build-ml-pipeline

What problem does it solve?

This Skill provides a structured approach to building machine learning pipelines, ensuring they are declarative and maintainable.

Core Features & Use Cases

• Declarative Pipeline Building: Utilizes skrub DataOps graphs for declarative pipeline construction.
• Early X Marker Placement: Ensures the X marker is placed correctly for proper feature engineering.
• Stateful vs Stateless Operations: Differentiates between stateless functions and stateful estimators.
• Multi-table Inputs and Joins: Supports multi-table inputs and joins using skrub joiners.
• Meta-estimators and Hyperparameter Knobs: Incorporates meta-estimators and provides hyperparameter tuning options.
• Use Case: Build a machine learning pipeline for a regression task that includes feature engineering, model selection, and hyperparameter tuning.

Quick Start

build-ml-pipeline "data_dir=/path/to/data" "predict_grid=/path/to/predict_grid" "history_source=/path/to/history_source" " learner=HistGradientBoostingRegressor"