mau.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: spacy in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (3.4.4)\n",
      "Requirement already satisfied: thinc<8.2.0,>=8.1.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy) (8.1.5)\n",
      "Requirement already satisfied: numpy>=1.15.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy) (1.23.2)\n",
      "Requirement already satisfied: typer<0.8.0,>=0.3.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy) (0.7.0)\n",
      "Requirement already satisfied: langcodes<4.0.0,>=3.2.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy) (3.3.0)\n",
      "Requirement already satisfied: requests<3.0.0,>=2.13.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy) (2.28.1)\n",
      "Requirement already satisfied: jinja2 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy) (3.1.2)\n",
      "Requirement already satisfied: wasabi<1.1.0,>=0.9.1 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy) (0.10.1)\n",
      "Requirement already satisfied: pydantic!=1.8,!=1.8.1,<1.11.0,>=1.7.4 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy) (1.10.2)\n",
      "Requirement already satisfied: preshed<3.1.0,>=3.0.2 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy) (3.0.8)\n",
      "Requirement already satisfied: setuptools in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy) (57.4.0)\n",
      "Requirement already satisfied: spacy-loggers<2.0.0,>=1.0.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy) (1.0.4)\n",
      "Requirement already satisfied: smart-open<7.0.0,>=5.2.1 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy) (6.3.0)\n",
      "Requirement already satisfied: cymem<2.1.0,>=2.0.2 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy) (2.0.7)\n",
      "Requirement already satisfied: tqdm<5.0.0,>=4.38.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy) (4.64.1)\n",
      "Requirement already satisfied: srsly<3.0.0,>=2.4.3 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy) (2.4.5)\n",
      "Requirement already satisfied: catalogue<2.1.0,>=2.0.6 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy) (2.0.8)\n",
      "Requirement already satisfied: spacy-legacy<3.1.0,>=3.0.10 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy) (3.0.10)\n",
      "Requirement already satisfied: pathy>=0.3.5 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy) (0.10.1)\n",
      "Requirement already satisfied: packaging>=20.0 in c:\\users\\dell\\appdata\\roaming\\python\\python39\\site-packages (from spacy) (21.3)\n",
      "Requirement already satisfied: murmurhash<1.1.0,>=0.28.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy) (1.0.9)\n",
      "Requirement already satisfied: pyparsing!=3.0.5,>=2.0.2 in c:\\users\\dell\\appdata\\roaming\\python\\python39\\site-packages (from packaging>=20.0->spacy) (3.0.9)\n",
      "Requirement already satisfied: typing-extensions>=4.1.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from pydantic!=1.8,!=1.8.1,<1.11.0,>=1.7.4->spacy) (4.2.0)\n",
      "Requirement already satisfied: charset-normalizer<3,>=2 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from requests<3.0.0,>=2.13.0->spacy) (2.0.12)\n",
      "Requirement already satisfied: certifi>=2017.4.17 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from requests<3.0.0,>=2.13.0->spacy) (2022.5.18.1)\n",
      "Requirement already satisfied: urllib3<1.27,>=1.21.1 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from requests<3.0.0,>=2.13.0->spacy) (1.26.9)\n",
      "Requirement already satisfied: idna<4,>=2.5 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from requests<3.0.0,>=2.13.0->spacy) (3.3)\n",
      "Requirement already satisfied: blis<0.8.0,>=0.7.8 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from thinc<8.2.0,>=8.1.0->spacy) (0.7.9)\n",
      "Requirement already satisfied: confection<1.0.0,>=0.0.1 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from thinc<8.2.0,>=8.1.0->spacy) (0.0.3)\n",
      "Requirement already satisfied: colorama in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from tqdm<5.0.0,>=4.38.0->spacy) (0.4.5)\n",
      "Requirement already satisfied: click<9.0.0,>=7.1.1 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from typer<0.8.0,>=0.3.0->spacy) (8.1.3)\n",
      "Requirement already satisfied: MarkupSafe>=2.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from jinja2->spacy) (2.1.1)\n",
      "Note: you may need to restart the kernel to use updated packages.\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "WARNING: You are using pip version 21.2.3; however, version 22.3.1 is available.\n",
      "You should consider upgrading via the 'c:\\Users\\DELL\\AppData\\Local\\Programs\\Python\\Python39\\python.exe -m pip install --upgrade pip' command.\n"
     ]
    }
   ],
   "source": [
    "%pip install spacy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: spacy in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (3.4.4)\n",
      "Requirement already satisfied: catalogue<2.1.0,>=2.0.6 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy) (2.0.8)\n",
      "Requirement already satisfied: packaging>=20.0 in c:\\users\\dell\\appdata\\roaming\\python\\python39\\site-packages (from spacy) (21.3)\n",
      "Requirement already satisfied: murmurhash<1.1.0,>=0.28.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy) (1.0.9)\n",
      "Requirement already satisfied: typer<0.8.0,>=0.3.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy) (0.7.0)\n",
