euro-equity-options-pricing-example.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "lucky-annual",
   "metadata": {},
   "source": [
    "# Pricing equity options denominated in Euro\n",
    "In this notebook I price American equity options denominated in Euro using volatility tracking, riskless zero rate curve construction, and options pricing code from this package. I ensure that all market and economic data required for pricing is obtained from [FRED](https://fred.stlouisfed.org), [Eurostat](https://ec.europa.eu/eurostat/data/database), and [Yahoo-finance](https://finance.yahoo.com) using [pandas-datareader](https://pydata.github.io/pandas-datareader/). Since the lifetime of an option is usually measured using trading days rather than calendar days, I make use of [the pandas-market-calendars library](https://pandas-market-calendars.readthedocs.io/en/latest/index.html) to get correct trading calendars.\n",
    "\n",
    "This notebook can also be used as a tutorial to using the `pricing.curves`, `pricing.options`, `volatility.parameter_estimators`, and `volatility.volatility_trackers` packages in this repository."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "interstate-paris",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Uncomment if running in Google Colaboratory, otherwise the import of the curves module in the cell below will fail\n",
    "#!git clone -l -s https://github.com/ilchen/options-pricing.git cloned-repo\n",
    "#%cd cloned-repo\n",
    "\n",
    "# Install the latest version of pandas-datareader, eurostat, yfinance, and pandas-market-calendars\n",
    "# !pip install pandas-datareader -U\n",
    "# !pip install eurostat -U\n",
    "# !pip install yfinance -U\n",
    "# !pip install pandas-market-calendars -U"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cultural-appeal",
   "metadata": {},
   "source": [
    "## Constructing a riskless zero rate curve for Euro\n",
    "Since I already covered it in a separate notebook, I will simply import it (along with all other imports that this notebook needs). The resultant YieldCurve object is\n",
    "assigned to the `curve` variable"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "important-switzerland",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1440x720 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "%run euro-riskless-rate-curve-construction-example.ipynb"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "regulated-moore",
   "metadata": {},
   "source": [
    "## Estimating and forecasting volatility of the stock, options on which we want to price\n",
    "Now that the riskless curve has been constructed, the next thing to do is obtain an accurate volatility estimate for the stock whose options we want to price. There are various methods for doing it. The most common are the Exponentially Weighted Moving Average (EWMA) and GARCH(1, 1) methods. You can read about them on the Internet or delve into John C. Hull's [Risk Management and Financial Institutions](http://www-2.rotman.utoronto.ca/~hull/riskman/index.html) or [Options, Futures, and Other Derivatives](http://www-2.rotman.utoronto.ca/~hull/ofod/index.html). For the purposes of pricing options GARCH(1, 1) is preferred because it supports volatility forecasting for future maturities by incorporating mean reversion (and volatility of equities lends itself to mean reversion). In this notebook I therefore use GARCH(1, 1).\n",
    "\n",
    "### GARCH(1, 1)\n",
    "In order to use GARCH(1, 1) one first needs to estimate its parameters based on the historical data for the equity whose options you want to price. GARCH(1, 1) has three parameters &mdash; ω, α, and β. I use the maximum likelihood method to estimate them, which is an optimization task. The `volatility.parameter_estimators.GARCHParameterEstimator` class comes to rescure. _Implementation detail_: In that class I use [SciPy](https://docs.scipy.org/doc/scipy/tutorial/optimize.html) to optimize for maximum likelihood. Alternatively I could've used Google's TensorFlow 2.x.\n",
    "\n",
    "Constraint optimization for three variables is not fast. If you are not content with the speed of `volatility.parameter_estimators.GARCHParameterEstimator`, you can use its `volatility.parameter_estimators.GARCHVarianceTargetingParameterEstimator` counterpart. This latter class is \n",
    "faster because it uses the so-called _variance targeting_ method whereby it sets ω based on the sample variance of price changes. Then it optimises for only two variables instead of three as GARCHParameterEstimator does. It's marginally less accurate.\n",
    "\n",
