004_Deploy_Infer_101_2.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 1;\n",
       "                var nbb_unformatted_code = \"%load_ext nb_black\";\n",
       "                var nbb_formatted_code = \"%load_ext nb_black\";\n",
       "                var nbb_cells = Jupyter.notebook.get_cells();\n",
       "                for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                    if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                        if (nbb_cells[i].get_text() == nbb_unformatted_code) {\n",
       "                             nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                        }\n",
       "                        break;\n",
       "                    }\n",
       "                }\n",
       "            }, 500);\n",
       "            "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "%load_ext nb_black"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 2;\n",
       "                var nbb_unformatted_code = \"import os\\nimport boto3\\nimport logging\\nfrom datetime import datetime\\n\\nboto3.set_stream_logger(name=\\\"botocore.credentials\\\", level=logging.WARNING)\";\n",
       "                var nbb_formatted_code = \"import os\\nimport boto3\\nimport logging\\nfrom datetime import datetime\\n\\nboto3.set_stream_logger(name=\\\"botocore.credentials\\\", level=logging.WARNING)\";\n",
       "                var nbb_cells = Jupyter.notebook.get_cells();\n",
       "                for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                    if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                        if (nbb_cells[i].get_text() == nbb_unformatted_code) {\n",
       "                             nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                        }\n",
       "                        break;\n",
       "                    }\n",
       "                }\n",
       "            }, 500);\n",
       "            "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import os\n",
    "import boto3\n",
    "import logging\n",
    "from datetime import datetime\n",
    "\n",
    "boto3.set_stream_logger(name=\"botocore.credentials\", level=logging.WARNING)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 3;\n",
       "                var nbb_unformatted_code = \"import sagemaker\\nfrom sagemaker.transformer import Transformer\";\n",
       "                var nbb_formatted_code = \"import sagemaker\\nfrom sagemaker.transformer import Transformer\";\n",
       "                var nbb_cells = Jupyter.notebook.get_cells();\n",
       "                for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                    if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                        if (nbb_cells[i].get_text() == nbb_unformatted_code) {\n",
       "                             nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                        }\n",
       "                        break;\n",
       "                    }\n",
       "                }\n",
       "            }, 500);\n",
       "            "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import sagemaker\n",
    "from sagemaker.transformer import Transformer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 4;\n",
       "                var nbb_unformatted_code = \"sgmkr_clnt = boto3.client(\\\"sagemaker\\\")\\nsgmkr_rt = boto3.client(\\\"runtime.sagemaker\\\")\";\n",
       "                var nbb_formatted_code = \"sgmkr_clnt = boto3.client(\\\"sagemaker\\\")\\nsgmkr_rt = boto3.client(\\\"runtime.sagemaker\\\")\";\n",
       "                var nbb_cells = Jupyter.notebook.get_cells();\n",
       "                for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                    if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                        if (nbb_cells[i].get_text() == nbb_unformatted_code) {\n",
       "                             nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                        }\n",
       "                        break;\n",
       "                    }\n",
       "                }\n",
       "            }, 500);\n",
       "            "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sgmkr_clnt = boto3.client(\"sagemaker\")\n",
    "sgmkr_rt = boto3.client(\"runtime.sagemaker\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 5;\n",
       "                var nbb_unformatted_code = \"# role_arn = sagemaker.get_execution_role()\\nrole_arn = os.getenv(\\\"SGMKR_ROLE_ARN\\\")\";\n",
       "                var nbb_formatted_code = \"# role_arn = sagemaker.get_execution_role()\\nrole_arn = os.getenv(\\\"SGMKR_ROLE_ARN\\\")\";\n",
       "                var nbb_cells = Jupyter.notebook.get_cells();\n",
