{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "fc17c2cd-136f-4d34-8258-3d4891bc557b",
   "metadata": {},
   "outputs": [],
   "source": [
    "from hestonpy.models.bates import Bates\n",
    "from hestonpy.models.calibration.volatilitySmile import VolatilitySmile\n",
    "from hestonpy.option.data import get_options_data, filter_data_for_maturity\n",
    "\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "fontdict_title = {\n",
    "    'fontsize': 20,\n",
    "    'fontweight': 'bold'\n",
    "}\n",
    "from datetime import datetime\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a4e77d56",
   "metadata": {},
   "source": [
    "# Calibration of Bates models on market data"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "51b46510-3251-4d86-95a6-7eaf6a46ad0a",
   "metadata": {},
   "source": [
    "We will calibrate our models on S&P smiles. You can also try with Apple, but there is less liquidity on the market, so less available maturities. Some parameters,"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "1c37e81f-1597-4885-9c48-aed6d7657494",
   "metadata": {},
   "outputs": [],
   "source": [
    "symbol = '^SPX'\n",
    "all_market_data, spot, maturities = get_options_data(symbol)\n",
    "if symbol == '^SPX':\n",
    "    considered_maturities = [maturities[7], maturities[14], maturities[28], maturities[38]]\n",
    "else:\n",
    "    considered_maturities = [maturities[1], maturities[3], maturities[8], maturities[14]]\n",
    "    \n",
    "r = 0.00\n",
    "params = {\n",
    "    \"vol_initial\": 0.06,\n",
    "    \"kappa\": 1.25,\n",
    "    \"theta\": 0.06,\n",
    "    \"drift_emm\": 0.00,\n",
    "    \"sigma\": 0.6,\n",
    "    \"rho\": -0.8,\n",
    "    \"lambda_jump\": 1.0,\n",
    "    \"mu_J\": -0.1,\n",
    "    'sigma_J': 0.3\n",
    "}"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "507845d6-7f3a-483e-bf97-50e82275f851",
   "metadata": {},
   "source": [
    "For each maturity/smile we filter the data (based on bid-ask spread, the moneyness etc.), then we calibrate with a local optimiser to initialise our global optimiser."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "2a491510-2b35-4682-bfd7-525ffcbe03c4",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "================================================================================\n",
      "2025-04-15\n",
      "================================================================================ \n",
      "\n",
      "Calibrated parameters:\n",
      " v0=0.223 | kappa=10.000 | theta=0.337 | sigma=4.583 | rho=-0.784  | lambda_jump=0.010  | mu_J=-0.042  | sigma_J=0.050\n",
      "\n",
      "at minimum 0.182654 accepted 1\n",
      "Parameters: kappa=10.000 | theta=0.337 | sigma=4.583 | rho=-0.784  | lambda_jump=0.010  | mu_J=-0.042  | sigma_J=0.050 \n",
      "\n",
      "at minimum 0.146750 accepted 1\n",
      "Parameters: kappa=10.000 | theta=0.001 | sigma=3.544 | rho=-0.738  | lambda_jump=0.367  | mu_J=-0.500  | sigma_J=0.050 \n",
      "\n",
      "at minimum 0.150792 accepted 1\n",
      "Parameters: kappa=10.000 | theta=0.002 | sigma=3.536 | rho=-0.739  | lambda_jump=0.434  | mu_J=-0.421  | sigma_J=0.155 \n",
      "\n",
      "at minimum 0.146750 accepted 1\n",
      "Parameters: kappa=10.000 | theta=0.001 | sigma=3.544 | rho=-0.738  | lambda_jump=0.367  | mu_J=-0.500  | sigma_J=0.050 \n",