      "Requirement already satisfied: cymem<2.1.0,>=2.0.2 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy) (2.0.7)\n",
      "Requirement already satisfied: setuptools in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy) (57.4.0)\n",
      "Requirement already satisfied: tqdm<5.0.0,>=4.38.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy) (4.64.1)\n",
      "Requirement already satisfied: thinc<8.2.0,>=8.1.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy) (8.1.5)\n",
      "Requirement already satisfied: langcodes<4.0.0,>=3.2.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy) (3.3.0)\n",
      "Requirement already satisfied: requests<3.0.0,>=2.13.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy) (2.28.1)\n",
      "Requirement already satisfied: srsly<3.0.0,>=2.4.3 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy) (2.4.5)\n",
      "Requirement already satisfied: spacy-legacy<3.1.0,>=3.0.10 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy) (3.0.10)\n",
      "Requirement already satisfied: smart-open<7.0.0,>=5.2.1 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy) (6.3.0)\n",
      "Requirement already satisfied: preshed<3.1.0,>=3.0.2 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy) (3.0.8)\n",
      "Requirement already satisfied: wasabi<1.1.0,>=0.9.1 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy) (0.10.1)\n",
      "Requirement already satisfied: pydantic!=1.8,!=1.8.1,<1.11.0,>=1.7.4 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy) (1.10.2)\n",
      "Requirement already satisfied: pathy>=0.3.5 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy) (0.10.1)\n",
      "Requirement already satisfied: jinja2 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy) (3.1.2)\n",
      "Requirement already satisfied: spacy-loggers<2.0.0,>=1.0.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy) (1.0.4)\n",
      "Requirement already satisfied: numpy>=1.15.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy) (1.23.2)\n",
      "Requirement already satisfied: pyparsing!=3.0.5,>=2.0.2 in c:\\users\\dell\\appdata\\roaming\\python\\python39\\site-packages (from packaging>=20.0->spacy) (3.0.9)\n",
      "Requirement already satisfied: typing-extensions>=4.1.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from pydantic!=1.8,!=1.8.1,<1.11.0,>=1.7.4->spacy) (4.2.0)\n",
      "Requirement already satisfied: charset-normalizer<3,>=2 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from requests<3.0.0,>=2.13.0->spacy) (2.0.12)\n",
      "Requirement already satisfied: urllib3<1.27,>=1.21.1 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from requests<3.0.0,>=2.13.0->spacy) (1.26.9)\n",
      "Requirement already satisfied: certifi>=2017.4.17 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from requests<3.0.0,>=2.13.0->spacy) (2022.5.18.1)\n",
      "Requirement already satisfied: idna<4,>=2.5 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from requests<3.0.0,>=2.13.0->spacy) (3.3)\n",
      "Requirement already satisfied: confection<1.0.0,>=0.0.1 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from thinc<8.2.0,>=8.1.0->spacy) (0.0.3)\n",
      "Requirement already satisfied: blis<0.8.0,>=0.7.8 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from thinc<8.2.0,>=8.1.0->spacy) (0.7.9)\n",
      "Requirement already satisfied: colorama in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from tqdm<5.0.0,>=4.38.0->spacy) (0.4.5)\n",
      "Requirement already satisfied: click<9.0.0,>=7.1.1 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from typer<0.8.0,>=0.3.0->spacy) (8.1.3)\n",
      "Requirement already satisfied: MarkupSafe>=2.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from jinja2->spacy) (2.1.1)\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "WARNING: You are using pip version 21.2.3; however, version 22.3.1 is available.\n",
      "You should consider upgrading via the 'c:\\Users\\DELL\\AppData\\Local\\Programs\\Python\\Python39\\python.exe -m pip install --upgrade pip' command.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "⚠ As of spaCy v3.0, shortcuts like 'en' are deprecated. Please use the full\n",
      "pipeline package name 'en_core_web_sm' instead.\n",
      "Collecting en-core-web-sm==3.4.1\n",
      "  Downloading https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.4.1/en_core_web_sm-3.4.1-py3-none-any.whl (12.8 MB)\n",
      "Requirement already satisfied: spacy<3.5.0,>=3.4.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from en-core-web-sm==3.4.1) (3.4.4)\n",
      "Requirement already satisfied: cymem<2.1.0,>=2.0.2 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (2.0.7)\n",
      "Requirement already satisfied: smart-open<7.0.0,>=5.2.1 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (6.3.0)\n",
      "Requirement already satisfied: murmurhash<1.1.0,>=0.28.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (1.0.9)\n",
      "Requirement already satisfied: catalogue<2.1.0,>=2.0.6 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (2.0.8)\n",
      "Requirement already satisfied: requests<3.0.0,>=2.13.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (2.28.1)\n",
      "Requirement already satisfied: typer<0.8.0,>=0.3.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (0.7.0)\n",
      "Requirement already satisfied: numpy>=1.15.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (1.23.2)\n",
