How to Build Data Processing Functions in Python

import csv
from pathlib import Path


def load_data(filepath):
    """Load CSV data into a list of dicts."""
    with open(filepath, "r", newline="", encoding="utf-8") as f:
        return list(csv.DictReader(f))


def filter_rows(rows, column, value):
    """Keep rows where column equals value."""
    return [row for row in rows if row.get(column) == value]


def transform_column(rows, column, func):
    """Apply func to a column and return new rows."""
    return [{**row, column: func(row[column])} for row in rows if column in row]


def aggregate(rows, group_key, value_key):
    """Sum value_key grouped by group_key."""
    result = {}
    for row in rows:
        result[row[group_key]] = result.get(row[group_key], 0) + int(row[value_key])
    return result


if __name__ == "__main__":
    sample = """name,department,salary
Alice,Engineering,100000
Bob,Engineering,90000
Carol,Sales,80000
Dave,Sales,85000
"""
    Path("employees.csv").write_text(sample, encoding="utf-8")

    data = load_data("employees.csv")
    print("Loaded rows:", len(data))

    engineers = filter_rows(data, "department", "Engineering")
    print("Engineers:", len(engineers))

    salaries = aggregate(data, "department", "salary")
    print("Salary sums:", salaries)