    "*NB* When estimating ω, α, and β it's vital to use _adjusted closing_ prices, i.e. prices that have been adjusted for dividends and stock splits. Failing to do that will result in too high an estimate. Yahoo Finance provides such prices in the `Adj Close` column.\n",
    "\n",
    "#### Estimating GARCH(1, 1) parameters for Shell plc\n",
    "Since volatility tends to change with time, it's recommended to estimate it based on the most recent 90 or 180 days, or on the same number of days as the duration of the option being priced. In this notebook I use date from the past two years."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "automated-macro",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Objective function: 3923.25911 after 140 iterations\n",
      "Optimal values for GARCH(1, 1) parameters:\n",
      "\tω=0.000001525767, α=0.02912, β=0.95778\n"
     ]
    }
   ],
   "source": [
    "# Shell plc as traded on Euronext Amsterdam\n",
    "TICKER = 'SHELL.AS'\n",
    "\n",
    "# I'll use price changes over the past two years to estimate GARCH(1, 1) ω, α, and β parameters\n",
    "start = BDay(1).rollback(date.today() - relativedelta(years=+2))\n",
    "ticker = yfin.Ticker(TICKER)\n",
    "data = ticker.history(start=start, actions=False, auto_adjust=False)\n",
    "asset_prices = data['Adj Close']\n",
    "\n",
    "vol_estimator = parameter_estimators.GARCHParameterEstimator(asset_prices)\n",
    "print('Optimal values for GARCH(1, 1) parameters:\\n\\tω=%.12f, α=%.5f, β=%.5f'\n",
    "      % (vol_estimator.omega, vol_estimator.alpha, vol_estimator.beta))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "together-shore",
   "metadata": {},
   "source": [
    "##### Optional: Estimating with a faster estimator &mdash; GARCHVarianceTargetingParameterEstimator"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "royal-lounge",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Objective function: 3921.87762 after 88 iterations\n",
      "Optimal values for GARCH(1, 1) parameters:\n",
      "\tω=0.000001825749, α=0.04717, β=0.94285\n"
     ]
    }
   ],
   "source": [
    "var_target_vol_estimator = parameter_estimators.GARCHVarianceTargetingParameterEstimator(asset_prices)\n",
    "print('Optimal values for GARCH(1, 1) parameters:\\n\\tω=%.12f, α=%.5f, β=%.5f'\n",
    "      % (var_target_vol_estimator.omega, var_target_vol_estimator.alpha, var_target_vol_estimator.beta))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "quantitative-champagne",
   "metadata": {},
   "source": [
    "As you can see, `GARCHParameterEstimator` is able to achieve a slightly higher value of the objective function than `GARCHVarianceTargetingParameterEstimator`. The higher, the more accurate as we are solving for the maximum value."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "generic-logging",
   "metadata": {},
   "source": [
    "#### Forecasting volatility for Shell plc\n",
    "Now that we have obtined optimal values for GARCH(1, 1) parameters ω, α, and β, we can proceed to forecast the volatility of Shell stock. I crated class `volatility.parameter_estimators.GARCHVolatilityTracker` to assist in it."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "appropriate-phoenix",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Volatility of SHELL.AS for term 0.6822 years: 0.15838\n"
     ]
    }
   ],
   "source": [
    "vol_tracker = volatility_trackers.GARCHVolatilityTracker(vol_estimator.omega, vol_estimator.alpha,\n",
    "                                                         vol_estimator.beta, asset_prices)\n",
    "\n",
    "# Let's get volatility forecast for next March options, i.e. maturity on the 3rd Friday of next March\n",
    "from dateutil.relativedelta import FR\n",
    "maturity_date = curve.date + relativedelta(years=0 if curve.date.month < 3 else 1, month=3, day=1, weekday=FR(3))\n",
    "vol = vol_tracker.get_annual_term_volatility_forecast(curve.to_years(maturity_date))\n",
    "print('Volatility of %s for term %.4f years: %.5f' % (TICKER, curve.to_years(maturity_date), vol))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "quick-control",
   "metadata": {},
   "source": [
    "#### Optional: Visualizing historical and future volatility of Shell stock for 200 business days into the future"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "first-bacteria",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1440x720 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "\n",
    "# Skipping the first n days of volatility forecast\n",
    "n_days_to_skip = 10\n",
    "x = vol_tracker.get_dates()[n_days_to_skip:]\n",
    "fig = plt.figure(figsize=(20, 10))\n",
