{
  "fetched_at": "2026-10-19T23:29:39Z",
  "source_url": "https://www.kaggle.com/competitions/blueberry-regression-sentence/data",
  "pages": [
    {
      "name": "Evaluation",
      "content": "## Evaluation\n\nSubmissions will be evaluated using [Mean Absolute Error (MAE)](https://en.wikipedia.org/wiki/Mean_absolute_error),\n\n![MAE](https://raw.githubusercontent.com/visipedia/iwildcam_comp/master/assets/MAE.png)\n\nwhere each `x_i` represents the predicted target, `y_i` represents the ground truth, and `n` is the number of rows in the test set.\n\n## Submission File\nFor each `id` in the test set, you must predict the target `yield`. The file should contain a header and have the following format:\n\n    id,yield\n    15289,6025.194\n    15290,1256.223\n    15291,357.44\n    etc.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "This is a page where you can include rules that participants must accept before joining. You may wish to include rules like:\n\n - Don't cheat!\n - Apply yourself!\n - Have fun!\n- And think a lot!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "**NOTE:** You can now create your own synthetic versions of this dataset by forking and running [this notebook](https://www.kaggle.com/inversion/make-synthetic-blueberry-yield-data/).\n\nThe dataset for this competition (both train and test) was generated from a deep learning model trained on the [Wild blueberry Yield Prediction Dataset](https://www.kaggle.com/datasets/shashwatwork/wild-blueberry-yield-prediction-dataset). (Since this is Playground 3.14, it seems like we need a Blueberry Pie joke here?) Feature distributions are close to, but not exactly the same, as the original. Feel free to use the original dataset as part of this competition, both to explore differences as well as to see whether incorporating the original in training improves model performance.\n\n## Files\n\n*   **train.csv** - the training dataset; `yield` is the target\n*   **test.csv** - the test dataset; your objective is to predict the `yield` given the other features\n*   **sample_submission.csv** - a sample submission file in the correct format",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "**Welcome to the 2023 Kaggle Playground Series!** Thank you to everyone who participated in and contributed to Season 3 Playground Series so far! \n\n**Your Goal:** For this Episode of the Series, your task is to use regression to predict the yield of wild blueberries. Good luck!\n\n## NOTE:\n\nYou can now create your own synthetic versions of this dataset by forking and running [this notebook](https://www.kaggle.com/inversion/make-synthetic-blueberry-yield-data/).",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}