haipipe-data-4-aidata

Transform CaseSets into ML-ready AIDataSets with splitting and input transformations.

Updated Feb 16, 2026

Search Tags:#machine learning #feature engineering #data pipeline #data transformation #dataset splitting #AIDataSet

Ready to run

npx skills add https://github.com/jluo41/research-skills --skill haipipe-data-4-aidata

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: haipipe-data-4-aidata
Source: https://github.com/jluo41/research-skills/tree/main/skills/haipipe-data-4-aidata
Command: npx skills add https://github.com/jluo41/research-skills --skill haipipe-data-4-aidata

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill transforms raw case data into machine-learning-ready datasets, handling complex splitting and feature transformations required for model training.

Core Features & Use Cases

Data Splitting: Divides datasets into training, validation, and testing sets using various strategies (time-based, random, stratified).
Feature Transformation: Converts raw case features into formats suitable for ML models (e.g., token embeddings, numerical sequences).
Use Case: Prepare a large patient dataset for a diabetes prediction model by splitting it into train/validation/test sets and transforming time-series CGM data into token sequences.

Quick Start

Use the haipipe-data-4-aidata skill to cook a new AIDataSet using the provided configuration file.

Frequently Asked Questions about haipipe-data-4-aidata

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I prepare raw case data for machine learning model training?▼

Preparing raw case data for machine learning model training involves transforming CaseSets into ML-ready AIDataSets by applying dataset splitting and input/output feature transformations. This process outputs HuggingFace DatasetDicts and vocabulary files required for training.

What is the best way to split a patient dataset into train and validation sets?▼

Splitting a patient dataset can be handled using strategies like RandomByPatient or time-based SplitByTimeBin. These methods divide raw case data into training, validation, and testing sets to ensure robust machine learning model evaluation.

Can I transform time-series data into token sequences for feature engineering?▼

Yes, you can transform time-series data into token sequences for feature engineering using the InputTEToken input transformation. This converts raw case features into token embeddings suitable for machine learning models.

Does this data pipeline support generating HuggingFace DatasetDicts?▼

Yes, the data pipeline explicitly supports generating HuggingFace DatasetDicts as an output. It transforms CaseSets into ML-ready AIDataSets and outputs these dictionaries alongside vocabulary files for model training.

What data splitting strategies are available for machine learning datasets?▼

Available data splitting strategies for machine learning datasets include time-based splitting via SplitByTimeBin, random splitting, and stratified splitting. These methods ensure proper partitioning into train, validation, and testing sets.

How do I convert raw case features into numerical sequences for ML models?▼

Converting raw case features into numerical sequences for ML models is achieved through input and output feature transformations. These transformations process CaseSets into ML-ready AIDataSets, generating formats like token embeddings for model training.