{
  "fetched_at": "2026-10-19T10:52:40Z",
  "source_url": "https://www.kaggle.com/competitions/air-toxicity-and-chronic-respiratory-diseases-us/data",
  "pages": [
    {
      "name": "data-description",
      "content": "# Dataset Description for \"Air Toxicity and Chronic Respiratory Diseases (US)\"\n\nWelcome to the dataset description page for the Kaggle competition \"Air Toxicity and Chronic Respiratory Diseases (US)\". Here we provide detailed information about the data files, format, the prediction task and definitions of acronyms used.\n\n## Files\n\n- **train.csv** - This is the training set, which you will use to build your models. It contains various features along with the target variable that represents the prevalence of chronic respiratory diseases.\n\n- **test.csv** - The test set contains the same features as the training set but without the target variable. You will use this to generate your predictions.\n\n- **sample_submission.csv** - This is a sample submission file in the correct format. It includes all the IDs from the test set and assumes a constant prediction for the target variable.\n\n- **State.Names.csv** - This file provides a list of all U.S states referenced in the data.\n\n- **supplementary_*.parquet** - These are supplementary files containing additional features that can be merged with the main training and test sets based on the 'example_id'.\n\n## Columns\n\n### train.csv\n\n- `ID` - The ID representing each record in the dataset. This ID is consistent across `train.csv`, `test.csv`, and the supplementary files.\n\n- `State.Name` - The name of the U.S. state where the data was recorded.\n\n- `Year` - The year when the data was recorded.\n\n- `Age` - The age group of the elderly population for which the data is recorded. Age is grouped into ranges, for example, \"65-69\", \"70-74\", etc.\n\n- `Incidence` - This is the target variable representing the incidence rate of chronic respiratory diseases in the given age group. This means how many new cases there are in a year divided by how many people there are in the middle of the year.\n\n### test.csv\n\n- `ID` - The ID representing each record in the dataset. This ID is consistent across `train.csv`, `test.csv`, and the supplementary files.\n\n- `State.Name` - The name of the U.S. state where the data was recorded.\n\n- `Year` - The year when the data was recorded.\n\n- `Age` - The age group of the elderly population for which the data is recorded. Age is grouped into ranges, for example, \"65-69\", \"70-74\", etc.\n\n### supplementary_*.parquet\n\n- `State.Name` - The name of the U.S. state where the data was recorded.\n\n- `Date.Local` - The local date when the measurements were taken.\n\n- `Parameter.Name` - The name or description assigned in AQS to the parameter measured by the monitor. Parameters may be pollutants or non-pollutants.\n\n- `Arithmetic.Mean` - The average (arithmetic mean) value for the year for the given parameter.\n\n- `X1st.Max.Value` - The highest value for the year for the given parameter.\n\n## Data Cleaning\nData cleaning was performed using the following GitHub repository: [Data Cleaning](https://github.com/josephcmac/chronic-respiratory-diseases)",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "Welcome to the Air Toxicity and Chronic Respiratory Diseases Kaggle competition! This competition is designed to challenge and inspire you to apply data science techniques in uncovering the underlying connections between air toxicity, specifically lead concentration, and the incidence of chronic respiratory diseases in the elderly population across the US. The dataset we provide for this competition combines data from the Global Burden of Disease (GBD) Results tool and the United States Environmental Protection Agency (EPA), giving you a unique opportunity to explore the multifaceted dynamics of health and environment. \n\n## About The Task\n\nYour task is to develop a predictive model that can accurately predict the incidence of chronic respiratory diseases based on the given air toxicity parameters and other relevant variables. The 'Incidence' rate is the number of new cases divided by the population at the middle of the year for that age group and state.\n\nUse the `train.csv` file to train your models, and make predictions on the `test.csv` dataset. The data has been split into training and testing sets to ensure fair evaluation of your model. Please make sure you understand the dataset structure, variables, and supplementary data provided.\n\n## How to Contribute to the Scientific Knowledge\n\nThe way to contribute to the scientific knowledge is to share the notebooks with the EDA and prediction models. Thus, epidemiologists can find your notebooks and use your data analysis and model in their research. Participants are encouraged to use external data on air pollution. However, external public health data should be avoided so that the model has environmental data as input and public health data as output.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "Submissions are evaluated on [Spearman's rank correlation coefficient](https://en.wikipedia.org/wiki/Spearman%27s_rank_correlation_coefficient) between the predicted and the observed incidences of chronic respiratory diseases. \n\nSpearman's rank correlation coefficient measures the strength and direction of association between two ranked variables. It is a nonparametric measure of rank correlation. Its values range from -1 to 1, where 1 denotes perfect positive association, -1 denotes perfect negative association, and 0 denotes no association.\n\nThe team with the highest Spearman's rank correlation coefficient will be declared the winner.\n\n## Submission File\nFor each ID in the test set, you must predict the incidence of the chronic respiratory disease. The file should contain a header and have the following format:\n\n```python\n    ID,Incidence\n    f8312a4,4827.05\n    3effa36,4827.05\n    1e8044b,4377.95\n    etc.\n```\n\nPlease ensure that your submission file has predictions for all the records in the test dataset and follows the correct format. Incomplete submissions or those not adhering to the correct format will be scored as zero.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "**One account per participant**\nYou cannot sign up to Kaggle from multiple accounts, and therefore you cannot submit from multiple accounts.\n\n**No private sharing outside teams**\nPrivately sharing code or data outside of teams is not permitted. It's okay to share code if made available to all participants on the forums.\n\n**Prizes**\nThere are no prizes for this competition.\n\n**External data**\nThe use of external datasets is allowed and encouraged as long as the external data is about the environment, e.g., air pollution, and not about public health, e.g., the incidence rate that is the solution of the problem.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "References",
      "content": "**References**\nBelow are references to the data sets we used for this competition. Our use of these datasets is non-commercial and motivated by educational and scientific purposes only.\n\n**GBD Results tool:**\n*Global Burden of Disease Collaborative Network.*\n*Global Burden of Disease Study 2019 (GBD 2019) Results.*\nSeattle, United States: Institute for Health Metrics and Evaluation (IHME), 2020.\nAvailable from: [https://vizhub.healthdata.org/gbd-results?params=gbd-api-2019-permalink/4236f14fa0a1ca16f5588ff87364c591](https://vizhub.healthdata.org/gbd-results?params=gbd-api-2019-permalink/4236f14fa0a1ca16f5588ff87364c591)\n\n**AQS Data:**\n*United States Environmental Protection Agency (EPA).* \n*Toxics, Precursors, and Lead Data.* \nUnited States Environmental Protection Agency, 2023. \nAvailable from: [https://aqs.epa.gov/aqsweb/airdata/download_files.html](https://aqs.epa.gov/aqsweb/airdata/download_files.html)",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}