.read_csv(\"data/adult.test\", header=None, skiprows=1, names=columns)\n",
    "df_test[\"class\"] = df_test[\"class\"].map(\n",
    "    {\n",
    "        \" <=50K.\": \" <=50K\",\n",
    "        \" >50K.\": \" >50K\",\n",
    "    }\n",
    ")\n",
    "df_test.to_csv(\"data/test.csv\")"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "8213590f",
   "metadata": {},
   "source": [
    "# Training"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "0b453761",
   "metadata": {},
   "source": [
    "Users can create their own training/inference scripts using [SageMaker Python SDK examples](https://sagemaker.readthedocs.io/en/stable/overview.html#prepare-a-training-script).\n",
    "The scripts we created allow to pass AutoGluon configuration as a YAML file (located in `data/config` directory).\n",
    "\n",
    "We are using [official AutoGluon Deep Learning Container images](https://github.com/aws/deep-learning-containers/blob/master/available_images.md#autogluon-training-containers) with custom training scripts (see `scripts/` directory)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "da167200",
   "metadata": {},
   "outputs": [],
   "source": [
    "ag = AutoGluonSagemakerEstimator(\n",
    "    role=role,\n",
    "    entry_point=\"scripts/tabular_train.py\",\n",
    "    region=region,\n",
    "    instance_count=1,\n",
    "    instance_type=\"ml.m5.2xlarge\",\n",
    "    framework_version=\"0.6\",\n",
    "    py_version=\"py38\",\n",
    "    base_job_name=\"autogluon-tabular-train\",\n",
    "    disable_profiler=True,\n",
    "    debugger_hook_config=False,\n",
    ")"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "69870f34",
   "metadata": {},
   "source": [
    "Upload the data to s3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "204a60b0",
   "metadata": {},
   "outputs": [],
   "source": [
    "s3_prefix = f\"autogluon_sm/{utils.sagemaker_timestamp()}\"\n",
    "train_input = ag.sagemaker_session.upload_data(\n",
    "    path=os.path.join(\"data\", \"train.csv\"), key_prefix=s3_prefix\n",
    ")\n",
    "eval_input = ag.sagemaker_session.upload_data(\n",
    "    path=os.path.join(\"data\", \"test.csv\"), key_prefix=s3_prefix\n",
    ")\n",
    "config_input = ag.sagemaker_session.upload_data(\n",
    "    path=os.path.join(\"config\", \"config-med.yaml\"), key_prefix=s3_prefix\n",
    ")\n",
    "\n",
    "# Provide inference script so the script repacking is not needed later\n",
    "# See more here: https://docs.aws.amazon.com/sagemaker/latest/dg/mlopsfaq.html\n",
    "# Q. Why do I see a repack step in my SageMaker pipeline?\n",
    "inference_script = ag.sagemaker_session.upload_data(\n",
    "    path=os.path.join(\"scripts\", \"tabular_serve.py\"), key_prefix=s3_prefix\n",
    ")"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "fedb3195",
   "metadata": {},
   "source": [
    "### Fit The Model\n",
    "For local training set `instance_type` to local.\n",
    "\n",
    "For non-local training the recommended instance type is `ml.m5.2xlarge`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "794ea738",
   "metadata": {},
   "outputs": [],
   "source": [
    "job_name = utils.unique_name_from_base(\"test-autogluon-image\")\n",
    "ag.fit(\n",
    "    {\n",
    "        \"config\": config_input,\n",
    "        \"train\": train_input,\n",
    "        \"test\": eval_input,\n",
    "        \"serving\": inference_script,\n",
    "    },\n",
    "    job_name=job_name,\n",
    ")"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "a4d57c00",
   "metadata": {},
   "source": [
    "### Model export\n",
    "\n",
    "AutoGluon models are portable: everything needed to deploy a trained model is in the tarball created by SageMaker.\n",
    "\n",
    "The artifact can be used locally, on EC2/ECS/EKS or served via SageMaker Inference."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e1d5dccd",
   "metadata": {},
   "outputs": [],
   "source": [
    "!aws s3 cp {ag.model_data} ."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b240c86b",
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "!ls -alF model.tar.gz"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "7633d597",
   "metadata": {
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "source": [
    "# Endpoint Deployment"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "bb4fb9ec",
   "metadata": {},
   "source": [
    "Upload the model we trained earlier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "90f6eaa2",
