File size: 3,985 Bytes
a9cce51 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 |
{
"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
}
|