Expand example to country

experiments/presentation/over_100k_cop_2021.ipynb

@@ -39,6 +39,14 @@
     ")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "8020a327-59cf-49ef-a6e3-122ea74f4eec",
+   "metadata": {},
+   "source": [
+    "# % of People Making Over $100,000 For Select Cities"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 9,
@@ -180,14 +188,118 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": null,
    "id": "f5dd0922-4c72-4911-8e06-da3f8bdb09bd",
    "metadata": {},
+   "outputs": [],
+   "source": [
+    "m = Map([basemap, cop_layer])\n",
+    "\n",
+    "m"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "186b159b-044a-4841-92e1-6a310f91c756",
+   "metadata": {},
+   "source": [
+    "# % of People Making Over $100,000 For The Whole Country"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "d359f0cf-4c05-4fca-9176-709cd5ff977e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "con.execute(\"\"\"\n",
+    "DROP TABLE IF EXISTS geo_data;\n",
+    "CREATE TABLE geo_data AS\n",
+    "SELECT\n",
+    "    geo.da_dguid,\n",
+    "    cop.count_total_1,\n",
+    "    cop.count_total_155,\n",
+    "    cop.count_total_168,\n",
+    "    CASE\n",
+    "        WHEN cop.count_total_168 = 0.0 THEN 0\n",
+    "        WHEN cop.count_total_155 = 0.0 THEN 0\n",
+    "        WHEN cop.count_total_168 IS NULL THEN 0\n",
+    "        WHEN cop.count_total_155 IS NULL THEN 0\n",
+    "        ELSE \n",
+    "            ((cop.count_total_168/cop.count_total_155) * 100) \n",
+    "    END AS percentage_over_100k,\n",
+    "    geo.geom\n",
+    "FROM\n",
+    "    'https://data-01.dataforcanada.org/processed/statistics_canada/census_of_population/2021/tabular/da_2021.parquet' AS cop,\n",
+    "    'https://data-01.dataforcanada.org/processed/statistics_canada/boundaries/2021/digital_boundary_files/da_2021.parquet' AS geo\n",
+    "WHERE cop.da_dguid = geo.da_dguid;\n",
+    "\"\"\")\n",
+    "\n",
+    "con.execute(\"\"\"\n",
+    "COPY geo_data TO './da_2021_characteristic.parquet' (FORMAT PARQUET);\n",
+    "\"\"\")\n",
+    "\n",
+    "characteristic_values = con.execute(\"SELECT DISTINCT percentage_over_100k FROM geo_data\").fetchall()\n",
+    "\n",
+    "values = np.array([v[0] for v in characteristic_values])\n",
+    "\n",
+    "# Compute Jenks breaks\n",
+    "num_classes = 5\n",
+    "breaks = jenkspy.jenks_breaks(values, n_classes=num_classes)\n",
+    "\n",
+    "# Create a bin range mapping: (lower, upper) for each bin\n",
+    "bin_ranges = [(breaks[i], breaks[i+1]) for i in range(len(breaks)-1)]\n",
+    "\n",
+    "# Create a function to get the range string for a value\n",
+    "def jenks_range(value) -> str:\n",
+    "    for i, (low, high) in enumerate(bin_ranges):\n",
+    "        if low <= value <= high:\n",
+    "            return f\"{int(low)}-{int(high)}\"\n",
+    "    return \"unknown\"\n",
+    "\n",
+    "\n",
+    "characteristic_df = gpd.read_parquet('./da_2021_characteristic.parquet')\n",
+    "characteristic_df['category'] = characteristic_df[\"percentage_over_100k\"].apply(lambda v: jenks_range(v))\n",
+    "characteristic_df['category'] = characteristic_df['category'].astype('category')\n",
+    "\n",
+    "# Categories to colors\n",
+    "cmap = {}\n",
+    "colors = [\n",
+    "    [255, 255, 255],\n",
+    "    [255, 191.25, 191.25],\n",
+    "    [255, 127.50, 127.50],\n",
+    "    [255, 63.75, 63.75],\n",
+    "    [255, 0, 0]\n",
+    "]\n",
+    "for index, value in enumerate(sorted(characteristic_df['category'].unique(), key=lambda x: int(x.split('-')[0]))):\n",
+    "    cmap[value] = colors[index]\n",
+    "\n",
+    "\n",
+    "get_color = apply_categorical_cmap(pa.array(characteristic_df['category']), cmap)\n",
+    "\n",
+    "cop_layer = PolygonLayer.from_geopandas(gdf=characteristic_df,\n",
+    "                                        stroked=True,\n",
+    "                                        get_fill_color=get_color,\n",
+    "                                        get_line_color=[255, 255, 255],\n",
+    "                                        get_line_width=5,\n",
+    "                                        line_width_min_pixels=0.2,\n",
+    "                                        line_width_units=\"meters\",\n",
+    "                                        opacity=0.4,\n",
+    "                                        auto_highlight = True\n",
+    "                                       )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "f4e168c8-ec3b-43db-a599-e4d0b01231a4",
+   "metadata": {},
    "outputs": [
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "2ce00adb4a304296996a446110f56863",
+       "model_id": "d556516d41394e13a62696c52bd6b32d",
        "version_major": 2,
        "version_minor": 1
       },
@@ -195,7 +307,7 @@
        "Map(custom_attribution='', layers=(BitmapTileLayer(data='http://mt0.google.com/vt/lyrs=s&hl=en&x={x}&y={y}&z={…"
       ]
      },
-     "execution_count": 12,
+     "execution_count": 16,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -209,7 +321,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "d359f0cf-4c05-4fca-9176-709cd5ff977e",
+   "id": "6ca88dbe-44de-408f-a791-4acb039758b0",
    "metadata": {},
    "outputs": [],
    "source": []