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "endpoint_name = sagemaker.utils.unique_name_from_base(\"sagemaker-autogluon-serving-trained-model\")\n",
    "\n",
    "model_data = sagemaker_session.upload_data(\n",
    "    path=os.path.join(\".\", \"model.tar.gz\"), key_prefix=f\"{endpoint_name}/models\"\n",
    ")"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "c4c9a075",
   "metadata": {},
   "source": [
    "Deploy remote or local endpoint"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "8fa6dd02",
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "instance_type = \"ml.m5.2xlarge\"\n",
    "# instance_type = 'local'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ae49533e",
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "model = AutoGluonNonRepackInferenceModel(\n",
    "    model_data=model_data,\n",
    "    role=role,\n",
    "    region=region,\n",
    "    framework_version=\"0.6\",\n",
    "    py_version=\"py38\",\n",
    "    instance_type=instance_type,\n",
    "    source_dir=\"scripts\",\n",
    "    entry_point=\"tabular_serve.py\",\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "7e333d24",
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "model.deploy(initial_instance_count=1, serializer=CSVSerializer(), instance_type=instance_type)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "30190a41-71df-4eca-a616-a32ee9b5b50a",
   "metadata": {},
   "outputs": [],
   "source": [
    "predictor = AutoGluonRealtimePredictor(model.endpoint_name)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "52982b98",
   "metadata": {},
   "source": [
    "### Predict on unlabeled test data\n",
    "\n",
    "Remove target variable (`class`) from the data and get predictions for a sample of 100 rows using the deployed endpoint."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "85e3fab4",
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "df = pd.read_csv(\"data/test.csv\")\n",
    "data = df[:100]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c61ab16a",
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "preds = predictor.predict(data.drop(columns=\"class\"))\n",
    "preds"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2f7a8ab4",
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "p = preds[[\"pred\"]]\n",
    "p = p.join(data[\"class\"]).rename(columns={\"class\": \"actual\"})\n",
    "p.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a9d9dcbe",
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "print(f\"{(p.pred==p.actual).astype(int).sum()}/{len(p)} are correct\")"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "084ee65e",
   "metadata": {},
   "source": [
    "### Cleanup Endpoint"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "cdd315e3",
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "predictor.delete_endpoint()"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "f8197080",
   "metadata": {},
   "source": [
    "# Batch Transform\n",
    "\n",
    "Deploying a trained model to a hosted endpoint has been available in SageMaker since launch and is a great way to provide real-time predictions to a service like a website or mobile app. But, if the goal is to generate predictions from a trained model on a large dataset where minimizing latency isn’t a concern, then the batch transform functionality may be easier, more scalable, and more appropriate.\n",
    "\n",
    "[Read more about Batch Transform](https://docs.aws.amazon.com/sagemaker/latest/dg/batch-transform.html)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "4b607438",
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "endpoint_name = sagemaker.utils.unique_name_from_base(\n",
    "    \"sagemaker-autogluon-batch_transform-trained-model\"\n",
    ")\n",
    "\n",
    "model_data = sagemaker_session.upload_data(\n",
    "    path=os.path.join(\".\", \"model.tar.gz\"), key_prefix=f\"{endpoint_name}/models\"\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ab078513",
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "instance_type = \"ml.m5.2xlarge\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c88630d4",
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "model = AutoGluonSagemakerInferenceModel(\n",
    "    model_data=model_data,\n",
    "    role=role,\n",
    "    region=region,\n",
    "    framework_version=\"0.6\",\n",
    "    py_version=\"py38\",\n",
    "    instance_type=instance_type,\n",
