{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "c3d7cc88",
   "metadata": {},
   "source": [
    "# Resume Analyzer"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9459843e",
   "metadata": {},
   "source": [
    "### Install Dependencies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "9a1fa2ec",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Defaulting to user installation because normal site-packages is not writeable\n",
      "Requirement already satisfied: scikit-learn in c:\\program files\\python311\\lib\\site-packages (1.5.0)\n",
      "Requirement already satisfied: numpy>=1.19.5 in c:\\program files\\python311\\lib\\site-packages (from scikit-learn) (1.26.4)\n",
      "Requirement already satisfied: scipy>=1.6.0 in c:\\program files\\python311\\lib\\site-packages (from scikit-learn) (1.11.3)\n",
      "Requirement already satisfied: joblib>=1.2.0 in c:\\program files\\python311\\lib\\site-packages (from scikit-learn) (1.3.2)\n",
      "Requirement already satisfied: threadpoolctl>=3.1.0 in c:\\program files\\python311\\lib\\site-packages (from scikit-learn) (3.5.0)\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "[notice] A new release of pip is available: 25.0.1 -> 25.1.1\n",
      "[notice] To update, run: python.exe -m pip install --upgrade pip\n"
     ]
    }
   ],
   "source": [
    "# Scikit-learn (for ML models)\n",
    "!pip install scikit-learn"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "f759f287",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Defaulting to user installation because normal site-packages is not writeable\n",
      "Requirement already satisfied: spacy in c:\\program files\\python311\\lib\\site-packages (3.7.2)\n",
      "Requirement already satisfied: spacy-legacy<3.1.0,>=3.0.11 in c:\\program files\\python311\\lib\\site-packages (from spacy) (3.0.12)\n",
      "Requirement already satisfied: spacy-loggers<2.0.0,>=1.0.0 in c:\\program files\\python311\\lib\\site-packages (from spacy) (1.0.5)\n",
      "Requirement already satisfied: murmurhash<1.1.0,>=0.28.0 in c:\\program files\\python311\\lib\\site-packages (from spacy) (1.0.10)\n",
      "Requirement already satisfied: cymem<2.1.0,>=2.0.2 in c:\\program files\\python311\\lib\\site-packages (from spacy) (2.0.8)\n",
      "Requirement already satisfied: preshed<3.1.0,>=3.0.2 in c:\\program files\\python311\\lib\\site-packages (from spacy) (3.0.9)\n",
      "Requirement already satisfied: thinc<8.3.0,>=8.1.8 in c:\\program files\\python311\\lib\\site-packages (from spacy) (8.2.1)\n",
      "Requirement already satisfied: wasabi<1.2.0,>=0.9.1 in c:\\program files\\python311\\lib\\site-packages (from spacy) (1.1.2)\n",
      "Requirement already satisfied: srsly<3.0.0,>=2.4.3 in c:\\program files\\python311\\lib\\site-packages (from spacy) (2.4.8)\n",
      "Requirement already satisfied: catalogue<2.1.0,>=2.0.6 in c:\\program files\\python311\\lib\\site-packages (from spacy) (2.0.10)\n",
      "Requirement already satisfied: weasel<0.4.0,>=0.1.0 in c:\\program files\\python311\\lib\\site-packages (from spacy) (0.3.3)\n",
      "Requirement already satisfied: typer<0.10.0,>=0.3.0 in c:\\program files\\python311\\lib\\site-packages (from spacy) (0.9.0)\n",
      "Requirement already satisfied: smart-open<7.0.0,>=5.2.1 in c:\\program files\\python311\\lib\\site-packages (from spacy) (6.4.0)\n",
      "Requirement already satisfied: tqdm<5.0.0,>=4.38.0 in c:\\program files\\python311\\lib\\site-packages (from spacy) (4.67.1)\n",
      "Requirement already satisfied: requests<3.0.0,>=2.13.0 in c:\\program files\\python311\\lib\\site-packages (from spacy) (2.32.3)\n",
      "Requirement already satisfied: pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4 in c:\\program files\\python311\\lib\\site-packages (from spacy) (2.4.2)\n",
      "Requirement already satisfied: jinja2 in c:\\program files\\python311\\lib\\site-packages (from spacy) (3.1.2)\n",
      "Requirement already satisfied: setuptools in c:\\program files\\python311\\lib\\site-packages (from spacy) (65.5.0)\n",
      "Requirement already satisfied: packaging>=20.0 in c:\\program files\\python311\\lib\\site-packages (from spacy) (24.0)\n",
      "Requirement already satisfied: langcodes<4.0.0,>=3.2.0 in c:\\program files\\python311\\lib\\site-packages (from spacy) (3.3.0)\n",
      "Requirement already satisfied: numpy>=1.19.0 in c:\\program files\\python311\\lib\\site-packages (from spacy) (1.26.4)\n",
      "Requirement already satisfied: annotated-types>=0.4.0 in c:\\program files\\python311\\lib\\site-packages (from pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4->spacy) (0.6.0)\n",
      "Requirement already satisfied: pydantic-core==2.10.1 in c:\\program files\\python311\\lib\\site-packages (from pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4->spacy) (2.10.1)\n",
      "Requirement already satisfied: typing-extensions>=4.6.1 in c:\\program files\\python311\\lib\\site-packages (from pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4->spacy) (4.12.1)\n",
      "Requirement already satisfied: charset-normalizer<4,>=2 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from requests<3.0.0,>=2.13.0->spacy) (3.2.0)\n",
      "Requirement already satisfied: idna<4,>=2.5 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from requests<3.0.0,>=2.13.0->spacy) (3.4)\n",
      "Requirement already satisfied: urllib3<3,>=1.21.1 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from requests<3.0.0,>=2.13.0->spacy) (1.26.16)\n",
      "Requirement already satisfied: certifi>=2017.4.17 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from requests<3.0.0,>=2.13.0->spacy) (2023.7.22)\n",
      "Requirement already satisfied: blis<0.8.0,>=0.7.8 in c:\\program files\\python311\\lib\\site-packages (from thinc<8.3.0,>=8.1.8->spacy) (0.7.11)\n",
      "Requirement already satisfied: confection<1.0.0,>=0.0.1 in c:\\program files\\python311\\lib\\site-packages (from thinc<8.3.0,>=8.1.8->spacy) (0.1.3)\n",
      "Requirement already satisfied: colorama in c:\\program files\\python311\\lib\\site-packages (from tqdm<5.0.0,>=4.38.0->spacy) (0.4.6)\n",
      "Requirement already satisfied: click<9.0.0,>=7.1.1 in c:\\program files\\python311\\lib\\site-packages (from typer<0.10.0,>=0.3.0->spacy) (8.1.7)\n",
      "Requirement already satisfied: cloudpathlib<0.17.0,>=0.7.0 in c:\\program files\\python311\\lib\\site-packages (from weasel<0.4.0,>=0.1.0->spacy) (0.16.0)\n",
      "Requirement already satisfied: MarkupSafe>=2.0 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from jinja2->spacy) (2.1.3)\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "[notice] A new release of pip is available: 25.0.1 -> 25.1.1\n",
      "[notice] To update, run: python.exe -m pip install --upgrade pip\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Defaulting to user installation because normal site-packages is not writeable\n",
      "Collecting en-core-web-sm==3.7.1\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\koppo\\AppData\\Roaming\\Python\\Python311\\site-packages\\torch\\utils\\_pytree.py:185: FutureWarning: optree is installed but the version is too old to support PyTorch Dynamo in C++ pytree. C++ pytree support is disabled. Please consider upgrading optree using `python3 -m pip install --upgrade 'optree>=0.13.0'`.\n",
      "  warnings.warn(\n",
      "  WARNING: Retrying (Retry(total=4, connect=None, read=None, redirect=None, status=None)) after connection broken by 'ProtocolError('Connection aborted.', ConnectionAbortedError(10053, 'An established connection was aborted by the software in your host machine', None, 10053, None))': /explosion/spacy-models/releases/download/en_core_web_sm-3.7.1/en_core_web_sm-3.7.1-py3-none-any.whl\n",
      "  WARNING: Retrying (Retry(total=3, connect=None, read=None, redirect=None, status=None)) after connection broken by 'NewConnectionError('<pip._vendor.urllib3.connection.HTTPSConnection object at 0x00000273147B7990>: Failed to establish a new connection: [WinError 10051] A socket operation was attempted to an unreachable network')': /explosion/spacy-models/releases/download/en_core_web_sm-3.7.1/en_core_web_sm-3.7.1-py3-none-any.whl\n",
      "  WARNING: Retrying (Retry(total=2, connect=None, read=None, redirect=None, status=None)) after connection broken by 'NewConnectionError('<pip._vendor.urllib3.connection.HTTPSConnection object at 0x00000273147B7FD0>: Failed to establish a new connection: [WinError 10051] A socket operation was attempted to an unreachable network')': /explosion/spacy-models/releases/download/en_core_web_sm-3.7.1/en_core_web_sm-3.7.1-py3-none-any.whl\n",
