import pandas as pd

df = pd.read_csv("../../data/COSING_Cleaned_Normalized_v7(1).csv")

# Ubah label jadi binary
df['Label'] = df['Risk Level'].apply(lambda x: 1 if str(x).lower() == 'low risk' else 0)

# Hapus baris tanpa deskripsi
df = df.dropna(subset=['Description'])

df[['Description', 'Label']].to_csv("bert_training_data.csv", index=False)