updated notebook

Prep_FINBert.ipynb

@@ -0,0 +1,167 @@
+{
+ "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
+}