      "\n",
      "at minimum 0.151485 accepted 1\n",
      "Parameters: kappa=10.000 | theta=0.008 | sigma=3.621 | rho=-0.735  | lambda_jump=0.371  | mu_J=-0.500  | sigma_J=0.058 \n",
      "\n",
      "at minimum 0.146750 accepted 1\n",
      "Parameters: kappa=10.000 | theta=0.001 | sigma=3.544 | rho=-0.738  | lambda_jump=0.367  | mu_J=-0.500  | sigma_J=0.050 \n",
      "\n",
      "at minimum 0.146750 accepted 1\n",
      "Parameters: kappa=10.000 | theta=0.001 | sigma=3.544 | rho=-0.738  | lambda_jump=0.367  | mu_J=-0.500  | sigma_J=0.050 \n",
      "\n",
      "at minimum 0.146750 accepted 1\n",
      "Parameters: kappa=10.000 | theta=0.001 | sigma=3.544 | rho=-0.738  | lambda_jump=0.367  | mu_J=-0.500  | sigma_J=0.050 \n",
      "\n",
      "at minimum 0.211669 accepted 1\n",
      "Parameters: kappa=0.001 | theta=2.360 | sigma=3.705 | rho=-0.776  | lambda_jump=0.086  | mu_J=-0.500  | sigma_J=0.050 \n",
      "\n",
      "at minimum 0.211667 accepted 1\n",
      "Parameters: kappa=0.001 | theta=2.179 | sigma=3.705 | rho=-0.776  | lambda_jump=0.086  | mu_J=-0.500  | sigma_J=0.050 \n",
      "\n",
      "at minimum 0.211671 accepted 1\n",
      "Parameters: kappa=0.001 | theta=2.483 | sigma=3.705 | rho=-0.776  | lambda_jump=0.086  | mu_J=-0.500  | sigma_J=0.050 \n",
      "\n",
      "['requested number of basinhopping iterations completed successfully'] True\n",
      "Calibrated parameters:\n",
      " v0=0.223 | kappa=10.000 | theta=0.001 | sigma=3.544 | rho=-0.738  | lambda_jump=0.367  | mu_J=-0.500  | sigma_J=0.050\n",
      "\n",
      "================================================================================\n",
      "2025-04-25\n",
      "================================================================================ \n",
      "\n",
      "Calibrated parameters:\n",
      " v0=0.132 | kappa=3.190 | theta=0.001 | sigma=1.861 | rho=-0.757  | lambda_jump=0.453  | mu_J=-0.493  | sigma_J=0.050\n",
      "\n",
      "at minimum 0.227626 accepted 1\n",
      "Parameters: kappa=10.000 | theta=0.001 | sigma=1.817 | rho=-0.704  | lambda_jump=1.068  | mu_J=-0.304  | sigma_J=0.050 \n",
      "\n",
      "at minimum 0.227626 accepted 1\n",
      "Parameters: kappa=10.000 | theta=0.001 | sigma=1.817 | rho=-0.704  | lambda_jump=1.068  | mu_J=-0.304  | sigma_J=0.050 \n",
      "\n",
      "at minimum 0.228971 accepted 1\n",
      "Parameters: kappa=9.239 | theta=0.001 | sigma=1.814 | rho=-0.710  | lambda_jump=0.975  | mu_J=-0.320  | sigma_J=0.050 \n",
      "\n",
      "at minimum 0.228551 accepted 1\n",
      "Parameters: kappa=9.537 | theta=0.002 | sigma=1.822 | rho=-0.708  | lambda_jump=1.004  | mu_J=-0.315  | sigma_J=0.050 \n",
      "\n",
      "at minimum 0.227986 accepted 1\n",
      "Parameters: kappa=9.799 | theta=0.001 | sigma=1.815 | rho=-0.705  | lambda_jump=1.039  | mu_J=-0.309  | sigma_J=0.054 \n",
      "\n",
      "at minimum 0.227626 accepted 1\n",
      "Parameters: kappa=10.000 | theta=0.001 | sigma=1.817 | rho=-0.704  | lambda_jump=1.068  | mu_J=-0.304  | sigma_J=0.050 \n",
      "\n",
      "at minimum 0.227626 accepted 1\n",
      "Parameters: kappa=10.000 | theta=0.001 | sigma=1.816 | rho=-0.704  | lambda_jump=1.067  | mu_J=-0.304  | sigma_J=0.050 \n",
      "\n",
      "['success condition satisfied'] True\n",
      "Calibrated parameters:\n",
