Sum data

sum data.py

import pandas as pd
import sys
from datetime import datetime, timedelta
import pytz

# Check if the correct number of arguments was passed
if len(sys.argv) != 2:
    print("Usage: python filter_csv.py <path_to_csv_file>")
    sys.exit(1)

# Get the file path from command line argument
file_path = sys.argv[1]

# Function to filter and consolidate the CSV
def filter_consolidate_csv(file_path):
    try:
        # open the file and check the first line
        with open(file_path, 'r') as file:
            first_line = file.readline().strip()

        # determine if 'sep=;' line needs to be skipped
        skip_rows = 1 if first_line.startswith('sep=') else 0

        # Load the CSV file
        data = pd.read_csv(file_path, delimiter=',', skiprows=skip_rows)

        # Debug: column names
        print("Columns found in CSV:", data.columns.tolist())
        print("Sample data:", data.head())

        # Ensure 'startdate' column exists
        if 'startdate' not in data.columns:
            print("Error: 'startdate' column is missing. Check column names in CSV.")
            return  # Exit the function if 'startdate' column is not found

        # Convert dates to ensure format
        data['startdate'] = pd.to_datetime(data['startdate'], utc=True, errors='coerce')

        # Debug: column names
        print("Columns found in CSV:", data.columns.tolist())
        print("Sample data:", data.head())

        # Group by day and sum the values
        data['startdate'] = data['startdate'].dt.date  # Normalize to date
        consolidated_data = data.groupby('startdate').agg({'value': 'sum'}).reset_index()

        # Save the consolidated data
        consolidated_data.to_csv(file_path.replace('.csv', '_consolidated.csv'), index=False)

    except Exception as e:
        print(f"An error occurred: {e}")

# Call the function with the provided file path
filter_consolidate_csv(file_path)