nb/fred-oil-brent-wti.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Crude Oil :: Brent vs. West Texas Intermediate (WTI)\n",
    "\n",
    "We examine the history of crude oil prices, and their spreads.\n",
    "A Boltzmann portfolio is computed for *optimal* financial positions.\n",
    "\n",
    "Deflated prices give additional insight, along with some of the\n",
    "statistical tools useful in financial economics.\n",
    "\n",
    "***Although WTI is more desirable than Brent from a petrochemical\n",
    "perspective, that preference is reversed when the metrics\n",
    "are financial.***\n",
    "\n",
    "Unless otherwise noted, the price per barrel is in U.S. dollars.\n",
    "The source of the data is the U.S. Department of Energy via FRED.\n",
    "We will use Federal Reserve USD index units to compute oil prices in non-dollar terms."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Petrochemical background\n",
    "\n",
    "Before exploring our financial metrics, let's get familiar\n",
    "with the physical aspects.\n",
    "\n",
    "> **Crude oil is arguably the most crucial commodity in the world today.**\n",
    "An important issue is the different benchmarks for crude oil prices. \n",
    "\n",
    "> The American Petroleum Institute ***API gravity*** is a measure that is\n",
    "used to compare a petroleum liquid's density to water.\n",
    "This scale generally falls between 10 and 70, with \"light\" crude oil\n",
    "typically having an API gravity on the higher side of the range, while\n",
    "\"heavy\" oil has a reading that falls on the lower end of the range.\n",
    "\n",
    "> The sulfur content of petroleum must also be considered.\n",
    "***Sulfur content of 0.50% is a key benchmark.***\n",
    "When oil has a total sulfur level greater than the benchmark, it is considered \"sour.\"\n",
    "Sulfur content less than the benchmark indicates that an oil is \"sweet.\"\n",
    "Sour crude oil is more prevalent than its sweet counterpart and comes from\n",
    "oil sands in Canada, the Gulf of Mexico, some South American nations,\n",
    "as well as most of the Middle East.\n",
    "Sweet crude is typically produced in the central United States,\n",
    "the North Sea region of Europe, and much of Africa and the Asia Pacific region.\n",
    "*End users generally prefer sweet crude as it requires less processing\n",
    "to remove impurities than its sour counterpart.*\n",
    "\n",
    "> [Edited source: Daniela Pylypczak-Wasylyszyn](http://commodityhq.com/education/crude-oil-guide-brent-vs-wti-whats-the-difference)\n",
    "\n",
    "Light and sweet forms of crude oil are generally valued higher while\n",
    "heavy and sour types often trade at a discount.\n",
    "These two key factors distinguish the two major benchmarks for\n",
    "world oil prices: West Texas Intermediate (WTI) and Brent crude oil.\n",
    "\n",
    "***WTI is generally lighter and sweeter than Brent, but the supply of each\n",
    "can differ considerably over time, thus their price difference will vary.***\n",
    "\n",
    "WTI is refined mostly in the Midwest and Gulf Coast regions of the United States,\n",
    "while Brent oil is typically refined in Northwest Europe.\n",
    "\n",
    "#### Approximate characteristics:\n",
    "- **Brent**: API gravity 38.06, sulfur 0.37%\n",
    "- **WTI**: API gravity 39.6, sulfur 0.24%\n",
    "\n",
    "---"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "*Dependencies:*\n",
    "\n",
    "- Repository: https://github.com/rsvp/fecon235\n",
    "\n",
    "*CHANGE LOG*\n",
    "\n",
    "    2017-08-08  Fix #2 and introduce Boltzmann portfolio of oils.\n",
    "    2015-05-26  Code review and revision.\n",
    "    2014-10-09  First version for oil, using 2014-09-28 Template."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from fecon235.fecon235 import *"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      " ::  Python 2.7.13\n",
      " ::  IPython 5.1.0\n",
      " ::  jupyter_core 4.2.1\n",
      " ::  notebook 4.1.0\n",
      " ::  matplotlib 1.5.1\n",
      " ::  numpy 1.11.0\n",
      " ::  scipy 0.17.0\n",
      " ::  sympy 1.0\n",
      " ::  pandas 0.19.2\n",
      " ::  pandas_datareader 0.2.1\n",
      " ::  Repository: fecon235 v5.17.0722 develop\n",
      " ::  Timestamp: 2017-08-09T09:31:30Z\n",
      " ::  $pwd: /media/yaya/virt15h/virt/dbx/Dropbox/ipy/fecon235/nb\n"
     ]
    }
   ],
   "source": [
    "#  PREAMBLE-p6.15.1223d :: Settings and system details\n",
    "from __future__ import absolute_import, print_function, division\n",
    "system.specs()\n",
    "pwd = system.getpwd()   # present working directory as variable.\n",
    "print(\" ::  $pwd:\", pwd)\n",
    "#  If a module is modified, automatically reload it:\n",
    "%load_ext autoreload\n",
    "%autoreload 2\n",
    "#       Use 0 to disable this feature.\n",
    "\n",
    "#  Notebook DISPLAY options:\n",
    "#      Represent pandas DataFrames as text; not HTML representation:\n",
    "import pandas as pd\n",
    "pd.set_option( 'display.notebook_repr_html', False )\n",
    "from IPython.display import HTML # useful for snippets\n",
    "#  e.g. HTML('<iframe src=http://en.mobile.wikipedia.org/?useformat=mobile width=700 height=350></iframe>')\n",
    "from IPython.display import Image \n",
    "#  e.g. Image(filename='holt-winters-equations.png', embed=True) # url= also works\n",
    "from IPython.display import YouTubeVideo\n",
    "#  e.g. YouTubeVideo('1j_HxD4iLn8', start='43', width=600, height=400)\n",
    "from IPython.core import page\n",
    "get_ipython().set_hook('show_in_pager', page.as_hook(page.display_page), 0)\n",
    "#  Or equivalently in config file: \"InteractiveShell.display_page = True\", \n",