       "                for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                    if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                        if (nbb_cells[i].get_text() == nbb_unformatted_code) {\n",
       "                             nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                        }\n",
       "                        break;\n",
       "                    }\n",
       "                }\n",
       "            }, 500);\n",
       "            "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# role_arn = sagemaker.get_execution_role()\n",
    "role_arn = os.getenv(\"SGMKR_ROLE_ARN\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Create model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 6;\n",
       "                var nbb_unformatted_code = \"model_img = '544295431143.dkr.ecr.ap-southeast-2.amazonaws.com/xgboost:latest'\";\n",
       "                var nbb_formatted_code = \"model_img = \\\"544295431143.dkr.ecr.ap-southeast-2.amazonaws.com/xgboost:latest\\\"\";\n",
       "                var nbb_cells = Jupyter.notebook.get_cells();\n",
       "                for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                    if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                        if (nbb_cells[i].get_text() == nbb_unformatted_code) {\n",
       "                             nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                        }\n",
       "                        break;\n",
       "                    }\n",
       "                }\n",
       "            }, 500);\n",
       "            "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "model_img = \"544295431143.dkr.ecr.ap-southeast-2.amazonaws.com/xgboost:latest\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 7;\n",
       "                var nbb_unformatted_code = \"model_path = 's3://sgmkr-course/iris/model/iris-xgboost-2023-02-03-06-03-15/output/model.tar.gz'\";\n",
       "                var nbb_formatted_code = \"model_path = (\\n    \\\"s3://sgmkr-course/iris/model/iris-xgboost-2023-02-03-06-03-15/output/model.tar.gz\\\"\\n)\";\n",
       "                var nbb_cells = Jupyter.notebook.get_cells();\n",
       "                for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                    if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                        if (nbb_cells[i].get_text() == nbb_unformatted_code) {\n",
       "                             nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                        }\n",
       "                        break;\n",
       "                    }\n",
       "                }\n",
       "            }, 500);\n",
       "            "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "model_path = (\n",
    "    \"s3://sgmkr-course/iris/model/iris-xgboost-2023-02-03-06-03-15/output/model.tar.gz\"\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "iris-xgboost-2023-03-22-19-14-35\n"
     ]
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 8;\n",
       "                var nbb_unformatted_code = \"model_name = 'iris-xgboost-' + datetime.today().strftime('%Y-%m-%d-%H-%M-%S')\\nprint(model_name)\";\n",
       "                var nbb_formatted_code = \"model_name = \\\"iris-xgboost-\\\" + datetime.today().strftime(\\\"%Y-%m-%d-%H-%M-%S\\\")\\nprint(model_name)\";\n",
       "                var nbb_cells = Jupyter.notebook.get_cells();\n",
       "                for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                    if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                        if (nbb_cells[i].get_text() == nbb_unformatted_code) {\n",
       "                             nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                        }\n",
       "                        break;\n",
       "                    }\n",
       "                }\n",
       "            }, 500);\n",
       "            "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "model_name = \"iris-xgboost-\" + datetime.today().strftime(\"%Y-%m-%d-%H-%M-%S\")\n",
    "print(model_name)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ModelArn': 'arn:aws:sagemaker:ap-southeast-2:042990164028:model/iris-xgboost-2023-03-22-19-14-35', 'ResponseMetadata': {'RequestId': 'eabdc9b6-c949-4dee-a498-67f728564b77', 'HTTPStatusCode': 200, 'HTTPHeaders': {'x-amzn-requestid': 'eabdc9b6-c949-4dee-a498-67f728564b77', 'content-type': 'application/x-amz-json-1.1', 'content-length': '99', 'date': 'Wed, 22 Mar 2023 08:14:38 GMT'}, 'RetryAttempts': 0}}\n"
     ]
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 9;\n",
       "                var nbb_unformatted_code = \"response = sgmkr_clnt.create_model(\\n    ModelName=model_name,\\n    PrimaryContainer={\\n        'Image': model_img,\\n        'ModelDataUrl': model_path\\n    },\\n    ExecutionRoleArn=role_arn\\n)\\n\\nprint(response)\";\n",
