{
  "fetched_at": "2026-10-19T09:17:45Z",
  "source_url": "https://www.kaggle.com/competitions/2023-gwdata-bootcamp/data",
  "pages": [
    {
      "name": "data-description",
      "content": "All files except for the `test.npy` can be found at the repo ([https://github.com/iphysresearch/GWData-Bootcamp/tree/main/2023/deep_learning/baseline](https://github.com/iphysresearch/GWData-Bootcamp/tree/main/2023/deep_learning/baseline))\n\n## Files\n\n*   **data_prep_bbh.py** - script for data generation (credit: [Dr. Hunter Gabbard](https://github.com/hagabbar/cnn_matchfiltering/))\n*   **utils.py** - supplemental script containing some useful functions\n*   **main.py** - main script for training/evaluation/submission\n*   **test.npy** - test data for submission (300MB)\n\nYou can use the test data in the Kaggle notebook as follows\n\n```python\nimport numpy as np\ntest_dataset = np.load('/kaggle/input/2023-gwdata-bootcamp/test.npy')\n```\n\n## Hints\n\nSome useful information about `test.npy` dataset\n\n- SNR: 2 4 5 6 7 8 9 10 15 20 25 30\n- num of injections: ~600 of 1200 samples\n- `astro_metric`\n- positive vs negative ~ 1:1\n\n---\n\nAnyway, just check the top notebook for everything!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "Submissions are evaluated on **AUC** ([area under the ROC curve](http://en.wikipedia.org/wiki/Receiver_operating_characteristic)) between the predicted probability and the observed target.\n\n\n## Submission File\nFor each ID in the test set, you must predict a probability for the TARGET variable. The file should contain a header and have the following format:\n\n    ID,TARGET\n    2,0\n    5,0\n    6,0\n    etc.\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "Basic rules like:\n\n - Don't cheat!（其实不限制，随便怎么搞，“不择手段的“把 AUC 成绩提上去！）\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "Welcome to the final challenge of the *[Gravitational Wave Data Exploration: A Practical Training in Programming and Analysis](https://github.com/iphysresearch/GWData-Bootcamp/)* (2023) - \"**Can you find the GW signals?**\" Kaggle Data Science Competition (Hackathon)! This competition is designed to apply the knowledge and skills you've learned throughout the course, focusing on gravitational wave data analysis and research.\n\n\n# Objective\n\nThe objective of this competition is to develop a model that can accurately identify gravitational wave signals from the provided dataset. You will be given a dataset containing a mix of noise and gravitational wave signals. Your task is to develop a model that can accurately distinguish between the two.\n\n\n# 概述\n\n欢迎参加“*[引力波数据探索：编程与分析实战训练营](https://github.com/iphysresearch/GWData-Bootcamp/)*”系列课程的最后挑战 - “**你能找到引力波信号吗？**”Kaggle数据科学竞赛（黑客马拉松）！这个竞赛旨在应用你在整个课程中学到的知识和技能，重点关注引力波数据分析和研究。\n\n# 任务目标\n\n本次竞赛的目标是开发一个能够准确识别引力波信号的模型。我们将提供一个包含噪声和引力波信号的数据集。你的任务是开发一个能够准确区分两者的模型。\n\n\n---\n\n\n# Timeline\n\nThis competition will start at 10:00 PM (Beijing Time) on December 29, 2023, and end at 11:59 PM (Beijing Time) on January 6, 2024. Please make sure to submit your solutions before the deadline.\n\nGood luck and may the best team win!\n\n# 时间线\n\n本竞赛将于**北京时间 2023年12月29日22:00** 开始，并于**北京时间 2024年1月6日23:59** 结束。请确保在截止日期前提交你的解决方案。\n\n\n祝你好运，排名靠前的团队将会有丰厚礼品等着你！",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}