cool stuff for the paper!

initial_view/secondtake.ipynb

@@ -2,12 +2,8 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "vscode": {
-     "languageId": "plaintext"
-    }
-   },
+   "execution_count": 1,
+   "metadata": {},
    "outputs": [],
    "source": [
     "# Project: California Equity Research\n",
@@ -15,37 +11,92 @@
     "#### Goal: Analyze the relationship between climate investment and environmental justice in California\n",
     "#### This notebook: second take \n",
     "##### Author: [dpadams](dpadams@fullerton.edu)\n",
-    "##### Date: 2024-10.11"
+    "##### Date: 2024-11-24"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "vscode": {
-     "languageId": "plaintext"
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "ModuleNotFoundError",
+     "evalue": "No module named 'scipy'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mModuleNotFoundError\u001b[0m                       Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[2], line 5\u001b[0m\n\u001b[1;32m      3\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mmatplotlib\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpyplot\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m \u001b[38;5;21;01mplt\u001b[39;00m\n\u001b[1;32m      4\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mseaborn\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m \u001b[38;5;21;01msns\u001b[39;00m\n\u001b[0;32m----> 5\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mscipy\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m stats\n\u001b[1;32m      7\u001b[0m \u001b[38;5;66;03m# Read the data (I see you already have this loaded as 'data')\u001b[39;00m\n\u001b[1;32m      8\u001b[0m \n\u001b[1;32m      9\u001b[0m \u001b[38;5;66;03m# 1. First, let's create our core analytical metrics\u001b[39;00m\n\u001b[1;32m     10\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mcalculate_program_metrics\u001b[39m(df):\n",
+      "\u001b[0;31mModuleNotFoundError\u001b[0m: No module named 'scipy'"
+     ]
     }
-   },
-   "outputs": [],
+   ],
    "source": [
-    "# set working directory as ~/home/dadams/repos/california_equity_git/\n"
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "import seaborn as sns\n",
+    "from scipy import stats\n",
+    "\n",
+    "# Read the data (I see you already have this loaded as 'data')\n",
+    "\n",
+    "# 1. First, let's create our core analytical metrics\n",
+    "def calculate_program_metrics(df):\n",
+    "    metrics = df.groupby('Program Name').agg({\n",
+    "        'Total Project Cost': ['count', 'sum', 'mean'],\n",
+    "        'Total Project GHGReductions': ['sum', 'mean'],\n",
+    "        'Total GGRFDisadvantaged Community Funding': ['sum', 'mean'],\n",
+    "        'Is Benefit Disadvantaged Communities': 'mean',\n",
+    "        'Is Low Income Communities': 'mean'\n",
+    "    }).round(2)\n",
+    "    \n",
+    "    # Add efficiency metrics\n",
+    "    metrics['GHG_per_dollar'] = (metrics[('Total Project GHGReductions', 'sum')] / \n",
+    "                                metrics[('Total Project Cost', 'sum')]).round(4)\n",
+    "    \n",
+    "    metrics['DAC_funding_ratio'] = (metrics[('Total GGRFDisadvantaged Community Funding', 'sum')] / \n",
+    "                                   metrics[('Total Project Cost', 'sum')]).round(4)\n",
+    "    \n",
+    "    return metrics\n",
+    "\n",
+    "program_metrics = calculate_program_metrics(data)\n",
+    "\n",
+    "# Display top programs by different metrics\n",
+    "print(\"\\nTop 5 Programs by Total Investment:\")\n",
+    "print(program_metrics.sort_values(('Total Project Cost', 'sum'), ascending=False).head())\n",
+    "\n",
+    "print(\"\\nTop 5 Programs by GHG Reduction Efficiency:\")\n",
+    "print(program_metrics.sort_values('GHG_per_dollar', ascending=False).head())\n",
+    "\n",
+    "print(\"\\nTop 5 Programs by DAC Funding Ratio:\")\n",
+    "print(program_metrics.sort_values('DAC_funding_ratio', ascending=False).head())"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {
-    "vscode": {
-     "languageId": "plaintext"
-    }
-   },
+   "metadata": {},
    "outputs": [],
    "source": []
   }
  ],
  "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
   "language_info": {
-   "name": "python"
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.6"
   }
  },
  "nbformat": 4,