ml-finance-python

python scripts for finance machine learning
git clone https://9o.is/git/ml-finance-python.git
lab_129.ipynb

(246419B)
      1 {
      2  "cells": [
      3   {
      4    "cell_type": "markdown",
      5    "metadata": {},
      6    "source": [
      7     "# Monte Carlo simulation of Dynamic Risk Budgeting between PSP and GHP\n",
      8     "\n",
      9     "We've looked at the fundamental problem of how much to allocate in the safe asset vs the performance seeking asset, and we investigated static and glidepath based techniques. Now we'll look at modern dynamic techniques that are inspired by CPPI to ensure that the account value reaches a certain target minimum floor, but also maintains exposure to the upside through a dynamic risk budget"
     10    ]
     11   },
     12   {
     13    "cell_type": "code",
     14    "execution_count": 1,
     15    "metadata": {},
     16    "outputs": [],
     17    "source": [
     18     "import numpy as np\n",
     19     "import pandas as pd\n",
     20     "import edhec_risk_kit_129 as erk\n",
     21     "import matplotlib.pyplot as plt\n",
     22     "import seaborn as sns\n",
     23     "\n",
     24     "%matplotlib inline\n",
     25     "%load_ext autoreload\n",
     26     "%autoreload 2"
     27    ]
     28   },
     29   {
     30    "cell_type": "markdown",
     31    "metadata": {},
     32    "source": [
     33     "Let's start by building 500 scenarios for interest rates, an duration matched bond portfolio (proxied by a zero coupon bond) and a stock portfolio."
     34    ]
     35   },
     36   {
     37    "cell_type": "code",
     38    "execution_count": 2,
     39    "metadata": {},
     40    "outputs": [
     41     {
     42      "data": {
     43       "text/html": [
     44        "<div>\n",
     45        "<style scoped>\n",
     46        "    .dataframe tbody tr th:only-of-type {\n",
     47        "        vertical-align: middle;\n",
     48        "    }\n",
     49        "\n",
     50        "    .dataframe tbody tr th {\n",
     51        "        vertical-align: top;\n",
     52        "    }\n",
     53        "\n",
     54        "    .dataframe thead th {\n",
     55        "        text-align: right;\n",
     56        "    }\n",
     57        "</style>\n",
     58        "<table border=\"1\" class=\"dataframe\">\n",
     59        "  <thead>\n",
     60        "    <tr style=\"text-align: right;\">\n",
     61        "      <th></th>\n",
     62        "      <th>ZC</th>\n",
     63        "      <th>Eq</th>\n",
     64        "      <th>70/30</th>\n",
     65        "    </tr>\n",
     66        "  </thead>\n",
     67        "  <tbody>\n",
     68        "    <tr>\n",
     69        "      <th>mean</th>\n",
     70        "      <td>1.34</td>\n",
     71        "      <td>1.95</td>\n",
     72        "      <td>1.74</td>\n",
     73        "    </tr>\n",
     74        "    <tr>\n",
     75        "      <th>std</th>\n",
     76        "      <td>0.00</td>\n",
     77        "      <td>0.95</td>\n",
     78        "      <td>0.58</td>\n",
     79        "    </tr>\n",
     80        "    <tr>\n",
     81        "      <th>p_breach</th>\n",
     82        "      <td>NaN</td>\n",
     83        "      <td>0.04</td>\n",
     84        "      <td>0.01</td>\n",
     85        "    </tr>\n",
     86        "    <tr>\n",
     87        "      <th>e_short</th>\n",
     88        "      <td>NaN</td>\n",
     89        "      <td>0.12</td>\n",
     90        "      <td>0.08</td>\n",
     91        "    </tr>\n",
     92        "    <tr>\n",
     93        "      <th>p_reach</th>\n",
     94        "      <td>NaN</td>\n",
     95        "      <td>NaN</td>\n",
     96        "      <td>NaN</td>\n",
     97        "    </tr>\n",
     98        "    <tr>\n",
     99        "      <th>e_surplus</th>\n",
    100        "      <td>NaN</td>\n",
    101        "      <td>NaN</td>\n",
    102        "      <td>NaN</td>\n",
    103        "    </tr>\n",
    104        "  </tbody>\n",
    105        "</table>\n",
    106        "</div>"
    107       ],
    108       "text/plain": [
    109        "             ZC    Eq  70/30\n",
    110        "mean       1.34  1.95   1.74\n",
    111        "std        0.00  0.95   0.58\n",
    112        "p_breach    NaN  0.04   0.01\n",
    113        "e_short     NaN  0.12   0.08\n",
    114        "p_reach     NaN   NaN    NaN\n",
    115        "e_surplus   NaN   NaN    NaN"
    116       ]
    117      },
    118      "execution_count": 2,
    119      "metadata": {},
    120      "output_type": "execute_result"
    121     }
    122    ],
    123    "source": [
    124     "n_scenarios =  5000\n",
    125     "rates, zc_prices = erk.cir(10, n_scenarios=n_scenarios, b=0.03, r_0 = 0.03, sigma=0.02)\n",
    126     "price_eq = erk.gbm(n_years=10,n_scenarios=n_scenarios, mu=0.07, sigma=0.15)\n",
    127     "rets_eq = price_eq.pct_change().dropna()\n",
    128     "rets_zc = zc_prices.pct_change().dropna()\n",
    129     "rets_7030b = erk.bt_mix(rets_eq, rets_zc, allocator=erk.fixedmix_allocator, w1=0.7)\n",
    130     "pd.concat([erk.terminal_stats(rets_zc, name=\"ZC\", floor=0.75), \n",
    131     "           erk.terminal_stats(rets_eq, name=\"Eq\", floor=0.75),\n",
