{
  "id": 402051,
  "title": "How many test files? Unlabelled? or just test folder?",
  "url": "/competitions/tlvmc-parkinsons-freezing-gait-prediction/discussion/402051",
  "author_name": "",
  "post_date": "2023-04-16T15:22:58.243981700Z",
  "votes": 1,
  "comment_count": 2,
  "views": 0,
  "content": "<p>Hello,<br>\n  I am wondering when generating submission file, where to get the right test input data? For test folder, I can only see one file under tdcsfog and defog separately, shall I use parquet files under unlabeled folder to generate output to be included in the submission.csv as well?</p>\n<p>Currently, I use the below two to list all test csv files, but when I submit notebook, I find only 1 file under each directory…. Is this correct? Shall I expect more files under these two directories when submitting notebook?</p>\n<p>defog_test_root = '/kaggle/input/tlvmc-parkinsons-freezing-gait-prediction/test/defog/'<br>\ntdcsfog_test_root = '/kaggle/input/tlvmc-parkinsons-freezing-gait-prediction/test/tdcsfog/'</p>\n<p>tdcsfog_test_names = os.listdir(tdcsfog_test_root)<br>\nprint(\"tdcsfog_test_names:\",tdcsfog_test_names)<br>\ntdcsfog_test_names: ['003f117e14.csv']</p>\n<p>defog_test_names = os.listdir(defog_test_root)<br>\nprint(\"defog_test_names:\",defog_test_names)<br>\ndefog_test_names: ['02ab235146.csv']</p>",
  "messages": [
    {
      "id": "2223749",
      "postDate": "04/16/2023 15:22:58",
      "content": "<p>Hello,<br>\n  I am wondering when generating submission file, where to get the right test input data? For test folder, I can only see one file under tdcsfog and defog separately, shall I use parquet files under unlabeled folder to generate output to be included in the submission.csv as well?</p>\n<p>Currently, I use the below two to list all test csv files, but when I submit notebook, I find only 1 file under each directory…. Is this correct? Shall I expect more files under these two directories when submitting notebook?</p>\n<p>defog_test_root = '/kaggle/input/tlvmc-parkinsons-freezing-gait-prediction/test/defog/'<br>\ntdcsfog_test_root = '/kaggle/input/tlvmc-parkinsons-freezing-gait-prediction/test/tdcsfog/'</p>\n<p>tdcsfog_test_names = os.listdir(tdcsfog_test_root)<br>\nprint(\"tdcsfog_test_names:\",tdcsfog_test_names)<br>\ntdcsfog_test_names: ['003f117e14.csv']</p>\n<p>defog_test_names = os.listdir(defog_test_root)<br>\nprint(\"defog_test_names:\",defog_test_names)<br>\ndefog_test_names: ['02ab235146.csv']</p>",
      "rawMarkdown": "Hello,\n  I am wondering when generating submission file, where to get the right test input data? For test folder, I can only see one file under tdcsfog and defog separately, shall I use parquet files under unlabeled folder to generate output to be included in the submission.csv as well?\n\nCurrently, I use the below two to list all test csv files, but when I submit notebook, I find only 1 file under each directory.... Is this correct? Shall I expect more files under these two directories when submitting notebook?\n\ndefog_test_root = '/kaggle/input/tlvmc-parkinsons-freezing-gait-prediction/test/defog/'\ntdcsfog_test_root = '/kaggle/input/tlvmc-parkinsons-freezing-gait-prediction/test/tdcsfog/'\n\n\ntdcsfog_test_names = os.listdir(tdcsfog_test_root)\nprint(\"tdcsfog_test_names:\",tdcsfog_test_names)\ntdcsfog_test_names: ['003f117e14.csv']\n\n\ndefog_test_names = os.listdir(defog_test_root)\nprint(\"defog_test_names:\",defog_test_names)\ndefog_test_names: ['02ab235146.csv']",
      "votes": null
    },
    {
      "id": "2223789",
      "postDate": "04/16/2023 16:07:21",
      "content": "<p>Hi, there are some hidden files for evaluating the code, we should assume that there are other files with the same format as we see in the two csvs. when code is being evaluated, some hidden files will be added to the test folders</p>",
      "rawMarkdown": "Hi, there are some hidden files for evaluating the code, we should assume that there are other files with the same format as we see in the two csvs. when code is being evaluated, some hidden files will be added to the test folders",
      "votes": null
    },
    {
      "id": "2226374",
      "postDate": "04/18/2023 21:43:32",
      "content": "<p>Keep in mind that when submitting code or models for evaluation, there may be more files included in the test folders during the private evaulations.</p>\n<p>These hidden files should have the same format as the provided CSVs, and they're used by Kaggle to confirm that your code is generating predictions correctly on new unseen data.</p>\n<p>It's a good practice to include code in your submission that checks for any additional files in the test folder and incorporates them into your data pipeline if needed.</p>\n<p>This will help ensure that your code can handle unseen data properly and generate accurate predictions even on new data points.</p>\n<p>Make sure to check the competition rules and guidelines before submitting to make sure you understand how the evaluation process works and any specific requirements for handling unseen data.</p>\n<p>The Devastator.</p>",
