{
  "id": 124217,
  "title": "Categorical feature encoding with TensorFlow",
  "url": "/competitions/cat-in-the-dat-ii/discussion/124217",
  "author_name": "",
  "post_date": "2020-01-02T16:30:10.143211Z",
  "votes": 17,
  "comment_count": 2,
  "views": 0,
  "content": "<p>I've just published a notebook as a starter for this competition:</p>\n\n<p><a href=\"https://www.kaggle.com/lucamassaron/categorical-feature-encoding-with-tensorflow\">https://www.kaggle.com/lucamassaron/categorical-feature-encoding-with-tensorflow</a></p>\n\n<p>The notebook applies TensorFlow / Keras tecniques for tabular data as described in:</p>\n\n<p><a href=\"https://github.com/lmassaron/deep_learning_for_tabular_data\">https://github.com/lmassaron/deep_learning_for_tabular_data</a>\n<a href=\"https://www.kaggle.com/lucamassaron/deep-learning-for-tabular-data\">https://www.kaggle.com/lucamassaron/deep-learning-for-tabular-data</a></p>\n\n<p>and as presented at various meetups and Google DevFests:</p>\n\n<p><a href=\"https://www.youtube.com/watch?v=nQgUt_uADSE\">https://www.youtube.com/watch?v=nQgUt_uADSE</a>\nIn particular, in the code you will find different data pipelines drafted for binary, high cardinality nominal, low cardinality nominal, ordinal, dates.</p>\n\n<p>The code is fully commented for you to explore and experiment, and, more important, it will be regularly updated during the competition with furthermore feature creation and more performing neural architectures.</p>",
  "messages": [
    {
      "id": "708758",
      "postDate": "01/02/2020 16:30:10",
      "content": "<p>I've just published a notebook as a starter for this competition:</p>\n\n<p><a href=\"https://www.kaggle.com/lucamassaron/categorical-feature-encoding-with-tensorflow\">https://www.kaggle.com/lucamassaron/categorical-feature-encoding-with-tensorflow</a></p>\n\n<p>The notebook applies TensorFlow / Keras tecniques for tabular data as described in:</p>\n\n<p><a href=\"https://github.com/lmassaron/deep_learning_for_tabular_data\">https://github.com/lmassaron/deep_learning_for_tabular_data</a>\n<a href=\"https://www.kaggle.com/lucamassaron/deep-learning-for-tabular-data\">https://www.kaggle.com/lucamassaron/deep-learning-for-tabular-data</a></p>\n\n<p>and as presented at various meetups and Google DevFests:</p>\n\n<p><a href=\"https://www.youtube.com/watch?v=nQgUt_uADSE\">https://www.youtube.com/watch?v=nQgUt_uADSE</a>\nIn particular, in the code you will find different data pipelines drafted for binary, high cardinality nominal, low cardinality nominal, ordinal, dates.</p>\n\n<p>The code is fully commented for you to explore and experiment, and, more important, it will be regularly updated during the competition with furthermore feature creation and more performing neural architectures.</p>",
      "rawMarkdown": "I've just published a notebook as a starter for this competition:\n\n[https://www.kaggle.com/lucamassaron/categorical-feature-encoding-with-tensorflow](https://www.kaggle.com/lucamassaron/categorical-feature-encoding-with-tensorflow)\n\nThe notebook applies TensorFlow / Keras tecniques for tabular data as described in:\n\n[https://github.com/lmassaron/deep_learning_for_tabular_data](https://github.com/lmassaron/deep_learning_for_tabular_data)\n[https://www.kaggle.com/lucamassaron/deep-learning-for-tabular-data](https://www.kaggle.com/lucamassaron/deep-learning-for-tabular-data)\n\nand as presented at various meetups and Google DevFests:\n\n[https://www.youtube.com/watch?v=nQgUt_uADSE](https://www.youtube.com/watch?v=nQgUt_uADSE)\nIn particular, in the code you will find different data pipelines drafted for binary, high cardinality nominal, low cardinality nominal, ordinal, dates.\n\nThe code is fully commented for you to explore and experiment, and, more important, it will be regularly updated during the competition with furthermore feature creation and more performing neural architectures.",
      "votes": null
    },
    {
      "id": "743107",
      "postDate": "02/11/2020 19:45:29",
      "content": "<p><a href=\"/lucamassaron\">@lucamassaron</a> </p>\n\n<p>Mi piace tantissimo il tuo lavoro !</p>\n\n<p>Avanti, dai !</p>",
      "rawMarkdown": "lucamassaron \n\nMi piace tantissimo il tuo lavoro !\n\nAvanti, dai !",
      "votes": null
    },
    {
      "id": "744938",
      "postDate": "02/13/2020 10:04:09",
      "content": "<p>Thanks for share 💯 </p>",
      "rawMarkdown": "Thanks for share 💯",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 743107,
      "author_name": "pfichou",
      "author_url": "",
      "post_date": "02/11/2020 19:45:29",
      "content": "<p><a href=\"/lucamassaron\">@lucamassaron</a> </p>\n\n<p>Mi piace tantissimo il tuo lavoro !</p>\n\n<p>Avanti, dai !</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 744938,
      "author_name": "dasmehdixtr",
      "author_url": "",
      "post_date": "02/13/2020 10:04:09",
      "content": "<p>Thanks for share 💯 </p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "708758": "I've just published a notebook as a starter for this competition:\n\n[https://www.kaggle.com/lucamassaron/categorical-feature-encoding-with-tensorflow](https://www.kaggle.com/lucamassaron/categorical-feature-encoding-with-tensorflow)\n\nThe notebook applies TensorFlow / Keras tecniques for tabular data as described in:\n\n[https://github.com/lmassaron/deep_learning_for_tabular_data](https://github.com/lmassaron/deep_learning_for_tabular_data)\n[https://www.kaggle.com/lucamassaron/deep-learning-for-tabular-data](https://www.kaggle.com/lucamassaron/deep-learning-for-tabular-data)\n\nand as presented at various meetups and Google DevFests:\n\n[https://www.youtube.com/watch?v=nQgUt_uADSE](https://www.youtube.com/watch?v=nQgUt_uADSE)\nIn particular, in the code you will find different data pipelines drafted for binary, high cardinality nominal, low cardinality nominal, ordinal, dates.\n\nThe code is fully commented for you to explore and experiment, and, more important, it will be regularly updated during the competition with furthermore feature creation and more performing neural architectures.",
    "743107": "lucamassaron \n\nMi piace tantissimo il tuo lavoro !\n\nAvanti, dai !",
    "744938": "Thanks for share 💯"
  },
  "source": "meta"
}