{
  "id": 57931,
  "title": "Tilted Tracks",
  "url": "/competitions/trackml-particle-identification/discussion/57931",
  "author_name": "",
  "post_date": "2018-05-31T03:01:59.594550500Z",
  "votes": null,
  "comment_count": 1,
  "views": 0,
  "content": "<p>Hello everyone, </p>\n\n<p>I was trying to apply PCA to the data and I'm getting some weird results (graph attached and shown below). What I did is that I changed the coordinate system to cylindrical, then I applied PCA as shown in this kernel:\n<a href=\"https://www.kaggle.com/osa111/transformation-visiualization-with-questions\">transformation visualization with questions</a></p>\n\n<p><img src=\"https://storage.googleapis.com/kaggle-forum-message-attachments/336079/9541/__results___12_1.png\" alt=\"enter image description here\"></p>\n\n<p>Not sure if it's a mistake on my side or there is something that I'm missing. The same process was applied to the hits set and they're showing fine, but the tracks get this weird tilt :/ </p>",
  "messages": [
    {
      "id": "336079",
      "postDate": "05/31/2018 03:01:59",
      "content": "<p>Hello everyone, </p>\n\n<p>I was trying to apply PCA to the data and I'm getting some weird results (graph attached and shown below). What I did is that I changed the coordinate system to cylindrical, then I applied PCA as shown in this kernel:\n<a href=\"https://www.kaggle.com/osa111/transformation-visiualization-with-questions\">transformation visualization with questions</a></p>\n\n<p><img src=\"https://storage.googleapis.com/kaggle-forum-message-attachments/336079/9541/__results___12_1.png\" alt=\"enter image description here\"></p>\n\n<p>Not sure if it's a mistake on my side or there is something that I'm missing. The same process was applied to the hits set and they're showing fine, but the tracks get this weird tilt :/ </p>",
      "rawMarkdown": "Hello everyone, \n\nI was trying to apply PCA to the data and I'm getting some weird results (graph attached and shown below). What I did is that I changed the coordinate system to cylindrical, then I applied PCA as shown in this kernel:\n[transformation visualization with questions][1]\n\n\n![enter image description here][2]\n\nNot sure if it's a mistake on my side or there is something that I'm missing. The same process was applied to the hits set and they're showing fine, but the tracks get this weird tilt :/ \n\n\n  [1]: https://www.kaggle.com/osa111/transformation-visiualization-with-questions\n  [2]: https://storage.googleapis.com/kaggle-forum-message-attachments/336079/9541/__results___12_1.png",
      "votes": null
    },
    {
      "id": "336566",
      "postDate": "06/01/2018 00:48:33",
      "content": "<p>Never mind ya'll ... I fixed the issue and it's shown on <a href=\"https://www.kaggle.com/osa111/transformation-visiualization-fixed\">transformation visualization with questions</a>. Before, I applied transformation and PCA on the tracks after selecting them from the truth dataset. I fixed it simply by applying both transformation and PCA on the truth dataset then I select the tracks...</p>\n\n<p><img src=\"https://storage.googleapis.com/kaggle-forum-message-attachments/336566/9555/__results___13_1.png\" alt=\"enter image description here\"></p>\n\n<p>&amp;</p>\n\n<p><img src=\"https://storage.googleapis.com/kaggle-forum-message-attachments/336566/9556/download%20(1).png\" alt=\"enter image description here\"></p>",
      "rawMarkdown": "Never mind ya'll ... I fixed the issue and it's shown on [transformation visualization with questions][1]. Before, I applied transformation and PCA on the tracks after selecting them from the truth dataset. I fixed it simply by applying both transformation and PCA on the truth dataset then I select the tracks...\n\n![enter image description here][2]\n\n&amp;\n\n ![enter image description here][3]\n\n\n  [1]: https://www.kaggle.com/osa111/transformation-visiualization-fixed\n  [2]: https://storage.googleapis.com/kaggle-forum-message-attachments/336566/9555/__results___13_1.png\n  [3]: https://storage.googleapis.com/kaggle-forum-message-attachments/336566/9556/download%20(1).png",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 336566,
      "author_name": "osa111",
      "author_url": "",
      "post_date": "06/01/2018 00:48:33",
      "content": "<p>Never mind ya'll ... I fixed the issue and it's shown on <a href=\"https://www.kaggle.com/osa111/transformation-visiualization-fixed\">transformation visualization with questions</a>. Before, I applied transformation and PCA on the tracks after selecting them from the truth dataset. I fixed it simply by applying both transformation and PCA on the truth dataset then I select the tracks...</p>\n\n<p><img src=\"https://storage.googleapis.com/kaggle-forum-message-attachments/336566/9555/__results___13_1.png\" alt=\"enter image description here\"></p>\n\n<p>&amp;</p>\n\n<p><img src=\"https://storage.googleapis.com/kaggle-forum-message-attachments/336566/9556/download%20(1).png\" alt=\"enter image description here\"></p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "336079": "Hello everyone, \n\nI was trying to apply PCA to the data and I'm getting some weird results (graph attached and shown below). What I did is that I changed the coordinate system to cylindrical, then I applied PCA as shown in this kernel:\n[transformation visualization with questions][1]\n\n\n![enter image description here][2]\n\nNot sure if it's a mistake on my side or there is something that I'm missing. The same process was applied to the hits set and they're showing fine, but the tracks get this weird tilt :/ \n\n\n  [1]: https://www.kaggle.com/osa111/transformation-visiualization-with-questions\n  [2]: https://storage.googleapis.com/kaggle-forum-message-attachments/336079/9541/__results___12_1.png",
    "336566": "Never mind ya'll ... I fixed the issue and it's shown on [transformation visualization with questions][1]. Before, I applied transformation and PCA on the tracks after selecting them from the truth dataset. I fixed it simply by applying both transformation and PCA on the truth dataset then I select the tracks...\n\n![enter image description here][2]\n\n&amp;\n\n ![enter image description here][3]\n\n\n  [1]: https://www.kaggle.com/osa111/transformation-visiualization-fixed\n  [2]: https://storage.googleapis.com/kaggle-forum-message-attachments/336566/9555/__results___13_1.png\n  [3]: https://storage.googleapis.com/kaggle-forum-message-attachments/336566/9556/download%20(1).png"
  },
  "source": "meta"
}