{
  "id": 442044,
  "title": "Has anyone tried interpolation?",
  "url": "/competitions/child-mind-institute-detect-sleep-states/discussion/442044",
  "author_name": "",
  "post_date": "2023-09-21T05:55:35.887711300Z",
  "votes": 2,
  "comment_count": 2,
  "views": 0,
  "content": "<p>I've hit a bottleneck in my modeling. It feels like up resample is a very violent method. Has anyone tried resample, maybe there is a surprise here? 😍</p>\n<p>e.g.<br>\n<code>scipy.signal.resample_poly</code> <a href=\"url\" target=\"_blank\">https://docs.scipy.org/doc/scipy/reference/generated/scipy.signal.resample_poly.html#scipy-signal-resample-poly</a></p>\n<p><code>mne.filter.resample</code> <a href=\"url\" target=\"_blank\">https://mne.tools/stable/generated/mne.filter.resample.html#mne-filter-resample</a></p>",
  "messages": [
    {
      "id": "2449323",
      "postDate": "09/21/2023 05:55:35",
      "content": "<p>I've hit a bottleneck in my modeling. It feels like up resample is a very violent method. Has anyone tried resample, maybe there is a surprise here? 😍</p>\n<p>e.g.<br>\n<code>scipy.signal.resample_poly</code> <a href=\"url\" target=\"_blank\">https://docs.scipy.org/doc/scipy/reference/generated/scipy.signal.resample_poly.html#scipy-signal-resample-poly</a></p>\n<p><code>mne.filter.resample</code> <a href=\"url\" target=\"_blank\">https://mne.tools/stable/generated/mne.filter.resample.html#mne-filter-resample</a></p>",
      "rawMarkdown": "I've hit a bottleneck in my modeling. It feels like up resample is a very violent method. Has anyone tried resample, maybe there is a surprise here? 😍\n\ne.g.\n`scipy.signal.resample_poly` [https://docs.scipy.org/doc/scipy/reference/generated/scipy.signal.resample_poly.html#scipy-signal-resample-poly](url)\n\n`mne.filter.resample` [https://mne.tools/stable/generated/mne.filter.resample.html#mne-filter-resample](url)",
      "votes": null
    },
    {
      "id": "2452131",
      "postDate": "09/23/2023 05:54:43",
      "content": "<p>Hi <a href=\"https://www.kaggle.com/jimmyisme1\" target=\"_blank\">@jimmyisme1</a>. I didn't have that idea. I'm having issues with data handling, so I'm considering downsampling.</p>",
      "rawMarkdown": "Hi @jimmyisme1. I didn't have that idea. I'm having issues with data handling, so I'm considering downsampling.",
      "votes": null
    },
    {
      "id": "2452215",
      "postDate": "09/23/2023 07:00:08",
      "content": "<p>Since the evaluation function is very concerned with STEP proximity, I intuitively feel that DOWN samples may innately lead to lower scores. However it is also possible that this could allow the model to save more useless data. Looking forward to your results.</p>",
      "rawMarkdown": "Since the evaluation function is very concerned with STEP proximity, I intuitively feel that DOWN samples may innately lead to lower scores. However it is also possible that this could allow the model to save more useless data. Looking forward to your results.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 2452131,
      "author_name": "mitsuyasuhoshino",
      "author_url": "",
      "post_date": "09/23/2023 05:54:43",
      "content": "<p>Hi <a href=\"https://www.kaggle.com/jimmyisme1\" target=\"_blank\">@jimmyisme1</a>. I didn't have that idea. I'm having issues with data handling, so I'm considering downsampling.</p>",
      "votes": null,
      "replies": [
        {
          "id": 2452215,
          "author_name": "jimmyisme1",
          "author_url": "",
          "post_date": "09/23/2023 07:00:08",
          "content": "<p>Since the evaluation function is very concerned with STEP proximity, I intuitively feel that DOWN samples may innately lead to lower scores. However it is also possible that this could allow the model to save more useless data. Looking forward to your results.</p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "2449323": "I've hit a bottleneck in my modeling. It feels like up resample is a very violent method. Has anyone tried resample, maybe there is a surprise here? 😍\n\ne.g.\n`scipy.signal.resample_poly` [https://docs.scipy.org/doc/scipy/reference/generated/scipy.signal.resample_poly.html#scipy-signal-resample-poly](url)\n\n`mne.filter.resample` [https://mne.tools/stable/generated/mne.filter.resample.html#mne-filter-resample](url)",
    "2452131": "Hi @jimmyisme1. I didn't have that idea. I'm having issues with data handling, so I'm considering downsampling.",
    "2452215": "Since the evaluation function is very concerned with STEP proximity, I intuitively feel that DOWN samples may innately lead to lower scores. However it is also possible that this could allow the model to save more useless data. Looking forward to your results."
  },
  "source": "meta"
}