    "#  which will display results in secondary notebook pager frame in a cell.\n",
    "\n",
    "#  Generate PLOTS inside notebook, \"inline\" generates static png:\n",
    "%matplotlib inline   \n",
    "#          \"notebook\" argument allows interactive zoom and resize."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "#  Define dictionary for dataframe:\n",
    "oils4d = { 'Brent' : d4brent, 'WTI' : d4wti }"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#  Retrieve data:\n",
    "oils = groupget( oils4d )"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## BoW spread := Brent - WTI\n",
    "\n",
    "***Brent over WTI spread***"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "#  Define price variables individually for convenience:\n",
    "brent = oils['Brent']\n",
    "wti   = oils['WTI']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "#  Define BoW: Brent over WTI spread:\n",
    "bow = todf( brent - wti, 'BoW' )"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### The difference between Brent and WTI is not superficial in the 21st century. Brent over WTI, bow, can represent over 20% of the underlying oil price!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXYAAAEaCAYAAAAFaHxEAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\ni/H/AfTmiOUogeybAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0xa982910c>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plot( bow )"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Define \"Oil\" as weighted average price\n",
    "\n",
    "When BoW is non-zero, the price of \"Oil\" is ambiguous,\n",
    "thus we define a weighted average price of oil\n",
    "between Brent and WTI.\n",
    "\n",
    "Note that the composition of Brent oil benchmark no longer\n",
    "really represents Brent as an location."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "#  Set wtbrent, the primary weight for Oil:\n",
    "wtbrent = 0.50\n",
    "#         0.50 represents the mean\n",
    "#  ==================================\n",
    "wtwti   = 1 - wtbrent\n",
    "\n",
    "#  Weighted average:\n",
    "oil = todf( (wtbrent * brent) + (wtwti * wti), 'Oil' )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXQAAAEaCAYAAAABnax5AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nYbQR/j8z0wHAcGc+GQAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0xa97d138c>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plot( oil )"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**The Great Recession plunge from \\$140 to \\$40 is extraordinary.**\n",
    "*But so is the post-2014 crash which wiped out legendary traders.*\n",
    "The volatility is around 33% annualized, as we shall see later.\n",
    "\n",
    "[Using equal weights, we have created two synthetic series called `d4oil` and `m4oil`\n",
    "for future convenience.]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "             Brent          WTI          Oil\n",
      "count  7879.000000  7879.000000  7879.000000\n",
      "mean     45.011701    44.248576    44.630138\n",
      "std      33.469778    30.000004    31.660557\n",
      "min       9.100000    10.820000     9.960000\n",
      "25%      18.500000    19.850000    19.177500\n",
      "50%      28.560000    30.080000    29.275000\n",
      "75%      64.985000    64.870000    64.987500\n",
      "max     143.950000   145.310000   144.630000\n",
      "\n",
      " ::  Index on min:\n",
      "Brent   1998-12-10\n",
      "WTI     1998-12-10\n",
      "Oil     1998-12-10\n",
      "dtype: datetime64[ns]\n",
      "\n",
      " ::  Index on max:\n",
      "Brent   2008-07-03\n",
      "WTI     2008-07-03\n",
      "Oil     2008-07-03\n",
      "dtype: datetime64[ns]\n",
      "\n",
      " ::  Head:\n",
      "            Brent    WTI     Oil\n",
      "T                               \n",
      "1987-05-20  18.63  19.75  19.190\n",
      "1987-05-21  18.45  19.95  19.200\n",
      "1987-05-22  18.55  19.68  19.115\n",
      " ::  Tail:\n",
      "            Brent    WTI    Oil\n",
      "T                              \n",
      "2017-07-27  50.67  49.05  49.86\n",
      "2017-07-28  52.00  49.72  50.86\n",
      "2017-07-31  51.99  50.21  51.10\n",
      "\n",
      " ::  Correlation matrix:\n",
      "          Brent       WTI       Oil\n",
      "Brent  1.000000  0.990614  0.997901\n",
      "WTI    0.990614  1.000000  0.997386\n",
      "Oil    0.997901  0.997386  1.000000\n"
     ]
    }
   ],
   "source": [
    "#  Temporarily combine data for Brent, WTI, and weighted Oil:\n",
    "stats( paste([oils, oil]) )"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The very tight correlation between Brent and WTI (> 99%)\n",
    "can mask the potential turbulence of the BoW spread. \n",
    "\n",
    "## BoW spread as a function of Oil price"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      " ::  FIRST variable:\n",
      "count    7879.000000\n",
      "mean        0.763125\n",
      "std         5.557796\n",
      "min       -22.180000\n",
      "25%        -1.810000\n",
      "50%        -1.160000\n",
      "75%         0.685000\n",
      "max        29.590000\n",
      "Name: BoW, dtype: float64\n",
      "\n",
      " ::  SECOND variable:\n",
      "count    7879.000000\n",
      "mean       44.630138\n",
      "std        31.660557\n",
      "min         9.960000\n",
      "25%        19.177500\n",
      "50%        29.275000\n",
      "75%        64.987500\n",
      "max       144.630000\n",
      "Name: Oil, dtype: float64\n",
      "\n",
      " ::  CORRELATION\n",
      "0.625773327194\n",
      "                            OLS Regression Results                            \n",