    "    entry_point=\"tabular_serve-batch.py\",\n",
    "    source_dir=\"scripts\",\n",
    "    predictor_cls=AutoGluonBatchPredictor,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "276fd30b",
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "transformer = model.transformer(\n",
    "    instance_count=1,\n",
    "    instance_type=instance_type,\n",
    "    strategy=\"MultiRecord\",\n",
    "    max_payload=6,\n",
    "    max_concurrent_transforms=1,\n",
    "    output_path=output_path,\n",
    "    accept=\"application/json\",\n",
    "    assemble_with=\"Line\",\n",
    ")"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "a9559625",
   "metadata": {},
   "source": [
    "Prepare data for batch transform"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a8dde772",
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "pd.read_csv(f\"data/test.csv\")[:100].to_csv(\"data/test_no_header.csv\", header=False, index=False)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "355fabc8",
   "metadata": {},
   "source": [
    "Upload data to sagemaker session"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "eb3dbd00",
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "test_input = transformer.sagemaker_session.upload_data(\n",
    "    path=os.path.join(\"data\", \"test_no_header.csv\"), key_prefix=s3_prefix\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b21b56f5",
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "transformer.transform(\n",
    "    test_input,\n",
    "    input_filter=\"$[:14]\",  # filter-out target variable\n",
    "    split_type=\"Line\",\n",
    "    content_type=\"text/csv\",\n",
    "    output_filter=\"$['class']\",  # keep only prediction class in the output\n",
    ")\n",
    "\n",
    "transformer.wait()"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "ee44ccfb",
   "metadata": {},
   "source": [
    "Download batch transform outputs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e07ff698",
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "!aws s3 cp {transformer.output_path[:-1]}/test_no_header.csv.out ."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ac3b0953",
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "p = pd.concat(\n",
    "    [\n",
    "        pd.read_json(\"test_no_header.csv.out\", orient=\"index\")\n",
    "        .sort_index()\n",
    "        .rename(columns={0: \"preds\"}),\n",
    "        pd.read_csv(\"data/test.csv\")[[\"class\"]].iloc[:100].rename(columns={\"class\": \"actual\"}),\n",
    "    ],\n",
    "    axis=1,\n",
    ")\n",
    "p.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "7150fa02",
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "print(f\"{(p.preds==p.actual).astype(int).sum()}/{len(p)} are correct\")"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "cd3e9e5a",
   "metadata": {
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "source": [
    "# Conclusion\n",
    "\n",
    "In this tutorial we successfully trained an AutoGluon model and explored a few options how to deploy it using SageMaker. Any of the sections of this tutorial (training/endpoint inference/batch inference) can be used independently (i.e. train locally, deploy to SageMaker, or vice versa).\n",
    "\n",
    "Next steps:\n",
    "* [Learn more](https://auto.gluon.ai) about AutoGluon, explore [tutorials](https://auto.gluon.ai/stable/tutorials/index.html).\n",
    "* Explore [SageMaker inference documentation](https://docs.aws.amazon.com/sagemaker/latest/dg/deploy-model.html)."
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "cffbeae1",
   "metadata": {},
   "source": [
    "## Notebook CI Test Results\n",
    "\n",
    "This notebook was tested in multiple regions. The test results are as follows, except for us-west-2 which is shown at the top of the notebook.\n",
    "\n",
    "![This us-east-1 badge failed to load. Check your device's internet connectivity, otherwise the service is currently unavailable](https://h75twx4l60.execute-api.us-west-2.amazonaws.com/sagemaker-nb/us-east-1/advanced_functionality|autogluon-tabular-containers|AutoGluon_Tabular_SageMaker_Containers.ipynb)\n",
    "\n",
    "![This us-east-2 badge failed to load. Check your device's internet connectivity, otherwise the service is currently unavailable](https://h75twx4l60.execute-api.us-west-2.amazonaws.com/sagemaker-nb/us-east-2/advanced_functionality|autogluon-tabular-containers|AutoGluon_Tabular_SageMaker_Containers.ipynb)\n",
    "\n",
