{
  "id": 53653,
  "title": "Weight of Evidence and Information Value (in Python)",
  "url": "/competitions/talkingdata-adtracking-fraud-detection/discussion/53653",
  "author_name": "Bryan Arnold",
  "post_date": "2018-04-03T02:09:33.212000",
  "votes": 4,
  "comment_count": 0,
  "views": 0,
  "content": "<p>Hi, all. </p>\n\n<p>Inspired by <a href=\"https://www.kaggle.com/pranav84/talkingdata-with-breaking-bad-feature-engg\">Pranav Pandya's \"Breaking Bad\" kernel</a>, I made a <a href=\"https://www.kaggle.com/puremath86/iv-woe-starter-for-python/notebook\">quick tutorial</a> on how to calculate WoE and IV in Python.  It needs some code-golf and run-time optimization for sure. But it can still be handy for running on sub-samples.</p>",
  "messages": [
    {
      "id": 308136,
      "postDate": "2018-04-03T02:09:33.213Z",
      "content": "<p>Hi, all. </p>\n\n<p>Inspired by <a href=\"https://www.kaggle.com/pranav84/talkingdata-with-breaking-bad-feature-engg\">Pranav Pandya's \"Breaking Bad\" kernel</a>, I made a <a href=\"https://www.kaggle.com/puremath86/iv-woe-starter-for-python/notebook\">quick tutorial</a> on how to calculate WoE and IV in Python.  It needs some code-golf and run-time optimization for sure. But it can still be handy for running on sub-samples.</p>",
      "rawMarkdown": "Hi, all. \n\nInspired by [Pranav Pandya's \"Breaking Bad\" kernel][1], I made a [quick tutorial][2] on how to calculate WoE and IV in Python.  It needs some code-golf and run-time optimization for sure. But it can still be handy for running on sub-samples.\n\n\n  [1]: https://www.kaggle.com/pranav84/talkingdata-with-breaking-bad-feature-engg\n  [2]: https://www.kaggle.com/puremath86/iv-woe-starter-for-python/notebook",
      "votes": 4
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "308136": "Hi, all. \n\nInspired by [Pranav Pandya's \"Breaking Bad\" kernel][1], I made a [quick tutorial][2] on how to calculate WoE and IV in Python.  It needs some code-golf and run-time optimization for sure. But it can still be handy for running on sub-samples.\n\n\n  [1]: https://www.kaggle.com/pranav84/talkingdata-with-breaking-bad-feature-engg\n  [2]: https://www.kaggle.com/puremath86/iv-woe-starter-for-python/notebook"
  }
}