clean_openml.py

import os
import csv



def clean(user_prompt):
    input_directory = os.path.join("input_folder", user_prompt)
    output_directory = "downloads/"+user_prompt

# Create the output directory if it doesn't exist
    os.makedirs(output_directory, exist_ok=True)

# Loop through all files in the user-specified input directory
    for filename in os.listdir(input_directory):
        file_path = os.path.join(input_directory, filename)

    # Skip directories or hidden files
        if os.path.isdir(file_path) or filename.startswith("."):
            continue

    # Output file path (.csv extension added)
        output_file = os.path.join(output_directory, filename + ".csv")

        with open(file_path, "r", encoding="utf-8", errors="ignore") as file:
            lines = file.readlines()

        headers = []
        data_rows = []
        data_started = False

        for line in lines:
            line = line.strip()
            if line.startswith("@ATTRIBUTE"):
                parts = line.split()
                if len(parts) >= 2:
                    headers.append(parts[1])
            elif line.startswith("@DATA"):
                data_started = True
            elif data_started and line:
                data_rows.append(line.split(","))

    # Write to CSV
        with open(output_file, "w", newline="") as csvfile:
            writer = csv.writer(csvfile)
            writer.writerow(headers)
            writer.writerows(data_rows)

        print(f"✅ CSV file created for: {filename} → {output_file}")