split-strategy

Select train/validation/test split strategies based on data characteristics.

14|2|Updated Feb 24, 2026

Search Tags:#split #time-series #cross-validation #model-evaluation #train-validation-test #grouped-data

Ready to run

npx skills add https://github.com/andikarachman/data-science-plugin --skill split-strategy

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: split-strategy
Source: https://github.com/andikarachman/data-science-plugin/tree/main/skills/split-strategy
Command: npx skills add https://github.com/andikarachman/data-science-plugin --skill split-strategy

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Selecting appropriate train/validation/test splits based on data characteristics to ensure robust model evaluation and prevent data leakage.

Core Features & Use Cases

Decision-tree guided selection for time-based splits, group-aware splits, imbalanced targets, and dataset size considerations
Clear recommendations of split ratios and validation strategies for common data regimes
Real-world scenarios: time-series forecasting, multi-group data, and small datasets requiring cross-validation

Quick Start

Apply the decision-tree approach to select and implement the appropriate train/validation/test split for your dataset.

Frequently Asked Questions about split-strategy

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

FAQPage Schema

How do I choose the right train validation test split for time-series data?▼

The appropriate train validation test split for time-series data requires time-based splits to preserve chronological order, preventing future data from leaking into the training set and ensuring reliable evaluation.

What is the best way to split grouped data for cross-validation?▼

The best way to split grouped data is using group-aware splits, ensuring all records from the same group remain entirely within either the training or validation set to prevent data leakage during cross-validation.

When should I use cross-validation instead of a standard train test split?▼

You should use cross-validation instead of a standard train test split when working with small datasets, as it maximizes available training data while still providing robust model evaluation metrics.

How do I prevent data leakage when splitting imbalanced target datasets?▼

To prevent data leakage when splitting imbalanced target datasets, apply split strategies that account for target distributions and enforce strict separation between training and test data across all evaluation frameworks.

Does dataset size affect the recommended train validation test split ratio?▼

Yes, dataset size directly affects the recommended split ratio, with smaller datasets requiring cross-validation strategies and larger datasets supporting standard proportions to maintain representative model evaluation.