{"id":8085,"date":"2025-10-27T01:29:53","date_gmt":"2025-10-27T01:29:53","guid":{"rendered":"https:\/\/techtrendfeed.com\/?p=8085"},"modified":"2025-10-27T01:29:54","modified_gmt":"2025-10-27T01:29:54","slug":"%f0%9f%9a%80-the-journey-of-deploying-a-home-value-prediction-venture-on-aws-by-indraseptianto-oct-2025","status":"publish","type":"post","link":"https:\/\/techtrendfeed.com\/?p=8085","title":{"rendered":"\ud83d\ude80 The Journey of Deploying a Home Value Prediction Venture on AWS | by Indraseptianto | Oct, 2025"},"content":{"rendered":"

\n<\/p>\n

\n

Picture for Modeling<\/figcaption><\/figure>\n
6. Prototyping<\/h2>\n
Subsequent got here the prototyping section.<\/p>\n
There have been two fundamental methods I attempted it:<\/p>\n
\n
**Native prototype utilizing Docker Desktop<\/strong><\/li>\n**
Cloud prototype utilizing Streamlit<\/strong><\/li>\n<\/ol>\n
\n
Press enter or click on to view picture in full dimension<\/span><\/p>\n
$\"\"$ <\/picture><\/div>\n<\/div>
Picture for deploy in streamlit<\/figcaption><\/figure>\n
Each had execs and cons.<\/p>\n
\n
Docker was versatile and allowed direct edits, however builds had been gradual, particularly when utilizing many dependencies (FastAPI, Grafana, MLflow).<\/li>\n
Streamlit was quicker to construct, however required pushing updates to GitHub ceaselessly \u2014 which might be time-consuming.<\/li>\n<\/ul>\n
On this undertaking, I ended up utilizing **each approaches<\/strong> \u2014 Docker for backend atmosphere management, Streamlit for fast iteration and testing.<\/p>\n**
Actually, this section took plenty of time.
Generally the `.pkl<\/code> mannequin wouldn\u2019t load appropriately in FastAPI, breaking predictions. However each error became a studying second.<\/p>\n`
7. Manufacturing Stage<\/h2>\nAfter the Streamlit prototype was secure, it was time to maneuver into manufacturing.<\/p>\n Earlier than buying a VPS or cloud occasion, I did some analysis on the perfect specs \u2014 RAM, CPU, storage \u2014 that may match this undertaking.<\/p>\n \nPress enter or click on to view picture in full dimension<\/span><\/p>\n<\/picture><\/div>\n<\/div>Picture create Container in AWS EC2<\/figcaption><\/figure>\nUltimately, I selected AWS Free Tier<\/strong>. Easy cause: it\u2019s free, however highly effective sufficient for a small-scale MLOps experiment.<\/p>\n Steps I took:<\/p>\n \nCreated an AWS account (fortunate sufficient to skip bank card verification \ud83d\ude05)<\/li>\n Launched an EC2 occasion (Ubuntu)<\/strong><\/li>\n Added an Elastic IP<\/strong> for a everlasting public IP<\/li>\n Configured Safety Teams<\/strong> to attach situations and containers<\/li>\n Accessed EC2 through SSH, up to date the OS<\/li>\n Put in Docker and EasyPanel<\/strong><\/li>\n Deployed FastAPI + Streamlit containers instantly<\/li>\n<\/ul>\n\nPress enter or click on to view picture in full dimension<\/span><\/p>\n<\/picture><\/div>\n<\/div>Picture create manufacturing in easypannel<\/figcaption><\/figure>\n\nSpecs: \ud83e\udde0 1 CPU \ud83d\udcbe 1 GB RAM \ud83d\udce6 30 GB Storage<\/p>\n Surprisingly, that\u2019s sufficient to run an end-to-end ML pipeline for observe.<\/p>\n \ud83c\udf89 The undertaking is now reside<\/strong> and publicly accessible: \ud83d\udc49 houseindo.my.id<\/a><\/p>\n<\/blockquote>\n \nPress enter or click on to view picture in full dimension<\/span><\/p>\n<\/picture><\/div>\n<\/div>Sumber apidog<\/figcaption><\/figure>\nReflection<\/h2>\nFor me, this entire journey wasn\u2019t nearly coding or deployment. It was about persistence, persistence, and problem-solving<\/strong>.<\/p>\n Deployment isn\u2019t solely about infrastructure \u2014 it\u2019s additionally a psychological sport of staying calm and curious when issues go improper.<\/p>\n Generally, you don\u2019t simply debug code \u2014 you debug your self too. \ud83d\ude05<\/p>\n<\/div>\n\n","protected":false},"excerpt":{"rendered":" Press enter or click on to view picture in full dimension Picture for Modeling 6. Prototyping Subsequent got here the prototyping section. There have been two fundamental methods I attempted it: Native prototype utilizing Docker Desktop Cloud prototype utilizing Streamlit Press enter or click on to view picture in full dimension Picture for deploy in […]<\/p>\n","protected":false},"author":2,"featured_media":8087,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[55],"tags":[2412,6109,2015,6110,2055,5655,3791,1046,1640],"class_list":["post-8085","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-machine-learning","tag-aws","tag-deploying","tag-house","tag-indraseptianto","tag-journey","tag-oct","tag-prediction","tag-price","tag-project"],"_links":{"self":[{"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=\/wp\/v2\/posts\/8085","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=8085"}],"version-history":[{"count":1,"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=\/wp\/v2\/posts\/8085\/revisions"}],"predecessor-version":[{"id":8086,"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=\/wp\/v2\/posts\/8085\/revisions\/8086"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=\/wp\/v2\/media\/8087"}],"wp:attachment":[{"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=8085"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=8085"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=8085"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}

