003_Deploy_Infer_101_1.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 25;\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": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 26;\n",
       "                var nbb_unformatted_code = \"import os\\nimport io\\nfrom datetime import datetime\\nimport logging\";\n",
       "                var nbb_formatted_code = \"import os\\nimport io\\nfrom datetime import datetime\\nimport logging\";\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 io\n",
    "from datetime import datetime\n",
    "import logging"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 27;\n",
       "                var nbb_unformatted_code = \"import boto3\\nimport sagemaker\\nfrom sagemaker.session import TrainingInput\\nfrom sagemaker import image_uris\\nfrom sagemaker import hyperparameters\";\n",
       "                var nbb_formatted_code = \"import boto3\\nimport sagemaker\\nfrom sagemaker.session import TrainingInput\\nfrom sagemaker import image_uris\\nfrom sagemaker import hyperparameters\";\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 boto3\n",
    "import sagemaker\n",
    "from sagemaker.session import TrainingInput\n",
    "from sagemaker import image_uris\n",
    "from sagemaker import hyperparameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 28;\n",
       "                var nbb_unformatted_code = \"boto3.set_stream_logger(name=\\\"botocore.credentials\\\", level=logging.WARNING)\";\n",
       "                var nbb_formatted_code = \"boto3.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": [
    "boto3.set_stream_logger(name=\"botocore.credentials\", level=logging.WARNING)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "ap-southeast-2\n"
     ]
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 29;\n",
       "                var nbb_unformatted_code = \"region = sagemaker.Session().boto_region_name\\nprint(region)\";\n",
       "                var nbb_formatted_code = \"region = sagemaker.Session().boto_region_name\\nprint(region)\";\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": [
    "region = sagemaker.Session().boto_region_name\n",
    "print(region)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 30;\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": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 31;\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": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                           PRE batch_transform/\r\n",
      "                           PRE data/\r\n",
      "                           PRE model/\r\n",
      "2023-02-03 13:15:44          0 \r\n"
     ]
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 32;\n",
       "                var nbb_unformatted_code = \"!aws s3 ls {bucket}/{prefix}/\";\n",
       "                var nbb_formatted_code = \"!aws s3 ls {bucket}/{prefix}/\";\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": [
    "!aws s3 ls {bucket}/{prefix}/"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2023-02-03 13:16:32          0 iris/data/\n",
      "2023-03-16 18:09:28        900 iris/data/iris_test.csv\n",
      "2023-03-16 18:09:27       1800 iris/data/iris_train.csv\n"
     ]
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 33;\n",
       "                var nbb_unformatted_code = \"!aws s3 ls {bucket}/{prefix}/data/ --recursive\";\n",
       "                var nbb_formatted_code = \"!aws s3 ls {bucket}/{prefix}/data/ --recursive\";\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": [
    "!aws s3 ls {bucket}/{prefix}/data/ --recursive"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 34;\n",
       "                var nbb_unformatted_code = \"train_file = \\\"data/iris_train.csv\\\"\\nvalid_file = \\\"data/iris_test.csv\\\"\";\n",
       "                var nbb_formatted_code = \"train_file = \\\"data/iris_train.csv\\\"\\nvalid_file = \\\"data/iris_test.csv\\\"\";\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": [
    "train_file = \"data/iris_train.csv\"\n",
    "valid_file = \"data/iris_test.csv\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 35;\n",
       "                var nbb_unformatted_code = \"train_ip = TrainingInput(\\n    \\\"s3://{}/{}/{}\\\".format(bucket, prefix, train_file), content_type=\\\"csv\\\"\\n)\\nvalid_ip = TrainingInput(\\n    \\\"s3://{}/{}/{}\\\".format(bucket, prefix, valid_file), content_type=\\\"csv\\\"\\n)\";\n",
       "                var nbb_formatted_code = \"train_ip = TrainingInput(\\n    \\\"s3://{}/{}/{}\\\".format(bucket, prefix, train_file), content_type=\\\"csv\\\"\\n)\\nvalid_ip = TrainingInput(\\n    \\\"s3://{}/{}/{}\\\".format(bucket, prefix, valid_file), content_type=\\\"csv\\\"\\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": [
    "train_ip = TrainingInput(\n",
    "    \"s3://{}/{}/{}\".format(bucket, prefix, train_file), content_type=\"csv\"\n",
    ")\n",
    "valid_ip = TrainingInput(\n",
    "    \"s3://{}/{}/{}\".format(bucket, prefix, valid_file), content_type=\"csv\"\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 36;\n",
       "                var nbb_unformatted_code = \"model_op = \\\"s3://{}/{}/{}\\\".format(bucket, prefix, \\\"model\\\")\";\n",
