{
  "id": 248680,
  "title": "23rd private (1437th public, 4 submissions total) - regular expressions",
  "url": "/competitions/coleridgeinitiative-show-us-the-data/discussion/248680",
  "author_name": "anatoly",
  "post_date": "2021-06-24T13:30:32.414000",
  "votes": 17,
  "comment_count": 2,
  "views": 0,
  "content": "<p>1) I look for any word from this list ['Survey', 'Data', 'Study', 'Database', 'Statistics'] in text.<br>\n2) Then I look 5 words backward and forward for words starting from upper case letter.<br>\n3) From all sequences I choose only sequences with more than 2 words<br>\n4) Then I add found labels from train dataset.</p>\n<p>Link: <a href=\"https://www.kaggle.com/ilyenkov/coleridgeinitiative-show-us-the-data-v0\" target=\"_blank\">https://www.kaggle.com/ilyenkov/coleridgeinitiative-show-us-the-data-v0</a></p>",
  "messages": [
    {
      "id": 1363928,
      "postDate": "2021-06-24T13:30:32.413Z",
      "content": "<p>1) I look for any word from this list ['Survey', 'Data', 'Study', 'Database', 'Statistics'] in text.<br>\n2) Then I look 5 words backward and forward for words starting from upper case letter.<br>\n3) From all sequences I choose only sequences with more than 2 words<br>\n4) Then I add found labels from train dataset.</p>\n<p>Link: <a href=\"https://www.kaggle.com/ilyenkov/coleridgeinitiative-show-us-the-data-v0\" target=\"_blank\">https://www.kaggle.com/ilyenkov/coleridgeinitiative-show-us-the-data-v0</a></p>",
      "rawMarkdown": "1) I look for any word from this list ['Survey', 'Data', 'Study', 'Database', 'Statistics'] in text.\n2) Then I look 5 words backward and forward for words starting from upper case letter.\n3) From all sequences I choose only sequences with more than 2 words\n4) Then I add found labels from train dataset.\n\nLink: https://www.kaggle.com/ilyenkov/coleridgeinitiative-show-us-the-data-v0",
      "votes": 17
    },
    {
      "id": 1364717,
      "postDate": "2021-06-25T06:52:06.970Z",
      "rawMarkdown": "",
      "isDeleted": true
    },
    {
      "id": 1364251,
      "postDate": "2021-06-24T18:42:25.697Z",
      "content": "<p>Nice approach. Thanks for sharing </p>",
      "rawMarkdown": "Nice approach. Thanks for sharing ",
      "votes": 1
    }
  ],
  "comments": [
    {
      "id": 1364717,
      "author_name": "",
      "author_url": "",
      "post_date": "2021-06-25T06:52:06.970000",
      "content": "",
      "votes": 0,
      "replies": []
    },
    {
      "id": 1364251,
      "author_name": "Peter Hahn",
      "author_url": "",
      "post_date": "2021-06-24T18:42:25.697000",
      "content": "<p>Nice approach. Thanks for sharing </p>",
      "votes": 1,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1363928": "1) I look for any word from this list ['Survey', 'Data', 'Study', 'Database', 'Statistics'] in text.\n2) Then I look 5 words backward and forward for words starting from upper case letter.\n3) From all sequences I choose only sequences with more than 2 words\n4) Then I add found labels from train dataset.\n\nLink: https://www.kaggle.com/ilyenkov/coleridgeinitiative-show-us-the-data-v0",
    "1364717": "",
    "1364251": "Nice approach. Thanks for sharing "
  },
  "complete": true,
  "source": "existing_discussion",
  "competition_id": 25925,
  "competition_slug": "coleridgeinitiative-show-us-the-data",
  "team_id": 6684830,
  "solution_url": "/competitions/coleridgeinitiative-show-us-the-data/writeups/anatoly-23rd-private-1437th-public-4-submissions-t"
}