      "  WARNING: Retrying (Retry(total=1, connect=None, read=None, redirect=None, status=None)) after connection broken by 'NewConnectionError('<pip._vendor.urllib3.connection.HTTPSConnection object at 0x00000273147C5010>: Failed to establish a new connection: [Errno 11001] getaddrinfo failed')': /explosion/spacy-models/releases/download/en_core_web_sm-3.7.1/en_core_web_sm-3.7.1-py3-none-any.whl\n",
      "  WARNING: Retrying (Retry(total=0, connect=None, read=None, redirect=None, status=None)) after connection broken by 'NewConnectionError('<pip._vendor.urllib3.connection.HTTPSConnection object at 0x00000273147C5B50>: Failed to establish a new connection: [Errno 11001] getaddrinfo failed')': /explosion/spacy-models/releases/download/en_core_web_sm-3.7.1/en_core_web_sm-3.7.1-py3-none-any.whl\n",
      "ERROR: Could not install packages due to an OSError: HTTPSConnectionPool(host='github.com', port=443): Max retries exceeded with url: /explosion/spacy-models/releases/download/en_core_web_sm-3.7.1/en_core_web_sm-3.7.1-py3-none-any.whl (Caused by NewConnectionError('<pip._vendor.urllib3.connection.HTTPSConnection object at 0x00000273147C6590>: Failed to establish a new connection: [Errno 11001] getaddrinfo failed'))\n",
      "\n",
      "\n",
      "[notice] A new release of pip is available: 25.0.1 -> 25.1.1\n",
      "[notice] To update, run: python.exe -m pip install --upgrade pip\n"
     ]
    }
   ],
   "source": [
    "# SpaCy (for NLP)\n",
    "!pip install spacy\n",
    "!python -m spacy download en_core_web_sm\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "e8b9c94d",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "[notice] A new release of pip is available: 25.0.1 -> 25.1.1\n",
      "[notice] To update, run: python.exe -m pip install --upgrade pip\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Defaulting to user installation because normal site-packages is not writeable\n",
      "Requirement already satisfied: nltk in c:\\program files\\python311\\lib\\site-packages (3.8.1)\n",
      "Requirement already satisfied: click in c:\\program files\\python311\\lib\\site-packages (from nltk) (8.1.7)\n",
      "Requirement already satisfied: joblib in c:\\program files\\python311\\lib\\site-packages (from nltk) (1.3.2)\n",
      "Requirement already satisfied: regex>=2021.8.3 in c:\\program files\\python311\\lib\\site-packages (from nltk) (2023.10.3)\n",
      "Requirement already satisfied: tqdm in c:\\program files\\python311\\lib\\site-packages (from nltk) (4.67.1)\n",
      "Requirement already satisfied: colorama in c:\\program files\\python311\\lib\\site-packages (from click->nltk) (0.4.6)\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[nltk_data] Error loading punkt: <urlopen error [Errno 11001]\n",
      "[nltk_data]     getaddrinfo failed>\n",
      "[nltk_data] Error loading stopwords: <urlopen error [Errno 11001]\n",
      "[nltk_data]     getaddrinfo failed>\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "False"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# NLTK (for NLP preprocessing)\n",
    "!pip install nltk\n",
    "import nltk\n",
    "nltk.download('punkt')\n",
    "nltk.download('stopwords')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "a6a1a611",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Defaulting to user installation because normal site-packages is not writeable\n",
      "Requirement already satisfied: pdfminer.six in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (20250506)\n",
      "Requirement already satisfied: charset-normalizer>=2.0.0 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from pdfminer.six) (3.2.0)\n",
      "Requirement already satisfied: cryptography>=36.0.0 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from pdfminer.six) (44.0.2)\n",
      "Requirement already satisfied: cffi>=1.12 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from cryptography>=36.0.0->pdfminer.six) (1.15.1)\n",
      "Requirement already satisfied: pycparser in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from cffi>=1.12->cryptography>=36.0.0->pdfminer.six) (2.21)\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "[notice] A new release of pip is available: 25.0.1 -> 25.1.1\n",
      "[notice] To update, run: python.exe -m pip install --upgrade pip\n"
     ]
    }
   ],
   "source": [
    "# PDFMiner (to extract text from PDF resumes)\n",
    "!pip install pdfminer.six"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "04d566f0",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Defaulting to user installation because normal site-packages is not writeable\n",
      "Requirement already satisfied: xgboost in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (3.0.0)\n",
      "Requirement already satisfied: numpy in c:\\program files\\python311\\lib\\site-packages (from xgboost) (1.26.4)\n",
      "Requirement already satisfied: scipy in c:\\program files\\python311\\lib\\site-packages (from xgboost) (1.11.3)\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "[notice] A new release of pip is available: 25.0.1 -> 25.1.1\n",
      "[notice] To update, run: python.exe -m pip install --upgrade pip\n"
     ]
    }
   ],
   "source": [
    "# XGBoost (for boosted tree models)\n",
    "!pip install xgboost"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "b152893d",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Defaulting to user installation because normal site-packages is not writeable\n",
      "Requirement already satisfied: matplotlib in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (3.7.2)\n",
      "Requirement already satisfied: contourpy>=1.0.1 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from matplotlib) (1.1.0)\n",
      "Requirement already satisfied: cycler>=0.10 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from matplotlib) (0.11.0)\n",
      "Requirement already satisfied: fonttools>=4.22.0 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from matplotlib) (4.42.1)\n",
      "Requirement already satisfied: kiwisolver>=1.0.1 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from matplotlib) (1.4.5)\n",
      "Requirement already satisfied: numpy>=1.20 in c:\\program files\\python311\\lib\\site-packages (from matplotlib) (1.26.4)\n",
      "Requirement already satisfied: packaging>=20.0 in c:\\program files\\python311\\lib\\site-packages (from matplotlib) (24.0)\n",
      "Requirement already satisfied: pillow>=6.2.0 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from matplotlib) (10.0.0)\n",
      "Requirement already satisfied: pyparsing<3.1,>=2.3.1 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from matplotlib) (3.0.9)\n",
      "Requirement already satisfied: python-dateutil>=2.7 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from matplotlib) (2.8.2)\n",
      "Requirement already satisfied: six>=1.5 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from python-dateutil>=2.7->matplotlib) (1.16.0)\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "[notice] A new release of pip is available: 25.0.1 -> 25.1.1\n",
      "[notice] To update, run: python.exe -m pip install --upgrade pip\n"
     ]
    }
   ],
   "source": [
    "# Matplotlib (for plotting)\n",
    "!pip install matplotlib"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "2d21e571",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Defaulting to user installation because normal site-packages is not writeable\n",
      "Requirement already satisfied: seaborn in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (0.13.2)\n",
      "Requirement already satisfied: numpy!=1.24.0,>=1.20 in c:\\program files\\python311\\lib\\site-packages (from seaborn) (1.26.4)\n",
      "Requirement already satisfied: pandas>=1.2 in c:\\program files\\python311\\lib\\site-packages (from seaborn) (2.2.2)\n",
      "Requirement already satisfied: matplotlib!=3.6.1,>=3.4 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from seaborn) (3.7.2)\n",
      "Requirement already satisfied: contourpy>=1.0.1 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from matplotlib!=3.6.1,>=3.4->seaborn) (1.1.0)\n",
      "Requirement already satisfied: cycler>=0.10 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from matplotlib!=3.6.1,>=3.4->seaborn) (0.11.0)\n",
