{
  "id": 317917,
  "title": "2nd place solution",
  "url": "/competitions/congressionaltweetcompetitionspring2022/discussion/317917",
  "author_name": "Andrew Hoang",
  "post_date": "2022-04-09T15:21:12.836000",
  "votes": 5,
  "comment_count": 0,
  "views": 0,
  "content": "<p>This is the github link for my notebook. The code I used is structured in various modules and scripts, but I had to copy paste everything into one notebook for submission, so I don't actually know if the notebook runs, but it should contain everything necessary to replicate my result.</p>\n<p><a href=\"https://github.com/ndrwhoang/kaggle_comp_congress_tweet\" target=\"_blank\">https://github.com/ndrwhoang/kaggle_comp_congress_tweet</a></p>\n<p>I did the transformer + prediction head thing and went with the kitchen sink approach of feature engineering. Based on the similar results on the LB, I suspect others also somewhat follow this approach; what I have done more is gradual unfreezing and data leakage abuse (there are some overlap between test set and train set, you can get around +0.009 accuracy, though that depends on your original accuracy)</p>",
  "messages": [
    {
      "id": 1750367,
      "postDate": "2022-04-09T15:21:12.837Z",
      "content": "<p>This is the github link for my notebook. The code I used is structured in various modules and scripts, but I had to copy paste everything into one notebook for submission, so I don't actually know if the notebook runs, but it should contain everything necessary to replicate my result.</p>\n<p><a href=\"https://github.com/ndrwhoang/kaggle_comp_congress_tweet\" target=\"_blank\">https://github.com/ndrwhoang/kaggle_comp_congress_tweet</a></p>\n<p>I did the transformer + prediction head thing and went with the kitchen sink approach of feature engineering. Based on the similar results on the LB, I suspect others also somewhat follow this approach; what I have done more is gradual unfreezing and data leakage abuse (there are some overlap between test set and train set, you can get around +0.009 accuracy, though that depends on your original accuracy)</p>",
      "rawMarkdown": "This is the github link for my notebook. The code I used is structured in various modules and scripts, but I had to copy paste everything into one notebook for submission, so I don't actually know if the notebook runs, but it should contain everything necessary to replicate my result.\n\nhttps://github.com/ndrwhoang/kaggle_comp_congress_tweet\n\nI did the transformer + prediction head thing and went with the kitchen sink approach of feature engineering. Based on the similar results on the LB, I suspect others also somewhat follow this approach; what I have done more is gradual unfreezing and data leakage abuse (there are some overlap between test set and train set, you can get around +0.009 accuracy, though that depends on your original accuracy)",
      "votes": 5
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "1750367": "This is the github link for my notebook. The code I used is structured in various modules and scripts, but I had to copy paste everything into one notebook for submission, so I don't actually know if the notebook runs, but it should contain everything necessary to replicate my result.\n\nhttps://github.com/ndrwhoang/kaggle_comp_congress_tweet\n\nI did the transformer + prediction head thing and went with the kitchen sink approach of feature engineering. Based on the similar results on the LB, I suspect others also somewhat follow this approach; what I have done more is gradual unfreezing and data leakage abuse (there are some overlap between test set and train set, you can get around +0.009 accuracy, though that depends on your original accuracy)"
  }
}