Update

.ipynb_checkpoints/CapiPort-checkpoint.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "id": "ef21dac5",
+   "id": "37b7d816",
    "metadata": {},
    "source": [
     "# CapiPort - PORTFOLIO OPTIMISATION"
@@ -10,7 +10,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "40001fdc",
+   "id": "b66aca9c",
    "metadata": {},
    "source": [
     "    Two things to consider for Portfolio Optimisation:\n",
@@ -21,7 +21,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "92c4e47e",
+   "id": "d0c0e49d",
    "metadata": {},
    "source": [
     "    Basic process of Portfolio Optimisation:\n",
@@ -30,6 +30,14 @@
     "            1.1) Asset Class choosen - Equity (Stocks)\n",
     "        2) Select the Companies which you want to use to build a Portfolio.\n",
     "            2.1) Companies choosen - \n",
+    "                2.1.1) Tata Power - TATAPOWER.NS\n",
+    "                2.1.2) Tata Motors - TATAMOTORS.NS\n",
+    "                2.1.3) Tata Steel - TATASTEEL.NS\n",
+    "                2.1.4) Zomato - ZOMATO.NS\n",
+    "                2.1.5) NHPC - NHPC.NS\n",
+    "                2.1.6) NCC - NCC.NS\n",
+    "                2.1.7) IREDA - IREDA.NS\n",
+    "                2.1.8) IRCON - IRCON.NS\n",
     "        3) To try various Statistical Methods relating to Portfolio Optimisation.\n",
     "            3.1) Method 1 - Result\n",
     "            3.2) Method 2 - Result\n",
@@ -44,7 +52,173 @@
   },
   {
    "cell_type": "markdown",
-   "id": "b9d59c90",
+   "id": "dbfe76bf",
+   "metadata": {},
+   "source": [
+    "## Importing the Libraries"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "20883492",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import yfinance as yf\n",
+    "\n",
+    "\n",
+    "from scipy.optimize import minimize\n",
+    "\n",
+    "\n",
+    "\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a0a3c96e",
+   "metadata": {},
+   "source": [
+    "## Get Stock Data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "f3937e5a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_historical_returns(tickers, start_date, end_date):\n",
+    "    \"\"\"\n",
+    "    Fetch historical returns data for the given tickers.\n",
+    "\n",
+    "    Args:\n",
+    "    - tickers: list of strings, tickers of assets\n",
+    "    - start_date: string, start date in the format 'YYYY-MM-DD'\n",
+    "    - end_date: string, end date in the format 'YYYY-MM-DD'\n",
+    "\n",
+    "    Returns:\n",
+    "    - pandas DataFrame, historical returns data\n",
+    "    \"\"\"\n",
+    "    data = yf.download(tickers, start=start_date, end=end_date)['Adj Close']\n",
+    "    returns = data.pct_change().dropna()\n",
+    "    return returns\n",
+    "\n",
+    "def get_risk_free_rate_india():\n",
+    "    \"\"\"\n",
+    "    Get the risk-free rate for the Indian market using the yield of the 10-year Indian Government Bond.\n",
+    "\n",
+    "    Returns:\n",
+    "    - float, risk-free rate\n",
+    "    \"\"\"\n",
+    "    # Ticker symbol for the 10-year Indian Government Bond yield\n",
+    "    bond_ticker = 'INR=X'  # You can replace this with the actual ticker symbol for the bond\n",
+    "\n",
+    "    # Fetch the bond data\n",
+    "    bond_data = yf.Ticker(bond_ticker)\n",
+    "\n",
+    "    # Get the latest yield\n",
+    "    risk_free_rate_india = bond_data.history(period='1d')['Close'][-1] / 100\n",
+    "    return risk_free_rate_india"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "id": "0a9e0e4e",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[*********************100%%**********************]  8 of 8 completed\n",
