{
  "fetched_at": "2026-10-24T03:21:19Z",
  "source_url": "https://www.kaggle.com/competitions/exmachina-phase-2/data",
  "pages": [
    {
      "name": "data-description",
      "content": "## Files\n\n*   **train** - This folder contain all the graphs for training purpose.\n*   **test** - This folder contain all the graphs for testing purpose.\n*   **train__csv.csv** - csv file consist of expected output from images in train folder.\n\n## Columns\n\n*   `ID` - Name of image.\n*   `0, 1, 2, 3, ...` - Value of graph at respective point in x-axis in image",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "Please refer to the Data section to get some in-depth information about the dataset and download the dataset.\n\nAfter the conclusion of phase 1 final standings will be calculated by incorporating the following points :\n\nKaggle Leaderboard standings\nData Visualization and EDA.\nData Preprocessing and cleaning.\nNote: You have to submit your python notebooks which will be thoroughly analyzed for plagiarism. You can take inspiration from other publicly available models and add the reference.\n\nPlease read and follow the submission guidelines from the next section.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The evaluation section describes how submissions will be scored and how participants should format their submissions.\n\n---\n\nSubmissions are evaluated on Mean Absolute Percentage Error (MAPE).\n\n\n## Submission File\nFor each ID in the test set, you must predict the array of 187 elements. The file should contain a header and have the following format:\n\n    ID,0,1,2,3,....,186\n    2,0,0.85,0.001,0.5,....,0.1\n    5,0.1,0.22,0.002,0.3,....,0\n    6,0,0.2,0.66,1,....,0.67\n    etc.",
      "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
    },
    {
      "name": "abstract",
      "content": "**Problem Statement**: In the field of ECG analysis, data comes in two forms: numerical arrays representing voltage measurements and visual representations of electrical activity as graphs. However, for tasks like prediction and analysis, we can only utilize one format at a time. This challenge specifically addresses this conversion process. You'll be presented with a dataset containing thousands of ECG graphs. Your objective is to develop an algorithm that can accurately translate these graphs, each containing 187 corresponding voltage data points, into the desired numerical voltage arrays. In essence, you'll be building a system that bridges the gap between the visual representation of heart activity (the ECG graph) and the underlying numerical data critical for further analysis.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}