Backtesting moving average crossover

backtesting-moving-average-crossover.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "https://www.quantstart.com/articles/Research-Backtesting-Environments-in-Python-with-pandas"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Requirements\n",
    "- Quandl\n",
    "- Python 3.4\n",
    "- pandas==0.17.1\n",
    "- numpy==1.10.4\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/usr/local/lib/python3.4/site-packages/pandas/io/data.py:33: FutureWarning: \n",
      "The pandas.io.data module is moved to a separate package (pandas-datareader) and will be removed from pandas in a future version.\n",
      "After installing the pandas-datareader package (https://github.com/pydata/pandas-datareader), you can change the import ``from pandas.io import data, wb`` to ``from pandas_datareader import data, wb``.\n",
      "  FutureWarning)\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import Quandl   # Necessary for obtaining financial data easily\n",
    "from abc import ABCMeta, abstractmethod\n",
    "\n",
    "import datetime\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "from pandas.io.data import DataReader"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Random strategy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "class Strategy(object):\n",
    "    \"\"\"Strategy is an abstract base class providing an interface for\n",
    "    all subsequent (inherited) trading strategies.\n",
    "\n",
    "    The goal of a (derived) Strategy object is to output a list of signals,\n",
    "    which has the form of a time series indexed pandas DataFrame.\n",
    "\n",
    "    In this instance only a single symbol/instrument is supported.\"\"\"\n",
    "\n",
    "    __metaclass__ = ABCMeta\n",
    "\n",
    "    @abstractmethod\n",
    "    def generate_signals(self):\n",
    "        \"\"\"An implementation is required to return the DataFrame of symbols \n",
    "        containing the signals to go long, short or hold (1, -1 or 0).\"\"\"\n",
    "        raise NotImplementedError(\"Should implement generate_signals()!\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "class Portfolio(object):\n",
    "    \"\"\"An abstract base class representing a portfolio of \n",
    "    positions (including both instruments and cash), determined\n",
    "    on the basis of a set of signals provided by a Strategy.\"\"\"\n",
    "\n",
    "    __metaclass__ = ABCMeta\n",
    "\n",
    "    @abstractmethod\n",
    "    def generate_positions(self):\n",
    "        \"\"\"Provides the logic to determine how the portfolio \n",
    "        positions are allocated on the basis of forecasting\n",
    "        signals and available cash.\"\"\"\n",
    "        raise NotImplementedError(\"Should implement generate_positions()!\")\n",
    "\n",
    "    @abstractmethod\n",
    "    def backtest_portfolio(self):\n",
    "        \"\"\"Provides the logic to generate the trading orders\n",
    "        and subsequent equity curve (i.e. growth of total equity),\n",
    "        as a sum of holdings and cash, and the bar-period returns\n",
    "        associated with this curve based on the 'positions' DataFrame.\n",
    "\n",
    "        Produces a portfolio object that can be examined by \n",
    "        other classes/functions.\"\"\"\n",
    "        raise NotImplementedError(\"Should implement backtest_portfolio()!\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "class RandomForecastingStrategy(Strategy):\n",
    "    \"\"\"Derives from Strategy to produce a set of signals that\n",
    "    are randomly generated long/shorts. Clearly a nonsensical\n",
    "    strategy, but perfectly acceptable for demonstrating the\n",
    "    backtesting infrastructure!\"\"\"    \n",
    "    \n",
    "    def __init__(self, symbol, bars):\n",
    "        \"\"\"Requires the symbol ticker and the pandas DataFrame of bars\"\"\"\n",
    "        self.symbol = symbol\n",
    "        self.bars = bars\n",
    "\n",
    "    def generate_signals(self):\n",
    "        \"\"\"Creates a pandas DataFrame of random signals.\"\"\"\n",
    "        signals = pd.DataFrame(index=self.bars.index)\n",
    "        signals['signal'] = np.sign(np.random.randn(len(signals)))\n",
    "\n",
    "        # The first five elements are set to zero in order to minimise\n",
    "        # upstream NaN errors in the forecaster.\n",
    "        signals['signal'][0:5] = 0.0\n",
    "        return signals"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "class MarketOnOpenPortfolio(Portfolio):\n",
    "    \"\"\"Inherits Portfolio to create a system that purchases 100 units of \n",
    "    a particular symbol upon a long/short signal, assuming the market \n",
