{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# USGS Data Loading "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Import the libraries and USGS TEEHR module."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from datetime import datetime\n",
    "from pathlib import Path\n",
    "\n",
    "from teehr.loading.usgs.usgs import usgs_to_parquet"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Define the input parameters."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "OUTPUT_ROOT = Path(Path().home(), \"temp\")\n",
    "OUTPUT_DIR = Path(OUTPUT_ROOT, \"usgs\")\n",
    "\n",
    "START_DATE = datetime(2023, 2, 20)\n",
    "END_DATE = datetime(2023, 3, 25)\n",
    "CHUNK_BY = \"month\"\n",
    "OVERWRITE = True\n",
    "\n",
    "SITES = [\n",
    "        \"02449838\",\n",
    "        \"02450825\"\n",
    "]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Fetch and load the data."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "usgs_to_parquet(\n",
    "    sites=SITES,\n",
    "    start_date=START_DATE,\n",
    "    end_date=END_DATE,\n",
    "    output_parquet_dir=OUTPUT_DIR,\n",
    "    chunk_by=CHUNK_BY,\n",
    "    overwrite_output=OVERWRITE\n",
    ")"
   ]
  }
 ],
 "metadata": {
  "language_info": {
   "name": "python"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}