      " v0=0.132 | kappa=10.000 | theta=0.001 | sigma=1.817 | rho=-0.704  | lambda_jump=1.068  | mu_J=-0.304  | sigma_J=0.050\n",
      "\n",
      "================================================================================\n",
      "2025-07-18\n",
      "================================================================================ \n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/theo/Documents/packages/hestonpy/src/hestonpy/models/blackScholes.py:140: RuntimeWarning: divide by zero encountered in divide\n",
      "  d1 = (np.log(spot / strike) + (r + 0.5 * volatility**2) * time_to_maturity) / (\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Calibrated parameters:\n",
      " v0=0.084 | kappa=1.733 | theta=0.382 | sigma=2.877 | rho=-0.866  | lambda_jump=1.918  | mu_J=-0.061  | sigma_J=0.050\n",
      "\n",
      "at minimum 0.677344 accepted 1\n",
      "Parameters: kappa=2.503 | theta=0.341 | sigma=3.738 | rho=-0.896  | lambda_jump=4.045  | mu_J=-0.039  | sigma_J=0.050 \n",
      "\n",
      "at minimum 0.620353 accepted 1\n",
      "Parameters: kappa=1.891 | theta=0.427 | sigma=3.897 | rho=-0.914  | lambda_jump=5.059  | mu_J=-0.037  | sigma_J=0.050 \n",
      "\n",
      "at minimum 0.737909 accepted 1\n",
      "Parameters: kappa=2.485 | theta=0.330 | sigma=3.583 | rho=-0.923  | lambda_jump=6.253  | mu_J=-0.001  | sigma_J=0.050 \n",
      "\n",
      "at minimum 1.516186 accepted 1\n",
      "Parameters: kappa=1.980 | theta=0.388 | sigma=3.353 | rho=-0.929  | lambda_jump=5.722  | mu_J=-0.017  | sigma_J=0.050 \n",
      "\n",
      "['success condition satisfied'] True\n",
      "Calibrated parameters:\n",
      " v0=0.084 | kappa=1.891 | theta=0.427 | sigma=3.897 | rho=-0.914  | lambda_jump=5.059  | mu_J=-0.037  | sigma_J=0.050\n",
      "\n",
      "================================================================================\n",
      "2026-01-16\n",
      "================================================================================ \n",
      "\n",
      "Calibrated parameters:\n",
      " v0=0.070 | kappa=0.697 | theta=0.034 | sigma=2.990 | rho=-0.889  | lambda_jump=0.562  | mu_J=0.166  | sigma_J=0.050\n",
      "\n",
      "at minimum nan accepted 1\n",
      "Parameters: kappa=0.697 | theta=0.034 | sigma=2.990 | rho=-0.889  | lambda_jump=0.562  | mu_J=0.166  | sigma_J=0.050 \n",
      "\n",
      "at minimum 8681.453210 accepted 1\n",
      "Parameters: kappa=3.563 | theta=1.040 | sigma=1.937 | rho=-0.647  | lambda_jump=3.544  | mu_J=0.235  | sigma_J=0.468 \n",
      "\n",
      "at minimum nan accepted 1\n",
      "Parameters: kappa=3.078 | theta=1.398 | sigma=1.808 | rho=-0.547  | lambda_jump=2.498  | mu_J=0.203  | sigma_J=0.335 \n",
      "\n",
      "at minimum nan accepted 1\n",
      "Parameters: kappa=3.326 | theta=1.664 | sigma=1.637 | rho=-0.580  | lambda_jump=2.047  | mu_J=0.227  | sigma_J=0.255 \n",
      "\n",
      "at minimum nan accepted 1\n",
      "Parameters: kappa=3.055 | theta=1.871 | sigma=1.677 | rho=-0.782  | lambda_jump=1.738  | mu_J=0.265  | sigma_J=0.274 \n",
      "\n",
      "at minimum 8681.453210 accepted 1\n",
      "Parameters: kappa=0.001 | theta=1.535 | sigma=2.932 | rho=-0.489  | lambda_jump=5.120  | mu_J=-0.500  | sigma_J=0.050 \n",
      "\n",
      "['success condition satisfied'] False\n",
      "Calibrated parameters:\n",
