Geospatial workbench

workbench.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "aacf3781",
   "metadata": {},
   "source": [
    "# Workbench"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "bb70572a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "9.0\r\n"
     ]
    }
   ],
   "source": [
    "! echo $GDS_ENV_VERSION"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "766a6172",
   "metadata": {},
   "outputs": [],
   "source": [
    "from libpysal import weights\n",
    "import pandas\n",
    "import geopandas\n",
    "import numpy as np\n",
    "import polars as pl"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e786da57",
   "metadata": {},
   "source": [
    "Utilities:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "d05eab7d",
   "metadata": {},
   "outputs": [],
   "source": [
    "def lag_spatial_adj(w_adj, y):\n",
    "    return (\n",
    "        w_synth_adj\n",
    "        .join(y_synth, on='focal')\n",
    "        .eval('product = weight * y_synth')\n",
    "        .groupby('focal')\n",
    "        ['product']\n",
    "        .mean()\n",
    "    )\n",
    "\n",
    "def lag_spatial_adj_polars(w_adj_pl, y_pl):\n",
    "    return (\n",
    "        w_adj_pl\n",
    "        .join()\n",
    "    )"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0fc56966",
   "metadata": {},
   "source": [
    "## Data setup"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "71c2aac9",
   "metadata": {},
   "source": [
    "- Synthetic data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "2ddaf1fe",
   "metadata": {},
   "outputs": [],
   "source": [
    "w_synth = weights.lat2W(1000, 1000, 'queen')\n",
    "w_synth.transform = 'R'\n",
    "w_synth_adj = w_synth.to_adjlist()\n",
    "w_synth_adj_pl = pl.DataFrame(w_synth_adj)\n",
    "y_synth = pandas.Series(np.random.random(1000000), name='y_synth')\n",
    "y_synth_pl = pl.Series(y_synth)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "58762ae2",
   "metadata": {},
   "source": [
    "- Spatial Signatures"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c772aa45",
   "metadata": {},
   "source": [
    "## Spatial ops"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ba7d354a",
   "metadata": {},
   "source": [
    "### Spatial Lag"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b5db2788",
   "metadata": {},
   "source": [
    "- PySAL"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "cacf2df9",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "4.02 ms ± 39.3 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n"
     ]
    }
   ],
   "source": [
    "_ = weights.lag_spatial(w_synth, y)\n",
    "%timeit pysal_lag = weights.lag_spatial(w_synth, y)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6739772f",
   "metadata": {},
   "source": [
    "- Adjacency `pandas`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "682417de",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "299 ms ± 7.8 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
     ]
    }
   ],
   "source": [
    "%timeit pandas_lag = lag_spatial_adj(w_synth_adj, y_synth)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "59d7f9ba",
   "metadata": {},
   "source": [
    "- Adjacency `polars`"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c1e51920",
   "metadata": {},
   "source": [
    "### LISA"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "eaec1895",
   "metadata": {},
   "source": [
    "- Single core"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4239a179",
   "metadata": {},
   "source": [
    "- Parallel"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fe04cafd",
   "metadata": {},
   "source": [
    "###  `geopandas.overlay`"
   ]
  }
 ],
 "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": "3.10.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}