       "                var nbb_formatted_code = \"model_op = \\\"s3://{}/{}/{}\\\".format(bucket, prefix, \\\"model\\\")\";\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_op = \"s3://{}/{}/{}\".format(bucket, prefix, \"model\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Ignoring unnecessary instance type: None.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "544295431143.dkr.ecr.ap-southeast-2.amazonaws.com/xgboost:latest\n"
     ]
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 37;\n",
       "                var nbb_unformatted_code = \"train_image_uri = sagemaker.image_uris.retrieve(\\\"xgboost\\\", region, \\\"latest\\\")\\nprint(train_image_uri)\";\n",
       "                var nbb_formatted_code = \"train_image_uri = sagemaker.image_uris.retrieve(\\\"xgboost\\\", region, \\\"latest\\\")\\nprint(train_image_uri)\";\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": [
    "train_image_uri = sagemaker.image_uris.retrieve(\"xgboost\", region, \"latest\")\n",
    "print(train_image_uri)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 38;\n",
       "                var nbb_unformatted_code = \"base_job_name = \\\"iris-xgboost\\\"\";\n",
       "                var nbb_formatted_code = \"base_job_name = \\\"iris-xgboost\\\"\";\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": [
    "base_job_name = \"iris-xgboost\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 41;\n",
       "                var nbb_unformatted_code = \"xgb_estimator = sagemaker.estimator.Estimator(\\n    image_uri=train_image_uri,\\n    role=role_arn,\\n    base_job_name=base_job_name,\\n    instance_count=1,\\n    instance_type=\\\"ml.m4.xlarge\\\",\\n    volume_size=5,\\n    output_path=model_op,\\n    sagemaker_session=sagemaker.Session(),\\n)\";\n",
       "                var nbb_formatted_code = \"xgb_estimator = sagemaker.estimator.Estimator(\\n    image_uri=train_image_uri,\\n    role=role_arn,\\n    base_job_name=base_job_name,\\n    instance_count=1,\\n    instance_type=\\\"ml.m4.xlarge\\\",\\n    volume_size=5,\\n    output_path=model_op,\\n    sagemaker_session=sagemaker.Session(),\\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": [
    "xgb_estimator = sagemaker.estimator.Estimator(\n",
    "    image_uri=train_image_uri,\n",
    "    role=role_arn,\n",
    "    base_job_name=base_job_name,\n",
    "    instance_count=1,\n",
    "    instance_type=\"ml.m4.xlarge\",\n",
    "    volume_size=5,\n",
    "    output_path=model_op,\n",
    "    sagemaker_session=sagemaker.Session(),\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 42;\n",
       "                var nbb_unformatted_code = \"xgb_estimator.set_hyperparameters(\\n    num_class=3, max_depth=5, num_round=10, objective=\\\"multi:softmax\\\",\\n)\";\n",
       "                var nbb_formatted_code = \"xgb_estimator.set_hyperparameters(\\n    num_class=3, max_depth=5, num_round=10, objective=\\\"multi:softmax\\\",\\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": [
    "xgb_estimator.set_hyperparameters(\n",
    "    num_class=3, max_depth=5, num_round=10, objective=\"multi:softmax\",\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 43;\n",
       "                var nbb_unformatted_code = \"xgb_estimator.set_hyperparameters(\\n    num_class=3,\\n    max_depth=5,\\n    eta=0.2,\\n    gamma=4,\\n    min_child_weight=6,\\n    subsample=0.7,\\n    objective=\\\"multi:softmax\\\",\\n    num_round=10,\\n)\";\n",
       "                var nbb_formatted_code = \"xgb_estimator.set_hyperparameters(\\n    num_class=3,\\n    max_depth=5,\\n    eta=0.2,\\n    gamma=4,\\n    min_child_weight=6,\\n    subsample=0.7,\\n    objective=\\\"multi:softmax\\\",\\n    num_round=10,\\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": [
    "# xgb_estimator.set_hyperparameters(\n",
    "#     num_class=3,\n",
    "#     max_depth=5,\n",
    "#     eta=0.2,\n",
    "#     gamma=4,\n",
    "#     min_child_weight=6,\n",
    "#     subsample=0.7,\n",
    "#     objective=\"multi:softmax\",\n",
    "#     num_round=10,\n",
    "# )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "iris-xgboost-2023-03-22-19-04-50\n"
     ]
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 47;\n",
       "                var nbb_unformatted_code = \"job_name = \\\"iris-xgboost-\\\" + datetime.today().strftime(\\\"%Y-%m-%d-%H-%M-%S\\\")\\nprint(job_name)\";\n",
       "                var nbb_formatted_code = \"job_name = \\\"iris-xgboost-\\\" + datetime.today().strftime(\\\"%Y-%m-%d-%H-%M-%S\\\")\\nprint(job_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": [
    "job_name = \"iris-xgboost-\" + datetime.today().strftime(\"%Y-%m-%d-%H-%M-%S\")\n",
    "print(job_name)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Creating training-job with name: iris-xgboost-2023-03-22-19-04-50\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2023-03-22 08:04:51 Starting - Starting the training job...\n",
      "2023-03-22 08:05:16 Starting - Preparing the instances for training......\n",
      "2023-03-22 08:06:23 Downloading - Downloading input data...\n",
      "2023-03-22 08:06:53 Training - Downloading the training image...\n",
