{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# calif equity\n",
    "## Looking at collaboration components \n",
    "Date: 2024-12-19"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": [
    "# Importing the necessary libraries\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "import os"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": [
    "## set directory\n",
    "import os\n",
    "os.chdir('/home/dadams/Repos/california_equity_git')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": [
    "data = pd.read_csv('data_raw/cci_programs_data.csv', low_memory=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": [
    "data.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": [
    "import geopandas as gpd\n",
    "\n",
    "# Load the shapefile\n",
    "shapefile_path = '/home/dadams/Repos/california_equity_git/california_enviroscreen/calif_enviroscreen_shape/CES4 Final Shapefile.shp'\n",
    "gdf = gpd.read_file(shapefile_path)\n",
    "\n",
    "# Print the head of the GeoDataFrame\n",
    "print(gdf.head())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "# Basic cleaning\n",
    "data['Date Operational'] = pd.to_datetime(data['Date Operational'])\n",
    "data = data[\n",
    "    (data['Date Operational'] >= '2010-01-01') & \n",
    "    (data['Date Operational'] <= '2024-11-01')\n",
    "].copy()\n",
    "\n",
    "# Remove rows with no GGRF funding\n",
    "data = data.dropna(subset=['Total Program GGRFFunding'])\n",
    "\n",
    "# Add derived columns\n",
    "data['Year'] = data['Date Operational'].dt.year\n",
    "data['is_multi_county'] = data['County'].str.contains(',', na=False)\n",
    "data['partnership_size'] = data['County'].str.count(',').fillna(0) + 1\n",
    "\n",
    "# Quick validation\n",
    "print(f\"Total GGRF Funding: ${data['Total Program GGRFFunding'].sum()/1e9:.2f}B\")\n",
    "print(f\"Number of projects: {len(data)}\")"
   ]
  }
 ],
 "metadata": {
  "language_info": {
   "name": "python"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}