target_yoy_mo

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from datetime import datetime

def calculate_monthly_yoy_fuel_burn(input_file, output_file=None):
    """
    Calculate YoY monthly fuel burn from monthly historical data.
    
    Args:
        input_file: Path to the CSV file with monthly fuel burn data
        output_file: Path to save the results (optional)
        
    Returns:
        DataFrame with the original data and YoY calculations
    """
    # Read the input file
    df = pd.read_csv(input_file)
    
    # Convert Month column to datetime
    df['Month'] = pd.to_datetime(df['Month'])
    
    # Sort by Month
    df = df.sort_values('Month')
    
    # Extract year and month for grouping
    df['Year'] = df['Month'].dt.year
    df['MonthNum'] = df['Month'].dt.month
    
    # Calculate YoY changes (percentage) directly comparing to same month last year
    df['YoY_FuelBurn'] = df.groupby('MonthNum')['FuelBurn'].pct_change(periods=1) * 100
    df['YoY_Flights'] = df.groupby('MonthNum')['Flights'].pct_change(periods=1) * 100
    df['YoY_Hours'] = df.groupby('MonthNum')['Hours'].pct_change(periods=1) * 100
    
    # Calculate Fuel Efficiency metrics
    df['FuelBurn_per_Flight'] = df['FuelBurn'] / df['Flights']
    df['FuelBurn_per_Hour'] = df['FuelBurn'] / df['Hours']
    
    # Calculate YoY changes in efficiency metrics
    df['YoY_FuelBurn_per_Flight'] = df.groupby('MonthNum')['FuelBurn_per_Flight'].pct_change(periods=1) * 100
    df['YoY_FuelBurn_per_Hour'] = df.groupby('MonthNum')['FuelBurn_per_Hour'].pct_change(periods=1) * 100
    
    # Save to output file if specified
    if output_file:
        df.to_csv(output_file, index=False)
        print(f"Results saved to {output_file}")
    
    return df

def visualize_monthly_yoy_data(df):
    """
    Create visualizations of the monthly YoY data.
    
    Args:
        df: DataFrame with YoY calculations
    """
    # Filter out NaN values (first year won't have YoY data)
    df_viz = df.dropna(subset=['YoY_FuelBurn'])
    
    # Set up the figure
    plt.figure(figsize=(12, 9))
    
    # Plot 1: YoY Fuel Burn
    plt.subplot(2, 1, 1)
    plt.plot(df_viz['Month'], df_viz['YoY_FuelBurn'], 'b-', label='YoY Fuel Burn (%)')
    plt.title('Year-over-Year Monthly Fuel Burn')
    plt.xlabel('Month')
    plt.ylabel('Percent Change (%)')
    plt.grid(True)
    plt.legend()
    
    # Plot 2: YoY Flights vs YoY Hours
    plt.subplot(2, 2, 3)
    plt.plot(df_viz['Month'], df_viz['YoY_Flights'], 'g-', label='YoY Flights (%)')
    plt.plot(df_viz['Month'], df_viz['YoY_Hours'], 'r-', label='YoY Hours (%)')
    plt.title('YoY Flights vs Hours')
    plt.xlabel('Month')
    plt.ylabel('Percent Change (%)')
    plt.grid(True)
    plt.legend()
    
    # Plot 3: YoY Efficiency Metrics
    plt.subplot(2, 2, 4)
    plt.plot(df_viz['Month'], df_viz['YoY_FuelBurn_per_Flight'], 'c-', label='YoY Fuel per Flight (%)')
    plt.plot(df_viz['Month'], df_viz['YoY_FuelBurn_per_Hour'], 'm-', label='YoY Fuel per Hour (%)')
    plt.title('YoY Efficiency Metrics')
    plt.xlabel('Month')
    plt.ylabel('Percent Change (%)')
    plt.grid(True)
    plt.legend()
    
    plt.tight_layout()
    plt.savefig('monthly_yoy_fuel_burn_analysis.png')
    print("Visualization saved to monthly_yoy_fuel_burn_analysis.png")
    plt.show()

def main():
    """Main function to run the YoY fuel burn calculator."""
    input_file = "argus_fuelburn_yrmo.csv"
    output_file = "argus_fuelburn_monthly_yoy.csv"
    
    print(f"Processing {input_file}...")
    df = calculate_monthly_yoy_fuel_burn(input_file, output_file)
    
    # Print sample of results
    print("\nSample of calculated YoY data:")
    
    # Get a sample of results that have YoY data (not NaN)
    sample_df = df.dropna(subset=['YoY_FuelBurn']).head(5)
    
    # Format the display for better readability
    pd.set_option('display.float_format', '{:.2f}'.format)
    display_cols = ['Month', 'FuelBurn', 'YoY_FuelBurn']
    print(sample_df[display_cols].to_string(index=False))
    
    # Print summary statistics
    print("\nSummary statistics for YoY Fuel Burn (%):")
    print(f"Mean: {df['YoY_FuelBurn'].mean():.2f}%")
    print(f"Median: {df['YoY_FuelBurn'].median():.2f}%")
    print(f"Min: {df['YoY_FuelBurn'].min():.2f}%")
    print(f"Max: {df['YoY_FuelBurn'].max():.2f}%")
    
    # Create visualizations
    print("\nCreating visualizations...")
    visualize_monthly_yoy_data(df)
    
    # Return the DataFrame for further analysis if needed
    return df

if __name__ == "__main__":
    main()