    "    open price of a bar.\n",
    "\n",
    "    In addition, there are zero transaction costs and cash can be immediately \n",
    "    borrowed for shorting (no margin posting or interest requirements). \n",
    "\n",
    "    Requires:\n",
    "    symbol - A stock symbol which forms the basis of the portfolio.\n",
    "    bars - A DataFrame of bars for a symbol set.\n",
    "    signals - A pandas DataFrame of signals (1, 0, -1) for each symbol.\n",
    "    initial_capital - The amount in cash at the start of the portfolio.\"\"\"\n",
    "\n",
    "    def __init__(self, symbol, bars, signals, initial_capital=100000.0):\n",
    "        self.symbol = symbol        \n",
    "        self.bars = bars\n",
    "        self.signals = signals\n",
    "        self.initial_capital = float(initial_capital)\n",
    "        self.positions = self.generate_positions()\n",
    "        \n",
    "    def generate_positions(self):\n",
    "        \"\"\"Creates a 'positions' DataFrame that simply longs or shorts\n",
    "        100 of the particular symbol based on the forecast signals of\n",
    "        {1, 0, -1} from the signals DataFrame.\"\"\"\n",
    "        positions = pd.DataFrame(index=self.signals.index).fillna(0.0)\n",
    "        positions[self.symbol] = 100 * self.signals['signal']\n",
    "        return positions\n",
    "                    \n",
    "    def backtest_portfolio(self):\n",
    "        \"\"\"Constructs a portfolio from the positions DataFrame by \n",
    "        assuming the ability to trade at the precise market open price\n",
    "        of each bar (an unrealistic assumption!). \n",
    "\n",
    "        Calculates the total of cash and the holdings (market price of\n",
    "        each position per bar), in order to generate an equity curve\n",
    "        ('total') and a set of bar-based returns ('returns').\n",
    "\n",
    "        Returns the portfolio object to be used elsewhere.\"\"\"\n",
    "\n",
    "        # Construct the portfolio DataFrame to use the same index\n",
    "        # as 'positions' and with a set of 'trading orders' in the\n",
    "        # 'pos_diff' object, assuming market open prices.\n",
    "        pf = pd.DataFrame(index=self.bars.index)\n",
    "        # Price of current operation\n",
    "        pf['holdings'] = self.positions.mul(self.bars['Open'], axis='index')\n",
    "        pf['cash'] = self.initial_capital - pf['holdings'].cumsum()\n",
    "        pf['total'] = pf['cash'] + self.positions[self.symbol].cumsum() * self.bars['Open']\n",
    "        pf['returns'] = pf['total'].pct_change()\n",
    "        return pf"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "symbol = 'SPY'\n",
    "bars = Quandl.get(\"GOOG/NYSE_%s\" % symbol, collapse=\"daily\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Open</th>\n",
       "      <th>High</th>\n",
       "      <th>Low</th>\n",
       "      <th>Close</th>\n",
       "      <th>Volume</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Date</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1997-08-21</th>\n",
       "      <td>0</td>\n",
       "      <td>94.25</td>\n",
       "      <td>92.09</td>\n",
       "      <td>92.59</td>\n",
       "      <td>5392600</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1997-08-22</th>\n",
       "      <td>0</td>\n",
       "      <td>92.73</td>\n",
       "      <td>90.56</td>\n",
       "      <td>92.56</td>\n",
       "      <td>7172900</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1997-08-25</th>\n",
       "      <td>0</td>\n",
       "      <td>93.41</td>\n",
       "      <td>91.84</td>\n",
       "      <td>92.22</td>\n",
       "      <td>3888000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1997-08-26</th>\n",
       "      <td>0</td>\n",
       "      <td>92.56</td>\n",
       "      <td>90.70</td>\n",
       "      <td>90.86</td>\n",
       "      <td>4290000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1997-08-27</th>\n",
       "      <td>0</td>\n",
       "      <td>91.97</td>\n",
       "      <td>90.41</td>\n",
       "      <td>91.41</td>\n",
       "      <td>5484300</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            Open   High    Low  Close   Volume\n",
       "Date                                          \n",
       "1997-08-21     0  94.25  92.09  92.59  5392600\n",
       "1997-08-22     0  92.73  90.56  92.56  7172900\n",
       "1997-08-25     0  93.41  91.84  92.22  3888000\n",
       "1997-08-26     0  92.56  90.70  90.86  4290000\n",
       "1997-08-27     0  91.97  90.41  91.41  5484300"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bars.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "# Fix open 0\n",
