{
  "id": 393642,
  "title": "Why am I getting submission scoring error?",
  "url": "/competitions/predict-student-performance-from-game-play/discussion/393642",
  "author_name": "",
  "post_date": "2023-03-10T08:44:55.756960100Z",
  "votes": 1,
  "comment_count": 4,
  "views": 0,
  "content": "<p>Hi! Can someone explain why I am getting a <code>Submission Scoring Error</code> in the notebook? <br>\n<a href=\"https://www.kaggle.com/code/pritamsinha23/student-performance-from-gameplay-v1-inference\" target=\"_blank\">notebook</a></p>",
  "messages": [
    {
      "id": "2175900",
      "postDate": "03/10/2023 08:44:55",
      "content": "<p>Hi! Can someone explain why I am getting a <code>Submission Scoring Error</code> in the notebook? <br>\n<a href=\"https://www.kaggle.com/code/pritamsinha23/student-performance-from-gameplay-v1-inference\" target=\"_blank\">notebook</a></p>",
      "rawMarkdown": "Hi! Can someone explain why I am getting a `Submission Scoring Error` in the notebook? \n[notebook](https://www.kaggle.com/code/pritamsinha23/student-performance-from-gameplay-v1-inference)",
      "votes": null
    },
    {
      "id": "2175967",
      "postDate": "03/10/2023 09:39:08",
      "content": "<p>The link to your notebook is not working for me, it shows a blank page. </p>\n<p>I had this error however and for me it seemed to be related to too much memory usage. I was saving features between iterations in the test loop for later reusage, and when i saved fewer the problem was solved. </p>",
      "rawMarkdown": "The link to your notebook is not working for me, it shows a blank page. \n\nI had this error however and for me it seemed to be related to too much memory usage. I was saving features between iterations in the test loop for later reusage, and when i saved fewer the problem was solved.",
      "votes": null
    },
    {
      "id": "2175983",
      "postDate": "03/10/2023 09:52:34",
      "content": "<p>Thanks for the reply. You said \"I was saving features between iterations in the test loop for later re-usage\", do you that piece of code? How are you doing this? Can you share? Only that part will do fine. Thanks.</p>",
      "rawMarkdown": "Thanks for the reply. You said \"I was saving features between iterations in the test loop for later re-usage\", do you that piece of code? How are you doing this? Can you share? Only that part will do fine. Thanks.",
      "votes": null
    },
    {
      "id": "2176044",
      "postDate": "03/10/2023 11:00:06",
      "content": "<p>No worries. Right now it looks like this. I am saving the dataframes from earlier groups in a dictionary with the session_id as key. Actually doing it before feature engineering here so i can create combined features </p>\n<pre><code>dfs = {}\n (sample_submission, test)  iter_test:\n    grp = test.level_group.values[]\n\n    df = (pl.from_pandas(test)\n      .drop([, , ])\n      .with_columns(columns))\n\n    sess_id = df[][]\n     grp == :\n        dfs[sess_id] = df\n     grp == :\n        df = pl.concat([dfs[sess_id], df])\n        dfs[sess_id] = df\n    :\n        df = pl.concat([dfs[sess_id], df])\n\n    df = feature_engineer(df, grp)\n</code></pre>",
      "rawMarkdown": "No worries. Right now it looks like this. I am saving the dataframes from earlier groups in a dictionary with the session_id as key. Actually doing it before feature engineering here so i can create combined features \n\n```python\n\ndfs = {}\nfor (sample_submission, test) in iter_test:\n    grp = test.level_group.values[0]\n    \n    df = (pl.from_pandas(test)\n      .drop([\"fullscreen\", \"hq\", \"music\"])\n      .with_columns(columns))\n\n    sess_id = df[\"session_id\"][0]\n    if grp == \"0-4\":\n        dfs[sess_id] = df\n    elif grp == \"5-12\":\n        df = pl.concat([dfs[sess_id], df])\n        dfs[sess_id] = df\n    else:\n        df = pl.concat([dfs[sess_id], df])\n    \n    df = feature_engineer(df, grp)\n```",
      "votes": null
    },
    {
      "id": "2176423",
      "postDate": "03/10/2023 16:33:41",
      "content": "<p>Hi! Thanks for the code snippet. I have a question, why you are concatenating the previous level group? And can you look into my code and see what is wrong? I am continuously getting submission scoring error.<br>\n<a href=\"https://www.kaggle.com/code/pritamsinha23/student-performance-from-gameplay-v1-inference\" target=\"_blank\">notebook</a></p>",