       "                var nbb_formatted_code = \"response = sgmkr_clnt.create_model(\\n    ModelName=model_name,\\n    PrimaryContainer={\\\"Image\\\": model_img, \\\"ModelDataUrl\\\": model_path},\\n    ExecutionRoleArn=role_arn,\\n)\\n\\nprint(response)\";\n",
       "                var nbb_cells = Jupyter.notebook.get_cells();\n",
       "                for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                    if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                        if (nbb_cells[i].get_text() == nbb_unformatted_code) {\n",
       "                             nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                        }\n",
       "                        break;\n",
       "                    }\n",
       "                }\n",
       "            }, 500);\n",
       "            "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "response = sgmkr_clnt.create_model(\n",
    "    ModelName=model_name,\n",
    "    PrimaryContainer={\"Image\": model_img, \"ModelDataUrl\": model_path},\n",
    "    ExecutionRoleArn=role_arn,\n",
    ")\n",
    "\n",
    "print(response)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 10;\n",
       "                var nbb_unformatted_code = \"bucket = 'sgmkr-course'\\nprefix = 'iris'\";\n",
       "                var nbb_formatted_code = \"bucket = \\\"sgmkr-course\\\"\\nprefix = \\\"iris\\\"\";\n",
       "                var nbb_cells = Jupyter.notebook.get_cells();\n",
       "                for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                    if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                        if (nbb_cells[i].get_text() == nbb_unformatted_code) {\n",
       "                             nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                        }\n",
       "                        break;\n",
       "                    }\n",
       "                }\n",
       "            }, 500);\n",
       "            "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "bucket = \"sgmkr-course\"\n",
    "prefix = \"iris\""
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Batch Transform"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 24;\n",
       "                var nbb_unformatted_code = \"batch_ip = 's3://{}/{}/{}'.format(bucket, prefix, 'batch_transform')\\nbatch_op = 's3://{}/{}/{}'.format(bucket, prefix, 'batch_transform')\";\n",
       "                var nbb_formatted_code = \"batch_ip = \\\"s3://{}/{}/{}\\\".format(bucket, prefix, \\\"batch_transform\\\")\\nbatch_op = \\\"s3://{}/{}/{}\\\".format(bucket, prefix, \\\"batch_transform\\\")\";\n",
       "                var nbb_cells = Jupyter.notebook.get_cells();\n",
       "                for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                    if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                        if (nbb_cells[i].get_text() == nbb_unformatted_code) {\n",
       "                             nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                        }\n",
       "                        break;\n",
       "                    }\n",
       "                }\n",
       "            }, 500);\n",
       "            "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "batch_ip = 's3://{}/{}/{}'.format(bucket, prefix, 'batch_transform')\n",
    "batch_op = 's3://{}/{}/{}'.format(bucket, prefix, 'batch_transform')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      ".................................\n",
      "\u001b[34mArguments: serve\u001b[0m\n",
      "\u001b[34m[2023-02-03 09:53:36 +0000] [1] [INFO] Starting gunicorn 19.9.0\u001b[0m\n",
      "\u001b[34m[2023-02-03 09:53:36 +0000] [1] [INFO] Listening at: http://0.0.0.0:8080 (1)\u001b[0m\n",
      "\u001b[34m[2023-02-03 09:53:36 +0000] [1] [INFO] Using worker: gevent\u001b[0m\n",
      "\u001b[34m[2023-02-03 09:53:36 +0000] [21] [INFO] Booting worker with pid: 21\u001b[0m\n",
      "\u001b[34m[2023-02-03 09:53:36 +0000] [22] [INFO] Booting worker with pid: 22\u001b[0m\n",
      "\u001b[34m/opt/amazon/lib/python3.7/site-packages/gunicorn/workers/ggevent.py:65: MonkeyPatchWarning: Monkey-patching ssl after ssl has already been imported may lead to errors, including RecursionError on Python 3.6. It may also silently lead to incorrect behaviour on Python 3.7. Please monkey-patch earlier. See https://github.com/gevent/gevent/issues/1016. Modules that had direct imports (NOT patched): ['urllib3.util.ssl_ (/opt/amazon/lib/python3.7/site-packages/urllib3/util/ssl_.py)', 'urllib3.util (/opt/amazon/lib/python3.7/site-packages/urllib3/util/__init__.py)']. \n",
      "  monkey.patch_all(subprocess=True)\u001b[0m\n",
      "\u001b[34m[2023-02-03 09:53:36 +0000] [23] [INFO] Booting worker with pid: 23\u001b[0m\n",
      "\u001b[34m[2023-02-03:09:53:36:INFO] Model loaded successfully for worker : 21\u001b[0m\n",