Picture for Modeling<\/figcaption><\/figure>\n
6. Prototyping<\/h2>\n
Subsequent got here the prototyping section.<\/p>\n
There have been two fundamental methods I attempted it:<\/p>\n
\n
**Native prototype utilizing Docker Desktop<\/strong><\/li>\n**
Cloud prototype utilizing Streamlit<\/strong><\/li>\n<\/ol>\n
\n
Press enter or click on to view picture in full dimension<\/span><\/p>\n
$\"\"$ <\/picture><\/div>\n<\/div>
Picture for deploy in streamlit<\/figcaption><\/figure>\n
Each had execs and cons.<\/p>\n
\n
Docker was versatile and allowed direct edits, however builds had been gradual, particularly when utilizing many dependencies (FastAPI, Grafana, MLflow).<\/li>\n
Streamlit was quicker to construct, however required pushing updates to GitHub ceaselessly \u2014 which might be time-consuming.<\/li>\n<\/ul>\n
On this undertaking, I ended up utilizing **each approaches<\/strong> \u2014 Docker for backend atmosphere management, Streamlit for fast iteration and testing.<\/p>\n**
Actually, this section took plenty of time.
Generally the `.pkl<\/code> mannequin wouldn\u2019t load appropriately in FastAPI, breaking predictions. However each error became a studying second.<\/p>\n`
7. Manufacturing Stage<\/h2>\nAfter the Streamlit prototype was secure, it was time to maneuver into manufacturing.<\/p>\n Earlier than buying a VPS or cloud occasion, I did some analysis on the perfect specs \u2014 RAM, CPU, storage \u2014 that may match this undertaking.<\/p>\n \nPress enter or click on to view picture in full dimension<\/span><\/p>\n<\/picture><\/div>\n<\/div>Picture create Container in AWS EC2<\/figcaption><\/figure>\nUltimately, I selected AWS Free Tier<\/strong>. Easy cause: it\u2019s free, however highly effective sufficient for a small-scale MLOps experiment.<\/p>\n Steps I took:<\/p>\n \nCreated an AWS account (fortunate sufficient to skip bank card verification \ud83d\ude05)<\/li>\n Launched an EC2 occasion (Ubuntu)<\/strong><\/li>\n Added an Elastic IP<\/strong> for a everlasting public IP<\/li>\n Configured Safety Teams<\/strong> to attach situations and containers<\/li>\n Accessed EC2 through SSH, up to date the OS<\/li>\n Put in Docker and EasyPanel<\/strong><\/li>\n Deployed FastAPI + Streamlit containers instantly<\/li>\n<\/ul>\n\nPress enter or click on to view picture in full dimension<\/span><\/p>\n<\/picture><\/div>\n<\/div>Picture create manufacturing in easypannel<\/figcaption><\/figure>\n\nSpecs: \ud83e\udde0 1 CPU \ud83d\udcbe 1 GB RAM \ud83d\udce6 30 GB Storage<\/p>\n Surprisingly, that\u2019s sufficient to run an end-to-end ML pipeline for observe.<\/p>\n \ud83c\udf89 The undertaking is now reside<\/strong> and publicly accessible: \ud83d\udc49 houseindo.my.id<\/a><\/p>\n<\/blockquote>\n \nPress enter or click on to view picture in full dimension<\/span><\/p>\n<\/picture><\/div>\n<\/div>Sumber apidog<\/figcaption><\/figure>\nReflection<\/h2>\nFor me, this entire journey wasn\u2019t nearly coding or deployment. It was about persistence, persistence, and problem-solving<\/strong>.<\/p>\n Deployment isn\u2019t solely about infrastructure \u2014 it\u2019s additionally a psychological sport of staying calm and curious when issues go improper.<\/p>\n Generally, you don\u2019t simply debug code \u2014 you debug your self too. \ud83d\ude05<\/p>\n<\/div>\n\n","protected":false},"excerpt":{"rendered":" Press enter or click on to view picture in full dimension Picture for Modeling 6. Prototyping Subsequent got here the prototyping section. There have been two fundamental methods I attempted it: Native prototype utilizing Docker Desktop Cloud prototype utilizing Streamlit Press enter or click on to view picture in full dimension Picture for deploy in […]<\/p>\n","protected":false},"author":2,"featured_media":8087,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[55],"tags":[2412,6109,2015,6110,2055,5655,3791,1046,1640],"class_list":["post-8085","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-machine-learning","tag-aws","tag-deploying","tag-house","tag-indraseptianto","tag-journey","tag-oct","tag-prediction","tag-price","tag-project"],"_links":{"self":[{"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=\/wp\/v2\/posts\/8085","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=8085"}],"version-history":[{"count":1,"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=\/wp\/v2\/posts\/8085\/revisions"}],"predecessor-version":[{"id":8086,"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=\/wp\/v2\/posts\/8085\/revisions\/8086"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=\/wp\/v2\/media\/8087"}],"wp:attachment":[{"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=8085"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=8085"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=8085"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}