app.py

import gradio as gr
from transformers import pipeline, AutoTokenizer
from classifier import MistralForSequenceClassification
import torch
import os

HF_TOKEN = os.getenv('hf_token')

hf_writer = gr.HuggingFaceDatasetSaver(HF_TOKEN,'aisyahhrazak/tpb-crowdsourced-dataset')

# TPB Classification
tokenizer_tpb = AutoTokenizer.from_pretrained('mesolitica/malaysian-mistral-191M-MLM-512')
model_tpb = MistralForSequenceClassification.from_pretrained('aisyahhrazak/tpb-model-halal', torch_dtype=torch.bfloat16)
model_sentiment = MistralForSequenceClassification.from_pretrained('malaysia-ai/sentiment-mistral-191M-MLM', torch_dtype=torch.bfloat16)

pipeline_tpb = pipeline(task="text-classification", model=model_tpb, tokenizer=tokenizer_tpb)

# Sentiment Analysis
sentiment_pipeline = pipeline("sentiment-analysis", model=model_sentiment, tokenizer=tokenizer_tpb)

def text_classification_and_sentiment(text):
    # TPB Classification
    result_tpb = pipeline_tpb(text)
    tpb_label = result_tpb[0]['label']
    tpb_score = result_tpb[0]['score']
    
    # Sentiment Analysis
    result_sentiment = sentiment_pipeline(text)
    sentiment_label = result_sentiment[0]['label']
    sentiment_score = result_sentiment[0]['score']
    
    formatted_output = f"TPB Label: {tpb_label} (Probability: {tpb_score*100:.2f}%)\n"
    formatted_output += f"Sentiment: {sentiment_label} (Probability: {sentiment_score*100:.2f}%)"
    
    return formatted_output

examples = [
    "Alhamdulillah, hari ni dapat makan dekat restoran halal baru. Rasa puas hati dan tenang bila tau makanan yang kita makan dijamin halal.",
    "Semua orang cakap kena check logo halal sebelum beli makanan. Dah jadi macam second nature dah sekarang. Korang pun sama kan?"
]

io = gr.Interface(
    fn=text_classification_and_sentiment,
    inputs=gr.Textbox(lines=2, label="Text", placeholder="Enter text here..."),
    outputs=gr.Textbox(lines=3, label="Classification and Sentiment Result"),
    title="Text Classification and Sentiment Analysis",
    description="Enter a text to see both TPB classification and sentiment analysis results!",
    examples=examples,
    flagging_callback=hf_writer,
    allow_flagging='auto'
)

io.launch()