Expand description
Classical ML pipeline integration for QuantRS2-ML
This module provides seamless integration between quantum ML models and existing classical ML workflows, enabling hybrid approaches and easy adoption of quantum ML in production environments.
Modules§
- utils
- Utility functions for classical ML integration
Structs§
- Adaptive
Weighting Ensemble - Auto
Optimization Config - Auto-optimization configuration
- Dataset
Info - Dataset information for pipeline recommendation
- Hybrid
Pipeline - Hybrid quantum-classical pipeline
- Hybrid
Pipeline Manager - Hybrid quantum-classical ML pipeline manager
- MinMax
Scaler - Min-max scaler preprocessor
- Model
Performance - Model performance metrics
- Model
Registry - Model registry for managing quantum and classical models
- Optimized
Pipeline - Optimized pipeline result
- Performance
Profile - Performance profile for pipelines
- Pipeline
Config - Pipeline configuration
- Pipeline
Recommendation - Pipeline recommendation
- Pipeline
Template - Pipeline template definition
- Principal
Component Analysis - Quantum
Classical Ensemble - Quantum-classical ensemble model
- Quantum
Data Encoder - Resource
Constraints - Resource constraints for pipeline execution
- Scalability
Profile - Scalability characteristics
- Simple
Hybrid Model - Simple hybrid model combining quantum and classical approaches
- Stacking
Ensemble - Standard
Scaler - Standard scaler preprocessor
- Weighted
Voting Ensemble - Weighted voting ensemble
Enums§
- Model
Type - Model types in pipelines
- Pipeline
Stage - Pipeline stage definition
- Validation
Strategy - Validation strategy options
Traits§
- Classical
Model - Classical model trait for integration
- Data
Preprocessor - Data preprocessing trait
- Ensemble
Strategy - Ensemble strategy trait
- Hybrid
Model - Hybrid quantum-classical model trait