      "\u001b[34m/opt/amazon/lib/python3.7/site-packages/gunicorn/workers/ggevent.py:65: MonkeyPatchWarning: Monkey-patching ssl after ssl has already been imported may lead to errors, including RecursionError on Python 3.6. It may also silently lead to incorrect behaviour on Python 3.7. Please monkey-patch earlier. See https://github.com/gevent/gevent/issues/1016. Modules that had direct imports (NOT patched): ['urllib3.util.ssl_ (/opt/amazon/lib/python3.7/site-packages/urllib3/util/ssl_.py)', 'urllib3.util (/opt/amazon/lib/python3.7/site-packages/urllib3/util/__init__.py)']. \n",
      "  monkey.patch_all(subprocess=True)\u001b[0m\n",
      "\u001b[34m[2023-02-03:09:53:36:INFO] Model loaded successfully for worker : 22\u001b[0m\n",
      "\u001b[34m[2023-02-03 09:53:36 +0000] [24] [INFO] Booting worker with pid: 24\u001b[0m\n",
      "\u001b[34m/opt/amazon/lib/python3.7/site-packages/gunicorn/workers/ggevent.py:65: MonkeyPatchWarning: Monkey-patching ssl after ssl has already been imported may lead to errors, including RecursionError on Python 3.6. It may also silently lead to incorrect behaviour on Python 3.7. Please monkey-patch earlier. See https://github.com/gevent/gevent/issues/1016. Modules that had direct imports (NOT patched): ['urllib3.util.ssl_ (/opt/amazon/lib/python3.7/site-packages/urllib3/util/ssl_.py)', 'urllib3.util (/opt/amazon/lib/python3.7/site-packages/urllib3/util/__init__.py)']. \n",
      "  monkey.patch_all(subprocess=True)\u001b[0m\n",
      "\u001b[34m[2023-02-03:09:53:36:INFO] Model loaded successfully for worker : 23\u001b[0m\n",
      "\u001b[34m/opt/amazon/lib/python3.7/site-packages/gunicorn/workers/ggevent.py:65: MonkeyPatchWarning: Monkey-patching ssl after ssl has already been imported may lead to errors, including RecursionError on Python 3.6. It may also silently lead to incorrect behaviour on Python 3.7. Please monkey-patch earlier. See https://github.com/gevent/gevent/issues/1016. Modules that had direct imports (NOT patched): ['urllib3.util.ssl_ (/opt/amazon/lib/python3.7/site-packages/urllib3/util/ssl_.py)', 'urllib3.util (/opt/amazon/lib/python3.7/site-packages/urllib3/util/__init__.py)']. \n",
      "  monkey.patch_all(subprocess=True)\u001b[0m\n",
      "\u001b[34m[2023-02-03:09:53:36:INFO] Model loaded successfully for worker : 24\u001b[0m\n",
      "\u001b[34m[2023-02-03:09:53:40:INFO] Sniff delimiter as '1'\u001b[0m\n",
      "\u001b[34m[2023-02-03:09:53:40:INFO] Determined delimiter of CSV input is ','\u001b[0m\n",
      "\u001b[34m[2023-02-03:09:53:40:ERROR] Feature size of csv inference data 1 is not consistent with feature size of trained model 4\u001b[0m\n",
      "\u001b[34mTraceback (most recent call last):\n",
      "  File \"/opt/amazon/lib/python3.7/site-packages/sage_xgboost/serve.py\", line 274, in invocations\n",
      "    preds = ScoringService.predict(data=dtest, content_type=content_type, model_format=format)\n",
      "  File \"/opt/amazon/lib/python3.7/site-packages/sage_xgboost/serve.py\", line 125, in predict\n",
      "    'with feature size of trained model {}'.format(y, x))\u001b[0m\n",
      "\u001b[34mValueError: Feature size of csv inference data 1 is not consistent with feature size of trained model 4\u001b[0m\n",
      "\u001b[34m[2023-02-03:09:53:40:INFO] Sniff delimiter as ','\u001b[0m\n",
      "\u001b[34m[2023-02-03:09:53:40:INFO] Determined delimiter of CSV input is ','\u001b[0m\n",
      "\u001b[32m2023-02-03T09:53:40.677:[sagemaker logs]: MaxConcurrentTransforms=4, MaxPayloadInMB=6, BatchStrategy=MULTI_RECORD\u001b[0m\n",
      "\u001b[32m2023-02-03T09:53:40.887:[sagemaker logs]: sgmkr-course/iris/batch_transform/iris_infer.csv.out: ClientError: 400\u001b[0m\n",
      "\u001b[32m2023-02-03T09:53:40.887:[sagemaker logs]: sgmkr-course/iris/batch_transform/iris_infer.csv.out: \u001b[0m\n",
      "\u001b[32m2023-02-03T09:53:40.887:[sagemaker logs]: sgmkr-course/iris/batch_transform/iris_infer.csv.out: Message:\u001b[0m\n",
      "\u001b[32m2023-02-03T09:53:40.888:[sagemaker logs]: sgmkr-course/iris/batch_transform/iris_infer.csv.out: Unable to evaluate payload provided: Feature size of csv inference data 1 is not consistent with feature size of trained model 4\u001b[0m\n"
     ]
    },
    {
     "ename": "UnexpectedStatusException",
