{
  "id": 195535,
  "title": "final submission format",
  "url": "/competitions/lyft-motion-prediction-autonomous-vehicles/discussion/195535",
  "author_name": "",
  "post_date": "2020-11-06T01:10:37.528101500Z",
  "votes": null,
  "comment_count": 4,
  "views": 0,
  "content": "<p>Hello everyone, for the final submission, do we only need submission.csv?<br>\nSo we can train offline, prediction off, only use a few lines of codes like this:</p>\n<p>sub=pd.read_csv('/kaggle/input/private_submssion.csv')<br>\nsub.to_csv('submission.csv',index=False)</p>\n<p>We do not need to provide codes of cfg, pertained model, inference, etc. Right? </p>\n<p>Thank you!</p>",
  "messages": [
    {
      "id": "1070622",
      "postDate": "11/06/2020 01:10:37",
      "content": "<p>Hello everyone, for the final submission, do we only need submission.csv?<br>\nSo we can train offline, prediction off, only use a few lines of codes like this:</p>\n<p>sub=pd.read_csv('/kaggle/input/private_submssion.csv')<br>\nsub.to_csv('submission.csv',index=False)</p>\n<p>We do not need to provide codes of cfg, pertained model, inference, etc. Right? </p>\n<p>Thank you!</p>",
      "rawMarkdown": "Hello everyone, for the final submission, do we only need submission.csv?\nSo we can train offline, prediction off, only use a few lines of codes like this:\n\nsub=pd.read_csv('/kaggle/input/private_submssion.csv')\nsub.to_csv('submission.csv',index=False)\n\nWe do not need to provide codes of cfg, pertained model, inference, etc. Right? \n\nThank you!",
      "votes": null
    },
    {
      "id": "1072274",
      "postDate": "11/08/2020 02:36:25",
      "content": "<p>As for my understanding, we do need to provide a configure file and a pretrained model, and everything that you need to accomplish an integrated prediction on the test set because the final result is based on another 50% of the test set.</p>",
      "rawMarkdown": "As for my understanding, we do need to provide a configure file and a pretrained model, and everything that you need to accomplish an integrated prediction on the test set because the final result is based on another 50% of the test set.",
      "votes": null
    },
    {
      "id": "1072423",
      "postDate": "11/08/2020 07:52:54",
      "content": "<p><a href=\"https://www.kaggle.com/c/lyft-motion-prediction-autonomous-vehicles/discussion/177414#1034502\" target=\"_blank\">https://www.kaggle.com/c/lyft-motion-prediction-autonomous-vehicles/discussion/177414#1034502</a><br>\nhere is the discussion about the final submission. <br>\nFrom the host, everything can be offline. We need only to upload csv.</p>\n<p>Vladimir IglovikovCompetition Host • a month ago • Options • Report • Reply</p>\n<p>keyboard_arrow_up<br>\n3</p>\n<p>keyboard_arrow_down<br>\nYou can do everything offline.<br>\nYou can upload the csv to the inference kernel and that is it.<br>\nIf you get into \"money\" we will need code that reproduces your submission from the data. But even in this case, until the end of the competition, you can submit csv's.<br>\nAll submissions that are made now, count both for Public and for Private test sets, no additional work is required.</p>",
      "rawMarkdown": "https://www.kaggle.com/c/lyft-motion-prediction-autonomous-vehicles/discussion/177414#1034502\nhere is the discussion about the final submission. \nFrom the host, everything can be offline. We need only to upload csv.\n\nVladimir IglovikovCompetition Host • a month ago • Options • Report • Reply\n\nkeyboard_arrow_up\n3\n\nkeyboard_arrow_down\nYou can do everything offline.\nYou can upload the csv to the inference kernel and that is it.\nIf you get into \"money\" we will need code that reproduces your submission from the data. But even in this case, until the end of the competition, you can submit csv's.\nAll submissions that are made now, count both for Public and for Private test sets, no additional work is required.",
      "votes": null
    },
    {
      "id": "1072463",
      "postDate": "11/08/2020 09:07:33",
      "content": "<p>when we have predicted on the test set, have we actually predicted both the public and private test set?</p>",
      "rawMarkdown": "when we have predicted on the test set, have we actually predicted both the public and private test set?",
      "votes": null
    },
    {
      "id": "1072487",
      "postDate": "11/08/2020 10:09:24",
      "content": "<blockquote>\n  <p>when we have predicted on the test set, have we actually predicted both the public and private test set?</p>\n</blockquote>\n<p>yes, test is both, public and private. If you predicted all Ids from the sample_submission you are good. Should be around 70k lines, iirc.</p>",
