[{"data":1,"prerenderedAt":272},["ShallowReactive",2],{"project-19492406":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":35,"aspects":36,"strip":42,"post_text":44,"what":45,"said":70,"maker_in_thread":153,"shape":160,"grid":164,"attempts":233,"same_week":234,"maker_shows":263,"maker_hidden":264,"reader_version":265,"card":266},"19492406","automl-gs","Provide a CSV and a target field, generate a model and code to run it","title","Show HN: Provide a CSV and a target field, generate a model and code to run it","https:\u002F\u002Fgithub.com\u002Fminimaxir\u002Fautoml-gs","github.com","minimaxir",1553612175,2019,172,26,236,2195,11,"notable","ai","automl","cli",[21,24,25,26,27],"machine learning","hyperparameter optimization","csv","tensorflow","mixed",0.087,{"positive":31,"neutral":32,"mixed":33,"critical":34},3,4,0,2,9,{"performance":37,"docs":38,"idea":40,"design":41},{"positive":33,"critical":33},{"positive":39,"critical":39},1,{"positive":34,"critical":39},{"positive":33,"critical":33},[31,33,33,33,33,39,43,33,43,39,31,31,33,33,33,33,33,33,33,33,33,43,31,33,33,33],5,null,{"problem":46,"audience":44,"pricing":44,"motivation":44,"time_to_build":44,"stack":52,"openness":67,"stage":68,"team_size":69},{"value":47,"source":48,"evidence":49},"Automatically building predictive models from a CSV and a target field","maker",[50],{"id":51},"post",[53,61],{"value":54,"source":55,"evidence":56},"Python","commenter",[57],{"id":58,"by":59,"text":60},"19495947","jdright","Please, consider changing instances of \"Generates native Python code\" to something like \"Generates standard Python code without 3rd party libraries dependencies\" or equivalent.…",{"value":62,"source":48,"evidence":63},"TensorFlow",[64],{"id":65,"by":11,"text":66},"19493944","The best way to do that is IMO to look at the templates itself: https:\u002F\u002Fgithub.com\u002Fminimaxir\u002Fautoml-gs\u002Ftree\u002Fmaster\u002Fautoml_gs\u002Ftemplates\u002Fmodels\u002Ftensorflow tl;dr it uses the…","open_source","launched","unknown",{"praise":71,"objections":90,"requests":109,"questions":129,"alternatives":141},[72,79],{"value":73,"source":55,"evidence":74},"Well explained and motivated project with a useful DESIGN.md",[75],{"id":76,"by":77,"text":78},"19495069","nickvincent","This is extremely cool\u002Fuseful. Really appreciated how well the project is explained\u002Fmotivated, e.g. the DESIGN.md file. Thanks for making it public! Question about the long-term…",{"value":80,"source":55,"evidence":81},"Useful, cool project",[82,86],{"id":83,"by":84,"text":85},"19494060","malshe","This is fantastic! Thanks for putting this on Github. I am planning to build a [R] Shiny app for automl. This gives me good learning opportunity.",{"id":87,"by":88,"text":89},"19498119","ptd","Cool project! Have you compared your results to Ludwig by Uber? It would be interesting to see where the results differ. https:\u002F\u002Fuber.github.io\u002Fludwig\u002F",[91,98,102],{"value":92,"source":55,"evidence":93},"Gridsearch is inferior to random search for hyperparameter optimization",[94],{"id":95,"by":96,"text":97},"19493880","human_scientist","Nice project! You use gridsearch for hyperparamter optimization and state that at some point you would like to add a bayesian approach. One simple change that could boost the…",{"value":99,"source":55,"evidence":100},"Use of the term 'native Python code' is confusing",[101],{"id":58,"by":59,"text":60},{"value":103,"source":55,"evidence":104},"Early stopping is not implemented",[105],{"id":106,"by":107,"text":108},"19495635","pplonski86","Congratulations on lunching! I'm also working on open source autoML solution and I have similar problem with finding good heuristics for column type inference - I always left the…",[110,115,122],{"value":111,"source":55,"evidence":112},"Compare accuracy against other AutoML frameworks",[113,114],{"id":106,"by":107,"text":108},{"id":87,"by":88,"text":89},{"value":116,"source":55,"evidence":117},"Add