examples/aws/sagemaker/notebook.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Execute this cell to install dependencies\n",
    "%pip install sf-hamilton[visualization]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Sagemaker tutorial [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/dagworks-inc/hamilton/blob/main/examples/aws/sagemaker/notebook.ipynb) [![GitHub badge](https://img.shields.io/badge/github-view_source-2b3137?logo=github)](https://github.com/dagworks-inc/hamilton/blob/main/examples/aws/sagemaker/notebook.ipynb)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sagemaker.processing import ScriptProcessor, ProcessingInput, ProcessingOutput"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "script_processor = ScriptProcessor(\n",
    "    command=['python3'],\n",
    "    image_uri='<account_number>.dkr.ecr.<region>.amazonaws.com/aws-sagemaker-hamilton:latest',  # Change to the actual URI\n",
    "    role='arn:aws:iam::<account_number>:role/SageMakerScriptProcessorRole',  # Change to the actual URI\n",
    "    instance_count=1,\n",
    "    instance_type='ml.t3.medium'\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# All inputs and outputs should be located in /opt/ml/processing/\n",
    "script_processor.run(\n",
    "    code='processing.py',\n",
    "    inputs=[\n",
    "        ProcessingInput(\n",
    "            source='data/',\n",
    "            destination='/opt/ml/processing/input/data'\n",
    "        ),\n",
    "        ProcessingInput(\n",
    "            source='app/',\n",
    "            destination='/opt/ml/processing/input/code/app'\n",
    "        )\n",
    "    ],\n",
    "    outputs=[\n",
    "        ProcessingOutput(\n",
    "            source='/opt/ml/processing/output/',\n",
    "            destination='s3://path/to/output/directory'  # Change to the actual URI\n",
    "        )\n",
    "    ]\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "After job finishes, the new files will appear in `s3://path/to/output/directory`:\n",
    "- `output_table.csv`\n",
    "- `dag_visualization.svg`"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "hamilton",
   "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": "3.11.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}