GeodataPostprocessor

`GeodataPostprocessor`

Bases: ABC, FromConfigMixin

Abstract class for geodata postprocessors

Geodata postprocessors are callables that postprocess geodata. The geodata postprocessor is used by the pipeline to postprocess the resulting geodata, which is the vectorized output of the model's inference.

Currently implemented geodata postprocessors

ClipPostprocessor: Clips the polygons based on the mask extent
CompositePostprocessor: Composes multiple geodata postprocessors
FieldNamePostprocessor: Renames the fields
FillPostprocessor: Fills holes in the polygons
SievePostprocessor: Sieves the polygons
SimplifyPostprocessor: Simplifies the polygons by applying the Douglas-Peucker algorithm
ValuePostprocessor: Maps the values of a field

`call` `abstractmethod`

Postprocesses the geodata.

PARAMETER	DESCRIPTION
`gdf`	geodataframe TYPE: `gpd.GeoDataFrame`

RETURNS	DESCRIPTION
`gpd.GeoDataFrame`	postprocessed geodataframe

`ClipPostprocessor`

Bases: GeodataPostprocessor

Geodata postprocessor that clips the polygons based on the mask extent

PARAMETER	DESCRIPTION
`mask`	geodataframe of the mask (may contain multiple polygons) TYPE: `gpd.GeoDataFrame`

`from_config` `classmethod`

Creates a clip postprocessor from the configuration.

PARAMETER	DESCRIPTION
`config`	configuration TYPE: `ClipPostprocessorConfig`

RETURNS	DESCRIPTION
`ClipPostprocessor`	clip postprocessor

`call`

Postprocesses the geodata by clipping the polygons based on the mask extent.

PARAMETER	DESCRIPTION
`gdf`	geodataframe TYPE: `gpd.GeoDataFrame`

RETURNS	DESCRIPTION
`gpd.GeoDataFrame`	postprocessed geodataframe

`ClipPostprocessorConfig`

Bases: pydantic.BaseModel

Configuration for the from_config class method of ClipPostprocessor

ATTRIBUTE	DESCRIPTION
`mask`	path to the geodataframe of the mask (may contain multiple polygons) TYPE: `Path`

`CompositePostprocessor`

Bases: GeodataPostprocessor

Geodata postprocessor that composes multiple geodata postprocessors

PARAMETER	DESCRIPTION
`geodata_postprocessors`	geodata postprocessors TYPE: `list[GeodataPostprocessor]`

`from_config` `classmethod`

Creates a composite postprocessor from the configuration.

PARAMETER	DESCRIPTION
`config`	configuration TYPE: `CompositePostprocessorConfig`

RETURNS	DESCRIPTION
`CompositePostprocessor`	composite postprocessor

`call`

Postprocesses the geodata with each geodata postprocessor.

PARAMETER	DESCRIPTION
`gdf`	geodataframe TYPE: `gpd.GeoDataFrame`

RETURNS	DESCRIPTION
`gpd.GeoDataFrame`	postprocessed geodataframe

`CompositePostprocessorConfig`

Bases: pydantic.BaseModel

Configuration for the from_config class method of CompositePostprocessor

ATTRIBUTE	DESCRIPTION
`geodata_postprocessors_configs`	configurations of the geodata postprocessors TYPE: `list[GeodataPostprocessorConfig]`

`GeodataPostprocessorConfig`

Bases: pydantic.BaseModel

Configuration for geodata postprocessors

ATTRIBUTE	DESCRIPTION
`name`	name of the geodata postprocessor TYPE: `str`
`config`	configuration of the geodata postprocessor TYPE: `ClipPostprocessorConfig \| FieldNamePostprocessorConfig \| FillPostprocessorConfig \| SievePostprocessorConfig \| SimplifyPostprocessorConfig \| ValuePostprocessorConfig`

`FieldNamePostprocessor`

Bases: GeodataPostprocessor

Geodata postprocessor that renames the fields

Examples:

Assume the geodataframe has the field 'class'.

