{
  "fetched_at": "2026-10-19T21:47:29Z",
  "source_url": "https://www.kaggle.com/competitions/edsa-individual-electricity-shortfall-challenge/data",
  "pages": [
    {
      "name": "data-description",
      "content": "<h2>Data Description</h2>\n\n\n\n<p>This dataset contains information about the weather conditions in various Spanish cities for the time of 2015-2017. The dataset also has information about the three hourly load shortfalls for the same period. In the context of this problem, the three hourly load shortfall is the difference between the energy generated by means of fossil fuels and renewable sources. </p>\n<p>\nThe dataset contains 47 features and 1 target. The features include the time and the city-specific weather variables i.e. the wind speed in the city of Barcelona. In total there is weather data available for 5 cities but not all cities have weather information available for every weather category e.g. we might have wind speed data for Barcelona but not rainfall data whereas we have both rainfall and wind speed information for Valencia.\n</p>\n\n<p>We have weather data for the following cities of Spain:</p>\n\n<ul>\n<li>Madrid</li>\n<li>Valencia</li>\n<li>Seville</li>\n<li>Bilbao</li>\n<li>Barcelona</li>\n</ul>\n\nThe weather categories in the dataset include:\n<ul>\n<li>wind_speed</li>\n<li>wind_degree</li>\n<li>rain_1h</li>\n<li>rain_3h</li>\n<li>humidity</li>\n<li>clouds_all<l/i>\n<li>pressure<l/i>\n<li>snow_3h<l/i>\n<li>weather_id<l/i>\n<li>temp_max<l/i>\n<li>temp<l/i>\n</ul>\n\n<h2>File descriptions</h2>\n<ul>\n<li><strong>df_train.csv</strong> - the training set</li>\n<li><strong>df_test.csv</strong> - the test set</li>\n<li><strong>sample_submission_load_shortfall.csv</strong> - a sample submission file in the correct format</li>\n</ul>\n\n<h2>Features</h2>\n\n<p>Below follows a brief description of the features and targets contained in the dataset.<p>\n\n<ul>\n<li><strong>time:</strong> Time at which the data was recorded</li>\n<li><strong>{City Name}_wind_speed:</strong> The wind speed at a specific time interval for the named city.</li>\n<li><strong>{City Name}_wind_degree: </strong>The strength of the wind for the named city at a specific time interval - expressed as a category.</li>\n<li><strong>{City Name}_rain_1h:</strong> A metric expressing the amount of rain that has fallen in the past hour in a particular city.</li>\n<li><strong>{City Name}_rain_3h:</strong>A metric expressing the amount of rain that has fallen in the past three hours in a particular city.</li>\n<li><strong>{City Name}_humidity:</strong> The level of humidity as measured at the defined time for the specific city mentioned.</li>\n<li><strong>{City Name}_clouds_all:</strong> The level of cloud coverage as measured at the specified point in time for the specific city mentioned.</li>\n<li><strong>{City Name}_pressure:</strong> The atmospheric pressure for the named city at a specific time interval - expressed as a category.</li>\n<li><strong>{City Name}_snow_3h:</strong> A metric expressing the amount of snow that has fallen in the past three hours in a particular city.</li>\n<li><strong>{City Name}_weather_id: </strong>A metric used to explain the weather condition of a specific city at a specified time.</li>\n<li><strong>{City Name}_temp_max: </strong>The maximum temperature for a specific city at a point in time.</li>\n<li><strong>{City Name}_temp_min:</strong> The minimum temperature for a specific city at a point in time.</li>\n<li><strong>{City Name}_temp:</strong> The average temperature for a specific city at a point in time.</li>\n</ul>\n\n\n<h2>Target Variable</h2>\n\n<li><strong>load_shortfall_3h:</strong> The difference between the energy generated by the method of renewable energy sources, such as solar, wind, geothermal, etc., and energy generated with fossil fuels - partitioned in three-hour windows.</li>\n\n\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "The supply of electricity plays a large role in the livelihood of citizens in a country. Electricity, amongst other things, helps us stay connected, keep warm, and feed our families. Therefore there's a need to keep the lights on in order to maintain and improve the standard of living by investing in electricity infrastructure. However, in recent years, there has been evidence that the use of purely non-renewable sources is not sustainable.\n\nThe government of Spain is considering an expansion of its renewable energy resource infrastructure investments. As such, they require information on the trends and patterns of the country's renewable sources and fossil fuel energy generation. For this very reason, the government of Spain has been tracking the different energy sources available within the country.\n\nIn this project, you are tasked to model the shortfall between the energy generated by means of fossil fuels and various renewable sources - for the country of Spain. The daily shortfall, which will be referred to as the target variable, will be modelled as a function of various city-specific weather features such as `pressure`, `wind speed`, `humidity`, etc.\n\n![Electricity_Pylon](https://cdn.pixabay.com/photo/2019/01/06/13/07/electricity-pylon-3916954_960_720.jpg)\n\n<h2>Acknowledgements</h2>\n<p>The original data was sourced from <a href=\"https://www.kaggle.com/nicholasjhana/energy-consumption-generation-prices-and-weather\">Kaggle</a></p>\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<hr>\n<p>The evaluation metric for this competition is <a href=\"https://surprise.readthedocs.io/en/stable/accuracy.html\"> Root Mean Square Error</a>. \n\nRoot Mean Square Error (RMSE) is commonly used in regression analysis and forecasting and measures the standard deviation of the residuals arising between predicted and actual observed values for a modeling process.  \n\n$$ RMSE = \\sqrt{\\frac{1}{N} \\sum_{i=0}^{N}{(y_{i}-\\hat{y}_{i})^2}} $$\n    \n</p><h2> Submission Format </h2>\n\nThe submission file should contain two columns: `time` and `load_shortfall_3h`. The `time` field is given in the test file and `load_shortfall_3h` is the predicted load shortfall over a 3 hour period<p></p>\n<p>The file should contain a header and have the following format:</p>\n<pre>time,load_shortfall_3h\n2018-01-01 00:00:00,13.94<br></pre>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "This is a private hackathon, whose primary purpose is for the members of the EXPLORE Data Science Academy to apply what they have learned. \n\nYou may use additional datasets from those provided within this competition. These datasets must be collected from public sources or must be in the public domain. Your solution must use machine learning with an emphasis on regression algorithms and their related techniques.\n\nParticipation within this competition occurs on a group level for full-time students, and on an individual basis for part-time students.\n\nMultiple accounts per user are not allowed. Collaboration across individuals in the same team is permitted for full-time students.  Collaboration between members of different teams is not permitted for full or part-time students. \n\nCode may not be shared in any public or private setting during or after the hackathon.\n\nThe solution must use publicly-available, open-source packages only. Maximum 20 solutions submitted per day. Your highest-scoring solution will be the one by which you are judged.\n\nRefer to the FAQs and Terms of Use for additional rules that may apply to this competition.\n\nWe reserve the right to modify these rules at any time as necessary.\n - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}