      "Requirement already satisfied: fonttools>=4.22.0 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from matplotlib!=3.6.1,>=3.4->seaborn) (4.42.1)\n",
      "Requirement already satisfied: kiwisolver>=1.0.1 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from matplotlib!=3.6.1,>=3.4->seaborn) (1.4.5)\n",
      "Requirement already satisfied: packaging>=20.0 in c:\\program files\\python311\\lib\\site-packages (from matplotlib!=3.6.1,>=3.4->seaborn) (24.0)\n",
      "Requirement already satisfied: pillow>=6.2.0 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from matplotlib!=3.6.1,>=3.4->seaborn) (10.0.0)\n",
      "Requirement already satisfied: pyparsing<3.1,>=2.3.1 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from matplotlib!=3.6.1,>=3.4->seaborn) (3.0.9)\n",
      "Requirement already satisfied: python-dateutil>=2.7 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from matplotlib!=3.6.1,>=3.4->seaborn) (2.8.2)\n",
      "Requirement already satisfied: pytz>=2020.1 in c:\\program files\\python311\\lib\\site-packages (from pandas>=1.2->seaborn) (2024.1)\n",
      "Requirement already satisfied: tzdata>=2022.7 in c:\\program files\\python311\\lib\\site-packages (from pandas>=1.2->seaborn) (2024.1)\n",
      "Requirement already satisfied: six>=1.5 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from python-dateutil>=2.7->matplotlib!=3.6.1,>=3.4->seaborn) (1.16.0)\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "[notice] A new release of pip is available: 25.0.1 -> 25.1.1\n",
      "[notice] To update, run: python.exe -m pip install --upgrade pip\n"
     ]
    }
   ],
   "source": [
    "# Seaborn (for visual analytics)\n",
    "!pip install seaborn"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "98ca75e6",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "[notice] A new release of pip is available: 25.0.1 -> 25.1.1\n",
      "[notice] To update, run: python.exe -m pip install --upgrade pip\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Defaulting to user installation because normal site-packages is not writeable\n",
      "Requirement already satisfied: python-docx in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (1.1.2)\n",
      "Requirement already satisfied: lxml>=3.1.0 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from python-docx) (5.4.0)\n",
      "Requirement already satisfied: typing-extensions>=4.9.0 in c:\\program files\\python311\\lib\\site-packages (from python-docx) (4.12.1)\n"
     ]
    }
   ],
   "source": [
    "!pip install python-docx"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "17364abc",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Defaulting to user installation because normal site-packages is not writeable\n",
      "Requirement already satisfied: pdfminer.six in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (20250506)\n",
      "Requirement already satisfied: charset-normalizer>=2.0.0 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from pdfminer.six) (3.2.0)\n",
      "Requirement already satisfied: cryptography>=36.0.0 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from pdfminer.six) (44.0.2)\n",
      "Requirement already satisfied: cffi>=1.12 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from cryptography>=36.0.0->pdfminer.six) (1.15.1)\n",
      "Requirement already satisfied: pycparser in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from cffi>=1.12->cryptography>=36.0.0->pdfminer.six) (2.21)\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "[notice] A new release of pip is available: 25.0.1 -> 25.1.1\n",
      "[notice] To update, run: python.exe -m pip install --upgrade pip\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Defaulting to user installation because normal site-packages is not writeable\n",
      "Requirement already satisfied: python-docx in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (1.1.2)\n",
      "Requirement already satisfied: lxml>=3.1.0 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from python-docx) (5.4.0)\n",
      "Requirement already satisfied: typing-extensions>=4.9.0 in c:\\program files\\python311\\lib\\site-packages (from python-docx) (4.12.1)\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "[notice] A new release of pip is available: 25.0.1 -> 25.1.1\n",
      "[notice] To update, run: python.exe -m pip install --upgrade pip\n"
     ]
    }
   ],
   "source": [
    "!pip install pdfminer.six\n",
    "!pip install python-docx"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "351c1057",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Defaulting to user installation because normal site-packages is not writeable\n",
      "Requirement already satisfied: ipywidgets in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (8.1.5)\n",
      "Requirement already satisfied: comm>=0.1.3 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from ipywidgets) (0.2.0)\n",
      "Requirement already satisfied: ipython>=6.1.0 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from ipywidgets) (8.17.2)\n",
      "Requirement already satisfied: traitlets>=4.3.1 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from ipywidgets) (5.13.0)\n",
      "Requirement already satisfied: widgetsnbextension~=4.0.12 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from ipywidgets) (4.0.13)\n",
      "Requirement already satisfied: jupyterlab-widgets~=3.0.12 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from ipywidgets) (3.0.13)\n",
      "Requirement already satisfied: decorator in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from ipython>=6.1.0->ipywidgets) (5.1.1)\n",
      "Requirement already satisfied: jedi>=0.16 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from ipython>=6.1.0->ipywidgets) (0.19.1)\n",
      "Requirement already satisfied: matplotlib-inline in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from ipython>=6.1.0->ipywidgets) (0.1.6)\n",
      "Requirement already satisfied: prompt-toolkit!=3.0.37,<3.1.0,>=3.0.30 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from ipython>=6.1.0->ipywidgets) (3.0.39)\n",
      "Requirement already satisfied: pygments>=2.4.0 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from ipython>=6.1.0->ipywidgets) (2.16.1)\n",
      "Requirement already satisfied: stack-data in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from ipython>=6.1.0->ipywidgets) (0.6.3)\n",
      "Requirement already satisfied: colorama in c:\\program files\\python311\\lib\\site-packages (from ipython>=6.1.0->ipywidgets) (0.4.6)\n",
      "Requirement already satisfied: parso<0.9.0,>=0.8.3 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from jedi>=0.16->ipython>=6.1.0->ipywidgets) (0.8.3)\n",
      "Requirement already satisfied: wcwidth in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from prompt-toolkit!=3.0.37,<3.1.0,>=3.0.30->ipython>=6.1.0->ipywidgets) (0.2.9)\n",
      "Requirement already satisfied: executing>=1.2.0 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from stack-data->ipython>=6.1.0->ipywidgets) (2.0.1)\n",
      "Requirement already satisfied: asttokens>=2.1.0 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from stack-data->ipython>=6.1.0->ipywidgets) (2.4.1)\n",
      "Requirement already satisfied: pure-eval in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from stack-data->ipython>=6.1.0->ipywidgets) (0.2.2)\n",
      "Requirement already satisfied: six>=1.12.0 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from asttokens>=2.1.0->stack-data->ipython>=6.1.0->ipywidgets) (1.16.0)\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "[notice] A new release of pip is available: 25.0.1 -> 25.1.1\n",
      "[notice] To update, run: python.exe -m pip install --upgrade pip\n"
     ]
    }
   ],
   "source": [
    "!pip install ipywidgets"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "9b970a94",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "usage: jupyter [-h] [--version] [--config-dir] [--data-dir] [--runtime-dir]\n",
      "               [--paths] [--json] [--debug]\n",
      "               [subcommand]\n",
      "\n",
      "Jupyter: Interactive Computing\n",
      "\n",
      "positional arguments:\n",
      "  subcommand     the subcommand to launch\n",
      "\n",
      "options:\n",
      "  -h, --help     show this help message and exit\n",
      "  --version      show the versions of core jupyter packages and exit\n",
