{
  "id": 113578,
  "title": "submissions",
  "url": "/competitions/ashrae-energy-prediction/discussion/113578",
  "author_name": "",
  "post_date": "2019-10-20T14:39:46.009949900Z",
  "votes": null,
  "comment_count": 5,
  "views": 0,
  "content": "<p>The only reason have not made submissions is the size of my submission freaking 1gigabyte lol when buying data is expensive here in my country.</p>",
  "messages": [
    {
      "id": "653485",
      "postDate": "10/20/2019 14:39:46",
      "content": "<p>The only reason have not made submissions is the size of my submission freaking 1gigabyte lol when buying data is expensive here in my country.</p>",
      "rawMarkdown": "The only reason have not made submissions is the size of my submission freaking 1gigabyte lol when buying data is expensive here in my country.",
      "votes": null
    },
    {
      "id": "653584",
      "postDate": "10/20/2019 17:18:29",
      "content": "<p>You can get them down to only 3/4 of GB by dropping precision to 4 decimals - as noted in the overview Kaggle using only 4.   I use this -</p>\n\n<p>```</p>\n\n<h1>need to format the res to only 4 decimals to reduce memory - kaggle evaluation only to 4 digets</h1>\n\n<p>res = np.round_(res, decimals=4, out=None)\n```</p>\n\n<p>Kaggle will also accept compressed files - zipped my 3/4GB gets to much more data friendly 0.16GB</p>\n\n<blockquote>\n  \n</blockquote>\n\n<p>File Format\nYour submission should be in CSV format. You can upload this in a zip/gz/rar/7z archive, if you prefer.&gt; </p>",
      "rawMarkdown": "You can get them down to only 3/4 of GB by dropping precision to 4 decimals - as noted in the overview Kaggle using only 4.   I use this -\n\n```\n# need to format the res to only 4 decimals to reduce memory - kaggle evaluation only to 4 digets\nres = np.round_(res, decimals=4, out=None)\n```\n\nKaggle will also accept compressed files - zipped my 3/4GB gets to much more data friendly 0.16GB\n\n\n&gt; \n\nFile Format\nYour submission should be in CSV format. You can upload this in a zip/gz/rar/7z archive, if you prefer.&gt;",
      "votes": null
    },
    {
      "id": "653627",
      "postDate": "10/20/2019 18:17:16",
      "content": "<p>Silly question but where does it say that only 4 decimals are used?</p>",
      "rawMarkdown": "Silly question but where does it say that only 4 decimals are used?",
      "votes": null
    },
    {
      "id": "653629",
      "postDate": "10/20/2019 18:21:44",
      "content": "<p>https://www.kaggle.com/c/ashrae-energy-prediction/data</p>\n\n<p>sample_submission.csv \nA valid sample submission.\nAll floats in the solution file were truncated to four decimal places; we recommend you do the same to save space on your file upload.\nThere are gaps in some of the meter readings for both the train and test sets. Gaps in the test set are not revealed or scored.</p>",
      "rawMarkdown": "[https://www.kaggle.com/c/ashrae-energy-prediction/data]()\n\nsample_submission.csv \nA valid sample submission.\nAll floats in the solution file were truncated to four decimal places; we recommend you do the same to save space on your file upload.\nThere are gaps in some of the meter readings for both the train and test sets. Gaps in the test set are not revealed or scored.",
      "votes": null
    },
    {
      "id": "653630",
      "postDate": "10/20/2019 18:22:41",
      "content": "<p>Got to read the fine print :)</p>",
      "rawMarkdown": "Got to read the fine print :)",
      "votes": null
    },
    {
      "id": "659686",
      "postDate": "10/28/2019 04:48:28",
      "content": "<p>bro <code>.zip</code> the balls off file first before uploading </p>",
      "rawMarkdown": "bro `.zip` the balls off file first before uploading",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 653584,
      "author_name": "pcjimmmy",
      "author_url": "",
      "post_date": "10/20/2019 17:18:29",
      "content": "<p>You can get them down to only 3/4 of GB by dropping precision to 4 decimals - as noted in the overview Kaggle using only 4.   I use this -</p>\n\n<p>```</p>\n\n<h1>need to format the res to only 4 decimals to reduce memory - kaggle evaluation only to 4 digets</h1>\n\n<p>res = np.round_(res, decimals=4, out=None)\n```</p>\n\n<p>Kaggle will also accept compressed files - zipped my 3/4GB gets to much more data friendly 0.16GB</p>\n\n<blockquote>\n  \n</blockquote>\n\n<p>File Format\nYour submission should be in CSV format. You can upload this in a zip/gz/rar/7z archive, if you prefer.&gt; </p>",
      "votes": null,
      "replies": [
        {
          "id": 653627,
          "author_name": "maxhalford",
          "author_url": "",
          "post_date": "10/20/2019 18:17:16",
          "content": "<p>Silly question but where does it say that only 4 decimals are used?</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 653629,
          "author_name": "pcjimmmy",
          "author_url": "",
          "post_date": "10/20/2019 18:21:44",
          "content": "<p>https://www.kaggle.com/c/ashrae-energy-prediction/data</p>\n\n<p>sample_submission.csv \nA valid sample submission.\nAll floats in the solution file were truncated to four decimal places; we recommend you do the same to save space on your file upload.\nThere are gaps in some of the meter readings for both the train and test sets. Gaps in the test set are not revealed or scored.</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 653630,
          "author_name": "pcjimmmy",
          "author_url": "",
          "post_date": "10/20/2019 18:22:41",
          "content": "<p>Got to read the fine print :)</p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 659686,
      "author_name": "lewington",
      "author_url": "",
      "post_date": "10/28/2019 04:48:28",
      "content": "<p>bro <code>.zip</code> the balls off file first before uploading </p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "653485": "The only reason have not made submissions is the size of my submission freaking 1gigabyte lol when buying data is expensive here in my country.",
    "653584": "You can get them down to only 3/4 of GB by dropping precision to 4 decimals - as noted in the overview Kaggle using only 4.   I use this -\n\n```\n# need to format the res to only 4 decimals to reduce memory - kaggle evaluation only to 4 digets\nres = np.round_(res, decimals=4, out=None)\n```\n\nKaggle will also accept compressed files - zipped my 3/4GB gets to much more data friendly 0.16GB\n\n\n&gt; \n\nFile Format\nYour submission should be in CSV format. You can upload this in a zip/gz/rar/7z archive, if you prefer.&gt;",
    "653627": "Silly question but where does it say that only 4 decimals are used?",
    "653629": "[https://www.kaggle.com/c/ashrae-energy-prediction/data]()\n\nsample_submission.csv \nA valid sample submission.\nAll floats in the solution file were truncated to four decimal places; we recommend you do the same to save space on your file upload.\nThere are gaps in some of the meter readings for both the train and test sets. Gaps in the test set are not revealed or scored.",
    "653630": "Got to read the fine print :)",
    "659686": "bro `.zip` the balls off file first before uploading"
  },
  "source": "meta"
}