+      "/var/folders/jx/_r4pg95j3pzdd581p_wql9pc0000gn/T/ipykernel_17224/562231645.py:14: FutureWarning: The default fill_method='pad' in DataFrame.pct_change is deprecated and will be removed in a future version. Call ffill before calling pct_change to retain current behavior and silence this warning.\n",
+      "  returns = data.pct_change().dropna()\n",
+      "/var/folders/jx/_r4pg95j3pzdd581p_wql9pc0000gn/T/ipykernel_17224/4250087689.py:15: FutureWarning: Series.__getitem__ treating keys as positions is deprecated. In a future version, integer keys will always be treated as labels (consistent with DataFrame behavior). To access a value by position, use `ser.iloc[pos]`\n",
+      "  risk_free_rate_india = bond_data.history(period='1d')['Close'][-1] / 100\n"
+     ]
+    }
+   ],
+   "source": [
+    "equity_list = [\"TATAPOWER.NS\", \"TATAMOTORS.NS\", \"TATASTEEL.NS\", \"ZOMATO.NS\", \"NHPC.NS\", \"NCC.NS\", \"IREDA.NS\", \"IRCON.NS\"]\n",
+    "\n",
+    "equity_data = get_historical_returns(equity_list, \"1900-01-01\", \"2024-03-04\")\n",
+    "\n",
+    "risk_free_rate = get_risk_free_rate_india()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2ad5b748",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def sharpe_ratio(weights, returns, risk_free_rate):\n",
+    "    \"\"\"\n",
+    "    Calculate the Sharpe Ratio of a portfolio.\n",
+    "\n",
+    "    Args:\n",
+    "    - weights: array-like, weights of assets in the portfolio\n",
+    "    - returns: pandas DataFrame, historical returns of assets\n",
+    "    - risk_free_rate: float, risk-free rate of return\n",
+    "\n",
+    "    Returns:\n",
+    "    - float, Sharpe Ratio of the portfolio\n",
+    "    \"\"\"\n",
+    "    portfolio_return = np.sum(weights * returns.mean() * 252)  # 252 trading days in a year\n",
+    "    portfolio_std_dev = np.sqrt(np.dot(weights.T, np.dot(returns.cov() * 252, weights)))\n",
+    "    sharpe_ratio = (portfolio_return - risk_free_rate) / portfolio_std_dev\n",
+    "    return -sharpe_ratio  # Minimize negative Sharpe Ratio for maximization\n",
+    "\n",
+    "\n",
+    "\n",
+    "def optimize_portfolio(returns, risk_free_rate):\n",
+    "    \"\"\"\n",
+    "    Optimize portfolio to maximize the Sharpe Ratio.\n",
+    "\n",
+    "    Args:\n",
+    "    - returns: pandas DataFrame, historical returns of assets\n",
+    "    - risk_free_rate: float, risk-free rate of return\n",
+    "\n",
+    "    Returns:\n",
+    "    - array, optimal weights of assets in the portfolio\n",
+    "    \"\"\"\n",
+    "    num_assets = len(returns.columns)\n",
+    "    initial_weights = np.array([1 / num_assets] * num_assets)\n",
+    "    bounds = [(0, 1)] * num_assets  # Bounds for asset weights (0 <= weight <= 1)\n",
+    "    constraints = ({'type': 'eq', 'fun': lambda weights: np.sum(weights) - 1})  # Sum of weights equals 1 constraint\n",
+    "\n",
+    "    optimized_result = minimize(sharpe_ratio, initial_weights, args=(returns, risk_free_rate),\n",
+    "                                method='SLSQP', bounds=bounds, constraints=constraints)\n",
+    "\n",
+    "    return optimized_result.x"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "afa17f35",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a17e46ca",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "38f5c7c7",
    "metadata": {},
    "source": [
     "## <u>STEPS FOR IMPLEMENTING<u>\n",
@@ -72,7 +246,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "2af6aaca",
+   "id": "df48c03f",
    "metadata": {},
    "outputs": [],
    "source": []

CapiPort.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "id": "ef21dac5",
+   "id": "db58d421",
    "metadata": {},
    "source": [
     "# CapiPort - PORTFOLIO OPTIMISATION"
@@ -10,7 +10,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "40001fdc",