      "2023-03-22 08:07:24 Training - Training image download completed. Training in progress...\u001b[34mArguments: train\u001b[0m\n",
      "\u001b[34m[2023-03-22:08:07:38:INFO] Running standalone xgboost training.\u001b[0m\n",
      "\u001b[34m[2023-03-22:08:07:38:INFO] File size need to be processed in the node: 0.0mb. Available memory size in the node: 8597.44mb\u001b[0m\n",
      "\u001b[34m[2023-03-22:08:07:38:INFO] Determined delimiter of CSV input is ','\u001b[0m\n",
      "\u001b[34m[08:07:38] S3DistributionType set as FullyReplicated\u001b[0m\n",
      "\u001b[34m[08:07:38] 100x4 matrix with 400 entries loaded from /opt/ml/input/data/train?format=csv&label_column=0&delimiter=,\u001b[0m\n",
      "\u001b[34m[2023-03-22:08:07:38:INFO] Determined delimiter of CSV input is ','\u001b[0m\n",
      "\u001b[34m[08:07:38] S3DistributionType set as FullyReplicated\u001b[0m\n",
      "\u001b[34m[08:07:38] 50x4 matrix with 200 entries loaded from /opt/ml/input/data/validation?format=csv&label_column=0&delimiter=,\u001b[0m\n",
      "\u001b[34m[08:07:38] src/tree/updater_prune.cc:74: tree pruning end, 1 roots, 2 extra nodes, 0 pruned nodes, max_depth=1\u001b[0m\n",
      "\u001b[34m[08:07:38] src/tree/updater_prune.cc:74: tree pruning end, 1 roots, 4 extra nodes, 0 pruned nodes, max_depth=2\u001b[0m\n",
      "\u001b[34m[08:07:38] src/tree/updater_prune.cc:74: tree pruning end, 1 roots, 2 extra nodes, 0 pruned nodes, max_depth=1\u001b[0m\n",
      "\u001b[34m[0]#011train-merror:0.03#011validation-merror:0.06\u001b[0m\n",
      "\u001b[34m[08:07:38] src/tree/updater_prune.cc:74: tree pruning end, 1 roots, 2 extra nodes, 0 pruned nodes, max_depth=1\u001b[0m\n",
      "\u001b[34m[08:07:38] src/tree/updater_prune.cc:74: tree pruning end, 1 roots, 4 extra nodes, 0 pruned nodes, max_depth=2\u001b[0m\n",
      "\u001b[34m[08:07:38] src/tree/updater_prune.cc:74: tree pruning end, 1 roots, 2 extra nodes, 0 pruned nodes, max_depth=1\u001b[0m\n",
      "\u001b[34m[1]#011train-merror:0.03#011validation-merror:0.06\u001b[0m\n",
      "\u001b[34m[08:07:38] src/tree/updater_prune.cc:74: tree pruning end, 1 roots, 2 extra nodes, 0 pruned nodes, max_depth=1\u001b[0m\n",
      "\u001b[34m[08:07:38] src/tree/updater_prune.cc:74: tree pruning end, 1 roots, 2 extra nodes, 4 pruned nodes, max_depth=1\u001b[0m\n",
      "\u001b[34m[08:07:38] src/tree/updater_prune.cc:74: tree pruning end, 1 roots, 2 extra nodes, 0 pruned nodes, max_depth=1\u001b[0m\n",
      "\u001b[34m[2]#011train-merror:0.03#011validation-merror:0.08\u001b[0m\n",
      "\u001b[34m[08:07:38] src/tree/updater_prune.cc:74: tree pruning end, 1 roots, 2 extra nodes, 0 pruned nodes, max_depth=1\u001b[0m\n",
      "\u001b[34m[08:07:38] src/tree/updater_prune.cc:74: tree pruning end, 1 roots, 4 extra nodes, 0 pruned nodes, max_depth=2\u001b[0m\n",
      "\u001b[34m[08:07:38] src/tree/updater_prune.cc:74: tree pruning end, 1 roots, 2 extra nodes, 0 pruned nodes, max_depth=1\u001b[0m\n",
      "\u001b[34m[3]#011train-merror:0.03#011validation-merror:0.08\u001b[0m\n",
      "\u001b[34m[08:07:38] src/tree/updater_prune.cc:74: tree pruning end, 1 roots, 2 extra nodes, 0 pruned nodes, max_depth=1\u001b[0m\n",
      "\u001b[34m[08:07:38] src/tree/updater_prune.cc:74: tree pruning end, 1 roots, 4 extra nodes, 0 pruned nodes, max_depth=2\u001b[0m\n",
      "\u001b[34m[08:07:38] src/tree/updater_prune.cc:74: tree pruning end, 1 roots, 2 extra nodes, 0 pruned nodes, max_depth=1\u001b[0m\n",
      "\u001b[34m[4]#011train-merror:0.03#011validation-merror:0.06\u001b[0m\n",
      "\u001b[34m[08:07:38] src/tree/updater_prune.cc:74: tree pruning end, 1 roots, 2 extra nodes, 0 pruned nodes, max_depth=1\u001b[0m\n",
      "\u001b[34m[08:07:38] src/tree/updater_prune.cc:74: tree pruning end, 1 roots, 4 extra nodes, 0 pruned nodes, max_depth=2\u001b[0m\n",
      "\u001b[34m[08:07:38] src/tree/updater_prune.cc:74: tree pruning end, 1 roots, 2 extra nodes, 0 pruned nodes, max_depth=1\u001b[0m\n",
      "\u001b[34m[5]#011train-merror:0.03#011validation-merror:0.06\u001b[0m\n",
      "\u001b[34m[08:07:38] src/tree/updater_prune.cc:74: tree pruning end, 1 roots, 2 extra nodes, 0 pruned nodes, max_depth=1\u001b[0m\n",
      "\u001b[34m[08:07:38] src/tree/updater_prune.cc:74: tree pruning end, 1 roots, 0 extra nodes, 4 pruned nodes, max_depth=0\u001b[0m\n",
      "\u001b[34m[08:07:38] src/tree/updater_prune.cc:74: tree pruning end, 1 roots, 2 extra nodes, 0 pruned nodes, max_depth=1\u001b[0m\n",
      "\u001b[34m[6]#011train-merror:0.03#011validation-merror:0.08\u001b[0m\n",
      "\u001b[34m[08:07:38] src/tree/updater_prune.cc:74: tree pruning end, 1 roots, 2 extra nodes, 0 pruned nodes, max_depth=1\u001b[0m\n",
      "\u001b[34m[08:07:38] src/tree/updater_prune.cc:74: tree pruning end, 1 roots, 0 extra nodes, 2 pruned nodes, max_depth=0\u001b[0m\n",
      "\u001b[34m[08:07:38] src/tree/updater_prune.cc:74: tree pruning end, 1 roots, 2 extra nodes, 0 pruned nodes, max_depth=1\u001b[0m\n",
      "\u001b[34m[7]#011train-merror:0.03#011validation-merror:0.08\u001b[0m\n",
      "\u001b[34m[08:07:38] src/tree/updater_prune.cc:74: tree pruning end, 1 roots, 2 extra nodes, 0 pruned nodes, max_depth=1\u001b[0m\n",