      "Requirement already satisfied: tqdm<5.0.0,>=4.38.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (4.64.1)\n",
      "Requirement already satisfied: pathy>=0.3.5 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (0.10.1)\n",
      "Requirement already satisfied: wasabi<1.1.0,>=0.9.1 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (0.10.1)\n",
      "Requirement already satisfied: pydantic!=1.8,!=1.8.1,<1.11.0,>=1.7.4 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (1.10.2)\n",
      "Requirement already satisfied: jinja2 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (3.1.2)\n",
      "Requirement already satisfied: langcodes<4.0.0,>=3.2.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (3.3.0)\n",
      "Requirement already satisfied: spacy-legacy<3.1.0,>=3.0.10 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (3.0.10)\n",
      "Requirement already satisfied: packaging>=20.0 in c:\\users\\dell\\appdata\\roaming\\python\\python39\\site-packages (from spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (21.3)\n",
      "Requirement already satisfied: thinc<8.2.0,>=8.1.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (8.1.5)\n",
      "Requirement already satisfied: srsly<3.0.0,>=2.4.3 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (2.4.5)\n",
      "Requirement already satisfied: spacy-loggers<2.0.0,>=1.0.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (1.0.4)\n",
      "Requirement already satisfied: setuptools in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (57.4.0)\n",
      "Requirement already satisfied: preshed<3.1.0,>=3.0.2 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (3.0.8)\n",
      "Requirement already satisfied: pyparsing!=3.0.5,>=2.0.2 in c:\\users\\dell\\appdata\\roaming\\python\\python39\\site-packages (from packaging>=20.0->spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (3.0.9)\n",
      "Requirement already satisfied: typing-extensions>=4.1.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from pydantic!=1.8,!=1.8.1,<1.11.0,>=1.7.4->spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (4.2.0)\n",
      "Requirement already satisfied: urllib3<1.27,>=1.21.1 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from requests<3.0.0,>=2.13.0->spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (1.26.9)\n",
      "Requirement already satisfied: idna<4,>=2.5 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from requests<3.0.0,>=2.13.0->spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (3.3)\n",
      "Requirement already satisfied: charset-normalizer<3,>=2 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from requests<3.0.0,>=2.13.0->spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (2.0.12)\n",
      "Requirement already satisfied: certifi>=2017.4.17 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from requests<3.0.0,>=2.13.0->spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (2022.5.18.1)\n",
      "Requirement already satisfied: confection<1.0.0,>=0.0.1 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from thinc<8.2.0,>=8.1.0->spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (0.0.3)\n",
      "Requirement already satisfied: blis<0.8.0,>=0.7.8 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from thinc<8.2.0,>=8.1.0->spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (0.7.9)\n",
      "Requirement already satisfied: colorama in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from tqdm<5.0.0,>=4.38.0->spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (0.4.5)\n",
      "Requirement already satisfied: click<9.0.0,>=7.1.1 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from typer<0.8.0,>=0.3.0->spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (8.1.3)\n",
      "Requirement already satisfied: MarkupSafe>=2.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from jinja2->spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (2.1.1)\n",
      "✔ Download and installation successful\n",
      "You can now load the package via spacy.load('en_core_web_sm')\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "WARNING: You are using pip version 21.2.3; however, version 22.3.1 is available.\n",
      "You should consider upgrading via the 'c:\\Users\\DELL\\AppData\\Local\\Programs\\Python\\Python39\\python.exe -m pip install --upgrade pip' command.\n"
     ]
    }
   ],
   "source": [
    "import sys\n",
    "!{sys.executable} -m pip install spacy\n",
    "!{sys.executable} -m spacy download en"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Note: you may need to restart the kernel to use updated packages.\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "WARNING: You are using pip version 21.2.3; however, version 22.3.1 is available.\n",
      "You should consider upgrading via the 'c:\\Users\\DELL\\AppData\\Local\\Programs\\Python\\Python39\\python.exe -m pip install --upgrade pip' command.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: keras in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (2.11.0)\n"
     ]
    }
   ],
   "source": [
    "pip install keras"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: tensorflow in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (2.11.0)\n",
      "Requirement already satisfied: tensorflow-intel==2.11.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from tensorflow) (2.11.0)\n",
