Osier chapter

.github/workflows/CI.yml

@@ -27,7 +27,7 @@ jobs:
     steps:
       # Checkout the repository
       - name: Checkout repository
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
 
       - name: Create environment with Mamba
         uses: conda-incubator/setup-miniconda@v2
@@ -82,7 +82,7 @@ jobs:
 
       # Upload the generated PDF as an artifact
       - name: Upload PDF artifact
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         with:
           name: 2025-dotson-thesis
           path: docs/2025-dotson-thesis.pdf

.gitignore

@@ -35,3 +35,4 @@ data/benchmark/data/*
 docs/_minted-thesis
 pres/_minted-arfc-pres
 _minted-*
+figure-log.txt

README.md

@@ -48,6 +48,14 @@ cd analysis
 snakemake --cores=1
 ```
 
+> [!NOTE]
+> _Why use `snakemake` to build the dissertation when there is already a `Make` file in the `docs` directory?_
+> 
+> Primarily because Windows _can't execute `make`_. There are additional
+> advantages as well. `snakemake` is arguably easier to understand and produces
+> a nice DAG model of the workflow itself.
+>  
+
 # Compiling the dissertation
 
 If you only want to reproduce the document itself without running any analysis,

analysis/Snakefile

@@ -8,6 +8,7 @@ latexopt = """
             """
 
 docs_path = "../docs/"
+figure_log = "figures.log"
 
 with open(f"{docs_path}Makefile", "r") as file:
     lines = file.readlines()
@@ -18,16 +19,35 @@ output_name = lines[0].strip('\n').replace(' ', '').split('=')[-1]
 rule targets:
     input:
         thesis = f"{docs_path}{output_name}.pdf",
-        dag = "dag.png"
+        dag = "dag.png",
+
+rule collect_figures:
+    input:
+        social_max_plot = f"{docs_path}figures/social_max.pgf",
+        elasticity_plot = f"{docs_path}figures/elasticity.pgf",
+        example_pareto_plot = f"{docs_path}figures/truss2d_pareto.pgf",
+        near_optimal_plot = f"{docs_path}figures/near-optimal-pareto.pgf",
+        interior_points_plot = f"{docs_path}figures/nd-mga-paretofront.pgf",
+        pareto_3d = f"{docs_path}figures/3d-mga-paretofront.pgf",
+        example_mga_plot = f"{docs_path}figures/mga-fft-example.pgf",
+    output:
+        log = figure_log
+    shell:
+        """
+        for file in {input}; do
+            echo $file >> {output.log}
+        done
+        """
 
 if sys.platform == 'Windows':
     rule build_thesis:
         input: 
-            main_tex = f"{docs_path}{output_name}.tex"
+            main_tex = f"{docs_path}{output_name}.tex",
+            log = figure_log
         output: f"{docs_path}{output_name}.pdf"
         shell:
             f"""
-            cd ../docs && \
+            cd {docs_path} && \
             pdflatex {latexopt} {output_name}.tex && \
             biber {output_name} && \
             pdflatex {latexopt} {output_name}.tex && \
@@ -36,7 +56,8 @@ if sys.platform == 'Windows':
 elif sys.platform in ['darwin', 'linux']:
     rule build_thesis:
         input: 
-            main_tex = f"{docs_path}{output_name}.tex"
+            main_tex = f"{docs_path}{output_name}.tex",
+            log = figure_log
         output: f"{docs_path}{output_name}.pdf"
         shell:
             f"""
@@ -48,4 +69,35 @@ rule build_dag:
     output:
         "dag.png"
     shell:
-        "snakemake --dag | dot -Tpng > {output}"
+        "snakemake --dag | dot -Tpng > {output}"
+
+
+rule plot_social_welfare_max:
+    input: "scripts/social_welfare_maximization.py"
+    output: 
+        social_max_plot = f"{docs_path}figures/social_max.pgf",
+        elasticity_plot = f"{docs_path}figures/elasticity.pgf"
+    script: f"{input}"
+
+
+rule plot_example_fronts:
+    input: "scripts/pareto_front.py"
+    output:
+        example_pareto_plot = f"{docs_path}figures/truss2d_pareto.pgf",
+        interior_points_plot = f"{docs_path}figures/nd-mga-paretofront.pgf",
+        near_optimal_plot = f"{docs_path}figures/near-optimal-pareto.pgf"
+    script: f"{input}"
+
+
+rule plot_mga_example:
+    input: "scripts/mga_fft_example.py"
+    output:
+        example_mga_plot = f"{docs_path}figures/mga-fft-example.pgf",
+    script: f"{input}"
+
+
+rule plot_3d_fronts:
+    input: "scripts/pareto_3D.py"
+    output:
+        pareto_3d = f"{docs_path}figures/3d-mga-paretofront.pgf"
+    script: f"{input}"

analysis/notebooks/energy-justice.ipynb

@@ -0,0 +1,196 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import requests\n",
+    "import matplotlib.pyplot as plt\n",
+    "import json\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import geopandas as gpd\n",
+    "import us\n",
+    "import os\n",
+    "from dotenv import load_dotenv\n",
+    "\n",
+    "load_dotenv(\"../../.env\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "eia_key = os.environ['EIA_API_KEY']"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Access power plant data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "params =  {\n",
+    "    \"frequency\": \"monthly\",\n",
+    "    \"data\": [\n",
+    "        \"latitude\",\n",
+    "        \"longitude\",\n",
+    "        \"nameplate-capacity-mw\",\n",
+    "        \"operating-year-month\"\n",
+    "    ],\n",
+    "    \"facets\": {\n",
+    "        \"energy_source_code\": [\n",
+    "            \"BIT\",\n",
+    "            \"SUB\"\n",
+    "        ]\n",
+    "    },\n",
+    "    \"start\": \"2024-09\",\n",
+    "    \"end\": None,\n",
+    "    \"sort\": [\n",
+    "        {\n",
+    "            \"column\": \"period\",\n",
+    "            \"direction\": \"desc\"\n",
+    "        }\n",
+    "    ],\n",
+    "    \"offset\": 0,\n",
+    "    \"length\": 5000\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "BASE_URL = \"https://api.eia.gov/v2/\"\n",
+    "\n",
+    "dataset = \"electricity/operating-generator-capacity\"\n",
+    "route = dataset + \"/data\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "headers = {\n",
+    "            \"X-Api-Key\": eia_key,\n",
+    "            \"X-Params\": json.dumps(params),\n",
+    "        }"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "r = requests.get(BASE_URL+route, headers=headers)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Total records: 428\n"
+     ]
+    }
+   ],
+   "source": [
+    "response = r.json()['response']\n",
+    "\n",
+    "print(f\"Total records: {response['total']}\")\n",
+    "\n",
+    "data = response['data']\n",
+    "\n",
+    "df = pd.DataFrame(data)\n",
+    "df.drop(columns=['stateName','sector','sectorName','entityid',\n",
+    "                    'balancing-authority-name','statusDescription', \n",
+    "                    'entityName','nameplate-capacity-mw-units',\n",
+    "                    'energy_source_code','generatorid','status',\n",
+    "                    'unit', 'period'\n",
+    "                    ],\n",
+    "        inplace=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df['nameplate-capacity-mw'] = df['nameplate-capacity-mw'].astype('float')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = df.pivot_table(index=['stateid','plantid','balancing_authority_code','latitude','longitude'],\n",
+    "               columns=['technology'],\n",
+    "               values=['nameplate-capacity-mw']).reset_index(drop=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "thesis",
+   "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": "3.11.10"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}