{
  "fetched_at": "2026-10-19T19:00:57Z",
  "source_url": "https://www.kaggle.com/competitions/Covid19-Death-Predictions/data",
  "pages": [
    {
      "name": "data-description",
      "content": "## Overview \n\nThe data contains cases, deaths, and vaccinations information about a region in a week. The weeks do not necessarily start with Monday.\n\nThe timeframe for the data is between the 27th of January 2020 to the 30th of June 2022 for feature columns, and between the 3rd of February 2020 to the 7th of July 2022 for the \"Next Week's Deaths\" column.\n\n## What am I predicting?\n\nParticipants are predicting the next week's deaths for a region.\n\n## Important notes\n\nThe rows containing non-available(n/a) data for the \"Next Week's Deaths\" column have been removed from the dataset. However, there are still rows containing zero value in the \"Next Week's Deaths\" column.\n\nThere are many n/a values in feature columns in both train and test datasets, so it is definitely worth checking into.\n\nMonth and day part of the date has been removed from datasets to prevent leakage.\n\n## Files\n\n*   **train.csv** - the training set\n*   **test.csv** - the test set\n*   **sample_submission.csv** - a sample submission file in the correct format\n\n## Columns\n\nId => Unique id for each row\n\nLocation => Name of the country/region/group of people\n\nYear  => Year of the start of the week is in\n\n# Cases\nWeekly Cases  => Weekly new confirmed cases of COVID-19. Counts can include probable cases, where reported. In rare cases where the source reports a negative daily change due to a data correction, the metric is set to n/a.\n\nWeekly Cases per Million => \"Weekly Cases\" per 1,000,000 people in the total population of the location\n\n# Deaths\nWeekly Deaths => Weekly new deaths attributed to COVID-19. Counts can include probable deaths, where reported. In rare cases where our source reports a negative daily change due to a data correction, the metric is set to n/a.\n\nWeekly Deaths per Million => \"Weekly Deaths\" per 1,000,000 people in the total population of the location\n\nNext Week's Deaths => Weekly Deaths for the next week. Counts can include probable deaths, where reported\n\n# Vaccinations\n\nTotal Vaccinations => Total number of doses administered. For vaccines that require multiple doses, each individual dose is counted. If a person receives one dose of the vaccine, this metric goes up by 1. If they receive a second dose, it goes up by 1 again. If they receive a third/booster dose, it goes up by 1 again\n\nPeople Vaccinated => Total number of people who received at least one vaccine dose. If a person receives the first dose of a 2-dose vaccine, this metric goes up by 1. If they receive the second dose, the metric stays the same\n\nPeople Fully Vaccinated => Total number of people who received all doses prescribed by the initial vaccination protocol. If a person receives the first dose of a 2-dose vaccine, this metric stays the same. If they receive the second dose, the metric goes up by 1\n\nTotal Boosters => Total number of COVID-19 vaccination booster doses administered (doses administered beyond the number prescribed by the initial vaccination protocol)\n\nDaily Vaccinations => New doses administered per day (7-day smoothed). For countries that don't report data on a daily basis, we assume that doses changed equally on a daily basis over any periods in which no data was reported. This produces a complete series of daily figures, which are then averaged over a rolling 7-day window\n\nTotal Vaccinations per Hundred => \"Total Vaccinations\" per 100 people in the total population of the location\n\nPeople Vaccinated per Hundred => \"People Vaccinated\" per 100 people in the total population of the location \n\nPeople Fully Vaccinated per Hundred => \"People Fully Vaccinated\" per 100 people in the total population of the location\n\nTotal Boosters per Hundred => \"Total Boosters\" per 100 people in the total population of the location\n\nDaily Vaccinations per Hundred => \"Daily Vaccinations\" per 100 people in the total population of the location\n\nDaily People Vaccinated => Daily number of people receiving a first COVID-19 vaccine dose (7-day smoothed).\n\nDaily People Vaccinated per Hundred => \"Daily People Vaccinated\" per 100 people in the total population of the location\n\n\n\n\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "There have been more than half a billion cases of COVID-19 cases resulting in more than 6 million deaths. The goal of this competition is to predict next week's deaths to hopefully provide insight into epidemiology.  We believe this problem is also a great way to practice data science skills.\n\nHere is a handy link to Kaggle's [competition documentation](https://www.kaggle.com/docs/competitions), which includes, among other things, instructions on [submitting predictions](https://www.kaggle.com/docs/competitions#making-a-submission).\n\nYou may see [important dates](https://fraser.stlouisfed.org/timeline/covid-19-pandemic) about COVID-19 pandemic.\n\nYou may get more information about [COVID-19](https://en.wikipedia.org/wiki/COVID-19).\n\nWe will be sharing the notebook that we used to create the dataset after the competition ends for use by anyone interested.\n\n## Acknowledgements\n\nWe thank Our World in Data for providing the datasets that are used to create the competition.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The evaluation metric for this competition is [RMSE](https://en.wikipedia.org/wiki/Root-mean-square_deviation). \n\nThe Root Mean Square Error or Root Mean Square Deviation is the square root of the Mean Square Error(MSE). Mean Square Error is the sum of squares of differences between predictions and true values, divided by the number of prediction/true values.\n\n RMSE = \\sqrt{\\frac{\\sum_{1}^{^{T}} (y_{true}-y_{prediction})^{2}}{T}}\n\n## Submission Format\n\nSubmission files should contain two columns `Id` and `Next Week's Deaths`.\n\nThe submission file should contain a header.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "Use of any external data except COVID-19 deaths data is allowed and encouraged.\n\nHave fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Timeline",
      "content": "**- 08/19/2022 11:00 PM UTC** - Final Submission Deadline\n**- 08/19/2022 11:01 PM UTC** - Private Leaderboard Release Date",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}