{
  "id": 121074,
  "title": "Stratified K Folds Improves the 1.08 score (Without leaks)",
  "url": "/competitions/ashrae-energy-prediction/discussion/121074",
  "author_name": "",
  "post_date": "2019-12-11T00:23:47.119862600Z",
  "votes": 17,
  "comment_count": 2,
  "views": 0,
  "content": "<p>Since the Kernel includes month as a categorical feature. I implemented a Stratified K Fold Technique instead of K and Group K Folds. The new lb score 1.08 with a much lower RMSE on CV. </p>\n\n<p>Notebook : <a href=\"https://www.kaggle.com/roydatascience/ashrae-energy-prediction-using-stratified-kfold\">https://www.kaggle.com/roydatascience/ashrae-energy-prediction-using-stratified-kfold</a></p>",
  "messages": [
    {
      "id": "692143",
      "postDate": "12/11/2019 00:23:47",
      "content": "<p>Since the Kernel includes month as a categorical feature. I implemented a Stratified K Fold Technique instead of K and Group K Folds. The new lb score 1.08 with a much lower RMSE on CV. </p>\n\n<p>Notebook : <a href=\"https://www.kaggle.com/roydatascience/ashrae-energy-prediction-using-stratified-kfold\">https://www.kaggle.com/roydatascience/ashrae-energy-prediction-using-stratified-kfold</a></p>",
      "rawMarkdown": "Since the Kernel includes month as a categorical feature. I implemented a Stratified K Fold Technique instead of K and Group K Folds. The new lb score 1.08 with a much lower RMSE on CV. \n\nNotebook : https://www.kaggle.com/roydatascience/ashrae-energy-prediction-using-stratified-kfold",
      "votes": null
    },
    {
      "id": "693773",
      "postDate": "12/12/2019 19:24:21",
      "content": "<p>Nice! Thanks!</p>",
      "rawMarkdown": "Nice! Thanks!",
      "votes": null
    },
    {
      "id": "694176",
      "postDate": "12/13/2019 09:14:10",
      "content": "<p>sounds great~</p>",
      "rawMarkdown": "sounds great~",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 693773,
      "author_name": "carlolepelaars",
      "author_url": "",
      "post_date": "12/12/2019 19:24:21",
      "content": "<p>Nice! Thanks!</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 694176,
      "author_name": "xingzhihao",
      "author_url": "",
      "post_date": "12/13/2019 09:14:10",
      "content": "<p>sounds great~</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "692143": "Since the Kernel includes month as a categorical feature. I implemented a Stratified K Fold Technique instead of K and Group K Folds. The new lb score 1.08 with a much lower RMSE on CV. \n\nNotebook : https://www.kaggle.com/roydatascience/ashrae-energy-prediction-using-stratified-kfold",
    "693773": "Nice! Thanks!",
    "694176": "sounds great~"
  },
  "source": "meta"
}