     "evalue": "Error for Transform job xgboost-2023-02-03-09-48-15-211: Failed. Reason: ClientError: See job logs for more information",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mUnexpectedStatusException\u001b[0m                 Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-28-8ce993580402>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      7\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      8\u001b[0m transformer.transform(\n\u001b[0;32m----> 9\u001b[0;31m     \u001b[0mdata\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mbatch_ip\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdata_type\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"S3Prefix\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcontent_type\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"text/csv\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     10\u001b[0m )\n\u001b[1;32m     11\u001b[0m \u001b[0mtransformer\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwait\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/opt/conda/lib/python3.7/site-packages/sagemaker/workflow/pipeline_context.py\u001b[0m in \u001b[0;36mwrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    270\u001b[0m             \u001b[0;32mreturn\u001b[0m \u001b[0m_StepArguments\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mretrieve_caller_name\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself_instance\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrun_func\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    271\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 272\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0mrun_func\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    273\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    274\u001b[0m     \u001b[0;32mreturn\u001b[0m \u001b[0mwrapper\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/opt/conda/lib/python3.7/site-packages/sagemaker/transformer.py\u001b[0m in \u001b[0;36mtransform\u001b[0;34m(self, data, data_type, content_type, compression_type, split_type, job_name, input_filter, output_filter, join_source, experiment_config, model_client_config, batch_data_capture_config, wait, logs)\u001b[0m\n\u001b[1;32m    268\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    269\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mwait\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 270\u001b[0;31m             \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlatest_transform_job\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwait\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlogs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mlogs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    271\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    272\u001b[0m     def transform_with_monitoring(\n",
      "\u001b[0;32m/opt/conda/lib/python3.7/site-packages/sagemaker/transformer.py\u001b[0m in \u001b[0;36mwait\u001b[0;34m(self, logs)\u001b[0m\n\u001b[1;32m    618\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0mwait\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlogs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    619\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mlogs\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 620\u001b[0;31m             \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msagemaker_session\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlogs_for_transform_job\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mjob_name\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mwait\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    621\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    622\u001b[0m             \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msagemaker_session\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwait_for_transform_job\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mjob_name\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/opt/conda/lib/python3.7/site-packages/sagemaker/session.py\u001b[0m in \u001b[0;36mlogs_for_transform_job\u001b[0;34m(self, job_name, wait, poll)\u001b[0m\n\u001b[1;32m   4240\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   4241\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mwait\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 4242\u001b[0;31m             \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_check_job_status\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mjob_name\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdescription\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"TransformJobStatus\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   4243\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0mdot\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   4244\u001b[0m                 \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/opt/conda/lib/python3.7/site-packages/sagemaker/session.py\u001b[0m in \u001b[0;36m_check_job_status\u001b[0;34m(self, job, desc, status_key_name)\u001b[0m\n\u001b[1;32m   3604\u001b[0m                 \u001b[0mmessage\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mmessage\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   3605\u001b[0m                 \u001b[0mallowed_statuses\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"Completed\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"Stopped\"\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 3606\u001b[0;31m                 \u001b[0mactual_status\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mstatus\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   3607\u001b[0m             )\n\u001b[1;32m   3608\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mUnexpectedStatusException\u001b[0m: Error for Transform job xgboost-2023-02-03-09-48-15-211: Failed. Reason: ClientError: See job logs for more information"
