Weather-Saaleaue

Weather measures from Saaleaue provided by the Max-Planck-Institute for Biogeochemistry. Several weather measures provided by Max-Planck-Institute for Biogeochemistry from the Weather Station on Top of the Roof of the Institute Building. We have assembled all the files available as of 24-05-2024 on https://www.bgc-jena.mpg.de/wetter/weather_data.html There are 32 columns: id_series: The id of the time series. date: The date of the time series in the format "%Y-%m-%d %H:%M:%S". time_step: The time step on the time series. value_X (X from 0 to 20): The values of the time series, which will be used for the forecasting task. Preprocessing: 1 - Renamed column 'Date Time' to 'date' 2 - Parsed the date with the format '%d.%m.%Y %H:%M:%S' and converted it to string with format %Y-%m-%d %H:%M:%S. 3 - Replaced values of -9999 to nan. Values of -9999 seems to indicate a problem with the measure. Besides, it seems that some measures only started to be collected later on the year of 2002. 4 - Renamed columns [1:] to 'value_X' with X from 0 to 20. 5 - Rounded 'date' to the nearest 10 minutes. Some 'date' values were not exactly at 10 minutes frequency (offset by some seconds or by 1 minute for '2011-09-26 13:41:00', '2012-07-24 06:51:00', '2013-08-23 10:11:00'). 6 - Created 'id_series' with value 0. There is only one multivariate time series. 7 - Ensured that there are no missing dates and that the frequency of the time_series is 10 minutes. Filled the missing dates with NaNs. 8 - Created 'time_step' column from 'date' and 'id_series' with increasing values from 0 to the size of the time series. 9 - Casted 'date' to str, 'time_step' to int, 'value_X' to float, and defined 'id_series' as 'category'.