{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "b2dd5b02",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "✅ All imports successful!\n",
      "📦 Pandas: 2.1.4\n",
      "📦 Numpy: 1.26.3\n"
     ]
    }
   ],
   "source": [
    "# ═══════════════════════════════════════════════════════════════════\n",
    "# 🚀 HRHUB V2.1 - PRODUCTION NOTEBOOK\n",
    "# Cell 1: Setup & Imports\n",
    "# ═══════════════════════════════════════════════════════════════════\n",
    "\n",
    "import warnings\n",
    "warnings.filterwarnings('ignore')\n",
    "\n",
    "# Core\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "from pathlib import Path\n",
    "\n",
    "# Embeddings\n",
    "from sentence_transformers import SentenceTransformer\n",
    "from sklearn.metrics.pairwise import cosine_similarity\n",
    "\n",
    "# Viz\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "import plotly.express as px\n",
    "import plotly.graph_objects as go\n",
    "from pyvis.network import Network\n",
    "\n",
    "# Dimensionality reduction\n",
    "from sklearn.manifold import TSNE\n",
    "\n",
    "# Utils\n",
    "from tqdm import tqdm\n",
    "import pickle\n",
    "from typing import List, Dict, Tuple\n",
    "import time\n",
    "\n",
    "# Config\n",
    "plt.style.use('seaborn-v0_8-darkgrid')\n",
    "sns.set_palette(\"husl\")\n",
    "pd.set_option('display.max_columns', None)\n",
    "pd.set_option('display.max_rows', 100)\n",
    "\n",
    "print(\"✅ All imports successful!\")\n",
    "print(f\"📦 Pandas: {pd.__version__}\")\n",
    "print(f\"📦 Numpy: {np.__version__}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "b8696a11",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "✅ Paths configured!\n",
      "📂 Base path: data\n",
      "🤖 Model: sentence-transformers/all-MiniLM-L6-v2\n"
     ]
    }
   ],
   "source": [
    "# ═══════════════════════════════════════════════════════════════════\n",
    "# Cell 2: Paths & Configuration\n",
    "# ═══════════════════════════════════════════════════════════════════\n",
    "\n",
    "# 🟢 VSCode local - path direto\n",
    "BASE_PATH = Path(\"data\")\n",
    "\n",
    "# Input paths\n",
    "DATA_PATHS = {\n",
    "    'benefits': BASE_PATH / \"benefits.csv\",\n",
    "    'companies': BASE_PATH / \"companies.csv\",\n",
    "    'company_industries': BASE_PATH / \"company_industries.csv\",\n",
    "    'company_specialties': BASE_PATH / \"company_specialties.csv\",\n",
    "    'employee_counts': BASE_PATH / \"employee_counts.csv\",\n",
    "    'industries': BASE_PATH / \"industries.csv\",\n",
    "    'job_industries': BASE_PATH / \"job_industries.csv\",\n",
    "    'job_skills': BASE_PATH / \"job_skills.csv\",\n",
    "    'postings': BASE_PATH / \"postings.csv\",\n",
    "    'resume_data': BASE_PATH / \"resume_data.csv\",\n",
    "    'salaries': BASE_PATH / \"salaries.csv\",\n",
    "    'skills': BASE_PATH / \"skills.csv\"\n",
    "}\n",
    "\n",
    "# Output files (salvamos direto com npy/pkl)\n",
    "OUTPUT_FILES = {\n",
    "    'candidate_embeddings': 'candidate_embeddings.npy',\n",
    "    'company_embeddings': 'company_embeddings.npy',\n",
    "    'candidate_metadata': 'candidate_metadata.pkl',\n",
    "    'company_metadata': 'company_metadata.pkl'\n",
    "}\n",
    "\n",
    "# Model config\n",
    "MODEL_NAME = \"sentence-transformers/all-MiniLM-L6-v2\"\n",
    "EMBEDDING_DIM = 384\n",
    "\n",
    "print(\"✅ Paths configured!\")\n",
    "print(f\"📂 Base path: {BASE_PATH}\")\n",
    "print(f\"🤖 Model: {MODEL_NAME}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "657220e4",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "📥 Loading data...\n",
