I created this topic not for reveal a top secret solution. It's basically a \"thank you\" to the people who create public kernels. But about my solution I of course will tell.
\n\nI didn't have real expirence. And ideas about data preparation i took from public kernels. I tryied to built many different models using: LGBM, CatBoost, XGBoost, Regressions etc. But their scores were not so good as best public solutions. Then came the leakege and I tangled: what can i do with leakege. Summing up this stage of my work - I learned very much about visualization, data preparation, modeling and cross-validation.
\n\nThen I tried to more usage public kernels. And my first selected submission was blend of publics. Submission public score 0.952, private 1.286. And with this solution i would get 493 place.\nMy second solution was stacking (LightGBM) of four models. All models for ensemble was made by using LightGBM. On this way i made many mistakes. And very often saw low public score of my submissions. But in the end got public score 0.959, private 1.25001, and 52 place.
\n\nIt was hard for me, but i learned very much during this competition. And first of all I learned a lot thanks to public kernels.\nI thank everyone who was my teachers (even if they didn't know it:) during this competition: \n@rohanrao @purist1024 @yamsam @gunesevitan @nroman @iwatatakuya @ragnar123 @khoongweihao
", "messages": [ { "id": "710519", "postDate": "01/04/2020 20:50:37", "content": "I created this topic not for reveal a top secret solution. It's basically a \"thank you\" to the people who create public kernels. But about my solution I of course will tell.
\n\nI didn't have real expirence. And ideas about data preparation i took from public kernels. I tryied to built many different models using: LGBM, CatBoost, XGBoost, Regressions etc. But their scores were not so good as best public solutions. Then came the leakege and I tangled: what can i do with leakege. Summing up this stage of my work - I learned very much about visualization, data preparation, modeling and cross-validation.
\n\nThen I tried to more usage public kernels. And my first selected submission was blend of publics. Submission public score 0.952, private 1.286. And with this solution i would get 493 place.\nMy second solution was stacking (LightGBM) of four models. All models for ensemble was made by using LightGBM. On this way i made many mistakes. And very often saw low public score of my submissions. But in the end got public score 0.959, private 1.25001, and 52 place.
\n\nIt was hard for me, but i learned very much during this competition. And first of all I learned a lot thanks to public kernels.\nI thank everyone who was my teachers (even if they didn't know it:) during this competition: \n@rohanrao @purist1024 @yamsam @gunesevitan @nroman @iwatatakuya @ragnar123 @khoongweihao
", "rawMarkdown": "I created this topic not for reveal a top secret solution. It's basically a \"thank you\" to the people who create public kernels. But about my solution I of course will tell.\n\nI didn't have real expirence. And ideas about data preparation i took from public kernels. I tryied to built many different models using: LGBM, CatBoost, XGBoost, Regressions etc. But their scores were not so good as best public solutions. Then came the leakege and I tangled: what can i do with leakege. Summing up this stage of my work - I learned very much about visualization, data preparation, modeling and cross-validation.\n\nThen I tried to more usage public kernels. And my first selected submission was blend of publics. Submission public score 0.952, private 1.286. And with this solution i would get 493 place.\nMy second solution was stacking (LightGBM) of four models. All models for ensemble was made by using LightGBM. On this way i made many mistakes. And very often saw low public score of my submissions. But in the end got public score 0.959, private 1.25001, and 52 place.\n\nIt was hard for me, but i learned very much during this competition. And first of all I learned a lot thanks to public kernels.\nI thank everyone who was my teachers (even if they didn't know it:) during this competition: \n@rohanrao @purist1024 @yamsam @gunesevitan @nroman @iwatatakuya @ragnar123 @khoongweihao", "votes": null }, { "id": "711089", "postDate": "01/05/2020 17:12:07", "content": "thanks for sharing with us!
", "rawMarkdown": "thanks for sharing with us!", "votes": null }, { "id": "711199", "postDate": "01/05/2020 19:56:11", "content": "Congrats! Always trust your own hard work and it will pay back, lol
", "rawMarkdown": "Congrats! Always trust your own hard work and it will pay back, lol", "votes": null }, { "id": "717368", "postDate": "01/13/2020 03:59:54", "content": "Thank you very much @gusevpvl for sharing! We would like to add your solution to our analysis of the top processes and models. Please let us know how you would like to be acknowledged. The default will be what you have on your profile. Thanks again!
