#!/usr/bin/env python3
"""Inference script for HR conversation multi-label classifier."""
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

MODEL_ID = "AurelPx/hr-conversations-classifier"

LABELS = [
    "Benefits", "Career Development", "Compliance & Legal", "Contracts",
    "Diversity, Equity & Inclusion", "Expense Management", "Harassment", "Health",
    "IT & Equipment", "Leave & Absence", "Mobility", "Offboarding",
    "Onboarding", "Payroll", "Performance Management", "Recruitment",
    "Safety", "Timetracking", "Training", "Work Arrangements",
]

tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
model = AutoModelForSequenceClassification.from_pretrained(MODEL_ID)
model.eval()

def classify(text: str, threshold: float = 0.5):
    inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=512)
    with torch.no_grad():
        logits = model(**inputs).logits
    probs = torch.sigmoid(logits).numpy()[0]
    predicted = [LABELS[i] for i, p in enumerate(probs) if p >= threshold]
    probs_dict = {LABELS[i]: round(float(p), 3) for i, p in enumerate(probs)}
    return predicted, probs_dict

if __name__ == "__main__":
    sample = (
        "USER: I haven't received my payslip for March yet. Could you please check what's going on?\n"
        "AGENT: Good morning. I've checked the payroll system and it appears your March payslip "
        "was generated on the 28th but there was a distribution delay. I've resent it to your "
        "registered email. You should receive it within the next hour."
    )
    preds, probs = classify(sample, threshold=0.5)
    print(f"Predicted: {preds}")
    print(f"Top probs: {sorted(probs.items(), key=lambda x: x[1], reverse=True)[:5]}")