{
  "fetched_at": "2026-10-20T08:17:48Z",
  "source_url": "https://www.kaggle.com/competitions/drinking-water-quality/data",
  "pages": [
    {
      "name": "data-description",
      "content": "# Overview\nThe data has been split into two groups:\n\n* **Training set (train.csv)**\n* **Test set (test.csv)**\n\n**The training set** should be used to build your machine learning models. The training set includes both the features and the result variable (`compliance_2021`).\n\nIf you succeed in building a good machine learning model, then you have created a model that enables to predict the quality of the next test based on the metrics of previous tests.\n\n**The test set** should be used to see how well your model performs on unseen data. The test set doesn’t include the result variable. It is your job to predict it using the model you built on the training data!\n\nWe also include **sample_submission.csv** - an example of what the submission file should look like (the predictions in the sample file are picked randomly).\n\n# Features\nThe features include various numeric metrics (e.g. color, smell, ph-level, coli-type bacteria) from previous water tests that are used by the inspectors to define whether the quality is compliant with the regulation. For each water station, you have information about the test results of the years 2019 and 2020. The corresponding year number is added at the end of each variable name.  In addition, you have the information about the compliance of the station in 2019 (`compliance_2019`) and 2020 (`compliance_2020`). The result variable is `compliance_2021`.\n\nNB: There are many missing values (not all of the variables are always tested in each station). Choose your own approach of how to deal with them.\n ",
      "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 Gov-stack. \nPick a competition you are interested in and help us to build the coolEST and brightEST digital state!\n\n#  Background\nDespite the fact that most of our planet is covered with water, not more than 3 % of this amount is fresh. To make sure that the water is safe to drink the Estonian Health Board has been measuring its quality in more than thousand water stations across the country thereby making sure that every citizen will get the freshest water right from their tap. \nTo bring water quality measurement to the next level and automate working process of Estonian water inspectors, we would like to invent predictive water quality model that would enable us to prioritize the tests or react proactively to the deterioration of the water conditions. Therefore, enhancing the role of scientific and data-driven approach on a governmental level.\n\n# Goal\nThe goal of this competition is to create a model that predicts the water quality in Estonian water stations based on the government’s open data of the previous measurements. \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",
      "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 dataset, submission files should contain two columns: ``station_id`` (representing the id of the water station) and ``compliance_2021`` (representing the prediction about the compliance of the water quality):\n* 0 – water quality in 2021 is **compliant** with the regulation.\n* 1 – water quality in 2021 is **not-compliant** with the regulation.\nThe file should contain a header and have the following format:\n\n```\nstation_id, compliance_2021\n165, 1\n123, 0\nEtc.\n```\nNB: the `compliance_2021` values will be treated as strings. Make sure that your result is presented without commas (1.0 is not the same as 1).",
      "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* You may submit a maximum of 5 entries per day.\n* You may select up to 3 final submissions for judging.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}