[{"data":1,"prerenderedAt":256},["ShallowReactive",2],{"project-20865012":3},{"id":4,"name":5,"line":6,"line_source":7,"title":8,"url":9,"domain":10,"maker":11,"posted_at":12,"year":13,"points":14,"comments":15,"rank_in_year":16,"shown_in_year":17,"top":18,"tier":19,"category":20,"subcategory":21,"format":22,"keywords":23,"reception":28,"sentiment":29,"stance_mix":30,"scored_comments":18,"aspects":34,"strip":39,"post_text":41,"what":42,"said":81,"maker_in_thread":157,"shape":159,"grid":163,"attempts":218,"same_week":219,"maker_shows":37,"maker_hidden":249,"reader_version":250,"card":251},"20865012","Fullstack ML","From Notebooks to Deployment","title","Show HN: Fullstack ML – From Notebooks to Deployment","https:\u002F\u002Fgithub.com\u002Fxadrianzetx\u002Ffullstack.ai","github.com","xadrianzetx",1567503946,2019,198,21,191,2195,9,"notable","ai","ml deployment example","web_app",[24,25,26,27],"machine learning deployment","flask api","docker nginx","ml pipeline","curious",-0.05,{"positive":31,"neutral":32,"mixed":33,"critical":31},2,5,0,{"idea":35,"docs":36,"execution":38},{"positive":31,"critical":33},{"positive":33,"critical":37},1,{"positive":33,"critical":37},[40,40,40,32,33,33,33,33,33,33,33,40,33,33,33,33,37,37,33,40,32],3,null,{"problem":43,"audience":41,"pricing":41,"motivation":41,"time_to_build":41,"stack":55,"openness":80,"stage":80,"team_size":80},{"value":44,"source":45,"evidence":46},"Showing how an ML model is taken from notebooks to a deployed web application","commenter",[47,51],{"id":48,"by":49,"text":50},"20868603","julienkervizic","Yes it covers a bit more than what people tend to see in Machine Learning which is the model training part. From the code base it looks to cover: 1) feature preparation and model…",{"id":52,"by":53,"text":54},"20866327","t0astbread","From what I can tell it's an example application to show how a machine learning project could be turned into a real world web app more or less from start to finish.",[56,63,68,72,76],{"value":57,"source":45,"evidence":58},"Python",[59],{"id":60,"by":61,"text":62},"20870551","olooney","This feels like it doesn't live up to its own hype because it doesn't really exhibit a production-quality deployment of a Python application but something closer to a dev server.…",{"value":64,"source":45,"evidence":65},"Flask",[66,67],{"id":48,"by":49,"text":50},{"id":60,"by":61,"text":62},{"value":69,"source":45,"evidence":70},"Docker",[71],{"id":48,"by":49,"text":50},{"value":73,"source":45,"evidence":74},"nginx",[75],{"id":48,"by":49,"text":50},{"value":77,"source":45,"evidence":78},"Jupyter notebooks",[79],{"id":48,"by":49,"text":50},"unknown",{"praise":82,"objections":91,"requests":118,"questions":134,"alternatives":142},[83],{"value":84,"source":45,"evidence":85},"Useful end-to-end demo of ML production scope",[86,87],{"id":48,"by":49,"text":50},{"id":88,"by":89,"text":90},"20871439","m23khan","this is freaking awesome! was looking for something like this for a long time. Much appreciated!!!",[92,96,103,107],{"value":93,"source":45,"evidence":94},"Flask built-in dev server is not production-ready; needs WSGI like gunicorn",[95],{"id":60,"by":61,"text":62},{"value":97,"source":45,"evidence":98},"Lacks documentation on structure and internals",[99],{"id":100,"by":101,"text":102},"20886459","jkaufmann_","While the example here is definitely trivial, it would be nice to see some more documentation. Particularly around project structure, internals, and thought process. Seeing e2e…",{"value":104,"source":45,"evidence":105},"Example is trivial",[106],{"id":100,"by":101,"text":102},{"value":108,"source":45,"evidence":109},"Unclear what it is from title alone",[110,114],{"id":111,"by":112,"text":113},"20865958","jbverschoor","I have