import pandas as pd
from sklearn.model_selection import train_test_split

# Load the data from the CSV file
data = pd.read_csv("data.csv")

# Split the data into train and validation sets, using 85% of the data for training and 15% for validation for the "labels" column
train_data, validation_data = train_test_split(data, train_size=0.85, test_size=0.15, random_state=42, stratify=data["labels"])

# Write the train and validation datasets to CSV files
train_data.to_csv("train.csv", index=False)
validation_data.to_csv("valid.csv", index=False)