Skip to content

foryourhealth111-pixel/Vibe-Skills / bundled/skills/splitting-datasets

splitting-datasets

Verified

Split datasets into training, validation, and test partitions with the right stratification and temporal rules. Use as a narrow preprocessing helper once the broader ML workflow is already chosen, not as the main route owner for an end-to-end ML task.

FileKindSize
SKILL.mdskill md1.4 KB
assets/README.mdmarkdown308 B
assets/dataset_schema.jsonconfig2.8 KB
assets/example_dataset.csvother668 B
assets/split_data_config.yamlconfig1.7 KB
references/README.mdmarkdown527 B
scripts/README.mdmarkdown302 B
scripts/split_data.pyscript2.8 KB

scripts/split_data.py

View on GitHub
#!/usr/bin/env python3
"""
dataset-splitter - split_data.py
Script to perform the actual dataset splitting, taking parameters for split ratios and file paths.
Generated: 2025-12-10 03:48:17
"""

import os
import sys
import json
import argparse
from pathlib import Path
from datetime import datetime

def process_file(file_path: Path) -> bool:
    """Process individual file."""
    if not file_path.exists():
        print(f"❌ File not found: {file_path}")
        return False

    print(f"πŸ“„ Processing: {file_path}")

    # Add processing logic here based on skill requirements
    # This is a template that can be customized

    try:
        if file_path.suffix == '.json':
            with open(file_path) as f:
                data = json.load(f)
            print(f"  βœ“ Valid JSON with {len(data)} keys")
        else:
            size = file_path.stat().st_size
            print(f"  βœ“ File size: {size:,} bytes")

        return True
    except Exception as e:
        print(f"  βœ— Error: {e}")
        return False

def process_directory(dir_path: Path) -> int:
    """Process all files in directory."""
    processed = 0
    failed = 0

    for file_path in dir_path.rglob('*'):
        if file_path.is_file():
            if process_file(file_path):
                processed += 1
            else:
                failed += 1

    return processed, failed

def main():
    parser = argparse.ArgumentParser(
        description="Script to perform the actual dataset splitting, taking parameters for split ratios and file paths."
    )
    parser.add_argument('input', help='Input file or directory')
    parser.add_argument('--output', '-o', help='Output directory')
    parser.add_argument('--verbose', '-v', action='store_true', help='Verbose output')
    parser.add_argument('--config', '-c', help='Configuration file')

    args = parser.parse_args()

    input_path = Path(args.input)

    print(f"πŸš€ dataset-splitter - split_data.py")
    print(f"   Category: ai-ml")
    print(f"   Plugin: dataset-splitter")
    print(f"   Input: {input_path}")

    if args.config:
        if Path(args.config).exists():
            with open(args.config) as f:
                config = json.load(f)
            print(f"   Config: {args.config}")

    # Process input
    if input_path.is_file():
        success = process_file(input_path)
        result = 0 if success else 1
    elif input_path.is_dir():
        processed, failed = process_directory(input_path)
        print(f"\nπŸ“Š SUMMARY")
        print(f"   βœ… Processed: {processed}")
        print(f"   ❌ Failed: {failed}")
        result = 0 if failed == 0 else 1
    else:
        print(f"❌ Invalid input: {input_path}")
        result = 1

    if result == 0:
        print("\nβœ… Completed successfully")
    else:
        print("\n❌ Completed with errors")

    return result

if __name__ == "__main__":
    sys.exit(main())
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 322kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 322kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 322kUpdated Claude CodeCodexVerifiedInstall
skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.Stars: 198kUpdated Claude CodeCodexVerifiedInstall