      "\u001b[34m[08:07:38] src/tree/updater_prune.cc:74: tree pruning end, 1 roots, 0 extra nodes, 4 pruned nodes, max_depth=0\u001b[0m\n",
      "\u001b[34m[08:07:38] src/tree/updater_prune.cc:74: tree pruning end, 1 roots, 2 extra nodes, 0 pruned nodes, max_depth=1\u001b[0m\n",
      "\u001b[34m[8]#011train-merror:0.03#011validation-merror:0.08\u001b[0m\n",
      "\u001b[34m[08:07:38] src/tree/updater_prune.cc:74: tree pruning end, 1 roots, 0 extra nodes, 2 pruned nodes, max_depth=0\u001b[0m\n",
      "\u001b[34m[08:07:38] src/tree/updater_prune.cc:74: tree pruning end, 1 roots, 0 extra nodes, 2 pruned nodes, max_depth=0\u001b[0m\n",
      "\u001b[34m[08:07:38] src/tree/updater_prune.cc:74: tree pruning end, 1 roots, 2 extra nodes, 0 pruned nodes, max_depth=1\u001b[0m\n",
      "\u001b[34m[9]#011train-merror:0.02#011validation-merror:0.04\u001b[0m\n",
      "\n",
      "2023-03-22 08:07:55 Uploading - Uploading generated training model\n",
      "2023-03-22 08:07:55 Completed - Training job completed\n",
      "Training seconds: 92\n",
      "Billable seconds: 92\n"
     ]
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 48;\n",
       "                var nbb_unformatted_code = \"xgb_estimator.fit(\\n    {\\\"train\\\": train_ip, \\\"validation\\\": valid_ip}, wait=True, job_name=job_name\\n)\";\n",
       "                var nbb_formatted_code = \"xgb_estimator.fit(\\n    {\\\"train\\\": train_ip, \\\"validation\\\": valid_ip}, wait=True, job_name=job_name\\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": [
    "xgb_estimator.fit(\n",
    "    {\"train\": train_ip, \"validation\": valid_ip}, wait=True, job_name=job_name\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                           PRE iris-xgboost-2023-03-22-18-12-49/\r\n",
      "                           PRE iris-xgboost-2023-03-22-18-58-53/\r\n",
      "                           PRE iris-xgboost-2023-03-22-19-04-50/\r\n",
      "                           PRE iris-xgboost2023-03-22-18-09-35/\r\n"
     ]
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 72;\n",
       "                var nbb_unformatted_code = \"!aws s3 ls {bucket}/{prefix}/model/\";\n",
       "                var nbb_formatted_code = \"!aws s3 ls {bucket}/{prefix}/model/\";\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": [
    "!aws s3 ls {bucket}/{prefix}/model/"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Inference "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 50;\n",
       "                var nbb_unformatted_code = \"from sagemaker.serializers import CSVSerializer\";\n",
       "                var nbb_formatted_code = \"from sagemaker.serializers import CSVSerializer\";\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": [
    "from sagemaker.serializers import CSVSerializer"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Deploy the model as an endpoint"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "sagemaker.estimator.Estimator"
      ]
     },
     "execution_count": 51,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 51;\n",
       "                var nbb_unformatted_code = \"type(xgb_estimator)\";\n",
       "                var nbb_formatted_code = \"type(xgb_estimator)\";\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": [
    "type(xgb_estimator)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Creating model with name: iris-xgboost-2023-03-22-08-09-03-677\n",
      "Creating endpoint-config with name iris-xgboost-2023-03-22-08-09-03-677\n",
      "Creating endpoint with name iris-xgboost-2023-03-22-08-09-03-677\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "------------!"
     ]
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 52;\n",
       "                var nbb_unformatted_code = \"xgb_predictor = xgb_estimator.deploy(\\n    initial_instance_count=1, instance_type=\\\"ml.t2.medium\\\", serializer=CSVSerializer()\\n)\";\n",
       "                var nbb_formatted_code = \"xgb_predictor = xgb_estimator.deploy(\\n    initial_instance_count=1, instance_type=\\\"ml.t2.medium\\\", serializer=CSVSerializer()\\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": [
    "xgb_predictor = xgb_estimator.deploy(\n",
    "    initial_instance_count=1, instance_type=\"ml.t2.medium\", serializer=CSVSerializer()\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Predictor single record"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "b'2.0'"
      ]
     },
     "execution_count": 53,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 53;\n",
       "                var nbb_unformatted_code = \"xgb_predictor.predict(\\\"7.7, 3.0, 6.1, 2.3\\\")\";\n",
       "                var nbb_formatted_code = \"xgb_predictor.predict(\\\"7.7, 3.0, 6.1, 2.3\\\")\";\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": [
    "xgb_predictor.predict(\"7.7, 3.0, 6.1, 2.3\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Endpoint"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "iris-xgboost-2023-03-22-08-09-03-677\n"
     ]
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 54;\n",
       "                var nbb_unformatted_code = \"endpoint_name = xgb_predictor.endpoint_name\\nprint(endpoint_name)\";\n",
