{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import gradio as gr\n",
    "from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "tokenizer = AutoTokenizer.from_pretrained(\"yiyanghkust/finbert-fls\")\n",
    "\n",
    "finbert = AutoModelForSequenceClassification.from_pretrained(\"yiyanghkust/finbert-fls\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "nlp = pipeline(\"text-classification\", model=finbert, tokenizer=tokenizer)\n",
    "results = nlp(['we expect the age of our fleet to enhance availability and reliability due to reduced downtime for repairs.',\n",
    "               'on an equivalent unit of production basis, general and administrative expenses declined 24 percent from 1994 to $.67 per boe.',\n",
    "               'we will continue to assess the need for a valuation allowance against deferred tax assets considering all available evidence obtained in future reporting periods.'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<transformers.pipelines.text_classification.TextClassificationPipeline at 0x144572f40>"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[{'label': 'Specific FLS', 'score': 0.77278733253479},\n",
       " {'label': 'Not FLS', 'score': 0.9905241131782532},\n",
       " {'label': 'Non-specific FLS', 'score': 0.975904107093811}]"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "results"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "['we expect the age of our fleet to enhance availability and reliability due to reduced downtime for repairs.',\n",
    "               'on an equivalent unit of production basis, general and administrative expenses declined 24 percent from 1994 to $.67 per boe.',\n",
    "               'we will continue to assess the need for a valuation allowance against deferred tax assets considering all available evidence obtained in future reporting periods.']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Running on local URL:  http://127.0.0.1:7860/\n",
      "\n",
      "To create a public link, set `share=True` in `launch()`.\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div><iframe src=\"http://127.0.0.1:7860/\" width=\"900\" height=\"500\" allow=\"autoplay; camera; microphone;\" frameborder=\"0\" allowfullscreen></iframe></div>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "title = \"Forward Looking Statement Classification with FinBERT\"\n",
    "description = \"This model classifies a sentence into one of the three categories: Specific FLS, Non- Specific FLS, and Not-FLS. We label a sentence as Specific FLS if it is about the future of the company, as Non-Specific FLS if it is future-oriented but could be said of any company (e.g., cautionary language or risk disclosure), and as Not-FLS if it is not about the future.\"\n",
    "examples =[['we expect the age of our fleet to enhance availability and reliability due to reduced downtime for repairs.'],\n",
    "               ['on an equivalent unit of production basis, general and administrative expenses declined 24 percent from 1994 to $.67 per boe.'],\n",
    "               ['we will continue to assess the need for a valuation allowance against deferred tax assets considering all available evidence obtained in future reporting periods.']]\n",
    "\n",
    "def get_sentiment(input_text):\n",
    "  return nlp(input_text)\n",
    "\n",
    "iface = gr.Interface(fn=get_sentiment, \n",
    "                     inputs=\"text\", \n",
    "                     outputs=[\"text\"],\n",
    "                     title=title,\n",
    "                     description=description,\n",
    "                     examples=examples)\n",
    "iface.launch(debug=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "interpreter": {
   "hash": "325bbc5f2b77b6a5675ad3f6ec2d9cde3e7a8993fd48d3c331b30741632a2dac"
  },
  "kernelspec": {
   "display_name": "Python 3.8.13 ('hf_public')",
   "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": "3.8.13"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}