      "  --config-dir   show Jupyter config dir\n",
      "  --data-dir     show Jupyter data dir\n",
      "  --runtime-dir  show Jupyter runtime dir\n",
      "  --paths        show all Jupyter paths. Add --json for machine-readable\n",
      "                 format.\n",
      "  --json         output paths as machine-readable json\n",
      "  --debug        output debug information about paths\n",
      "\n",
      "Available subcommands: dejavu events execute kernel kernelspec lab\n",
      "labextension labhub migrate nbconvert notebook run server troubleshoot trust\n",
      "\n",
      "Jupyter command `jupyter-nbextension` not found.\n"
     ]
    }
   ],
   "source": [
    "!jupyter nbextension enable --py widgetsnbextension"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "ebdb2ee4",
   "metadata": {},
   "outputs": [],
   "source": [
    "from IPython.display import display, HTML\n",
    "import html"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ce436add",
   "metadata": {},
   "source": [
    "###  Create Resume Upload & Text Extraction Section"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "c501080f",
   "metadata": {},
   "outputs": [],
   "source": [
    "# import os\n",
    "# from tkinter import Tk\n",
    "# from tkinter.filedialog import askopenfilename\n",
    "# from pdfminer.high_level import extract_text\n",
    "# from docx import Document\n",
    "\n",
    "# def extract_text_from_pdf(file_path):\n",
    "#     return extract_text(file_path)\n",
    "\n",
    "# def extract_text_from_docx(file_path):\n",
    "#     doc = Document(file_path)\n",
    "#     return '\\n'.join([p.text for p in doc.paragraphs])\n",
    "\n",
    "# def extract_resume_text_with_dialog():\n",
    "#     Tk().withdraw()  # Hide the root window\n",
    "#     file_path = askopenfilename(title=\"Select a Resume File (.pdf or .docx)\",\n",
    "#                                 filetypes=[(\"PDF files\", \"*.pdf\"), (\"Word files\", \"*.docx\")])\n",
    "\n",
    "#     if not file_path:\n",
    "#         print(\"❌ No file selected.\")\n",
    "#         return None\n",
    "\n",
    "#     if file_path.endswith(\".pdf\"):\n",
    "#         text = extract_text_from_pdf(file_path)\n",
    "#     elif file_path.endswith(\".docx\"):\n",
    "#         text = extract_text_from_docx(file_path)\n",
    "#     else:\n",
    "#         print(\"❌ Unsupported file format.\")\n",
    "#         return None\n",
    "\n",
    "#     print(\"\\n✅ Resume text preview:\\n\")\n",
    "#     print(text[:500])\n",
    "#     return text\n",
    "\n",
    "# # Run the picker\n",
    "# resume_text = extract_resume_text_with_dialog()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "d9926991",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "962fe321bc774c7caa5142e801b751a4",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HTML(value='<b>Upload your resume (.pdf or .docx):</b>')"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "84ff72f66eb5407385f5514cb4a4d380",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "FileUpload(value=(), accept='.pdf,.docx', description='Upload')"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import io\n",
    "import ipywidgets as widgets\n",
    "from IPython.display import display\n",
    "from pdfminer.high_level import extract_text_to_fp\n",
    "from docx import Document\n",
    "\n",
    "# Upload widget\n",
    "uploader = widgets.FileUpload(\n",
    "    accept='.pdf,.docx',  # Only accept PDFs and DOCX\n",
    "    multiple=False\n",
    ")\n",
    "\n",
    "display(widgets.HTML(\"<b>Upload your resume (.pdf or .docx):</b>\"))\n",
    "display(uploader)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "12528f2e",
   "metadata": {},
   "outputs": [],
   "source": [
    "def extract_text_from_uploaded_file(uploader):\n",
    "    if not uploader.value:\n",
    "        print(\"⚠️ No file uploaded yet.\")\n",
    "        return None\n",
    "\n",
    "    # uploader.value is a tuple of dicts\n",
    "    file_info = uploader.value[0]\n",
    "    file_name = file_info['name']\n",
    "    content = io.BytesIO(file_info['content'])\n",
    "\n",
    "    if file_name.endswith('.pdf'):\n",
    "        output = io.StringIO()\n",
    "        extract_text_to_fp(content, output)\n",
    "        return output.getvalue()\n",
    "\n",
    "    elif file_name.endswith('.docx'):\n",
    "        doc = Document(content)\n",
    "        return '\\n'.join([p.text for p in doc.paragraphs])\n",
    "\n",
    "    else:\n",
    "        print(\"❌ Unsupported file type.\")\n",
    "        return None\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "6ef959f7",
   "metadata": {},
   "outputs": [],
   "source": [
    "def preview_resume_text(text, max_lines=30):\n",
    "    if not text:\n",
    "        print(\"❌ No text to display.\")\n",
    "        return\n",
    "    \n",
    "    # Clean and split text into lines\n",
    "    lines = [line.strip() for line in text.splitlines() if line.strip()]\n",
    "    \n",
    "    # Limit number of lines\n",
    "    lines = lines[:max_lines]\n",
    "    \n",
    "    # Escape HTML and number the lines\n",
    "    numbered = [f\"<b>{i+1:02d}</b>: {html.escape(line)}\" for i, line in enumerate(lines)]\n",
    "\n",
    "    # Format with <pre> for alignment\n",
    "    html_content = \"<pre style='font-size: 14px; line-height: 1.5em; background-color:#f9f9f9; padding: 10px; border-radius: 5px;'>\"\n",
    "    html_content += \"\\n\".join(numbered)\n",
    "    html_content += \"</pre>\"\n",
    "\n",
    "    display(HTML(html_content))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "ac518e33",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "✅ Extracted successfully. Preview below:\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<pre style='font-size: 14px; line-height: 1.5em; background-color:#f9f9f9; padding: 10px; border-radius: 5px;'><b>01</b>: SATHVIKKIRANKOPPOLU(+91)9063714302(cid:5)koppolusathvikkiran@gmail.comGuntur,AndhraPradesh(cid:5)LinkedIn—GitHubPROFESSIONALSUMMARYAspiringFull-StackDeveloperandAIEnthusiastwithhands-onexperienceinbuildingscalablewebappsandintelligentsystems.SkilledinJavaScript,Python,SQL,andcontainerizeddeploymentusingDockerandKubernetes.Passionateaboutproblem-solving,innovation,anddeliveringreal-worldimpactthroughsoftware.Experiencedinsupervisedandunsupervisedlearning,modeldeployment,andMLOpspracticesincludingversioningandexperimenttracking.EDUCATIONIndianInstituteOfInformationTechnology,KottayamAug2022-PresentB.TechinComputerScience(AI&amp;DataScience)—CGPA:6.9BhashyamJuniorCollege,Guntur2020-2022Intermediate—75%EXPERIENCESCIHUBSemiconductorSolutionsPvt.Ltd.Nov2024-Feb2025SoftwareDevelopmentEngineer(FullStack)-RemoteInternshipSoftwareDevelopmentInternshipCertificate•Revampedthecompanyswebsite,leadingtoa30%improvementinloadingtimeandUIresponsiveness.•EngineeredmodulesthatcutaverageAPIresponsetimefrom1.2sto950ms.•Reducedclient-sidebugreportsby40%throughrigorousdebuggingandtesting.•CollaboratedinAgilesprintstoimplementmodularfeatures,reducingreleasecyclesfrom2weeksto5days.PROJECTSFilm-Buddy-EJS,JavaScript,CSS•Launchedaresponsivewebplatformforfilmmakers,achieving100+uniquevisitorsinthefirstmonth.•DesignedanaccessibleUIwitha90+Lighthousescore;ensuredcross-devicecompatibility.•SecureduserdataandworkflowsusingMongoDB&amp;SQLwithJWT-basedauthenticationandRBAC.HandGestureControl-OpenCV,Python,Mediapipe,scikit-learn•Builtareal-timegesturerecognitiontool,enablinghands-freecontrolinGUIapps.•Achieved92%precisionusingMediapipeslandmarktrackingandscikit-learnclassifiers.•Integratedmodeldeploymentinbatchmodeforperiodicupdates.CIFAR-10Classification-TensorFlow,Python,Keras,MLOps,GoogleCloudPlatform•Achieved85%+accuracyusingCNN-basedimageclassificationonCIFAR-10dataset.•AppliedTransferLearning(ResNet50,VGG16),improvingbaselineperformanceby15%.•Usedexperimenttrackingandmodelversioningtoolstobenchmarkresults.•DeployedmodelendpointusingDockerandGoogleCloudcontainers.\n",
