eogrow.pipelines.batch_to_eopatch
Pipeline for conversion of batch results to EOPatches.
- pydantic model eogrow.pipelines.batch_to_eopatch.FeatureMappingSchema[source]
Bases:
Schema
Defines a mapping between 1 or more batch outputs into an EOPatch feature
Create a new model by parsing and validating input data from keyword arguments.
Raises ValidationError if the input data cannot be parsed to form a valid model.
- Fields:
- field batch_files: List[str] [Required]
A list of files that will be converted into an EOPatch feature. If you specify multiple tiff files they will be concatenated together over the bands dimension in the specified order.
- field dtype: dtype | None = None
Dtype of the output feature.
- Validated by:
optional_parse_dtype
- field feature: Tuple[FeatureType, str] [Required]
- field multiply_factor: float = 1
Factor used to multiply feature values with.
- class eogrow.pipelines.batch_to_eopatch.BatchToEOPatchPipeline(*args, **kwargs)[source]
Bases:
Pipeline
Additionally sets some basic parameters calculated from config parameters
- Parameters:
args (Any) –
kwargs (Any) –
- pydantic model Schema[source]
Bases:
Schema
Create a new model by parsing and validating input data from keyword arguments.
Raises ValidationError if the input data cannot be parsed to form a valid model.
- Fields:
input_folder_key (str)
mapping (List[eogrow.pipelines.batch_to_eopatch.FeatureMappingSchema])
output_folder_key (str)
remove_batch_data (bool)
userdata_feature_name (str | None)
userdata_timestamp_reader (str | None)
- field input_folder_key: str [Required]
Storage manager key pointing to the path with Batch results
- Validated by:
validate_storage_key
- field mapping: List[FeatureMappingSchema] [Required]
A list of mapping from batch files into EOPatch features.
- Validated by:
check_nonempty_input
- field output_folder_key: str [Required]
Storage manager key pointing to where the EOPatches are saved
- Validated by:
validate_storage_key
- field remove_batch_data: bool = True
Remove the raw batch data after the conversion is complete
- field userdata_feature_name: str | None = None
A name of META_INFO feature in which userdata.json would be stored.
- field userdata_timestamp_reader: str | None = None
Either an import path to a utility function or a Python code describing how to read dates from userdata dictionary.
- filter_patch_list(patch_list)[source]
EOPatches are filtered according to existence of specified output features
- Parameters:
patch_list (List[Tuple[str, BBox]]) –
- Return type:
List[Tuple[str, BBox]]