    132     "           erk.terminal_stats(rets_7030b, name=\"70/30\", floor=0.75)],\n",
    133     "          axis=1).round(2)"
    134    ]
    135   },
    136   {
    137    "cell_type": "markdown",
    138    "metadata": {},
    139    "source": [
    140     "Let's write a new allocator that we'll call a Floor Allocator applies a dynamic risk budget to allocate more to the PSP when there is a cushion, similar to what we did for CPPI\n",
    141     "\n",
    142     "```python\n",
    143     "def floor_allocator(psp_r, ghp_r, floor, zc_prices, m=3):\n",
    144     "    \"\"\"\n",
    145     "    Allocate between PSP and GHP with the goal to provide exposure to the upside\n",
    146     "    of the PSP without going violating the floor.\n",
    147     "    Uses a CPPI-style dynamic risk budgeting algorithm by investing a multiple\n",
    148     "    of the cushion in the PSP\n",
    149     "    Returns a DataFrame with the same shape as the psp/ghp representing the weights in the PSP\n",
    150     "    \"\"\"\n",
    151     "    if zc_prices.shape != psp_r.shape:\n",
    152     "        raise ValueError(\"PSP and ZC Prices must have the same shape\")\n",
    153     "    n_steps, n_scenarios = psp_r.shape\n",
    154     "    account_value = np.repeat(1, n_scenarios)\n",
    155     "    floor_value = np.repeat(1, n_scenarios)\n",
    156     "    w_history = pd.DataFrame(index=psp_r.index, columns=psp_r.columns)\n",
    157     "    for step in range(n_steps):\n",
    158     "        floor_value = floor*zc_prices.iloc[step] ## PV of Floor assuming today's rates and flat YC\n",
    159     "        cushion = (account_value - floor_value)/account_value\n",
    160     "        psp_w = (m*cushion).clip(0, 1) # same as applying min and max\n",
    161     "        ghp_w = 1-psp_w\n",
    162     "        psp_alloc = account_value*psp_w\n",
    163     "        ghp_alloc = account_value*ghp_w\n",
    164     "        # recompute the new account value at the end of this step\n",
    165     "        account_value = psp_alloc*(1+psp_r.iloc[step]) + ghp_alloc*(1+ghp_r.iloc[step])\n",
    166     "        w_history.iloc[step] = psp_w\n",
    167     "    return w_history\n",
    168     "```\n"
    169    ]
    170   },
    171   {
    172    "cell_type": "code",
    173    "execution_count": 3,
    174    "metadata": {},
    175    "outputs": [
    176     {
    177      "data": {
    178       "text/html": [
    179        "<div>\n",
    180        "<style scoped>\n",
    181        "    .dataframe tbody tr th:only-of-type {\n",
    182        "        vertical-align: middle;\n",
    183        "    }\n",
    184        "\n",
    185        "    .dataframe tbody tr th {\n",
    186        "        vertical-align: top;\n",
    187        "    }\n",
    188        "\n",
    189        "    .dataframe thead th {\n",
    190        "        text-align: right;\n",
    191        "    }\n",
    192        "</style>\n",
    193        "<table border=\"1\" class=\"dataframe\">\n",
    194        "  <thead>\n",
    195        "    <tr style=\"text-align: right;\">\n",
    196        "      <th></th>\n",
    197        "      <th>ZC</th>\n",
    198        "      <th>Eq</th>\n",
    199        "      <th>70/30</th>\n",
    200        "      <th>Floor75</th>\n",
    201        "    </tr>\n",
    202        "  </thead>\n",
    203        "  <tbody>\n",
    204        "    <tr>\n",
    205        "      <th>mean</th>\n",
    206        "      <td>1.34</td>\n",
    207        "      <td>1.95</td>\n",
    208        "      <td>1.74</td>\n",
    209        "      <td>1.92</td>\n",
    210        "    </tr>\n",
    211        "    <tr>\n",
    212        "      <th>std</th>\n",
    213        "      <td>0.00</td>\n",
    214        "      <td>0.95</td>\n",
    215        "      <td>0.58</td>\n",
    216        "      <td>0.96</td>\n",
    217        "    </tr>\n",
    218        "    <tr>\n",
    219        "      <th>p_breach</th>\n",
    220        "      <td>NaN</td>\n",
    221        "      <td>0.04</td>\n",
    222        "      <td>0.01</td>\n",
    223        "      <td>NaN</td>\n",
    224        "    </tr>\n",
    225        "    <tr>\n",
    226        "      <th>e_short</th>\n",
    227        "      <td>NaN</td>\n",
    228        "      <td>0.12</td>\n",
    229        "      <td>0.08</td>\n",
    230        "      <td>NaN</td>\n",
    231        "    </tr>\n",
    232        "    <tr>\n",
    233        "      <th>p_reach</th>\n",
    234        "      <td>NaN</td>\n",
    235        "      <td>NaN</td>\n",
    236        "      <td>NaN</td>\n",
    237        "      <td>NaN</td>\n",
    238        "    </tr>\n",
    239        "    <tr>\n",
    240        "      <th>e_surplus</th>\n",
    241        "      <td>NaN</td>\n",
    242        "      <td>NaN</td>\n",
    243        "      <td>NaN</td>\n",
    244        "      <td>NaN</td>\n",
    245        "    </tr>\n",
    246        "  </tbody>\n",
    247        "</table>\n",
    248        "</div>"
    249       ],
    250       "text/plain": [
    251        "             ZC    Eq  70/30  Floor75\n",
    252        "mean       1.34  1.95   1.74     1.92\n",
    253        "std        0.00  0.95   0.58     0.96\n",
