import os
import sys
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import re

def main(input_directory, pattern):
    # Initialize an empty DataFrame to store the data
    df_all_deltas = pd.DataFrame()

    # Include the '*_DELTA_*.xml3.csv' part in the pattern
    full_pattern = f'{pattern}_DELTA_.*\.xmlv3\.csv'
    
    # Load all *_DELTA_*.xml3.csv files into a single DataFrame
    for filename in os.listdir(input_directory):
        if re.match(full_pattern, filename):
            filepath = os.path.join(input_directory, filename)
            df = pd.read_csv(filepath)
            df['Task Set'] = filename  # Add a column indicating the task set
            df_all_deltas = pd.concat([df_all_deltas, df])

    # Reset the index of the combined DataFrame
    df_all_deltas = df_all_deltas.reset_index(drop=True)
    
    # Extract numeric task numbers and sort them
    task_numbers = df_all_deltas['task'].str.extract(r'(\d+)').astype(int)
    df_all_deltas['num'] = task_numbers
    df_all_deltas = df_all_deltas.sort_values(by='num')

    # Dropping irrelevant columns
    df_all_deltas = df_all_deltas.drop(columns=['num', 'missed', 'Task Set'])

    # Melting the df_all_deltas into a format suitable for a boxplot
    df_all_deltas_melted = pd.melt(df_all_deltas, id_vars=['task'], var_name='Measure', value_name='Difference')

    # Converting 'Difference' column to numeric (to handle any non-numeric entries)
    df_all_deltas_melted['Difference'] = pd.to_numeric(df_all_deltas_melted['Difference'], errors='coerce')

    # Filtering out the zero values from the 'Difference' column before calculating medians
    df_all_deltas_melted = df_all_deltas_melted[df_all_deltas_melted['Difference'] != 0]
    
    # Creating the boxplot of differences in response times
    plt.figure(figsize=(12, 8))
    boxplot = df_all_deltas_melted.boxplot(column='Difference', by='Measure', grid=False, 
                                  medianprops={'color': 'red', 'linewidth': 2})

    # Adding the median values as text
    for i, measure in enumerate(df_all_deltas_melted['Measure'].unique()):
        median_value = df_all_deltas_melted[df_all_deltas_melted['Measure'] == measure]['Difference'].median()
        y_position = median_value + (df_all_deltas_melted['Difference'].max() - df_all_deltas_melted['Difference'].min()) * 0.03  # Adjust position
        plt.text(i + 1, y_position, f'{median_value:.2f}', horizontalalignment='center', color='blue',
                 fontsize=10, weight='semibold', backgroundcolor='white')

    # Increase font size for title and axes labels
    title_fontsize = 16       # Adjust this size as needed
    axes_label_fontsize = 14  # Adjust this size as needed
    plt.title('Response Time Differences (PCP vs PPCP)', fontsize=title_fontsize)
    plt.suptitle('')  # Removes the automatic 'Measure' subtitle
    plt.xlabel('Response Time Measure', fontsize=axes_label_fontsize)
    plt.ylabel('Response Time Difference', fontsize=axes_label_fontsize)

    # Adjust the tick parameters
    plt.xticks(rotation=0, fontsize=12)  # Adjust fontsize as needed
    plt.yticks(fontsize=12)              # Adjust fontsize as needed
    
    # Adjusting grid and removing margins
    plt.grid(axis='y', linestyle='--', alpha=0.7)
    plt.margins(x=0, y=0)  # This reduces the margins around the plot
    
    # We want the plot to be tightly fitted
    plt.tight_layout()

    # Remove special characters and use the cleaned pattern in the output filename
    clean_pattern = re.sub(r'[^a-zA-Z0-9_]', '', pattern)
    output_filename = f'response_time_diffs_by_kind_{clean_pattern}.png'

    # Save the plot as a PNG figure in the same directory
    output_filepath = os.path.join(input_directory, output_filename)
    plt.savefig(output_filepath)

    # Debug
    df_all_deltas_melted.to_csv(os.path.join(input_directory, f'response_time_diffs_by_kind_{clean_pattern}.csv'), index=False)
    
    # Show the plot
    #plt.show()

if __name__ == "__main__":
    if len (sys.argv) < 1 or len(sys.argv) > 3:
        print("Usage: python script.py [ input_directory [pattern]  ]")
        sys.exit(1)

    input_directory = sys.argv[1] if len(sys.argv) > 1 else '.'
    pattern = sys.argv[2] if len(sys.argv) > 2 else '.*'

    print (input_directory, pattern)

    main (input_directory, pattern)