{
  "id": 329465,
  "title": "\"Unsupported type_id conversion to cudf\" while reading from feather",
  "url": "/competitions/amex-default-prediction/discussion/329465",
  "author_name": "",
  "post_date": "2022-06-06T20:10:47.719924800Z",
  "votes": 3,
  "comment_count": 2,
  "views": 0,
  "content": "<p>Hi! I was trying to read this dataset with CUDF (<a href=\"https://www.kaggle.com/datasets/munumbutt/amexfeather/version/1)\" target=\"_blank\">https://www.kaggle.com/datasets/munumbutt/amexfeather/version/1)</a>, but I was prompted </p>\n<pre><code>&lt;decorator-gen-53&gt; in time(self, line, cell, local_ns)\n\n&lt;timed exec&gt; in &lt;module&gt;()\n\n&lt;timed exec&gt; in read_file(path, usecols, isfeather)\n\n/usr/local/lib/python3.7/site-packages/cudf/core/frame.py in from_arrow(cls, data)\n   2196             {}\n   2197             if data.num_columns == 0\n-&gt; 2198             else libcudf.interop.from_arrow(data, data.column_names)[0]\n   2199         )\n   2200 \n\ncudf/_lib/interop.pyx in cudf._lib.interop.from_arrow()\n\nRuntimeError: cuDF failure at: ../src/interop/from_arrow.cu:85: Unsupported type_id conversion to cudf\n</code></pre>\n<p>I was wondering how to fix it.</p>\n<p><a href=\"https://www.kaggle.com/cdeotte\" target=\"_blank\">@cdeotte</a> </p>",
  "messages": [
    {
      "id": "1813436",
      "postDate": "06/06/2022 20:10:47",
      "content": "<p>Hi! I was trying to read this dataset with CUDF (<a href=\"https://www.kaggle.com/datasets/munumbutt/amexfeather/version/1)\" target=\"_blank\">https://www.kaggle.com/datasets/munumbutt/amexfeather/version/1)</a>, but I was prompted </p>\n<pre><code>&lt;decorator-gen-53&gt; in time(self, line, cell, local_ns)\n\n&lt;timed exec&gt; in &lt;module&gt;()\n\n&lt;timed exec&gt; in read_file(path, usecols, isfeather)\n\n/usr/local/lib/python3.7/site-packages/cudf/core/frame.py in from_arrow(cls, data)\n   2196             {}\n   2197             if data.num_columns == 0\n-&gt; 2198             else libcudf.interop.from_arrow(data, data.column_names)[0]\n   2199         )\n   2200 \n\ncudf/_lib/interop.pyx in cudf._lib.interop.from_arrow()\n\nRuntimeError: cuDF failure at: ../src/interop/from_arrow.cu:85: Unsupported type_id conversion to cudf\n</code></pre>\n<p>I was wondering how to fix it.</p>\n<p><a href=\"https://www.kaggle.com/cdeotte\" target=\"_blank\">@cdeotte</a> </p>",
      "rawMarkdown": "Hi! I was trying to read this dataset with CUDF (https://www.kaggle.com/datasets/munumbutt/amexfeather/version/1), but I was prompted \n\n```\n<decorator-gen-53> in time(self, line, cell, local_ns)\n\n<timed exec> in <module>()\n\n<timed exec> in read_file(path, usecols, isfeather)\n\n/usr/local/lib/python3.7/site-packages/cudf/core/frame.py in from_arrow(cls, data)\n   2196             {}\n   2197             if data.num_columns == 0\n-> 2198             else libcudf.interop.from_arrow(data, data.column_names)[0]\n   2199         )\n   2200 \n\ncudf/_lib/interop.pyx in cudf._lib.interop.from_arrow()\n\nRuntimeError: cuDF failure at: ../src/interop/from_arrow.cu:85: Unsupported type_id conversion to cudf\n```\n\nI was wondering how to fix it.\n\n@cdeotte",
      "votes": null
    },
    {
      "id": "1813850",
      "postDate": "06/07/2022 09:40:30",
      "content": "<p><a href=\"https://www.kaggle.com/tonychenxyz\" target=\"_blank\">@tonychenxyz</a> Hi. RAPIDS cuDF does not support <code>float16</code> currently. You will need to read the <code>f32</code> feathers in that Kaggle dataset. Namely</p>\n<p><code>https://www.kaggle.com/datasets/munumbutt/amexfeather?select=train_data_f32.ftr</code><br>\n<code>https://www.kaggle.com/datasets/munumbutt/amexfeather?select=test_data_f32.ftr</code></p>",
      "rawMarkdown": "tonychenxyz Hi. RAPIDS cuDF does not support `float16` currently. You will need to read the `f32` feathers in that Kaggle dataset. Namely\n\n`https://www.kaggle.com/datasets/munumbutt/amexfeather?select=train_data_f32.ftr`\n`https://www.kaggle.com/datasets/munumbutt/amexfeather?select=test_data_f32.ftr`",
      "votes": null
    },
    {
      "id": "1814372",
      "postDate": "06/07/2022 20:00:26",
      "content": "<p>Thank you very much!</p>",
      "rawMarkdown": "Thank you very much!",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1813850,
      "author_name": "cdeotte",
      "author_url": "",
      "post_date": "06/07/2022 09:40:30",
      "content": "<p><a href=\"https://www.kaggle.com/tonychenxyz\" target=\"_blank\">@tonychenxyz</a> Hi. RAPIDS cuDF does not support <code>float16</code> currently. You will need to read the <code>f32</code> feathers in that Kaggle dataset. Namely</p>\n<p><code>https://www.kaggle.com/datasets/munumbutt/amexfeather?select=train_data_f32.ftr</code><br>\n<code>https://www.kaggle.com/datasets/munumbutt/amexfeather?select=test_data_f32.ftr</code></p>",
      "votes": null,
      "replies": [
        {
          "id": 1814372,
          "author_name": "tonychenxyz",
          "author_url": "",
          "post_date": "06/07/2022 20:00:26",
          "content": "<p>Thank you very much!</p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "1813436": "Hi! I was trying to read this dataset with CUDF (https://www.kaggle.com/datasets/munumbutt/amexfeather/version/1), but I was prompted \n\n```\n<decorator-gen-53> in time(self, line, cell, local_ns)\n\n<timed exec> in <module>()\n\n<timed exec> in read_file(path, usecols, isfeather)\n\n/usr/local/lib/python3.7/site-packages/cudf/core/frame.py in from_arrow(cls, data)\n   2196             {}\n   2197             if data.num_columns == 0\n-> 2198             else libcudf.interop.from_arrow(data, data.column_names)[0]\n   2199         )\n   2200 \n\ncudf/_lib/interop.pyx in cudf._lib.interop.from_arrow()\n\nRuntimeError: cuDF failure at: ../src/interop/from_arrow.cu:85: Unsupported type_id conversion to cudf\n```\n\nI was wondering how to fix it.\n\n@cdeotte",
    "1813850": "tonychenxyz Hi. RAPIDS cuDF does not support `float16` currently. You will need to read the `f32` feathers in that Kaggle dataset. Namely\n\n`https://www.kaggle.com/datasets/munumbutt/amexfeather?select=train_data_f32.ftr`\n`https://www.kaggle.com/datasets/munumbutt/amexfeather?select=test_data_f32.ftr`",
    "1814372": "Thank you very much!"
  },
  "source": "meta"
}