{
  "id": 205680,
  "title": "Unseen Questions In Test",
  "url": "/competitions/riiid-test-answer-prediction/discussion/205680",
  "author_name": "",
  "post_date": "2020-12-21T10:43:16.688281700Z",
  "votes": null,
  "comment_count": 1,
  "views": 0,
  "content": "<p>There is likely possibility of unseen questions in Test set. </p>\n<p><a href=\"https://www.kaggle.com/c/riiid-test-answer-prediction/discussion/205662\" target=\"_blank\">https://www.kaggle.com/c/riiid-test-answer-prediction/discussion/205662</a></p>\n<p>If i dont do left  join  between Test df  and questions , my submission is ending Sub Scoring Error. </p>\n<p>Is  any one also facing this is same issue ?</p>",
  "messages": [
    {
      "id": "1121065",
      "postDate": "12/21/2020 10:43:16",
      "content": "<p>There is likely possibility of unseen questions in Test set. </p>\n<p><a href=\"https://www.kaggle.com/c/riiid-test-answer-prediction/discussion/205662\" target=\"_blank\">https://www.kaggle.com/c/riiid-test-answer-prediction/discussion/205662</a></p>\n<p>If i dont do left  join  between Test df  and questions , my submission is ending Sub Scoring Error. </p>\n<p>Is  any one also facing this is same issue ?</p>",
      "rawMarkdown": "There is likely possibility of unseen questions in Test set. \n\nhttps://www.kaggle.com/c/riiid-test-answer-prediction/discussion/205662\n\nIf i dont do left  join  between Test df  and questions , my submission is ending Sub Scoring Error. \n\nIs  any one also facing this is same issue ?",
      "votes": null
    },
    {
      "id": "1121069",
      "postDate": "12/21/2020 10:48:03",
      "content": "<p><a href=\"https://www.kaggle.com/sohier\" target=\"_blank\">@sohier</a>  could you please throw some highlight on this. I know this is already dicussed in other forums but why do i see sub scoring error when i not do left join between Test df and Question df  to get  desired features related to question.</p>\n<p>Also i suspect Tag/Part for Test question also could be differring . <br>\nPlease help clarify</p>\n<pre><code>test_df = test_df[test_df.content_type_id == False]\n\n test_df=pd.merge(test_df,questions_df[['question_id','XXXXX']],\n                          left_on='content_id',right_on='question_id',copy=False) \n</code></pre>\n<p>above fails</p>\n<p>#but when i do merge with how=left</p>\n<h1>followed by XXX.isnull= Default value</h1>\n<p>it works</p>",
      "rawMarkdown": "sohier  could you please throw some highlight on this. I know this is already dicussed in other forums but why do i see sub scoring error when i not do left join between Test df and Question df  to get  desired features related to question.\n\nAlso i suspect Tag/Part for Test question also could be differring . \nPlease help clarify\n\n ```\ntest_df = test_df[test_df.content_type_id == False]\n        \n test_df=pd.merge(test_df,questions_df[['question_id','XXXXX']],\n                          left_on='content_id',right_on='question_id',copy=False) \n```\n\nabove fails\n\n #but when i do merge with how=left\n#followed by XXX.isnull= Default value \n\nit works",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1121069,
      "author_name": "jaideepvalani",
      "author_url": "",
      "post_date": "12/21/2020 10:48:03",
      "content": "<p><a href=\"https://www.kaggle.com/sohier\" target=\"_blank\">@sohier</a>  could you please throw some highlight on this. I know this is already dicussed in other forums but why do i see sub scoring error when i not do left join between Test df and Question df  to get  desired features related to question.</p>\n<p>Also i suspect Tag/Part for Test question also could be differring . <br>\nPlease help clarify</p>\n<pre><code>test_df = test_df[test_df.content_type_id == False]\n\n test_df=pd.merge(test_df,questions_df[['question_id','XXXXX']],\n                          left_on='content_id',right_on='question_id',copy=False) \n</code></pre>\n<p>above fails</p>\n<p>#but when i do merge with how=left</p>\n<h1>followed by XXX.isnull= Default value</h1>\n<p>it works</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1121065": "There is likely possibility of unseen questions in Test set. \n\nhttps://www.kaggle.com/c/riiid-test-answer-prediction/discussion/205662\n\nIf i dont do left  join  between Test df  and questions , my submission is ending Sub Scoring Error. \n\nIs  any one also facing this is same issue ?",
    "1121069": "sohier  could you please throw some highlight on this. I know this is already dicussed in other forums but why do i see sub scoring error when i not do left join between Test df and Question df  to get  desired features related to question.\n\nAlso i suspect Tag/Part for Test question also could be differring . \nPlease help clarify\n\n ```\ntest_df = test_df[test_df.content_type_id == False]\n        \n test_df=pd.merge(test_df,questions_df[['question_id','XXXXX']],\n                          left_on='content_id',right_on='question_id',copy=False) \n```\n\nabove fails\n\n #but when i do merge with how=left\n#followed by XXX.isnull= Default value \n\nit works"
  },
  "source": "meta"
}