    254        "p_breach    NaN  0.04   0.01      NaN\n",
    255        "e_short     NaN  0.12   0.08      NaN\n",
    256        "p_reach     NaN   NaN    NaN      NaN\n",
    257        "e_surplus   NaN   NaN    NaN      NaN"
    258       ]
    259      },
    260      "execution_count": 3,
    261      "metadata": {},
    262      "output_type": "execute_result"
    263     }
    264    ],
    265    "source": [
    266     "rets_floor75 = erk.bt_mix(rets_eq, rets_zc, allocator=erk.floor_allocator, floor=.75,  zc_prices=zc_prices[1:])\n",
    267     "pd.concat([erk.terminal_stats(rets_zc, name=\"ZC\", floor=0.75), \n",
    268     "           erk.terminal_stats(rets_eq, name=\"Eq\", floor=0.75),\n",
    269     "           erk.terminal_stats(rets_7030b, name=\"70/30\", floor=0.75),\n",
    270     "           erk.terminal_stats(rets_floor75, name=\"Floor75\", floor=0.75),\n",
    271     "          ],\n",
    272     "          axis=1).round(2)"
    273    ]
    274   },
    275   {
    276    "cell_type": "code",
    277    "execution_count": 4,
    278    "metadata": {},
    279    "outputs": [
    280     {
    281      "data": {
    282       "text/html": [
    283        "<div>\n",
    284        "<style scoped>\n",
    285        "    .dataframe tbody tr th:only-of-type {\n",
    286        "        vertical-align: middle;\n",
    287        "    }\n",
    288        "\n",
    289        "    .dataframe tbody tr th {\n",
    290        "        vertical-align: top;\n",
    291        "    }\n",
    292        "\n",
    293        "    .dataframe thead th {\n",
    294        "        text-align: right;\n",
    295        "    }\n",
    296        "</style>\n",
    297        "<table border=\"1\" class=\"dataframe\">\n",
    298        "  <thead>\n",
    299        "    <tr style=\"text-align: right;\">\n",
    300        "      <th></th>\n",
    301        "      <th>ZC</th>\n",
    302        "      <th>Eq</th>\n",
    303        "      <th>70/30</th>\n",
    304        "      <th>Floor75</th>\n",
    305        "      <th>Floor75m1</th>\n",
    306        "    </tr>\n",
    307        "  </thead>\n",
    308        "  <tbody>\n",
    309        "    <tr>\n",
    310        "      <th>mean</th>\n",
    311        "      <td>1.34</td>\n",
    312        "      <td>1.95</td>\n",
    313        "      <td>1.74</td>\n",
    314        "      <td>1.92</td>\n",
    315        "      <td>1.61</td>\n",
    316        "    </tr>\n",
    317        "    <tr>\n",
    318        "      <th>std</th>\n",
    319        "      <td>0.00</td>\n",
    320        "      <td>0.95</td>\n",
    321        "      <td>0.58</td>\n",
    322        "      <td>0.96</td>\n",
    323        "      <td>0.42</td>\n",
    324        "    </tr>\n",
    325        "    <tr>\n",
    326        "      <th>p_breach</th>\n",
    327        "      <td>NaN</td>\n",
    328        "      <td>0.04</td>\n",
    329        "      <td>0.01</td>\n",
    330        "      <td>NaN</td>\n",
    331        "      <td>NaN</td>\n",
    332        "    </tr>\n",
    333        "    <tr>\n",
    334        "      <th>e_short</th>\n",
    335        "      <td>NaN</td>\n",
    336        "      <td>0.12</td>\n",
    337        "      <td>0.08</td>\n",
    338        "      <td>NaN</td>\n",
    339        "      <td>NaN</td>\n",
    340        "    </tr>\n",
    341        "    <tr>\n",
    342        "      <th>p_reach</th>\n",
    343        "      <td>NaN</td>\n",
    344        "      <td>NaN</td>\n",
    345        "      <td>NaN</td>\n",
    346        "      <td>NaN</td>\n",
    347        "      <td>NaN</td>\n",
    348        "    </tr>\n",
    349        "    <tr>\n",
    350        "      <th>e_surplus</th>\n",
    351        "      <td>NaN</td>\n",
    352        "      <td>NaN</td>\n",
    353        "      <td>NaN</td>\n",
    354        "      <td>NaN</td>\n",
    355        "      <td>NaN</td>\n",
    356        "    </tr>\n",
    357        "  </tbody>\n",
    358        "</table>\n",
    359        "</div>"
    360       ],
    361       "text/plain": [
    362        "             ZC    Eq  70/30  Floor75  Floor75m1\n",
    363        "mean       1.34  1.95   1.74     1.92       1.61\n",
    364        "std        0.00  0.95   0.58     0.96       0.42\n",
    365        "p_breach    NaN  0.04   0.01      NaN        NaN\n",
    366        "e_short     NaN  0.12   0.08      NaN        NaN\n",
    367        "p_reach     NaN   NaN    NaN      NaN        NaN\n",
    368        "e_surplus   NaN   NaN    NaN      NaN        NaN"
    369       ]
    370      },
    371      "execution_count": 4,
    372      "metadata": {},
    373      "output_type": "execute_result"
    374     }
    375    ],
    376    "source": [
    377     "rets_floor75m1 = erk.bt_mix(rets_eq, rets_zc, allocator=erk.floor_allocator, zc_prices=zc_prices[1:], floor=.75, m=1)\n",
    378     "pd.concat([erk.terminal_stats(rets_zc, name=\"ZC\", floor=0.75), \n",
    379     "           erk.terminal_stats(rets_eq, name=\"Eq\", floor=0.75),\n",
    380     "           erk.terminal_stats(rets_7030b, name=\"70/30\", floor=0.75),\n",
    381     "           erk.terminal_stats(rets_floor75, name=\"Floor75\", floor=0.75),\n",