    "bars = bars[bars.Open > 0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "# Create a set of random forecasting signals for SPY\n",
    "rfs = RandomForecastingStrategy(symbol, bars)\n",
    "signals = rfs.generate_signals()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>signal</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Date</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2000-01-03</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2000-01-04</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2000-01-05</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2000-01-06</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2000-01-07</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2000-01-10</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2000-01-11</th>\n",
       "      <td>-1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2000-01-12</th>\n",
       "      <td>-1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2000-01-13</th>\n",
       "      <td>-1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2000-01-14</th>\n",
       "      <td>-1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            signal\n",
       "Date              \n",
       "2000-01-03       0\n",
       "2000-01-04       0\n",
       "2000-01-05       0\n",
       "2000-01-06       0\n",
       "2000-01-07       0\n",
       "2000-01-10       1\n",
       "2000-01-11      -1\n",
       "2000-01-12      -1\n",
       "2000-01-13      -1\n",
       "2000-01-14      -1"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "signals.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "portfolio = MarketOnOpenPortfolio(symbol, bars, signals, initial_capital=100000.0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "pf = portfolio.backtest_portfolio()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>holdings</th>\n",
       "      <th>cash</th>\n",
       "      <th>total</th>\n",
       "      <th>returns</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Date</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2000-01-03</th>\n",
       "      <td>0</td>\n",
       "      <td>100000</td>\n",
       "      <td>100000</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2000-01-04</th>\n",
       "      <td>0</td>\n",
       "      <td>100000</td>\n",
       "      <td>100000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2000-01-05</th>\n",
       "      <td>0</td>\n",
       "      <td>100000</td>\n",
       "      <td>100000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2000-01-06</th>\n",
       "      <td>0</td>\n",
       "      <td>100000</td>\n",
       "      <td>100000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2000-01-07</th>\n",
       "      <td>0</td>\n",
       "      <td>100000</td>\n",
       "      <td>100000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2000-01-10</th>\n",
       "      <td>14625</td>\n",
       "      <td>85375</td>\n",
       "      <td>100000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2000-01-11</th>\n",
       "      <td>-14581</td>\n",
       "      <td>99956</td>\n",
       "      <td>99956</td>\n",
       "      <td>-0.000440</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2000-01-12</th>\n",
       "      <td>-14459</td>\n",
       "      <td>114415</td>\n",
       "      <td>99956</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2000-01-13</th>\n",
       "      <td>-14447</td>\n",
       "      <td>128862</td>\n",
       "      <td>99968</td>\n",
       "      <td>0.000120</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2000-01-14</th>\n",
       "      <td>-14653</td>\n",
       "      <td>143515</td>\n",
       "      <td>99556</td>\n",
       "      <td>-0.004121</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            holdings    cash   total   returns\n",
       "Date                                          \n",
       "2000-01-03         0  100000  100000       NaN\n",
       "2000-01-04         0  100000  100000  0.000000\n",
       "2000-01-05         0  100000  100000  0.000000\n",
       "2000-01-06         0  100000  100000  0.000000\n",
       "2000-01-07         0  100000  100000  0.000000\n",
       "2000-01-10     14625   85375  100000  0.000000\n",
       "2000-01-11    -14581   99956   99956 -0.000440\n",
       "2000-01-12    -14459  114415   99956  0.000000\n",
       "2000-01-13    -14447  128862   99968  0.000120\n",
       "2000-01-14    -14653  143515   99556 -0.004121"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pf.head(10)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "# BACKTESTING A MOVING AVERAGE CROSSOVER \n",