      "Requirement already satisfied: flatbuffers>=2.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from tensorflow-intel==2.11.0->tensorflow) (22.12.6)\n",
      "Requirement already satisfied: grpcio<2.0,>=1.24.3 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from tensorflow-intel==2.11.0->tensorflow) (1.51.1)\n",
      "Requirement already satisfied: google-pasta>=0.1.1 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from tensorflow-intel==2.11.0->tensorflow) (0.2.0)\n",
      "Requirement already satisfied: wrapt>=1.11.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from tensorflow-intel==2.11.0->tensorflow) (1.14.1)\n",
      "Requirement already satisfied: protobuf<3.20,>=3.9.2 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from tensorflow-intel==2.11.0->tensorflow) (3.19.6)\n",
      "Requirement already satisfied: absl-py>=1.0.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from tensorflow-intel==2.11.0->tensorflow) (1.3.0)\n",
      "Requirement already satisfied: six>=1.12.0 in c:\\users\\dell\\appdata\\roaming\\python\\python39\\site-packages (from tensorflow-intel==2.11.0->tensorflow) (1.16.0)\n",
      "Requirement already satisfied: packaging in c:\\users\\dell\\appdata\\roaming\\python\\python39\\site-packages (from tensorflow-intel==2.11.0->tensorflow) (21.3)\n",
      "Requirement already satisfied: gast<=0.4.0,>=0.2.1 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from tensorflow-intel==2.11.0->tensorflow) (0.4.0)\n",
      "Requirement already satisfied: tensorboard<2.12,>=2.11 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from tensorflow-intel==2.11.0->tensorflow) (2.11.0)\n",
      "Requirement already satisfied: tensorflow-io-gcs-filesystem>=0.23.1 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from tensorflow-intel==2.11.0->tensorflow) (0.28.0)\n",
      "Requirement already satisfied: opt-einsum>=2.3.2 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from tensorflow-intel==2.11.0->tensorflow) (3.3.0)\n",
      "Requirement already satisfied: keras<2.12,>=2.11.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from tensorflow-intel==2.11.0->tensorflow) (2.11.0)\n",
      "Requirement already satisfied: setuptools in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from tensorflow-intel==2.11.0->tensorflow) (57.4.0)\n",
      "Requirement already satisfied: tensorflow-estimator<2.12,>=2.11.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from tensorflow-intel==2.11.0->tensorflow) (2.11.0)\n",
      "Requirement already satisfied: typing-extensions>=3.6.6 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from tensorflow-intel==2.11.0->tensorflow) (4.2.0)\n",
      "Requirement already satisfied: numpy>=1.20 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from tensorflow-intel==2.11.0->tensorflow) (1.23.2)\n",
      "Requirement already satisfied: h5py>=2.9.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from tensorflow-intel==2.11.0->tensorflow) (3.7.0)\n",
      "Requirement already satisfied: libclang>=13.0.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from tensorflow-intel==2.11.0->tensorflow) (14.0.6)\n",
      "Requirement already satisfied: astunparse>=1.6.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from tensorflow-intel==2.11.0->tensorflow) (1.6.3)\n",
      "Requirement already satisfied: termcolor>=1.1.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from tensorflow-intel==2.11.0->tensorflow) (2.1.1)\n",
      "Requirement already satisfied: wheel<1.0,>=0.23.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from astunparse>=1.6.0->tensorflow-intel==2.11.0->tensorflow) (0.38.4)\n",
      "Requirement already satisfied: google-auth-oauthlib<0.5,>=0.4.1 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from tensorboard<2.12,>=2.11->tensorflow-intel==2.11.0->tensorflow) (0.4.6)\n",
      "Requirement already satisfied: markdown>=2.6.8 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from tensorboard<2.12,>=2.11->tensorflow-intel==2.11.0->tensorflow) (3.4.1)\n",
      "Requirement already satisfied: tensorboard-data-server<0.7.0,>=0.6.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from tensorboard<2.12,>=2.11->tensorflow-intel==2.11.0->tensorflow) (0.6.1)\n",
      "Requirement already satisfied: google-auth<3,>=1.6.3 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from tensorboard<2.12,>=2.11->tensorflow-intel==2.11.0->tensorflow) (2.15.0)\n",
      "Requirement already satisfied: requests<3,>=2.21.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from tensorboard<2.12,>=2.11->tensorflow-intel==2.11.0->tensorflow) (2.28.1)\n",
      "Requirement already satisfied: werkzeug>=1.0.1 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from tensorboard<2.12,>=2.11->tensorflow-intel==2.11.0->tensorflow) (2.2.2)\n",
      "Requirement already satisfied: tensorboard-plugin-wit>=1.6.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from tensorboard<2.12,>=2.11->tensorflow-intel==2.11.0->tensorflow) (1.8.1)\n",
      "Requirement already satisfied: cachetools<6.0,>=2.0.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from google-auth<3,>=1.6.3->tensorboard<2.12,>=2.11->tensorflow-intel==2.11.0->tensorflow) (5.2.0)\n",
      "Requirement already satisfied: pyasn1-modules>=0.2.1 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from google-auth<3,>=1.6.3->tensorboard<2.12,>=2.11->tensorflow-intel==2.11.0->tensorflow) (0.2.8)\n",
