Package index • MLSampling

Main Interface

Primary entry point for the MLSampling framework. Use create_ml_sampling_tool() to create a fully configured MLSampling R6 instance that integrates BDL, RF, UDL, UFN, and ensemble optimization methods.

MLSampling: MLSampling
create_ml_sampling_tool(): Create Enhanced ML Sampling Tool
SoilSamplingTool: Legacy SoilSamplingTool Class (Deprecated)
create_soil_sampling_tool(): Create default SoilSamplingTool instance (Deprecated)

ML Model Classes

R6 classes implementing the individual ML models. These are instantiated automatically by MLSampling but can also be used directly.

BayesianDeepLearning: BayesianDeepLearning
RandomForestOptimization: RandomForestOptimization
MLEnsembleManager: MLEnsembleManager
DesignComparison: DesignComparison
SpatialAnalysisEngine: SpatialAnalysisEngine
SpatialUncertainty: SpatialUncertainty

Service Classes

Supporting R6 service classes for configuration management, benchmarking, progress tracking, resource management, visualization, and reporting.

BenchmarkingService: BenchmarkingService
create_benchmarking_service(): Create default benchmarking service
ConfigManager: ConfigManager
create_default_config_manager(): Create default configuration manager instance
ProgressManager: ProgressManager
create_progress_manager(): Create default progress manager
ReportingService: ReportingService
ResourceManager: ResourceManager
create_resource_manager(): Create default resource manager
VisualizationService: VisualizationService

Field Data Validation

Functions for validating system requirements, field data structures, CRS consistency, and ML-related spatial data quality.

validate_system_requirements(): Validate system requirements for constitutional compliance
validate_field_data_structure(): Enhanced Field Data Model with ML Metadata Support
validate_field_data(): Validate field data structure and spatial integrity
validate_crs_consistency(): Validate CRS consistency between spatial objects
validate_ml_data(): Validate data for ML modeling

Sampling & Result Validation

Validation functions for sampling location sets, optimization results, and uncertainty quantification outputs.

validate_sampling_locations(): Validate sampling locations against field data
validate_sampling_locations_model(): Validate sampling locations data structure
validate_optimization_result(): Validate optimization result (backward compatibility)
validate_ml_optimization_result(): Validate ML optimization result structure
validate_uncertainty_results(): Validate uncertainty quantification results

Data Structures

Factory functions for creating standardized result objects used throughout the optimization pipeline.

create_sampling_locations(): Sampling Locations Model
create_uncertainty_results(): Uncertainty Quantification Model
create_spatial_uncertainty(): Create Spatial Uncertainty instance
create_ml_optimization_result(): Enhanced ML Results Model
create_optimization_result(): Create backward compatibility wrapper

Error Handling

Structured error class hierarchy and handler utilities for robust exception management. All domain errors inherit from MLSamplingError.

MLSamplingErrors: Standardized Error Classes
MLSamplingError(): Base MLSampling Error
BDLError(): Bayesian Deep Learning Error
RFError(): Random Forest Optimization Error
SpatialError(): Spatial Analysis Error
ResourceError(): Resource/Memory Error
ConfigError(): Configuration Error
ValidationError(): Data Validation Error
create_error(): Create a custom error condition
raise_error(): Raise a specific error
with_error_handling(): Safe execution wrapper

Internal Functions

Low-level helper functions used internally by the package. Documented here for developer reference.