       "                var nbb_formatted_code = \"endpoint_name = xgb_predictor.endpoint_name\\nprint(endpoint_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": [
    "endpoint_name = xgb_predictor.endpoint_name\n",
    "print(endpoint_name)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 55;\n",
       "                var nbb_unformatted_code = \"sgmkr_runtime = boto3.client(\\\"runtime.sagemaker\\\")\";\n",
       "                var nbb_formatted_code = \"sgmkr_runtime = 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_runtime = boto3.client(\"runtime.sagemaker\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Endpoint - One record"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ResponseMetadata': {'RequestId': '7a8b2061-5659-4e0a-b335-dceab7d92266', 'HTTPStatusCode': 200, 'HTTPHeaders': {'x-amzn-requestid': '7a8b2061-5659-4e0a-b335-dceab7d92266', 'x-amzn-invoked-production-variant': 'AllTraffic', 'date': 'Wed, 22 Mar 2023 08:15:38 GMT', 'content-type': 'text/csv; charset=utf-8', 'content-length': '3'}, 'RetryAttempts': 0}, 'ContentType': 'text/csv; charset=utf-8', 'InvokedProductionVariant': 'AllTraffic', 'Body': <botocore.response.StreamingBody object at 0x7fd8c818fa90>}\n"
     ]
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 56;\n",
       "                var nbb_unformatted_code = \"payload_csv_text = \\\"7.7, 3.0, 6.1, 2.3\\\"\\nresponse = sgmkr_runtime.invoke_endpoint(\\n    EndpointName=endpoint_name, ContentType=\\\"text/csv\\\", Body=payload_csv_text\\n)\\nprint(response)\";\n",
       "                var nbb_formatted_code = \"payload_csv_text = \\\"7.7, 3.0, 6.1, 2.3\\\"\\nresponse = sgmkr_runtime.invoke_endpoint(\\n    EndpointName=endpoint_name, ContentType=\\\"text/csv\\\", Body=payload_csv_text\\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": [
    "payload_csv_text = \"7.7, 3.0, 6.1, 2.3\"\n",
    "response = sgmkr_runtime.invoke_endpoint(\n",
    "    EndpointName=endpoint_name, ContentType=\"text/csv\", Body=payload_csv_text\n",
    ")\n",
    "print(response)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2.0\n"
     ]
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 57;\n",
       "                var nbb_unformatted_code = \"print(response[\\\"Body\\\"].read().decode())\";\n",
       "                var nbb_formatted_code = \"print(response[\\\"Body\\\"].read().decode())\";\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": [
    "print(response[\"Body\"].read().decode())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Endpoint - Multiple records"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2.0,2.0\n"
     ]
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 58;\n",
       "                var nbb_unformatted_code = \"payload_csv_text = \\\"7.7, 3.0, 6.1, 2.3 \\\\n 7.9, 3.8, 6.4, 2.1\\\"\\n\\nresponse = sgmkr_runtime.invoke_endpoint(\\n    EndpointName=endpoint_name, ContentType=\\\"text/csv\\\", Body=payload_csv_text\\n)\\nprint(response[\\\"Body\\\"].read().decode())\";\n",
       "                var nbb_formatted_code = \"payload_csv_text = \\\"7.7, 3.0, 6.1, 2.3 \\\\n 7.9, 3.8, 6.4, 2.1\\\"\\n\\nresponse = sgmkr_runtime.invoke_endpoint(\\n    EndpointName=endpoint_name, ContentType=\\\"text/csv\\\", Body=payload_csv_text\\n)\\nprint(response[\\\"Body\\\"].read().decode())\";\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_csv_text = \"7.7, 3.0, 6.1, 2.3 \\n 7.9, 3.8, 6.4, 2.1\"\n",
    "\n",
    "response = sgmkr_runtime.invoke_endpoint(\n",
    "    EndpointName=endpoint_name, ContentType=\"text/csv\", Body=payload_csv_text\n",
    ")\n",
    "print(response[\"Body\"].read().decode())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Endpoint - Multiple records from a local file"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2.0,1.0,0.0,1.0,2.0,1.0,1.0,0.0,1.0,1.0,0.0,0.0,0.0,0.0,0.0,2.0,2.0,1.0,2.0,1.0,2.0,1.0,0.0,2.0,0.0,2.0,2.0,0.0,0.0,2.0,2.0,2.0,0.0,1.0,0.0,0.0,2.0,1.0,2.0,1.0,1.0,1.0,0.0,0.0,2.0,1.0,2.0,1.0,1.0,2.0\n"
     ]
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 59;\n",
       "                var nbb_unformatted_code = \"csv_buffer = open(\\\"data/iris_infer.csv\\\")\\npayload_csv_text = csv_buffer.read()\\n\\nresponse = sgmkr_runtime.invoke_endpoint(\\n    EndpointName=endpoint_name, ContentType=\\\"text/csv\\\", Body=payload_csv_text\\n)\\nprint(response[\\\"Body\\\"].read().decode())\";\n",
       "                var nbb_formatted_code = \"csv_buffer = open(\\\"data/iris_infer.csv\\\")\\npayload_csv_text = csv_buffer.read()\\n\\nresponse = sgmkr_runtime.invoke_endpoint(\\n    EndpointName=endpoint_name, ContentType=\\\"text/csv\\\", Body=payload_csv_text\\n)\\nprint(response[\\\"Body\\\"].read().decode())\";\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": [
    "csv_buffer = open(\"data/iris_infer.csv\")\n",
    "payload_csv_text = csv_buffer.read()\n",
    "\n",
    "response = sgmkr_runtime.invoke_endpoint(\n",
    "    EndpointName=endpoint_name, ContentType=\"text/csv\", Body=payload_csv_text\n",
    ")\n",