      "Requirement already satisfied: rsa<5,>=3.1.4 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from google-auth<3,>=1.6.3->tensorboard<2.12,>=2.11->tensorflow-intel==2.11.0->tensorflow) (4.9)\n",
      "Requirement already satisfied: requests-oauthlib>=0.7.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from google-auth-oauthlib<0.5,>=0.4.1->tensorboard<2.12,>=2.11->tensorflow-intel==2.11.0->tensorflow) (1.3.1)\n",
      "Requirement already satisfied: importlib-metadata>=4.4 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from markdown>=2.6.8->tensorboard<2.12,>=2.11->tensorflow-intel==2.11.0->tensorflow) (5.0.0)\n",
      "Requirement already satisfied: zipp>=0.5 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from importlib-metadata>=4.4->markdown>=2.6.8->tensorboard<2.12,>=2.11->tensorflow-intel==2.11.0->tensorflow) (3.10.0)\n",
      "Requirement already satisfied: pyasn1<0.5.0,>=0.4.6 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from pyasn1-modules>=0.2.1->google-auth<3,>=1.6.3->tensorboard<2.12,>=2.11->tensorflow-intel==2.11.0->tensorflow) (0.4.8)\n",
      "Requirement already satisfied: charset-normalizer<3,>=2 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from requests<3,>=2.21.0->tensorboard<2.12,>=2.11->tensorflow-intel==2.11.0->tensorflow) (2.0.12)\n",
      "Requirement already satisfied: idna<4,>=2.5 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from requests<3,>=2.21.0->tensorboard<2.12,>=2.11->tensorflow-intel==2.11.0->tensorflow) (3.3)\n",
      "Requirement already satisfied: urllib3<1.27,>=1.21.1 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from requests<3,>=2.21.0->tensorboard<2.12,>=2.11->tensorflow-intel==2.11.0->tensorflow) (1.26.9)\n",
      "Requirement already satisfied: certifi>=2017.4.17 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from requests<3,>=2.21.0->tensorboard<2.12,>=2.11->tensorflow-intel==2.11.0->tensorflow) (2022.5.18.1)\n",
      "Requirement already satisfied: oauthlib>=3.0.0 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from requests-oauthlib>=0.7.0->google-auth-oauthlib<0.5,>=0.4.1->tensorboard<2.12,>=2.11->tensorflow-intel==2.11.0->tensorflow) (3.2.2)\n",
      "Requirement already satisfied: MarkupSafe>=2.1.1 in c:\\users\\dell\\appdata\\local\\programs\\python\\python39\\lib\\site-packages (from werkzeug>=1.0.1->tensorboard<2.12,>=2.11->tensorflow-intel==2.11.0->tensorflow) (2.1.1)\n",
      "Requirement already satisfied: pyparsing!=3.0.5,>=2.0.2 in c:\\users\\dell\\appdata\\roaming\\python\\python39\\site-packages (from packaging->tensorflow-intel==2.11.0->tensorflow) (3.0.9)\n",
      "Note: you may need to restart the kernel to use updated packages.\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "WARNING: You are using pip version 21.2.3; however, version 22.3.1 is available.\n",
      "You should consider upgrading via the 'c:\\Users\\DELL\\AppData\\Local\\Programs\\Python\\Python39\\python.exe -m pip install --upgrade pip' command.\n"
     ]
    }
   ],
   "source": [
    "pip install tensorflow"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Nguồn tham khảo\n",
    "https://github.com/ElzatY/aspect-based-sentiment-classification-model/blob/master/aspect_based_sentiment.ipynb\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[nltk_data] Downloading package stopwords to\n",
      "[nltk_data]     C:\\Users\\DELL\\AppData\\Roaming\\nltk_data...\n",
      "[nltk_data]   Package stopwords is already up-to-date!\n",
      "c:\\Users\\DELL\\AppData\\Local\\Programs\\Python\\Python39\\lib\\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": [
    "\n",
    "# NLTK\n",
    "import nltk\n",
    "from nltk.corpus import stopwords\n",
    "from nltk.stem import SnowballStemmer\n",
    "nltk.download('stopwords')\n",
    "\n",
    "#Spacy\n",
    "import spacy\n",
    "nlp = spacy.load('en_core_web_sm')\n",
    "\n",
    "# Other\n",
    "import re\n",
    "import json\n",
    "import string\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import warnings\n",
    "warnings.filterwarnings('ignore')\n",
    "from sklearn.preprocessing import LabelEncoder\n",
    "\n",
    "#Keras\n",
    "from keras.models import load_model\n",
    "from keras.models import Sequential\n",
    "from keras.layers import Dense, Activation\n",
    "from keras.preprocessing.text import Tokenizer\n",
    "from keras.utils import to_categorical"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Unnamed: 0</th>\n",
       "      <th>Comment</th>\n",
       "      <th>Aspect</th>\n",
       "      <th>polarity</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>interesting concept grab quick bite</td>\n",
       "      <td>general</td>\n",
       "      <td>positive</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>small selection sandwich chip thing pop microwave</td>\n",
       "      <td>general</td>\n",
       "      <td>neutral</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>5</td>\n",
       "      <td>interesting concept chain convenience store op...</td>\n",
       "      <td>experience</td>\n",
       "      <td>positive</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>6</td>\n",
       "      <td>interesting concept chain convenience store op...</td>\n",
       "      <td>general</td>\n",
       "      <td>positive</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>8</td>\n",
       "      <td>found store partially customer able purchase p...</td>\n",
