geossm.datasets.load_dataset

geossm.datasets.load_dataset(name, return_geometry=True)[source]

Load one of the example datasets bundled with geossm.

Parameters:

  • name (str) – Dataset identifier, e.g. "agrimonia". See list_datasets for the full list of names currently bundled with the package.

  • return_geometry (bool, default True) – If True, also return the dataset’s region shapefile (e.g. an administrative boundary) as a geopandas.GeoDataFrame, when one is available for name. If False, only the observations table is returned.

Returns:

  • df (pandas.DataFrame or geopandas.GeoDataFrame) – The dataset’s observations, as stored in its Parquet file.

  • gdf (geopandas.GeoDataFrame) – The dataset’s region shapefile. Only returned when return_geometry is True.

Raises:

ValueError – If name is not one of the bundled dataset identifiers.