{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "63b4b4b5",
   "metadata": {},
   "source": [
    "<div style=\"background-color:#000;\"><img src=\"pqn.png\"></img></div>"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "89c213c7",
   "metadata": {},
   "source": [
    "## Load financial data, perform factor analysis, and optimize portfolio"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2c15281f",
   "metadata": {},
   "source": [
    "This code loads historical financial data for selected assets and factors. It calculates daily returns and performs factor analysis using principal component regression. The portfolio is optimized using the `riskfolio-lib` library, incorporating the factor loadings. The objective is to maximize the Sharpe ratio while minimizing variance. Finally, it visualizes the optimized portfolio weights in a pie chart."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "0015b086",
   "metadata": {},
   "outputs": [],
   "source": [
    "import yfinance as yf\n",
    "import riskfolio as rf\n",
    "import pandas as pd\n",
    "import warnings\n",
    "pd.options.display.float_format = \"{:.4%}\".format\n",
    "warnings.filterwarnings(\"ignore\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f8c086a1",
   "metadata": {},
   "source": [
    "Define the list of assets in the portfolio"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "fe06a269",
   "metadata": {},
   "outputs": [],
   "source": [
    "mag_7 = [\n",
    "    \"AMZN\",\n",
    "    \"AAPL\",\n",
    "    \"NVDA\",\n",
    "    \"META\",\n",
    "    \"TSLA\",\n",
    "    \"MSFT\",\n",
    "    \"GOOG\",\n",
    "]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ae283cbf",
   "metadata": {},
   "source": [
    "Define the list of factor indices"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "55060d5e",
   "metadata": {},
   "outputs": [],
   "source": [
    "factors = [\"MTUM\", \"QUAL\", \"VLUE\", \"SIZE\", \"USMV\"]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "454eaad5",
   "metadata": {},
   "source": [
    "Define the date range for historical data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "52b422ae",
   "metadata": {},
   "outputs": [],
   "source": [
    "start = \"2020-01-01\"\n",
    "end = \"2024-07-31\""
   ]
  },
  {
   "cell_type": "markdown",
   "id": "563e78fd",
   "metadata": {},
   "source": [
    "Download the historical adjusted close price data for the assets"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "9f8f17a5",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[*********************100%%**********************]  7 of 7 completed\n"
     ]
    }
   ],
   "source": [
    "port_returns = (\n",
    "    yf\n",
    "    .download(\n",
    "        mag_7, \n",
    "        start=start, \n",
    "        end=end\n",
    "    )[\"Adj Close\"]\n",
    "    .pct_change()\n",
    "    .dropna()\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1e72633f",
   "metadata": {},
   "source": [
    "Download the historical adjusted close price data for the factors"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "5c3e89a6",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[*********************100%%**********************]  5 of 5 completed\n"
     ]
    }
   ],
   "source": [
    "factor_returns = (\n",
    "    yf\n",
    "    .download(\n",
    "        factors, \n",
    "        start=start, \n",
    "        end=end\n",
    "    )[\"Adj Close\"]\n",
    "    .pct_change()\n",
    "    .dropna()\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c4793efa",
   "metadata": {},
   "source": [
    "Initialize the Portfolio object with the asset returns data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "5e59c2c6",
   "metadata": {},
   "outputs": [],
   "source": [
    "port = rf.Portfolio(returns=port_returns)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "884c3ab1",
   "metadata": {},
   "source": [
    "Compute historical mean returns and covariance matrix using the Ledoit-Wolf shrinkage method"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "b0f678d4",
   "metadata": {},
   "outputs": [],
   "source": [
    "port.assets_stats(method_mu=\"hist\", method_cov=\"ledoit\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "41f5be20",