       "      <td>payment</td>\n",
       "      <td>neutral</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Unnamed: 0                                            Comment      Aspect  \\\n",
       "0          1                interesting concept grab quick bite     general   \n",
       "1          2  small selection sandwich chip thing pop microwave     general   \n",
       "2          5  interesting concept chain convenience store op...  experience   \n",
       "3          6  interesting concept chain convenience store op...     general   \n",
       "4          8  found store partially customer able purchase p...     payment   \n",
       "\n",
       "   polarity  \n",
       "0  positive  \n",
       "1   neutral  \n",
       "2  positive  \n",
       "3  positive  \n",
       "4   neutral  "
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#load data\n",
    "import pandas as pd\n",
    "reviews_train = pd.read_csv(\"sampleDataset.csv\").astype(str)\n",
    "\n",
    "#show first 5 records\n",
    "reviews_train.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "#drop unnecessary columns\n",
    "reviews_train = reviews_train.drop(['Unnamed: 0'], axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# plot the number of reviews per polarity\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "# create a countplot\n",
    "sns.countplot(x='polarity', data=reviews_train)\n",
    "# show the plot\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "#tokenize review text\n",
    "vocab_size = 6000 # We set a maximum size for the vocabulary\n",
    "tokenizer = Tokenizer(num_words=vocab_size)\n",
    "tokenizer.fit_on_texts(reviews_train.Comment)\n",
    "reviews_tokenized = pd.DataFrame(tokenizer.texts_to_matrix(reviews_train.Comment))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "      <th>6</th>\n",
       "      <th>7</th>\n",
       "      <th>8</th>\n",
       "      <th>9</th>\n",
       "      <th>...</th>\n",
       "      <th>5990</th>\n",
       "      <th>5991</th>\n",
       "      <th>5992</th>\n",
       "      <th>5993</th>\n",
       "      <th>5994</th>\n",
       "      <th>5995</th>\n",
       "      <th>5996</th>\n",
       "      <th>5997</th>\n",
       "      <th>5998</th>\n",
       "      <th>5999</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>76254</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>76255</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>76256</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>76257</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>76258</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>76259 rows × 6000 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       0     1     2     3     4     5     6     7     8     9     ...  5990  \\\n",
       "0       0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  ...   0.0   \n",
       "1       0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  ...   0.0   \n",
       "2       0.0   1.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  ...   0.0   \n",
       "3       0.0   1.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  ...   0.0   \n",
       "4       0.0   1.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  ...   0.0   \n",
       "...     ...   ...   ...   ...   ...   ...   ...   ...   ...   ...  ...   ...   \n",
       "76254   0.0   0.0   0.0   0.0   0.0   1.0   0.0   0.0   0.0   0.0  ...   0.0   \n",
       "76255   0.0   0.0   1.0   0.0   1.0   0.0   0.0   0.0   0.0   0.0  ...   0.0   \n",
       "76256   0.0   0.0   1.0   0.0   1.0   0.0   0.0   1.0   0.0   0.0  ...   0.0   \n",
       "76257   0.0   0.0   1.0   0.0   1.0   0.0   0.0   1.0   0.0   0.0  ...   0.0   \n",
       "76258   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  ...   0.0   \n",
       "\n",
       "       5991  5992  5993  5994  5995  5996  5997  5998  5999  \n",
       "0       0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "1       0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "2       0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "3       0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "4       0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "...     ...   ...   ...   ...   ...   ...   ...   ...   ...  \n",
       "76254   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "76255   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "76256   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "76257   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "76258   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "\n",
       "[76259 rows x 6000 columns]"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "reviews_tokenized"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "#encode aspect classes\n",
    "label_encoder = LabelEncoder()\n",
    "integer_category = label_encoder.fit_transform(reviews_train.Aspect)\n",
    "encoded_aspect = to_categorical(integer_category)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-1 {color: black;background-color: white;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>DecisionTreeClassifier()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">DecisionTreeClassifier</label><div class=\"sk-toggleable__content\"><pre>DecisionTreeClassifier()</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "DecisionTreeClassifier()"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# build a decision tree classifier for aspect classification\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.metrics import accuracy_score\n",