       "<b>02</b>: CourseEnrollmentApp-Java,SQL•DesignedaJava-basedstudentenrollmentsystemwithCRUDoperationsandauthentication.•IntegratedSQLforstructureddatastorageanddynamicrecordvisualization.•Implementeduserauthenticationandadminprivilegesforsecureandrole-basedaccess.•Handled200+studentrecordswithfiltering,search,andenrollmentstatusupdatefunctionality.TECHNICALSKILLSProgrammingLanguages:Python,Java,C++,JavaScript,SQLMachineLearning&amp;AI:Tensor-Flow,Keras,OpenCV,scikit-learn,DeepLearning(CNN,TransferLearning),SupervisedandUnsupervisedLearningFull-StackDevelopment:React.js,Node.js,Express.js,RESTAPIs,MongoDB,MySQLSoft-wareEngineering:Object-OrientedProgramming(OOP),Agile,SoftwareTesting,DebuggingSystemDesign&amp;DevOps:Microservices,APIDesign,Docker,Kubernetes,MLOps(experimenttracking,ver-sioning),CI/CD(Jenkins,GitHubActions)DeveloperTools:Git,VSCode,Postman,MiniforgeCloudPlatforms:GoogleCloudPlatformDataProcessing:DataCleaning,DataPreprocessing,SQLCERTIFICATIONS•DataVisualizationusingPython(GreatLearning)•AIWorkflow:MachineLearning,VisualRecognition,NLP(IBM,Coursera)•Front-EndDeveloperCourse(META,Coursera)•CrashCourseinPython(CodeChef)•MLOpsToolsandTechniquesInview•GoogleCloudMachineLearningSpecializationInviewPROFESSIONALTRAITSDetail-oriented,teamplayer,flexible,strongcommunicator,quicklearner.ThrivesincollaborativeAgileenvironmentsandpassionateaboutsolvingreal-worldproblemsthroughscalablesoftwaresolutions.LANGUAGESTelugu(Native),English(Professional),Hindi(Professional)</pre>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "resume_text = extract_text_from_uploaded_file(uploader)\n",
    "if resume_text:\n",
    "    print(\"✅ Extracted successfully. Preview below:\")\n",
    "    preview_resume_text(resume_text)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bd9df665",
   "metadata": {},
   "source": [
    "## Resume–Job Description Analyzer (With or Without JD Input)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "03942a66",
   "metadata": {},
   "source": [
    "### Step 1: Install Required Libraries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "04ef6903",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Defaulting to user installation because normal site-packages is not writeable\n",
      "Requirement already satisfied: datasets in c:\\program files\\python311\\lib\\site-packages (3.3.2)\n",
      "Requirement already satisfied: scikit-learn in c:\\program files\\python311\\lib\\site-packages (1.5.0)\n",
      "Requirement already satisfied: nltk in c:\\program files\\python311\\lib\\site-packages (3.8.1)\n",
      "Requirement already satisfied: spacy in c:\\program files\\python311\\lib\\site-packages (3.7.2)\n",
      "Requirement already satisfied: tqdm in c:\\program files\\python311\\lib\\site-packages (4.67.1)\n",
      "Requirement already satisfied: filelock in c:\\program files\\python311\\lib\\site-packages (from datasets) (3.13.1)\n",
      "Requirement already satisfied: numpy>=1.17 in c:\\program files\\python311\\lib\\site-packages (from datasets) (1.26.4)\n",
      "Requirement already satisfied: pyarrow>=15.0.0 in c:\\program files\\python311\\lib\\site-packages (from datasets) (19.0.1)\n",
      "Requirement already satisfied: dill<0.3.9,>=0.3.0 in c:\\program files\\python311\\lib\\site-packages (from datasets) (0.3.8)\n",
      "Requirement already satisfied: pandas in c:\\program files\\python311\\lib\\site-packages (from datasets) (2.2.2)\n",
      "Requirement already satisfied: requests>=2.32.2 in c:\\program files\\python311\\lib\\site-packages (from datasets) (2.32.3)\n",
      "Requirement already satisfied: xxhash in c:\\program files\\python311\\lib\\site-packages (from datasets) (3.5.0)\n",
      "Requirement already satisfied: multiprocess<0.70.17 in c:\\program files\\python311\\lib\\site-packages (from datasets) (0.70.16)\n",
      "Requirement already satisfied: fsspec<=2024.12.0,>=2023.1.0 in c:\\program files\\python311\\lib\\site-packages (from fsspec[http]<=2024.12.0,>=2023.1.0->datasets) (2024.2.0)\n",
      "Requirement already satisfied: aiohttp in c:\\program files\\python311\\lib\\site-packages (from datasets) (3.11.13)\n",
      "Requirement already satisfied: huggingface-hub>=0.24.0 in c:\\program files\\python311\\lib\\site-packages (from datasets) (0.29.3)\n",
      "Requirement already satisfied: packaging in c:\\program files\\python311\\lib\\site-packages (from datasets) (24.0)\n",
      "Requirement already satisfied: pyyaml>=5.1 in c:\\program files\\python311\\lib\\site-packages (from datasets) (6.0.1)\n",
      "Requirement already satisfied: scipy>=1.6.0 in c:\\program files\\python311\\lib\\site-packages (from scikit-learn) (1.11.3)\n",
      "Requirement already satisfied: joblib>=1.2.0 in c:\\program files\\python311\\lib\\site-packages (from scikit-learn) (1.3.2)\n",
      "Requirement already satisfied: threadpoolctl>=3.1.0 in c:\\program files\\python311\\lib\\site-packages (from scikit-learn) (3.5.0)\n",
      "Requirement already satisfied: click in c:\\program files\\python311\\lib\\site-packages (from nltk) (8.1.7)\n",
      "Requirement already satisfied: regex>=2021.8.3 in c:\\program files\\python311\\lib\\site-packages (from nltk) (2023.10.3)\n",
      "Requirement already satisfied: spacy-legacy<3.1.0,>=3.0.11 in c:\\program files\\python311\\lib\\site-packages (from spacy) (3.0.12)\n",
      "Requirement already satisfied: spacy-loggers<2.0.0,>=1.0.0 in c:\\program files\\python311\\lib\\site-packages (from spacy) (1.0.5)\n",
      "Requirement already satisfied: murmurhash<1.1.0,>=0.28.0 in c:\\program files\\python311\\lib\\site-packages (from spacy) (1.0.10)\n",
      "Requirement already satisfied: cymem<2.1.0,>=2.0.2 in c:\\program files\\python311\\lib\\site-packages (from spacy) (2.0.8)\n",
      "Requirement already satisfied: preshed<3.1.0,>=3.0.2 in c:\\program files\\python311\\lib\\site-packages (from spacy) (3.0.9)\n",
      "Requirement already satisfied: thinc<8.3.0,>=8.1.8 in c:\\program files\\python311\\lib\\site-packages (from spacy) (8.2.1)\n",
      "Requirement already satisfied: wasabi<1.2.0,>=0.9.1 in c:\\program files\\python311\\lib\\site-packages (from spacy) (1.1.2)\n",
      "Requirement already satisfied: srsly<3.0.0,>=2.4.3 in c:\\program files\\python311\\lib\\site-packages (from spacy) (2.4.8)\n",
      "Requirement already satisfied: catalogue<2.1.0,>=2.0.6 in c:\\program files\\python311\\lib\\site-packages (from spacy) (2.0.10)\n",
      "Requirement already satisfied: weasel<0.4.0,>=0.1.0 in c:\\program files\\python311\\lib\\site-packages (from spacy) (0.3.3)\n",
      "Requirement already satisfied: typer<0.10.0,>=0.3.0 in c:\\program files\\python311\\lib\\site-packages (from spacy) (0.9.0)\n",
      "Requirement already satisfied: smart-open<7.0.0,>=5.2.1 in c:\\program files\\python311\\lib\\site-packages (from spacy) (6.4.0)\n",
      "Requirement already satisfied: pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4 in c:\\program files\\python311\\lib\\site-packages (from spacy) (2.4.2)\n",
      "Requirement already satisfied: jinja2 in c:\\program files\\python311\\lib\\site-packages (from spacy) (3.1.2)\n",
      "Requirement already satisfied: setuptools in c:\\program files\\python311\\lib\\site-packages (from spacy) (65.5.0)\n",
      "Requirement already satisfied: langcodes<4.0.0,>=3.2.0 in c:\\program files\\python311\\lib\\site-packages (from spacy) (3.3.0)\n",
      "Requirement already satisfied: colorama in c:\\program files\\python311\\lib\\site-packages (from tqdm) (0.4.6)\n",
      "Requirement already satisfied: aiohappyeyeballs>=2.3.0 in c:\\program files\\python311\\lib\\site-packages (from aiohttp->datasets) (2.5.0)\n",
      "Requirement already satisfied: aiosignal>=1.1.2 in c:\\program files\\python311\\lib\\site-packages (from aiohttp->datasets) (1.3.2)\n",
      "Requirement already satisfied: attrs>=17.3.0 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from aiohttp->datasets) (23.1.0)\n",
      "Requirement already satisfied: frozenlist>=1.1.1 in c:\\program files\\python311\\lib\\site-packages (from aiohttp->datasets) (1.5.0)\n",
      "Requirement already satisfied: multidict<7.0,>=4.5 in c:\\program files\\python311\\lib\\site-packages (from aiohttp->datasets) (6.1.0)\n",
      "Requirement already satisfied: propcache>=0.2.0 in c:\\program files\\python311\\lib\\site-packages (from aiohttp->datasets) (0.3.0)\n",
      "Requirement already satisfied: yarl<2.0,>=1.17.0 in c:\\program files\\python311\\lib\\site-packages (from aiohttp->datasets) (1.18.3)\n",
      "Requirement already satisfied: typing-extensions>=3.7.4.3 in c:\\program files\\python311\\lib\\site-packages (from huggingface-hub>=0.24.0->datasets) (4.12.1)\n",
      "Requirement already satisfied: annotated-types>=0.4.0 in c:\\program files\\python311\\lib\\site-packages (from pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4->spacy) (0.6.0)\n",
