fix typos

preprocess.ipynb

@@ -1,18 +1,24 @@
 {
  "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "4b4adc2a-bf0c-4ace-87be-dbaf90be0125",
+   "metadata": {},
+   "source": [
+    "# Preporcessing"
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 1,
    "id": "f7e6298c-d886-432a-a1b7-c3fee914c24f",
    "metadata": {},
    "outputs": [],
    "source": [
-    "# boilerplate setup\n",
-    "import leafmap.maplibregl as leafmap\n",
     "import ibis\n",
     "from ibis import _\n",
     "\n",
-    "conn = ibis.duckdb.connect(\"tmp\")\n",
+    "conn = ibis.duckdb.connect(\"tmp\", extensions=[\"spatial\"])\n",
     "ca_parquet = \"https://data.source.coop/cboettig/ca30x30/ca_areas.parquet\"\n",
     "# or use local copy:\n",
     "ca_parquet = \"/home/rstudio/source.coop/cboettig/ca30x30/ca_areas.parquet\"\n"
@@ -20,15 +26,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 2,
    "id": "a0cb34b1-8d70-49bf-80c6-244ecc8ddf84",
    "metadata": {},
    "outputs": [],
    "source": [
-    "buffer = -0.00003 \n",
+    "buffer = -0.00001\n",
     "\n",
     "tbl = (\n",
-    "    conn.read_parquet(\"https://data.source.coop/cboettig/ca30x30/ca_areas.parquet\")\n",
+    "    conn.read_parquet(ca_parquet)\n",
     "    .cast({\"SHAPE\": \"geometry\"})\n",
     "    .rename(geom = \"SHAPE\")\n",
     "   # .filter(_.UNIT_NAME == \"Angeles National Forest\")\n",
@@ -43,14 +49,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 3,
    "id": "275c171a-f82f-4ee8-991c-1e34eb83a33d",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "998c2484ba604297ad438ed5c17dc59d",
+       "model_id": "dd86bb91838d45aa87197fc49a3b2362",
        "version_major": 2,
        "version_minor": 0
       },
@@ -77,7 +83,54 @@
     "      .select(_.established, _.reGAP, _.name, _.access_type, _.manager, _.manager_type,\n",
     "              _.Easement, _.Acres, _.id, _.type, _.geom)\n",
     "     )\n",
-    "ca.to_parquet(\"ca2024.parquet\")"
+    "ca.execute().to_parquet(\"ca2024.parquet\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cebd0ff5-8353-4b84-b9ee-182b74613554",
+   "metadata": {},
+   "source": [
+    "# Testing & visualization\n",
+    "\n",
+    "`ca2024.parquet()` now contains all we need.  The code below illustrates some quick examples of the kinds of visualizations and summaries we might want to compute with this data.  \n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "55afe07c-8681-4308-bbb9-e460f7380f86",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import leafmap.maplibregl as leafmap\n",
+    "import ibis\n",
+    "from ibis import _\n",
+    "conn = ibis.duckdb.connect(extensions=[\"spatial\"])\n",
+    "\n",
+    "ca2024 = conn.read_parquet(\"ca2024.parquet\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "9d4cd1c4-288b-4d1c-907c-ca76ccbdb1d6",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "geopandas.geodataframe.GeoDataFrame"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "gdf = ca2024.execute()\n",
+    "gdf.__class__"
    ]
   },
   {
@@ -90,16 +143,178 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "id": "6f3df8c1-a603-4dd5-be84-8deaae928d0a",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>manager</th>\n",
+       "      <th>manager_type</th>\n",
+       "      <th>area</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>California Department of Fish and Wildlife</td>\n",
+       "      <td>State</td>\n",
+       "      <td>42086.259379</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>California Department of Parks and Recreation</td>\n",
+       "      <td>State</td>\n",
+       "      <td>17931.321473</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>California Tahoe Conservancy</td>\n",
+       "      <td>State</td>\n",
+       "      <td>4803.250929</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>California Department of Water Resources</td>\n",
+       "      <td>State</td>\n",
+       "      <td>2248.610289</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>University of California</td>\n",
+       "      <td>State</td>\n",
+       "      <td>1860.854444</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>California Department of Forestry and Fire Pro...</td>\n",
+       "      <td>State</td>\n",
+       "      <td>1089.029581</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>Coachella Valley Mountains Conservancy</td>\n",
+       "      <td>State</td>\n",
+       "      <td>119.907070</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>California State Lands Commission</td>\n",