      "❌ benefits: ERROR - [Errno 2] No such file or directory: 'data/benefits.csv'\n",
      "❌ companies: ERROR - [Errno 2] No such file or directory: 'data/companies.csv'\n",
      "❌ company_industries: ERROR - [Errno 2] No such file or directory: 'data/company_industries.csv'\n",
      "❌ company_specialties: ERROR - [Errno 2] No such file or directory: 'data/company_specialties.csv'\n",
      "❌ employee_counts: ERROR - [Errno 2] No such file or directory: 'data/employee_counts.csv'\n",
      "❌ industries: ERROR - [Errno 2] No such file or directory: 'data/industries.csv'\n",
      "❌ job_industries: ERROR - [Errno 2] No such file or directory: 'data/job_industries.csv'\n",
      "❌ job_skills: ERROR - [Errno 2] No such file or directory: 'data/job_skills.csv'\n",
      "❌ postings: ERROR - [Errno 2] No such file or directory: 'data/postings.csv'\n",
      "❌ resume_data: ERROR - [Errno 2] No such file or directory: 'data/resume_data.csv'\n",
      "❌ salaries: ERROR - [Errno 2] No such file or directory: 'data/salaries.csv'\n",
      "❌ skills: ERROR - [Errno 2] No such file or directory: 'data/skills.csv'\n",
      "\n",
      "⏱️  Loaded in 0.00s\n",
      "\n",
      "======================================================================\n",
      "🔍 KEY DATASETS PREVIEW\n",
      "======================================================================\n",
      "\n",
      "📋 CANDIDATES (resume_data):\n",
      "\n",
      "🏢 COMPANIES:\n",
      "\n",
      "📄 JOB POSTINGS:\n",
      "\n",
      "✅ Data loaded! Ready to inspect and clean.\n"
     ]
    }
   ],
   "source": [
    "# ═══════════════════════════════════════════════════════════════════\n",
    "# Cell 3: Load Raw Data\n",
    "# ═══════════════════════════════════════════════════════════════════\n",
    "\n",
    "print(\"📥 Loading data...\")\n",
    "start_time = time.time()\n",
    "\n",
    "# Load all CSVs\n",
    "data = {}\n",
    "for name, path in DATA_PATHS.items():\n",
    "    try:\n",
    "        df = pd.read_csv(path)\n",
    "        data[name] = df\n",
    "        print(f\"✅ {name}: {df.shape[0]:,} rows × {df.shape[1]} cols\")\n",
    "    except Exception as e:\n",
    "        print(f\"❌ {name}: ERROR - {e}\")\n",
    "        data[name] = None\n",
    "\n",
    "load_time = time.time() - start_time\n",
    "print(f\"\\n⏱️  Loaded in {load_time:.2f}s\")\n",
    "\n",
    "# Quick peek at key datasets\n",
    "print(\"\\n\" + \"=\"*70)\n",
    "print(\"🔍 KEY DATASETS PREVIEW\")\n",
    "print(\"=\"*70)\n",
    "\n",
    "print(\"\\n📋 CANDIDATES (resume_data):\")\n",
    "if data['resume_data'] is not None:\n",
    "    print(f\"Shape: {data['resume_data'].shape}\")\n",
    "    print(f\"Columns: {list(data['resume_data'].columns)}\")\n",
    "    print(data['resume_data'].head(2))\n",
    "\n",
    "print(\"\\n🏢 COMPANIES:\")\n",
    "if data['companies'] is not None:\n",
    "    print(f\"Shape: {data['companies'].shape}\")\n",
    "    print(f\"Columns: {list(data['companies'].columns)}\")\n",
    "    print(data['companies'].head(2))\n",
    "\n",
    "print(\"\\n📄 JOB POSTINGS:\")\n",
    "if data['postings'] is not None:\n",
    "    print(f\"Shape: {data['postings'].shape}\")\n",
    "    print(f\"Columns: {list(data['postings'].columns)}\")\n",
    "    print(data['postings'].head(2))\n",
    "\n",
    "print(\"\\n✅ Data loaded! Ready to inspect and clean.\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "52833afd",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "venv",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.12.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}