You can rename the field 'class' to 'type'.

>>> field_name_postprocessor = FieldNamePostprocessor(
...     mapping={
...         'class': 'type',
...     },
... )
...
>>> gdf = field_name_postprocessor(gdf)

PARAMETER	DESCRIPTION
`mapping`	mapping of the field names (old field name: new field name) TYPE: `dict`

`from_config` `classmethod`

Creates a field name postprocessor from the configuration.

PARAMETER	DESCRIPTION
`config`	configuration TYPE: `FieldNamePostprocessorConfig`

RETURNS	DESCRIPTION
`FieldNamePostprocessor`	field name postprocessor

`call`

Postprocesses the geodata by renaming the fields.

PARAMETER	DESCRIPTION
`gdf`	geodataframe TYPE: `gpd.GeoDataFrame`

RETURNS	DESCRIPTION
`gpd.GeoDataFrame`	postprocessed geodataframe

`FieldNamePostprocessorConfig`

Bases: pydantic.BaseModel

Configuration for the from_config class method of FieldNamePostprocessor

ATTRIBUTE	DESCRIPTION
`mapping`	mapping of the field names (old field name: new field name) TYPE: `dict`

`FillPostprocessor`

Bases: GeodataPostprocessor

Geodata postprocessor that fills holes in the polygons

PARAMETER	DESCRIPTION
`max_area`	maximum area of the holes to retain in square meters TYPE: `float`

`from_config` `classmethod`

Creates a fill postprocessor from the configuration.

PARAMETER	DESCRIPTION
`config`	configuration TYPE: `FillPostprocessorConfig`

RETURNS	DESCRIPTION
`FillPostprocessor`	fill postprocessor

`call`

Postprocesses the geodata by filling holes in the polygons.

PARAMETER	DESCRIPTION
`gdf`	geodataframe TYPE: `gpd.GeoDataFrame`

RETURNS	DESCRIPTION
`gpd.GeoDataFrame`	postprocessed geodataframe

`FillPostprocessorConfig`

Bases: pydantic.BaseModel

Configuration for the from_config class method of FillPostprocessor

ATTRIBUTE	DESCRIPTION
`max_area`	maximum area of the holes to retain in square meters TYPE: `float`

`SievePostprocessor`

Bases: GeodataPostprocessor

Geodata postprocessor that sieves the polygons

PARAMETER	DESCRIPTION
`min_area`	minimum area of the polygons to retain in square meters TYPE: `float`

`from_config` `classmethod`

Creates a sieve postprocessor from the configuration.

PARAMETER	DESCRIPTION
`config`	configuration TYPE: `SievePostprocessorConfig`

RETURNS	DESCRIPTION
`SievePostprocessor`	sieve postprocessor

`call`

Postprocesses the geodata by sieving the polygons.

PARAMETER	DESCRIPTION
`gdf`	geodataframe TYPE: `gpd.GeoDataFrame`

RETURNS	DESCRIPTION
`gpd.GeoDataFrame`	postprocessed geodataframe

`SievePostprocessorConfig`

Bases: pydantic.BaseModel

Configuration for the from_config class method of SievePostprocessor

ATTRIBUTE	DESCRIPTION
`min_area`	minimum area of the polygons to retain in square meters TYPE: `float`

`SimplifyPostprocessor`

Bases: GeodataPostprocessor

Geodata postprocessor that simplifies the polygons by applying the Douglas-Peucker algorithm

PARAMETER	DESCRIPTION
`tolerance`	tolerance of the Douglas-Peucker algorithm in meters (a lower value will result in less simplification, a higher value will result in more simplification, a value equal to the ground sampling distance is recommended) TYPE: `float`

`from_config` `classmethod`

Creates a simplify postprocessor from the configuration.

PARAMETER	DESCRIPTION
`config`	configuration TYPE: `SimplifyPostprocessorConfig`

RETURNS	DESCRIPTION
`SimplifyPostprocessor`	simplify postprocessor

`call`

Postprocesses the geodata by simplifying the polygons.

