extract_unique_values.py

import pandas as pd
import argparse

def extract_unique_values(csv_file, column_name):
    """
    Read a CSV file into a DataFrame and extract unique values from a specified column.

    Args:
        csv_file (str): Path to the CSV file
        column_name (str): Name of the column to extract unique values from

    Returns:
        list: A sorted list of unique values from the specified column
    """
    try:
        # Read the CSV file into a DataFrame
        df = pd.read_csv(csv_file)

        # Check if the column exists in the DataFrame
        if column_name not in df.columns:
            raise ValueError(f"Column '{column_name}' not found in the CSV file. Available columns: {', '.join(df.columns)}")

        # Extract the column and convert it to a set of unique values, then sort
        unique_values = sorted(set(df[column_name]))

        return unique_values

    except FileNotFoundError:
        print(f"Error: File '{csv_file}' not found.")
        return None
    except Exception as e:
        print(f"Error: {str(e)}")
        return None

def main():
    # Set up command-line argument parsing
    parser = argparse.ArgumentParser(description='Extract unique values from a column in a CSV file.')
    parser.add_argument('csv_file', help='Path to the CSV file')
    parser.add_argument('column_name', help='Name of the column to extract unique values from')

    args = parser.parse_args()

    # Extract unique values
    unique_values = extract_unique_values(args.csv_file, args.column_name)

    # Display the results
    if unique_values is not None:
        print(f"\nUnique values in column '{args.column_name}':")
        for value in unique_values:
            print(f"  - {value}")
        print(f"\nTotal number of unique values: {len(unique_values)}")

if __name__ == "__main__":
    main()