csv_process.py

import os
import subprocess
import pandas as pd

def count_matching_repeats(df, repeat_type):
    """
    Counts the matching sequences for a specified repeat type (CAG or CTG) where
    the matching percentage is 100, and also counts the total occurrences of that
    repeat type.
    """
    if 'Repeat Type' in df.columns and 'Matching Percentage' in df.columns:
        matching_count = ((df['Repeat Type'] == repeat_type) & (df['Matching Percentage'] == 100)).sum()
        total_count = (df['Repeat Type'] == repeat_type).sum()
        return matching_count, total_count
    return None, None

def count_fasta_sequences(fasta_path):
    """
    Counts the number of sequences in a FASTA file by counting the number of header lines.
    """
    try:
        result = subprocess.run(['grep', '-c', '^>', fasta_path], capture_output=True, text=True)
        return int(result.stdout.strip())
    except Exception as e:
        print(f"Error processing file {fasta_path}: {e}")
        return None

def process_files(directory):
    """
    Processes CSV and FASTA files in the directory to summarize matching and total counts for CAG and CTG repeats.
    """
    results = []

    for filename in os.listdir(directory):
        file_path = os.path.join(directory, filename)
        if filename.endswith(".csv"):
            df = pd.read_csv(file_path)
            matching_cag, total_cag = count_matching_repeats(df, 'CAG')
            matching_ctg, total_ctg = count_matching_repeats(df, 'CTG')
            results.append({
                'Filename': filename,
                'CAG Matching Count': matching_cag,
                'CAG Total Count': total_cag,
                'CTG Matching Count': matching_ctg,
                'CTG Total Count': total_ctg,
                'FASTA Total Count': None  # Placeholder for FASTA counts
            })
        elif filename.endswith(".fasta"):
            fasta_count = count_fasta_sequences(file_path)
            results.append({
                'Filename': filename,
                'CAG Matching Count': None,
                'CAG Total Count': None,
                'CTG Matching Count': None,
                'CTG Total Count': None,
                'FASTA Total Count': fasta_count
            })

    results_df = pd.DataFrame(results)
    
    # Separate CSV and FASTA entries
    csv_results_df = results_df[results_df['Filename'].str.endswith('.csv')].reset_index(drop=True)
    fasta_results_df = results_df[results_df['Filename'].str.endswith('.fasta')].reset_index(drop=True)
    
    # Remove '_comparison_report.csv' and '.fasta' from filenames for alignment
    csv_results_df['Filename'] = csv_results_df['Filename'].str.replace('_comparison_report.csv', '', regex=False)
    fasta_results_df['Filename'] = fasta_results_df['Filename'].str.replace('.fasta', '', regex=False)

    # Merge dataframes on Filename
    merged_df = pd.merge(csv_results_df, fasta_results_df, on='Filename', how='outer', suffixes=('_csv', '_fasta'))

    # Save the merged results to a new CSV file
    output_path = os.path.join(directory, 'results_summary.csv')
    merged_df.to_csv(output_path, index=False)
    print(f'Results saved to {output_path}')

import os

if __name__ == "__main__":
    # Get the current working directory (the folder where the script is being run)
    folder_path = os.getcwd()
    
    # Call the function to process files in the current folder
    process_files(folder_path)