      "==============================================================================\n",
      "Dep. Variable:                      Y   R-squared:                       0.392\n",
      "Model:                            OLS   Adj. R-squared:                  0.392\n",
      "Method:                 Least Squares   F-statistic:                     5070.\n",
      "Date:                Wed, 09 Aug 2017   Prob (F-statistic):               0.00\n",
      "Time:                        02:31:49   Log-Likelihood:                -22736.\n",
      "No. Observations:                7879   AIC:                         4.548e+04\n",
      "Df Residuals:                    7877   BIC:                         4.549e+04\n",
      "Df Model:                           1                                         \n",
      "Covariance Type:            nonrobust                                         \n",
      "==============================================================================\n",
      "                 coef    std err          t      P>|t|      [95.0% Conf. Int.]\n",
      "------------------------------------------------------------------------------\n",
      "Intercept     -4.1395      0.084    -49.036      0.000        -4.305    -3.974\n",
      "X              0.1099      0.002     71.203      0.000         0.107     0.113\n",
      "==============================================================================\n",
      "Omnibus:                     1718.842   Durbin-Watson:                   0.053\n",
      "Prob(Omnibus):                  0.000   Jarque-Bera (JB):            10202.633\n",
      "Skew:                           0.913   Prob(JB):                         0.00\n",
      "Kurtosis:                       8.267   Cond. No.                         94.6\n",
      "==============================================================================\n",
      "\n",
      "Warnings:\n",
      "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n"
     ]
    }
   ],
   "source": [
    "#  Do the regression:\n",
    "stat2( bow['BoW'], oil['Oil'] )"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Does the price of Oil influence the BoW spread?\n",
    "Not much, the correlation is about 63%, and the linear regression is not robust.\n",
    "\n",
    "*To roughly estimate BoW*: take 11% of Oil price and subtract $4.\n",
    "So higher Oil prices imply greater Brent premium over WTI."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Record LOW: Oil on 1998-12-10 at 9.96 USD\n",
    "\n",
    "We use that date to define the variable `tmin`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "tmin = '1998-12-10'"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**What is the geometric mean rate since tmin?**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[1.9017090903568512,\n",
       " 8.6098951245776831,\n",
       " 33.342833957643094,\n",
       " 7.4891318245988723,\n",
       " 256,\n",
       " 4862]"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "gemrat( oil[tmin:], yearly=256 )"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "May 2015: The geometric mean rate since tmin is around 11%\n",
    "with volatility of 33% -- both very high relative to traditional assets.\n",
    "\n",
    "Aug 2017: The geometric mean rate since tmin is down to around 2%\n",
    "with volatility still of 33%. The kurtosis of 7.5 is very high\n",
    "since it would be 3 for a Gaussian distribution:\n",
    "hence oil returns are leptokurtotic, i.e. have \"fat tails.\""
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Oil trend since tmin on 1998-12-10\n",
    "\n",
    "Given the high price volatility,\n",
    "what seems to be underlying trend?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      " ::  regresstime slope = 0.0131256573363\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXQAAAEaCAYAAAABnax5AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0xa9b6698c>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plot( trend(todf(oil[tmin:])) )"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Oil prices can easily go +/- 40% off their statistical trend (about 1.2 std).\n",
    "So the trend is very deceptive.\n",
    "\n",
    "Aug 2017: the trend indicates \\$92 oil, but the\n",
    "current market average is in fact around \\$50."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Boltzmann portfolio of oils\n",
    "\n",
    "Given the BoW spread, correlations, volatilities, and overall uptrend --\n",
    "what would be an *optimal* portfolio structure out-of-sample?\n",
    "\n",
    "We shall compute a **Boltzmann portfolio**\n",
    "(see https://git.io/boltz1 for details),\n",
    "consisting of Brent and WTI, which uses cross-entropy\n",
    "as its foundation for best geometric growth at minimized risk.\n",
    "\n",
    "The short-side shall be practically unrestricted (floor=level=-25)\n",
    "since we assume that crude oil derivatives will be used\n",
    "to implement the strategy.\n",
    "\n",
    "The history since *tmin* will be the base,\n",
    "but the user can modify the date interactively\n",
    "(see https://git.io/boltz2 for details on sequential decisions)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[0.7845, [[0.9814, 0.8337, 'Brent'], [0.0186, -1.82, 'WTI']]]"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "prtf = boltzportfolio( oils[tmin:], temp=55, floor=-25, level=-25, n=4 )\n",
    "prtf"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Brent has a higher geometric mean rate (0.83% vs. -1.82 for WTI),\n",
    "hence ***0.98 of the portfolio's notional principal is dedicated to Brent***,\n",
    "and 0.02 towards WTI.\n",
    "The expected geometric mean rate of this particular\n",