     ]
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 28;\n",
       "                var nbb_unformatted_code = \"transformer = Transformer(\\n    model_name=model_name,\\n    instance_count=1,\\n    instance_type='ml.m4.xlarge',\\n    output_path=batch_op,\\n)\\n\\ntransformer.transform(\\n    data=batch_ip, data_type=\\\"S3Prefix\\\", content_type=\\\"text/csv\\\"\\n)\\ntransformer.wait()\";\n",
       "                var nbb_formatted_code = \"transformer = Transformer(\\n    model_name=model_name,\\n    instance_count=1,\\n    instance_type=\\\"ml.m4.xlarge\\\",\\n    output_path=batch_op,\\n)\\n\\ntransformer.transform(data=batch_ip, data_type=\\\"S3Prefix\\\", content_type=\\\"text/csv\\\")\\ntransformer.wait()\";\n",
       "                var nbb_cells = Jupyter.notebook.get_cells();\n",
       "                for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                    if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                        if (nbb_cells[i].get_text() == nbb_unformatted_code) {\n",
       "                             nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                        }\n",
       "                        break;\n",
       "                    }\n",
       "                }\n",
       "            }, 500);\n",
       "            "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "transformer = Transformer(\n",
    "    model_name=model_name,\n",
    "    instance_count=1,\n",
    "    instance_type='ml.m4.xlarge',\n",
    "    output_path=batch_op,\n",
    ")\n",
    "\n",
    "transformer.transform(\n",
    "    data=batch_ip, data_type=\"S3Prefix\", content_type=\"text/csv\"\n",
    ")\n",
    "transformer.wait()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Endpoint"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "tmp-ep-config-2023-03-22-19-15-04-118177\n"
     ]
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 11;\n",
       "                var nbb_unformatted_code = \"ep_config_name = 'tmp-ep-config-' + datetime.today().strftime(\\\"%Y-%m-%d-%H-%M-%S-%f\\\")\\nprint(ep_config_name)\";\n",
       "                var nbb_formatted_code = \"ep_config_name = \\\"tmp-ep-config-\\\" + datetime.today().strftime(\\\"%Y-%m-%d-%H-%M-%S-%f\\\")\\nprint(ep_config_name)\";\n",
       "                var nbb_cells = Jupyter.notebook.get_cells();\n",
       "                for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                    if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                        if (nbb_cells[i].get_text() == nbb_unformatted_code) {\n",
       "                             nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                        }\n",
       "                        break;\n",
       "                    }\n",
       "                }\n",
       "            }, 500);\n",
       "            "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "ep_config_name = \"tmp-ep-config-\" + datetime.today().strftime(\"%Y-%m-%d-%H-%M-%S-%f\")\n",
    "print(ep_config_name)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'EndpointConfigArn': 'arn:aws:sagemaker:ap-southeast-2:042990164028:endpoint-config/tmp-ep-config-2023-03-22-19-15-04-118177', 'ResponseMetadata': {'RequestId': '4d2e8005-d4fb-45d1-9113-f57bc6157274', 'HTTPStatusCode': 200, 'HTTPHeaders': {'x-amzn-requestid': '4d2e8005-d4fb-45d1-9113-f57bc6157274', 'content-type': 'application/x-amz-json-1.1', 'content-length': '126', 'date': 'Wed, 22 Mar 2023 08:15:04 GMT'}, 'RetryAttempts': 0}}\n"
     ]
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 12;\n",
       "                var nbb_unformatted_code = \"response = sgmkr_clnt.create_endpoint_config(\\n    EndpointConfigName = ep_config_name,\\n    ProductionVariants = [\\n        {\\n            'VariantName': 'version-1',\\n            'ModelName': model_name,\\n            'InitialInstanceCount': 1,\\n            'InstanceType': 'ml.m4.xlarge',\\n            #sever_less = ''\\n        },\\n    ]\\n)\\n\\nprint(response)\";\n",
       "                var nbb_formatted_code = \"response = sgmkr_clnt.create_endpoint_config(\\n    EndpointConfigName=ep_config_name,\\n    ProductionVariants=[\\n        {\\n            \\\"VariantName\\\": \\\"version-1\\\",\\n            \\\"ModelName\\\": model_name,\\n            \\\"InitialInstanceCount\\\": 1,\\n            \\\"InstanceType\\\": \\\"ml.m4.xlarge\\\",\\n            # sever_less = ''\\n        },\\n    ],\\n)\\n\\nprint(response)\";\n",