    "from sklearn.metrics import confusion_matrix\n",
    "from sklearn.metrics import classification_report\n",
    "\n",
    "# split the dataset into training and testing sets\n",
    "X_train, X_test, y_train, y_test = train_test_split(reviews_tokenized, encoded_aspect, test_size=0.2, random_state=42)\n",
    "\n",
    "# build a decision tree classifier\n",
    "dtree = DecisionTreeClassifier()\n",
    "dtree.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[ 301   21   37    3    9    6    2  102    3]\n",
      " [ 484 2322  365   26  349   55   23   58  107]\n",
      " [ 672  387 3003   38   89  113   42   70   77]\n",
      " [ 177   46   40  244   58   46    3    2    5]\n",
      " [ 465  362   77   69  501  223   12  164   18]\n",
      " [ 402   45   96   41  154  737   12    7   33]\n",
      " [ 157   15   37    5   10   16  145    6    6]\n",
      " [ 376   62   98    4  163   10    5  359   45]\n",
      " [ 167  100   72   10   16   37    2   30  496]]\n"
     ]
    }
   ],
   "source": [
    "# predict the labels on validation dataset\n",
    "predictions = dtree.predict(X_test)\n",
    "\n",
    "# Report the confusion matrix for multi-class classification\n",
    "print(confusion_matrix(y_test.argmax(axis=1), predictions.argmax(axis=1)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.5226199842643587\n"
     ]
    }
   ],
   "source": [
    "#print model accuracy\n",
    "print(\"Accuracy:\",accuracy_score(y_test, predictions))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0., 0., 0., ..., 0., 1., 0.],\n",
       "       [0., 0., 1., ..., 0., 0., 0.],\n",
       "       [0., 0., 0., ..., 1., 0., 0.],\n",
       "       ...,\n",
       "       [0., 0., 0., ..., 0., 0., 0.],\n",
       "       [0., 0., 0., ..., 0., 0., 0.],\n",
       "       [0., 0., 0., ..., 0., 0., 0.]], dtype=float32)"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# print classification results\n",
    "predictions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "# convert predictions to aspect classes\n",
    "predictions_text = label_encoder.inverse_transform(predictions.argmax(axis=1))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['technology', 'general', 'privacy', ..., 'availability',\n",
       "       'availability', 'payment'], dtype=object)"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "predictions_text"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "# function to predict aspect class for a given review\n",
    "def predict_aspect(review):\n",
    "    # remove punctuation\n",
    "    review = review.translate(str.maketrans('', '', string.punctuation))\n",
    "    # remove numbers\n",
    "    review = re.sub(r'\\d+', '', review)\n",
    "    # remove stopwords\n",
    "    review = ' '.join([word for word in review.split() if word not in (stopwords.words('english'))])\n",
    "    # stemming\n",
    "    stemmer = SnowballStemmer(\"english\")\n",
    "    review = ' '.join([stemmer.stem(word) for word in review.split()])\n",
    "    # lowercase\n",
    "    review = review.lower()\n",
    "    # tokenize the review\n",
    "    review_tokenized = tokenizer.texts_to_matrix([review])\n",
    "    # predict the aspect class\n",
    "    prediction = dtree.predict(review_tokenized)\n",
    "    # convert the prediction to aspect class\n",
    "    prediction_text = label_encoder.inverse_transform(prediction.argmax(axis=1))\n",
    "    return prediction_text"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['unemployment'], dtype=object)"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# predict aspect class for a given review\n",
    "predict_aspect(\"There will be less jobs in the future.\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "#encode polarity classes\n",
    "label_encoder = LabelEncoder()\n",
    "integer_category = label_encoder.fit_transform(reviews_train.polarity)\n",
    "encoded_polarity = to_categorical(integer_category)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "# build a decision tree classifier for polarity classification\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.metrics import accuracy_score\n",
    "from sklearn.metrics import confusion_matrix\n",
    "from sklearn.metrics import classification_report\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "#split dataset into training and testing sets\n",
    "X_train, X_test, y_train, y_test = train_test_split(reviews_tokenized, encoded_polarity, test_size=0.2, random_state=42)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-2 {color: black;background-color: white;}#sk-container-id-2 pre{padding: 0;}#sk-container-id-2 div.sk-toggleable {background-color: white;}#sk-container-id-2 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-2 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-2 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-2 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-2 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-2 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-2 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-2 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-2 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-2 div.sk-item {position: relative;z-index: 1;}#sk-container-id-2 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-2 div.sk-item::before, #sk-container-id-2 