    "print(response[\"Body\"].read().decode())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'6.3,3.3,4.7,1.6\\n5.0,3.4,1.5,0.2\\n5.8,2.7,4.1,1.0\\n7.3,2.9,6.3,1.8\\n4.9,2.4,3.3,1.0\\n5.7,2.8,4.5,1.3\\n5.7,3.8,1.7,0.3\\n5.6,3.0,4.5,1.5\\n5.5,2.3,4.0,1.3\\n4.4,3.2,1.3,0.2\\n5.8,4.0,1.2,0.2\\n5.1,3.3,1.7,0.5\\n5.1,3.4,1.5,0.2\\n5.4,3.7,1.5,0.2\\n6.4,2.8,5.6,2.2\\n6.0,3.0,4.8,1.8\\n5.6,2.5,3.9,1.1\\n7.7,2.8,6.7,2.0\\n5.7,2.8,4.1,1.3\\n6.5,3.0,5.2,2.0\\n5.6,3.0,4.1,1.3\\n4.7,3.2,1.3,0.2\\n6.5,3.0,5.5,1.8\\n4.6,3.6,1.0,0.2\\n6.5,3.0,5.8,2.2\\n6.7,3.1,5.6,2.4\\n5.0,3.2,1.2,0.2\\n5.4,3.4,1.7,0.2\\n6.2,3.4,5.4,2.3\\n6.4,2.7,5.3,1.9\\n6.9,3.1,5.1,2.3\\n5.1,3.7,1.5,0.4\\n5.4,3.0,4.5,1.5\\n5.2,3.4,1.4,0.2\\n4.5,2.3,1.3,0.3\\n6.7,3.0,5.2,2.3\\n5.7,2.9,4.2,1.3\\n6.7,3.0,5.0,1.7\\n6.0,3.4,4.5,1.6\\n6.1,2.9,4.7,1.4\\n5.0,2.3,3.3,1.0\\n4.4,3.0,1.3,0.2\\n4.9,3.0,1.4,0.2\\n6.1,2.6,5.6,1.4\\n6.0,2.9,4.5,1.5\\n6.7,2.5,5.8,1.8\\n4.9,2.5,4.5,1.7\\n6.4,3.2,4.5,1.5\\n6.1,3.0,4.9,1.8\\n'"
      ]
     },
     "execution_count": 77,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 77;\n",
       "                var nbb_unformatted_code = \"payload_csv_text\";\n",
       "                var nbb_formatted_code = \"payload_csv_text\";\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_csv_text"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Endpoint - Multiple records from a S3 file"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1.0,0.0,1.0,2.0,1.0,1.0,0.0,1.0,1.0,0.0,0.0,0.0,0.0,0.0,2.0,2.0,1.0,2.0,1.0,2.0,1.0,0.0,2.0,0.0,2.0,2.0,0.0,0.0,2.0,2.0,2.0,0.0,1.0,0.0,0.0,2.0,1.0,2.0,1.0,1.0,1.0,0.0,0.0,2.0,1.0,2.0,1.0,1.0,2.0\n"
     ]
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 60;\n",
       "                var nbb_unformatted_code = \"infer_ip_s3_uri = \\\"s3://{}/{}/{}\\\".format(\\n    bucket, prefix, \\\"batch_transform/iris_infer.csv\\\"\\n)\\n\\n# payload_df = pd.read_csv(infer_ip_s3_uri)\\n# payload_df = wr.s3.read_csv(path=infer_ip_s3_uri)\\ns3_clnt = boto3.client(\\\"s3\\\")\\nobj = s3_clnt.get_object(Bucket=bucket, Key=\\\"iris/batch_transform/iris_infer.csv\\\")\\npayload_df = pd.read_csv(obj[\\\"Body\\\"])\\n\\ncsv_buffer = io.StringIO()\\npayload_df.to_csv(csv_buffer, header=None, index=None)\\npayload_csv_text = payload_file.getvalue()\\n\\nresponse = sgmkr_runtime.invoke_endpoint(\\n    EndpointName=endpoint_name, ContentType=\\\"text/csv\\\", Body=payload_csv_text\\n)\\nprint(response[\\\"Body\\\"].read().decode())\";\n",
       "                var nbb_formatted_code = \"infer_ip_s3_uri = \\\"s3://{}/{}/{}\\\".format(\\n    bucket, prefix, \\\"batch_transform/iris_infer.csv\\\"\\n)\\n\\n# payload_df = pd.read_csv(infer_ip_s3_uri)\\n# payload_df = wr.s3.read_csv(path=infer_ip_s3_uri)\\ns3_clnt = boto3.client(\\\"s3\\\")\\nobj = s3_clnt.get_object(Bucket=bucket, Key=\\\"iris/batch_transform/iris_infer.csv\\\")\\npayload_df = pd.read_csv(obj[\\\"Body\\\"])\\n\\ncsv_buffer = io.StringIO()\\npayload_df.to_csv(csv_buffer, header=None, index=None)\\npayload_csv_text = payload_file.getvalue()\\n\\nresponse = sgmkr_runtime.invoke_endpoint(\\n    EndpointName=endpoint_name, ContentType=\\\"text/csv\\\", Body=payload_csv_text\\n)\\nprint(response[\\\"Body\\\"].read().decode())\";\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": [
    "infer_ip_s3_uri = \"s3://{}/{}/{}\".format(\n",
    "    bucket, prefix, \"batch_transform/iris_infer.csv\"\n",
    ")\n",
    "\n",
    "# payload_df = pd.read_csv(infer_ip_s3_uri)\n",
    "# payload_df = wr.s3.read_csv(path=infer_ip_s3_uri)\n",
    "s3_clnt = boto3.client(\"s3\")\n",
    "obj = s3_clnt.get_object(Bucket=bucket, Key=\"iris/batch_transform/iris_infer.csv\")\n",
    "payload_df = pd.read_csv(obj[\"Body\"])\n",
    "\n",
    "csv_buffer = io.StringIO()\n",
    "payload_df.to_csv(csv_buffer, header=None, index=None)\n",
    "payload_csv_text = payload_file.getvalue()\n",
    "\n",
    "response = sgmkr_runtime.invoke_endpoint(\n",
    "    EndpointName=endpoint_name, ContentType=\"text/csv\", Body=payload_csv_text\n",
    ")\n",
    "print(response[\"Body\"].read().decode())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Delete the endpoint"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 62;\n",
       "                var nbb_unformatted_code = \"sgmkr_clnt = boto3.client(\\\"sagemaker\\\")\";\n",
       "                var nbb_formatted_code = \"sgmkr_clnt = boto3.client(\\\"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\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'ResponseMetadata': {'RequestId': '4a34bbbc-0aea-4d4e-8d5d-1e4657e626fd',\n",
       "  'HTTPStatusCode': 200,\n",
       "  'HTTPHeaders': {'x-amzn-requestid': '4a34bbbc-0aea-4d4e-8d5d-1e4657e626fd',\n",
       "   'content-type': 'application/x-amz-json-1.1',\n",
       "   'content-length': '0',\n",
       "   'date': 'Wed, 22 Mar 2023 08:16:50 GMT'},\n",
       "  'RetryAttempts': 0}}"
      ]
     },
     "execution_count": 63,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 63;\n",
       "                var nbb_unformatted_code = \"sgmkr_clnt.delete_endpoint(EndpointName=endpoint_name)\";\n",
       "                var nbb_formatted_code = \"sgmkr_clnt.delete_endpoint(EndpointName=endpoint_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": [
