{
  "fetched_at": "2026-10-19T16:13:07Z",
  "source_url": "https://www.kaggle.com/competitions/9oct23jh-genomics/data",
  "pages": [
    {
      "name": "data-description",
      "content": "Read more about Genomics dataset here: https://www.tensorflow.org/datasets/catalog/genomics_ood",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "# Hi Class.\n \nYour goal is to classify two bacteria based on their DNA sequences. See Rules tab for guidelines, grading, submission details, and the starter Colab notebook. This private in-class competition is strictly for HSE students, Fall 2021. You are encouraged to learn from other competitions in Kaggle or elsewhere, but keep your modeling constrained by rules of this competition.\n\n\n## Acknowledgements\n1. We thank TensorFlow team for making [Genomics_ood dataset](https://www.tensorflow.org/datasets/catalog/genomics_ood) available.\n1. Illustration is from https://www.genome.gov/genetics-glossary/acgt\n1. **Competition Authors**: [Oleg Melnikov](https://www.linkedin.com/in/olegmelnikov/), [Alexey Boldyrev](https://www.hse.ru/org/persons/223985242), [Vladimir Kirillin](https://www.hse.ru/org/persons/499313273), [Sergey Chervontsev](https://www.hse.ru/org/persons/305134539), [Maria Tikhonova](https://www.hse.ru/org/persons/218372994), Mikhail Makarov, [Daniil Vankov](https://www.hse.ru/org/persons/137289166), Margarita Lazareva, Tatyana Yazykova, Mike Ovyan, Lika Lomidze, Vladimir Novikov, Valeriya Rogovchenko",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The evaluation metric is <a href=\"https://scikit-learn.org/stable/modules/generated/sklearn.metrics.accuracy_score.html\">accuracy score</a>, which is the default classification accuracy in `sklearn` library.\n\nExample submission file:\n\n        id,y\n        0,0\n        1,0\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "Please follow **[these guidelines](https://colab.research.google.com/drive/1riOGrE_Fv-yfIbM5V4pgJx4DWcd92cZr?usp=sharing)** to avoid penalties. This [**Python Starter Colab**](https://colab.research.google.com/drive/1JMaJkTxxafsY_dep-4vQY-rH7YH1xGDz?usp=sharing) generates a baseline submission (CSV) file. Have fun! \n \n## 𝓐𝓵𝓵𝓸𝔀𝓮𝓭 𝓜𝓸𝓭𝓮𝓵𝓼 𝓪𝓷𝓭 𝓔𝓷𝓰𝓲𝓷𝓮𝓮𝓻𝓲𝓷𝓰:\n1.  **DNN models covered so far via TF, (any popular) sentence embeddings, and transfer learning** (See HOML10-12). Ok to use SVC variants from SKLearn or TF.\n1. You can also use clustering algorithms and dimensions reduction algorithms\n1. Ok to engineer features, tune hyperparameters/optimizers, sub/oversample, regularize, do stepwise selection, reduce dimensions, use CPU/GPU/TPU.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}