      "Requirement already satisfied: pydantic-core==2.10.1 in c:\\program files\\python311\\lib\\site-packages (from pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4->spacy) (2.10.1)\n",
      "Requirement already satisfied: charset-normalizer<4,>=2 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from requests>=2.32.2->datasets) (3.2.0)\n",
      "Requirement already satisfied: idna<4,>=2.5 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from requests>=2.32.2->datasets) (3.4)\n",
      "Requirement already satisfied: urllib3<3,>=1.21.1 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from requests>=2.32.2->datasets) (1.26.16)\n",
      "Requirement already satisfied: certifi>=2017.4.17 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from requests>=2.32.2->datasets) (2023.7.22)\n",
      "Requirement already satisfied: blis<0.8.0,>=0.7.8 in c:\\program files\\python311\\lib\\site-packages (from thinc<8.3.0,>=8.1.8->spacy) (0.7.11)\n",
      "Requirement already satisfied: confection<1.0.0,>=0.0.1 in c:\\program files\\python311\\lib\\site-packages (from thinc<8.3.0,>=8.1.8->spacy) (0.1.3)\n",
      "Requirement already satisfied: cloudpathlib<0.17.0,>=0.7.0 in c:\\program files\\python311\\lib\\site-packages (from weasel<0.4.0,>=0.1.0->spacy) (0.16.0)\n",
      "Requirement already satisfied: MarkupSafe>=2.0 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from jinja2->spacy) (2.1.3)\n",
      "Requirement already satisfied: python-dateutil>=2.8.2 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from pandas->datasets) (2.8.2)\n",
      "Requirement already satisfied: pytz>=2020.1 in c:\\program files\\python311\\lib\\site-packages (from pandas->datasets) (2024.1)\n",
      "Requirement already satisfied: tzdata>=2022.7 in c:\\program files\\python311\\lib\\site-packages (from pandas->datasets) (2024.1)\n",
      "Requirement already satisfied: six>=1.5 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from python-dateutil>=2.8.2->pandas->datasets) (1.16.0)\n",
      "Note: you may need to restart the kernel to use updated packages.\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "[notice] A new release of pip is available: 25.0.1 -> 25.1.1\n",
      "[notice] To update, run: python.exe -m pip install --upgrade pip\n",
      "<frozen runpy>:128: RuntimeWarning: 'nltk.downloader' found in sys.modules after import of package 'nltk', but prior to execution of 'nltk.downloader'; this may result in unpredictable behaviour\n",
      "[nltk_data] Downloading package stopwords to\n",
      "[nltk_data]     C:\\Users\\koppo\\AppData\\Roaming\\nltk_data...\n",
      "[nltk_data]   Package stopwords is already up-to-date!\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Defaulting to user installation because normal site-packages is not writeable\n",
      "Collecting en-core-web-sm==3.7.1\n",
      "  Downloading https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.7.1/en_core_web_sm-3.7.1-py3-none-any.whl (12.8 MB)\n",
      "     ---------------------------------------- 0.0/12.8 MB ? eta -:--:--\n",
      "     ----- ---------------------------------- 1.8/12.8 MB 10.1 MB/s eta 0:00:02\n",
      "     --------- ------------------------------ 3.1/12.8 MB 8.8 MB/s eta 0:00:02\n",
      "     ------------ --------------------------- 3.9/12.8 MB 7.8 MB/s eta 0:00:02\n",
      "     ------------ --------------------------- 3.9/12.8 MB 7.8 MB/s eta 0:00:02\n",
      "     ------------ --------------------------- 3.9/12.8 MB 7.8 MB/s eta 0:00:02\n",
      "     --------------- ------------------------ 5.0/12.8 MB 3.9 MB/s eta 0:00:02\n",
      "     ---------------------- ----------------- 7.1/12.8 MB 4.8 MB/s eta 0:00:02\n",
      "     --------------------------- ------------ 8.7/12.8 MB 5.1 MB/s eta 0:00:01\n",
      "     -------------------------------- ------- 10.5/12.8 MB 5.6 MB/s eta 0:00:01\n",
      "     ------------------------------------ --- 11.5/12.8 MB 5.5 MB/s eta 0:00:01\n",
      "     ---------------------------------------- 12.8/12.8 MB 5.7 MB/s eta 0:00:00\n",
      "Requirement already satisfied: spacy<3.8.0,>=3.7.2 in c:\\program files\\python311\\lib\\site-packages (from en-core-web-sm==3.7.1) (3.7.2)\n",
      "Requirement already satisfied: spacy-legacy<3.1.0,>=3.0.11 in c:\\program files\\python311\\lib\\site-packages (from spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (3.0.12)\n",
      "Requirement already satisfied: spacy-loggers<2.0.0,>=1.0.0 in c:\\program files\\python311\\lib\\site-packages (from spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (1.0.5)\n",
      "Requirement already satisfied: murmurhash<1.1.0,>=0.28.0 in c:\\program files\\python311\\lib\\site-packages (from spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (1.0.10)\n",
      "Requirement already satisfied: cymem<2.1.0,>=2.0.2 in c:\\program files\\python311\\lib\\site-packages (from spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (2.0.8)\n",
      "Requirement already satisfied: preshed<3.1.0,>=3.0.2 in c:\\program files\\python311\\lib\\site-packages (from spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (3.0.9)\n",
      "Requirement already satisfied: thinc<8.3.0,>=8.1.8 in c:\\program files\\python311\\lib\\site-packages (from spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (8.2.1)\n",
      "Requirement already satisfied: wasabi<1.2.0,>=0.9.1 in c:\\program files\\python311\\lib\\site-packages (from spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (1.1.2)\n",
      "Requirement already satisfied: srsly<3.0.0,>=2.4.3 in c:\\program files\\python311\\lib\\site-packages (from spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (2.4.8)\n",
      "Requirement already satisfied: catalogue<2.1.0,>=2.0.6 in c:\\program files\\python311\\lib\\site-packages (from spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (2.0.10)\n",
      "Requirement already satisfied: weasel<0.4.0,>=0.1.0 in c:\\program files\\python311\\lib\\site-packages (from spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (0.3.3)\n",
      "Requirement already satisfied: typer<0.10.0,>=0.3.0 in c:\\program files\\python311\\lib\\site-packages (from spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (0.9.0)\n",
      "Requirement already satisfied: smart-open<7.0.0,>=5.2.1 in c:\\program files\\python311\\lib\\site-packages (from spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (6.4.0)\n",
      "Requirement already satisfied: tqdm<5.0.0,>=4.38.0 in c:\\program files\\python311\\lib\\site-packages (from spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (4.67.1)\n",
      "Requirement already satisfied: requests<3.0.0,>=2.13.0 in c:\\program files\\python311\\lib\\site-packages (from spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (2.32.3)\n",
      "Requirement already satisfied: pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4 in c:\\program files\\python311\\lib\\site-packages (from spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (2.4.2)\n",
      "Requirement already satisfied: jinja2 in c:\\program files\\python311\\lib\\site-packages (from spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (3.1.2)\n",
      "Requirement already satisfied: setuptools in c:\\program files\\python311\\lib\\site-packages (from spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (65.5.0)\n",
      "Requirement already satisfied: packaging>=20.0 in c:\\program files\\python311\\lib\\site-packages (from spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (24.0)\n",
      "Requirement already satisfied: langcodes<4.0.0,>=3.2.0 in c:\\program files\\python311\\lib\\site-packages (from spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (3.3.0)\n",
      "Requirement already satisfied: numpy>=1.19.0 in c:\\program files\\python311\\lib\\site-packages (from spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (1.26.4)\n",
      "Requirement already satisfied: annotated-types>=0.4.0 in c:\\program files\\python311\\lib\\site-packages (from pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4->spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (0.6.0)\n",
      "Requirement already satisfied: pydantic-core==2.10.1 in c:\\program files\\python311\\lib\\site-packages (from pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4->spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (2.10.1)\n",