BDLError(): Bayesian Deep Learning Error
BayesianDeepLearning: BayesianDeepLearning
BenchmarkingService: BenchmarkingService
ConfigError(): Configuration Error
ConfigManager: ConfigManager
DesignComparison: DesignComparison
MLEnsembleManager: MLEnsembleManager
MLSampling: MLSampling
MLSamplingError(): Base MLSampling Error
MLSamplingErrors: Standardized Error Classes
ProgressManager: ProgressManager
RFError(): Random Forest Optimization Error
RandomForestOptimization: RandomForestOptimization
ReportingService: ReportingService
ResourceError(): Resource/Memory Error
ResourceManager: ResourceManager
SoilSamplingTool: Legacy SoilSamplingTool Class (Deprecated)
SpatialAnalysisEngine: SpatialAnalysisEngine
SpatialError(): Spatial Analysis Error
SpatialUncertainty: SpatialUncertainty
ValidationError(): Data Validation Error
VisualizationService: VisualizationService
calculate_derived_uncertainties(): Calculate derived uncertainty measures
check_duplicate_coordinates(): Check for duplicate coordinates
create_benchmarking_service(): Create default benchmarking service
create_default_config_manager(): Create default configuration manager instance
create_default_metrics(): Create default performance metrics
create_empty_ml_metadata(): Create empty ML metadata structure for future use
create_error(): Create a custom error condition
create_ml_optimization_result(): Enhanced ML Results Model
create_ml_result_metadata(): Create ML result metadata
create_ml_sampling_tool(): Create Enhanced ML Sampling Tool
create_optimization_result(): Create backward compatibility wrapper
create_progress_manager(): Create default progress manager
create_resource_manager(): Create default resource manager
create_result_metadata(): Create result metadata
create_sampling_locations(): Sampling Locations Model
create_soil_sampling_tool(): Create default SoilSamplingTool instance (Deprecated)
create_spatial_uncertainty(): Create Spatial Uncertainty instance
create_uncertainty_results(): Uncertainty Quantification Model
determine_primary_crs(): Determine primary CRS from field data
extract_metric_value(): Extract metric value safely
extract_ml_component(): Extract ML component from ml_components list
generate_sample_ids(): Generate automatic sample IDs
`%||%`: Helper function for NULL coalescing
raise_error(): Raise a specific error
standardize_confidence_intervals(): Standardize confidence intervals
standardize_existing_samples(): Standardize existing samples format
standardize_field_data_structure(): Standardize field data structure with ML enhancements
standardize_location_output(): Standardize location output format
standardize_ml_metadata(): Standardize ML metadata structure
standardize_ml_performance_metrics(): Standardize ML performance metrics
standardize_optimization_parameters(): Standardize optimization parameters
standardize_performance_metrics(): Standardize performance metrics structure
standardize_uncertainty_component(): Standardize uncertainty component
standardize_uncertainty_rasters(): Standardize uncertainty rasters
standardize_uncertainty_validation_metrics(): Standardize uncertainty validation metrics
validate_and_expand_vector(): Validate and expand vector to match required length
validate_boundary_geometry(): Validate boundary geometry integrity
validate_compliance_structure(): Validate compliance structure
validate_confidence_intervals_structure(): Validate confidence intervals structure
validate_constitutional_compliance(): Validate constitutional compliance
validate_constitutional_spatial_standards(): Validate constitutional spatial standards compliance
validate_coordinates_input(): Validate coordinate input format
validate_covariate_rasters(): Validate covariate rasters
validate_covariates_raster(): Validate covariates raster integrity
validate_crs_consistency(): Validate CRS consistency between spatial objects
validate_data_quality(): Validate data quality standards
validate_feature_importance(): Validate feature importance scores
validate_field_boundary_geometry(): Validate boundary geometry
validate_field_crs_consistency(): Validate CRS consistency across spatial objects
validate_field_data(): Validate field data structure and spatial integrity
validate_field_data_structure(): Enhanced Field Data Model with ML Metadata Support
validate_location_types(): Validate location types
validate_locations_in_boundary(): Validate locations are within field boundary
validate_mc_samples(): Validate Monte Carlo samples
validate_mc_samples_consistency(): Validate Monte Carlo samples consistency
validate_ml_components(): Validate ML components structure
validate_ml_components_consistency(): Validate ML components consistency
validate_ml_constitutional_compliance(): Validate ML constitutional compliance
validate_ml_data(): Validate data for ML modeling
validate_ml_metadata(): Validate ML metadata structure
validate_ml_method(): Validate ML method specification
validate_ml_optimization_result(): Validate ML optimization result structure
validate_n_samples(): Validate number of samples
validate_numeric_coordinates(): Validate numeric coordinates
validate_optimization_result(): Validate optimization result (backward compatibility)
validate_result_metrics(): Validate result metrics structure
validate_sample_ids(): Validate sample IDs
validate_sampling_locations(): Validate sampling locations against field data
validate_sampling_locations_model(): Validate sampling locations data structure
validate_selected_locations(): Validate selected locations structure
validate_single_uncertainty_component(): Validate single uncertainty component
validate_spatial_consistency(): Validate spatial consistency across uncertainty components
validate_spatial_extent_alignment(): Validate spatial extent alignment
validate_spatial_weights(): Validate spatial weights matrix
validate_system_requirements(): Validate system requirements for constitutional compliance
validate_uncertainty_components(): Validate uncertainty components
validate_uncertainty_consistency(): Validate uncertainty consistency
validate_uncertainty_maps(): Validate uncertainty maps
validate_uncertainty_method(): Validate uncertainty method
validate_uncertainty_results(): Validate uncertainty quantification results
with_error_handling(): Safe execution wrapper