      " v0=0.070 | kappa=0.697 | theta=0.034 | sigma=2.990 | rho=-0.889  | lambda_jump=0.562  | mu_J=0.166  | sigma_J=0.050\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/theo/Documents/packages/hestonpy/src/hestonpy/models/bates.py:271: RuntimeWarning: overflow encountered in exp\n",
      "  (bj - rho * sigma * u * 1j + dj(u)) * tau - 2 * np.log((1 - gj(u) * np.exp(dj(u) * tau)) / (1 - gj(u)))\n",
      "/home/theo/Documents/packages/hestonpy/src/hestonpy/models/bates.py:271: RuntimeWarning: invalid value encountered in scalar multiply\n",
      "  (bj - rho * sigma * u * 1j + dj(u)) * tau - 2 * np.log((1 - gj(u) * np.exp(dj(u) * tau)) / (1 - gj(u)))\n",
      "/home/theo/Documents/packages/hestonpy/src/hestonpy/models/bates.py:273: RuntimeWarning: overflow encountered in exp\n",
      "  Dj = lambda tau, u: (bj - rho * sigma * u * 1j + dj(u)) / sigma**2 * (1 - np.exp(dj(u) * tau)) / (1 - gj(u) * np.exp(dj(u) * tau))\n",
      "/home/theo/Documents/packages/hestonpy/src/hestonpy/models/bates.py:273: RuntimeWarning: invalid value encountered in scalar multiply\n",
      "  Dj = lambda tau, u: (bj - rho * sigma * u * 1j + dj(u)) / sigma**2 * (1 - np.exp(dj(u) * tau)) / (1 - gj(u) * np.exp(dj(u) * tau))\n",
      "/home/theo/Documents/packages/hestonpy/src/hestonpy/models/bates.py:273: RuntimeWarning: invalid value encountered in scalar divide\n",
      "  Dj = lambda tau, u: (bj - rho * sigma * u * 1j + dj(u)) / sigma**2 * (1 - np.exp(dj(u) * tau)) / (1 - gj(u) * np.exp(dj(u) * tau))\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 4 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, axs = plt.subplots(2, 2, layout=\"constrained\")\n",
    "fig.suptitle(f'Market smiles: {symbol}', **fontdict_title)\n",
    "\n",
    "############################################################\n",
    "##### Absolute\n",
    "############################################################\n",
    "for maturity, ax in zip(considered_maturities, axs.flatten()):\n",
    "\n",
    "    print(\"=\"*80)\n",
    "    print(maturity)\n",
    "    print(\"=\"*80,\"\\n\")\n",
    "\n",
    "    ####################################\n",
    "    ### Getting and filtering data \n",
    "    ####################################\n",
    "\n",
    "    full_market_data = filter_data_for_maturity(all_market_data, maturity)\n",
    "    time_to_maturity = full_market_data['Time to Maturity'].iloc[0]\n",
    "    strikes = full_market_data['Strike'].values\n",
    "    bid_prices = full_market_data[\"Bid\"].values\n",
    "    ask_prices = full_market_data['Ask'].values\n",
    "    market_ivs = full_market_data['Implied Volatility'].values\n",
    "    market_prices = full_market_data['Call Price'].values\n",
    "\n",
    "    marketVolatilitySmile = VolatilitySmile(\n",
    "        strikes=strikes,\n",
    "        time_to_maturity=time_to_maturity,\n",
    "        atm=spot,\n",
    "        market_ivs=market_ivs,\n",
    "        r=r\n",
    "    )\n",
    "    market_data = marketVolatilitySmile.filters(full_market_data, select_mid_ivs=True)\n",
    "\n",
    "    ####################################\n",
    "    ### Calibration \n",
    "    ####################################\n",
    "    bates = Bates(spot=spot, r=r, **params)\n",
    "    initial_guess = [params['kappa'], params['theta'], params['sigma'], params['rho'], params['lambda_jump'], params['mu_J'], params['sigma_J']]\n",
