07-visualizing-geospatial-data

notebooks/07-visualizing-geospatial-data.ipynb

@@ -0,0 +1,145 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "77527494-9ecd-49d4-b5c1-f8c8250124ca",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from bokeh.io import output_notebook\n",
+    "\n",
+    "output_notebook()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1d72683c-156a-45de-b49b-58928549e102",
+   "metadata": {},
+   "source": [
+    "## Data preparation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2f54b495-5d47-433e-8d96-ae0241a02296",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "file = \"../data/csv_files/US_census.csv\"\n",
+    "df = pd.read_csv(file)\n",
+    "\n",
+    "new_df = df.groupby(\"state\", as_index=False).agg(\n",
+    "    income=(\"median_household_income\", \"mean\"), density=(\"density\", \"mean\")\n",
+    ")\n",
+    "\n",
+    "bins = [-1, 39_000, 50_000, 60_000, 70_000, 100_000]\n",
+    "labels = [\"<$40k\", \"$40k-$50k\", \"$50k-$60k\", \"$60k-$70k\", \">$70k\"]\n",
+    "colors = [\"#f1e0e3\", \"#d8bbc4\", \"#ba93ab\", \"#966B93\", \"#6B467A\"]\n",
+    "\n",
+    "new_df[\"income_range\"] = pd.cut(new_df[\"income\"], bins=bins, labels=labels, right=False)\n",
+    "new_df[\"colors\"] = pd.cut(new_df[\"income\"], bins=bins, labels=colors, right=False)\n",
+    "\n",
+    "new_df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fbe81a2c-ee20-49c8-8035-1111150853e5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from bokeh.sampledata.us_states import data\n",
+    "\n",
+    "us_df = (\n",
+    "    pd.DataFrame(data)\n",
+    "    .T.loc[lambda df: ~df[\"name\"].isin([\"Alaska\", \"Hawaii\"])]\n",
+    "    .reset_index(drop=True)\n",
+    "    .rename(columns={\"name\": \"state\"})\n",
+    "    .drop(columns=\"region\")\n",
+    ")\n",
+    "\n",
+    "us_df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ecbc44a5-7a59-4c43-8e86-872ad604cb5f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "plot_df = new_df.merge(us_df, on=\"state\")\n",
+    "plot_df.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d733ec5e-74c9-48ee-b346-42fedf219ea1",
+   "metadata": {},
+   "source": [
+    "## Plotting"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0efc3827-9ad7-4ff0-a771-6b77f9f215cf",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from bokeh.models import ColumnDataSource\n",
+    "from bokeh.plotting import figure, show\n",
+    "\n",
+    "source = ColumnDataSource(data=plot_df)\n",
+    "\n",
+    "p = figure(\n",
+    "    width=900,\n",
+    "    height=600,\n",
+    "    tooltips=[(\"State\", \"@state\"), (\"Average income\", \"@income_range\")],\n",
+    ")\n",
+    "\n",
+    "p.patches(\n",
+    "    \"lons\",\n",
+    "    \"lats\",\n",
+    "    fill_color=\"colors\",\n",
+    "    line_color=\"black\",\n",
+    "    legend_field=\"income_range\",\n",
+    "    source=source,\n",
+    ")\n",
+    "\n",
+    "p.yaxis.visible = False\n",
+    "p.xaxis.visible = False\n",
+    "p.grid.grid_line_color = None\n",
+    "p.legend.location = \"bottom_left\"\n",
+    "\n",
+    "show(p)"
+   ]
+  }
+ ],
+ "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": "3.10.11"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}