geovalidate.ConstantClassSampler¶

class geovalidate.ConstantClassSampler(n_per_class=100, quasi_random=None, random_state=None)[source]¶

Sample exactly n_per_class points from each class.

Accepts a geopandas.GeoSeries / geopandas.GeoDataFrame paired with a labels vector, or a rasterio dataset paired with a 2-D numpy array of class labels read from the desired band.

Parameters:¶

n_per_class : int, default 100¶: Exact number of points to generate per class.
quasi_random : str or None¶
random_state : int, RandomState instance, or None¶

Examples

GeoDataFrame path:

pts = ConstantClassSampler(n_per_class=50).sample(
    gdf.geometry, gdf["lc_class"]
)

Raster path – read the band yourself, pass it as labels:

with rasterio.open("landcover.tif") as ds:
    pts = ConstantClassSampler(n_per_class=50).sample(ds, ds.read(1))

__init__(n_per_class=100, quasi_random=None, random_state=None)[source]¶

Methods

`__init__`([n_per_class, quasi_random, ...])
`get_metadata_routing`()	Get metadata routing of this object.
`get_params`([deep])	Get parameters for this estimator.
`sample`(geometry[, labels])	Generate balanced class samples.
`set_params`(**params)	Set the parameters of this estimator.

get_metadata_routing()[source]¶

Get metadata routing of this object.

Please check User Guide on how the routing mechanism works.

Returns:¶: routing – A MetadataRequest encapsulating routing information.
Return type:¶: MetadataRequest

get_params(deep=True)[source]¶

Get parameters for this estimator.

Parameters:¶

deep : bool, default=True¶: If True, will return the parameters for this estimator and contained subobjects that are estimators.

Returns:¶

params – Parameter names mapped to their values.

Return type:¶

dict

sample(geometry, labels=None)[source]¶

Generate balanced class samples.

Parameters:¶

geometry : GeoSeries | GeoDataFrame | rasterio.DatasetReader | path-like¶: Spatial source. For the raster path a DatasetReader (or file path) is used for its transform / CRS / nodata metadata only – no band is read from it here.
labels : array-like of shape (n,) or 2-D ndarray, required¶: Class label for each geometry (GDF path) or a 2-D numpy array of integer class labels with shape (nrows, ncols) (raster path, e.g. ds.read(1)).

Returns:¶

Columns: geometry, class_label.

Return type:¶

geopandas.GeoDataFrame

set_params(**params)[source]¶

Set the parameters of this estimator.

The method works on simple estimators as well as on nested objects (such as Pipeline). The latter have parameters of the form <component>__<parameter> so that it’s possible to update each component of a nested object.

Parameters:¶

**params : dict¶: Estimator parameters.

Returns:¶

self – Estimator instance.

Return type:¶

estimator instance