src.driver.workflow

Workflow orchestration and main execution logic for MMM V2.

This module handles the main workflow execution, feature engineering, data description, and LLM interpretation integration.

Module Contents

class src.driver.workflow.WorkflowExecutor(driver)

Handles main workflow execution for V2 architecture.

This class manages the complete MMM workflow including data description, feature engineering, model execution, and result generation.

run_feature_engineering() → src.prepro.input_data.InputData

Placeholder for feature engineering steps. Currently a no-op.

Returns:

The (potentially modified) input data object.

describe_data(input_data_raw: src.prepro.input_data.InputData, input_data_processed: src.prepro.input_data.InputData, current_commit: str) → None

Generates descriptive outputs for raw and processed data.

Parameters:

• input_data_raw – InputData object before feature engineering.

• input_data_processed – InputData object after feature engineering.

• current_commit – Git commit hash for reproducibility.

execute() → str | None

Main execution workflow for the V2 MMM driver.

Returns:

Path to results directory, or None if execution fails.