{
  "id": 320476,
  "title": "k-means clustering of customers with RAPIDS",
  "url": "/competitions/h-and-m-personalized-fashion-recommendations/discussion/320476",
  "author_name": "",
  "post_date": "2022-04-21T19:56:45.439401100Z",
  "votes": 4,
  "comment_count": 2,
  "views": 0,
  "content": "<p>I made this notebook to do k-means clusters for customers. What was utterly impossible to do with pandas/scikit in free kaggle notebooks is pretty easy with RAPIDS cuDF/cuML/cuPY.</p>\n<p>Anyway, just basic clustering stuff that you'd need to do for a recommender. I still have a long way to go to build a reasonable model in the 11 days left…<br>\n<a href=\"https://www.kaggle.com/code/beezus666/k-means-for-customers?scriptVersionId=93663053\" target=\"_blank\">https://www.kaggle.com/code/beezus666/k-means-for-customers?scriptVersionId=93663053</a></p>",
  "messages": [
    {
      "id": "1763779",
      "postDate": "04/21/2022 19:56:45",
      "content": "<p>I made this notebook to do k-means clusters for customers. What was utterly impossible to do with pandas/scikit in free kaggle notebooks is pretty easy with RAPIDS cuDF/cuML/cuPY.</p>\n<p>Anyway, just basic clustering stuff that you'd need to do for a recommender. I still have a long way to go to build a reasonable model in the 11 days left…<br>\n<a href=\"https://www.kaggle.com/code/beezus666/k-means-for-customers?scriptVersionId=93663053\" target=\"_blank\">https://www.kaggle.com/code/beezus666/k-means-for-customers?scriptVersionId=93663053</a></p>",
      "rawMarkdown": "I made this notebook to do k-means clusters for customers. What was utterly impossible to do with pandas/scikit in free kaggle notebooks is pretty easy with RAPIDS cuDF/cuML/cuPY.\n\nAnyway, just basic clustering stuff that you'd need to do for a recommender. I still have a long way to go to build a reasonable model in the 11 days left...\nhttps://www.kaggle.com/code/beezus666/k-means-for-customers?scriptVersionId=93663053",
      "votes": null
    },
    {
      "id": "1763939",
      "postDate": "04/22/2022 01:47:37",
      "content": "<p>Great work! Thanks for sharing!</p>",
      "rawMarkdown": "Great work! Thanks for sharing!",
      "votes": null
    },
    {
      "id": "1786120",
      "postDate": "05/12/2022 16:04:58",
      "content": "<p>This is really helpful! I was able to get a lot of useful insights from your notebook.</p>",
      "rawMarkdown": "This is really helpful! I was able to get a lot of useful insights from your notebook.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1763939,
      "author_name": "",
      "author_url": "",
      "post_date": "04/22/2022 01:47:37",
      "content": "<p>Great work! Thanks for sharing!</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 1786120,
      "author_name": "",
      "author_url": "",
      "post_date": "05/12/2022 16:04:58",
      "content": "<p>This is really helpful! I was able to get a lot of useful insights from your notebook.</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1763779": "I made this notebook to do k-means clusters for customers. What was utterly impossible to do with pandas/scikit in free kaggle notebooks is pretty easy with RAPIDS cuDF/cuML/cuPY.\n\nAnyway, just basic clustering stuff that you'd need to do for a recommender. I still have a long way to go to build a reasonable model in the 11 days left...\nhttps://www.kaggle.com/code/beezus666/k-means-for-customers?scriptVersionId=93663053",
    "1763939": "Great work! Thanks for sharing!",
    "1786120": "This is really helpful! I was able to get a lot of useful insights from your notebook."
  },
  "source": "meta"
}