{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from transformers import AutoModelForSequenceClassification, AutoTokenizer, TextClassificationPipeline\n",
    "import torch\n",
    "import gradio as gr\n",
    "\n",
    "device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
    "# Load the fine-tuned model and tokenizer\n",
    "new_model = AutoModelForSequenceClassification.from_pretrained('roberta-rating')\n",
    "new_tokenizer = AutoTokenizer.from_pretrained('roberta-rating')\n",
    "\n",
    "\n",
    "# Create a classification pipeline\n",
    "classifier = TextClassificationPipeline(model=new_model, tokenizer=new_tokenizer, device=device)\n",
    "\n",
    "# Add label mapping for sentiment analysis (assuming LABEL_0 = 'negative' and LABEL_1 = 'positive')\n",
    "label_mapping = {1: '1/5', 2: '2/5', 3: '3/5', 4: '4/5', 5: '5/5'}\n",
    "\n",
    "def evaluate(text):\n",
    "    result = classifier(text)\n",
    "    return label_mapping[int(result[0]['label'].split('_')[1])] + \".\", result[0]['score']\n",
    "\n",
    "iface = gr.Interface(\n",
    "    fn=evaluate,\n",
    "    inputs=gr.Textbox(label=\"Review\"),\n",
    "    outputs=[gr.Textbox(label=\"Evaluation\"), gr.Textbox(label=\"Score\")],\n",
    "    title='Write a review',\n",
    "    description=\"Write a product review, and the model will evaluate its numerical rating\"\n",
    ")\n",
    "\n",
    "iface.launch(share=True)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "SolutionsInPR",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "name": "python",
   "version": "3.12.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}