    "    initial_params = marketVolatilitySmile.calibration(\n",
    "        price_function=bates.call_price,\n",
    "        initial_guess=initial_guess,\n",
    "        guess_correlation_sign='negative',\n",
    "        speed='local',\n",
    "    )\n",
    "\n",
    "    initial_guess = [initial_params['kappa'], initial_params['theta'], initial_params['sigma'], initial_params['rho'], \n",
    "                    initial_params['lambda_jump'], initial_params['mu_J'], initial_params['sigma_J']]\n",
    "    calibrated_params = marketVolatilitySmile.calibration(\n",
    "        price_function=bates.call_price,\n",
    "        guess_correlation_sign='negative',\n",
    "        initial_guess=initial_guess,\n",
    "        speed='global',\n",
    "    )\n",
    "    calibrated_prices = bates.call_price(\n",
    "        strike=marketVolatilitySmile.strikes, time_to_maturity=time_to_maturity, **calibrated_params\n",
    "    )\n",
    "    calibrated_ivs = marketVolatilitySmile.compute_smile(prices=calibrated_prices)\n",
    "\n",
    "    # Some plots\n",
    "    ask_ivs = market_data['Ask ivs'].values\n",
    "    bid_ivs = market_data['Bid ivs'].values\n",
    "    forward = marketVolatilitySmile.atm * np.exp(marketVolatilitySmile.r * marketVolatilitySmile.time_to_maturity)\n",
    "\n",
    "    if ax == axs.flatten()[-2]:\n",
    "        ax.axvline(1, linestyle=\"--\", color=\"gray\", label=\"ATM\")\n",
    "        ax.plot(marketVolatilitySmile.strikes / forward, calibrated_ivs, label=\"absolute calibration\", marker='+', color='blue', linestyle=\"dotted\", markersize=4)\n",
    "        ax.scatter(marketVolatilitySmile.strikes / forward, marketVolatilitySmile.market_ivs, label=\"mid\", marker='o', color='red', s=20)\n",
    "        ax.scatter(marketVolatilitySmile.strikes / forward, bid_ivs, label=\"bid\", marker=6, color='black', s=20)\n",
    "        ax.scatter(marketVolatilitySmile.strikes / forward, ask_ivs, label=\"ask\", marker=7, color='gray', s=20)\n",
    "        ax.legend(loc='upper right', ncol=2, alignment='left')\n",
    "    else:\n",
    "        ax.axvline(1, linestyle=\"--\", color=\"gray\")\n",
    "        ax.plot(marketVolatilitySmile.strikes / forward, calibrated_ivs, marker='+', color='blue', linestyle=\"dotted\", markersize=4)\n",
    "        ax.scatter(marketVolatilitySmile.strikes / forward, marketVolatilitySmile.market_ivs, marker='o', color='red', s=20)\n",
    "        ax.scatter(marketVolatilitySmile.strikes / forward, bid_ivs, marker=6, color='black', s=20)\n",
    "        ax.scatter(marketVolatilitySmile.strikes / forward, ask_ivs, marker=7, color='gray', s=20)\n",
    "\n",
    "    ax.set_xlabel(\"Moneyness [%]\")\n",
    "    ax.set_ylabel(\"Implied Volatility [%]\")\n",
    "\n",
    "    date = datetime.strptime(maturity, '%Y-%m-%d').date().strftime(\"%d-%B-%y\")\n",
    "    title = f\"{date}: {marketVolatilitySmile.time_to_maturity * 252 / 5:.1f} semaines\"\n",
    "    ax.set_title(title)\n",
    "    ax.grid(visible=True, which=\"major\", linestyle=\"--\", dashes=(5, 10), color=\"gray\", linewidth=0.5, alpha=0.8)\n",
    "\n",
    "plt.show()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".venv",
   "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": "3.10.16"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}