    "sgmkr_clnt.delete_endpoint(EndpointName=endpoint_name)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Batch Transform"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 64;\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": 65,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2023-02-03 13:29:08          0 iris/batch_transform/\r\n",
      "2023-03-16 18:09:29        800 iris/batch_transform/iris_infer.csv\r\n"
     ]
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 65;\n",
       "                var nbb_unformatted_code = \"!aws s3 ls {batch_ip}/ --recursive\";\n",
       "                var nbb_formatted_code = \"!aws s3 ls {batch_ip}/ --recursive\";\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": [
    "!aws s3 ls {batch_ip}/ --recursive"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Creating model with name: iris-xgboost-2023-03-22-08-17-15-602\n"
     ]
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 67;\n",
       "                var nbb_unformatted_code = \"transformer = xgb_estimator.transformer(\\n    instance_count=1, instance_type=\\\"ml.m4.xlarge\\\", output_path=batch_op\\n)\";\n",
       "                var nbb_formatted_code = \"transformer = xgb_estimator.transformer(\\n    instance_count=1, instance_type=\\\"ml.m4.xlarge\\\", output_path=batch_op\\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": [
    "transformer = xgb_estimator.transformer(\n",
    "    instance_count=1, instance_type=\"ml.m4.xlarge\", output_path=batch_op\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Creating transform job with name: iris-xgboost-2023-03-22-08-17-22-760\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      ".................................\n",
      "\u001b[34mArguments: serve\u001b[0m\n",
      "\u001b[34m[2023-03-22 08:22:53 +0000] [1] [INFO] Starting gunicorn 19.9.0\u001b[0m\n",
      "\u001b[34m[2023-03-22 08:22:53 +0000] [1] [INFO] Listening at: http://0.0.0.0:8080 (1)\u001b[0m\n",
      "\u001b[34m[2023-03-22 08:22:53 +0000] [1] [INFO] Using worker: gevent\u001b[0m\n",
      "\u001b[34m[2023-03-22 08:22:53 +0000] [21] [INFO] Booting worker with pid: 21\u001b[0m\n",
      "\u001b[34m[2023-03-22 08:22:53 +0000] [22] [INFO] Booting worker with pid: 22\u001b[0m\n",
      "\u001b[35mArguments: serve\u001b[0m\n",
      "\u001b[35m[2023-03-22 08:22:53 +0000] [1] [INFO] Starting gunicorn 19.9.0\u001b[0m\n",
      "\u001b[35m[2023-03-22 08:22:53 +0000] [1] [INFO] Listening at: http://0.0.0.0:8080 (1)\u001b[0m\n",
      "\u001b[35m[2023-03-22 08:22:53 +0000] [1] [INFO] Using worker: gevent\u001b[0m\n",
      "\u001b[35m[2023-03-22 08:22:53 +0000] [21] [INFO] Booting worker with pid: 21\u001b[0m\n",
      "\u001b[35m[2023-03-22 08:22:53 +0000] [22] [INFO] Booting worker with pid: 22\u001b[0m\n",
      "\u001b[34m[2023-03-22 08:22:53 +0000] [23] [INFO] Booting worker with pid: 23\u001b[0m\n",
      "\u001b[34m[2023-03-22 08:22:53 +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/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[2023-03-22:08:22:53:INFO] Model loaded successfully for worker : 21\u001b[0m\n",
      "\u001b[34m[2023-03-22:08:22:53:INFO] Model loaded successfully for worker : 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[2023-03-22:08:22:53: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[2023-03-22:08:22:53:INFO] Model loaded successfully for worker : 24\u001b[0m\n",
      "\u001b[35m[2023-03-22 08:22:53 +0000] [23] [INFO] Booting worker with pid: 23\u001b[0m\n",
      "\u001b[35m[2023-03-22 08:22:53 +0000] [24] [INFO] Booting worker with pid: 24\u001b[0m\n",
      "\u001b[35m/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[35m/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[35m[2023-03-22:08:22:53:INFO] Model loaded successfully for worker : 21\u001b[0m\n",
      "\u001b[35m[2023-03-22:08:22:53:INFO] Model loaded successfully for worker : 22\u001b[0m\n",
      "\u001b[35m/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[35m[2023-03-22:08:22:53:INFO] Model loaded successfully for worker : 23\u001b[0m\n",
      "\u001b[35m/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[35m[2023-03-22:08:22:53:INFO] Model loaded successfully for worker : 24\u001b[0m\n",
      "\u001b[34m[2023-03-22:08:22:57:INFO] Sniff delimiter as ','\u001b[0m\n",
      "\u001b[34m[2023-03-22:08:22:57:INFO] Determined delimiter of CSV input is ','\u001b[0m\n",
      "\u001b[35m[2023-03-22:08:22:57:INFO] Sniff delimiter as ','\u001b[0m\n",
      "\u001b[35m[2023-03-22:08:22:57:INFO] Determined delimiter of CSV input is ','\u001b[0m\n",
      "\u001b[32m2023-03-22T08:22:57.683:[sagemaker logs]: MaxConcurrentTransforms=4, MaxPayloadInMB=6, BatchStrategy=MULTI_RECORD\u001b[0m\n",
      "\u001b[34mArguments: serve\u001b[0m\n",
      "\u001b[34m[2023-03-22 08:22:53 +0000] [1] [INFO] Starting gunicorn 19.9.0\u001b[0m\n",
      "\u001b[34m[2023-03-22 08:22:53 +0000] [1] [INFO] Listening at: http://0.0.0.0:8080 (1)\u001b[0m\n",
      "\u001b[34m[2023-03-22 08:22:53 +0000] [1] [INFO] Using worker: gevent\u001b[0m\n",
      "\u001b[34m[2023-03-22 08:22:53 +0000] [21] [INFO] Booting worker with pid: 21\u001b[0m\n",
      "\u001b[34m[2023-03-22 08:22:53 +0000] [22] [INFO] Booting worker with pid: 22\u001b[0m\n",
