Hi All,
\n\nI'm new to Kaggle and looking for people around my rank to team up and enjoy this competition with. I've recently added a new set of features which based on preliminary results, should improve my score to between -1.85 and -1.90. Currently, I haven't bothered with any hyperparameter tuning (all models same params) so I expect further improvements if I follow the advice from -\nhttps://www.kaggle.com/c/champs-scalar-coupling/discussion/97705#latest-565957
\n\nSomeone with domain knowledge or 32 GB RAM would prove invaluable!
\n\nPlease let me know if you're interested in teaming up.
\n\nCheers,
\n\nJosh
", "messages": [ { "id": 566220, "postDate": "2019-07-01T23:04:16.243Z", "content": "Hi All,
\n\nI'm new to Kaggle and looking for people around my rank to team up and enjoy this competition with. I've recently added a new set of features which based on preliminary results, should improve my score to between -1.85 and -1.90. Currently, I haven't bothered with any hyperparameter tuning (all models same params) so I expect further improvements if I follow the advice from -\nhttps://www.kaggle.com/c/champs-scalar-coupling/discussion/97705#latest-565957
\n\nSomeone with domain knowledge or 32 GB RAM would prove invaluable!
\n\nPlease let me know if you're interested in teaming up.
\n\nCheers,
\n\nJosh
", "rawMarkdown": "Hi All,\n\nI'm new to Kaggle and looking for people around my rank to team up and enjoy this competition with. I've recently added a new set of features which based on preliminary results, should improve my score to between -1.85 and -1.90. Currently, I haven't bothered with any hyperparameter tuning (all models same params) so I expect further improvements if I follow the advice from -\nhttps://www.kaggle.com/c/champs-scalar-coupling/discussion/97705#latest-565957\n\nSomeone with domain knowledge or 32 GB RAM would prove invaluable!\n\nPlease let me know if you're interested in teaming up. \n\nCheers,\n\nJosh", "votes": 5 }, { "id": 566455, "postDate": "2019-07-02T07:25:56.807Z", "content": "Hi Josh, would you like to join our team?
", "rawMarkdown": "Hi Josh, would you like to join our team?", "votes": 2, "replies": [ { "id": 566463, "postDate": "2019-07-02T07:50:57.400Z", "content": "Hi Kha Vo,
\n\nI'm very interested in joining your team. Please invite me when you have the opportunity. I can send you some information about my methodology before the invite if you'd prefer?
\n\nJosh
", "rawMarkdown": "Hi Kha Vo,\n\nI'm very interested in joining your team. Please invite me when you have the opportunity. I can send you some information about my methodology before the invite if you'd prefer?\n\nJosh", "votes": 1 }, { "id": 566470, "postDate": "2019-07-02T08:04:19.720Z", "content": "Merge sent. Thanks Joshua.
", "rawMarkdown": "Merge sent. Thanks Joshua. ", "votes": 1 }, { "id": 566671, "postDate": "2019-07-02T12:44:32.377Z", "content": "@khahuras I am also looking for a team. Are you looking for any more teammates? My best lb score came from a single lightgbm model with about 50-80 features per type. I have not done any hyper parameter tuning. And, I am using an old fc oof feature that I have not been able to update yet. If you are interested, send a merge request and the method of communication that works for you.
", "rawMarkdown": "@khahuras I am also looking for a team. Are you looking for any more teammates? My best lb score came from a single lightgbm model with about 50-80 features per type. I have not done any hyper parameter tuning. And, I am using an old fc oof feature that I have not been able to update yet. If you are interested, send a merge request and the method of communication that works for you.", "votes": 2 }, { "id": 567266, "postDate": "2019-07-03T08:56:53.990Z", "content": "Thanks Kyle for the proposal!\nMessage sent (from team Kha/Zidmie/Joshua)
", "rawMarkdown": "Thanks Kyle for the proposal!\nMessage sent (from team Kha/Zidmie/Joshua)", "votes": 2 }, { "id": 567363, "postDate": "2019-07-03T11:58:59.123Z", "content": "I didn't get any message from your team. Can you please try to send the message again.
", "rawMarkdown": "I didn't get any message from your team. Can you please try to send the message again." }, { "id": 567376, "postDate": "2019-07-03T12:20:18.900Z", "content": "Can you send me your mail? Through Kaggle or here: zidmie@free.fr\nThanks!