PARAMETER	DESCRIPTION
`gdf`	geodataframe TYPE: `gpd.GeoDataFrame`

RETURNS	DESCRIPTION
`gpd.GeoDataFrame`	postprocessed geodataframe

`SimplifyPostprocessorConfig`

Bases: pydantic.BaseModel

Configuration for the from_config class method of SimplifyPostprocessor

ATTRIBUTE	DESCRIPTION
`tolerance`	tolerance of the Douglas-Peucker algorithm in meters (a lower value will result in less simplification, a higher value will result in more simplification, a value equal to the ground sampling distance is recommended) TYPE: `float`

`ValuePostprocessor`

Bases: GeodataPostprocessor

Geodata postprocessor that maps the values of a field

Examples:

Assume the geodataframe has the values 0, 1 and 2 in the field 'class'.

You can map the values 0, 1 and 2 to 'class_1', 'class_2' and 'class_3'.

>>> value_postprocessor = ValuePostprocessor(
...     mapping={
...         0: 'class_1',
...         1: 'class_2',
...         2: 'class_3',
...     },
...     field_name='class',
... )
...
>>> gdf = value_postprocessor(gdf)

PARAMETER	DESCRIPTION
`mapping`	mapping of the values (old value: new value) TYPE: `dict`
`field_name`	name of the field TYPE: `str` DEFAULT: `'class'`

`from_config` `classmethod`

Creates a value postprocessor from the configuration.

PARAMETER	DESCRIPTION
`config`	configuration TYPE: `ValuePostprocessorConfig`

RETURNS	DESCRIPTION
`ValuePostprocessor`	value postprocessor

`call`

Postprocesses the geodata by mapping the values of a field.

PARAMETER	DESCRIPTION
`gdf`	geodataframe TYPE: `gpd.GeoDataFrame`

RETURNS	DESCRIPTION
`gpd.GeoDataFrame`	postprocessed geodataframe

`ValuePostprocessorConfig`

Bases: pydantic.BaseModel

Configuration for the from_config class method of ValuePostprocessor

ATTRIBUTE	DESCRIPTION
`mapping`	mapping of the values (old value: new value) TYPE: `dict`
`field_name`	name of the field TYPE: `str`

GeodataPostprocessor

__call__ abstractmethod

ClipPostprocessor

from_config classmethod

__call__

ClipPostprocessorConfig

CompositePostprocessor

from_config classmethod

__call__

CompositePostprocessorConfig

GeodataPostprocessorConfig

FieldNamePostprocessor

from_config classmethod

__call__

FieldNamePostprocessorConfig

FillPostprocessor

from_config classmethod

__call__

FillPostprocessorConfig

SievePostprocessor

from_config classmethod

__call__

SievePostprocessorConfig

SimplifyPostprocessor

from_config classmethod

__call__

SimplifyPostprocessorConfig

ValuePostprocessor

from_config classmethod

__call__

ValuePostprocessorConfig

`GeodataPostprocessor`

`call` `abstractmethod`

`ClipPostprocessor`

`from_config` `classmethod`

`call`

`ClipPostprocessorConfig`

`CompositePostprocessor`

`from_config` `classmethod`

`call`

`CompositePostprocessorConfig`

`GeodataPostprocessorConfig`

`FieldNamePostprocessor`

`from_config` `classmethod`

`call`

`FieldNamePostprocessorConfig`

`FillPostprocessor`

`from_config` `classmethod`

`call`

`FillPostprocessorConfig`

`SievePostprocessor`

`from_config` `classmethod`

`call`

`SievePostprocessorConfig`

`SimplifyPostprocessor`

`from_config` `classmethod`

`call`

`SimplifyPostprocessorConfig`

`ValuePostprocessor`

`from_config` `classmethod`

`call`

`ValuePostprocessorConfig`