    382     "           erk.terminal_stats(rets_floor75m1, name=\"Floor75m1\", floor=0.75),\n",
    383     "          ],\n",
    384     "          axis=1).round(2)"
    385    ]
    386   },
    387   {
    388    "cell_type": "code",
    389    "execution_count": 5,
    390    "metadata": {},
    391    "outputs": [
    392     {
    393      "data": {
    394       "text/html": [
    395        "<div>\n",
    396        "<style scoped>\n",
    397        "    .dataframe tbody tr th:only-of-type {\n",
    398        "        vertical-align: middle;\n",
    399        "    }\n",
    400        "\n",
    401        "    .dataframe tbody tr th {\n",
    402        "        vertical-align: top;\n",
    403        "    }\n",
    404        "\n",
    405        "    .dataframe thead th {\n",
    406        "        text-align: right;\n",
    407        "    }\n",
    408        "</style>\n",
    409        "<table border=\"1\" class=\"dataframe\">\n",
    410        "  <thead>\n",
    411        "    <tr style=\"text-align: right;\">\n",
    412        "      <th></th>\n",
    413        "      <th>ZC</th>\n",
    414        "      <th>Eq</th>\n",
    415        "      <th>70/30</th>\n",
    416        "      <th>Floor75</th>\n",
    417        "      <th>Floor75m1</th>\n",
    418        "      <th>Floor75m5</th>\n",
    419        "      <th>Floor75m10</th>\n",
    420        "    </tr>\n",
    421        "  </thead>\n",
    422        "  <tbody>\n",
    423        "    <tr>\n",
    424        "      <th>mean</th>\n",
    425        "      <td>1.34</td>\n",
    426        "      <td>1.95</td>\n",
    427        "      <td>1.74</td>\n",
    428        "      <td>1.92</td>\n",
    429        "      <td>1.61</td>\n",
    430        "      <td>1.93</td>\n",
    431        "      <td>1.93</td>\n",
    432        "    </tr>\n",
    433        "    <tr>\n",
    434        "      <th>std</th>\n",
    435        "      <td>0.00</td>\n",
    436        "      <td>0.95</td>\n",
    437        "      <td>0.58</td>\n",
    438        "      <td>0.96</td>\n",
    439        "      <td>0.42</td>\n",
    440        "      <td>0.96</td>\n",
    441        "      <td>0.96</td>\n",
    442        "    </tr>\n",
    443        "    <tr>\n",
    444        "      <th>p_breach</th>\n",
    445        "      <td>NaN</td>\n",
    446        "      <td>0.04</td>\n",
    447        "      <td>0.01</td>\n",
    448        "      <td>NaN</td>\n",
    449        "      <td>NaN</td>\n",
    450        "      <td>0.00</td>\n",
    451        "      <td>0.02</td>\n",
    452        "    </tr>\n",
    453        "    <tr>\n",
    454        "      <th>e_short</th>\n",
    455        "      <td>NaN</td>\n",
    456        "      <td>0.12</td>\n",
    457        "      <td>0.08</td>\n",
    458        "      <td>NaN</td>\n",
    459        "      <td>NaN</td>\n",
    460        "      <td>0.00</td>\n",
    461        "      <td>0.00</td>\n",
    462        "    </tr>\n",
    463        "    <tr>\n",
    464        "      <th>p_reach</th>\n",
    465        "      <td>NaN</td>\n",
    466        "      <td>NaN</td>\n",
    467        "      <td>NaN</td>\n",
    468        "      <td>NaN</td>\n",
    469        "      <td>NaN</td>\n",
    470        "      <td>NaN</td>\n",
    471        "      <td>NaN</td>\n",
    472        "    </tr>\n",
    473        "    <tr>\n",
    474        "      <th>e_surplus</th>\n",
    475        "      <td>NaN</td>\n",
    476        "      <td>NaN</td>\n",
    477        "      <td>NaN</td>\n",
    478        "      <td>NaN</td>\n",
    479        "      <td>NaN</td>\n",
    480        "      <td>NaN</td>\n",
    481        "      <td>NaN</td>\n",
    482        "    </tr>\n",
    483        "  </tbody>\n",
    484        "</table>\n",
    485        "</div>"
    486       ],
    487       "text/plain": [
    488        "             ZC    Eq  70/30  Floor75  Floor75m1  Floor75m5  Floor75m10\n",
    489        "mean       1.34  1.95   1.74     1.92       1.61       1.93        1.93\n",
    490        "std        0.00  0.95   0.58     0.96       0.42       0.96        0.96\n",
    491        "p_breach    NaN  0.04   0.01      NaN        NaN       0.00        0.02\n",
    492        "e_short     NaN  0.12   0.08      NaN        NaN       0.00        0.00\n",
    493        "p_reach     NaN   NaN    NaN      NaN        NaN        NaN         NaN\n",
    494        "e_surplus   NaN   NaN    NaN      NaN        NaN        NaN         NaN"
    495       ]
    496      },
    497      "execution_count": 5,
    498      "metadata": {},
    499      "output_type": "execute_result"
    500     }
    501    ],
    502    "source": [
    503     "rets_floor75m5 = erk.bt_mix(rets_eq, rets_zc, allocator=erk.floor_allocator, zc_prices=zc_prices[1:], floor=.75, m=5)\n",
    504     "rets_floor75m10 = erk.bt_mix(rets_eq, rets_zc, allocator=erk.floor_allocator, zc_prices=zc_prices[1:], floor=.75, m=10)\n",
    505     "pd.concat([erk.terminal_stats(rets_zc, name=\"ZC\", floor=0.75), \n",
    506     "           erk.terminal_stats(rets_eq, name=\"Eq\", floor=0.75),\n",
    507     "           erk.terminal_stats(rets_7030b, name=\"70/30\", floor=0.75),\n",
    508     "           erk.terminal_stats(rets_floor75, name=\"Floor75\", floor=0.75),\n",
