{
  "fetched_at": "2026-10-19T22:28:37Z",
  "source_url": "https://www.kaggle.com/competitions/accelerometer-gesture-classification/data",
  "pages": [
    {
      "name": "data-description",
      "content": "## Files\n\n*   **train.csv** - the training set\n*   **test.csv** - the test set\n*   **sample_submission.csv** - a sample submission file in the correct format\n\n## Columns\n\n*   `id` - Identifying value for each gesture attempt.\n* `user` - Zero-based user ID value.\n* `gesture` - Zero-based gesture ID value. \n* `x` - X-axis accelerometer data for the gesture attempt.\n* `y` - Y-axis accelerometer data for the gesture attempt.\n* `z` - Z-axis accelerometer data for the gesture attempt.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "# Classifying Hand Gestures Using Accelerometer Data for CSCE/BMEN 5280\n\n## Overview\nWe have a dataset of accelerometer data from 8 users performing 20 gestures (approximately) 20 times each for a total of 3,251 gesture attempts. The gestures and their labels are shown in the image below. Note that in the aggregated dataset provided in this competition, the gestures are instead zero-based.\n\n![Gesture images and labels](https://tev.fbk.eu/sites/tev.fbk.eu/files/gestures_0.png)\n\n## Data\nIn this competition, the data is provided in a test and train dataset as two CSV files (`train.csv` and `test.csv`). These files are ready for import as pandas DataFrames. Both files contain the gesture ID (`id`); the user ID (`user`); and the x, y, and z accelerometer vectors for the entire gesture (`x`, `y`, and `z`). The train data file also includes the gesture label (`gesture`). The accelerometer data has been scaled using the Scikit Learn StandardScaler. The `x`, `y`, and `z` cell in each row contains a list. To properly read the lists in when opening the DataFrame, use `literal_eval` from the built-in package `ast` in the converter option of the pandas `read_csv` function. \n\nThe rows in both data files have been pre-shuffled so that the gesture IDs can not be inferred from the order of the test data.\n\n## Submission\nTo generate a submission, train your model on the `train.csv` data and generate a prediction on the `test.csv` data. The submission file should be a CSV with two columns: `id` and `gesture`. The `id` should match the values from the test data and the `gesture` value should be the zero-based gesture prediction from the test data.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The evaluation metric for this competition is [Mean F1-Score](https://en.wikipedia.org/wiki/F-score). The F1 score, commonly used in information retrieval, measures accuracy using the statistics precision \\( \\text{p} \\) and recall \\( \\text{r} \\).\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\nSubmission files should be CSVs with two columns: `id` and `gesture`. The `id` corresponds to the gestures in the `test.csv` testing dataset. The `gesture` is the predicted gesture label for the gesture attempt.\n\n\nThe file should contain a header and have the following format:\n```\nid,gesture\n0,0\n1,0\n```",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}