final_code.py

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load model directly\n",
    "from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, AutoModelForSequenceClassification, TextClassificationPipeline\n",
    "import torch\n",
    "import gradio as gr\n",
    "from openpyxl import load_workbook\n",
    "from numpy import mean\n",
    "\n",
    "tokenizer = AutoTokenizer.from_pretrained(\"suriya7/bart-finetuned-text-summarization\")\n",
    "model = AutoModelForSeq2SeqLM.from_pretrained(\"suriya7/bart-finetuned-text-summarization\")\n",
    "\n",
    "tokenizer_keywords = AutoTokenizer.from_pretrained(\"transformer3/H2-keywordextractor\")\n",
    "model_keywords = AutoModelForSeq2SeqLM.from_pretrained(\"transformer3/H2-keywordextractor\")\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\n",
    "label_mapping = {1: '1/5', 2: '2/5', 3: '3/5', 4: '4/5', 5: '5/5'}\n",
    "\n",
    "def parse_xl(file_path):\n",
    "    cells = []\n",
    "\n",
    "    workbook = load_workbook(filename=file_path)\n",
    "    for sheet in workbook.worksheets:\n",
    "        for row in sheet.iter_rows():\n",
    "            for cell in row:\n",
    "                if cell.value != None:\n",
    "                    cells.append(cell.value)\n",
    "\n",
    "    return cells\n",
    "\n",
    "def evaluate(file):\n",
    "    reviews = parse_xl(file)\n",
    "    ratings = []\n",
    "    text = \"\"\n",
    "\n",
    "    for review in reviews:\n",
    "        ratings.append(int(classifier(review)[0]['label'].split('_')[1]))\n",
    "        text += review\n",
    "        text += \" \"\n",
    "            \n",
    "    inputs = tokenizer([text], max_length=1024, truncation=True, return_tensors=\"pt\")\n",
    "    summary_ids = model.generate(inputs[\"input_ids\"], num_beams=2, min_length=50, max_length=1000)\n",
    "    summary = tokenizer.batch_decode(summary_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]\n",
    "\n",
    "    inputs_keywords = tokenizer_keywords([text], max_length=1024, truncation=True, return_tensors=\"pt\")\n",
    "    summary_ids_keywords = model_keywords.generate(inputs_keywords[\"input_ids\"], num_beams=2, min_length=0, max_length=100)\n",
    "    keywords = tokenizer_keywords.batch_decode(summary_ids_keywords, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]   \n",
    "\n",
    "    return round(mean(ratings), 2), summary, keywords\n",
    "\n",
    "iface = gr.Interface(\n",
    "    fn=evaluate,\n",
    "    inputs=gr.File(label=\"Reviews\", file_types=[\".xlsx\", \".xlsm\", \".xltx\", \".xltm\"]),\n",
    "    outputs=[gr.Textbox(label=\"Rating\"), gr.Textbox(label=\"Summary\"), gr.Textbox(label=\"Keywords\")],\n",
    "    title='Summarize Reviews',\n",
    "    description=\"Evaluate and summarize collection of reviews. Reviews are submitted as an Excel file, where each reviews is in its own cell.\"\n",
    ")\n",
    "\n",
    "iface.launch(share=True)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "SolutionsInPR",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.12.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}