[{"data":1,"prerenderedAt":237},["ShallowReactive",2],{"project-32721754":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":34,"aspects":35,"strip":38,"post_text":29,"what":41,"said":57,"maker_in_thread":128,"shape":131,"grid":135,"attempts":165,"same_week":199,"maker_shows":228,"maker_hidden":229,"reader_version":230,"card":231},"32721754","MLJAR AutoML","AutoML Python Package for Tabular Data with Automatic Documentation","title","Show HN: AutoML Python Package for Tabular Data with Automatic Documentation","https:\u002F\u002Fgithub.com\u002Fmljar\u002Fmljar-supervised","github.com","pplonski86",1662365710,2022,67,15,808,2570,32,"notable","ai","automl","library",[21,24,25,26,27],"tabular data","machine learning","python","model selection","quiet",null,{"positive":31,"neutral":32,"mixed":32,"critical":33},2,1,0,4,{"idea":36,"execution":37},{"positive":31,"critical":33},{"positive":33,"critical":33},[33,33,33,33,33,33,33,33,33,39,33,33,40,39,40],5,3,{"problem":42,"audience":29,"pricing":29,"motivation":29,"time_to_build":29,"stack":49,"openness":56,"stage":56,"team_size":56},{"value":43,"source":44,"evidence":45},"Automating machine learning on tabular data, including preprocessing and checking simple baseline models","maker",[46],{"id":47,"by":11,"text":48},"32724486","If your data doesn't require preprocessing ... Very often you need to prepare data to use xgboost\u002Flightgbm. You need to fill missing values, convert categoricals\u002Fdates\u002Ftext to…",[50],{"value":51,"source":52,"evidence":53},"Python","inferred",[54],{"id":55},"post","unknown",{"praise":58,"objections":71,"requests":90,"questions":95,"alternatives":102},[59],{"value":60,"source":61,"evidence":62},"Useful for exploring ML on tabular data and educational","commenter",[63,67],{"id":64,"by":65,"text":66},"32724705","chrisgd","This looks really great. I can imagine adding some features around the explanations from an educational standpoint. You could go from never having done this to understanding a…",{"id":68,"by":69,"text":70},"32724265","nlh","Sometimes I just absolutely love hacker news more than words can explain. I am knee deep in a personal project exploring machine learning on tabular data and it’s been consuming…",[72,79],{"value":73,"source":61,"evidence":74},"Only tests one neural network model, not several top architectures",[75],{"id":76,"by":77,"text":78},"32726827","Tenoke","Neat! I'll test it tomorrow. My only 'complaint' from reading the docs is that it only tests one NN model (which is the same for all types of data), rather than at least a few of…",{"value":80,"source":61,"evidence":81},"Gradient boosting libraries like XGBoost and LightGBM may be better without AutoML",[82,86],{"id":83,"by":84,"text":85},"32724408","nojito","If you have tabular data just run with xgboost\u002Flightgbm.",{"id":87,"by":88,"text":89},"32724570","sebastiansm","At least for tabular data there is no clear evidence that a neural network is superior than a tree-based model [0]. Many Data Scientist colleagues go straight to neural networks…",[91],{"value":92,"source":61,"evidence":93},"Add explanations to support learning",[94],{"id":64,"by":65,"text":66},[96],{"value":97,"source":61,"evidence":98},"Can XGBoost\u002FLightGBM handle out-of-time predictions for price regression",[99],{"id":100,"by":69,"text":101},"32724859","Yeah it seems those are still kings of the hill. One newbie question maybe you can answer: Can XGboost\u002FLightGBM