{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/emmanuelkoupoh/Documents/Github/LP_NLP/venv/lib/python3.9/site-packages/tqdm/auto.py:22: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
      "  from .autonotebook import tqdm as notebook_tqdm\n"
     ]
    }
   ],
   "source": [
    "from transformers import AutoModelForSequenceClassification\n",
    "from transformers import TFAutoModelForSequenceClassification\n",
    "from transformers import AutoTokenizer, AutoConfig\n",
    "import numpy as np\n",
    "from scipy.special import softmax\n",
    "import gradio as gr"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Requirements\n",
    "model_path = f\"test_trainer/checkpoint-1000/\"\n",
    "tokenizer = AutoTokenizer.from_pretrained('bert-base-cased')\n",
    "config = AutoConfig.from_pretrained(model_path)\n",
    "model = AutoModelForSequenceClassification.from_pretrained(model_path)\n",
    "\n",
    "# Preprocess text (username and link placeholders)\n",
    "def preprocess(text):\n",
    "    new_text = []\n",
    "    for t in text.split(\" \"):\n",
    "        t = '@user' if t.startswith('@') and len(t) > 1 else t\n",
    "        t = 'http' if t.startswith('http') else t\n",
    "        new_text.append(t)\n",
    "    return \" \".join(new_text)\n",
    "\n",
    "\n",
    "def sentiment_analysis(text):\n",
    "    text = preprocess(text)\n",
    "\n",
    "    # PyTorch-based models\n",
    "    encoded_input = tokenizer(text, return_tensors='pt')\n",
    "    output = model(**encoded_input)\n",
    "    scores_ = output[0][0].detach().numpy()\n",
    "    scores_ = softmax(scores_)\n",
    "    \n",
    "    # Format output dict of scores\n",
    "    labels = ['Negative', 'Neutral', 'Positive']\n",
    "    scores = {l:float(s) for (l,s) in zip(labels, scores_) }\n",
    "    \n",
    "    return scores\n",
    "\n",
    "demo = gr.Interface(\n",
    "    fn=sentiment_analysis, \n",
    "    inputs=gr.Textbox(placeholder=\"Write your tweet here...\"), \n",
    "    outputs=\"label\", \n",
    "    interpretation=\"default\",\n",
    "    examples=[[\"This is wonderful!\"]])\n",
    "\n",
    "demo.launch()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.9.6 ('venv': venv)",
   "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": "3.9.6 (default, Aug  5 2022, 15:21:02) \n[Clang 14.0.0 (clang-1400.0.29.102)]"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "1ab24538aa0da4b2d8c48eaca591ff7ffc54671225fb0511b432fd9e26a098ba"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}