data.py

import kagglehub
import pandas as pd
import os


def resumes_data():
    # Download latest version
    path = kagglehub.dataset_download("gauravduttakiit/resume-dataset")
    df = pd.read_csv(os.path.join(path, os.listdir(path)[0]))
    df = df[df['Category'].isin(['ETL Developer', 'Automation Testing', 'Java Developer', 'DotNet Developer'])]
    df = df.reset_index(drop=True)  # Drop old indices and reset to 0-based
    return df