{"id":24003397,"url":"https://github.com/dmschauer/aws-sagemaker-deployment-test","last_synced_at":"2026-05-02T08:34:35.099Z","repository":{"id":184843336,"uuid":"275641247","full_name":"dmschauer/AWS-Sagemaker-deployment-test","owner":"dmschauer","description":"I did a simple test to see how deploying a machine learning model on AWS Sagemaker and thus turning it into an API works. Since scikit-learn models require less dependencies than e.g. TensorFlow models I went with them for this test. To do so I used a tutorial.","archived":false,"fork":false,"pushed_at":"2022-06-29T17:32:15.000Z","size":954,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-02-25T10:34:35.103Z","etag":null,"topics":["aws","boto3","python","sagemaker","scikit-learn"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/dmschauer.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2020-06-28T18:07:16.000Z","updated_at":"2020-06-28T18:20:31.000Z","dependencies_parsed_at":"2023-07-30T15:40:16.000Z","dependency_job_id":null,"html_url":"https://github.com/dmschauer/AWS-Sagemaker-deployment-test","commit_stats":null,"previous_names":["dmschauer/aws-sagemaker-deployment-test"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/dmschauer/AWS-Sagemaker-deployment-test","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dmschauer%2FAWS-Sagemaker-deployment-test","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dmschauer%2FAWS-Sagemaker-deployment-test/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dmschauer%2FAWS-Sagemaker-deployment-test/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dmschauer%2FAWS-Sagemaker-deployment-test/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dmschauer","download_url":"https://codeload.github.com/dmschauer/AWS-Sagemaker-deployment-test/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dmschauer%2FAWS-Sagemaker-deployment-test/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32528343,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-02T01:12:54.858Z","status":"online","status_checked_at":"2026-05-02T02:00:05.923Z","response_time":132,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["aws","boto3","python","sagemaker","scikit-learn"],"created_at":"2025-01-08T01:10:47.123Z","updated_at":"2026-05-02T08:34:35.083Z","avatar_url":"https://github.com/dmschauer.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# AWS Sagemaker API test\n\nI did a simple test to see how deploying a machine learning model on AWS Sagemaker and thus turning it into an API works.\nSince scikit-learn models require less dependencies than e.g. TensorFlow models I went with them for this test.\nTo do so I used a tutorial.\n\nThough not explicitly mentioned in the text, this tutorial assumes that you have AWS CLI setup on your local machine.\nKeep this in mind if you run into `ValueError: Must setup local AWS configuration with a region supported by SageMaker`.\n\nThe steps termed '(optional)' in the tutorial aren't optional at all. Rather in the context of this tutorial they are crucial for things to function.\n\nAlso as of writing this, your training script must be a Python 2.7 or 3.6 compatible source file for the sagemaker library Version 1.66 to work.\n\n### My environment used during the test:\n- Windows 10 64-Bit\n- Python 3.7.7\n- (Spyder 4.1.3)\n- (Anaconda 4.8.3)\n\n### Dependencies:\n- boto3=1.14.12=pypi_0\n- botocore=1.17.12=pypi_0\n- numpy=1.18.5=pypi_0\n- pandas=1.0.5=pypi_0\n- sagemaker=1.66.0=pypi_0\n- scikit-learn=0.23.1=pypi_0\n- see also requirements.txt\n\n### Tutorial link:\nhttps://towardsdatascience.com/deploying-a-scikit-learn-model-on-aws-using-sklearn-estimators-local-jupyter-notebooks-and-the-d94396589498\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdmschauer%2Faws-sagemaker-deployment-test","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdmschauer%2Faws-sagemaker-deployment-test","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdmschauer%2Faws-sagemaker-deployment-test/lists"}