df.py

import pandas as pd
import os
folders = [
    "Men I",
    "Men II",
    "Men Neuro",
    "Women I",
    "Women II",
    "Women III",
    "Women IV",
]

# get the all the files in the folders
files = []
for folder in folders:
    files.extend([f"{folder}/img/{file}" for file in os.listdir(os.path.join(folder, "img"))])

print(files)

# create a dataframe

rows = {
    "image_paths": files,
    "image_urls": [None] * len(files),
    "mask_paths": [file.replace("img", "mask") for file in files],
    "gender": [file.split(" ")[0] for file in files],
}

num_votes = 3
voters = [
    "osman",
    "eren",
    "robin",
    "mira",
    "bilal",
    "volunteer-1",
    "volunteer-2",
    "volunteer-3",
    "volunteer-4",
    "volunteer-5",
]

for vote in range(num_votes):
    for voter in voters:
        rows[f"vote_{vote}_{voter}"] = [None] * len(files)

df = pd.DataFrame(rows)

print(df.head())

df.to_csv("data.csv", index=False)