{
  "fetched_at": "2026-10-19T19:10:10Z",
  "source_url": "https://www.kaggle.com/competitions/aiandhealthcareminiproject1/data",
  "pages": [
    {
      "name": "data-description",
      "content": "## Files\n\n*   **test.csv** - the test set\n*   **kaggle_sample_target.csv** - a sample submission file in the correct format\n*   **participant_number.csv** - The participant numbers of the corresponding rows for the kaggle dataset. You can map both by matching the indexes.\n\n## Columns\n\nThe first column has the Id's, while the rest of the 360 columns have time series data points.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "This is the home page of the competition. The main objective is to do multi-class classification of the heart-beat type. We have the following classes of heartbeats present in the dataset :\nN: Normal beat\nL: Left bundle branch block beat\nR: Right bundle branch block beat\nA: Atrial premature beat\nV: Premature ventricular contraction\nU: All other types of beats should be classified as this\n\n \n## Acknowledgements\n\nWe thank George Moody and Roger Mark for providing this dataset at https://physionet.org/content/mitdb/1.0.0/.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The evaluation is done on the accuracy score. The kaggle.csv has got 9117 rows along with their Id's. The csv file you upload on kaggle should have 2 columns - Id, heartbeat_type. The 'Id' should map the corresponding row from kaggle.csv to it's prediction. The 'Predicted' column should have the binary prediction(0 or 1) in each row.\nIf you are using a dataframe, the following command shall be helpful in creating the output file correctly -\n`df.to_csv('kaggle_target.csv',index=False)`\n---\n\nPrecision is the ratio of true positives \\(\\text{tp}\\) to all predicted positives \\(\\text{tp} + \\text{fp}\\). Recall is the ratio of true positives \\(\\text{tp}\\) to all actual positives \\(\\text{tp} + \\text{fn}\\). The F1 score is given by:\n\n\\[ \\text{F1} = 2\\frac{\\text{p} \\cdot \\text{r}}{\\text{p}+\\text{r}}\\ \\ \\mathrm{where}\\ \\ \\text{p} = \\frac{\\text{tp}}{\\text{tp}+\\text{fp}},\\ \\ \\text{r} = \\frac{\\text{tp}}{\\text{tp}+\\text{fn}} \\]\n\nThe F1 metric weights recall and precision equally, and a good retrieval algorithm will maximize both precision and recall simultaneously. Thus, moderately good performance on both will be favored over extremely good performance on one and poor performance on the other.\n\n## Submission Format\n\n**For every author in the dataset**, submission files should contain two columns: `AuthorId` and `DuplicateAuthorIds`. `DuplicateAuthorIds` should be a space-delimited list. Every `AuthorId` counts as its own duplicate, and every duplicate should be listed under each of its respective ids. For example, if you suspect author A, B, and C are the same, you should list `A,A B C`, `B,B A C`, `C,C A B`.\n\n\nThe file should contain a header and have the following format:\n```\nAuthorId,DuplicateAuthorIds\n1,1\n```",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": " - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}