       "                var nbb_cells = Jupyter.notebook.get_cells();\n",
       "                for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                    if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                        if (nbb_cells[i].get_text() == nbb_unformatted_code) {\n",
       "                             nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                        }\n",
       "                        break;\n",
       "                    }\n",
       "                }\n",
       "            }, 500);\n",
       "            "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "response = sgmkr_clnt.create_endpoint_config(\n",
    "    EndpointConfigName=ep_config_name,\n",
    "    ProductionVariants=[\n",
    "        {\n",
    "            \"VariantName\": \"version-1\",\n",
    "            \"ModelName\": model_name,\n",
    "            \"InitialInstanceCount\": 1,\n",
    "            \"InstanceType\": \"ml.m4.xlarge\",\n",
    "            # sever_less = ''\n",
    "        },\n",
    "    ],\n",
    ")\n",
    "\n",
    "print(response)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "tmp-ep-2023-03-22-19-15-06-049247\n"
     ]
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 13;\n",
       "                var nbb_unformatted_code = \"ep_name = 'tmp-ep-' + datetime.today().strftime(\\\"%Y-%m-%d-%H-%M-%S-%f\\\")\\nprint(ep_name)\";\n",
       "                var nbb_formatted_code = \"ep_name = \\\"tmp-ep-\\\" + datetime.today().strftime(\\\"%Y-%m-%d-%H-%M-%S-%f\\\")\\nprint(ep_name)\";\n",
       "                var nbb_cells = Jupyter.notebook.get_cells();\n",
       "                for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                    if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                        if (nbb_cells[i].get_text() == nbb_unformatted_code) {\n",
       "                             nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                        }\n",
       "                        break;\n",
       "                    }\n",
       "                }\n",
       "            }, 500);\n",
       "            "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "ep_name = \"tmp-ep-\" + datetime.today().strftime(\"%Y-%m-%d-%H-%M-%S-%f\")\n",
    "print(ep_name)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'EndpointArn': 'arn:aws:sagemaker:ap-southeast-2:042990164028:endpoint/tmp-ep-2023-03-22-19-15-06-049247', 'ResponseMetadata': {'RequestId': '5414cf48-20bf-45c1-9c6a-7a907267fe4f', 'HTTPStatusCode': 200, 'HTTPHeaders': {'x-amzn-requestid': '5414cf48-20bf-45c1-9c6a-7a907267fe4f', 'content-type': 'application/x-amz-json-1.1', 'content-length': '106', 'date': 'Wed, 22 Mar 2023 08:15:06 GMT'}, 'RetryAttempts': 0}}\n"
     ]
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 14;\n",
       "                var nbb_unformatted_code = \"response = sgmkr_clnt.create_endpoint(\\n    EndpointName = ep_name,\\n    EndpointConfigName = ep_config_name,\\n)\\nprint(response)\";\n",
       "                var nbb_formatted_code = \"response = sgmkr_clnt.create_endpoint(\\n    EndpointName=ep_name, EndpointConfigName=ep_config_name,\\n)\\nprint(response)\";\n",
       "                var nbb_cells = Jupyter.notebook.get_cells();\n",
       "                for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                    if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                        if (nbb_cells[i].get_text() == nbb_unformatted_code) {\n",
       "                             nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                        }\n",
       "                        break;\n",
       "                    }\n",
       "                }\n",
       "            }, 500);\n",
       "            "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "response = sgmkr_clnt.create_endpoint(\n",
    "    EndpointName=ep_name, EndpointConfigName=ep_config_name,\n",
    ")\n",
    "print(response)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Endpoint created\n"
     ]
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 15;\n",
       "                var nbb_unformatted_code = \"waiter = sgmkr_clnt.get_waiter('endpoint_in_service')\\nwaiter.wait(EndpointName = ep_name, WaiterConfig = {'Delay': 123, 'MaxAttempts': 123})\\nprint(\\\"Endpoint created\\\")\";\n",
       "                var nbb_formatted_code = \"waiter = sgmkr_clnt.get_waiter(\\\"endpoint_in_service\\\")\\nwaiter.wait(EndpointName=ep_name, WaiterConfig={\\\"Delay\\\": 123, \\\"MaxAttempts\\\": 123})\\nprint(\\\"Endpoint created\\\")\";\n",
       "                var nbb_cells = Jupyter.notebook.get_cells();\n",
       "                for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                    if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                        if (nbb_cells[i].get_text() == nbb_unformatted_code) {\n",
