Demo of AZP variants

demo_AZP-BasicTabu.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# AZP-BasicTabu demo"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The basic tabu version of the AZP as described on p. 432 in Openshaw & Rao (1995) is lacking a stopping condition. That's why the implementation in [commit ee3f08f44](https://github.com/yogabonito/region/commit/ee3f08f441f7367204fc2d1d391e7e3bedacdc80) doesn't terminate. Therefore we left the cells in this notebook unexecuted."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from region.azp import *"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "from matplotlib import pyplot as plt\n",
    "import pandas as pd\n",
    "import geopandas as gpd\n",
    "from shapely.geometry import Polygon"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Example 1: 3x3 lattice"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Inputs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "geometry = [\n",
    "    Polygon([(x, y),\n",
    "             (x, y+1),\n",
    "             (x+1, y+1),\n",
    "             (x+1, y)]) for y in range(3) for x in range(3)\n",
    "]\n",
    "\n",
    "areas_gdf = gpd.GeoDataFrame(\n",
    "    {\"values\": [726.7, 623.6, 487.3,\n",
    "                200.4, 245.0, 481.0,\n",
    "                170.9, 225.9, 226.9]},\n",
    "    geometry=geometry)\n",
    "areas_gdf.plot(column=\"values\")\n",
    "plt.gca().invert_yaxis()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Clustering"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "###     without initial solution"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "azpbt = AZPBasicTabu(n_regions=2, random_state=2, tabu_length=20)\n",
    "regions_dict_bt_wo = azpbt.fit(areas=areas_gdf,\n",
    "                               data=[\"values\"],\n",
    "                               contiguity=\"rook\")\n",
    "areas_gdf[\"region\"] = pd.Series(regions_dict_bt_wo)\n",
    "areas_gdf.plot(column=\"region\", cmap='tab20c')\n",
    "plt.gca().invert_yaxis()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Example 2: Islands"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "islands_geometry = [\n",
    "    Polygon([(x, y),\n",
    "             (x, y+1),\n",
    "             (x+1, y+1),\n",
    "             (x+1, y)]) for y in range(3) for x in range(3)\n",
    "] + [\n",
    "    Polygon([(x, y),\n",
    "             (x, y+1),\n",
    "             (x+1, y+1),\n",
    "             (x+1, y)]) for y in range(4,6) for x in range(5,8)\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "islands_gdf = gpd.GeoDataFrame(\n",
    "    {\"values\": [726.7, 623.6, 487.3,\n",
    "                200.4, 245.0, 481.0,\n",
    "                170.9, 225.9, 226.9] +\n",
    "               [100,   120,   190,\n",
    "                175,   185,   210]},\n",
    "    geometry=islands_geometry)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "islands_gdf.plot(column=\"values\")\n",
    "plt.gca().invert_yaxis()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Clustering"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "###     without initial solution"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "azpbt = AZPBasicTabu(n_regions=3, tabu_length=3, random_state=0)\n",
    "islands_dict_bt_wo = azpbt.fit(areas=islands_gdf,\n",
    "                               data=[\"values\"],\n",
    "                               contiguity=\"rook\")\n",
    "islands_gdf[\"region\"] = pd.Series(islands_dict_bt_wo)\n",
    "islands_gdf.plot(column=\"region\", cmap='tab20c')\n",
    "plt.gca().invert_yaxis()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Example 3: A tricky toy example"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Inputs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "squares = [\n",
    "    Polygon([(x,   0),\n",
    "             (x,   1),\n",
    "             (x+1, 1),\n",
    "             (x+1, 0)]) for x in range(3)\n",
    "]\n",
    "values = [0, 1, 0]\n",
    "squares_gdf = gpd.GeoDataFrame({\"values\": values},\n",
    "                           geometry=squares)\n",
    "squares_gdf.plot(column=\"values\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Clustering"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "azpbt = AZPSimulatedAnnealing(n_regions=2, init_temperature=1, max_iterations=3, random_state=0)\n",
    "regions_dict_squares_bt = azpbt.fit(areas=squares_gdf,\n",
    "                                    data=[\"values\"],\n",
    "                                    contiguity=\"rook\",\n",
    "                                    cooling_factor=0.85)\n",
    "squares_gdf[\"region\"] = pd.Series(regions_dict_squares_bt)\n",
    "squares_gdf.plot(column=\"region\", cmap='tab20c')\n",
    "plt.gca().invert_yaxis()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.5.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}

demo_AZP-ReactiveTabu.ipynb

demo_AZP-SA.ipynb

demo_AZP.ipynb