{
  "id": 418804,
  "title": "Score blocked to 0.217",
  "url": "/competitions/predict-student-performance-from-game-play/discussion/418804",
  "author_name": "",
  "post_date": "2023-06-22T15:43:12.031354900Z",
  "votes": 1,
  "comment_count": 5,
  "views": 0,
  "content": "<p>Hi,</p>\n<p>I'm developing a cart tree model for the competition.</p>\n<p>I have changed various time the notebook but i'm still blocked to a score of 0.217</p>\n<p><img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F5088070%2Fc5746fe43d9668761c874f614a0f6997%2FCapture%20decran%202023-06-22%20a%2017.40.06.png?generation=1687448536584146&amp;alt=media\" alt=\"\"></p>\n<p>For the version 9, i have completely changed the data engineering part so i don't understand how i can still have the same score ?</p>\n<p><a href=\"https://www.kaggle.com/code/maximeperez/student-perf-cart-tree\" target=\"_blank\">Here is the notebook</a></p>",
  "messages": [
    {
      "id": "2313336",
      "postDate": "06/22/2023 15:43:12",
      "content": "<p>Hi,</p>\n<p>I'm developing a cart tree model for the competition.</p>\n<p>I have changed various time the notebook but i'm still blocked to a score of 0.217</p>\n<p><img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F5088070%2Fc5746fe43d9668761c874f614a0f6997%2FCapture%20decran%202023-06-22%20a%2017.40.06.png?generation=1687448536584146&amp;alt=media\" alt=\"\"></p>\n<p>For the version 9, i have completely changed the data engineering part so i don't understand how i can still have the same score ?</p>\n<p><a href=\"https://www.kaggle.com/code/maximeperez/student-perf-cart-tree\" target=\"_blank\">Here is the notebook</a></p>",
      "rawMarkdown": "Hi,\n\nI'm developing a cart tree model for the competition.\n\nI have changed various time the notebook but i'm still blocked to a score of 0.217\n\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F5088070%2Fc5746fe43d9668761c874f614a0f6997%2FCapture%20decran%202023-06-22%20a%2017.40.06.png?generation=1687448536584146&alt=media)\n\nFor the version 9, i have completely changed the data engineering part so i don't understand how i can still have the same score ?\n\n[Here is the notebook](https://www.kaggle.com/code/maximeperez/student-perf-cart-tree)",
      "votes": null
    },
    {
      "id": "2313409",
      "postDate": "06/22/2023 16:44:21",
      "content": "<p>My transformer was block at same score. I don't know why so i turn my model to catboost case.</p>",
      "rawMarkdown": "My transformer was block at same score. I don't know why so i turn my model to catboost case.",
      "votes": null
    },
    {
      "id": "2313427",
      "postDate": "06/22/2023 16:57:18",
      "content": "<p>Very strange</p>",
      "rawMarkdown": "Very strange",
      "votes": null
    },
    {
      "id": "2313508",
      "postDate": "06/22/2023 18:06:57",
      "content": "<pre><code>for (test, sample_submission)  iter_test:\n\n    #### add this ########################################################################\n    test = test.sort_values(by = )\n    sample_submission[] = sample_submission.session_id.apply(lambda x: x.split()[]).astype(int)\n    sample_submission = sample_submission.sort_values(by = )\n    sample_submission.drop(,axis=,inplace=)\n    ######################################################################################\n\n    X_clean = feature_engineer(test)\n\n    num_models = sample_submission.session_id.apply(lambda x: int(x.split()[])).to_list()\n\n\n    for i, num_model  enumerate(num_models):\n        sample_submission[][i] = models[num_model].predict(X_clean[FEATURES])\n\n    env.predict(sample_submission)\n</code></pre>",
      "rawMarkdown": "```\nfor (test, sample_submission) in iter_test:\n\n    #### add this ########################################################################\n    test = test.sort_values(by = 'index')\n    sample_submission['q'] = sample_submission.session_id.apply(lambda x: x.split(\"_q\")[1]).astype(int)\n    sample_submission = sample_submission.sort_values(by = 'q')\n    sample_submission.drop('q',axis=1,inplace=True)\n    ######################################################################################\n\n    X_clean = feature_engineer(test)\n    \n    num_models = sample_submission.session_id.apply(lambda x: int(x.split('_q')[1])).to_list()\n        \n    \n    for i, num_model in enumerate(num_models):\n        sample_submission['correct'][i] = models[num_model].predict(X_clean[FEATURES])\n    \n    env.predict(sample_submission)\n```",
      "votes": null