   "metadata": {},
   "source": [
    "Set the lower return constraint for the portfolio optimization"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "744d8d78",
   "metadata": {},
   "outputs": [],
   "source": [
    "port.lowerret = 0.00056488 * 1.5"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5a7015cc",
   "metadata": {},
   "source": [
    "Compute the loadings matrix using principal component regression on factor returns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "9eddcb56",
   "metadata": {},
   "outputs": [],
   "source": [
    "loadings = rf.loadings_matrix(\n",
    "    X=factor_returns,\n",
    "    Y=port_returns, \n",
    "    feature_selection=\"PCR\",\n",
    "    n_components=0.95\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ee20362f",
   "metadata": {},
   "source": [
    "Display the loadings matrix with a background gradient color mapping"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "63cb59c6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style type=\"text/css\">\n",
       "#T_f520b_row0_col0 {\n",
       "  background-color: #e44c34;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "#T_f520b_row0_col1 {\n",
       "  background-color: #e75337;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "#T_f520b_row0_col2 {\n",
       "  background-color: #e24731;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "#T_f520b_row0_col3 {\n",
       "  background-color: #5ab760;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "#T_f520b_row0_col4 {\n",
       "  background-color: #219c52;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "#T_f520b_row0_col5 {\n",
       "  background-color: #4eb15d;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "#T_f520b_row1_col0, #T_f520b_row1_col4, #T_f520b_row2_col1, #T_f520b_row2_col2, #T_f520b_row5_col3, #T_f520b_row5_col5 {\n",
       "  background-color: #a50026;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "#T_f520b_row1_col1, #T_f520b_row3_col2 {\n",
       "  background-color: #fba35c;\n",
       "  color: #000000;\n",
       "}\n",
       "#T_f520b_row1_col2 {\n",
       "  background-color: #a90426;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "#T_f520b_row1_col3 {\n",
       "  background-color: #fa9857;\n",
       "  color: #000000;\n",
       "}\n",
       "#T_f520b_row1_col5 {\n",
       "  background-color: #f5fbb2;\n",
       "  color: #000000;\n",
       "}\n",
       "#T_f520b_row2_col0, #T_f520b_row3_col0 {\n",
       "  background-color: #d22b27;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "#T_f520b_row2_col3, #T_f520b_row2_col4, #T_f520b_row2_col5, #T_f520b_row5_col0, #T_f520b_row5_col1, #T_f520b_row5_col2 {\n",
       "  background-color: #006837;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "#T_f520b_row3_col1 {\n",
       "  background-color: #fb9d59;\n",
       "  color: #000000;\n",
       "}\n",
       "#T_f520b_row3_col3 {\n",
       "  background-color: #8ecf67;\n",
       "  color: #000000;\n",
       "}\n",
       "#T_f520b_row3_col4 {\n",
       "  background-color: #118848;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "#T_f520b_row3_col5 {\n",
       "  background-color: #93d168;\n",
       "  color: #000000;\n",
       "}\n",
       "#T_f520b_row4_col0 {\n",
       "  background-color: #d42d27;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "#T_f520b_row4_col1 {\n",
       "  background-color: #f57547;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "#T_f520b_row4_col2 {\n",
       "  background-color: #e54e35;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "#T_f520b_row4_col3 {\n",
       "  background-color: #addc6f;\n",
       "  color: #000000;\n",
       "}\n",
       "#T_f520b_row4_col4 {\n",
       "  background-color: #96d268;\n",
       "  color: #000000;\n",
       "}\n",
       "#T_f520b_row4_col5 {\n",
       "  background-color: #89cc67;\n",
       "  color: #000000;\n",
       "}\n",
       "#T_f520b_row5_col4 {\n",
       "  background-color: #b3df72;\n",
       "  color: #000000;\n",
       "}\n",
       "#T_f520b_row6_col0 {\n",
       "  background-color: #48ae5c;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "#T_f520b_row6_col1 {\n",