", "rawMarkdown": "Can you send me your mail? Through Kaggle or here: zidmie@free.fr\nThanks!" }, { "id": 567378, "postDate": "2019-07-03T12:25:05.100Z", "content": "I just sent you an email.
", "rawMarkdown": "I just sent you an email." }, { "id": 567394, "postDate": "2019-07-03T12:48:54.670Z", "content": "If that doesn't work, you can reach me at my other email: kylepeters0872@yahoo.com
", "rawMarkdown": "If that doesn't work, you can reach me at my other email: kylepeters0872@yahoo.com" }, { "id": 567433, "postDate": "2019-07-03T14:12:05.833Z", "content": "Merge sent Kyle!
", "rawMarkdown": "Merge sent Kyle!", "votes": 1 }, { "id": 567444, "postDate": "2019-07-03T14:27:42.420Z", "content": "Epochs come and go, stars explode, entire atmospheres are formed and lost, and the planets themselves even begin to alter course. Ideologies and empires rise and fall, cults form and religions die, technologies evolve and fall into the nothingness. And it seems that everybody in this thread find a team except me 🐼
", "rawMarkdown": "Epochs come and go, stars explode, entire atmospheres are formed and lost, and the planets themselves even begin to alter course. Ideologies and empires rise and fall, cults form and religions die, technologies evolve and fall into the nothingness. And it seems that everybody in this thread find a team except me 🐼 ", "votes": 1 }, { "id": 570414, "postDate": "2019-07-08T08:57:21.437Z", "rawMarkdown": "", "votes": 1, "isDeleted": true } ] }, { "id": 566451, "postDate": "2019-07-02T07:22:33.767Z", "content": "Hi Josh!\nI'm interested!\nAbout me:\nI am also quite new to kaggle though already earned a couple of medals, and not very experienced in data science in general (did my very first print('hello, world') ~7 months ago) and therefore would really love to have an experienced teammate / s.\nAbout my model:\nI've tried a lot of different features for the moment, and I have couple more ideas that I currently didn't figure out how to implement correctly (based on given dataset). All my algo is done in several separate kernels. My model is GPU-accelerated LGBM, last 2 versions summary below:\nv1 mean CV -1.3764125, LB -1.529\nv2 mean CV -1.6487375, LB -1.555\nImportant: I'm going on vacation July 15-30, therefore I won't be able to participate during this days. I am ready to put some other things aside and make more spare time to spend on this comp in August if necessary (discussable 😉 )
Anyhow, if you're interested, you cant contact me here on kaggle or via e-mail blinberg@mail.ru.
\n\nRegards, \nStas
", "rawMarkdown": "Hi Josh!\nI'm interested!\n**About me:**\nI am also quite new to kaggle though already earned a couple of medals, and not very experienced in data science in general (did my very first `print('hello, world')` ~7 months ago) and therefore would really love to have an experienced teammate / s.\n**About my model:**\nI've tried a lot of different features for the moment, and I have couple more ideas that I currently didn't figure out how to implement correctly (based on given dataset). All my algo is done in several separate kernels. My model is GPU-accelerated LGBM, last 2 versions summary below:\nv1 mean CV -1.3764125, LB -1.529\nv2 mean CV -1.6487375, LB -1.555\n**Important:** I'm going on vacation July 15-30, therefore I won't be able to participate during this days. I am ready to put some other things aside and make more spare time to spend on this comp in August if necessary (discussable 😉 )\n\nAnyhow, if you're interested, you cant contact me here on kaggle or via e-mail blinberg@mail.ru.\n\nRegards, \nStas", "votes": 2, "replies": [ { "id": 566499, "postDate": "2019-07-02T08:43:09.257Z", "content": "Hi Stanislav,
\n\nThanks for your response.
\n\nI've decided to team up with Kha Vo but really hope you find the right teammate (probably someone with more experience than myself).
\n\nWishing you the best of luck in this competition!
