import pandas as pd
from pathlib import Path

IN_CSV = Path("data_processed/metadata_resized.csv")
OUT_CSV = Path("data_processed/metadata_final.csv")
MAP_CSV = Path("data_processed/label_map.csv")

df = pd.read_csv(IN_CSV)

labels = sorted(df["label"].unique())
label_to_id = {label: i for i, label in enumerate(labels)}

df["label_id"] = df["label"].map(label_to_id)

df.to_csv(OUT_CSV, index=False)

pd.DataFrame({
    "label": labels,
    "label_id": [label_to_id[l] for l in labels]
}).to_csv(MAP_CSV, index=False)

print("Total classes:", len(labels))