    509     "           erk.terminal_stats(rets_floor75m1, name=\"Floor75m1\", floor=0.75),\n",
    510     "           erk.terminal_stats(rets_floor75m5, name=\"Floor75m5\", floor=0.75),\n",
    511     "           erk.terminal_stats(rets_floor75m10, name=\"Floor75m10\", floor=0.75)\n",
    512     "          ],\n",
    513     "          axis=1).round(2)"
    514    ]
    515   },
    516   {
    517    "cell_type": "code",
    518    "execution_count": 6,
    519    "metadata": {},
    520    "outputs": [
    521     {
    522      "name": "stderr",
    523      "output_type": "stream",
    524      "text": [
    525       "/home/vijay/anaconda3/lib/python3.7/site-packages/scipy/stats/stats.py:1713: FutureWarning: Using a non-tuple sequence for multidimensional indexing is deprecated; use `arr[tuple(seq)]` instead of `arr[seq]`. In the future this will be interpreted as an array index, `arr[np.array(seq)]`, which will result either in an error or a different result.\n",
    526       "  return np.add.reduce(sorted[indexer] * weights, axis=axis) / sumval\n"
    527      ]
    528     },
    529     {
    530      "data": {
    531       "image/png": "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\n",
    532       "text/plain": [
    533        "<Figure size 864x432 with 1 Axes>"
    534       ]
    535      },
    536      "metadata": {
    537       "needs_background": "light"
    538      },
    539      "output_type": "display_data"
    540     }
    541    ],
    542    "source": [
    543     "tv_eq = erk.terminal_values(rets_eq)\n",
    544     "tv_zc = erk.terminal_values(rets_zc)\n",
    545     "tv_7030b = erk.terminal_values(rets_7030b)\n",
    546     "tv_floor75 = erk.terminal_values(rets_floor75)\n",
    547     "tv_floor75m1 = erk.terminal_values(rets_floor75m1)\n",
    548     "import seaborn as sns\n",
    549     "import matplotlib.pyplot as plt\n",
    550     "plt.figure(figsize=(12, 6))\n",
    551     "sns.distplot(tv_eq, color=\"red\", label=\"100% Equities\", bins=100)\n",
    552     "#sns.distplot(tv_zc, color=\"blue\", label=\"100% Immunized Bonds\")\n",
    553     "sns.distplot(tv_7030b, color=\"orange\", label=\"70/30 Equities/Bonds\", bins=100)\n",
    554     "sns.distplot(tv_floor75, color=\"green\", label=\"Floor at 75%\", bins=100)\n",
    555     "\n",
    556     "plt.legend();"
    557    ]
    558   },
    559   {
    560    "cell_type": "code",
    561    "execution_count": 7,
    562    "metadata": {},
    563    "outputs": [
    564     {
    565      "data": {
    566       "image/png": "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\n",
    567       "text/plain": [
    568        "<Figure size 864x432 with 1 Axes>"
    569       ]
    570      },
    571      "metadata": {
    572       "needs_background": "light"
    573      },
    574      "output_type": "display_data"
    575     }
    576    ],
    577    "source": [
    578     "tv_eq = erk.terminal_values(rets_eq)\n",
    579     "tv_zc = erk.terminal_values(rets_zc)\n",
    580     "tv_7030b = erk.terminal_values(rets_7030b)\n",
    581     "tv_floor75 = erk.terminal_values(rets_floor75)\n",
    582     "tv_floor75m1 = erk.terminal_values(rets_floor75m1)\n",
    583     "import seaborn as sns\n",
    584     "import matplotlib.pyplot as plt\n",
    585     "plt.figure(figsize=(12, 6))\n",
    586     "sns.distplot(tv_eq, color=\"red\", label=\"100% Equities\", bins=100)\n",
    587     "plt.axvline(tv_eq.mean(), ls=\"--\", color=\"red\")\n",
    588     "#sns.distplot(tv_zc, color=\"blue\", label=\"100% Immunized Bonds\")\n",
    589     "#plt.axvline(tv_zc.mean(), ls=\"--\", color=\"blue\")\n",
    590     "sns.distplot(tv_7030b, color=\"orange\", label=\"70/30 Equities/Bonds\", bins=100)\n",
    591     "plt.axvline(tv_7030b.mean(), ls=\"--\", color=\"orange\")\n",
    592     "sns.distplot(tv_floor75, color=\"green\", label=\"Floor at 75%\", bins=100)\n",
    593     "plt.axvline(tv_floor75.mean(), ls=\"--\", color=\"green\")\n",
    594     "\n",
    595     "plt.legend();"
    596    ]
    597   },
    598   {
    599    "cell_type": "markdown",
    600    "metadata": {},
    601    "source": [
    602     "## Dynamic Risk Budgeting with Drawdown instead of a fixed floor"
    603    ]
    604   },
    605   {
    606    "cell_type": "markdown",
    607    "metadata": {},
    608    "source": [
    609     "```python\n",
    610     "def drawdown_allocator(psp_r, ghp_r, maxdd, m=3):\n",
    611     "    \"\"\"\n",
    612     "    Allocate between PSP and GHP with the goal to provide exposure to the upside\n",
    613     "    of the PSP without going violating the floor.\n",
    614     "    Uses a CPPI-style dynamic risk budgeting algorithm by investing a multiple\n",
    615     "    of the cushion in the PSP\n",
    616     "    Returns a DataFrame with the same shape as the psp/ghp representing the weights in the PSP\n",
    617     "    \"\"\"\n",
    618     "    n_steps, n_scenarios = psp_r.shape\n",
    619     "    account_value = np.repeat(1, n_scenarios)\n",
    620     "    floor_value = np.repeat(1, n_scenarios)\n",
    621     "    ### For MaxDD\n",
    622     "    peak_value = np.repeat(1, n_scenarios)\n",
