automl-pipeline-setup

What problem does it solve?

This Skill automates the complex and time-consuming process of setting up machine learning pipelines, including data validation, feature engineering, model training, and deployment.

Core Features & Use Cases

• Automated Pipeline Configuration: Define and configure entire ML pipelines using YAML.
• Data Validation: Integrates with Great Expectations for robust data quality checks.
• Feature Engineering: Provides pre-built transformers for numerical and categorical data.
• AutoML Training: Leverages H2O.ai for automated model selection and hyperparameter tuning.
• Experiment Tracking: Integrates with MLflow for logging and model registry.
• Orchestration: Includes an example Airflow DAG for pipeline scheduling.
• Use Case: Quickly set up a customer churn prediction pipeline by defining your data source and target variable in a YAML configuration, letting the skill handle the rest.

Quick Start

Use the automl-pipeline-setup skill to configure and train a customer churn prediction model using the provided YAML configuration.