{
  "id": 416888,
  "title": "205th solution, no DL at all ",
  "url": "/competitions/tlvmc-parkinsons-freezing-gait-prediction/discussion/416888",
  "author_name": "Aviv Levi",
  "post_date": "2023-06-13T10:33:30.524000",
  "votes": 0,
  "comment_count": 0,
  "views": 0,
  "content": "<p>Thank you to the organizers and Kaggle!<br>\nIt was awesome to take part.<br>\nCongratulations to the winners :)!</p>\n<p>For my final solution, I used 10 models, and 2 ways to look at the data.</p>\n<p>1st way - Classic Time Series problem<br>\nI used lags, expanding/moving statistics, and graph statistics.</p>\n<p>2nd way - Using tsflex.</p>\n<p>I trained 5 models per data preparation technique, namely: XGBoost, LightGBM, Catboost, Random Forest, and Adaboost.</p>\n<p>my final submission notebook can be found here:<br>\n<a href=\"https://www.kaggle.com/code/avivlevi815/submit-bagging-v9\" target=\"_blank\">https://www.kaggle.com/code/avivlevi815/submit-bagging-v9</a></p>\n<p>Cheers!</p>",
  "messages": [
    {
      "id": 2300646,
      "postDate": "2023-06-13T10:33:30.523Z",
      "content": "<p>Thank you to the organizers and Kaggle!<br>\nIt was awesome to take part.<br>\nCongratulations to the winners :)!</p>\n<p>For my final solution, I used 10 models, and 2 ways to look at the data.</p>\n<p>1st way - Classic Time Series problem<br>\nI used lags, expanding/moving statistics, and graph statistics.</p>\n<p>2nd way - Using tsflex.</p>\n<p>I trained 5 models per data preparation technique, namely: XGBoost, LightGBM, Catboost, Random Forest, and Adaboost.</p>\n<p>my final submission notebook can be found here:<br>\n<a href=\"https://www.kaggle.com/code/avivlevi815/submit-bagging-v9\" target=\"_blank\">https://www.kaggle.com/code/avivlevi815/submit-bagging-v9</a></p>\n<p>Cheers!</p>",
      "rawMarkdown": "Thank you to the organizers and Kaggle!\nIt was awesome to take part.\nCongratulations to the winners :)!\n\nFor my final solution, I used 10 models, and 2 ways to look at the data.\n\n1st way - Classic Time Series problem\nI used lags, expanding/moving statistics, and graph statistics.\n\n2nd way - Using tsflex.\n\nI trained 5 models per data preparation technique, namely: XGBoost, LightGBM, Catboost, Random Forest, and Adaboost.\n\nmy final submission notebook can be found here:\nhttps://www.kaggle.com/code/avivlevi815/submit-bagging-v9\n\nCheers!"
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "2300646": "Thank you to the organizers and Kaggle!\nIt was awesome to take part.\nCongratulations to the winners :)!\n\nFor my final solution, I used 10 models, and 2 ways to look at the data.\n\n1st way - Classic Time Series problem\nI used lags, expanding/moving statistics, and graph statistics.\n\n2nd way - Using tsflex.\n\nI trained 5 models per data preparation technique, namely: XGBoost, LightGBM, Catboost, Random Forest, and Adaboost.\n\nmy final submission notebook can be found here:\nhttps://www.kaggle.com/code/avivlevi815/submit-bagging-v9\n\nCheers!"
  }
}