How to Build a Simple Data Pipeline in Python

import json
from pathlib import Path


def load_json(filepath: str | Path) -> list[dict]:
    """Load a JSON file containing a list of records."""
    with Path(filepath).open("r", encoding="utf-8") as f:
        return json.load(f)


def filter_records(records: list[dict], field: str, value) -> list[dict]:
    """Keep records where the given field exactly equals value."""
    return [r for r in records if r.get(field) == value]


def aggregate_count(records: list[dict], group_by: str) -> dict[str, int]:
    """Count records per unique value of group_by field."""
    counts: dict[str, int] = {}
    for record in records:
        key = record.get(group_by)
        counts[key] = counts.get(key, 0) + 1
    return counts


def pipeline(filepath: str | Path, filter_field: str, filter_value, group_by: str) -> dict[str, int]:
    """Run a complete mini pipeline: load → filter → aggregate."""
    data = load_json(filepath)
    filtered = filter_records(data, filter_field, filter_value)
    return aggregate_count(filtered, group_by)


if __name__ == "__main__":
    # Sample data written to a temp file for demonstration
    sample = [
        {"city": "Berlin", "status": "active"},
        {"city": "Munich", "status": "active"},
        {"city": "Berlin", "status": "inactive"},
        {"city": "Hamburg", "status": "active"},
    ]
    temp_file = Path("sample_data.json")
    temp_file.write_text(json.dumps(sample), encoding="utf-8")

    result = pipeline(temp_file, "status", "active", "city")
    print(result)

    temp_file.unlink()