How to Validate Data Before Scaling in Python

def validate_data(data, required_fields, constraints=None):
    """
    Basic validation helper demonstrating data-quality workflows
    before scaling (catches bad rows early, improves throughput).
    """
    constraints = constraints or {}

    errors = []
    for field in required_fields:
        if field not in data or data[field] == "" or data[field] is None:
            errors.append(f"Missing required field: {field}")

    for field, check in constraints.items():
        if field in data and data[field] is not None and data[field] != "":
            if not check(data[field]):
                errors.append(f"Invalid value for {field}: {data[field]!r}")

    return {"is_valid": not errors, "errors": errors}


def common_constraints():
    """Reusable validator functions for typical column types."""
    return {
        "age": lambda v: isinstance(v, int) and 0 <= v <= 150,
        "email": lambda v: "@" in v and "." in v.split("@")[-1],
        "score": lambda v: isinstance(v, (int, float)) and 0 <= v <= 100,
    }


if __name__ == "__main__":
    # Simulated incoming rows — one clean, one dirty
    rows = [
        {"name": "Alice", "age": 30, "email": "alice@example.com", "score": 85.5},
        {"name": "", "age": 300, "email": "bob_at_bad_domain", "score": "high"},
    ]

    required = ["name", "age", "email"]
    checks = common_constraints()

    # Fast pre-scaling validation loop
    for i, row in enumerate(rows, 1):
        result = validate_data(row, required, checks)
        status = "PASS" if result["is_valid"] else "REJECT"
        print(f"Row {i}: {status} -> {result['errors'] if result['errors'] else 'OK'}")