    "https://www.quantstart.com/articles/Backtesting-a-Moving-Average-Crossover-in-Python-with-pandas"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "class MovingAverageCrossStrategy(Strategy):\n",
    "    \"\"\"    \n",
    "    Requires:\n",
    "    symbol - A stock symbol on which to form a strategy on.\n",
    "    bars - A DataFrame of bars for the above symbol.\n",
    "    short_window - Lookback period for short moving average.\n",
    "    long_window - Lookback period for long moving average.\"\"\"\n",
    "\n",
    "    def __init__(self, symbol, bars, short_window=100, long_window=400):\n",
    "        self.symbol = symbol\n",
    "        self.bars = bars\n",
    "\n",
    "        self.short_window = short_window\n",
    "        self.long_window = long_window\n",
    "\n",
    "    def generate_signals(self):\n",
    "        \"\"\"Returns the DataFrame of symbols containing the signals\n",
    "        to go long, short or hold (1, -1 or 0).\"\"\"\n",
    "        signals = pd.DataFrame(index=self.bars.index)\n",
    "        signals['signal'] = 0.0\n",
    "\n",
    "        # Create the set of short and long simple moving averages over the \n",
    "        # respective periods\n",
    "        signals['short_mavg'] = pd.rolling_mean(self.bars['Close'], self.short_window, min_periods=1)\n",
    "        signals['long_mavg'] = pd.rolling_mean(self.bars['Close'], self.long_window, min_periods=1)\n",
    "\n",
    "        # Create a 'signal' (invested or not invested) when the short moving average crosses the long\n",
    "        # moving average, but only for the period greater than the shortest moving average window\n",
    "        signals['signal'][self.short_window:] = np.where(signals['short_mavg'][self.short_window:] \n",
    "            > signals['long_mavg'][self.short_window:], 1.0, 0.0)   \n",
    "\n",
    "        # Take the difference of the signals in order to generate actual trading orders\n",
    "        signals['positions'] = signals['signal'].diff()   \n",
    "\n",
    "        return signals"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "class MarketOnClosePortfolio(Portfolio):\n",
    "    \"\"\"Encapsulates the notion of a portfolio of positions based\n",
    "    on a set of signals as provided by a Strategy.\n",
    "\n",
    "    Requires:\n",
    "    symbol - A stock symbol which forms the basis of the portfolio.\n",
    "    bars - A DataFrame of bars for a symbol set.\n",
    "    signals - A pandas DataFrame of signals (1, 0, -1) for each symbol.\n",
    "    initial_capital - The amount in cash at the start of the portfolio.\"\"\"\n",
    "\n",
    "    def __init__(self, symbol, bars, signals, initial_capital=100000.0):\n",
    "        self.symbol = symbol        \n",
    "        self.bars = bars\n",
    "        self.signals = signals\n",
    "        self.initial_capital = float(initial_capital)\n",
    "        self.positions = self.generate_positions()\n",
    "        \n",
    "    def generate_positions(self):\n",
    "        positions = pd.DataFrame(index=self.signals.index).fillna(0.0)\n",
    "        positions[self.symbol] = 100 * self.signals['positions']   # This strategy buys 100 shares\n",
    "        return positions\n",
    "                    \n",
    "    def backtest_portfolio(self):\n",
    "        pf = pd.DataFrame(index=self.bars.index)\n",
    "        pf['holdings'] = self.positions.mul(self.bars['Close'], axis='index')\n",
    "        pf['cash'] = self.initial_capital - pf['holdings'].cumsum()\n",
    "        pf['total'] = pf['cash'] + self.positions[self.symbol].cumsum() * self.bars['Close']\n",
    "        pf['returns'] = pf['total'].pct_change()\n",
    "        return pf"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "# Obtain daily bars of AAPL from Yahoo Finance for the period\n",
    "# 1st Jan 1990 to 1st Jan 2002 - This is an example from ZipLine\n",
    "symbol = 'AAPL'\n",
    "bars = DataReader(symbol, \"yahoo\", datetime.datetime(1990, 1, 1), datetime.datetime(2002, 1, 1))\n",
    "\n",
    "# Create a Moving Average Cross Strategy instance with a short moving\n",
    "# average window of 100 days and a long window of 400 days\n",
    "mac = MovingAverageCrossStrategy(symbol, bars, short_window=100, long_window=400)\n",
    "signals = mac.generate_signals()\n",
    "\n",
    "# Create a portfolio of AAPL, with $100,000 initial capital\n",
    "portfolio = MarketOnClosePortfolio(symbol, bars, signals, initial_capital=100000.0)\n",
    "pf = portfolio.backtest_portfolio()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Open</th>\n",
       "      <th>High</th>\n",
       "      <th>Low</th>\n",
       "      <th>Close</th>\n",
       "      <th>Volume</th>\n",