      "Requirement already satisfied: typing-extensions>=4.6.1 in c:\\program files\\python311\\lib\\site-packages (from pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4->spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (4.12.1)\n",
      "Requirement already satisfied: charset-normalizer<4,>=2 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from requests<3.0.0,>=2.13.0->spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (3.2.0)\n",
      "Requirement already satisfied: idna<4,>=2.5 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from requests<3.0.0,>=2.13.0->spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (3.4)\n",
      "Requirement already satisfied: urllib3<3,>=1.21.1 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from requests<3.0.0,>=2.13.0->spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (1.26.16)\n",
      "Requirement already satisfied: certifi>=2017.4.17 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from requests<3.0.0,>=2.13.0->spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (2023.7.22)\n",
      "Requirement already satisfied: blis<0.8.0,>=0.7.8 in c:\\program files\\python311\\lib\\site-packages (from thinc<8.3.0,>=8.1.8->spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (0.7.11)\n",
      "Requirement already satisfied: confection<1.0.0,>=0.0.1 in c:\\program files\\python311\\lib\\site-packages (from thinc<8.3.0,>=8.1.8->spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (0.1.3)\n",
      "Requirement already satisfied: colorama in c:\\program files\\python311\\lib\\site-packages (from tqdm<5.0.0,>=4.38.0->spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (0.4.6)\n",
      "Requirement already satisfied: click<9.0.0,>=7.1.1 in c:\\program files\\python311\\lib\\site-packages (from typer<0.10.0,>=0.3.0->spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (8.1.7)\n",
      "Requirement already satisfied: cloudpathlib<0.17.0,>=0.7.0 in c:\\program files\\python311\\lib\\site-packages (from weasel<0.4.0,>=0.1.0->spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (0.16.0)\n",
      "Requirement already satisfied: MarkupSafe>=2.0 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from jinja2->spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (2.1.3)\n",
      "\u001b[38;5;2m✔ Download and installation successful\u001b[0m\n",
      "You can now load the package via spacy.load('en_core_web_sm')\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\koppo\\AppData\\Roaming\\Python\\Python311\\site-packages\\torch\\utils\\_pytree.py:185: FutureWarning: optree is installed but the version is too old to support PyTorch Dynamo in C++ pytree. C++ pytree support is disabled. Please consider upgrading optree using `python3 -m pip install --upgrade 'optree>=0.13.0'`.\n",
      "  warnings.warn(\n",
      "\n",
      "[notice] A new release of pip is available: 25.0.1 -> 25.1.1\n",
      "[notice] To update, run: python.exe -m pip install --upgrade pip\n"
     ]
    }
   ],
   "source": [
    "%pip install datasets scikit-learn nltk spacy tqdm\n",
    "!python -m nltk.downloader stopwords\n",
    "!python -m spacy download en_core_web_sm"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "02a240ec",
   "metadata": {},
   "source": [
    "### Load Job Descriptions Dataset from Hugging Face"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "f7383cd0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "7cd26f6084fb4b918a61b4de2e7c5e71",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "VBox(children=(HTML(value='<center> <img\\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.sv…"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from huggingface_hub import login\n",
    "login()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "fecad2dd",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "701f82681e2644bdbcabb34252b2dcdc",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "README.md:   0%|          | 0.00/24.0 [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "22ee0b4619ab4d598ed0946e305d9d2a",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "training_data.csv:   0%|          | 0.00/3.77M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "8204dc32b4064bf9bc5128f81a018e77",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Generating train split:   0%|          | 0/853 [00:00<?, ? examples/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from datasets import load_dataset\n",
    "\n",
    "ds = load_dataset(\"jacob-hugging-face/job-descriptions\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "5ffd7256",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "33c0a5e3af27476c873340f8dadfed36",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "README.md:   0%|          | 0.00/411 [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "ec2efe15fba0486abb002c061a8b62bb",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "train-00000-of-00001.parquet:   0%|          | 0.00/29.0M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "e0432b78d68b46418ddf03e432192ad4",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "test-00000-of-00001.parquet:   0%|          | 0.00/8.07M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "09ab2bd6268c4d06bc77465ec789056d",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Generating train split:   0%|          | 0/6241 [00:00<?, ? examples/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "7057297e24d1428e8689777fb7411ff4",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Generating test split:   0%|          | 0/1759 [00:00<?, ? examples/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from datasets import load_dataset\n",
    "\n",
    "ds = load_dataset(\"facehuggerapoorv/resume-jd-match\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "c5631cfe",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Defaulting to user installation because normal site-packages is not writeable\n",
      "Collecting kagglehub[hf-datasets]\n",
      "  Downloading kagglehub-0.3.12-py3-none-any.whl.metadata (38 kB)\n",
      "Requirement already satisfied: packaging in c:\\program files\\python311\\lib\\site-packages (from kagglehub[hf-datasets]) (24.0)\n",
      "Requirement already satisfied: pyyaml in c:\\program files\\python311\\lib\\site-packages (from kagglehub[hf-datasets]) (6.0.1)\n",
      "Requirement already satisfied: requests in c:\\program files\\python311\\lib\\site-packages (from kagglehub[hf-datasets]) (2.32.3)\n",
      "Requirement already satisfied: tqdm in c:\\program files\\python311\\lib\\site-packages (from kagglehub[hf-datasets]) (4.67.1)\n",
      "Requirement already satisfied: datasets in c:\\program files\\python311\\lib\\site-packages (from kagglehub[hf-datasets]) (3.3.2)\n",
      "Requirement already satisfied: pandas in c:\\program files\\python311\\lib\\site-packages (from kagglehub[hf-datasets]) (2.2.2)\n",
      "Requirement already satisfied: filelock in c:\\program files\\python311\\lib\\site-packages (from datasets->kagglehub[hf-datasets]) (3.13.1)\n",
      "Requirement already satisfied: numpy>=1.17 in c:\\program files\\python311\\lib\\site-packages (from datasets->kagglehub[hf-datasets]) (1.26.4)\n",
      "Requirement already satisfied: pyarrow>=15.0.0 in c:\\program files\\python311\\lib\\site-packages (from datasets->kagglehub[hf-datasets]) (19.0.1)\n",
      "Requirement already satisfied: dill<0.3.9,>=0.3.0 in c:\\program files\\python311\\lib\\site-packages (from datasets->kagglehub[hf-datasets]) (0.3.8)\n",
      "Requirement already satisfied: xxhash in c:\\program files\\python311\\lib\\site-packages (from datasets->kagglehub[hf-datasets]) (3.5.0)\n",
      "Requirement already satisfied: multiprocess<0.70.17 in c:\\program files\\python311\\lib\\site-packages (from datasets->kagglehub[hf-datasets]) (0.70.16)\n",
      "Requirement already satisfied: fsspec<=2024.12.0,>=2023.1.0 in c:\\program files\\python311\\lib\\site-packages (from fsspec[http]<=2024.12.0,>=2023.1.0->datasets->kagglehub[hf-datasets]) (2024.2.0)\n",
      "Requirement already satisfied: aiohttp in c:\\program files\\python311\\lib\\site-packages (from datasets->kagglehub[hf-datasets]) (3.11.13)\n",
      "Requirement already satisfied: huggingface-hub>=0.24.0 in c:\\program files\\python311\\lib\\site-packages (from datasets->kagglehub[hf-datasets]) (0.29.3)\n",
      "Requirement already satisfied: charset-normalizer<4,>=2 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from requests->kagglehub[hf-datasets]) (3.2.0)\n",