+       "      <td>State</td>\n",
+       "      <td>109.016475</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>California State Coastal Conservancy</td>\n",
+       "      <td>State</td>\n",
+       "      <td>97.314705</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>California State University Sonoma</td>\n",
+       "      <td>State</td>\n",
+       "      <td>38.760956</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10</th>\n",
+       "      <td>Other State</td>\n",
+       "      <td>State</td>\n",
+       "      <td>32.927882</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>11</th>\n",
+       "      <td>San Joaquin River Conservancy</td>\n",
+       "      <td>State</td>\n",
+       "      <td>1.531470</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>12</th>\n",
+       "      <td>California Department of Transportation</td>\n",
+       "      <td>State</td>\n",
+       "      <td>1.261433</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>13</th>\n",
+       "      <td>Unknown</td>\n",
+       "      <td>State</td>\n",
+       "      <td>0.255531</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>14</th>\n",
+       "      <td>California State University</td>\n",
+       "      <td>State</td>\n",
+       "      <td>0.021589</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                              manager manager_type  \\\n",
+       "0          California Department of Fish and Wildlife        State   \n",
+       "1       California Department of Parks and Recreation        State   \n",
+       "2                        California Tahoe Conservancy        State   \n",
+       "3            California Department of Water Resources        State   \n",
+       "4                            University of California        State   \n",
+       "5   California Department of Forestry and Fire Pro...        State   \n",
+       "6              Coachella Valley Mountains Conservancy        State   \n",
+       "7                   California State Lands Commission        State   \n",
+       "8                California State Coastal Conservancy        State   \n",
+       "9                  California State University Sonoma        State   \n",
+       "10                                        Other State        State   \n",
+       "11                      San Joaquin River Conservancy        State   \n",
+       "12            California Department of Transportation        State   \n",
+       "13                                            Unknown        State   \n",
+       "14                        California State University        State   \n",
+       "\n",
+       "            area  \n",
+       "0   42086.259379  \n",
+       "1   17931.321473  \n",
+       "2    4803.250929  \n",
+       "3    2248.610289  \n",
+       "4    1860.854444  \n",
+       "5    1089.029581  \n",
+       "6     119.907070  \n",
+       "7     109.016475  \n",
+       "8      97.314705  \n",
+       "9      38.760956  \n",
+       "10     32.927882  \n",
+       "11      1.531470  \n",
+       "12      1.261433  \n",
+       "13      0.255531  \n",
+       "14      0.021589  "
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "# compute some summary tables:\n",
     "\n",
-    "(ca\n",
+    "(ca2024\n",
     " .filter(_.established == 2024)\n",
-    " .filter(_.manager_type == manager_type)\n",
+    " .filter(_.manager_type == \"State\")\n",
     " .group_by(_.manager, _.manager_type)\n",
     " .agg(area = _.Acres.sum())\n",
     " .order_by(_.area.desc())\n",
@@ -109,12 +324,29 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 7,
    "id": "c62854f6-1456-4207-8c69-53af17970102",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "10329a95c7b84de4b598f0ccf4c6af20",
+       "version_major": 2,
+       "version_minor": 1
+      },
+      "text/plain": [
+       "Map(height='600px', map_options={'bearing': 0, 'center': (0, 20), 'pitch': 0, 'style': 'https://basemaps.carto…"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
-    "gdf = ca.filter(_.manager == \"United States National Park Service\", _.established== 2024).execute()\n",
+    "gdf = ca2024.filter(_.manager == \"California Department of Parks and Recreation\", _.established== 2024).execute()\n",
+    "\n",
     "established = {'property': 'established',\n",
     "               'type': 'categorical',\n",
     "               'stops': [\n",