Build a Data Helper Class in Python for ML Pipelines

from typing import List, Dict, Any
import json

class DataHelper:
    """Beginner-friendly helpers for ML data pipelines."""
    
    def __init__(self, data: List[Dict[str, Any]]):
        self.data = data
        self.keys = list(data[0].keys()) if data else []
    
    def summary(self) -> Dict[str, Any]:
        """Return basic stats: row count, columns, missing values."""
        missing = {k: sum(1 for row in self.data if not row.get(k)) for k in self.keys}
        return {
            "rows": len(self.data),
            "columns": self.keys,
            "missing_values": missing
        }
    
    def filter_by(self, key: str, value: Any) -> "DataHelper":
        """Return new DataHelper filtered by key-value match."""
        filtered = [row for row in self.data if row.get(key) == value]
        return DataHelper(filtered)
    
    def to_json(self, filepath: str) -> None:
        """Save data to a JSON file."""
        with open(filepath, "w") as f:
            json.dump(self.data, f, indent=2)

if __name__ == "__main__":
    sample = [
        {"name": "alice", "age": 25, "score": 88},
        {"name": "bob", "age": 30, "score": 0},
        {"name": "carol", "age": 22, "score": 95}
    ]
    helper = DataHelper(sample)
    print(helper.summary())
    adults = helper.filter_by("age", 30)
    print(adults.data)
    helper.to_json("output.json")
    print("saved to output.json")