{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "# pyJedAI Spatial Component\n",
    "\n",
    "\n",
    "In this notebook we present the pyJedAI Geospatial Interlinking functionality."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "^C\n"
     ]
    }
   ],
   "source": [
    "!pip install pyjedai:0.1.4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "pycharm": {
     "is_executing": true
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Python 3.9.16\n"
     ]
    }
   ],
   "source": [
    "!python --version"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Libraries injection"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "pycharm": {
     "is_executing": true
    }
   },
   "outputs": [],
   "source": [
    "import csv\n",
    "import sys\n",
    "import os\n",
    "\n",
    "from pyjedai.datamodel import SpatialData\n",
    "from pyjedai.spatial.filtering import StandardSpatialFiltering\n",
    "from pyjedai.spatial.initialization import StandardSpatialInitialization\n",
    "from pyjedai.spatial.verification import StandardSpatialVerification"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Data reading and pyJedAI-formating"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "data_dir = '../data/spatial/'\n",
    "\n",
    "maxInt = sys.maxsize\n",
    "while True:\n",
    "    try:\n",
    "        csv.field_size_limit(maxInt)\n",
    "        break\n",
    "    except OverflowError:\n",
    "        maxInt = int(maxInt/10)\n",
    "\n",
    "path1 = os.path.join(data_dir,\"regions_gr.csv\")\n",
    "path2 = os.path.join(data_dir,\"wildlife_sanctuaries.csv\")\n",
    "\n",
    "delimiter1 = \"\\t\"\n",
    "delimiter2 = \"\\t\"\n",
    "\n",
    "# Read the CSV files\n",
    "file1 = open(path1, newline='', encoding='utf-8')\n",
    "file2 = open(path2, newline='', encoding='utf-8')\n",
    "\n",
    "dataset_1 = csv.reader(file1, delimiter=delimiter1)\n",
    "dataset_2 = csv.reader(file2, delimiter=delimiter1)\n",
    "\n",
    "spatial_data = \\\n",
    "    SpatialData(source_reader=dataset_1,\n",
    "                source_delimiter=\"\\t\",\n",
    "                target_reader=dataset_2, target_delimiter=\"\\t\",\n",
    "                skip_header=True)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Spatial Filtering"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "SSF = StandardSpatialFiltering()\n",
    "spatial_index, theta_x, theta_y = SSF.process(spatial_data)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Spatial Initialization"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "SSI = StandardSpatialInitialization(budget=1000, wScheme=\"MBR\")\n",
    "priority_pairs = SSI.process(spatial_data, spatial_index, theta_x=theta_x, theta_y=theta_y)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Spatial Verification"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────\n",
      "Performance:\n",
      "\tPrecision:      0.72% \n",
      "\tRecall:         6.48%\n",
      "\tF1-score:       1.29%\n",
      "\tProgressive Geometry Recall:      2.33%\n",
      "───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "{'Precision:': 0.7192008879023307,\n",
       " 'Recall:': 6.48,\n",
       " 'F1-score:': 1.2947052947052946,\n",
       " 'Progressivr geometry recall:': 2.3338068812430635}"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "SSV = StandardSpatialVerification(q_pairs=100)\n",
    "SSV.process(spatial_data=spatial_data, priority_pairs=priority_pairs)\n",
    "SSV.evaluate()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.10.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}