split_data.py

import pandas as pd
from sklearn.model_selection import train_test_split

# Load dataset from the HF dataset location
data = pd.read_csv("data/dataset.csv")  # Ensure your dataset is in the `data` directory

# Split into train and validation sets
train, validation = train_test_split(data, test_size=0.3, random_state=42)

# Save to CSV files
train.to_csv("data/train.csv", index=False)
validation.to_csv("data/validation.csv", index=False)