{
  "id": 436126,
  "title": "Thanks for the organisation. ",
  "url": "/competitions/anomaly-class-detection/discussion/436126",
  "author_name": "Lucas Morin",
  "post_date": "2023-09-01T07:07:49.197000",
  "votes": 3,
  "comment_count": 0,
  "views": 0,
  "content": "<p>Thanks for the organisation <a href=\"https://www.kaggle.com/kindspidey787\" target=\"_blank\">@kindspidey787</a>. For those interested I end up with a small ensemble of xgboost:</p>\n<pre><code>ss = ShuffleSplit(n_splits=  DEBUG  , train_size=, random_state=)\n\nparams = {\n    : ,\n    :,\n    \n    :,\n    :   DEBUG  ,\n    :,\n    :,\n    :,\n    :,\n    : ,\n    :\n}\n</code></pre>\n<p>I tuned the binarisation threshold on the LB (bad, I know). </p>\n<p>Keep up the good work, this serie is currently the most interesting financial competition out there.</p>",
  "messages": [
    {
      "id": 2418154,
      "postDate": "2023-09-01T07:07:49.197Z",
      "content": "<p>Thanks for the organisation <a href=\"https://www.kaggle.com/kindspidey787\" target=\"_blank\">@kindspidey787</a>. For those interested I end up with a small ensemble of xgboost:</p>\n<pre><code>ss = ShuffleSplit(n_splits=  DEBUG  , train_size=, random_state=)\n\nparams = {\n    : ,\n    :,\n    \n    :,\n    :   DEBUG  ,\n    :,\n    :,\n    :,\n    :,\n    : ,\n    :\n}\n</code></pre>\n<p>I tuned the binarisation threshold on the LB (bad, I know). </p>\n<p>Keep up the good work, this serie is currently the most interesting financial competition out there.</p>",
      "rawMarkdown": "Thanks for the organisation @kindspidey787. For those interested I end up with a small ensemble of xgboost:\n\n```python\nss = ShuffleSplit(n_splits=3 if DEBUG else 11, train_size=.5, random_state=0)\n\nparams = {\n    'verbosity': 1,\n    'booster':'gbtree',\n    #'rate_drop':0.05,\n    'learning_rate':0.1,\n    'n_estimators': 10 if DEBUG else 500,\n    'lambda':0.1,\n    'alpha':0.1,\n    'subsample':0.6,\n    'colsample_bytree':0.6,\n    'max_depth': 4,\n    'early_stopping_rounds':20\n}\n```\n\nI tuned the binarisation threshold on the LB (bad, I know). \n\nKeep up the good work, this serie is currently the most interesting financial competition out there.\n",
      "votes": 3
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "2418154": "Thanks for the organisation @kindspidey787. For those interested I end up with a small ensemble of xgboost:\n\n```python\nss = ShuffleSplit(n_splits=3 if DEBUG else 11, train_size=.5, random_state=0)\n\nparams = {\n    'verbosity': 1,\n    'booster':'gbtree',\n    #'rate_drop':0.05,\n    'learning_rate':0.1,\n    'n_estimators': 10 if DEBUG else 500,\n    'lambda':0.1,\n    'alpha':0.1,\n    'subsample':0.6,\n    'colsample_bytree':0.6,\n    'max_depth': 4,\n    'early_stopping_rounds':20\n}\n```\n\nI tuned the binarisation threshold on the LB (bad, I know). \n\nKeep up the good work, this serie is currently the most interesting financial competition out there.\n"
  }
}