{
  "id": 89324,
  "title": "65th-Place Simple Solution Without Using Data Leakage",
  "content": "<p>𝙷𝚒</p>\n\n<p>I had 9 submissions with different complexities. Here I'll present the winning one.</p>\n\n<p>The solution is simple. It uses <a href=\"https://github.com/blue-yonder/tsfresh\"><strong>tsfresh</strong></a> to extract and select features from our time-series data. tsfresh calculates a <em>lot</em> of features with many parameters including the minimum value of the signal, the maximum, standard deviation, approximate entropy, skewness, number of peaks, etc. </p>\n\n<p>After that, LightGBM is used to build the model and generate predictions. The generated predictions are the probabilities of each type of surfaces for each test case. The surface with the highest probability was chosen.</p>\n\n<p>The code used is available in <a href=\"https://github.com/ammar1y/My-Solution-to-Help-Navigate-Robots-Competition\">this Github repository</a> in <code>eda.ipynb</code> and <code>kernel.ipynb</code> files.</p>\n\n<p><a href=\"https://github.com/ammar1y/My-Solution-to-Help-Navigate-Robots-Competition\">https://github.com/ammar1y/My-Solution-to-Help-Navigate-Robots-Competition</a></p>",
  "comments": [
    {
      "id": 515995,
      "author_name": "dhaqui the kaggler",
      "author_url": "",
      "post_date": "2019-04-13T14:01:13.697000",
      "content": "<p>Thanks for sharing your solution and code.</p>",
      "votes": 1,
      "replies": [
        {
          "id": 516101,
          "author_name": "Ammar Alyousfi",
          "author_url": "",
          "post_date": "2019-04-13T15:59:44.997000",
          "content": "<p>You are welcome :)</p>",
          "votes": 0,
          "replies": []
        }
      ]
    }
  ],
  "comment_count": 2,
  "messages": [
    {
      "id": 515703,
      "postDate": "2019-04-13T01:33:59.743Z",
      "content": "<p>𝙷𝚒</p>\n\n<p>I had 9 submissions with different complexities. Here I'll present the winning one.</p>\n\n<p>The solution is simple. It uses <a href=\"https://github.com/blue-yonder/tsfresh\"><strong>tsfresh</strong></a> to extract and select features from our time-series data. tsfresh calculates a <em>lot</em> of features with many parameters including the minimum value of the signal, the maximum, standard deviation, approximate entropy, skewness, number of peaks, etc. </p>\n\n<p>After that, LightGBM is used to build the model and generate predictions. The generated predictions are the probabilities of each type of surfaces for each test case. The surface with the highest probability was chosen.</p>\n\n<p>The code used is available in <a href=\"https://github.com/ammar1y/My-Solution-to-Help-Navigate-Robots-Competition\">this Github repository</a> in <code>eda.ipynb</code> and <code>kernel.ipynb</code> files.</p>\n\n<p><a href=\"https://github.com/ammar1y/My-Solution-to-Help-Navigate-Robots-Competition\">https://github.com/ammar1y/My-Solution-to-Help-Navigate-Robots-Competition</a></p>",
      "rawMarkdown": "𝙷𝚒\n\nI had 9 submissions with different complexities. Here I'll present the winning one.\n\nThe solution is simple. It uses [**tsfresh**](https://github.com/blue-yonder/tsfresh) to extract and select features from our time-series data. tsfresh calculates a *lot* of features with many parameters including the minimum value of the signal, the maximum, standard deviation, approximate entropy, skewness, number of peaks, etc. \n\nAfter that, LightGBM is used to build the model and generate predictions. The generated predictions are the probabilities of each type of surfaces for each test case. The surface with the highest probability was chosen.\n\nThe code used is available in [this Github repository](https://github.com/ammar1y/My-Solution-to-Help-Navigate-Robots-Competition) in `eda.ipynb` and `kernel.ipynb` files.\n\n[https://github.com/ammar1y/My-Solution-to-Help-Navigate-Robots-Competition](https://github.com/ammar1y/My-Solution-to-Help-Navigate-Robots-Competition)",
      "votes": 5
    },
    {
      "id": 515995,
      "postDate": "2019-04-13T14:01:13.697Z",
      "content": "<p>Thanks for sharing your solution and code.</p>",
      "rawMarkdown": "Thanks for sharing your solution and code.",
      "votes": 1,
      "replies": [
        {
          "id": 516101,
          "postDate": "2019-04-13T15:59:44.997Z",
          "content": "<p>You are welcome :)</p>",
          "rawMarkdown": "You are welcome :)"
        }
      ]
    }
  ],
  "complete": true,
  "source": "live",
  "fetched_at": "2026-10-19T15:43:21Z",
  "competition_id": 13242,
  "competition_slug": "career-con-2019",
  "team_id": 2944502,
  "solution_url": "/competitions/career-con-2019/writeups/ammar-alyousfi-65th-place-simple-solution-without-"
}