    "ax = fig.add_subplot(1, 1, 1)\n",
    "ax.plot(x, vol_tracker.get_annual_volatilities()[n_days_to_skip:] * 100,\n",
    "        label='Historical Annual Volatility (GARCH(1,1) ω=%.5f, α=%.5f, β=%.5f)' \n",
    "            % (vol_estimator.omega, vol_estimator.alpha, vol_estimator.beta),\n",
    "        linewidth=2, color='k')\n",
    "\n",
    "# Forecasting volatility of Shell stock 200 days into the future\n",
    "future_volatilities = vol_tracker.get_annual_volatility_forecast_for_next_n_days(200)\n",
    "ax.plot(future_volatilities.index, future_volatilities * 100, label='Forecast Annual Volatility', linewidth=1, color='k')\n",
    "ax.hlines(vol_tracker.get_annual_long_term_volatility() * 100, xmin=future_volatilities.index[0], xmax=future_volatilities.index[-1],\n",
    "         label=\"Long-term Annual Volatility\", linestyle='--')\n",
    "ax.legend()\n",
    "ax.grid(True)\n",
    "x_axis = x.append(future_volatilities.index)\n",
    "ax.set_xticks(x_axis[::36])\n",
    "ax.set_xticklabels(x_axis[::36].strftime('%Y-%m-%d'), rotation=45)\n",
    "ax.yaxis.set_major_formatter(mtick.PercentFormatter())"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "baking-stream",
   "metadata": {},
   "source": [
    "#### Optional: Visualizing the volatility term structure of Shell stock for 5 years into the future\n",
    "A very important notion in pricing options is the _volatility term structure_. It defines the relationship between\n",
    "the maturity of options and their volatilities. In other words it defines what the average volatility for a given maturity is forecast to be. Given the mean reverting nature of volatility, volatility for the longer terms trends towards the mean volatility of a given asset."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "noticed-consortium",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1440x720 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "from math import floor, ceil\n",
    "\n",
    "terms = [x / 100 for x in range(5, 505, 5)]\n",
    "term_vols = [vol_tracker.get_annual_term_volatility_forecast(term) * 100 for term in terms]\n",
    "series = pd.Series(term_vols, index=terms)\n",
    "\n",
    "ax = series.plot(figsize=(20,10), grid=True, kind='bar', title='Term structure of ' + TICKER + ' volatility')\n",
    "ax.set_ylim(bottom=floor(series.min()), top=ceil(series.max()))\n",
    "ax.yaxis.set_major_formatter(mtick.PercentFormatter())\n",
    "ax.set_ylabel('Annual Volatility')\n",
    "_ = ax.set_xlabel('Terms in years')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "afraid-elevation",
   "metadata": {},
   "source": [
    "## Pricing using Black-Scholes-Merton Pricer\n",
    "The Black-Scholes-Merton model can be used to price European options, including on stock that pays dividends. With enough customizations it can also be used to price American call options (even those paying dividends). This is based on the fact that it is never optimal to exercise an American call option prematurely except on days immediately preceeding ex-dividend days for the stock. The `pricing.options.BlackScholesMertonPricer` class from this repository implements this customization to price American call options.\n",
    "\n",
    "Let's put it to use to price a Shell call option with a strike of €28. Shell pays dividends. It's essential to take into account dividends that get payed during the lifetime of an option to get an accurate price. An interesting nuance about Shell is that it switched to declaring its dividend in USD, which makes it extra difficult when pricing its options where the unerlying is Shell's equity price in Euros (which is the case in this notebook). It would actually be easier to price its USD option where the underlying is Shell's share price traded on NYSE (ticker `SHEL`) and also priced in USD.\n",
    "\n",
    "Market makers tend to calculate the life time of options using trading days rather than calendar days. The `pricing.options.BlackScholesMertonPricer` class supports both ways of pricing options. It's determined by the `holidays` parameter of its constructor, passing an array of `datetime64[D]` values implies calculating the life of\n",
    "the option using the number trading days to its expiry and dividing by 252. Not passing a value for this parameter\n",
    "will imply calculating the life of he option using the number of calendar days to its expiry and dividing by a value between 365 and 366. It **does** make an impact of about 3\\%-5\\% on the price of the option depending on its maturity, for longer-dated options the impact is smaller. In the below notebook I price based on the trading\n",