       "      <th>Adj Close</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Date</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1990-01-02</th>\n",
       "      <td>35.249999</td>\n",
       "      <td>37.500000</td>\n",
       "      <td>35.000000</td>\n",
       "      <td>37.250001</td>\n",
       "      <td>45799600</td>\n",
       "      <td>1.151017</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1990-01-03</th>\n",
       "      <td>37.999999</td>\n",
       "      <td>37.999999</td>\n",
       "      <td>37.500000</td>\n",
       "      <td>37.500000</td>\n",
       "      <td>51998800</td>\n",
       "      <td>1.158742</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1990-01-04</th>\n",
       "      <td>38.250001</td>\n",
       "      <td>38.749999</td>\n",
       "      <td>37.250001</td>\n",
       "      <td>37.625000</td>\n",
       "      <td>55378400</td>\n",
       "      <td>1.162604</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1990-01-05</th>\n",
       "      <td>37.750000</td>\n",
       "      <td>38.250001</td>\n",
       "      <td>36.999999</td>\n",
       "      <td>37.750000</td>\n",
       "      <td>30828000</td>\n",
       "      <td>1.166467</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1990-01-08</th>\n",
       "      <td>37.500000</td>\n",
       "      <td>37.999999</td>\n",
       "      <td>36.999999</td>\n",
       "      <td>37.999999</td>\n",
       "      <td>25393200</td>\n",
       "      <td>1.174191</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                 Open       High        Low      Close    Volume  Adj Close\n",
       "Date                                                                       \n",
       "1990-01-02  35.249999  37.500000  35.000000  37.250001  45799600   1.151017\n",
       "1990-01-03  37.999999  37.999999  37.500000  37.500000  51998800   1.158742\n",
       "1990-01-04  38.250001  38.749999  37.250001  37.625000  55378400   1.162604\n",
       "1990-01-05  37.750000  38.250001  36.999999  37.750000  30828000   1.166467\n",
       "1990-01-08  37.500000  37.999999  36.999999  37.999999  25393200   1.174191"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bars.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Plot two charts to assess trades and equity curve"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 102,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/usr/local/lib/python3.4/site-packages/matplotlib/figure.py:397: UserWarning: matplotlib is currently using a non-GUI backend, so cannot show the figure\n",
      "  \"matplotlib is currently using a non-GUI backend, \"\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA4sAAAR+CAYAAAB566BHAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nB5JFAAAAAEAPJIsAAAAAgB7+H3D2GEyfkWIrAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7ff78cbd5908>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig = plt.figure(figsize=(15, 20))\n",
    "#fig = plt.figure()\n",
    "fig.patch.set_facecolor('white')     # Set the outer colour to white\n",
    "ax1 = fig.add_subplot(411,  ylabel='Price in $')\n",
    "\n",
    "# Plot the AAPL closing price overlaid with the moving averages\n",
    "bars['Close'].plot(ax=ax1, color='r', lw=2.)\n",
    "signals[['short_mavg', 'long_mavg']].plot(ax=ax1, lw=2.)\n",
    "\n",
    "# Plot the \"buy\" trades against AAPL\n",
    "ax1.plot(signals.ix[signals.positions == 1.0].index, \n",
    "         signals.short_mavg[signals.positions == 1.0],\n",
    "         '^', markersize=10, color='m')\n",
    "\n",
    "# Plot the \"sell\" trades against AAPL\n",
    "ax1.plot(signals.ix[signals.positions == -1.0].index, \n",
    "         signals.short_mavg[signals.positions == -1.0],\n",
    "         'v', markersize=10, color='k')\n",
    "\n",
    "# Plot the equity curve in dollars\n",
    "ax2 = fig.add_subplot(412, ylabel='Portfolio value in $')\n",
    "pf['total'].plot(ax=ax2, lw=2.)\n",
    "\n",
    "# Plot the \"buy\" and \"sell\" trades against the equity curve\n",
    "ax2.plot(pf.ix[signals.positions == 1.0].index, \n",
    "         pf.total[signals.positions == 1.0],\n",
    "         '^', markersize=10, color='m')\n",
    "ax2.plot(pf.ix[signals.positions == -1.0].index, \n",
    "         pf.total[signals.positions == -1.0],\n",
    "         'v', markersize=10, color='k')\n",
    "\n",
    "# signal\n",
    "ax3 = fig.add_subplot(413, ylabel='signal')\n",
    "signals.signal.plot(ax=ax3)\n",
    "\n",
    "# signal\n",
    "ax4 = fig.add_subplot(414, ylabel='signal')\n",
    "signals.positions.plot(ax=ax4)\n",
    "\n",
    "# Plot the figure\n",
    "fig.show()"
   ]
  }
 ],
 "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": "3.4.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}