      "rawMarkdown": "> when we have predicted on the test set, have we actually predicted both the public and private test set?\n\nyes, test is both, public and private. If you predicted all Ids from the sample_submission you are good. Should be around 70k lines, iirc.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1072274,
      "author_name": "spicychicken38",
      "author_url": "",
      "post_date": "11/08/2020 02:36:25",
      "content": "<p>As for my understanding, we do need to provide a configure file and a pretrained model, and everything that you need to accomplish an integrated prediction on the test set because the final result is based on another 50% of the test set.</p>",
      "votes": null,
      "replies": [
        {
          "id": 1072423,
          "author_name": "shuozhang",
          "author_url": "",
          "post_date": "11/08/2020 07:52:54",
          "content": "<p><a href=\"https://www.kaggle.com/c/lyft-motion-prediction-autonomous-vehicles/discussion/177414#1034502\" target=\"_blank\">https://www.kaggle.com/c/lyft-motion-prediction-autonomous-vehicles/discussion/177414#1034502</a><br>\nhere is the discussion about the final submission. <br>\nFrom the host, everything can be offline. We need only to upload csv.</p>\n<p>Vladimir IglovikovCompetition Host • a month ago • Options • Report • Reply</p>\n<p>keyboard_arrow_up<br>\n3</p>\n<p>keyboard_arrow_down<br>\nYou can do everything offline.<br>\nYou can upload the csv to the inference kernel and that is it.<br>\nIf you get into \"money\" we will need code that reproduces your submission from the data. But even in this case, until the end of the competition, you can submit csv's.<br>\nAll submissions that are made now, count both for Public and for Private test sets, no additional work is required.</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 1072463,
          "author_name": "spicychicken38",
          "author_url": "",
          "post_date": "11/08/2020 09:07:33",
          "content": "<p>when we have predicted on the test set, have we actually predicted both the public and private test set?</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 1072487,
          "author_name": "ilu000",
          "author_url": "",
          "post_date": "11/08/2020 10:09:24",
          "content": "<blockquote>\n  <p>when we have predicted on the test set, have we actually predicted both the public and private test set?</p>\n</blockquote>\n<p>yes, test is both, public and private. If you predicted all Ids from the sample_submission you are good. Should be around 70k lines, iirc.</p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "1070622": "Hello everyone, for the final submission, do we only need submission.csv?\nSo we can train offline, prediction off, only use a few lines of codes like this:\n\nsub=pd.read_csv('/kaggle/input/private_submssion.csv')\nsub.to_csv('submission.csv',index=False)\n\nWe do not need to provide codes of cfg, pertained model, inference, etc. Right? \n\nThank you!",
    "1072274": "As for my understanding, we do need to provide a configure file and a pretrained model, and everything that you need to accomplish an integrated prediction on the test set because the final result is based on another 50% of the test set.",
    "1072423": "https://www.kaggle.com/c/lyft-motion-prediction-autonomous-vehicles/discussion/177414#1034502\nhere is the discussion about the final submission. \nFrom the host, everything can be offline. We need only to upload csv.\n\nVladimir IglovikovCompetition Host • a month ago • Options • Report • Reply\n\nkeyboard_arrow_up\n3\n\nkeyboard_arrow_down\nYou can do everything offline.\nYou can upload the csv to the inference kernel and that is it.\nIf you get into \"money\" we will need code that reproduces your submission from the data. But even in this case, until the end of the competition, you can submit csv's.\nAll submissions that are made now, count both for Public and for Private test sets, no additional work is required.",
    "1072463": "when we have predicted on the test set, have we actually predicted both the public and private test set?",
    "1072487": "> when we have predicted on the test set, have we actually predicted both the public and private test set?\n\nyes, test is both, public and private. If you predicted all Ids from the sample_submission you are good. Should be around 70k lines, iirc."
  },
  "source": "meta"
}