       "  background-color: #4bb05c;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "#T_f520b_row6_col2 {\n",
       "  background-color: #7ac665;\n",
       "  color: #000000;\n",
       "}\n",
       "#T_f520b_row6_col3 {\n",
       "  background-color: #c21c27;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "#T_f520b_row6_col4 {\n",
       "  background-color: #fbfdba;\n",
       "  color: #000000;\n",
       "}\n",
       "#T_f520b_row6_col5 {\n",
       "  background-color: #dd3d2d;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "</style>\n",
       "<table id=\"T_f520b\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th class=\"blank level0\" >&nbsp;</th>\n",
       "      <th id=\"T_f520b_level0_col0\" class=\"col_heading level0 col0\" >const</th>\n",
       "      <th id=\"T_f520b_level0_col1\" class=\"col_heading level0 col1\" >MTUM</th>\n",
       "      <th id=\"T_f520b_level0_col2\" class=\"col_heading level0 col2\" >QUAL</th>\n",
       "      <th id=\"T_f520b_level0_col3\" class=\"col_heading level0 col3\" >SIZE</th>\n",
       "      <th id=\"T_f520b_level0_col4\" class=\"col_heading level0 col4\" >USMV</th>\n",
       "      <th id=\"T_f520b_level0_col5\" class=\"col_heading level0 col5\" >VLUE</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th id=\"T_f520b_level0_row0\" class=\"row_heading level0 row0\" >AAPL</th>\n",
       "      <td id=\"T_f520b_row0_col0\" class=\"data row0 col0\" >0.0006</td>\n",
       "      <td id=\"T_f520b_row0_col1\" class=\"data row0 col1\" >0.6574</td>\n",
       "      <td id=\"T_f520b_row0_col2\" class=\"data row0 col2\" >0.2702</td>\n",
       "      <td id=\"T_f520b_row0_col3\" class=\"data row0 col3\" >0.0832</td>\n",
       "      <td id=\"T_f520b_row0_col4\" class=\"data row0 col4\" >0.1876</td>\n",
       "      <td id=\"T_f520b_row0_col5\" class=\"data row0 col5\" >-0.0609</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_f520b_level0_row1\" class=\"row_heading level0 row1\" >AMZN</th>\n",
       "      <td id=\"T_f520b_row1_col0\" class=\"data row1 col0\" >0.0003</td>\n",
       "      <td id=\"T_f520b_row1_col1\" class=\"data row1 col1\" >0.7814</td>\n",
       "      <td id=\"T_f520b_row1_col2\" class=\"data row1 col2\" >0.2458</td>\n",
       "      <td id=\"T_f520b_row1_col3\" class=\"data row1 col3\" >0.0017</td>\n",
       "      <td id=\"T_f520b_row1_col4\" class=\"data row1 col4\" >0.1140</td>\n",
       "      <td id=\"T_f520b_row1_col5\" class=\"data row1 col5\" >-0.1846</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_f520b_level0_row2\" class=\"row_heading level0 row2\" >GOOG</th>\n",
       "      <td id=\"T_f520b_row2_col0\" class=\"data row2 col0\" >0.0005</td>\n",
       "      <td id=\"T_f520b_row2_col1\" class=\"data row2 col1\" >0.5038</td>\n",
       "      <td id=\"T_f520b_row2_col2\" class=\"data row2 col2\" >0.2437</td>\n",
       "      <td id=\"T_f520b_row2_col3\" class=\"data row2 col3\" >0.1110</td>\n",
       "      <td id=\"T_f520b_row2_col4\" class=\"data row2 col4\" >0.1968</td>\n",
       "      <td id=\"T_f520b_row2_col5\" class=\"data row2 col5\" >0.0079</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_f520b_level0_row3\" class=\"row_heading level0 row3\" >META</th>\n",
       "      <td id=\"T_f520b_row3_col0\" class=\"data row3 col0\" >0.0005</td>\n",
       "      <td id=\"T_f520b_row3_col1\" class=\"data row3 col1\" >0.7736</td>\n",
       "      <td id=\"T_f520b_row3_col2\" class=\"data row3 col2\" >0.2974</td>\n",
       "      <td id=\"T_f520b_row3_col3\" class=\"data row3 col3\" >0.0713</td>\n",
       "      <td id=\"T_f520b_row3_col4\" class=\"data row3 col4\" >0.1910</td>\n",
       "      <td id=\"T_f520b_row3_col5\" class=\"data row3 col5\" >-0.1023</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_f520b_level0_row4\" class=\"row_heading level0 row4\" >MSFT</th>\n",
       "      <td id=\"T_f520b_row4_col0\" class=\"data row4 col0\" >0.0005</td>\n",
       "      <td id=\"T_f520b_row4_col1\" class=\"data row4 col1\" >0.7110</td>\n",
       "      <td id=\"T_f520b_row4_col2\" class=\"data row4 col2\" >0.2721</td>\n",
       "      <td id=\"T_f520b_row4_col3\" class=\"data row4 col3\" >0.0641</td>\n",
