{
  "id": 59653,
  "title": "fast triplet search in 2d",
  "url": "/competitions/trackml-particle-identification/discussion/59653",
  "author_name": "",
  "post_date": "2018-06-25T13:54:05.683709300Z",
  "votes": 1,
  "comment_count": 3,
  "views": 0,
  "content": "<p>as attached</p>\n\n<p><img src=\"https://storage.googleapis.com/kaggle-forum-message-attachments/347830/9693/search.png\" alt=\"enter image description here\"></p>",
  "messages": [
    {
      "id": "347830",
      "postDate": "06/25/2018 13:54:05",
      "content": "<p>as attached</p>\n\n<p><img src=\"https://storage.googleapis.com/kaggle-forum-message-attachments/347830/9693/search.png\" alt=\"enter image description here\"></p>",
      "rawMarkdown": "as attached\n\n  ![enter image description here][1]\n\n\n  [1]: https://storage.googleapis.com/kaggle-forum-message-attachments/347830/9693/search.png",
      "votes": null
    },
    {
      "id": "347834",
      "postDate": "06/25/2018 13:59:16",
      "content": "<p>reference:</p>\n\n<p><a href=\"https://indico.cern.ch/event/658267/contributions/2881175/attachments/1621912/2581064/Farrell_heptrkx_ctd2018.pdf\">https://indico.cern.ch/event/658267/contributions/2881175/attachments/1621912/2581064/Farrell_heptrkx_ctd2018.pdf</a></p>\n\n<p><img src=\"https://storage.googleapis.com/kaggle-forum-message-attachments/347834/9694/reference.png\" alt=\"enter image description here\"></p>",
      "rawMarkdown": "reference:\n\nhttps://indico.cern.ch/event/658267/contributions/2881175/attachments/1621912/2581064/Farrell_heptrkx_ctd2018.pdf\n\n\n  ![enter image description here][1]\n\n\n  [1]: https://storage.googleapis.com/kaggle-forum-message-attachments/347834/9694/reference.png",
      "votes": null
    },
    {
      "id": "349767",
      "postDate": "06/28/2018 15:57:34",
      "content": "<p>results and code:\n   <img src=\"https://storage.googleapis.com/kaggle-forum-message-attachments/349767/9718/Slide1.png\" alt=\"enter image description here\"></p>\n\n<p><img src=\"https://storage.googleapis.com/kaggle-forum-message-attachments/349767/9720/Slide2.png\" alt=\"enter image description here\"></p>\n\n<p><img src=\"https://storage.googleapis.com/kaggle-forum-message-attachments/349767/9719/Slide3.png\" alt=\"enter image description here\"></p>\n\n<p>how to use:</p>\n\n<p>fast triplet searches --&gt; merge or grow --&gt; ...</p>",
      "rawMarkdown": "results and code:\n   ![enter image description here][1]\n\n   ![enter image description here][2]\n\n   ![enter image description here][3]\n\nhow to use:\n\nfast triplet searches --&gt; merge or grow --&gt; ...\n\n\n  [1]: https://storage.googleapis.com/kaggle-forum-message-attachments/349767/9718/Slide1.png\n  [2]: https://storage.googleapis.com/kaggle-forum-message-attachments/349767/9720/Slide2.png\n  [3]: https://storage.googleapis.com/kaggle-forum-message-attachments/349767/9719/Slide3.png",
      "votes": null
    },
    {
      "id": "349771",
      "postDate": "06/28/2018 16:26:13",
      "content": "<p>change threshold parameters to get more triplets at lower precision:</p>\n\n<p>you can use a classifier to score the triplets  later</p>\n\n<pre><code>Elapsed: 1.026766300201416 sec\nnum_tracklets:    12387\nnum_particle_ids: 2296\nnum_valid_ids:    1275\nnum_hits:         9794\n\n scores:               0.233 = 2888.000 / 12387.000\n coverage_at_least3:   0.844 = 1076.000 / 1275.000\n coverage          :   4.635 = 4987.000 / 1076.000\n</code></pre>",