      "Requirement already satisfied: idna<4,>=2.5 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from requests->kagglehub[hf-datasets]) (3.4)\n",
      "Requirement already satisfied: urllib3<3,>=1.21.1 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from requests->kagglehub[hf-datasets]) (1.26.16)\n",
      "Requirement already satisfied: certifi>=2017.4.17 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from requests->kagglehub[hf-datasets]) (2023.7.22)\n",
      "Requirement already satisfied: colorama in c:\\program files\\python311\\lib\\site-packages (from tqdm->kagglehub[hf-datasets]) (0.4.6)\n",
      "Requirement already satisfied: python-dateutil>=2.8.2 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from pandas->kagglehub[hf-datasets]) (2.8.2)\n",
      "Requirement already satisfied: pytz>=2020.1 in c:\\program files\\python311\\lib\\site-packages (from pandas->kagglehub[hf-datasets]) (2024.1)\n",
      "Requirement already satisfied: tzdata>=2022.7 in c:\\program files\\python311\\lib\\site-packages (from pandas->kagglehub[hf-datasets]) (2024.1)\n",
      "Requirement already satisfied: aiohappyeyeballs>=2.3.0 in c:\\program files\\python311\\lib\\site-packages (from aiohttp->datasets->kagglehub[hf-datasets]) (2.5.0)\n",
      "Requirement already satisfied: aiosignal>=1.1.2 in c:\\program files\\python311\\lib\\site-packages (from aiohttp->datasets->kagglehub[hf-datasets]) (1.3.2)\n",
      "Requirement already satisfied: attrs>=17.3.0 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from aiohttp->datasets->kagglehub[hf-datasets]) (23.1.0)\n",
      "Requirement already satisfied: frozenlist>=1.1.1 in c:\\program files\\python311\\lib\\site-packages (from aiohttp->datasets->kagglehub[hf-datasets]) (1.5.0)\n",
      "Requirement already satisfied: multidict<7.0,>=4.5 in c:\\program files\\python311\\lib\\site-packages (from aiohttp->datasets->kagglehub[hf-datasets]) (6.1.0)\n",
      "Requirement already satisfied: propcache>=0.2.0 in c:\\program files\\python311\\lib\\site-packages (from aiohttp->datasets->kagglehub[hf-datasets]) (0.3.0)\n",
      "Requirement already satisfied: yarl<2.0,>=1.17.0 in c:\\program files\\python311\\lib\\site-packages (from aiohttp->datasets->kagglehub[hf-datasets]) (1.18.3)\n",
      "Requirement already satisfied: typing-extensions>=3.7.4.3 in c:\\program files\\python311\\lib\\site-packages (from huggingface-hub>=0.24.0->datasets->kagglehub[hf-datasets]) (4.12.1)\n",
      "Requirement already satisfied: six>=1.5 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from python-dateutil>=2.8.2->pandas->kagglehub[hf-datasets]) (1.16.0)\n",
      "Downloading kagglehub-0.3.12-py3-none-any.whl (67 kB)\n",
      "Installing collected packages: kagglehub\n",
      "Successfully installed kagglehub-0.3.12\n",
      "Note: you may need to restart the kernel to use updated packages.\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "[notice] A new release of pip is available: 25.0.1 -> 25.1.1\n",
      "[notice] To update, run: python.exe -m pip install --upgrade pip\n"
     ]
    }
   ],
   "source": [
    "pip install kagglehub[hf-datasets]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "d0dcf353",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Defaulting to user installation because normal site-packages is not writeable\n",
      "Collecting kaggle\n",
      "  Downloading kaggle-1.7.4.5-py3-none-any.whl.metadata (16 kB)\n",
      "Requirement already satisfied: bleach in c:\\program files\\python311\\lib\\site-packages (from kaggle) (6.1.0)\n",
      "Requirement already satisfied: certifi>=14.05.14 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from kaggle) (2023.7.22)\n",
      "Requirement already satisfied: charset-normalizer in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from kaggle) (3.2.0)\n",
      "Requirement already satisfied: idna in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from kaggle) (3.4)\n",
      "Requirement already satisfied: protobuf in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from kaggle) (5.29.4)\n",
      "Requirement already satisfied: python-dateutil>=2.5.3 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from kaggle) (2.8.2)\n",
      "Collecting python-slugify (from kaggle)\n",
      "  Downloading python_slugify-8.0.4-py2.py3-none-any.whl.metadata (8.5 kB)\n",
      "Requirement already satisfied: requests in c:\\program files\\python311\\lib\\site-packages (from kaggle) (2.32.3)\n",
      "Requirement already satisfied: setuptools>=21.0.0 in c:\\program files\\python311\\lib\\site-packages (from kaggle) (65.5.0)\n",
      "Requirement already satisfied: six>=1.10 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from kaggle) (1.16.0)\n",
      "Collecting text-unidecode (from kaggle)\n",
      "  Downloading text_unidecode-1.3-py2.py3-none-any.whl.metadata (2.4 kB)\n",
      "Requirement already satisfied: tqdm in c:\\program files\\python311\\lib\\site-packages (from kaggle) (4.67.1)\n",
      "Requirement already satisfied: urllib3>=1.15.1 in c:\\users\\koppo\\appdata\\roaming\\python\\python311\\site-packages (from kaggle) (1.26.16)\n",
      "Requirement already satisfied: webencodings in c:\\program files\\python311\\lib\\site-packages (from kaggle) (0.5.1)\n",
      "Requirement already satisfied: colorama in c:\\program files\\python311\\lib\\site-packages (from tqdm->kaggle) (0.4.6)\n",
      "Downloading kaggle-1.7.4.5-py3-none-any.whl (181 kB)\n",
      "Downloading python_slugify-8.0.4-py2.py3-none-any.whl (10 kB)\n",
      "Downloading text_unidecode-1.3-py2.py3-none-any.whl (78 kB)\n",
      "Installing collected packages: text-unidecode, python-slugify, kaggle\n",
      "Successfully installed kaggle-1.7.4.5 python-slugify-8.0.4 text-unidecode-1.3\n",
      "Note: you may need to restart the kernel to use updated packages.\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "[notice] A new release of pip is available: 25.0.1 -> 25.1.1\n",
      "[notice] To update, run: python.exe -m pip install --upgrade pip\n"
     ]
    }
   ],
   "source": [
    "pip install kaggle"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "0c7c78fc",
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import json\n",
    "\n",
    "# Define path\n",
    "kaggle_json = {\n",
    "    \"username\": \"sathvikkirank\",\n",
    "    \"key\": \"4e476a595ed72c041efbd856398c5bee\"\n",
    "}\n",
    "\n",
    "# Write this JSON to ~/.kaggle/kaggle.json\n",
    "os.makedirs(os.path.expanduser(\"~/.kaggle\"), exist_ok=True)\n",
    "with open(os.path.expanduser(\"~/.kaggle/kaggle.json\"), \"w\") as f:\n",
    "    json.dump(kaggle_json, f)\n",
    "\n",
    "# Set permission\n",
    "os.chmod(os.path.expanduser(\"~/.kaggle/kaggle.json\"), 0o600)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "ce656b75",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Dataset URL: https://www.kaggle.com/datasets/gauravduttakiit/resume-dataset\n",
      "License(s): CC0-1.0\n",
      "Downloading resume-dataset.zip to f:\\New folder (2)\\resume-analyzer\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "  0%|          | 0.00/383k [00:00<?, ?B/s]\n",
      "100%|██████████| 383k/383k [00:00<00:00, 193MB/s]\n"
     ]
    }
   ],
   "source": [
    "!kaggle datasets download -d gauravduttakiit/resume-dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "61447abf",
   "metadata": {},
   "outputs": [],
   "source": [
    "import zipfile\n",
    "\n",
    "with zipfile.ZipFile(\"resume-dataset.zip\", 'r') as zip_ref:\n",
    "    zip_ref.extractall(\"resume_dataset\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "63f7fd63",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 962 entries, 0 to 961\n",
      "Data columns (total 2 columns):\n",
      " #   Column    Non-Null Count  Dtype \n",
      "---  ------    --------------  ----- \n",
      " 0   Category  962 non-null    object\n",
      " 1   Resume    962 non-null    object\n",
      "dtypes: object(2)\n",
      "memory usage: 15.2+ KB\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "Category    0\n",
       "Resume      0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "\n",
    "df = pd.read_csv(\"resume_dataset/UpdatedResumeDataSet.csv\")  # or .json if applicable\n",
    "df.head()\n",
    "df.info()\n",
    "df.describe(include='all')\n",
    "df.isnull().sum()"
   ]
  }
 ],
 "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": "3.11.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}