    "calendar of the Eurex exchange."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "superior-proposal",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "SHELL.AS AMERICAN call option with strike 28.0 and maturity 2025-12-19, price: 5.71, σ: 0.1646, Δ: 0.999, Γ: 0.001, ν: 0.033\n"
     ]
    }
   ],
   "source": [
    "strike = 28.\n",
    "\n",
    "# Yahoo-dividends returns the most recent ex-dividend date in the last row\n",
    "last_divs = ticker.dividends[-1:]\n",
    "\n",
    "# An approximate rule for Shell's ex-dividend dates -- ex-dividend date is on the second Thursday\n",
    "# of the last month of a season.\n",
    "idx = (pd.date_range(last_divs.index[0].date(), freq='WOM-2THU', periods=30)[::3])\n",
    "divs = pd.Series([last_divs[0]] * len(idx), index=idx, name=TICKER + ' Dividends')\n",
    "\n",
    "# Shell aims to grow the dividend per share by around 4 percent every year\n",
    "divs.loc['2024':] *= 1.04\n",
    "divs.loc['2025':] *= 1.04\n",
    "\n",
    "# Shell recently switched to declaring dividends in USD, as a result the above estimates of future dividends are \n",
    "# also in USD. Since the underlying share is priced in EUR, we need to convert these USD dividend amounts into EUR.\n",
    "# I will use a simplistic approach of using the current EURUSD spot rate. A better approach would to use\n",
    "# the riskless rate USD curve and calculate forward exchange rates using riskneutral valuation.\n",
    "eurusd = yfin.Ticker('EURUSD=X').history(start=today-BDay(12), end=today, actions=False, auto_adjust=False)\n",
    "eurusd_rate = eurusd['Adj Close']\n",
    "divs /= eurusd_rate.iloc[-1]\n",
    "\n",
    "# Taking the trading calendar into account when pricing\n",
    "import pandas_market_calendars as mcal\n",
    "holidays = mcal.get_calendar('EUREX').holidays().holidays\n",
    "\n",
    "cur_price = asset_prices[-1]\n",
    "pricer = options.BlackScholesMertonPricer(maturity_date, vol_tracker, strike, curve, cur_price, ticker=TICKER,\n",
    "                                          dividends=divs, opt_type=options.OptionType.AMERICAN, holidays=holidays)\n",
    "print(pricer)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "defined-geography",
   "metadata": {},
   "source": [
    "Sometimes you might want to price using _an implied volatility_ for a given expiry date. You get the implied volatilty from the option prices of market makers. The `pricing.options.BlackScholesMertonPricer` class supports this. Just enter the implied volatility value instead of passing it a volatility_tracker object:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "preliminary-reform",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "SHELL.AS AMERICAN call option with strike 28.0 and maturity 2025-03-21, price: 6.60, σ: 0.3200, Δ: 0.798, Γ: 0.033, ν: 7.515\n"
     ]
    }
   ],
   "source": [
    "# Pricing with an implied volatility of 32%\n",
    "pricer = options.BlackScholesMertonPricer(maturity_date, .32, strike, curve, cur_price,\n",
    "                                          ticker=TICKER, dividends=divs, opt_type=options.OptionType.AMERICAN)\n",
    "print(pricer)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "formed-brave",
   "metadata": {},
   "source": [
    "As you can see, a different volatility resulted in a significant change in the price.\n",
    "\n",
    "Let's now price a Shell call option with a longer maturity. This is a little more complex as there are more ex-dividend dates during the option's lifetime."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "several-investigation",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "SHELL.AS AMERICAN call option with strike 28.0 and maturity 2025-12-19, price: 5.71, σ: 0.1646, Δ: 0.999, Γ: 0.001, ν: 0.033\n"
     ]
    }
   ],
   "source": [
    "# Let's get volatility forecast for next December options, i.e. maturity on the 3rd Friday of next December\n",
    "maturity_date = curve.date + relativedelta(years=0 if curve.date.month < 3 else 1, month=12, day=1, weekday=FR(3))\n",
    "pricer = options.BlackScholesMertonPricer(maturity_date, vol_tracker, strike, curve, cur_price,\n",
    "                                          ticker=TICKER, dividends=divs, opt_type=options.OptionType.AMERICAN,\n",
    "                                          holidays=holidays)\n",
    "print(pricer)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "furnished-prescription",
   "metadata": {},
   "source": [
