personal-portfolio/notebooks/demographics/age_distribution.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Age Distribution Analysis\n",
    "\n",
    "Compares median age and age index across Toronto neighbourhoods."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 1. Data Reference\n",
    "\n",
    "### Source Tables\n",
    "\n",
    "| Table | Grain | Key Columns |\n",
    "|-------|-------|-------------|\n",
    "| `mart_neighbourhood_demographics` | neighbourhood \u00d7 year | median_age, age_index, city_avg_age |\n",
    "\n",
    "### SQL Query"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "from sqlalchemy import create_engine\n",
    "from dotenv import load_dotenv\n",
    "import os\n",
    "\n",
    "# Load .env from project root\n",
    "load_dotenv('../../.env')\n",
    "\n",
    "engine = create_engine(os.environ.get('DATABASE_URL'))\n",
    "\n",
    "query = \"\"\"\n",
    "SELECT\n",
    "    neighbourhood_name,\n",
    "    median_age,\n",
    "    age_index,\n",
    "    city_avg_age,\n",
    "    population,\n",
    "    income_quintile,\n",
    "    pct_renter_occupied\n",
    "FROM public_marts.mart_neighbourhood_demographics\n",
    "WHERE year = (SELECT MAX(year) FROM public_marts.mart_neighbourhood_demographics)\n",
    "  AND median_age IS NOT NULL\n",
    "ORDER BY median_age DESC\n",
    "\"\"\"\n",
    "\n",
    "df = pd.read_sql(query, engine)\n",
    "print(f\"Loaded {len(df)} neighbourhoods with age data\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Transformation Steps\n",
    "\n",
    "1. Filter to most recent census year\n",
    "2. Calculate deviation from city average\n",
    "3. Classify as younger/older than average"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "city_avg = df['city_avg_age'].iloc[0]\n",
    "df['age_category'] = df['median_age'].apply(\n",
    "    lambda x: 'Younger' if x < city_avg else 'Older'\n",
    ")\n",
    "df['age_deviation'] = df['median_age'] - city_avg\n",
    "\n",
    "data = df.to_dict('records')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Sample Output"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(f\"City Average Age: {city_avg:.1f}\")\n",
    "print(\"\\nYoungest Neighbourhoods:\")\n",
    "display(df.tail(5)[['neighbourhood_name', 'median_age', 'age_index', 'pct_renter_occupied']])\n",
    "print(\"\\nOldest Neighbourhoods:\")\n",
    "display(df.head(5)[['neighbourhood_name', 'median_age', 'age_index', 'pct_renter_occupied']])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 2. Data Visualization\n",
    "\n",
    "### Figure Factory\n",
    "\n",
    "Uses `create_ranking_bar` from `portfolio_app.figures.bar_charts`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import sys\n",
    "sys.path.insert(0, '../..')\n",
    "\n",
    "from portfolio_app.figures.bar_charts import create_ranking_bar\n",
    "\n",
    "fig = create_ranking_bar(\n",
    "    data=data,\n",
    "    name_column='neighbourhood_name',\n",
    "    value_column='median_age',\n",
    "    title='Youngest & Oldest Neighbourhoods (Median Age)',\n",
    "    top_n=10,\n",
    "    bottom_n=10,\n",
    "    color_top='#FF9800',  # Orange for older\n",
    "    color_bottom='#2196F3',  # Blue for younger\n",
    "    value_format='.1f',\n",
    ")\n",
    "\n",
    "fig.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Age vs Income Correlation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Age by income quintile\n",
    "print(\"Median Age by Income Quintile:\")\n",
    "df.groupby('income_quintile')['median_age'].mean().round(1)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "name": "python",
   "version": "3.11.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}