import pandas as pd

# Specify the path to your CSV file
file_path = 'car_specification_value.csv'

# Read the file and fix inconsistencies
try:
    with open(file_path, 'r') as file:
        lines = file.readlines()

    # Fix the problematic lines
    fixed_lines = []
    for line in lines:
        # Remove single quotes and strip whitespace
        columns = [col.strip().replace("'", "") for col in line.strip().split(',')]
        if len(columns) >= 8:  # Ensure at least 8 fields
            fixed_line = ','.join(f'"{col}"' for col in columns[:8])  # Truncate to 8 fields and add double quotes
            fixed_lines.append(fixed_line)

    # Save the cleaned data to a new CSV file
    cleaned_file_path = 'car_specification_value_cleaned.csv'
    with open(cleaned_file_path, 'w') as file:
        file.write('\n'.join(fixed_lines))

    # Load the cleaned data into a DataFrame
    cleaned_df = pd.read_csv(cleaned_file_path)
    print("Cleaned data preview:")
    print(cleaned_df.head())
    print(f"Cleaned file saved as: {cleaned_file_path}")
except Exception as e:
    print(f"An error occurred: {e}")