      "\u001b[35mArguments: serve\u001b[0m\n",
      "\u001b[35m[2023-03-22 08:22:53 +0000] [1] [INFO] Starting gunicorn 19.9.0\u001b[0m\n",
      "\u001b[35m[2023-03-22 08:22:53 +0000] [1] [INFO] Listening at: http://0.0.0.0:8080 (1)\u001b[0m\n",
      "\u001b[35m[2023-03-22 08:22:53 +0000] [1] [INFO] Using worker: gevent\u001b[0m\n",
      "\u001b[35m[2023-03-22 08:22:53 +0000] [21] [INFO] Booting worker with pid: 21\u001b[0m\n",
      "\u001b[35m[2023-03-22 08:22:53 +0000] [22] [INFO] Booting worker with pid: 22\u001b[0m\n",
      "\u001b[34m[2023-03-22 08:22:53 +0000] [23] [INFO] Booting worker with pid: 23\u001b[0m\n",
      "\u001b[34m[2023-03-22 08:22:53 +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/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[2023-03-22:08:22:53:INFO] Model loaded successfully for worker : 21\u001b[0m\n",
      "\u001b[34m[2023-03-22:08:22:53:INFO] Model loaded successfully for worker : 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[2023-03-22:08:22:53: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[2023-03-22:08:22:53:INFO] Model loaded successfully for worker : 24\u001b[0m\n",
      "\u001b[35m[2023-03-22 08:22:53 +0000] [23] [INFO] Booting worker with pid: 23\u001b[0m\n",
      "\u001b[35m[2023-03-22 08:22:53 +0000] [24] [INFO] Booting worker with pid: 24\u001b[0m\n",
      "\u001b[35m/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[35m/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[35m[2023-03-22:08:22:53:INFO] Model loaded successfully for worker : 21\u001b[0m\n",
      "\u001b[35m[2023-03-22:08:22:53:INFO] Model loaded successfully for worker : 22\u001b[0m\n",
      "\u001b[35m/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[35m[2023-03-22:08:22:53:INFO] Model loaded successfully for worker : 23\u001b[0m\n",
      "\u001b[35m/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[35m[2023-03-22:08:22:53:INFO] Model loaded successfully for worker : 24\u001b[0m\n",
      "\u001b[34m[2023-03-22:08:22:57:INFO] Sniff delimiter as ','\u001b[0m\n",
      "\u001b[34m[2023-03-22:08:22:57:INFO] Determined delimiter of CSV input is ','\u001b[0m\n",
      "\u001b[35m[2023-03-22:08:22:57:INFO] Sniff delimiter as ','\u001b[0m\n",
      "\u001b[35m[2023-03-22:08:22:57:INFO] Determined delimiter of CSV input is ','\u001b[0m\n",
      "\u001b[32m2023-03-22T08:22:57.683:[sagemaker logs]: MaxConcurrentTransforms=4, MaxPayloadInMB=6, BatchStrategy=MULTI_RECORD\u001b[0m\n"
     ]
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 69;\n",
       "                var nbb_unformatted_code = \"transformer.transform(\\n    data=batch_ip, data_type=\\\"S3Prefix\\\", content_type=\\\"text/csv\\\", split_type=\\\"Line\\\"\\n)\\ntransformer.wait()\";\n",
       "                var nbb_formatted_code = \"transformer.transform(\\n    data=batch_ip, data_type=\\\"S3Prefix\\\", content_type=\\\"text/csv\\\", split_type=\\\"Line\\\"\\n)\\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.transform(\n",
    "    data=batch_ip, data_type=\"S3Prefix\", content_type=\"text/csv\", split_type=\"Line\"\n",
    ")\n",
    "transformer.wait()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2023-02-03 13:29:08          0 iris/batch_transform/\r\n",
      "2023-03-16 18:09:29        800 iris/batch_transform/iris_infer.csv\r\n",
      "2023-03-22 19:22:58        200 iris/batch_transform/iris_infer.csv.out\r\n"
     ]
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 70;\n",
       "                var nbb_unformatted_code = \"!aws s3 ls {bucket}/{prefix}/batch_transform/ --recursive\";\n",
       "                var nbb_formatted_code = \"!aws s3 ls {bucket}/{prefix}/batch_transform/ --recursive\";\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": [
    "!aws s3 ls {bucket}/{prefix}/batch_transform/ --recursive"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Completed 200 Bytes/200 Bytes (1.2 KiB/s) with 1 file(s) remaining\r",
      "download: s3://sgmkr-course/iris/batch_transform/iris_infer.csv.out to ./iris_infer.csv.out\r\n"
     ]
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 74;\n",
       "                var nbb_unformatted_code = \"!aws s3 cp s3://{bucket}/{prefix}/batch_transform/iris_infer.csv.out .\";\n",
       "                var nbb_formatted_code = \"!aws s3 cp s3://{bucket}/{prefix}/batch_transform/iris_infer.csv.out .\";\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": [
    "!aws s3 cp s3://{bucket}/{prefix}/batch_transform/iris_infer.csv.out ."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2.0\r\n",
      "1.0\r\n",
      "0.0\r\n",
      "1.0\r\n",
      "2.0\r\n"
     ]
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "            setTimeout(function() {\n",
       "                var nbb_cell_id = 76;\n",
       "                var nbb_unformatted_code = \"!head -n 5 iris_infer.csv.out\";\n",
       "                var nbb_formatted_code = \"!head -n 5 iris_infer.csv.out\";\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": [
    "!head -n 5 iris_infer.csv.out"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "\n"
   ]
  },
  {
   "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
}