    623     "    w_history = pd.DataFrame(index=psp_r.index, columns=psp_r.columns)\n",
    624     "    for step in range(n_steps):\n",
    625     "        ### For MaxDD\n",
    626     "        floor_value = (1-maxdd)*peak_value ### Floor is based on Prev Peak\n",
    627     "        cushion = (account_value - floor_value)/account_value\n",
    628     "        psp_w = (m*cushion).clip(0, 1) # same as applying min and max\n",
    629     "        ghp_w = 1-psp_w\n",
    630     "        psp_alloc = account_value*psp_w\n",
    631     "        ghp_alloc = account_value*ghp_w\n",
    632     "        # recompute the new account value at the end of this step\n",
    633     "        account_value = psp_alloc*(1+psp_r.iloc[step]) + ghp_alloc*(1+ghp_r.iloc[step])\n",
    634     "        ### For MaxDD\n",
    635     "        peak_value = np.maximum(peak_value, account_value) ### For MaxDD\n",
    636     "        w_history.iloc[step] = psp_w\n",
    637     "    return w_history\n",
    638     "```"
    639    ]
    640   },
    641   {
    642    "cell_type": "code",
    643    "execution_count": 8,
    644    "metadata": {},
    645    "outputs": [
    646     {
    647      "data": {
    648       "text/html": [
    649        "<div>\n",
    650        "<style scoped>\n",
    651        "    .dataframe tbody tr th:only-of-type {\n",
    652        "        vertical-align: middle;\n",
    653        "    }\n",
    654        "\n",
    655        "    .dataframe tbody tr th {\n",
    656        "        vertical-align: top;\n",
    657        "    }\n",
    658        "\n",
    659        "    .dataframe thead th {\n",
    660        "        text-align: right;\n",
    661        "    }\n",
    662        "</style>\n",
    663        "<table border=\"1\" class=\"dataframe\">\n",
    664        "  <thead>\n",
    665        "    <tr style=\"text-align: right;\">\n",
    666        "      <th></th>\n",
    667        "      <th>ZC</th>\n",
    668        "      <th>Eq</th>\n",
    669        "      <th>70/30</th>\n",
    670        "      <th>Floor75</th>\n",
    671        "      <th>Floor75m1</th>\n",
    672        "      <th>Floor75m5</th>\n",
    673        "      <th>Floor75m10</th>\n",
    674        "      <th>MaxDD25</th>\n",
    675        "    </tr>\n",
    676        "  </thead>\n",
    677        "  <tbody>\n",
    678        "    <tr>\n",
    679        "      <th>mean</th>\n",
    680        "      <td>1.34</td>\n",
    681        "      <td>1.95</td>\n",
    682        "      <td>1.74</td>\n",
    683        "      <td>1.92</td>\n",
    684        "      <td>1.61</td>\n",
    685        "      <td>1.93</td>\n",
    686        "      <td>1.93</td>\n",
    687        "      <td>1.61</td>\n",
    688        "    </tr>\n",
    689        "    <tr>\n",
    690        "      <th>std</th>\n",
    691        "      <td>0.00</td>\n",
    692        "      <td>0.95</td>\n",
    693        "      <td>0.58</td>\n",
    694        "      <td>0.96</td>\n",
    695        "      <td>0.42</td>\n",
    696        "      <td>0.96</td>\n",
    697        "      <td>0.96</td>\n",
    698        "      <td>0.53</td>\n",
    699        "    </tr>\n",
    700        "    <tr>\n",
    701        "      <th>p_breach</th>\n",
    702        "      <td>NaN</td>\n",
    703        "      <td>0.04</td>\n",
    704        "      <td>0.01</td>\n",
    705        "      <td>NaN</td>\n",
    706        "      <td>NaN</td>\n",
    707        "      <td>0.00</td>\n",
    708        "      <td>0.02</td>\n",
    709        "      <td>NaN</td>\n",
    710        "    </tr>\n",
    711        "    <tr>\n",
    712        "      <th>e_short</th>\n",
    713        "      <td>NaN</td>\n",
    714        "      <td>0.12</td>\n",
    715        "      <td>0.08</td>\n",
    716        "      <td>NaN</td>\n",
    717        "      <td>NaN</td>\n",
    718        "      <td>0.00</td>\n",
    719        "      <td>0.00</td>\n",
    720        "      <td>NaN</td>\n",
    721        "    </tr>\n",
    722        "    <tr>\n",
    723        "      <th>p_reach</th>\n",
    724        "      <td>NaN</td>\n",
    725        "      <td>NaN</td>\n",
    726        "      <td>NaN</td>\n",
    727        "      <td>NaN</td>\n",
    728        "      <td>NaN</td>\n",
    729        "      <td>NaN</td>\n",
    730        "      <td>NaN</td>\n",
    731        "      <td>NaN</td>\n",
    732        "    </tr>\n",
    733        "    <tr>\n",
    734        "      <th>e_surplus</th>\n",
    735        "      <td>NaN</td>\n",
    736        "      <td>NaN</td>\n",
    737        "      <td>NaN</td>\n",
    738        "      <td>NaN</td>\n",
    739        "      <td>NaN</td>\n",
    740        "      <td>NaN</td>\n",
    741        "      <td>NaN</td>\n",
    742        "      <td>NaN</td>\n",
    743        "    </tr>\n",
    744        "  </tbody>\n",
    745        "</table>\n",
    746        "</div>"
    747       ],
    748       "text/plain": [
    749        "             ZC    Eq  70/30  Floor75  Floor75m1  Floor75m5  Floor75m10  \\\n",
    750        "mean       1.34  1.95   1.74     1.92       1.61       1.93        1.93   \n",
    751        "std        0.00  0.95   0.58     0.96       0.42       0.96        0.96   \n",