absolutely no idea what this is, supposed to do, and what the demo shows.",{"id":115,"by":116,"text":117},"20870881","jetti","I made the same mistake for this post. I'm not very familiar with Machine Learning so notebook doesn't give it away for me. But then throw in \"fullstack\" and it makes it seem, to…",[119,123,127],{"value":120,"source":45,"evidence":121},"More documentation on project structure and thought process",[122],{"id":100,"by":101,"text":102},{"value":124,"source":45,"evidence":125},"Production-grade deployment with WSGI, logging and error handling",[126],{"id":60,"by":61,"text":62},{"value":128,"source":45,"evidence":129},"Comparison with Rust or Go backends",[130],{"id":131,"by":132,"text":133},"20868708","s3nh_","Looks really nice! Love to see it next to some Rust-like or Golang=like backend. What do you think?",[135],{"value":136,"source":45,"evidence":137},"What happened to Yhat",[138],{"id":139,"by":140,"text":141},"20868061","mahesh_rm","What happened to them?",[143,150],{"value":144,"source":45,"evidence":145},"Yhat",[146],{"id":147,"by":148,"text":149},"20867129","leetrout","This is very, very similar to what Yhat (YC W15) did. You dropped some code in your Python or R project and it would slurp everything in to one package and, for Python, run it in…",{"value":151,"source":45,"evidence":152},"Domino Data Lab",[153],{"id":154,"by":155,"text":156},"20869549","djp518","That's my take as well. yhat, datascience.com, and Domino Data Lab were the first players in this space. Domino has a webinar and trial project to see how these platforms…",{"comments":33,"answered":33,"key":158},[],{"commenters":160,"max_depth":40,"maker_replies":33,"first_comment_mins":161,"lifespan_hours":162},20,183,52,[164,166,169,170,172,174,177,180,183,186,190,193,195,198,201,202,204,206,209,213,216],[111,33,40,165,112,33],"project\u002Fneutral\u002Fidea",[167,33,40,165,168,33],"20866323","nitelord",[52,33,40,165,53,33],[48,33,32,171,49,33],"project\u002Fpositive\u002Fidea",[154,33,33,173,155,33],"other\u002Fneutral\u002Fnone",[175,33,33,173,176,33],"20866886","discordance",[178,37,33,173,179,33],"20866786","visarga",[181,31,33,173,182,33],"20865986","dotdi",[184,31,33,173,185,33],"20866083","taneq",[187,31,33,188,189,33],"20866751","commenter\u002Fneutral\u002Fnone","gumby",[191,31,33,173,192,33],"20866638","tasogare",[115,31,40,194,116,33],"project\u002Fneutral\u002Fdocs",[196,40,33,173,197,33],"20871318","screaminghawk",[147,199,33,200,148,33],4,"other\u002Fneutral\u002Fidea",[139,199,33,173,140,33],[203,199,33,173,49,33],"20868415",[100,32,37,205,101,33],"project\u002Fcritical\u002Fdocs",[60,207,37,208,61,33],6,"project\u002Fcritical\u002Fexecution",[210,207,33,211,212,33],"20875567","commenter\u002Fneutral\u002Fexecution","astonex",[131,214,40,215,132,33],7,"project\u002Fneutral\u002Fnone",[88,217,32,171,89,33],8,[],[220,225,230,235,240,244],{"id":221,"name":222,"points":223,"category":224},"20872696","IgushArray",300,"languages",{"id":226,"name":227,"points":228,"category":229},"20860852","Face Generator",256,"creative",{"id":231,"name":232,"points":233,"category":234},"20865426","Ackee",214,"web_saas",{"id":236,"name":237,"points":238,"category":239},"20857887","Hacker News Clone",179,"learning_science",{"id":241,"name":242,"points":243,"category":234},"20830726","HackerRank Projects",134,{"id":245,"name":246,"points":247,"category":248},"20860053","workoutbff.com",131,"consumer_social",false,"v2",{"id":252,"name":5,"line":6,"ai":249,"cat":20,"year":13,"points":14,"comments":15,"rec":28,"s":29,"top":18,"kw":253,"maker":11,"domain":10,"tier":19,"attempts":33,"strip":254,"url":9,"mix":255,"praise":84,"objection":93,"sub":21},20865012,[24,25,26,27],"333500000003000011035",[31,32,33,31],1794036580458]