Add notebook demonstrating how to add polygons to the database

notebooks/WritePolygonstoDB.ipynb

@@ -0,0 +1,140 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "01363705-ba78-40ce-a70d-6c519d94ddaa",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "# These are the default AWS configurations for the Analysis Sandbox.\n",
+    "# that are set in the environmnet variables. \n",
+    "aws_default_config = {\n",
+    "    #'AWS_NO_SIGN_REQUEST': 'YES', \n",
+    "    'AWS_SECRET_ACCESS_KEY': 'fake',\n",
+    "    'AWS_ACCESS_KEY_ID': 'fake',\n",
+    "}\n",
+    "\n",
+    "# To access public bucket, need to remove the AWS credentials in \n",
+    "# the environment variables or the following error will occur.\n",
+    "# PermissionError: The AWS Access Key Id you provided does not exist in our records.\n",
+    "\n",
+    "for key in aws_default_config.keys():\n",
+    "    if key in os.environ:\n",
+    "        del os.environ[key]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f5f80385-ffe6-4508-b11a-bd1e13671585",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sqlalchemy import create_engine\n",
+    "import deafrica_conflux.db\n",
+    "from deafrica_conflux.cli.logs import logging_setup\n",
+    "import geopandas as gpd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "22f27ebd-4c23-44d1-9c3f-de88302a30f4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Set up logger.\n",
+    "logging_setup(1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c14c5a92-de32-4545-8cd1-c7714fdc3727",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Get the engine\n",
+    "username = \"waterbodies_writer\"\n",
+    "password = \"xxxx\"\n",
+    "host = \"db-writer\"\n",
+    "port =  5432\n",
+    "database_name = \"waterbodies\"\n",
+    "\n",
+    "# identifying name of the SQLAlchemy dialect\n",
+    "dialect = \"postgresql\"\n",
+    "# name of the DBAPI to be used to connect to the database\n",
+    "driver = \"psycopg2\"\n",
+    "# dialect+driver://username:password@host:port/database\n",
+    "database_url = f\"{dialect}+{driver}://{username}:{password}@{host}:{port}/{database_name}\"\n",
+    "engine = create_engine(database_url, future=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "addfece4-625f-437a-8e15-fcc50b7eaaa2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "deafrica_conflux.db.add_waterbody_polygons_to_db(\n",
+    "    engine=engine,\n",
+    "    drop_table=False,\n",
+    "    update_rows=True,\n",
+    "    waterbodies_polygons_fp=\"s3://deafrica-waterbodies-dev/waterbodies/v0.0.2/senegal_basin/historical_extent/waterbodies.parquet\",\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c6100db6-975c-4b88-97fe-6ab3cc63ea56",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%%time\n",
+    "# Define your SQL query\n",
+    "sql_query = \"SELECT * FROM waterbodies\"\n",
+    "\n",
+    "# Load GeoDataFrame from SQL database\n",
+    "waterbodies = gpd.read_postgis(sql_query, con=engine, geom_col=\"geometry\")\n",
+    "\n",
+    "# Print the GeoDataFrame\n",
+    "len(waterbodies)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "015f870a-e65d-42eb-9b62-0acb56fe4753",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "waterbodies"
+   ]
+  }
+ ],
+ "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": "3.10.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}