    "If you wonder where the volatility forecast came from, it came from the GARCH(1, 1) `vol_tracker` object I passed to the BlackScholesMertonPricer. You can easily see this:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "legendary-glance",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.16460685252128204"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "vol_tracker.get_annual_term_volatility_forecast(curve.to_years(maturity_date))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "accessible-thomson",
   "metadata": {},
   "source": [
    "## Pricing using Binomial Tree Pricer\n",
    "The Binomial Tree model can be used to price any European or American option, including on stock that pays dividends.\n",
    "\n",
    "Let's put it to use to price a Shell call and put options with a strike of €28 and compare resulting prices for call options."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "secure-trinity",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "SHELL.AS AMERICAN call option with strike 28.0 and maturity 2025-12-19, price: 5.85, σ: 0.1646, Δ: 0.887, Γ: 0.047, ν: 6.556\n",
      "Price difference between Black-Scholes-Merton and Binomial Treee pricers: 0.133002\n"
     ]
    }
   ],
   "source": [
    "bin_tree_pricer = options.BinomialTreePricer(maturity_date, vol_tracker, strike, curve, cur_price,\n",
    "                                             ticker=TICKER, dividends=divs, opt_type=options.OptionType.AMERICAN,\n",
    "                                             holidays=holidays)\n",
    "print(bin_tree_pricer)\n",
    "\n",
    "print('Price difference between Black-Scholes-Merton and Binomial Treee pricers: %.6f'\n",
    "      % abs(pricer.get_price() - bin_tree_pricer.get_price()))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ceramic-borough",
   "metadata": {},
   "source": [
    "Let's now price a Shell put option with the same maturity. You cannot price put options with a BlackScholesMerton pricer, with a BinomialTreePricer you can."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "handmade-return",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "SHELL.AS AMERICAN put option with strike 28.0 and maturity 2025-12-19, price: 0.67, σ: 0.1646, Δ: -0.179, Γ: 0.043, ν: 10.056\n"
     ]
    }
   ],
   "source": [
    "bin_tree_pricer_put = options.BinomialTreePricer(maturity_date, vol_tracker, strike, curve, cur_price, is_call=False,\n",
    "                                                 ticker=TICKER, dividends=divs, opt_type=options.OptionType.AMERICAN,\n",
    "                                                 holidays=holidays)\n",
    "print(bin_tree_pricer_put)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "abroad-premium",
   "metadata": {},
   "source": [
    "#### Put-Call Parity\n",
    "An important theoretical property of the price of an American option is the so-called put-call parity, which is expressed as:\n",
    "$$S_0 - D - K <= C - P <= S_0 - K\\cdot e^{-r\\cdot T}$$\n",
    "where:\n",
    "* C is the price of an American call option\n",
    "* P is the price of the corresponding American put option\n",
    "* S<sub>0</sub> is the present price of the underlying stock\n",
    "* D is the present value of the dividents whose ex-dividend dates happen before the maturity date of the option\n",
    "* K is the strike price\n",
    "* T is the liefteime of the option expressed in years\n",
    "* r is the riskless rate for maturity T\n",
    "\n",
    "Let's put it to the test:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "sitting-thumb",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Put-Call parity: 3.58 <= 5.18 <= 6.74\n"
     ]
    }
   ],
   "source": [
    "from math import exp\n",
    "price_difference = bin_tree_pricer.get_price() - bin_tree_pricer_put.get_price()\n",
    "left_hand_side_expr = bin_tree_pricer.s0 - bin_tree_pricer.get_npv_dividends() - bin_tree_pricer.strike\n",
    "right_hand_side_expr = bin_tree_pricer.s0 - bin_tree_pricer.strike\\\n",
    "    * exp(-bin_tree_pricer.r * bin_tree_pricer.T)\n",
    "\n",
    "assert left_hand_side_expr <= price_difference <= right_hand_side_expr\n",
    "print(f'Put-Call parity: {left_hand_side_expr:.2f} <= {price_difference:.2f} <= {right_hand_side_expr:.2f}')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "loaded-chambers",
   "metadata": {},
   "source": [
    "If you wish to price with a given implied volatility, just pass it to the pricer as the second parameter:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "manufactured-cooperative",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "SHELL.AS AMERICAN call option with strike 28.0 and maturity 2025-12-19, price: 6.96, σ: 0.2800, Δ: 0.769, Γ: 0.031, ν: 11.275\n",