      "rawMarkdown": "change threshold parameters to get more triplets at lower precision:\n\nyou can use a classifier to score the triplets  later\n\n    Elapsed: 1.026766300201416 sec\n    num_tracklets:    12387\n    num_particle_ids: 2296\n    num_valid_ids:    1275\n    num_hits:         9794\n\n\t scores:               0.233 = 2888.000 / 12387.000\n\t coverage_at_least3:   0.844 = 1076.000 / 1275.000\n\t coverage          :   4.635 = 4987.000 / 1076.000",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 347834,
      "author_name": "hengck23",
      "author_url": "",
      "post_date": "06/25/2018 13:59:16",
      "content": "<p>reference:</p>\n\n<p><a href=\"https://indico.cern.ch/event/658267/contributions/2881175/attachments/1621912/2581064/Farrell_heptrkx_ctd2018.pdf\">https://indico.cern.ch/event/658267/contributions/2881175/attachments/1621912/2581064/Farrell_heptrkx_ctd2018.pdf</a></p>\n\n<p><img src=\"https://storage.googleapis.com/kaggle-forum-message-attachments/347834/9694/reference.png\" alt=\"enter image description here\"></p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 349767,
      "author_name": "hengck23",
      "author_url": "",
      "post_date": "06/28/2018 15:57:34",
      "content": "<p>results and code:\n   <img src=\"https://storage.googleapis.com/kaggle-forum-message-attachments/349767/9718/Slide1.png\" alt=\"enter image description here\"></p>\n\n<p><img src=\"https://storage.googleapis.com/kaggle-forum-message-attachments/349767/9720/Slide2.png\" alt=\"enter image description here\"></p>\n\n<p><img src=\"https://storage.googleapis.com/kaggle-forum-message-attachments/349767/9719/Slide3.png\" alt=\"enter image description here\"></p>\n\n<p>how to use:</p>\n\n<p>fast triplet searches --&gt; merge or grow --&gt; ...</p>",
      "votes": null,
      "replies": [
        {
          "id": 349771,
          "author_name": "hengck23",
          "author_url": "",
          "post_date": "06/28/2018 16:26:13",
          "content": "<p>change threshold parameters to get more triplets at lower precision:</p>\n\n<p>you can use a classifier to score the triplets  later</p>\n\n<pre><code>Elapsed: 1.026766300201416 sec\nnum_tracklets:    12387\nnum_particle_ids: 2296\nnum_valid_ids:    1275\nnum_hits:         9794\n\n scores:               0.233 = 2888.000 / 12387.000\n coverage_at_least3:   0.844 = 1076.000 / 1275.000\n coverage          :   4.635 = 4987.000 / 1076.000\n</code></pre>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "347830": "as attached\n\n  ![enter image description here][1]\n\n\n  [1]: https://storage.googleapis.com/kaggle-forum-message-attachments/347830/9693/search.png",
    "347834": "reference:\n\nhttps://indico.cern.ch/event/658267/contributions/2881175/attachments/1621912/2581064/Farrell_heptrkx_ctd2018.pdf\n\n\n  ![enter image description here][1]\n\n\n  [1]: https://storage.googleapis.com/kaggle-forum-message-attachments/347834/9694/reference.png",
    "349767": "results and code:\n   ![enter image description here][1]\n\n   ![enter image description here][2]\n\n   ![enter image description here][3]\n\nhow to use:\n\nfast triplet searches --&gt; merge or grow --&gt; ...\n\n\n  [1]: https://storage.googleapis.com/kaggle-forum-message-attachments/349767/9718/Slide1.png\n  [2]: https://storage.googleapis.com/kaggle-forum-message-attachments/349767/9720/Slide2.png\n  [3]: https://storage.googleapis.com/kaggle-forum-message-attachments/349767/9719/Slide3.png",
    "349771": "change threshold parameters to get more triplets at lower precision:\n\nyou can use a classifier to score the triplets  later\n\n    Elapsed: 1.026766300201416 sec\n    num_tracklets:    12387\n    num_particle_ids: 2296\n    num_valid_ids:    1275\n    num_hits:         9794\n\n\t scores:               0.233 = 2888.000 / 12387.000\n\t coverage_at_least3:   0.844 = 1076.000 / 1275.000\n\t coverage          :   4.635 = 4987.000 / 1076.000"
  },
  "source": "meta"
}