       "      <td id=\"T_f520b_row4_col4\" class=\"data row4 col4\" >0.1738</td>\n",
       "      <td id=\"T_f520b_row4_col5\" class=\"data row4 col5\" >-0.0958</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_f520b_level0_row5\" class=\"row_heading level0 row5\" >NVDA</th>\n",
       "      <td id=\"T_f520b_row5_col0\" class=\"data row5 col0\" >0.0022</td>\n",
       "      <td id=\"T_f520b_row5_col1\" class=\"data row5 col1\" >1.4838</td>\n",
       "      <td id=\"T_f520b_row5_col2\" class=\"data row5 col2\" >0.4343</td>\n",
       "      <td id=\"T_f520b_row5_col3\" class=\"data row5 col3\" >-0.0386</td>\n",
       "      <td id=\"T_f520b_row5_col4\" class=\"data row5 col4\" >0.1696</td>\n",
       "      <td id=\"T_f520b_row5_col5\" class=\"data row5 col5\" >-0.3989</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_f520b_level0_row6\" class=\"row_heading level0 row6\" >TSLA</th>\n",
       "      <td id=\"T_f520b_row6_col0\" class=\"data row6 col0\" >0.0019</td>\n",
       "      <td id=\"T_f520b_row6_col1\" class=\"data row6 col1\" >1.3202</td>\n",
       "      <td id=\"T_f520b_row6_col2\" class=\"data row6 col2\" >0.3901</td>\n",
       "      <td id=\"T_f520b_row6_col3\" class=\"data row6 col3\" >-0.0296</td>\n",
       "      <td id=\"T_f520b_row6_col4\" class=\"data row6 col4\" >0.1562</td>\n",
       "      <td id=\"T_f520b_row6_col5\" class=\"data row6 col5\" >-0.3494</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n"
      ],
      "text/plain": [
       "<pandas.io.formats.style.Styler at 0x307ab26b0>"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "loadings.style.format(\"{:.4f}\").background_gradient(cmap='RdYlGn')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "49caab33",
   "metadata": {},
   "source": [
    "Set the factor returns and compute their statistics"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "8e37737c",
   "metadata": {},
   "outputs": [],
   "source": [
    "port.factors = factor_returns\n",
    "port.factors_stats(\n",
    "    method_mu=\"hist\",\n",
    "    method_cov=\"ledoit\",\n",
    "    feature_selection=\"PCR\",  # Method to select best model, could be PCR or Stepwise,\n",
    "    dict_risk=dict(\n",
    "        n_components=0.95  # 95% of explained variance.\n",
    "    )\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a6aa1350",
   "metadata": {},
   "source": [
    "Optimize the portfolio using a factor model, variance as the risk measure, and Sharpe ratio as the objective function"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "94613b72",
   "metadata": {},
   "outputs": [],
   "source": [
    "w = port.optimization(\n",
    "    model=\"FM\",  # Factor model\n",
    "    rm=\"MV\",  # Risk measure used, this time will be variance\n",
    "    obj=\"Sharpe\",  # Objective function, could be MinRisk, MaxRet, Utility or Sharpe\n",
    "    hist=False,  # Use risk factor model for expected returns\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cbec3a31",
   "metadata": {},
   "source": [
    "Plot the optimized portfolio weights as a pie chart"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "f04cc6a6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 800x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "ax = rf.plot_pie(\n",
    "    w=w,\n",
    "    title='Sharpe FM Mean Variance',\n",
    "    others=0.05,\n",
    "    nrow=25,\n",
    "    cmap=\"tab20\"\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ac56eec5",
   "metadata": {},
   "source": [
    "<a href=\"https://pyquantnews.com/\">PyQuant News</a> is where finance practitioners level up with Python for quant finance, algorithmic trading, and market data analysis. Looking to get started? Check out the fastest growing, top-selling course to <a href=\"https://gettingstartedwithpythonforquantfinance.com/\">get started with Python for quant finance</a>. For educational purposes. Not investment advise. Use at your own risk."
   ]
  }
 ],
 "metadata": {
  "jupytext": {
   "cell_metadata_filter": "-all",
   "main_language": "python",
   "notebook_metadata_filter": "-all"
  },
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.10.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}