      "SHELL.AS AMERICAN put option with strike 28.0 and maturity 2025-12-19, price: 1.95, σ: 0.2800, Δ: -0.256, Γ: 0.031, ν: 12.877\n"
     ]
    }
   ],
   "source": [
    "impl_vol = .28\n",
    "bin_tree_pricer = options.BinomialTreePricer(maturity_date, impl_vol, strike, curve, cur_price,\n",
    "                                             ticker=TICKER, dividends=divs, opt_type=options.OptionType.AMERICAN,\n",
    "                                             holidays=holidays)\n",
    "print(bin_tree_pricer)\n",
    "bin_tree_pricer_put = options.BinomialTreePricer(maturity_date, impl_vol, strike, curve, cur_price, is_call=False,\n",
    "                                                 ticker=TICKER, dividends=divs, opt_type=options.OptionType.AMERICAN,\n",
    "                                                 holidays=holidays)\n",
    "print(bin_tree_pricer_put)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "sized-crawford",
   "metadata": {},
   "source": [
    "## Pricing with your own discount curve\n",
    "You might want to prefer to price using your own discount curve. The `YieldCurve` class of the `pricing.curves` package makes it fairly easy to do."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "latter-chase",
   "metadata": {},
   "source": [
    "The `parallel_shift` method of the `YieldCurve` class allows for pricing using a parallel shift to the yield curve. Let's price the same options but with a curve points shifted down by 200bps. As expected, this makes calls cheaper and puts more expensive."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "crude-coral",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "SHELL.AS AMERICAN call option with strike 28.0 and maturity 2025-12-19, price: 6.62, σ: 0.2800, Δ: 0.765, Γ: 0.035, ν: 10.861\n",
      "SHELL.AS AMERICAN put option with strike 28.0 and maturity 2025-12-19, price: 2.26, σ: 0.2800, Δ: -0.285, Γ: 0.033, ν: 13.561\n"
     ]
    }
   ],
   "source": [
    "bin_tree_pricer = options.BinomialTreePricer(maturity_date, impl_vol, strike, curve.parallel_shift(-200), cur_price,\n",
    "                                             ticker=TICKER, dividends=divs, opt_type=options.OptionType.AMERICAN,\n",
    "                                             holidays=holidays)\n",
    "print(bin_tree_pricer)\n",
    "bin_tree_pricer_put = options.BinomialTreePricer(maturity_date, impl_vol, strike, curve.parallel_shift(-200),\n",
    "                                                 cur_price, is_call=False, ticker=TICKER, dividends=divs,\n",
    "                                                 opt_type=options.OptionType.AMERICAN, holidays=holidays)\n",
    "print(bin_tree_pricer_put)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "marked-mouth",
   "metadata": {},
   "source": [
    "Let's now price with a flat discount curve, which I'll construct by reusing the offsets from earlier in this notebook:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "laden-extraction",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "SHELL.AS AMERICAN call option with strike 28.0 and maturity 2025-12-19, price: 6.78, σ: 0.2800, Δ: 0.766, Γ: 0.033, ν: 11.357\n",
      "SHELL.AS AMERICAN put option with strike 28.0 and maturity 2025-12-19, price: 2.10, σ: 0.2800, Δ: -0.270, Γ: 0.032, ν: 13.237\n"
     ]
    }
   ],
   "source": [
    "# Reusing 'relativedelta' offsets defined in Cell 3, which are for 0, 1 month, 3 months, 6 months, 1 year, 2 years,\n",
    "# 3 years, 5 years, 7 years, 10 years, 20 years, 30 years.\",\n",
    "\n",
    "# Defining a flat curve with a discount rate of 2% and yearly compounding frequency.\n",
    "custom_curve = curves.YieldCurve(today, offsets, [.02]*len(offsets), compounding_freq=1)\n",
    "\n",
    "bin_tree_pricer = options.BinomialTreePricer(maturity_date, impl_vol, strike, custom_curve, cur_price,\n",
    "                                             ticker=TICKER, dividends=divs, opt_type=options.OptionType.AMERICAN,\n",
    "                                             holidays=holidays)\n",
    "print(bin_tree_pricer)\n",
    "bin_tree_pricer_put = options.BinomialTreePricer(maturity_date, impl_vol, strike, custom_curve, cur_price,\n",
    "                                                 is_call=False, ticker=TICKER, dividends=divs,\n",
    "                                                 opt_type=options.OptionType.AMERICAN, holidays=holidays)\n",
    "print(bin_tree_pricer_put)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "radio-brass",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.9.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}