    752        "p_breach    NaN  0.04   0.01      NaN        NaN       0.00        0.02   \n",
    753        "e_short     NaN  0.12   0.08      NaN        NaN       0.00        0.00   \n",
    754        "p_reach     NaN   NaN    NaN      NaN        NaN        NaN         NaN   \n",
    755        "e_surplus   NaN   NaN    NaN      NaN        NaN        NaN         NaN   \n",
    756        "\n",
    757        "           MaxDD25  \n",
    758        "mean          1.61  \n",
    759        "std           0.53  \n",
    760        "p_breach       NaN  \n",
    761        "e_short        NaN  \n",
    762        "p_reach        NaN  \n",
    763        "e_surplus      NaN  "
    764       ]
    765      },
    766      "execution_count": 8,
    767      "metadata": {},
    768      "output_type": "execute_result"
    769     }
    770    ],
    771    "source": [
    772     "0 scenarios for interest rates, an duracashrate = 0.02\n",
    773     "monthly_cashreturn = (1+cashrate)**(1/12) - 1\n",
    774     "rets_cash = pd.DataFrame(data= monthly_cashreturn, index=rets_eq.index, columns=rets_eq.columns)\n",
    775     "rets_maxdd25 = erk.bt_mix(rets_eq, rets_cash, allocator=erk.drawdown_allocator, maxdd=.25)\n",
    776     "tv_maxdd25 = erk.terminal_values(rets_maxdd25)\n",
    777     "pd.concat([erk.terminal_stats(rets_zc, name=\"ZC\", floor=0.75), \n",
    778     "           erk.terminal_stats(rets_eq, name=\"Eq\", floor=0.75),\n",
    779     "           erk.terminal_stats(rets_7030b, name=\"70/30\", floor=0.75),\n",
    780     "           erk.terminal_stats(rets_floor75, name=\"Floor75\", floor=0.75),\n",
    781     "           erk.terminal_stats(rets_floor75m1, name=\"Floor75m1\", floor=0.75),\n",
    782     "           erk.terminal_stats(rets_floor75m5, name=\"Floor75m5\", floor=0.75),\n",
    783     "           erk.terminal_stats(rets_floor75m10, name=\"Floor75m10\", floor=0.75),\n",
    784     "           erk.terminal_stats(rets_maxdd25, name=\"MaxDD25\", floor=0.75)           \n",
    785     "          ],\n",
    786     "          axis=1).round(2)"
    787    ]
    788   },
    789   {
    790    "cell_type": "code",
    791    "execution_count": 9,
    792    "metadata": {},
    793    "outputs": [
    794     {
    795      "data": {
    796       "text/plain": [
    797        "-0.2350481271095253"
    798       ]
    799      },
    800      "execution_count": 9,
    801      "metadata": {},
    802      "output_type": "execute_result"
    803     }
    804    ],
    805    "source": [
    806     "erk.summary_stats(rets_maxdd25)[\"Max Drawdown\"].min()"
    807    ]
    808   },
    809   {
    810    "cell_type": "code",
    811    "execution_count": 10,
    812    "metadata": {},
    813    "outputs": [
    814     {
    815      "data": {
    816       "image/png": "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\n",
    817       "text/plain": [
    818        "<Figure size 864x432 with 1 Axes>"
    819       ]
    820      },
    821      "metadata": {
    822       "needs_background": "light"
    823      },
    824      "output_type": "display_data"
    825     }
    826    ],
    827    "source": [
    828     "# Plot\n",
    829     "plt.figure(figsize=(12, 6))\n",
    830     "sns.distplot(tv_eq, color=\"red\", label=\"100% Equities\", bins=100)\n",
    831     "plt.axvline(tv_eq.mean(), ls=\"--\", color=\"red\")\n",
    832     "#sns.distplot(tv_zc, color=\"blue\", label=\"100% Immunized Bonds\")\n",
    833     "#plt.axvline(tv_zc.mean(), ls=\"--\", color=\"blue\")\n",
    834     "sns.distplot(tv_7030b, color=\"orange\", label=\"70/30 Equities/Bonds\", bins=100)\n",
    835     "plt.axvline(tv_7030b.mean(), ls=\"--\", color=\"orange\")\n",
    836     "sns.distplot(tv_floor75, color=\"green\", label=\"Floor at 75%\", bins=100)\n",
    837     "plt.axvline(tv_floor75.mean(), ls=\"--\", color=\"green\")\n",
    838     "sns.distplot(tv_maxdd25, color=\"yellow\", label=\"MaxDD = 25%\", bins=100)\n",
    839     "plt.axvline(tv_maxdd25.mean(), ls=\"--\", color=\"yellow\")\n",
    840     "plt.legend();"
    841    ]
    842   },
    843   {
    844    "cell_type": "markdown",
    845    "metadata": {},
    846    "source": [
    847     "## Backtesting Dynamic Strategies with Historical Data\n",
    848     "\n",
    849     "Try and work with real historic data such as a the Industry Portfolios or the Total Market Index we constructed and run back tests with different parameter values. For instance:"
    850    ]
    851   },
    852   {
    853    "cell_type": "code",
    854    "execution_count": 11,
    855    "metadata": {},
    856    "outputs": [
    857     {
    858      "data": {
    859       "text/plain": [
    860        "<matplotlib.axes._subplots.AxesSubplot at 0x7fdbf4f5ec18>"
    861       ]
    862      },
    863      "execution_count": 11,
    864      "metadata": {},
    865      "output_type": "execute_result"
    866     },
    867     {
    868      "data": {
    869       "image/png": "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\n",
    870       "text/plain": [
    871        "<Figure size 864x432 with 1 Axes>"
    872       ]
    873      },
    874      "metadata": {
    875       "needs_background": "light"