handle out of band data predictions? The specific regression…",[103,110,117,121],{"value":104,"source":61,"evidence":105},"FLAML",[106],{"id":107,"by":108,"text":109},"32864807","d3nigma","There are many AutoML frameworks out there. For example, I recently found FLAML, which focuses on finding an optimal model given a budget. In case, you wanna check it out:…",{"value":111,"source":61,"evidence":112},"H2O AutoML",[113],{"id":114,"by":115,"text":116},"32730332","eyeball","https:\u002F\u002Fh2o-release.s3.amazonaws.com\u002Fh2o\u002Frel-zumbo\u002F4\u002Findex.html",{"value":118,"source":61,"evidence":119},"XGBoost and LightGBM",[120],{"id":83,"by":84,"text":85},{"value":122,"source":61,"evidence":123},"PyGraphistry",[124],{"id":125,"by":126,"text":127},"32724804","lmeyerov","Maybe useful: As part of improving autoML in PyGraphistry, we have been a doing a lot of auto-feature-engineering and auto-clustering work for one-liners like:…",{"comments":32,"answered":33,"key":129},[130],{"id":47,"text":48},{"commenters":132,"max_depth":39,"maker_replies":32,"first_comment_mins":133,"lifespan_hours":134},12,281,267,[136,138,140,142,145,146,149,152,153,154,157,158,160,162,163],[68,33,33,137,69,33],"other\u002Fneutral\u002Fnone",[83,33,33,139,84,33],"commenter\u002Fneutral\u002Fnone",[47,33,33,141,11,32],"project\u002Fpositive\u002Fidea",[143,33,33,139,144,33],"32725316","thegginthesky",[100,33,33,139,69,33],[147,33,33,139,148,33],"32725196","claytonjy",[150,33,33,151,69,33],"32730271","commenter\u002Fpositive\u002Fnone",[125,33,33,137,126,33],[114,33,33,137,115,33],[155,32,39,141,156,33],"32723780","mark_l_watson",[87,32,33,139,88,33],[159,32,33,139,156,33],"32724788",[107,31,40,161,108,33],"project\u002Fneutral\u002Fnone",[64,40,39,141,65,33],[76,34,40,164,77,33],"project\u002Fmixed\u002Fexecution",[166,169,172,175,178,181,184,187,190,193,198],{"id":167,"t":168,"points":32,"comments":32},"23153532",1589288879,{"id":170,"t":171,"points":39,"comments":32},"23166647",1589376425,{"id":173,"t":174,"points":34,"comments":32},"23201130",1589613106,{"id":176,"t":177,"points":31,"comments":33},"23244257",1589959881,{"id":179,"t":180,"points":31,"comments":33},"23270739",1590145295,{"id":182,"t":183,"points":39,"comments":33},"23800384",1594454119,{"id":185,"t":186,"points":40,"comments":32},"23836713",1594755495,{"id":188,"t":189,"points":32,"comments":33},"24775368",1602674734,{"id":191,"t":192,"points":34,"comments":33},"24905452",1603787638,{"id":194,"t":195,"points":196,"comments":197},"25644733",1609848834,33,8,{"id":4,"t":12,"points":14,"comments":15},[200,205,210,215,219,223],{"id":201,"name":202,"points":203,"category":204},"32690410","Openship",1335,"web_saas",{"id":206,"name":207,"points":208,"category":209},"32747067","quake_watch",692,"games",{"id":211,"name":212,"points":213,"category":214},"32688646","Wavvy",530,"creative",{"id":216,"name":217,"points":218,"category":209},"32717133","Zelda Breath of the Wild Street View",456,{"id":220,"name":221,"points":222,"category":214},"32738654","Bauble",252,{"id":224,"name":225,"points":226,"category":227},"32753471","TinyClock",192,"productivity",14,false,"v2",{"id":232,"name":5,"line":6,"ai":229,"cat":20,"year":13,"points":14,"comments":15,"rec":28,"s":29,"top":18,"kw":233,"maker":11,"domain":10,"tier":19,"attempts":234,"strip":235,"url":9,"mix":236,"praise":60,"objection":73,"sub":21},32721754,[21,24,25,26,27],11,"000000000500353",[31,32,32,33],1794036624473]