       "                             nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                        }\n",
       "                        break;\n",
       "                    }\n",
       "                }\n",
       "            }, 500);\n",
       "            "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "waiter = sgmkr_clnt.get_waiter(\"endpoint_in_service\")\n",
    "waiter.wait(EndpointName=ep_name, WaiterConfig={\"Delay\": 123, \"MaxAttempts\": 123})\n",
    "print(\"Endpoint created\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 16;\n",
       "                var nbb_unformatted_code = \"payload = '7.7, 3.0, 6.1, 2.3'\\n#payload = '7.7, 3.0, 6.1, 2.3 \\\\n 7.9, 3.8, 6.4, 2.1'\";\n",
       "                var nbb_formatted_code = \"payload = \\\"7.7, 3.0, 6.1, 2.3\\\"\\n# payload = '7.7, 3.0, 6.1, 2.3 \\\\n 7.9, 3.8, 6.4, 2.1'\";\n",
       "                var nbb_cells = Jupyter.notebook.get_cells();\n",
       "                for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                    if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                        if (nbb_cells[i].get_text() == nbb_unformatted_code) {\n",
       "                             nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                        }\n",
       "                        break;\n",
       "                    }\n",
       "                }\n",
       "            }, 500);\n",
       "            "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "payload = \"7.7, 3.0, 6.1, 2.3\"\n",
    "# payload = '7.7, 3.0, 6.1, 2.3 \\n 7.9, 3.8, 6.4, 2.1'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 20;\n",
       "                var nbb_unformatted_code = \"sgmkr_runt = boto3.client(\\\"runtime.sagemaker\\\")\";\n",
       "                var nbb_formatted_code = \"sgmkr_runt = boto3.client(\\\"runtime.sagemaker\\\")\";\n",
       "                var nbb_cells = Jupyter.notebook.get_cells();\n",
       "                for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                    if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                        if (nbb_cells[i].get_text() == nbb_unformatted_code) {\n",
       "                             nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                        }\n",
       "                        break;\n",
       "                    }\n",
       "                }\n",
       "            }, 500);\n",
       "            "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sgmkr_runt = boto3.client(\"runtime.sagemaker\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2.0\n"
     ]
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 22;\n",
       "                var nbb_unformatted_code = \"response = sgmkr_runt.invoke_endpoint(\\n    EndpointName=ep_name, ContentType=\\\"text/csv\\\", Body=payload,\\n)\\n\\nprediction = response[\\\"Body\\\"].read().decode()\\nprint(prediction)\";\n",
       "                var nbb_formatted_code = \"response = sgmkr_runt.invoke_endpoint(\\n    EndpointName=ep_name, ContentType=\\\"text/csv\\\", Body=payload,\\n)\\n\\nprediction = response[\\\"Body\\\"].read().decode()\\nprint(prediction)\";\n",
       "                var nbb_cells = Jupyter.notebook.get_cells();\n",
       "                for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                    if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                        if (nbb_cells[i].get_text() == nbb_unformatted_code) {\n",
       "                             nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                        }\n",
       "                        break;\n",
       "                    }\n",
       "                }\n",
       "            }, 500);\n",
       "            "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "response = sgmkr_runt.invoke_endpoint(\n",
    "    EndpointName=ep_name, ContentType=\"text/csv\", Body=payload,\n",
    ")\n",
    "\n",
    "prediction = response[\"Body\"].read().decode()\n",
    "print(prediction)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(\"Deleting sagemaker endpoint\")\n",
    "response = sgmkr_clnt.delete_endpoint(EndpointName = endpoint_name)  \n",
    "print(\"Deleted sagemaker endpoint\")\n",
    "#print(response)    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(\"Deleting sagemaker endpoint configuration\")\n",
    "response = sgmkr_clnt.delete_endpoint_config(EndpointConfigName = endpoint_config_name)\n",
    "print(\"Deleted sagemaker endpoint configuration\")\n",
    "#print(response)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.8.13"
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": false,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {},
   "toc_section_display": true,
   "toc_window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}