    "Boltzmann portfolio is a mere 0.78%,\n",
    "hardly better than a Treasury note.\n",
    "\n",
    "In a Boltzmann portfolio, the second and fourth centralized moments\n",
    "are taken into account to properly access risk,\n",
    "and to adjust the geometric mean rates.\n",
    "\n",
    "This component analysis is more accurate out-of-sample than a\n",
    "treatment of a single time-series such as the weighted average."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Deflated oil prices\n",
    "\n",
    "We use our monthly deflator consisting of CPI and PCE,\n",
    "both core and headline versions for each,\n",
    "to compute ***real*** oil prices."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "#  First change the sampling frequency to match inflation data:\n",
    "oilmth = todf(monthly( oil ))\n",
    "defl = todf(get( m4defl ))\n",
    "oildefl = todf( oilmth * defl )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXQAAAEaCAYAAAABnax5AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nmeADusfj8ZQJPqB7PB5PmfD/Af3lThpuITFaAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0xa9b8c3ec>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "#  Deflated Oil price:\n",
    "plot( oildefl )"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The supportive 1998 uptrend is broken by the post-2014 crash in prices.\n",
    "The level support from the 1990's is around \\$20 in current US dollars."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Oil price ex-USD\n",
    "\n",
    "Here we are interested in how oil prices appear when priced in\n",
    "foreign currencies (outside the United States).\n",
    "A basket of trade-weighted currencies against USD helps\n",
    "our foreign exchange viewpoint."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "#  rtb is the real trade-weighted USD index,\n",
    "#      computed monthly by the Federal Reserve.\n",
    "rtb = get( m4usdrtb )\n",
    "oilrtb = todf( oilmth / rtb )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXEAAAEaCAYAAADntGc9AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAIABJREFUeJztnXeYlNX1xz+HqtSlIyAgKFgRe8Gytp9KYu/EAhbUWBIT\nY9RorNFEE2NssUtMYu8aYwPGgF0EsdCld5ZditL3/P44M+7s7PR9Z+a97P08zz67b5n7fudlOO+d\n7z33XFFVPB6Px+MmjUotwOPxeDz544O4x+PxOIwP4h6Px+MwPoh7PB6Pw/gg7vF4PA7jg7jH4/E4\njA/inoyISLWI9Cm1Do/HUxcfxEOIiMwUkUOLfM2tRGRuisP1nkwgIqNF5Nw0x7cTkVdEZImILBOR\n/4pIv4RzrhCRhSJSJSKPikjTuGOXiMhnIrJWRB5PeN0QEVklIiujP99HH0y7pdFzmIhMEpHVIjJS\nRHrGHXszob11IvJlhvf/p+j7Wioif0w4drOITBSRDSLy+3TtZHEf2onIy1HdM0XkjAxtpXyfmXQn\naauXiIyK3t9vReSwhONDRGRW9N69JCJlmd6rJzM+iHtiDAb+m+KYFOH6ZcCrQD+gC/BZdNsEiBwJ\nXAUcAvQC+gI3xb1+PnAL8Fhiw6r6lKq2VtU2qtoG+DkwQ1XHJxMiIh2AF4HfAe2BccCzce0NTmjv\nQ+C5VG9MRC4EjgV2AQYAx4jI8LhTpgG/Ad5I1UZcW5nuwwPAWqATcCbwdxHZIZ/3mYXuRJ6OttEe\nuA54IXoNRGQn4EHgZ9i/7xrg75nerycLVNX/hOgHeBLYBHwPrASuxP6zVgNDgTlABXAhsCfwJbAc\nuDeujXOAscC9QBXwLXBohuu+CByf4lg10Cf692DgC2AFMBu4Ie685sA/gWVAJfAJFkxuBTYCP0Tf\n0z1Z3Id20eu2i27/G7g17vghwMIkr7sFeDxD26OA69McvwAYG7fdIqq9X5Jze0ffW8807X0AnB+3\nPQz4MMl5/wR+n0F7yvsQ1bkO6Bt3/B/Abfm8z2x1R49thwXmlnH73geGR//+A/CvuGN9olpbpnu/\n/ifzj++JhwxVPRsL1D9V6+n9Oe7w3sC2wGnA3cC1wKHAzsCpInJg3Ln7YD28DsCNQMqvryLSBDgI\neDcLiauBs1S1LfAT4CIROTZ67BygDdAd641dBKxR1euAMcCl0fd0eRbXORgLTpXR7Z2wB1aML4HO\nItIui7Z+RER6AQdiD8tU1LqWqv4ATI/uT+Rs4H+qOifb9qJ/J2srG9Ldh37ABlWdkepaIlIpIvsn\nayvJ+0yrW0ReF5Gr4s79TlW/T3F+4rW+w4J4LcvMkzs+iIeXRAtDgZtVdb2qvof11J9W1QpVXYAF\nyXiPd7Gq3qOqm1T1OWAKFnSTcRAwIeE/YFJU9X+q+k3076+BZ7CAC7ABe2j0U2O8qq7O7u3WICI9\ngPuAK+J2t8J6/zFWYveodY7Nnw2MUdXZac5JvFbsesmudRbwRIZrJtPeKsNrcmkrdh9aRbdJOP6j\nblVtp6ofpmgr8fy0ulX1GFW9I8+26mjz5IcP4m6xJO7vNcDihO34wDA/4bWzgW4p2h0MvJmNABHZ\nJzp4tUREqjBbp2P08D+Bt4FnRGRedFCscTbtxrXfKdrGfdGHT4zVWC8/RlvswbYql/axoDsi7npb\nRwfaVolILAAmXit2vVrXEpEDMH/3xbh918QNej6QRnvOD7c0bcXuQ1a607SVeH4uunNtK5M2T5b4\nIB5Ogigt2T1huyewIMW5WQdxzJN9BeiuqmXAQ0S/NajqRlW9RVV3AvYHfor1fCGL9xS1e94GXlHV\nxEyIb4Bd47YHYt82KskSERkEbEVc0FXVuWqDlK3VBilj1xoY97qW2ADiNwlNng28FLUhYu3drjWD\nnj9Poz2xrWxJdx+mAk1EpG/c8V3TXCvV+/w6D93fAH2ibSS7dq22ohqbRjV76oEP4uFkETbwE0+u\nGSKdReQyEWkiIqcA25MkUItIb6CZqk7Jst1WQKWqbhCRvYEhcW2Vi8jOItII63ltwAZpwb41pMw1\nF5HWwDvYQNvvkpzyJHCeiOwQ9X+vI87GEJHGIrIF0BgLZM2TfAs4B3gxC9voZWAnETlBRJoDN2B2\n048BJ3qtU8lspcS0/0pEuolId+BXCdqbRNtrBDSNak/1fzPlfYg+TF4CbhaRFtFvCsdg35ByeZ/T\nstEdT/Q1E4AbovpPxMZqYg/Mf2PZLYOigf5msvu38GSi1COr/qfuD5bWNRvLOvkVlp2yCWgUd84c\n4KC47SeBa6N/n4N55Pdg2SmTgcNSXOsSMmSLRK8dy045EZiF+ZuvRa/xZPTY6dFrrQIWAn+NaQb2\nxXz5CuDuJNc4O3qdVXE/K4Eecef8EnvAVQGPAk3jjt2AZbNsivv5fdzx5tH7WZ7lv8GhwCRs7GEU\nCdkn0fc6M4d/0z9G3/sy4PaEY08k0X52mrbS3Yd2WHBeHf13Oi3htauAQTm8z3S63wSujtvuCYzG\nMlwmAYckuWezoxpeAspK/X9tc/iR6M1NiYg8hn0tXqyqA1KcU479h20KLFXVQ9I26ikoInIOcJ6q\nHpTFuf/B0hPfKrwyj8cTNNnYKU8AR6Y6KCJtgfuxlLidgVMC0uYpDqOjPx6Px0EyBnFVHYtN3EjF\nEMzbmh89f1lA2jxFQFX/rKrrSq3D4/HkRxADm/2A9mK1MT4TkbMCaNNTD1T1H9lYKR6Px32aBNTG\n7tgASUvgIxH5SFWnB9C2x+PxeNIQRBCfByxT1bXAWhH5H5YPWieIi0gQ+c8ej8fT4FDVpGnG2dop\nQuo85VeBA6J5ui2wmh2T0ggJ5OeGG24oeWrP5qzXRc1eb/1/qquV0aOViRPd0ezaPc5HczoyBnER\neQortdlPROaIyDARuTBWklJVJ2Oz7CYCHwMPq+q3mdqtL7NmzSr0JQLFNb3gnmavt/6MGgWHHAJ3\n3JH8eBg1p8M1vZC75ox2iqoOyeKcPwN/znSex+MJNwsXQpMmsM7nKzmDs9Puhw4dWmoJOeGaXnBP\ns9dbf6qqoEsXWL8++fEwak6Ha3ohd80ZZ2wGiYhoMa/n8Xhy45Zb4JVXoHNn+G+qdZ48RUdE0HoO\nbIaOSCRSagk54ZpecE+z11t/MvXEw6g5Ha7phdw1OxvEPR5P8FRVWS/ce+Lu4O0Uj8fzIyedBNtu\nC6NHw6efllqNJ8Zmaad4PJ7gqaw0O8X3xN3B2SDumtflml5wT7PXW3+8J156vCfu8Xjyxnvi7uE9\ncY/H8yPt20MkAoMHw7x5pVbjieE9cY/Hk5Hqali5Ejp18j1xl3A2iLvmdbmmF9zT7PXWj1WroGVL\naNHCe+KlxHviHo8nL6qqoKwMmjXzPXGX8J64x+MBYMIEOOcc+OILaNoUNm0CSVWA2lNUvCfu8Xgy\nsnIltGkDjRtDo0awcWOpFXmywdkg7prX5ZpecE+z11s/Vq+G1q3t7+bNk/viYdOcCdf0gvfEPR5P\nnqxeDa1a2d/eF3cH74l7PB4AHn8cxo613127mkfetWupVXnAe+IejycLwtATf/VV2LCh+Nd1GWeD\nuGtel2t6wT3NXm/9iA/ipfLEL7oIpk8Prr2w3eNsCNwTF5HHRGSxiEzMcN5eIrJBRE7MSYHH4wkF\nYeiJr1hhk4482ZPRExeRA4DVwJOqOiDFOY2Ad4E1wOOq+lKK87wn7vGElMsvh7594Re/gN13h0cf\ntd/FYv16+wYwciQcemjxrusC9fLEVXUsUJnhtMuAF4AlucvzeDxhoNQ98RUr7LfviedGvT1xEekG\nHK+qfweKNr/LNa/LNb3gnmavt358/31pPfGqKvsdZBAP2z3OhlLkid8N/DZu20/U9XgcxPfE3aRJ\nAG3sCTwjIgJ0BI4WkQ2q+lqyk4cOHUrv3r0BKCsrY+DAgZSXlwM1T6BstsvLy3M6v9TbrumNEYlE\nQqPH6y3s9rx5EaZNAyineXMYNy5Cs2Z1z4/XHuT133/ftletynz+O+/AqlUROnTI3H6h9BZyOxKJ\nMGLECIAf42UqsprsIyK9gddVdZcM5z0RPc8PbHo8jrHHHvDww/b7xBPhZz+zhZOLxYsvwsknw3XX\nwS23pD/34INh6FAYNqwo0kpOvQY2ReQp4EOgn4jMEZFhInKhiAxPcnrRInTiUzbsuKYX3NPs9daP\nUueJ5+KJz50Ls2dnPi9s9zgbctWc0U5R1SHZNqaq5+Z0dY/HExrC4Im3apU5iFdX29Jx2QTxhoCv\nneLxeABo29YCY1kZDB8Oe+5pv4vF738PL7wAO+8Mzz2X+rxFi2CrrSyXfOTI4ukrJb52isfjSYuq\n9cRbtrTtUvXEe/TI3BOfO9fqnvueuOFsEHfN63JNL7in2evNn7VrbTWfpk1tuxSe+IoVsPXW2QXx\nffc1S6W6Ov25YbrH2ZKrZmeDuMfjCY54PxxK0xOvqqrpiavC5MnJz5s7F/r1M/tn0aLiagwjzgbx\n+FxbF3BNL7in2evNn3grBVL3xAupOb4nPm2apREmY+5cC/Y9e8KcOenbDNM9zpZcNTsbxD0eT3DE\nVrqPUSpPvHt3e6BMmVIzgzORpUuhSxfo0AEqM1V1agA4G8Rd87pc0wvuafZ686eyEtq1q9kuhSe+\nZo0F51hPfN265A+Sigpo397sn9Wr07cZpnucLd4T93g8OZMsiK9ZU1wNa9eaz71hA0yaZPuSDXJW\nVFgvvGXLzEG8IeBsEHfN63JNL7in2evNn8Qg3rJl8iBeSM3r1sGWW1qe+Isv2r6VK+uet3y5BfFW\nrazyYjrCdI+zxXviHo8nZxKDeIsWmQNk0Kxda98AzjvP9LRpkzyIx3ri2dgpDQFng7hrXpdresE9\nzV5v/iTrif/wQ93zCql57VrYYgsrvDVwIOy0U90gXl1tg7Dt2hXeEz//fPjoo7xfnjfeE/d4PDlT\n6p64qtkpzZvboOX48aYnMYhXVVnwbtLEHjT5avz+e/jHP+y6qXj7bRg3Lr/2i4mzQdw1r8s1veCe\nZq83f2K92xipeuKF0rxxI4hYcI6RzE6JWSmQXU88mV5Vy0E/99zUU/crK21G6PTp2b+HoPCeuMfj\nyZlS98RjVko8yYJ4bFATsgviM2bAV1/V3jdliuWan3ACjB2b/HXffGMPlVIE8VxxNoiHyU/MBtf0\ngnuavd78qaysPdmn2J74unXZBfFYjjhkF8SvuCLCAw/U3heJwCGHwIEHpg7iX30F++1XmiDuPXGP\nx5MzYeiJN29ee18mOyUbT3zcOFi2rPa+SATKy+GAA1IH8YkT4bjjYNYs2LQpyzdRIpwN4mHyE7PB\nNb3gnmavN3+SBfFieuKp7JTEyT7pPPEffoBbb63ZnjMHFiwoZ+nS2m189BEMGgQ77mgzQxMrIW7a\nBK+/DoMHQ+fOmeuzBI33xD0eT06o1h3YjAXxYq3hkq2dsmgRdOpkfycG8VGj4IYb7IEA8P77sP32\ntXviqrBwoRXa2nJLaN26bk/93Xdt0Ymdd7YiW/PmBfMeC4WzQTxMfmI2uKYX3NPs9ebH6tVW8KpZ\ns5p9TZrYT2LtkkJpzmSnbNpkf48da7XEoW4Qf+cd61VPnWrbM2dCnz6RWj3xFSvsYRF7YPToYcH/\nqqtqznnmGTj7bPu7Uyfq9OQLTeCeuIg8JiKLRWRiiuNDROTL6M9YEdklJwUej6ekrFhhNUsSqU8e\ndq5kyk755z/hoINgwgSzQpLpe+cd6NsXvv3WtufOte2KihrLZOnSmp48WI/86afh+efNK7/+essP\n/8lP7HjnzrBkSeBvN1Cy6Yk/ARyZ5vh3wEGquitwK/BIEMIyESY/MRtc0wvuafZ682PlyuRBPJkv\nXijNyeyU1q1rgviUKfDll7buZ4sWti++J75qlQXt00+vKZ41bx4ceWQ5LVvWlLVNDOI9esDo0eZ7\nv/su3Habtdunjx0vRU88cE9cVccCKav2qurHqhqr/Psx0D0nBR6Pp6SsWmUBM5FS98S7dTNrZOxY\n+O47GDYMfvnLmuPNm5vNsn69Dcy2b28+dqwnPm+e9bTjA3GyIL5qlfXU33nHHmZHH11zvBRBPFeC\n9sTPB/4bcJtJCYufmC2u6QX3NHu9+bFypVkXiSTriRfTE+/ZEx57DC64wPzt4cPh+ONrjovUVDKM\nLWqx44617ZRZsyJ07FgzeLl0qVkkMbbe2n736AGffw4vvwy3315zvFOn4tspJcsTF5FDgGHAb4Nq\n0+PxFJ5UQbyYPfFkdgrAscdaj/rbb2Gbbeoej2mMBfF+/azXXllpdclbt7ZAHB/EE3viTZvCEUfY\n9u67116mrnPn8PfEm2Q+JTMiMgB4GDhKVdMumDR06FB69+4NQFlZGQMHDvzRA4o9gbLZLi8vz+n8\nUm+7pjdGJBIJjR6vtzDbq1aV06ZN3eNr10b46CM48MDa58drD0rP2rVQWRnBJuLUPr777uV8/jl8\n+22ESZNqH2/UCFavLqeqCjZujPDxx7D11uWMHg3t20cQsaC9aJGdP24c7LdfzesrK+Gkk8rp1w86\ndrTj8e3PmgVLlgR7v7PZjkQijBgxAuDHeJkK0SwSQUWkN/C6qtbJPBGRnsBI4CxV/ThDO5rN9Twe\nT/G45x6b9HLvvbX3n3ACnHUWnHhi4TX8/e82cPngg3WPXXUV/Oc/Vs8kkT32gIcesp76u+9aFstx\nx1me97RpMHKkvb+vv4aHH4Yzz4T/+7+aFMIYr7xi137rrdr7Fyyw3vmiRcG913wQEVRVkh3LJsXw\nKeBDoJ+IzBGRYSJyoYgMj55yPdAeeEBExovIp4EpT0NiryDsuKYX3NPs9eZHGDzxVHYKwKGHwm67\nJT+W6ImD+eJPPQV77WV6DzwQxoyxY4l2SoxjjrH88EQ6dqydolgMcr3HGe0UVR2S4fgFwAU5XdXj\n8YSGlStrprLHk6oIViFIlp0S46ij7CcZsXU2E4P4Dz/AJZdYFcMBA2yW5qGHwgcfwF131W2ncePa\nBcBiNGtmD4rKyuT3KAwE4omXgnhf0QVc0wvuafZ682PVquSDhsmKYBVKc7LslGyI5YpXVUH3aHLz\nEUeYNbT11uaPg00UatXKBjiTpVOmo0sXWLy4eEE813vsbBD3eDzBsHJl6jzxYvXE161LbulkIj6I\n77ST7evaFS6+uPZ5Tz9ttVIa5ZGP162b9eR33DH31xYDXzulSLimF9zT7PXmRypPfIst6q54XyjN\n6eyUdCTzxOOJ6W3ZMr8ADhbE58/P77X5kOs9djaIezyeYFi1KnkQb9rUlk0rBvnaKfGeeLLSAUHQ\nvbtlqYQVZ4N4WPzEbHFNL7in2evNj1Q98SZN6gbxQmlOl52Sjng7JVlPPAi9xe6J56rZ2SDu8XiC\nIZUnniyIF4o1a+o/sJksiAeB74kXiLD4idniml5wT7PXmx+59MQLoVnVVtvZeefcXxvzxFesSO+J\n1wfviXs8ntCimrqeeJMmVn+k0Hz+ufXCBwzI/bWxMrOp3kMQhL0nntW0+8Au5qfdezyhYulSW8Ks\noqLusccegw8/tN+F5Oqr7YERvz5mtrzxBtx8sxW9SlxmLSjWr7ce/9q1+We41Jd6Tbv3eDybL7Ga\n28kolic+fjzst19+r23VymZldu0arKZ4mjUzuynZgy4MOBvEw+InZotresE9zV5v7sybZ+VYk1Es\nT3zKFOjfP7/XtmoFy5enDuJB6W3TxlIxi4H3xD0eT9bkGsSDZs0aqxCYodpqSmK1v7t0CUxSUhIX\nZQ4TzgbxsOTYZotresE9zV5v9sSq8uUaxIPWPG2arWfZJM8CIK1a2e9UPfGg9LZqVbyeuM8T93g8\nGRk82Cr6zZ2bPogXOjulPlYKZA7iQdG6te+JB04Y/MRccE0vuKfZ682eBQssta/Unnh9g3jMTim0\nJ15MO8V74h6PJyMrV9pqN+mCeDFqp8ycaXZKvjRrZjobsifu88Q9ngZIu3bQvr0tdrBokQXDREaN\nstztUaMKp+OII+DKK+HII/Nvo317iETymyyULZdcYqVoL7mkcNdIR7o8cV9P3ONpYKhaT7yqCoYO\nTR7AoTjZKXPmpM5Tz5azz65fbz4bWrcu3sBmrjhrp3j/s/C4ptnrzY7vv7eKgVttBaedlvq8Qnvi\nqjawWt8gfvfdNQOciXhPHBCRx0RksYhMTHPOPSIyTUQmiMjAnBR4PJ6iEqsz8v776W2MQmenVFTY\nwyTX5dJKgdOeuIgcAKwGnlTVOq6TiBwNXKqqPxGRfYC/qeq+KdrynrjHU2ImTYITT7Tf6fjiCzjv\nPJsWXwjGj4dhw2DChMK0HySPPgoff2y/S0G9aqeo6ligMs0pxwFPRs/9BGgrIgUeK/Z4PPmyYkV2\n61kWOjslCD+8WGzunnh3YG7c9vzovoLi/c/C45pmrzc7Vq7MrmxroT3xWbOgZ8/AmkuK98Q9Hs9m\nR7Y98UJnp3z4Iey9d+HaD5Iwe+JBpBjOB+K/FPWI7kvK0KFD6R2tdlNWVsbAgQN/rBUQewJls11e\nXp7T+aXedk1vjEgkEho9Xm8w2ytXltO2bebzP/88ErUQah+P156vnupqeOutCCefXLf9oN9vEHpb\ntYKFCyNEIsX5fEQiEUaMGAHwY7xMRVaTfUSkN/C6qu6S5Nhg4JLowOa+wN1+YNPjCS933WWpfX/9\na/rz5s61Ot/z5gWvYfx4GDIk8+BqWJg6FY45xsoElIJ6DWyKyFPAh0A/EZkjIsNE5EIRGQ6gqm8C\nM0VkOvAQ8PMAtack8SkbdlzTC+5p9nqzI9ulzArpiX/6Key/fyBNpSUovcWsYpir5ox2iqoOyeKc\nS3O6qsfjKRkrV2Y3oFjI7JSKisLXOwmSMHvivnaKx9PAOPdcGDTIcsDTUVVlizVUVeV/LVU4/HB4\n801bDDnGb34DnTvbbxfYtMn0r19fmnU2/RqbHo/nR+qTYpgrixdbAa0VK2rvX77cinC5QuPGliue\n+D7CgLNB3Pufhcc1zV5vdixfDmVlmc8LwhOfMcN+J1oRlZXFCeJB3uP27YuzWHKump0N4h6PJz+W\nLYNOnTKfF0RPfPp0+504KFisIB4kHTqEc8V774l7PA2MrbaCceOgW7f056ma/1tdDZLUjc3M9ddb\nTfKxY82HjzFwIDzxBOy2W37tloKjjoJf/AKOPrr41/aeuMfjASwwV1RYrzITIvXvjcfslGQ98fbt\n82+3FIS1J+5sEPf+Z+FxTbPXm5mVK638a3ymSDoSg3iumqdPtx5/oiderIHNoD3x5csDay4l3hP3\neDwpydYPj1HfnvjMmbZsWnwQ37AB1qxxo454PGHtiXtP3ONpQHz8sfm6n3yS3fnt2sF33+XXa163\nzgL1+efDDjvAZZfZ/qVLbXvZstzbLCX33GPT7++7r/jX9p64x+MBLHB27Jj9+fXpiS9aZLMy27Sp\n3RN3MTMFrCdeDDslV5wN4t7/LDyuafZ6M5OPnRK/RFsumhcuND+8devSBfGGkCfuV7v3eBoQS5fm\n1hPPtX7K/fdb+z/8AEuWWDpjq1Y2czOGa7M1Y4S1J+49cY+nAfHb31oAvfrq7M7v0wfee89+Z8PA\ngdC/P3z2mdUZOfZY2HNPyxN//HE757rr7MHwxz/m9x5KxYwZcMQRNkZQbNJ54r4n7vE0IJYtg+22\ny/78XDzx+fNh8mRbdi1WYyTWE4+3U15+uSagu0S7dmYFhQ3viRcJ1/SCe5q93swsX57bJJtc8sTf\negtOOMEsmAMOsH0xT3zVKlvVvn17C4R77ZWf/lwJ8h5vsQWsXRtYcynxnrjH40lJfYN4OqZNs5zw\nH36Aww6r7YmvXg1vv212xKWXlqaca31p3tzSJlXzL0NQCLwn7vE0IAYMgH/9y35nw+67wyOPwB57\nZD53+HA776STLHBPn27WzbffWg3zrl3tnBNOqN97KCVNm8L330OzZsW9rvfEPR4PkHtmSC498Vg9\nlFj2y8472+/Wre26M2bYA8RlYr3xYgfxdDj4pcbw/mfhcU2z15uZXO2UxBTDdJpTPSBatYI5c2xN\nzWwKbwVJ0Pe4GL54QTxxETkKuBsL+o+p6p8SjrcB/gX0BBoDf1HVETkp8Xg8BeNvfzNfetMmaNEi\n+9fl0hNP9YAoK4O994ZHH83+umEl1hMPExk9cRFpBEwFDgMWAJ8Bp6vq5LhzrgHaqOo1ItIRmAJ0\nUdWNCW15T9zjKQGXXAJTpsDXX9t0+Gw57DC49lr7nYleveD9921dzs2VPn3g3Xehb9/iXre+tVP2\nBqap6mxV3QA8AxyXcI4CsZpkrYGKxADu8XhKx5Il8MUXudfwDqInvjlRrDTDXMgmiHcH5sZtz4vu\ni+c+YEcRWQB8CfwiGHmp8f5n4XFNs9ebmiVL8luIIZvaKR99BDfcEM7yskHf42LYKaWqJ34kMF5V\nuwG7AfeLSKuA2vZ4PPVk6VL7nWvNkmx64l9+aWmI7dqFK3+6EITRE89mYHM+NmAZo0d0XzzDgNsB\nVHWGiMwEtgc+T2xs6NCh9I6aZmVlZQwcOJDy8nKg5gmUzXZ5eXlO55d62zW9MSKRSGj0eL35by9Z\nAltsEWH9eoDsX19VBRs31j4erx1g+fJyFi6EHj0iRCLhub+p9NanvbVrYe3awuuPRCKMGDEC4Md4\nmYpsBjYbYwOVhwELgU+BM1R1Utw59wNLVPUmEemCBe9dVXV5Qlt+YNPjKTIbN8KWW8I++9h097/+\nNfvXnn46HH+8/U7Fr38Nd91l7X/8cf31hpkjj4QrrrBFk4tJvQY2VXUTcCnwDvAN8IyqThKRC0Vk\nePS0W4H9RWQi8C5wVWIAD5rEp2zYcU0vuKfZ601ORYWl+fXtW/+BzWSaly83GyWMg5pB3+MweuJZ\n5Ymr6ltA/4R9D8X9vRDzxT0eT8hYutQWgrjggtwHHrPxxJcvh112CWcQD5owZqf42ikej6PceacF\nzvPOS3/eqFFw882QT6f0/PPNJrnggrrHVGHBAjjtNBg2DLbdFg4+OPdruMRZZ1kRr7PPLu51fe0U\nj2cz5O096g4+AAAgAElEQVS3Lff7xBPTZ53EeuL5kK4nPmEC/Oxn9ve++8JOO+V3DZcIY3aKr51S\nJFzTC+5pbmh6J0+2GYSvv57+vAULrIJgPjRrRjSjxYjXvHy5VSpcujS8VkrQn4kw1k5xNoh7PA0V\nVaiqssk7++2Xed3HadOgX7/8rrXlljaJJxmrVtlEoGXLwhvEg8b3xAMkPtfWBVzTC+5pbih677gD\nDjrIAnNspZx0TJ0aXBCP17xqlf1u2dKCWxgJ+jNRjCCeq2Zng7jH01B55hmYNAm239688Kqq9OcH\nGcTjiQXxYpeXLSVhzE5xNog3NP+zFLimuSHonTnTFiS+8044/HDL/07XE//hB6ub0rNn6nPS0aJF\n7SAer3nlSqs3HmYrxeeJezyeUDF2rJWF/eUvbfvVV9P3xGfMsMHPxo3zu96WW9qDIBmrVsGuu+Ze\nj8VlvCceIA3F/ywlrmluCHoXLYLucTVEy8pSB/Gvv4af/MRsl3zJ5IkPGQJPPpl/+4XGe+IejydU\nLF4MXbrUbLdrl9pO+eorW+fy4Yfzv146T3zlSnuI5Ju+6CLeEw+QhuB/lhrXNDcEvYlBPF1PfMEC\n64XHFi7Oh8QgHq951arw1Q9PpCF44s4GcY+nIZJLT3zBAujWrX7XSxzYjGfVKmjTpn7tu4b3xAOk\nIfifpcY1zZuL3urq1K9JDOKtWtnX+/jVd2IEEcQTBzYTPfGw98SD/kwUw07xnrjH4zjHHgtvvpn8\nWGIQF0ltqSxcCFttVT8tmTzxsAfxoEnWE6+uTv/gLTTOBvGG4H+WGtc0by56Z82CZ5+tu7+62mqD\nJ3rc8UG8vBy+/97+Dqon7j3xGpIF8auusrz9oPCeuMfjOEuXWlGrWPXAdetsIeKKCmjb1ibYxBPz\nxZcvh/fftzTEWJlY74kHSzI75euv4emnS6MHfD1xjydUVFdbb69/f1t8eL/9YMoUyzIZOxaGD4dv\nvqn9miOOgCuvtGC+zz7wySd2fvfuNVPj86Wy0iYLJQ6eqtrDZO1aK1fbUJg40crvfvVVzb5tt4V5\n82zfdtsV5rr1Wp7N4/EUj+XLzaLYbTcrNQvWowarHx7vh8fo1cssmBkzatoIohcOqWdsrlljQbwh\nBXCoay9t3Ahz58IJJ9i3oFLgbBDfXPzPMOOa5s1B79Kl0Lmz9cSnTrV9sSD+6KOwxx5129lxR/j2\n25ogXlEBX35Zv5maMZo3t8yXTZtqa3bFSgn6M9GqVe1vN3Pm2GSnXr2sRk0QFMQTF5GjRGSyiEwV\nkd+mOKdcRMaLyNciMjonFR6PB7BA0KmTVR2cMsX2LVxoXvjChTB4cN3XxIL49OlWFraiAsaMgQMP\nrL8ekeQ+cEPMTAF7cMUH8enTzU7p1MnqqpeCjEFcRBoB92ELIe8EnCEi2yec0xa4H/ipqu4MnFIA\nrbXYXHKCw4xrmjcHval64kceab3AQYPqthPfE99jD7NTxoyxmuNBED+4GdNcWRnu6oUxgv5MtGhh\nA82xQecZM6BvX8sYWro0mGsUIk98b2Caqs5W1Q3AM8BxCecMAV5U1fkAqlqiZ5LH4zax9TC33dYC\nxKZNFsSPPRY+/tiWS0tk661hxQpbwefQQ2v88d12C0ZTslzx5csbVvXCGCK1LZW5c81KCXVPHOgO\nzI3bnhfdF08/oL2IjBaRz0TkrKAEpmJz8D/DjmuaNwe9MTulZUv7PXu22Sjdu6deiFgEjj7aCl31\n7WtZLP37101FzJf4IB7T7EpPvBCfidata4J4bEJVkD3xUuWJNwF2B44GjgKuF5FtA2rb42kwxOwU\nMF986tTsMk2ef9566x06WC98hx2C05QsQ6Wh9sShti++aJENbHbsWLqeeDYJQvOB+HVBekT3xTMP\nWKaqa4G1IvI/YFdgemJjQ4cOpXfv3gCUlZUxcODAHz2g2BMom+3y8vKczi/1tmt6Y0QikdDoaQh6\nJ06EAw+07VatIrzxBixcWM5WW2XX/qxZAOXssENwelu0KGfNmto9xMpKWLUqQiQSnvuZajtGUO21\nbl1OVRW89FKEadOga9dyOnWCRYuCux+RSIQRI0YA/BgvU5Fxso+INAamAIcBC4FPgTNUdVLcOdsD\n92K98ObAJ8BpqvptQlt+so/HkwJV87cjEfPE77kH3nvPvPBs09emT7cJJy++CCeeGIyuQw+F666z\n3zF+9SuzeH7962Cu4RKHH24rGn36qd3vcePMUtliC3u4tWgR/DXrNdlHVTcBlwLvAN8Az6jqJBG5\nUESGR8+ZDLwNTAQ+Bh5ODOBBk/iUDTuu6QX3NLuud9Ysm7HZt69t9+sH//kPHHJI9m3GFi0O2k7x\nnngNrVvbRKxvvjELpVMnG5cIanAzV81ZzbdS1beA/gn7HkrY/jPw55yu7vF4fuR//7O0QIn2t/r3\nt6Ae3wPORNu2sP/+NQ+CIPDZKbVp3dq+HVVWWuCODSDHfPF8F6XOF2cnzcb7ii7gml5wT7OLelUt\njbBJEwsM++9fc7xnT/tqfthh2bfZqBF88EGwOlu0qKmMGLvHrvTEC/GZaNMGZs60v+OXpuvUKZgM\nlVw1Ozvt3uPZHHjqKTj9dPt7+nTrfcdo3NhmbW5b4jyv1q1h9era+xp6T3zjRitJEF+vvUMHuy/F\nxtkg7rr/6QKuaXZR79y58Morlqr23XdWMTCeHj1Koy2e1q1tmj3U3GNXgnihPHGAffet3RNv1y6Y\nIF4QT9zj8RSGpUutxz1ihJUz7dWr1IrqEj+5JYYrdkohiAXxq66qHcTbt/c98Zxw0f90Ddc0u6h3\n2TKbpPPII/bVvFmSafWlJn5yS3m55YxXV9uAZ9gpxGcivie+++41+4MI4itWwKhR5Tm9xtkg7vFs\nDixbBscfb+mFiVZKWEjsic+bZzaPJM1a3vxp08YyUhLtpPbt6y6ekSu33gq33GL2VbYLejgbxF30\nP13DNc1h16tqRaliU9gjkQjLllk64O67hzuIx3vis2eH0/ZJRqE88S5d6j7E6tsTf/99+Mc/oHPn\nCH/7Gxx8cHavczaIezyu8cMPMGGCZaHEWLbM8ouPOSa4qoNBk9gTnzXLnSBeCLp1S74MW32D+M9+\nBv/6l2UojRgB48fDpEkZX+bX2PR4isWcORb8XngBTjrJ9rVpY/vLykqrLR0ffwy//KX9Brj+ehuM\nvfHGksoKHd98A6ecYrXd07Fpk40pxCYJvfeefRPr1s0mVV19NdxxB+y8s5VOuOkmv8amxxMKYr20\n2GIP69bZijlt25ZOUzbE2ymAU3ZKMcmmJ64Kxx0Ht91Ws+/cc+Gll2osmlgv//rrs1u309kgHnb/\nMxHX9IJ7msOut6LCfk+bZr9ffz1Chw7hHyCMt1O8J56aWJ64as3Seok8+yyMHm1WCVg2yty58Pnn\nNemKa9dG2HFHK7cwYQLMT6wZm4CzQdzjcY2KCpuaPXWq/cf91a/MDw87iZ64S0G8mGyxhVkkH3xg\nBcisLHBtPvsMTj65xuuOWS+ffVYTxHfayerodOxo937o0PTX9Z64x1MkHnwQ3nwTPvkEnngCrrgC\nLrsMLr201MrSE5tivnGj+bktWtg0/DDmtJearbe25dtmzIB33oHENPWTToITToDzz4dzzrEH4siR\nduzcc+Ghh2qff+yx8PrrAN4T93hKTkWF9bK+/x6+/NJKzIY9gIMV52re3LJrFiywbxM+gCenfXsb\n4zjpJAvQicyaZSWGe/eGxx+Ht9+GAw6wB2T87M8Yu+1mx9PhbBAPu/+ZiGt6wT3NYddbUWFFkrbb\nDt59F6qrI6WWlDUxS+WVVyJOWSnF/kxcfDE8+aTl/KcK4r17m91y6qkwbBicFV2ROBbE4zVfeKF9\ng0