import torch
from transformers import AutoTokenizer, AutoModel

# Danh sách aspect và sentiment labels
aspect_labels = [
    "FACILITIES#CLEANLINESS", "FACILITIES#COMFORT", "FACILITIES#DESIGN&FEATURES",
    "FACILITIES#GENERAL", "FACILITIES#MISCELLANEOUS", "FACILITIES#PRICES",
    "FACILITIES#QUALITY", "FOOD&DRINKS#MISCELLANEOUS", "FOOD&DRINKS#PRICES",
    "FOOD&DRINKS#QUALITY", "FOOD&DRINKS#STYLE&OPTIONS", "HOTEL#CLEANLINESS",
    "HOTEL#COMFORT", "HOTEL#DESIGN&FEATURES", "HOTEL#GENERAL",
    "HOTEL#MISCELLANEOUS", "HOTEL#PRICES", "HOTEL#QUALITY", "LOCATION#GENERAL",
    "ROOMS#CLEANLINESS", "ROOMS#COMFORT", "ROOMS#DESIGN&FEATURES",
    "ROOMS#GENERAL", "ROOMS#MISCELLANEOUS", "ROOMS#PRICES", "ROOMS#QUALITY",
    "ROOM_AMENITIES#CLEANLINESS", "ROOM_AMENITIES#COMFORT",
    "ROOM_AMENITIES#DESIGN&FEATURES", "ROOM_AMENITIES#GENERAL",
    "ROOM_AMENITIES#MISCELLANEOUS", "ROOM_AMENITIES#PRICES",
    "ROOM_AMENITIES#QUALITY", "SERVICE#GENERAL"
]
sentiment_labels = ["POSITIVE", "NEGATIVE", "NEUTRAL"]

# Load tokenizer và model (phải về đúng class TransformerForABSA)
repo = "visolex/phobert-absa-hotel"
tokenizer = AutoTokenizer.from_pretrained(repo, trust_remote_code=True)
model = AutoModel.from_pretrained(repo, trust_remote_code=True)
model.eval()

def predict_absa_multi(
    text: str,
    aspect_labels: list[str],
    sentiment_labels: list[str],
    threshold: float = 0.5
) -> list[tuple[str,str]]:
    inputs = tokenizer(
        text,
        return_tensors="pt",
        padding=True,
        truncation=True,
        max_length=256
    )
    inputs.pop("token_type_ids", None)

    with torch.no_grad():
        out = model(**inputs)

    # out.logits có shape [1, A, S+1]
    logits = out.logits.squeeze(0)
    probs = torch.softmax(logits, dim=-1)

    num_s = len(sentiment_labels)
    none_id = probs.size(-1) - 1
    results = []

    for i, asp in enumerate(aspect_labels):
        prob_i = probs[i]
        pred_id = int(prob_i.argmax().item())

        if pred_id != none_id and pred_id < num_s:
            score = prob_i[pred_id].item()
            if score >= threshold:
                results.append((asp, sentiment_labels[pred_id].lower()))

    return results

# Example usage
text = "Khách sạn này sạch sẽ nhưng phòng lại hơi nhỏ và dịch vụ chưa tốt lắm."
preds = predict_absa_multi(text, aspect_labels, sentiment_labels, threshold=0.2)
print(preds)
# Expected output similar to: [('HOTEL#CLEANLINESS', 'positive'), ('ROOMS#COMFORT', 'negative'), ('SERVICE#GENERAL', 'negative')]