{
  "id": 71310,
  "title": "Kernel is died after loading train data.",
  "url": "/competitions/ga-customer-revenue-prediction/discussion/71310",
  "author_name": "",
  "post_date": "2018-11-12T14:08:35.810653500Z",
  "votes": -1,
  "comment_count": 4,
  "views": 0,
  "content": "<p>Each time I load train data(train_v2) my Kaggle notebook dying. Any suggestions? </p>",
  "messages": [
    {
      "id": "419752",
      "postDate": "11/12/2018 14:08:35",
      "content": "<p>Each time I load train data(train_v2) my Kaggle notebook dying. Any suggestions? </p>",
      "rawMarkdown": "Each time I load train data(train_v2) my Kaggle notebook dying. Any suggestions?",
      "votes": null
    },
    {
      "id": "419756",
      "postDate": "11/12/2018 14:17:55",
      "content": "<p>Hello Nandan,</p>\n\n<p>You probably run out of ram in your kernel. If you look at the top right of your kernel, in \"sessions\", you will see the ram available. If you get above 17.2 Gb RAM, then your kernel will die.</p>\n\n<p>In this competition, the train set is about 20gb and the test 7gb, which is above 17.2 gb ram. If you try to load the entier train set, you will exceed the available ram in the kernel, and it will die.</p>",
      "rawMarkdown": "Hello Nandan,\n\nYou probably run out of ram in your kernel. If you look at the top right of your kernel, in \"sessions\", you will see the ram available. If you get above 17.2 Gb RAM, then your kernel will die.\n\nIn this competition, the train set is about 20gb and the test 7gb, which is above 17.2 gb ram. If you try to load the entier train set, you will exceed the available ram in the kernel, and it will die.",
      "votes": null
    },
    {
      "id": "419765",
      "postDate": "11/12/2018 14:22:17",
      "content": "<p>Thank you Y Assous.\nAt this point I don't know what to do. I don't have GPU and my computer has just 8GB RAM. </p>",
      "rawMarkdown": "Thank you Y Assous.\nAt this point I don't know what to do. I don't have GPU and my computer has just 8GB RAM.",
      "votes": null
    },
    {
      "id": "419826",
      "postDate": "11/12/2018 15:53:38",
      "content": "<p>No need for GPU at this point.\nEither you reduce the number of columns you are importing (but you will lose information), or you use the 300$ on Google Cloud : <a href=\"https://cloud.google.com/blog/products/gcp/google-cloud-platform-for-data-scientists-using-jupyter-notebooks-with-apache-spark-on-google-cloud\">https://cloud.google.com/blog/products/gcp/google-cloud-platform-for-data-scientists-using-jupyter-notebooks-with-apache-spark-on-google-cloud</a></p>",
      "rawMarkdown": "No need for GPU at this point.\nEither you reduce the number of columns you are importing (but you will lose information), or you use the 300$ on Google Cloud : https://cloud.google.com/blog/products/gcp/google-cloud-platform-for-data-scientists-using-jupyter-notebooks-with-apache-spark-on-google-cloud",
      "votes": null
    },
    {
      "id": "419859",
      "postDate": "11/12/2018 16:39:47",
      "content": "<p>Go ahead </p>",
      "rawMarkdown": "Go ahead",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 419756,
      "author_name": "xtelima",
      "author_url": "",
      "post_date": "11/12/2018 14:17:55",
      "content": "<p>Hello Nandan,</p>\n\n<p>You probably run out of ram in your kernel. If you look at the top right of your kernel, in \"sessions\", you will see the ram available. If you get above 17.2 Gb RAM, then your kernel will die.</p>\n\n<p>In this competition, the train set is about 20gb and the test 7gb, which is above 17.2 gb ram. If you try to load the entier train set, you will exceed the available ram in the kernel, and it will die.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 419765,
      "author_name": "nandanlahurikar",
      "author_url": "",
      "post_date": "11/12/2018 14:22:17",
      "content": "<p>Thank you Y Assous.\nAt this point I don't know what to do. I don't have GPU and my computer has just 8GB RAM. </p>",
      "votes": null,
      "replies": [
        {
          "id": 419826,
          "author_name": "xtelima",
          "author_url": "",
          "post_date": "11/12/2018 15:53:38",
          "content": "<p>No need for GPU at this point.\nEither you reduce the number of columns you are importing (but you will lose information), or you use the 300$ on Google Cloud : <a href=\"https://cloud.google.com/blog/products/gcp/google-cloud-platform-for-data-scientists-using-jupyter-notebooks-with-apache-spark-on-google-cloud\">https://cloud.google.com/blog/products/gcp/google-cloud-platform-for-data-scientists-using-jupyter-notebooks-with-apache-spark-on-google-cloud</a></p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 419859,
      "author_name": "amuchand47",
      "author_url": "",
      "post_date": "11/12/2018 16:39:47",
      "content": "<p>Go ahead </p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "419752": "Each time I load train data(train_v2) my Kaggle notebook dying. Any suggestions?",
    "419756": "Hello Nandan,\n\nYou probably run out of ram in your kernel. If you look at the top right of your kernel, in \"sessions\", you will see the ram available. If you get above 17.2 Gb RAM, then your kernel will die.\n\nIn this competition, the train set is about 20gb and the test 7gb, which is above 17.2 gb ram. If you try to load the entier train set, you will exceed the available ram in the kernel, and it will die.",
    "419765": "Thank you Y Assous.\nAt this point I don't know what to do. I don't have GPU and my computer has just 8GB RAM.",
    "419826": "No need for GPU at this point.\nEither you reduce the number of columns you are importing (but you will lose information), or you use the 300$ on Google Cloud : https://cloud.google.com/blog/products/gcp/google-cloud-platform-for-data-scientists-using-jupyter-notebooks-with-apache-spark-on-google-cloud",
    "419859": "Go ahead"
  },
  "source": "meta"
}