    },
    {
      "id": "2313676",
      "postDate": "06/22/2023 20:53:48",
      "content": "<p>I add your suggestion for my version 10, unfortunately it does not solved the problem</p>",
      "rawMarkdown": "I add your suggestion for my version 10, unfortunately it does not solved the problem",
      "votes": null
    },
    {
      "id": "2320713",
      "postDate": "06/28/2023 03:42:15",
      "content": "<p>Thank you i had the same problem and this code worked for me but why we did this?</p>",
      "rawMarkdown": "Thank you i had the same problem and this code worked for me but why we did this?",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 2313409,
      "author_name": "junhanzangai",
      "author_url": "",
      "post_date": "06/22/2023 16:44:21",
      "content": "<p>My transformer was block at same score. I don't know why so i turn my model to catboost case.</p>",
      "votes": null,
      "replies": [
        {
          "id": 2313427,
          "author_name": "maximeperez",
          "author_url": "",
          "post_date": "06/22/2023 16:57:18",
          "content": "<p>Very strange</p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 2313508,
      "author_name": "jimmyliao86204",
      "author_url": "",
      "post_date": "06/22/2023 18:06:57",
      "content": "<pre><code>for (test, sample_submission)  iter_test:\n\n    #### add this ########################################################################\n    test = test.sort_values(by = )\n    sample_submission[] = sample_submission.session_id.apply(lambda x: x.split()[]).astype(int)\n    sample_submission = sample_submission.sort_values(by = )\n    sample_submission.drop(,axis=,inplace=)\n    ######################################################################################\n\n    X_clean = feature_engineer(test)\n\n    num_models = sample_submission.session_id.apply(lambda x: int(x.split()[])).to_list()\n\n\n    for i, num_model  enumerate(num_models):\n        sample_submission[][i] = models[num_model].predict(X_clean[FEATURES])\n\n    env.predict(sample_submission)\n</code></pre>",
      "votes": null,
      "replies": [
        {
          "id": 2313676,
          "author_name": "maximeperez",
          "author_url": "",
          "post_date": "06/22/2023 20:53:48",
          "content": "<p>I add your suggestion for my version 10, unfortunately it does not solved the problem</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 2320713,
          "author_name": "mohamedbotaleb",
          "author_url": "",
          "post_date": "06/28/2023 03:42:15",
          "content": "<p>Thank you i had the same problem and this code worked for me but why we did this?</p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "2313336": "Hi,\n\nI'm developing a cart tree model for the competition.\n\nI have changed various time the notebook but i'm still blocked to a score of 0.217\n\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F5088070%2Fc5746fe43d9668761c874f614a0f6997%2FCapture%20decran%202023-06-22%20a%2017.40.06.png?generation=1687448536584146&alt=media)\n\nFor the version 9, i have completely changed the data engineering part so i don't understand how i can still have the same score ?\n\n[Here is the notebook](https://www.kaggle.com/code/maximeperez/student-perf-cart-tree)",
    "2313409": "My transformer was block at same score. I don't know why so i turn my model to catboost case.",
    "2313427": "Very strange",
    "2313508": "```\nfor (test, sample_submission) in iter_test:\n\n    #### add this ########################################################################\n    test = test.sort_values(by = 'index')\n    sample_submission['q'] = sample_submission.session_id.apply(lambda x: x.split(\"_q\")[1]).astype(int)\n    sample_submission = sample_submission.sort_values(by = 'q')\n    sample_submission.drop('q',axis=1,inplace=True)\n    ######################################################################################\n\n    X_clean = feature_engineer(test)\n    \n    num_models = sample_submission.session_id.apply(lambda x: int(x.split('_q')[1])).to_list()\n        \n    \n    for i, num_model in enumerate(num_models):\n        sample_submission['correct'][i] = models[num_model].predict(X_clean[FEATURES])\n    \n    env.predict(sample_submission)\n```",
    "2313676": "I add your suggestion for my version 10, unfortunately it does not solved the problem",
    "2320713": "Thank you i had the same problem and this code worked for me but why we did this?"
  },
  "source": "meta"
}