\n\nJosh
", "rawMarkdown": "Hi Stanislav,\n\nThanks for your response. \n\nI've decided to team up with Kha Vo but really hope you find the right teammate (probably someone with more experience than myself).\n\nWishing you the best of luck in this competition!\n\nJosh", "votes": 1 }, { "id": 569465, "postDate": "2019-07-06T17:43:18.707Z", "content": "DM me if you want to join our team @stanislavblinov, or anyone else . We meet up weekly in-person. I am looking for team mates who want to work on this at night/over the weekends. I am free to use email/slack/skype/etc. The only requirement is you are willing to commit to working at least a few hours a week (except your vacation) so we can make progress. A lot of people say they are interested, but lose interest after 5 minutes.
\n\nI have a masters degree in data science and a lot of enthusiasm. A team is always better than going alone. A team allows us to \"divide and conquer.\" It also means more sharing of ideas and techniques.
", "rawMarkdown": "DM me if you want to join our team @stanislavblinov, or anyone else . We meet up weekly in-person. I am looking for team mates who want to work on this at night/over the weekends. I am free to use email/slack/skype/etc. The only requirement is you are willing to commit to working at least a few hours a week (except your vacation) so we can make progress. A lot of people say they are interested, but lose interest after 5 minutes.\n\nI have a masters degree in data science and a lot of enthusiasm. A team is always better than going alone. A team allows us to \"divide and conquer.\" It also means more sharing of ideas and techniques.", "votes": 1 } ] } ], "comments": [ { "id": 566455, "author_name": "Kha Vo", "author_url": "", "post_date": "2019-07-02T07:25:56.807000", "content": "Hi Josh, would you like to join our team?
", "votes": 2, "replies": [ { "id": 566463, "author_name": "Joshua Colmer", "author_url": "", "post_date": "2019-07-02T07:50:57.400000", "content": "Hi Kha Vo,
\n\nI'm very interested in joining your team. Please invite me when you have the opportunity. I can send you some information about my methodology before the invite if you'd prefer?
\n\nJosh
", "votes": 1, "replies": [] }, { "id": 566470, "author_name": "Kha Vo", "author_url": "", "post_date": "2019-07-02T08:04:19.720000", "content": "Merge sent. Thanks Joshua.
", "votes": 1, "replies": [] }, { "id": 566671, "author_name": "Kyle Peters", "author_url": "", "post_date": "2019-07-02T12:44:32.377000", "content": "@khahuras I am also looking for a team. Are you looking for any more teammates? My best lb score came from a single lightgbm model with about 50-80 features per type. I have not done any hyper parameter tuning. And, I am using an old fc oof feature that I have not been able to update yet. If you are interested, send a merge request and the method of communication that works for you.
", "votes": 2, "replies": [] }, { "id": 567266, "author_name": "Zidmie", "author_url": "", "post_date": "2019-07-03T08:56:53.990000", "content": "Thanks Kyle for the proposal!\nMessage sent (from team Kha/Zidmie/Joshua)
", "votes": 2, "replies": [] }, { "id": 567363, "author_name": "Kyle Peters", "author_url": "", "post_date": "2019-07-03T11:58:59.123000", "content": "I didn't get any message from your team. Can you please try to send the message again.
", "votes": 0, "replies": [] }, { "id": 567376, "author_name": "Zidmie", "author_url": "", "post_date": "2019-07-03T12:20:18.900000", "content": "Can you send me your mail? Through Kaggle or here: zidmie@free.fr\nThanks!
", "votes": 0, "replies": [] }, { "id": 567378, "author_name": "Kyle Peters", "author_url": "", "post_date": "2019-07-03T12:25:05.100000", "content": "I just sent you an email.
", "votes": 0, "replies": [] }, { "id": 567394, "author_name": "Kyle Peters", "author_url": "", "post_date": "2019-07-03T12:48:54.670000", "content": "If that doesn't work, you can reach me at my other email: kylepeters0872@yahoo.com
", "votes": 0, "replies": [] }, { "id": 567433, "author_name": "Kha Vo", "author_url": "", "post_date": "2019-07-03T14:12:05.833000", "content": "Merge sent Kyle!