uHr53i8RSJigrYZRcL4q++CoMGlVpR9rRubYNwixd7PzwdF11kv3v1MtssnlWrLIWwUye48krz\nvPv3t8HQ885L3hPv1i3z+qrO9sRdrJPhGq5pDrve5cutJ96vH6xfD4MHl5daUta0aWO1zsePL3cq\niJfqM9GrV92e+OzZ1gsXsQd4rOxwu3Y2zhAL4r6euMcTUioqzDON5QFnWP82VLRubQ+e//7XLd2l\nIlkQj1kpiYjAmWcmnwWaDc4G8bD7n4m4phfc0xxmvT/9qeUGxzzxZs1g0qRIqWVlzU03wcsvA3hP\nPBt69bI00urqmn0zZsA22yQ//6GHatJNc9WcVRAXkaNEZLKITBWR36Y5by8R2SAiAa2z7fG4z/r1\nlkb217/aKj0DBtjU6kYOdaHKy22ZuL59YfvtS60m/Gy5pWWpLF5cs2/69Px72+nImCcuIo2AqcBh\nwALgM+D06Ar3iee9C6wBHlfVl5K0Fbo8cVV7WjZuXGolns2Vr76yTIRsihl5Nh/23hv+9jfYbz/b\nPvpouOQS+1aWK/WtnbI3ME1VZ6vqBuAZ4Lgk510GvAAsyV1i6Xjuucwzojye+jBxomWleBoWib74\ntGmF6YlnE8S7A3PjtudF9/2IiHQDjlfVvwNFqQQRlNc1YYJNeS00YfZrU+Ga5rDq/eors1ASCave\ndLimuZR644P4hg3mkafyxOMpiCeeBXcD8V55yEv61DB5sj0h16wptRLP5orviTdM4oP47NnQvXth\nZrpmM9lnPtAzbrtHdF88ewLPiIgAHYGjRWSDqr6W2NjQoUPpHc2zKSsrY+DAgT/mRcaeQNlsl5eX\n53R+qu1x42CLLcqZPBlWrKh/e4XWW8zt2L6w6HFV71dflTNggDt6M23Haw+DnrDqXbkywhdfAJQz\nYwa0axchEsnu9ZFIhBEjRgD8GC9Tkc3AZmNgCjawuRD4FDhDVZMO04jIE8DrLgxsbthg+a8/+YnV\n+D377FIr8mxOzJtnv3fcEaqq3MpG8dSfiRNhyBD4+mtbqWf0aFt+LR/qNbCpqpuAS4F3gG+AZ1R1\nkohcKCLDk70kP5m5kfiUzYcZM6zq2J572o0uJEHoLTauaQ6b3vPOg9NPtxVakgXwsOnNBtc0l1Jv\nz562ahPA0qU23T4bctWcVe0UVX0L6J+w76EU556bk4ISMmOG5b1us40NcHo8QbF2LYwZY2MtF15Y\najWeUtC2rc0R+OEHWLIEOncuzHWc/YIX7yvmy6JFNQVmFiyov6Z0BKG32LimOUx6P/zQMlK22Sb1\noGaY9GaLa5pLqVfEllxbvDi3IJ6r5gZdxXDhQis6U4wg7mk4jBtnCz6cdBIcfHBNoSNPw6Nr19yD\neK442xMPwutatAi22sp+Fiyw2ZuFwjUvEdzTHBa9f/qTrVJ+7bUWxJOVGIXw6M0F1zSXWm+XLhZn\nCumJOxvEgyDWE2/Z0lYuqaoqtSKPy6hCZaUty3XRRbYijqdhU4yeeINeY3PQIOs1HXCApYE9/7wt\nn+Xx5MMzz1hJ0b32go8+KrUaTxi4/np7mN9+u9WTb9Eiv3bqWztlsyXWEwfvi7vG2rXFKyhVWVmT\n852OF1+0kq1PPll4TR436NLFZoQ3aZJ/AM+Es0G8vl6XqnlVxQripfbm8iHMmp9/3nzneAql94Yb\nbO3EdKxbZ+tmDh+efZGjMN/fVLimudR6u3a1ST+5WCneE8+SlSut/GyrVrbdrVt2vS1POPjgA6t7\n8+mn1tMpFKrw2mtWD3zFitTnvfuupRRmO3jlaRh06WIF0A46qHDXaLCe+JQpcMwxMHWqbT/5JLz5\npvmanvBSXW2zH3fZxXq/8+dbj/yf/yzM9b76Co491sZKzjzTZmAm4/TTbeGE2EK5Hg/Ad9/ZZ2fK\nFJvBmS/eE09CYsrPnntafq8nvCxYYDNsZ8609QpvvNGWO5ufWI4tQN5+GwYPts/HN9/U7Fe1Y+vX\nw803w1tvwSmnFE6Hx0369LGp9/UJ4JlwNojX1+uqqrJVpmP0728eeaHSDEvtzeVDWDS/+SZs3GhB\nc9YsOPxwWyVlyBDbF7PBCqH3gw8se6lPH3t4gNkq990HRx0FDz9sRY2efNIeKLkQlvubC65pDoPe\nXC0274lnSVUVlJXVbDduDLvuSrR0pCcsvPmmVZkcP94C9m9+Y+tUPvywHd96awvihXDpVG36/KBB\nNn3+u+9g0ybYfXd45BF7mNx+Oxx/vFkuHk9JUNWi/djlwsE996heckntfZddpvrnP5dGTxj4/e9V\nJ0xQPe881YkTS61GtaJCtXt31b59VZ9+WrVDB9W5c+ueV1amumxZ8NefNs2uX11t1+3aVfWNN1T3\n3tuOP/+8Kqi++mrw1/Z44onGzqRx1ffE4+jf31akbojMnQt/+AMceaRlYhxxhFVfKyWXX26Dliee\naLWYt9wSevSoe16PHsFlFqnW2Caffgr77muFjLp1s3zxu++uqUpYXg5bbAEHHhjMtT2efHA2iAft\niYN9TS9UEA+DN5eOxx6z+tc9esATT9hSUk88ESmZnhdegE8+MbuiTx94/XWry52Mrbe2ssLDhkXq\nPTj9j3/Y9W66yQYyYxUIGzWy5bY+/RROO832dexoD7/Ez1G2hP0zkQzXNLumF7wnnjWVlXV74pmC\n+KJF8Pe/my+ajOrq4PQVk40bLYj//Oe2aHR5Oey2W2Hzr9Pxv/+Zln//2+rabLONza5NFcR79IBz\nzoFXX4Vnn7U5AL17w9VX5+aVz59vnvs778Bf/mKTNHbcseb4NttYmmHLljX7OnbM6y16PMGRymcp\nxA8h8sRPOEH1hRdq71u/XrVZM9W1a5O/5oYbVFu3Vv35z+se27RJddttzWdfulT1qadU16wJXHYg\nRCKqV19ds/3aa6r77FP7nPvuUz3//OLqinHSSaqPPlqzPXWqec8jRiQ//+mnVa+/XvWdd1QPPFD1\ntttUjztOdeutVb/6Kvt/h6FDa+7LzjvbZ+Hrr2uOf/CB6rx5+b0nj6c+kMYTb7BB/JBDVEeOrLu/\nb1/VyZPr7q+utmP/+If9TuSjj1T79VM97TTVJk1Ud9pJdf/9g9cdBAccoLrFFqorVtj7OuAAe1/x\nfPih6h57FFdXdbXqhg2qnTqpzplTs3/dOlUR1c8/T//6qirVli3t9d9+aw/bY49VbdrUfqdi5kzV\n775Tbd/e7omq6kUXqTZubNf2eEpNuiDurJ2SrW90wQXwwAN19ycb2ASzVGbMqLv/mWdsEOtnP7PS\nkon55C+8YF7p00+bDTFxog2QxWaEhsWb+/xzsw3Ky206+fPPw+rV9r7iGTAAvvkmwvffF0/bo4+a\njdOihfncMZo1g1tvTW2nxBg/PkKfPjYgusMONknntdfgzjth1Kjk1srw4fZvftRRcNZZ0KaN7T/w\nQKuB0qxZcO8vkbB8JnLBNc2u6YUCeeIicpSITBaRqSLy2yTHh4jIl9GfsSKSYkGq4jJzJrz0khUw\nmjKl9rFknjhYGdG337Y1N5cvt32vvGKB4Z//rMknHz++5jULF9qxM86wTIbevW0g7LjjzKctBqNG\nmfZY/nQq3njDZhaef75lWtx0k5Xjbdy49nktW5of/NZbtl2Maglvv21jEsnqTFx7rdV8z0QkAr/7\nnf196KHmcV96qQXjZctqn7toETz3nA1gNmpUu8jV8cdbLrjHE3pSddG1xgJpBEwHegFNgQnA9gnn\n7Au0jf59FPBxirYC/Yqxdq3qvfeqbtyY/PgVV6j+5jeqV12l+rvf1T5WVqa6fHnd18yda753hw72\n9fqll1Q7dzZ7IcZll6neckvN9sknW451Im+9pbrbbuaXq6p+9pnq4MGqhx+uOmlSbu81E6edZu+1\nY8faPm4i++2n+t57Zl3su69ZJtXVyc/9+99VzzjDPPNTTql9bPZs1dWrg9NfXW02yAcfmL0RNHvu\nqfrxx7X33XWX6jnnBH8tjydoqI8nHg3Q/43bvhr4bZrzy4C5KY4F+sYuvFC1USMbRExkxQoLwrNn\nWwDeaaeaY5s2md+ZKvg/+KB5qjfdZINbf/hD7eP/+59NAtluO9U77rCAnyygbdpkE0Mef1z1kUdU\nu3WzwHjDDaqHHpo6eCZj5MgavzbZdTp2NB/5D39QHT689vH161X/9CfVTz6xB1RsoG/WrOT+f4zF\ni+1hd/jh5vPHHnqbNqluv73q2Wdnrz8T336rus02wbWXyKmnqv7737X3HXqoTd7xeMJOfYP4ScDD\ncdtnAvekOf/K+PMTjun996veemv939Rzz43Wdu2sp9y3r83uiw2G3XSTBbVTT7XtTZtstt20abZd\nWanapk3ma1RVqZaXJ58NWF2tOmaMBbkrr0zdxrhx1sNs1260jhtn+zZsUN1hB+vhZsPIkfawivX2\nV6+uyayprrZ70L+/bc+caQ+V9etVp0+3a913n+pWW9kA3yOPZHdNVdXRo0frWWfZtQcNUt1rL8v4\nGDzYHoq9etmAbhAke/jkyujRo1Meu+aa2t+eqqvtPi1YUL9r1od0esOKa5pd06uaXHO6IB7oKoAi\ncggwDDgg1TlXXDGUxo17M3kyLF9exp57DuTGG8sRqTH0y8vLgfTbY8bAnntGaNfOts2HjnDllfDw\nw+X85z+waFGESMSOH3ss/OUvEU47DXr1KqesLPP1xo+PcMMN0KFD3eMisHFjhHvvheOOS6/3ppvK\nefVVWLmyRs9f/gLnnx/h1Vdh+PBy7rgDLr44QuPGtV+/bh1ceGE599wD114boVUre3/z5sGSJRE+\n/xzefbec3/++5nrbb1/OHnvYwOR++8GUKeW89x7Mnx+Jri6S+f4CTJgwgUMOgbKycg4/HO64I8It\nt8Bnn5UzfDg8+2yEBx+EfffNrr1U24MGlfPAA3DjjTX3J5/2JkyYkPJ4nz7wwgs17S9cCBs2RJg8\nGbbaqn76C6E3rNsTJkwIlZ7NTW+MSCTCiBEjAOjduzdpSRXdtab3vC/wVtx2UjsFGABMA/qmaUtH\njbJ0tgEDVM880/JxL7+8xlpYsMCOpUsnO+ss60m/8optr1ljX4tPPdW+9o8aVfc1b75pqXSxnutR\nR2X5WCwQ1dWqt9+uOmSIfR8qKzMPPZE//lH1xBPt7zvvVO3TR/WJJ8zG2WUX1S5d6uYuL11queAL\nF5qX/d57hXkPb7xhlkR9ee016+kXkjFjVHfdtWb7v/9VPeywwl7T4wkK6mmnNKZmYLMZNrC5Q8I5\nPaMBfN8MbdURV1lpA2y77mqTOh5+2AJ7165mZyTy0Uf2NX78+JoBwxizZyf3x1VtELSszDzhU0+1\n4BgWJk9WvftuezjFs3Gjao8eVpQqkYoK1WHDzDIpFZWVqq1a1T+X+uKL7QFVSDZssAHqmKV2yy02\n8O3xuEC9gri9nqOAKdFAfXV034XA8OjfjwAVwBfAeODTFO0kFVhdrXr//Rac99/fBqDOPdeyShI5\n4wyrQJiP11VZaZM4oG6mQqHJpHfhQtW2bWsHxPiKeaUgm3u822420Jsv1dU2oBlE1cRMei++2DJ4\nxoyxcYpkD8disrn4tWHGNb2quXviWeWJq+pbqtpfVbdT1T9G9z2kqg9H/75AVTuo6u6qupuq7p1N\nuzFErFbG5Zdb0aMjj7TJHY89ZjWca3RYNbtjjsml9RrKyuDKK61a4e6759dGoeja1SaojBlTs++R\nRyyfO8z89Kc2oSZfPvrIllnLNJEnCC691PLIL7jAcuR33bXw1/R4Ck3o1ticP98q6AHcdhuMGGG/\nTz7ZZlIefLBVjpOkq81lh2r9Xl8obr0V3n/fysAOGWIV9ObMgdatS60sNePG2fqSU6fmdk9V4d57\nrUrhgw/axCiPx5Mcp9bYjAVwsCp0d91lPag1a2yprEGD6h+AwxjAwWZS/vCDzarcZRcL5GEO4GDf\naFSthGsufPONzRR9/nkfwD2e+hC6IB5Po0b2dX2ffeCee2xqezQbp1Y6jgtko7d/f3tQjRxpdavv\nuafwutKRjWYRe+hcc42VJ/jLX0x/JkaOtNomB6RMRs2dzfEzETZc0+yaXthM64nfeSfcfz+sXRt+\njzgImja14kuJ9UzCyvbbW5GxE06wNUpj3yjSMXIkHHZYcfR5PJszofPEU1FZCU2ahN9eaMjMnWvV\nB48+2nzyM8+Ehx6yB/Btt9XYJhs32mIKU6dC586l1ezxuEA6T9yZIO5xh5dftnUxd9gBliyxAds7\n74TJk+1bxkcf2TqVEyeWWqnH4wZODWxmi2tel2t6IX/NJ5wA69fbmp2/+Q1cdBH07GnLrV1zDfz1\nr3D44cFqBffusWt6wT3NrumF3DUHWjvF44nRtCn8+tc12zfcYL3zRo2gosIGQz0eT/3xdoqnaJx8\nMpx9NrRtC/vvb4He4/FkxnviHo/H4zDeEw8BrukF9zR7vYXHNc2u6YXNNE/c4/F4PMnxdorH4/GE\nnM3STvF4PB6Pw0HcNa/LNb3gnmavt/C4ptk1veA9cY/H42lQeE/c4/F4Qo73xD0ej2czJasgLiJH\nichkEZkqIr9Ncc49IjJNRCaIyMBgZdbFNa/LNb3gnmavt/C4ptk1vVAAT1xEGgH3AUcCOwFniMj2\nCeccDfRV1e2wBZQfzElFHkyYMKHQlwgU1/SCe5q93sLjmmbX9ELumrPpie8NTFPV2aq6AXgGSFxQ\n6zjgSQBV/QRoKyJdclKSI1VVVYVsPnBc0wvuafZ6C49rml3TC7lrziaIdwfmxm3Pi+5Ld878JOd4\nPB6PJ2CcHdicNWtWqSXkhGt6wT3NXm/hcU2za3ohd80ZUwxFZF/gRlU9Krp9NaCq+qe4cx4ERqvq\ns9HtycDBqro4oS2fX+jxeDx5kCrFMJtFIT4DthWRXsBC4HTgjIRzXgMuAZ6NBv2qxACeToTH4/F4\n8iNjEFfVTSJyKfAOZr88pqqTRORCO6wPq+qbIjJYRKYD3wPDCivb4/F4PFDkGZsej8fjCRZnBzY9\nHo/H44O4x+PxOI0P4h6Px+MwPoh7NjtE5Pel1pCIiHRM2D4zWm9ouIiEMmtLRA4RkftE5FUReUlE\n/vPuvnIAAAahSURBVCgi25ZaVyrEOFVETon+fVj0Hv88Wj4kVIjIXSIyqN7tuDKwKSKHACcBWwOb\ngKnAo6o6vaTCkhD9T3kKoMALwKFYaYLJwIOqWl1CeUkRkbuAF1X1g1JrqS8iMkdVe5ZaRzwi8oWq\n7h79+zrgQOAp4KfAPFW9opT6EhGR24GuwEjgeGAm9n/u58Btqvp8CeUlRUQeADoDzYCVQHMs/fkn\nwGJV/UUJ5dVBRJYCs4FOwLPA06o6Pud2XAjirn2gXPswQXAfqGIhIitTHQK2VNVs5kAUDREZr6q7\nRf/+AjhQVb8XkabAF6q6S2kV1kZEvoppEpEmwPuqOkhE2gFjVHXn0iqsS0xz9J4uArZS1fVR/V+o\n6oASS6xF7DMhIv2A07A5OI2Bp7H/f1OzaSdUH/Q0/DTuA/UM9oH6jYi8AIwBQhXEsf+gyT5MTwNf\nlFhbKuap6p5xH6h/iUjOH6giUgXslWxSmYjMTXJ+qdlSRHbDLMymqvo9gKpuEJFNpZWWlGoRaa+q\ny4FuWHBBVSvDav8AG+HHe/qZqq6Pbm8UkdB9+8W+qRP9v3ULcIuIDMAmU74JZGVdhc4nSkG1iLSP\n/l3rA4X1vMLGjx8moNaHCQjjhwniPlCqeouq7gScCmyBfaDCxpNArxTHniqmkCxZCNwF/BlYJiJb\nAYhIB6Kfl5BxGzBeRN4FxmJBBhHpBHxZSmFpWCQirQBiZUIARKQrsL5kqlJTJ3ap6kRVvUZVsx57\ncMVOOQ24A7NQ+gMXq+p/oh+ov6nqkJIKTEBE/gucoqqrE/Z3BV5T1b1Loyw18V/3PcUj+m2nuar+\nUGotiUQ7Tn2A6arqXk3XKCLSEmipqktKrSUeEWmVGCPyaseFIA6bxwcqrB8mCO4DVUyiX+v3pqbs\n8Xzg07Au5Or1lg4R2V5VJ5daR7bkotelIN4TWKmqVSLSG9gTmKyqX5dUWBpEZE/ismlc+BC5ollE\n/g94AJiGBReAHpiP+HNVfadU2pLh9ZaWMGYspSMXvU4E8Wj52wuBdZineCXwAbAvVpDrrhLKq4OI\nHAz8BRt82wPT2g7YAJylqqEbeHNNs4hMAo5W1VkJ+7cB3lTVHUoiLAVeb+ERkXtSHQLOUdU2xdST\niaD0upKdchawI9ACmAX0UdWlUXviE2zAKEzcDfxfVOM2wF3R9KwjgMeA/yutvKS4prkJtspUIvOB\npkXWkg1eb+EZBvwa6+wlklg+OwwEoteVIL5JVdeIyHpgDVABEM2zLa2y5DRW1aXRv+cQzaJQ1XdF\n5O7SyUqLa5ofBz6LppzGviVsjeXaPlYyVanxegvPZ8DXqvph4gERubH4cjISiF5X7JQR2MSZlsAP\nWErWW9hMyNaqemrp1NVFRB7HUvZGAccC81X1VyLSApt0sH1JBSbBUc07YlrjB95eU9VvS6cqNV5v\nYYkmP6wNY6ZPMoLS60oQb0Ltaez7YF835gD3xyZOhIXoJJ8LMAvoS+BxtcU1tgQ6q+rskgpMgoua\nPR6PI0Hc40lERNoC12BlGDpjD/glwKvAH8OWhur1Fh7XNAel14kZmyLSSkRuFpFvRGSFiCwVkY9F\n5JxSa0tGnN6vE/QOLbW2VDio+TmgEihX1faq2gE4JLrvuZIqS47XW3hc0xyIXid64iLyKvAy8B42\nFbwl8AxwHebdXltCeXVwTS+4p1lEpqhq/1yPlQqvt/C4pjkovU70xIHeqjpCVedFc8KPVdVpWIrO\niSXWlgzX9IJ7mmeLyFUi0iW2Q0S6iMhvqcmmCBNeb+FxTXMgel0J4t+LyAEAInIssBxArS53GHMM\nXdML7mk+DegAvC8ilSKyHIgA7bFvEmHD6y08rmkORq+qhv4HGAB8inlFY4F+0f2dgMtLrc91vQ5r\n3h44HGiVsP+oUmvzer3mYukt+ZsI4CYMK7WGzVlvWDUDlwNTgFewWbzHxR37otT6vF6vuVh6S/5G\nArgRc0qtYXPWG1bNwFex3gvQG/gc+EV0e3yp9Xm9XnOx9Dox7V5EJqY6BHRJcaxkuKYXnNTcSKOl\nc1V1loiUAy+ISC/C6eF7vYXHNc2B6HUiiGNB5EjMr41HgDp1B0KAa3rBPc2LRWSgqk4AUNXVIvJT\nrOZHqNarjOL1Fh7XNAei15Ug/gb2tWNC4gERiRRfTkZc0wvuaT6bhGXN1Ja/O1tEHiqNpLR4vYXH\nNc2B6HViso/H4/F4kuNKnrjH4/F4kuCDuMfj8TiMD+Iej8fjMD6Iezwej8P4IO7xeDwO8/83CaaE\nfWYHdwAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0xa82bfa6c>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "#  Oil priced in rtb index units:\n",
    "plot( oilrtb )"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "No big suprises here. Oil from world-ex-USD perspective looks very similar to the dollar-only perspective."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "##  Concluding remarks\n",
    "\n",
    "Although WTI has more desirable petrochemical properties than Brent oil,\n",
    "our analysis of their prices reveal that Brent is preferable over WTI\n",
    "in the context of a financial portfolio -- denominated in practically\n",
    "any currency.\n",
    "\n",
    "Before taking a position in oil, carefully evaluate the premium of Brent over WTI,\n",
    "i.e. the BoW spread.\n",
    "\n",
    "The post-2014 crash in oil prices portends a downward look at\n",
    "the \\$20 support level in current U.S. dollars especially in view\n",
    "of the caveats listed below.\n",
    "This would be a major concern for oil companies worldwide\n",
    "(for example, in August 2017 BP announced their break-even point\n",
    "was \\$47 with respect to the price of oil). \n",
    "\n",
    "\n",
    "### Caveats\n",
    "\n",
    "- A complete analysis would include the impact of shale oil and *alternate energy sources*.\n",
    "\n",
    "- As electric cars become more popular, the demand for petroleum will obviously diminish.\n",
    "\n",
    "- If ISIS becomes dominate over oil fields, expect some minor supply at half the market price.\n",
    "\n",
    "- Be attentive to offshore storage of crude oil, literally on non-active tanker ships with no destinations."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---\n",
    "\n",
    "*Dedicated to recently retired Andrew Hall: the name of the game has changed.*"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}