\n\nAlso, for everyone else, we are in the process of curating a directory of Notebooks for building performance engineers and analysts from the competition that will serve as a recipe book for beginners as well as experts who are curious to learn about certain topics. We highly encourage you all to share your solutions (or any part of your process) as a notebook for this purpose. We will acknowledge the authors of all notebooks in this process, so please annotate your notebook or profile with how you would like to be acknowledged. We will also include general solutions and process information that is not in notebooks as well. It would also be helpful if you could indicate whether you are an ASHRAE member.
", "rawMarkdown": "Thank you very much @gusevpvl for sharing! We would like to add your solution to our analysis of the top processes and models. Please let us know how you would like to be acknowledged. The default will be what you have on your profile. Thanks again!\n\n**Also, for everyone else, we are in the process of curating a directory of Notebooks for building performance engineers and analysts from the competition that will serve as a recipe book for beginners as well as experts who are curious to learn about certain topics. We highly encourage you all to share your solutions (or any part of your process) as a notebook for this purpose. We will acknowledge the authors of all notebooks in this process, so please annotate your notebook or profile with how you would like to be acknowledged. We will also include general solutions and process information that is not in notebooks as well. It would also be helpful if you could indicate whether you are an ASHRAE member.**", "votes": null } ], "comments": [ { "id": 711089, "author_name": "amitthakare", "author_url": "", "post_date": "01/05/2020 17:12:07", "content": "thanks for sharing with us!
", "votes": null, "replies": [] }, { "id": 711199, "author_name": "b0wang", "author_url": "", "post_date": "01/05/2020 19:56:11", "content": "Congrats! Always trust your own hard work and it will pay back, lol
", "votes": null, "replies": [] }, { "id": 717368, "author_name": "claytonmiller", "author_url": "", "post_date": "01/13/2020 03:59:54", "content": "Thank you very much @gusevpvl for sharing! We would like to add your solution to our analysis of the top processes and models. Please let us know how you would like to be acknowledged. The default will be what you have on your profile. Thanks again!
\n\nAlso, for everyone else, we are in the process of curating a directory of Notebooks for building performance engineers and analysts from the competition that will serve as a recipe book for beginners as well as experts who are curious to learn about certain topics. We highly encourage you all to share your solutions (or any part of your process) as a notebook for this purpose. We will acknowledge the authors of all notebooks in this process, so please annotate your notebook or profile with how you would like to be acknowledged. We will also include general solutions and process information that is not in notebooks as well. It would also be helpful if you could indicate whether you are an ASHRAE member.
", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "710519": "I created this topic not for reveal a top secret solution. It's basically a \"thank you\" to the people who create public kernels. But about my solution I of course will tell.\n\nI didn't have real expirence. And ideas about data preparation i took from public kernels. I tryied to built many different models using: LGBM, CatBoost, XGBoost, Regressions etc. But their scores were not so good as best public solutions. Then came the leakege and I tangled: what can i do with leakege. Summing up this stage of my work - I learned very much about visualization, data preparation, modeling and cross-validation.\n\nThen I tried to more usage public kernels. And my first selected submission was blend of publics. Submission public score 0.952, private 1.286. And with this solution i would get 493 place.\nMy second solution was stacking (LightGBM) of four models. All models for ensemble was made by using LightGBM. On this way i made many mistakes. And very often saw low public score of my submissions. But in the end got public score 0.959, private 1.25001, and 52 place.\n\nIt was hard for me, but i learned very much during this competition. And first of all I learned a lot thanks to public kernels.\nI thank everyone who was my teachers (even if they didn't know it:) during this competition: \n@rohanrao @purist1024 @yamsam @gunesevitan @nroman @iwatatakuya @ragnar123 @khoongweihao", "711089": "thanks for sharing with us!", "711199": "Congrats! Always trust your own hard work and it will pay back, lol", "717368": "Thank you very much @gusevpvl for sharing! We would like to add your solution to our analysis of the top processes and models. Please let us know how you would like to be acknowledged. The default will be what you have on your profile. Thanks again!\n\n**Also, for everyone else, we are in the process of curating a directory of Notebooks for building performance engineers and analysts from the competition that will serve as a recipe book for beginners as well as experts who are curious to learn about certain topics. We highly encourage you all to share your solutions (or any part of your process) as a notebook for this purpose. We will acknowledge the authors of all notebooks in this process, so please annotate your notebook or profile with how you would like to be acknowledged. We will also include general solutions and process information that is not in notebooks as well. It would also be helpful if you could indicate whether you are an ASHRAE member.**" }, "source": "meta" }