", "votes": 1, "replies": [] }, { "id": 567444, "author_name": "Stanislav Blinov", "author_url": "", "post_date": "2019-07-03T14:27:42.420000", "content": "Epochs come and go, stars explode, entire atmospheres are formed and lost, and the planets themselves even begin to alter course. Ideologies and empires rise and fall, cults form and religions die, technologies evolve and fall into the nothingness. And it seems that everybody in this thread find a team except me 🐼
", "votes": 1, "replies": [] }, { "id": 570414, "author_name": "", "author_url": "", "post_date": "2019-07-08T08:57:21.437000", "content": "", "votes": 1, "replies": [] } ] }, { "id": 566451, "author_name": "Stanislav Blinov", "author_url": "", "post_date": "2019-07-02T07:22:33.767000", "content": "Hi Josh!\nI'm interested!\nAbout me:\nI am also quite new to kaggle though already earned a couple of medals, and not very experienced in data science in general (did my very first print('hello, world') ~7 months ago) and therefore would really love to have an experienced teammate / s.\nAbout my model:\nI've tried a lot of different features for the moment, and I have couple more ideas that I currently didn't figure out how to implement correctly (based on given dataset). All my algo is done in several separate kernels. My model is GPU-accelerated LGBM, last 2 versions summary below:\nv1 mean CV -1.3764125, LB -1.529\nv2 mean CV -1.6487375, LB -1.555\nImportant: I'm going on vacation July 15-30, therefore I won't be able to participate during this days. I am ready to put some other things aside and make more spare time to spend on this comp in August if necessary (discussable 😉 )
Anyhow, if you're interested, you cant contact me here on kaggle or via e-mail blinberg@mail.ru.
\n\nRegards, \nStas
", "votes": 2, "replies": [ { "id": 566499, "author_name": "Joshua Colmer", "author_url": "", "post_date": "2019-07-02T08:43:09.257000", "content": "Hi Stanislav,
\n\nThanks for your response.
\n\nI've decided to team up with Kha Vo but really hope you find the right teammate (probably someone with more experience than myself).
\n\nWishing you the best of luck in this competition!
\n\nJosh
", "votes": 1, "replies": [] }, { "id": 569465, "author_name": "lowecoryr", "author_url": "", "post_date": "2019-07-06T17:43:18.707000", "content": "DM me if you want to join our team @stanislavblinov, or anyone else . We meet up weekly in-person. I am looking for team mates who want to work on this at night/over the weekends. I am free to use email/slack/skype/etc. The only requirement is you are willing to commit to working at least a few hours a week (except your vacation) so we can make progress. A lot of people say they are interested, but lose interest after 5 minutes.
\n\nI have a masters degree in data science and a lot of enthusiasm. A team is always better than going alone. A team allows us to \"divide and conquer.\" It also means more sharing of ideas and techniques.
", "votes": 1, "replies": [] } ] } ], "raw_markdown_by_id": { "566220": "Hi All,\n\nI'm new to Kaggle and looking for people around my rank to team up and enjoy this competition with. I've recently added a new set of features which based on preliminary results, should improve my score to between -1.85 and -1.90. Currently, I haven't bothered with any hyperparameter tuning (all models same params) so I expect further improvements if I follow the advice from -\nhttps://www.kaggle.com/c/champs-scalar-coupling/discussion/97705#latest-565957\n\nSomeone with domain knowledge or 32 GB RAM would prove invaluable!\n\nPlease let me know if you're interested in teaming up. \n\nCheers,\n\nJosh", "566455": "Hi Josh, would you like to join our team?", "566451": "Hi Josh!\nI'm interested!\n**About me:**\nI am also quite new to kaggle though already earned a couple of medals, and not very experienced in data science in general (did my very first `print('hello, world')` ~7 months ago) and therefore would really love to have an experienced teammate / s.\n**About my model:**\nI've tried a lot of different features for the moment, and I have couple more ideas that I currently didn't figure out how to implement correctly (based on given dataset). All my algo is done in several separate kernels. My model is GPU-accelerated LGBM, last 2 versions summary below:\nv1 mean CV -1.3764125, LB -1.529\nv2 mean CV -1.6487375, LB -1.555\n**Important:** I'm going on vacation July 15-30, therefore I won't be able to participate during this days. I am ready to put some other things aside and make more spare time to spend on this comp in August if necessary (discussable 😉 )\n\nAnyhow, if you're interested, you cant contact me here on kaggle or via e-mail blinberg@mail.ru.\n\nRegards, \nStas" } }