{
  "id": 427046,
  "title": "why I use a quick saving trick fail",
  "url": "/competitions/cafa-5-protein-function-prediction/discussion/427046",
  "author_name": "",
  "post_date": "2023-07-26T08:45:19.469902900Z",
  "votes": 1,
  "comment_count": 5,
  "views": 0,
  "content": "<p>I add a quick saving block:<br>\n<code>test_sequences = SeqIO.parse(test_fasta_path, \"fasta\")</code><br>\n<code>test_sequence_df = pd.DataFrame([{\"id\": s.id, \"seq\": str(s.seq)} for s in test_sequences])</code><br>\n<code>if test_sequence_df.shape[0] == 141865:\n     test_sequence_df = test_sequence_df[:100]</code><br>\nwhen I submit it, the notebook threw exception </p>",
  "messages": [
    {
      "id": "2359575",
      "postDate": "07/26/2023 08:45:19",
      "content": "<p>I add a quick saving block:<br>\n<code>test_sequences = SeqIO.parse(test_fasta_path, \"fasta\")</code><br>\n<code>test_sequence_df = pd.DataFrame([{\"id\": s.id, \"seq\": str(s.seq)} for s in test_sequences])</code><br>\n<code>if test_sequence_df.shape[0] == 141865:\n     test_sequence_df = test_sequence_df[:100]</code><br>\nwhen I submit it, the notebook threw exception </p>",
      "rawMarkdown": "I add a quick saving block:\n`test_sequences = SeqIO.parse(test_fasta_path, \"fasta\")`\n`test_sequence_df = pd.DataFrame([{\"id\": s.id, \"seq\": str(s.seq)} for s in test_sequences])`\n`if test_sequence_df.shape[0] == 141865:\n     test_sequence_df = test_sequence_df[:100]`\nwhen I submit it, the notebook threw exception",
      "votes": null
    },
    {
      "id": "2359616",
      "postDate": "07/26/2023 09:25:51",
      "content": "<p>If I get it right, you are saving/submitting the first 100 predictions. However, if your sub does not contains the proteins in the LB, it will fail.</p>",
      "rawMarkdown": "If I get it right, you are saving/submitting the first 100 predictions. However, if your sub does not contains the proteins in the LB, it will fail.",
      "votes": null
    },
    {
      "id": "2359624",
      "postDate": "07/26/2023 09:29:27",
      "content": "<p>If I understand correctly, the number of test samples will change when submitting, so the condition of taking the top 100 samples will no longer apply.</p>",
      "rawMarkdown": "If I understand correctly, the number of test samples will change when submitting, so the condition of taking the top 100 samples will no longer apply.",
      "votes": null
    },
    {
      "id": "2359717",
      "postDate": "07/26/2023 10:51:09",
      "content": "<p>No, this is not a real code competition - you can calculate <code>submission.csv</code> locally, attach it to a notebook, submit, and it will be scored. There is no private set here, we're given the entire test superset and need to submit all predictions. </p>",
      "rawMarkdown": "No, this is not a real code competition - you can calculate `submission.csv` locally, attach it to a notebook, submit, and it will be scored. There is no private set here, we're given the entire test superset and need to submit all predictions.",
      "votes": null
    },
    {
      "id": "2359767",
      "postDate": "07/26/2023 11:12:34",
      "content": "<p>I may have miss something. Where does host say so?</p>",
      "rawMarkdown": "I may have miss something. Where does host say so?",
      "votes": null
    },
    {
      "id": "2359798",
      "postDate": "07/26/2023 11:28:51",
      "content": "<p>I think I see it. Amazing. I can inference locally.  Thanks</p>",
      "rawMarkdown": "I think I see it. Amazing. I can inference locally.  Thanks",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 2359616,
      "author_name": "mtinti",
      "author_url": "",
      "post_date": "07/26/2023 09:25:51",
      "content": "<p>If I get it right, you are saving/submitting the first 100 predictions. However, if your sub does not contains the proteins in the LB, it will fail.</p>",
      "votes": null,
      "replies": [
        {
          "id": 2359624,
          "author_name": "daishu",
          "author_url": "",
          "post_date": "07/26/2023 09:29:27",
          "content": "<p>If I understand correctly, the number of test samples will change when submitting, so the condition of taking the top 100 samples will no longer apply.</p>",
          "votes": null,
          "replies": [
            {
              "id": 2359717,
              "author_name": "thedrcat",
              "author_url": "",
              "post_date": "07/26/2023 10:51:09",
              "content": "<p>No, this is not a real code competition - you can calculate <code>submission.csv</code> locally, attach it to a notebook, submit, and it will be scored. There is no private set here, we're given the entire test superset and need to submit all predictions. </p>",
              "votes": null,
              "replies": [
                {
                  "id": 2359767,
                  "author_name": "daishu",
                  "author_url": "",
                  "post_date": "07/26/2023 11:12:34",
                  "content": "<p>I may have miss something. Where does host say so?</p>",
                  "votes": null,
                  "replies": []
                },
                {
                  "id": 2359798,
                  "author_name": "daishu",
                  "author_url": "",
                  "post_date": "07/26/2023 11:28:51",
                  "content": "<p>I think I see it. Amazing. I can inference locally.  Thanks</p>",
                  "votes": null,
                  "replies": []
                }
              ]
            }
          ]
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "2359575": "I add a quick saving block:\n`test_sequences = SeqIO.parse(test_fasta_path, \"fasta\")`\n`test_sequence_df = pd.DataFrame([{\"id\": s.id, \"seq\": str(s.seq)} for s in test_sequences])`\n`if test_sequence_df.shape[0] == 141865:\n     test_sequence_df = test_sequence_df[:100]`\nwhen I submit it, the notebook threw exception",
    "2359616": "If I get it right, you are saving/submitting the first 100 predictions. However, if your sub does not contains the proteins in the LB, it will fail.",
    "2359624": "If I understand correctly, the number of test samples will change when submitting, so the condition of taking the top 100 samples will no longer apply.",
    "2359717": "No, this is not a real code competition - you can calculate `submission.csv` locally, attach it to a notebook, submit, and it will be scored. There is no private set here, we're given the entire test superset and need to submit all predictions.",
    "2359767": "I may have miss something. Where does host say so?",
    "2359798": "I think I see it. Amazing. I can inference locally.  Thanks"
  },
  "source": "meta"
}