      "rawMarkdown": "Keep in mind that when submitting code or models for evaluation, there may be more files included in the test folders during the private evaulations.\n\nThese hidden files should have the same format as the provided CSVs, and they're used by Kaggle to confirm that your code is generating predictions correctly on new unseen data.\n\nIt's a good practice to include code in your submission that checks for any additional files in the test folder and incorporates them into your data pipeline if needed.\n\nThis will help ensure that your code can handle unseen data properly and generate accurate predictions even on new data points.\n\nMake sure to check the competition rules and guidelines before submitting to make sure you understand how the evaluation process works and any specific requirements for handling unseen data.\n\n\nThe Devastator.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 2223789,
      "author_name": "irajahangari",
      "author_url": "",
      "post_date": "04/16/2023 16:07:21",
      "content": "<p>Hi, there are some hidden files for evaluating the code, we should assume that there are other files with the same format as we see in the two csvs. when code is being evaluated, some hidden files will be added to the test folders</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 2226374,
      "author_name": "thedevastator",
      "author_url": "",
      "post_date": "04/18/2023 21:43:32",
      "content": "<p>Keep in mind that when submitting code or models for evaluation, there may be more files included in the test folders during the private evaulations.</p>\n<p>These hidden files should have the same format as the provided CSVs, and they're used by Kaggle to confirm that your code is generating predictions correctly on new unseen data.</p>\n<p>It's a good practice to include code in your submission that checks for any additional files in the test folder and incorporates them into your data pipeline if needed.</p>\n<p>This will help ensure that your code can handle unseen data properly and generate accurate predictions even on new data points.</p>\n<p>Make sure to check the competition rules and guidelines before submitting to make sure you understand how the evaluation process works and any specific requirements for handling unseen data.</p>\n<p>The Devastator.</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "2223749": "Hello,\n  I am wondering when generating submission file, where to get the right test input data? For test folder, I can only see one file under tdcsfog and defog separately, shall I use parquet files under unlabeled folder to generate output to be included in the submission.csv as well?\n\nCurrently, I use the below two to list all test csv files, but when I submit notebook, I find only 1 file under each directory.... Is this correct? Shall I expect more files under these two directories when submitting notebook?\n\ndefog_test_root = '/kaggle/input/tlvmc-parkinsons-freezing-gait-prediction/test/defog/'\ntdcsfog_test_root = '/kaggle/input/tlvmc-parkinsons-freezing-gait-prediction/test/tdcsfog/'\n\n\ntdcsfog_test_names = os.listdir(tdcsfog_test_root)\nprint(\"tdcsfog_test_names:\",tdcsfog_test_names)\ntdcsfog_test_names: ['003f117e14.csv']\n\n\ndefog_test_names = os.listdir(defog_test_root)\nprint(\"defog_test_names:\",defog_test_names)\ndefog_test_names: ['02ab235146.csv']",
    "2223789": "Hi, there are some hidden files for evaluating the code, we should assume that there are other files with the same format as we see in the two csvs. when code is being evaluated, some hidden files will be added to the test folders",
    "2226374": "Keep in mind that when submitting code or models for evaluation, there may be more files included in the test folders during the private evaulations.\n\nThese hidden files should have the same format as the provided CSVs, and they're used by Kaggle to confirm that your code is generating predictions correctly on new unseen data.\n\nIt's a good practice to include code in your submission that checks for any additional files in the test folder and incorporates them into your data pipeline if needed.\n\nThis will help ensure that your code can handle unseen data properly and generate accurate predictions even on new data points.\n\nMake sure to check the competition rules and guidelines before submitting to make sure you understand how the evaluation process works and any specific requirements for handling unseen data.\n\n\nThe Devastator."
  },
  "source": "meta"
}