convert.py

from datasets import load_dataset
import pandas as pd

# Load the dataset
dataset = load_dataset("mteb/JapaneseSentimentClassification")

# Convert each split to pandas DataFrame
for split in ["train", "test"]:
    df = pd.DataFrame(dataset[split])
    # Optional: rename columns if you like
    df = df.rename(columns={"text": "text", "label": "label"})
    
    # Save to CSV
    df.to_csv(f"japanese_sentiment_{split}.csv", index=False, encoding="utf-8-sig")
    print(f"{split} split saved: japanese_sentiment_{split}.csv")