+   "id": "a9c51b1c",
    "metadata": {},
    "source": [
     "    Two things to consider for Portfolio Optimisation:\n",
@@ -21,7 +21,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "92c4e47e",
+   "id": "80e6fed1",
    "metadata": {},
    "source": [
     "    Basic process of Portfolio Optimisation:\n",
@@ -30,6 +30,14 @@
     "            1.1) Asset Class choosen - Equity (Stocks)\n",
     "        2) Select the Companies which you want to use to build a Portfolio.\n",
     "            2.1) Companies choosen - \n",
+    "                2.1.1) Tata Power - TATAPOWER.NS\n",
+    "                2.1.2) Tata Motors - TATAMOTORS.NS\n",
+    "                2.1.3) Tata Steel - TATASTEEL.NS\n",
+    "                2.1.4) Zomato - ZOMATO.NS\n",
+    "                2.1.5) NHPC - NHPC.NS\n",
+    "                2.1.6) NCC - NCC.NS\n",
+    "                2.1.7) IREDA - IREDA.NS\n",
+    "                2.1.8) IRCON - IRCON.NS\n",
     "        3) To try various Statistical Methods relating to Portfolio Optimisation.\n",
     "            3.1) Method 1 - Result\n",
     "            3.2) Method 2 - Result\n",
@@ -44,7 +52,192 @@
   },
   {
    "cell_type": "markdown",
-   "id": "b9d59c90",
+   "id": "e630d5b1",
+   "metadata": {},
+   "source": [
+    "## Importing the Libraries"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "7de120f8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import yfinance as yf\n",
+    "\n",
+    "\n",
+    "from scipy.optimize import minimize\n",
+    "\n",
+    "\n",
+    "\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "91fcb51f",
+   "metadata": {},
+   "source": [
+    "## Get Stock Data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "4f30295f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_historical_returns(tickers, start_date, end_date):\n",
+    "    \"\"\"\n",
+    "    Fetch historical returns data for the given tickers.\n",
+    "\n",
+    "    Args:\n",
+    "    - tickers: list of strings, tickers of assets\n",
+    "    - start_date: string, start date in the format 'YYYY-MM-DD'\n",
+    "    - end_date: string, end date in the format 'YYYY-MM-DD'\n",
+    "\n",
+    "    Returns:\n",
+    "    - pandas DataFrame, historical returns data\n",
+    "    \"\"\"\n",
+    "    data = yf.download(tickers, start=start_date, end=end_date)['Adj Close']\n",
+    "    returns = data.pct_change().dropna()\n",
+    "    return returns\n",
+    "\n",
+    "def get_risk_free_rate_india():\n",
+    "    \"\"\"\n",
+    "    Get the risk-free rate for the Indian market using the yield of the 10-year Indian Government Bond.\n",
+    "\n",
+    "    Returns:\n",
+    "    - float, risk-free rate\n",
+    "    \"\"\"\n",
+    "    # Ticker symbol for the 10-year Indian Government Bond yield\n",
+    "    bond_ticker = 'INR=X'  # You can replace this with the actual ticker symbol for the bond\n",
+    "\n",
+    "    # Fetch the bond data\n",
+    "    bond_data = yf.Ticker(bond_ticker)\n",
+    "\n",
+    "    # Get the latest yield\n",
+    "    risk_free_rate_india = bond_data.history(period='1d')['Close'][-1] / 100\n",
+    "    return risk_free_rate_india"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "id": "c2f02cbe",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[*********************100%%**********************]  8 of 8 completed\n",
+      "/var/folders/jx/_r4pg95j3pzdd581p_wql9pc0000gn/T/ipykernel_17224/562231645.py:14: FutureWarning: The default fill_method='pad' in DataFrame.pct_change is deprecated and will be removed in a future version. Call ffill before calling pct_change to retain current behavior and silence this warning.\n",
+      "  returns = data.pct_change().dropna()\n",
