{
  "fetched_at": "2026-10-19T21:58:10Z",
  "source_url": "https://www.kaggle.com/competitions/caps-in-museums-data/data",
  "pages": [
    {
      "name": "data-description",
      "content": "# Files\n\n## unique_types.csv \nThis file represents the unique museum object types that can be predicted. All types are in Estonian language.\n\n## train.csv \nTraining set that should be used to build your machine learning models. The training set includes both the descriptive variables of the museum object and the ground truth about the ``type`` of the object. \n\n## test.csv \nTest set should be used to see how well your model performs on unseen data. The test set includes the descriptive variables about the objects but not the ``type`` of the object. It is your job to predict it using the model you built on the training data!\n\n## sample_submission.csv\nAn example of what the submission file should look like. For every row in the test data, submission files should contain two columns: ``id`` (representing the id of the museum object) and ``type`` (representing the **type** of the object). Example format:\n\n``id, type``\n\n``2652198, foto``\n\n``3851731, kiri``\n\n``Etc.``\n\n*NB: the types in the sample file are picked randomly*.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "Estonian government AI testbed competition invites everyone with expertise in data science and analysis to join an experimental testbed to find solutions to real-world problems using open data. We look forward to welcoming a range of specialists to come and work with us and become part of one of the most technologically advanced government projects in Europe contributing to the development of AI Gov stack that benefits people across the globe. The AI testbed competition encompasses various works in the fields of data science, machine learning, and language technology, that open a way to contribute and become a part of developing the open-source AI Govstack. \n\nPick a competition you are interested in and help us to build the coolEST and brightEST digital state!\n\n# Background \nAmong European countries, Estonia has the most museums per 100,000 inhabitants.  \nYou can visit them physically or take a virtual trip via the Estonian museums information system to explore the abundant choice of collections. \n\nThe Estonian museums information system [MuIS](https://www.muis.ee/en_GB/) is the online gateway to Estonian museums, giving everybody an opportunity to study the collections of the institutions that have joined the system. \n\nThe information system contains almost 4 million objects, but not all of the objects are labeled ideally. Manual improvement of such state would take years. Thus, we ask you to help us by creating a smart model to fill in the gaps in the data based on existing descriptive variables.  \nLet’s improve Estonian museums information system and preserve Estonia’s cultural heritage altogether!\n\n# Goal\nThe goal of this competition is to create a model to predict the *`type`* of the museum object based on its descriptive variables. \n\n\n# Praise\n* The best solutions will be publicly introduced to Estonian public sector.\n* The best solutions become a part of Estonian e-government [code repository]( https://koodivaramu.eesti.ee/explore/projects).\n* Social impact by creating a solution which would benefit a society as a whole.\n* Chance to virtually meet top Estonian data scientists and build your network.\n\n\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "# Metric\nThe evaluation metric for this competition is [Accuracy]( https://en.wikipedia.org/wiki/Accuracy_and_precision#In_binary_classification) – the number of correct predictions divided by the number of all predictions.\n\n# Submission format\nYou should submit a csv file with the same number of rows + header row as in test.csv file. For every row in the test data, submission files should contain two columns: ``id`` (representing the id of the museum object) and ``type`` (representing the **type** of the object). Example format:\n\n``id, type``\n\n``2652198, foto``\n\n``3851731, kiri``\n\n``Etc.``\n\nIn the example above, we say that object with id **2652198** has a type **foto**. All unique types are described in ``unique_types.csv`` (read more under data section). \n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "# Open code\nThis competition is all about openness and you should be willing to publish your code. The easiest way to do this is to publish your solution as a Kaggle notebook. This is easily done by going to the “Code” tab within a competition’s page and then clicking “New Notebook.” \n\n# Team limits\nThere is no minimum limit to the team size (you can work alone if you wish to do so).\n\n# Submission limits\n\n* You may submit a maximum of 5 entries per day.\n* You may select up to 2 final submissions for judging.\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}