feat: create notebook exporting information in EIA 860 for generators…

… in MISO footprint

notebooks/explore_data/export_eia860.ipynb

@@ -0,0 +1,222 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Export EIA 860"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "from oge.load_data import load_pudl_table"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Load data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gens_eia860 = load_pudl_table(\"core_eia860__scd_generators\")\n",
+    "plants_eia860 = load_pudl_table(\"core_eia860__scd_plants\")\n",
+    "plants_entity = load_pudl_table(\"core_eia__entity_plants\")\n",
+    "generators_entity = load_pudl_table(\"core_eia__entity_generators\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Merge data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "eia_gens = gens_eia860.merge(\n",
+    "    plants_eia860,\n",
+    "    how=\"left\",\n",
+    "    on=[\"report_date\", \"plant_id_eia\"],\n",
+    "    suffixes=(None, \"_remove\"),\n",
+    "    validate=\"m:1\",\n",
+    ")\n",
+    "\n",
+    "eia_gens = eia_gens.merge(\n",
+    "    generators_entity,\n",
+    "    how=\"left\",\n",
+    "    on=[\"plant_id_eia\", \"generator_id\"],\n",
+    "    suffixes=(None, \"_remove\"),\n",
+    "    validate=\"m:1\",\n",
+    ")\n",
+    "\n",
+    "eia_gens = eia_gens.merge(\n",
+    "    plants_entity,\n",
+    "    how=\"left\",\n",
+    "    on=[\"plant_id_eia\"],\n",
+    "    suffixes=(None, \"_remove\"),\n",
+    "    validate=\"m:1\",\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Keep only the most recent entry for each generator"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "eia_gens = eia_gens.sort_values(\n",
+    "    by=[\"plant_id_eia\", \"generator_id\", \"report_date\"], ascending=True\n",
+    ")\n",
+    "eia_gens = eia_gens.drop_duplicates(\n",
+    "    subset=[\"plant_id_eia\", \"generator_id\"], keep=\"last\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Remove duplicate columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "eia_gens = eia_gens[[col for col in eia_gens.columns if \"_remove\" not in col]]\n",
+    "eia_gens = eia_gens[\n",
+    "    [\n",
+    "        \"plant_id_eia\",\n",
+    "        \"plant_name_eia\",\n",
+    "        \"generator_id\",\n",
+    "        \"report_date\",\n",
+    "        \"rto_iso_lmp_node_id\",\n",
+    "        \"transmission_distribution_owner_name\",\n",
+    "        \"transmission_distribution_owner_state\",\n",
+    "        \"balancing_authority_code_eia\",\n",
+    "        \"balancing_authority_name_eia\",\n",
+    "        \"iso_rto_code\",\n",
+    "        \"nerc_region\",\n",
+    "        \"latitude\",\n",
+    "        \"longitude\",\n",
+    "        \"street_address\",\n",
+    "        \"city\",\n",
+    "        \"county\",\n",
+    "        \"state\",\n",
+    "        \"zip_code\",\n",
+    "        \"capacity_mw\",\n",
+    "        \"grid_voltage_1_kv\",\n",
+    "        \"prime_mover_code\",\n",
+    "        \"energy_source_code_1\",\n",
+    "        \"energy_source_code_2\",\n",
+    "        \"multiple_fuels\",\n",
+    "        \"cofire_fuels\",\n",
+    "        \"switch_oil_gas\",\n",
+    "        \"energy_storage\",\n",
+    "        \"generator_operating_date\",\n",
+    "        \"current_planned_generator_operating_date\",\n",
+    "        \"operational_status\",\n",
+    "        \"generator_retirement_date\",\n",
+    "    ]\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Keep only states in MISO footprint"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "states_to_remove = [\n",
+    "    \"AK\",\n",
+    "    \"HI\",\n",
+    "    \"WA\",\n",
+    "    \"OR\",\n",
+    "    \"CA\",\n",
+    "    \"ID\",\n",
+    "    \"NV\",\n",
+    "    \"AZ\",\n",
+    "    \"UT\",\n",
+    "    \"WY\",\n",
+    "    \"CO\",\n",
+    "    \"ME\",\n",
+    "    \"NH\",\n",
+    "    \"RI\",\n",
+    "]\n",
+    "\n",
+    "# to filter this a bit, get rid of generators in WECC, Texas, Alaska, and Hawaii\n",
+    "eia_gens = eia_gens[~eia_gens[\"state\"].isin([\"UNK\", \"TRE\", \"WECC\"])]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Export file"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "eia_gens.to_csv(\"~/Desktop/eia860_export.csv\", index=False)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "open-grid-emissions-zm3GQQDc",
+   "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": "3.11.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}