early stopping",[118,119],{"id":106,"by":107,"text":108},{"id":120,"by":11,"text":121},"19495765","> Have you compared the solution accuracy with other frameworks? (or is it not the priority for your package right now) Still working on that. > Do you have early stopping…",{"value":123,"source":55,"evidence":124},"Longer demo gif and different demo dataset",[125],{"id":126,"by":127,"text":128},"19498042","caseyf7","The titanic data is a nice demo, but I’m kinda disappointed you didn’t try to predict WWMWD? Longer demo gif please!",[130,137],{"value":131,"source":55,"evidence":132},"How are models architected?",[133],{"id":134,"by":135,"text":136},"19493888","ashelmire","Very cool. Can you provide some details about how this tool architects models?",{"value":138,"source":55,"evidence":139},"How does it compare to Ludwig by Uber?",[140],{"id":87,"by":88,"text":89},[142,146],{"value":143,"source":55,"evidence":144},"Ludwig by Uber",[145],{"id":87,"by":88,"text":89},{"value":147,"source":55,"evidence":148},"HyperOpt",[149],{"id":150,"by":151,"text":152},"19584362","MasterScrat","What about HyperOpt?",{"comments":31,"answered":31,"key":154},[155,156,159],{"id":120,"text":121},{"id":157,"text":158},"19494400","Modeling is just a small part of data science (the percentage of time I've spent modeling as a data science is in the single digits). Automating modeling is a bit easier than…",{"id":65,"text":66},{"commenters":161,"max_depth":43,"maker_replies":31,"first_comment_mins":162,"lifespan_hours":163},21,141,558,[165,167,169,171,173,175,177,179,181,183,185,189,190,195,197,200,203,207,210,213,216,219,222,225,227,230],[95,33,31,166,96,33],"project\u002Fneutral\u002Fperformance",[150,33,33,168,151,33],"commenter\u002Fneutral\u002Fnone",[170,33,33,168,96,33],"19656837",[172,33,33,168,151,33],"19689616",[174,33,33,168,96,33],"19694554",[58,39,39,176,59,33],"project\u002Fcritical\u002Fdocs",[106,34,43,178,107,33],"maker\u002Fpositive\u002Fidea",[120,34,33,180,11,39],"maker\u002Fneutral\u002Fperformance",[76,31,43,182,77,33],"maker\u002Fpositive\u002Fdocs",[126,32,39,184,127,33],"project\u002Fcritical\u002Fidea",[186,32,31,187,188,33],"19503927","maker\u002Fneutral\u002Fdocs","yboris",[87,43,31,166,88,33],[191,192,33,193,194,33],"19494336",6,"other\u002Fneutral\u002Fnone","mrwebmaster",[157,192,33,196,11,39],"maker\u002Fneutral\u002Fidea",[198,192,33,193,199,33],"19494422","princeofwands",[201,192,33,193,202,33],"19496631","pmart123",[204,192,33,205,206,33],"19497370","other\u002Fneutral\u002Fidea","ken",[208,192,33,193,209,33],"19497427","paddy_m",[211,192,33,193,212,33],"19497430","laingc",[214,192,33,193,215,33],"19497547","MuffinFlavored",[217,192,33,193,218,33],"19498405","nl",[83,220,43,221,84,33],7,"project\u002Fpositive\u002Fidea",[134,223,31,224,135,33],8,"project\u002Fneutral\u002Fdesign",[65,223,33,226,11,39],"maker\u002Fneutral\u002Fdesign",[228,35,33,193,229,33],"19497555","aymeric",[231,35,33,193,232,33],"19498211","steve19",[],[235,240,245,250,254,258],{"id":236,"name":237,"points":238,"category":239},"19455441","Color Supply",591,"creative",{"id":241,"name":242,"points":243,"category":244},"19468993","Everything I Know Wiki",434,"productivity",{"id":246,"name":247,"points":248,"category":249},"19482280","Baxx",424,"infrastructure",{"id":251,"name":252,"points":253,"category":239},"19474853","ManyPixels Gallery",295,{"id":255,"name":256,"points":257,"category":239},"19454962","stereogram-raycaster",277,{"id":259,"name":260,"points":261,"category":262},"19477888","Harmopark",153,"languages",13,false,"v2",{"id":267,"name":5,"line":6,"ai":264,"cat":20,"year":13,"points":14,"comments":15,"rec":28,"s":268,"top":18,"kw":269,"maker":11,"domain":10,"tier":19,"attempts":33,"strip":270,"url":9,"mix":271,"praise":73,"objection":92,"sub":21},19492406,0.09,[21,24,25,26,27],"30000150513300000000053000",[31,32,33,34],1794036576125]