    "![This us-west-1 badge failed to load. Check your device's internet connectivity, otherwise the service is currently unavailable](https://h75twx4l60.execute-api.us-west-2.amazonaws.com/sagemaker-nb/us-west-1/advanced_functionality|autogluon-tabular-containers|AutoGluon_Tabular_SageMaker_Containers.ipynb)\n",
    "\n",
    "![This ca-central-1 badge failed to load. Check your device's internet connectivity, otherwise the service is currently unavailable](https://h75twx4l60.execute-api.us-west-2.amazonaws.com/sagemaker-nb/ca-central-1/advanced_functionality|autogluon-tabular-containers|AutoGluon_Tabular_SageMaker_Containers.ipynb)\n",
    "\n",
    "![This sa-east-1 badge failed to load. Check your device's internet connectivity, otherwise the service is currently unavailable](https://h75twx4l60.execute-api.us-west-2.amazonaws.com/sagemaker-nb/sa-east-1/advanced_functionality|autogluon-tabular-containers|AutoGluon_Tabular_SageMaker_Containers.ipynb)\n",
    "\n",
    "![This eu-west-1 badge failed to load. Check your device's internet connectivity, otherwise the service is currently unavailable](https://h75twx4l60.execute-api.us-west-2.amazonaws.com/sagemaker-nb/eu-west-1/advanced_functionality|autogluon-tabular-containers|AutoGluon_Tabular_SageMaker_Containers.ipynb)\n",
    "\n",
    "![This eu-west-2 badge failed to load. Check your device's internet connectivity, otherwise the service is currently unavailable](https://h75twx4l60.execute-api.us-west-2.amazonaws.com/sagemaker-nb/eu-west-2/advanced_functionality|autogluon-tabular-containers|AutoGluon_Tabular_SageMaker_Containers.ipynb)\n",
    "\n",
    "![This eu-west-3 badge failed to load. Check your device's internet connectivity, otherwise the service is currently unavailable](https://h75twx4l60.execute-api.us-west-2.amazonaws.com/sagemaker-nb/eu-west-3/advanced_functionality|autogluon-tabular-containers|AutoGluon_Tabular_SageMaker_Containers.ipynb)\n",
    "\n",
    "![This eu-central-1 badge failed to load. Check your device's internet connectivity, otherwise the service is currently unavailable](https://h75twx4l60.execute-api.us-west-2.amazonaws.com/sagemaker-nb/eu-central-1/advanced_functionality|autogluon-tabular-containers|AutoGluon_Tabular_SageMaker_Containers.ipynb)\n",
    "\n",
    "![This eu-north-1 badge failed to load. Check your device's internet connectivity, otherwise the service is currently unavailable](https://h75twx4l60.execute-api.us-west-2.amazonaws.com/sagemaker-nb/eu-north-1/advanced_functionality|autogluon-tabular-containers|AutoGluon_Tabular_SageMaker_Containers.ipynb)\n",
    "\n",
    "![This ap-southeast-1 badge failed to load. Check your device's internet connectivity, otherwise the service is currently unavailable](https://h75twx4l60.execute-api.us-west-2.amazonaws.com/sagemaker-nb/ap-southeast-1/advanced_functionality|autogluon-tabular-containers|AutoGluon_Tabular_SageMaker_Containers.ipynb)\n",
    "\n",
    "![This ap-southeast-2 badge failed to load. Check your device's internet connectivity, otherwise the service is currently unavailable](https://h75twx4l60.execute-api.us-west-2.amazonaws.com/sagemaker-nb/ap-southeast-2/advanced_functionality|autogluon-tabular-containers|AutoGluon_Tabular_SageMaker_Containers.ipynb)\n",
    "\n",
    "![This ap-northeast-1 badge failed to load. Check your device's internet connectivity, otherwise the service is currently unavailable](https://h75twx4l60.execute-api.us-west-2.amazonaws.com/sagemaker-nb/ap-northeast-1/advanced_functionality|autogluon-tabular-containers|AutoGluon_Tabular_SageMaker_Containers.ipynb)\n",
    "\n",
    "![This ap-northeast-2 badge failed to load. Check your device's internet connectivity, otherwise the service is currently unavailable](https://h75twx4l60.execute-api.us-west-2.amazonaws.com/sagemaker-nb/ap-northeast-2/advanced_functionality|autogluon-tabular-containers|AutoGluon_Tabular_SageMaker_Containers.ipynb)\n",
    "\n",
    "![This ap-south-1 badge failed to load. Check your device's internet connectivity, otherwise the service is currently unavailable](https://h75twx4l60.execute-api.us-west-2.amazonaws.com/sagemaker-nb/ap-south-1/advanced_functionality|autogluon-tabular-containers|AutoGluon_Tabular_SageMaker_Containers.ipynb)\n"
   ]
  }
 ],
 "metadata": {
  "instance_type": "ml.t3.medium",
  "kernelspec": {
   "display_name": "conda_pytorch_p38",
   "language": "python",
   "name": "conda_pytorch_p38"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}