+      "/var/folders/jx/_r4pg95j3pzdd581p_wql9pc0000gn/T/ipykernel_17224/4250087689.py:15: FutureWarning: Series.__getitem__ treating keys as positions is deprecated. In a future version, integer keys will always be treated as labels (consistent with DataFrame behavior). To access a value by position, use `ser.iloc[pos]`\n",
+      "  risk_free_rate_india = bond_data.history(period='1d')['Close'][-1] / 100\n"
+     ]
+    }
+   ],
+   "source": [
+    "equity_list = [\"TATAPOWER.NS\", \"TATAMOTORS.NS\", \"TATASTEEL.NS\", \"ZOMATO.NS\", \"NHPC.NS\", \"NCC.NS\", \"IREDA.NS\", \"IRCON.NS\"]\n",
+    "\n",
+    "equity_data = get_historical_returns(equity_list, \"1900-01-01\", \"2024-03-04\")\n",
+    "\n",
+    "risk_free_rate = get_risk_free_rate_india()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "id": "b9cb34f2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def sharpe_ratio(weights, returns, risk_free_rate):\n",
+    "    \"\"\"\n",
+    "    Calculate the Sharpe Ratio of a portfolio.\n",
+    "\n",
+    "    Args:\n",
+    "    - weights: array-like, weights of assets in the portfolio\n",
+    "    - returns: pandas DataFrame, historical returns of assets\n",
+    "    - risk_free_rate: float, risk-free rate of return\n",
+    "\n",
+    "    Returns:\n",
+    "    - float, Sharpe Ratio of the portfolio\n",
+    "    \"\"\"\n",
+    "    portfolio_return = np.sum(weights * returns.mean() * 252)  # 252 trading days in a year\n",
+    "    portfolio_std_dev = np.sqrt(np.dot(weights.T, np.dot(returns.cov() * 252, weights)))\n",
+    "    sharpe_ratio = (portfolio_return - risk_free_rate) / portfolio_std_dev\n",
+    "    return -sharpe_ratio  # Minimize negative Sharpe Ratio for maximization\n",
+    "\n",
+    "\n",
+    "\n",
+    "def optimize_portfolio(returns, risk_free_rate):\n",
+    "    \"\"\"\n",
+    "    Optimize portfolio to maximize the Sharpe Ratio.\n",
+    "\n",
+    "    Args:\n",
+    "    - returns: pandas DataFrame, historical returns of assets\n",
+    "    - risk_free_rate: float, risk-free rate of return\n",
+    "\n",
+    "    Returns:\n",
+    "    - array, optimal weights of assets in the portfolio\n",
+    "    \"\"\"\n",
+    "    num_assets = len(returns.columns)\n",
+    "    initial_weights = np.array([1 / num_assets] * num_assets)\n",
+    "    bounds = [(0, 1)] * num_assets  # Bounds for asset weights (0 <= weight <= 1)\n",
+    "    constraints = ({'type': 'eq', 'fun': lambda weights: np.sum(weights) - 1})  # Sum of weights equals 1 constraint\n",
+    "\n",
+    "    optimized_result = minimize(sharpe_ratio, initial_weights, args=(returns, risk_free_rate),\n",
+    "                                method='SLSQP', bounds=bounds, constraints=constraints)\n",
+    "\n",
+    "    return optimized_result.x"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "id": "6af1a0ad",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "TATAPOWER.NS  :  0.0\n",
+      "TATAMOTORS.NS  :  0.236548217499089\n",
+      "TATASTEEL.NS  :  0.17568900379556238\n",
+      "ZOMATO.NS  :  0.07826482194498546\n",
+      "NHPC.NS  :  0.21116461887342103\n",
+      "NCC.NS  :  0.0\n",
+      "IREDA.NS  :  0.0\n",
+      "IRCON.NS  :  0.2983333378869751\n"
+     ]
+    }
+   ],
+   "source": [
+    "optimal_weights = optimize_portfolio(equity_data, risk_free_rate)\n",
+    "for i,j in zip(equity_list, optimal_weights):\n",
+    "    print(i, \" : \", j)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "39b7e975",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a672bdae",
    "metadata": {},
    "source": [
     "## <u>STEPS FOR IMPLEMENTING<u>\n",
@@ -72,7 +265,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "2af6aaca",
+   "id": "00d89b09",
    "metadata": {},
    "outputs": [],
    "source": []