      "rawMarkdown": "Hi! Thanks for the code snippet. I have a question, why you are concatenating the previous level group? And can you look into my code and see what is wrong? I am continuously getting submission scoring error.\n[notebook](https://www.kaggle.com/code/pritamsinha23/student-performance-from-gameplay-v1-inference)",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 2175967,
      "author_name": "erijoel",
      "author_url": "",
      "post_date": "03/10/2023 09:39:08",
      "content": "<p>The link to your notebook is not working for me, it shows a blank page. </p>\n<p>I had this error however and for me it seemed to be related to too much memory usage. I was saving features between iterations in the test loop for later reusage, and when i saved fewer the problem was solved. </p>",
      "votes": null,
      "replies": [
        {
          "id": 2175983,
          "author_name": "pritamsinha23",
          "author_url": "",
          "post_date": "03/10/2023 09:52:34",
          "content": "<p>Thanks for the reply. You said \"I was saving features between iterations in the test loop for later re-usage\", do you that piece of code? How are you doing this? Can you share? Only that part will do fine. Thanks.</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 2176044,
          "author_name": "erijoel",
          "author_url": "",
          "post_date": "03/10/2023 11:00:06",
          "content": "<p>No worries. Right now it looks like this. I am saving the dataframes from earlier groups in a dictionary with the session_id as key. Actually doing it before feature engineering here so i can create combined features </p>\n<pre><code>dfs = {}\n (sample_submission, test)  iter_test:\n    grp = test.level_group.values[]\n\n    df = (pl.from_pandas(test)\n      .drop([, , ])\n      .with_columns(columns))\n\n    sess_id = df[][]\n     grp == :\n        dfs[sess_id] = df\n     grp == :\n        df = pl.concat([dfs[sess_id], df])\n        dfs[sess_id] = df\n    :\n        df = pl.concat([dfs[sess_id], df])\n\n    df = feature_engineer(df, grp)\n</code></pre>",
          "votes": null,
          "replies": [
            {
              "id": 2176423,
              "author_name": "pritamsinha23",
              "author_url": "",
              "post_date": "03/10/2023 16:33:41",
              "content": "<p>Hi! Thanks for the code snippet. I have a question, why you are concatenating the previous level group? And can you look into my code and see what is wrong? I am continuously getting submission scoring error.<br>\n<a href=\"https://www.kaggle.com/code/pritamsinha23/student-performance-from-gameplay-v1-inference\" target=\"_blank\">notebook</a></p>",
              "votes": null,
              "replies": []
            }
          ]
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "2175900": "Hi! Can someone explain why I am getting a `Submission Scoring Error` in the notebook? \n[notebook](https://www.kaggle.com/code/pritamsinha23/student-performance-from-gameplay-v1-inference)",
    "2175967": "The link to your notebook is not working for me, it shows a blank page. \n\nI had this error however and for me it seemed to be related to too much memory usage. I was saving features between iterations in the test loop for later reusage, and when i saved fewer the problem was solved.",
    "2175983": "Thanks for the reply. You said \"I was saving features between iterations in the test loop for later re-usage\", do you that piece of code? How are you doing this? Can you share? Only that part will do fine. Thanks.",
    "2176044": "No worries. Right now it looks like this. I am saving the dataframes from earlier groups in a dictionary with the session_id as key. Actually doing it before feature engineering here so i can create combined features \n\n```python\n\ndfs = {}\nfor (sample_submission, test) in iter_test:\n    grp = test.level_group.values[0]\n    \n    df = (pl.from_pandas(test)\n      .drop([\"fullscreen\", \"hq\", \"music\"])\n      .with_columns(columns))\n\n    sess_id = df[\"session_id\"][0]\n    if grp == \"0-4\":\n        dfs[sess_id] = df\n    elif grp == \"5-12\":\n        df = pl.concat([dfs[sess_id], df])\n        dfs[sess_id] = df\n    else:\n        df = pl.concat([dfs[sess_id], df])\n    \n    df = feature_engineer(df, grp)\n```",
    "2176423": "Hi! Thanks for the code snippet. I have a question, why you are concatenating the previous level group? And can you look into my code and see what is wrong? I am continuously getting submission scoring error.\n[notebook](https://www.kaggle.com/code/pritamsinha23/student-performance-from-gameplay-v1-inference)"
  },
  "source": "meta"
}