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-2 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-2 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-2 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-2 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-2 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-2 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-2 div.sk-label-container {text-align: center;}#sk-container-id-2 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-2 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>DecisionTreeClassifier()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" checked><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">DecisionTreeClassifier</label><div class=\"sk-toggleable__content\"><pre>DecisionTreeClassifier()</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "DecisionTreeClassifier()"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# build a decision tree classifier\n",
    "dtree = DecisionTreeClassifier()\n",
    "dtree.fit(X_train, y_train)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[2742   61  215]\n",
      " [  45 4965   54]\n",
      " [ 165   49 6956]]\n"
     ]
    }
   ],
   "source": [
    "#predict the labels on validation dataset\n",
    "predictions = dtree.predict(X_test)\n",
    "# Report the confusion matrix for multi-class classification\n",
    "print(confusion_matrix(y_test.argmax(axis=1), predictions.argmax(axis=1)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.9613821138211383\n"
     ]
    }
   ],
   "source": [
    "#print model accuracy\n",
    "print(\"Accuracy:\",accuracy_score(y_test, predictions))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0., 1., 0.],\n",
       "       [0., 0., 1.],\n",
       "       [1., 0., 0.],\n",
       "       ...,\n",
       "       [0., 0., 1.],\n",
       "       [0., 1., 0.],\n",
       "       [0., 0., 1.]], dtype=float32)"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# print classification results\n",
    "predictions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['neutral', 'positive', 'negative', ..., 'positive', 'neutral',\n",
       "       'positive'], dtype=object)"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# convert predictions to polarity classes\n",
    "predictions_text = label_encoder.inverse_transform(predictions.argmax(axis=1))\n",
    "predictions_text\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [],
   "source": [
    "# function to predict polarity class for a given review\n",
    "def predict_polarity(review):\n",
    "    # remove punctuation\n",
    "    review = review.translate(str.maketrans('', '', string.punctuation))\n",
    "    # remove numbers\n",
    "    review = re.sub(r'\\d+', '', review)\n",
    "    # remove stopwords\n",
    "    review = ' '.join([word for word in review.split() if word not in (stopwords.words('english'))])\n",
    "    # stemming\n",
    "    stemmer = SnowballStemmer(\"english\")\n",
    "    review = ' '.join([stemmer.stem(word) for word in review.split()])\n",
    "    # lowercase\n",
    "    review = review.lower()\n",
    "    # tokenize the review\n",
    "    review_tokenized = tokenizer.texts_to_matrix([review])\n",
    "    # predict the polarity class\n",
    "    prediction = dtree.predict(review_tokenized)\n",
    "    # convert the prediction to polarity class\n",
    "    prediction_text = label_encoder.inverse_transform(prediction.argmax(axis=1))\n",
    "    return prediction_text\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['neutral'], dtype=object)"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# predict polarity class for a given review\n",
    "predict_polarity(\"There will be less jobs in the future.\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['positive'], dtype=object)"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "predict_polarity(\"interesting concept grab quick bite\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [],
   "source": [
    "#K-fold cross validation\n",
    "#from sklearn.model_selection import KFold\n",
    "#from sklearn.model_selection import cross_val_score\n",
    "#from sklearn.model_selection import cross_val_predict\n",
    "#from sklearn.metrics import confusion_matrix\n",
    "#from sklearn.metrics import classification_report\n",
    "#from sklearn.metrics import accuracy_score\n",
    "\n",
    "# define 10-fold cross validation test harness\n",
    "#kfold = KFold(n_splits=10, shuffle=True, random_state=42)\n",
    "#cv_results = cross_val_score(dtree, reviews_tokenized, encoded_polarity, cv=kfold, scoring='accuracy')\n",
    "#print(cv_results.mean())\n",
    "\n",
    "# predict the labels on validation dataset\n",
    "#predictions = cross_val_predict(dtree, reviews_tokenized, encoded_polarity, cv=kfold)\n",
    "\n",
    "# Report the confusion matrix for multi-class classification\n",
    "#print(confusion_matrix(encoded_polarity.argmax(axis=1), predictions.argmax(axis=1)))\n",
    "\n",
    "#print model accuracy\n",
    "#print(\"Accuracy:\",accuracy_score(encoded_polarity, predictions))\n",
    "\n",
    "\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.9.13 (tags/v3.9.13:6de2ca5, May 17 2022, 16:36:42) [MSC v.1929 64 bit (AMD64)]"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "14958d3aee5f1cad06795f787e54b96185c25fb40dfec723a5be941f3a531b8c"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}