    876      },
    877      "output_type": "display_data"
    878     }
    879    ],
    880    "source": [
    881     "rets_tmi =  erk.get_total_market_index_returns()[\"1990\":]\n",
    882     "dd_tmi = erk.drawdown(rets_tmi)\n",
    883     "ax = dd_tmi[\"Wealth\"].plot(figsize=(12,6), ls=\"-\", color=\"goldenrod\")\n",
    884     "dd_tmi[\"Previous Peak\"].plot(ax=ax, ls=\":\", color=\"goldenrod\")"
    885    ]
    886   },
    887   {
    888    "cell_type": "code",
    889    "execution_count": 15,
    890    "metadata": {},
    891    "outputs": [
    892     {
    893      "data": {
    894       "text/plain": [
    895        "<matplotlib.axes._subplots.AxesSubplot at 0x7fdbf418a588>"
    896       ]
    897      },
    898      "execution_count": 15,
    899      "metadata": {},
    900      "output_type": "execute_result"
    901     },
    902     {
    903      "data": {
    904       "image/png": "iVBORw0KGgoAAAANSUhEUgAAAtYAAAFpCAYAAAC4ZG/7AAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDMuMC4yLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvOIA7rQAAIABJREFUeJzs3XeY1eWd///nffrMmV5gGIYuVYogNrBh1xBxk7ixJJofbkzWbGKya1w1q0lM+X6zZlNM1nw1xmXNZlFjiRp7jIhRiihIx6HPwMD0evo59++PcziADExnGOb1uC4uzl3PfQ7zx5t73p/7NtZaRERERESkZxz9vQARERERkZOBAmsRERERkV6gwFpEREREpBcosBYRERER6QUKrEVEREREeoECaxERERGRXqDAWkRERESkFyiwFhERERHpBQqsRURERER6gQJrEREREZFe4OrvBXRXUVGRHT16dH8vQ0REREROYh988EGttba4M30HbGA9evRoVq1a1d/LEBEREZGTmDFmV2f7KhVERERERKQXKLAWEREREekFCqxFRERERHrBgM2xbk80GqWyspJQKNTfSxmUfD4fZWVluN3u/l6KiIiIyHF3UgXWlZWVZGdnM3r0aIwx/b2cQcVaS11dHZWVlYwZM6a/lyMiIiJy3J1UqSChUIjCwkIF1f3AGENhYaF+WyAiIiKD1kkVWAMKqvuRvnsREREZzE66wLq/GWP44he/mC7HYjGKi4uZP39+l+ZZsmRJl8asWbOGl19+uUvvISIiIiK9R4F1L/P7/axfv55gMAjAG2+8wfDhw7s0RywW6/L7KrAWERER6V8KrPvAlVdeyUsvvQTA4sWLuf7669NtK1euZM6cOcycOZM5c+awZcsWABYtWsS1117Lpz/9aS677LLD5nv//feZOXMm27dvp62tjYULF3LGGWcwc+ZMnn/+eSKRCPfddx9PPvkkp512Gk8++eTx+7AiIiIiApxkp4IcquaD+wk3bOzVOb35Uyg+/b4O+1133XXcf//9zJ8/n7Vr17Jw4ULeeecdACZNmsTSpUtxuVz85S9/4Z577uGZZ54BYNmyZaxdu5aCggKWLFkCwHvvvcfXv/51nn/+eUaOHMk999zDRRddxGOPPUZjYyNnnnkml1xyCffffz+rVq3i17/+da9+ZhERERHpnJM2sO5P06dPZ+fOnSxevJirrrrqsLampiZuvvlmysvLMcYQjUbTbZdeeikFBQXp8qZNm7j11lt5/fXXKS0tBeD111/nhRde4Kc//SmQPAll9+7dx+FTiYiIiPQtm4gSbtxCIhbE4fTgK5wBQKh+A76CU/t5dR07aQPrzuws96Wrr76aO+64gyVLllBXV5euv/fee5k3bx7PPfccO3fu5MILL0y3+f3+w+YYNmwYoVCI1atXpwNray3PPPMMEydOPKzvihUr+u7DiIiIiPSxmg9/TMvOZ4mH6nBnj8HtL2P4RY8D0LDhPxl23kP9vMKOKce6jyxcuJD77ruPadOmHVbf1NSUfphx0aJFx5wjLy+Pl156iXvuuSedGnL55Zfzq1/9CmstAKtXrwYgOzublpaW3v0QIiIiIsdBIhahcfNvMa7kJmPWiMspPv276fbCGd/ur6V1iQLrPlJWVsbtt99+RP2dd97J3Xffzdy5c4nH4x3OM3ToUF588UW+9rWvsWLFCu69916i0SjTp09n6tSp3HvvvQDMmzePjRs36uFFERERGXCirdsB8JfOAwzG4cGTOy7d7skZGLc6mwM7nwPN7Nmz7apVqw6r27RpE5MnT+6nFQno30BERES6rm3PX9n79i2UXfpH9r79ZbJHzWfIGT/o72UBYIz5wFo7uzN9tWMtIiIiIv0q3Jg8ftiTMw6nN594uLGfV9Q9CqxFREREpF81b/8jGAdOb34ysI409PeSukWBtYiIiIj0L2Nw+ZOHOzg9eSTCCqxFRERERLosHm4gs+RcABy+AqWCiIiIiIh0VTSwj0S4AU9O8hQQpyePuHasRURERES6pq3iVQASsRAATm8+Nh5MlweSDgNrY8xjxphqY8z6T9R/3RizxRizwRjz74fU322M2Zpqu/yQ+itSdVuNMXcdUj/GGLPCGFNujHnSGOPprQ/XH4wxfPGLX0yXY7EYxcXFzJ8/v1vzLVq0iOLiYmbOnMn48eO5/PLLee+999LtX/rSlxgzZgwzZsxgwoQJ3HTTTezZs6fduW688UYmTpzI1KlTWbhwYfo69SVLlpCbm8tpp53Gaaedxv333w9ATU0N5557LlOnTuVPf/pTep4FCxawd+/ebn0eERERkUMlYm0A+EvOA5KBNTAgH2DszI71IuCKQyuMMfOABcB0a+2pwE9T9VOA64BTU2MeMsY4jTFO4D+BK4EpwPWpvgA/AX5urR0PNAC39PRD9Se/38/69esJBoMAvPHGG+mbFrvr85//PKtXr6a8vJy77rqLz3zmM2zatCnd/sADD/DRRx+xZcsWZs6cybx584hEIkfMc+ONN7J582bWrVtHMBjk0UcfTbedd955rFmzhjVr1nDffcnr4BcvXszNN9/MsmXLeOCBBwB48cUXmTVrVvqKdREREZGeiIcaME4f3sKpwMHAeiA+wNhhYG2tXQrUf6L6H4H/a60Np/pUp+oXAE9Ya8PW2h3AVuDM1J+t1trt1toI8ASwwBhjgIuAp1Pj/xu4poefqd9deeWVvPTSS0AyOL3++uvTbStXrmTOnDnMnDmTOXPmsGVL8tzGn/3sZyxcuBCAdevWMXXqVAKBwBFzz5s3j1tvvZVHHnnkiDZjDN/61rcoKSnhlVdeOaL9qquuwhiDMYYzzzyTysrKY34Ot9tNMBgkHA7jcDiIxWL84he/4NvfHhjXioqIiMiJLREPE9j/Hu7ssRiTDEsdnjyAAZln7ermuAnAecaYHwEh4A5r7fvAcGD5If0qU3UAFZ+oPwsoBBqttbF2+vfIE39ro6K24yvDu2JEkZPrzvV32O+6667j/vvvZ/78+axdu5aFCxfyzjvvADBp0iSWLl2Ky+XiL3/5C/fccw/PPPMM3/zmN7nwwgt57rnn+NGPfsTDDz9MZmZmu/PPmjWLhx9++KjvP2vWLDZv3syCBQvabY9Go/z+97/nl7/8Zbpu2bJlzJgxg9LSUn76059y6qmncsMNN3DDDTfw+OOP85Of/ISHHnqIm2666ajrEhEREemK1l1/JtK4iYyS89N1Tm8BMLgCaxeQD5wNnAE8ZYwZC5h2+lra3xm3x+jfLmPMrcCtACNHjuziko+f6dOns3PnThYvXsxVV111WFtTUxM333wz5eXlGGPSec4Oh4NFixYxffp0vvKVrzB37tyjzt/RNfQdtd92222cf/75nHdeMpdp1qxZ7Nq1i6ysLF5++WWuueYaysvLyc3NTe+8NzQ08JOf/IRnn32WL3/5yzQ0NPAv//IvnHPOOR1+HyIiIjL4xMONOL3J3edw42ac3kJcGcVYmyDS9DFOXxGZpRcAkFkyJz0unWM9iALrSuBZm4zgVhpjEkBRqn7EIf3KgANPubVXXwvkGWNcqV3rQ/sfwVr7CPAIwOzZs48ZPXZmZ7kvXX311dxxxx0sWbKEurq6dP29997LvHnzeO6559i5cycXXnhhuq28vJysrKwOHwxcvXo1kydPPmb7xRdf3G7b97//fWpqag7b8c7JyUm/vuqqq7jtttuora2lqKgoXX///ffzne98h8WLF3P66adzww03sGDBAt56661jrlVEREQGn2Dtaipf/ywlc39F9qhPsfvlKymY+g0Kp38LEjF2v3wlhTPuwFd0OgDe/INxjdOTCwzMwLq7x+39iWRuNMaYCYCHZJD8AnCdMcZrjBkDjAdWAu8D41MngHhIPuD4Qiowfwv4XGrem4Hnu/thTiQLFy7kvvvuY9q0aYfVNzU1pR9mXLRo0WH1t99+O0uXLqWuro6nn36a9rz99ts88sgjfPnLXz6izVrLgw8+SFVVFVdcccUR7Y8++iivvfYaixcvxuE4+E+/b9++9C73ypUrSSQSFBYWptvLy8vZu3cvF1xwAYFAAIfDgTGGUGjgHYMjIiIifS+wdwlgCex7F4CScx8ia1TqhDSHK1kuu4JIY/IwBm/epPRY4/TgcGWRiAy8S2I6c9zeYmAZMNEYU2mMuQV4DBibOoLvCeBmm7QBeArYCLwKfM1aG0/tRv8T8BqwCXgq1RfgX4F/NsZsJZlz/bve/Yj9o6ysjNtvv/2I+jvvvJO7776buXPnEo8fzAH/1re+xW233caECRP43e9+x1133UV1dfKZ0CeffJLTTjuNCRMm8OMf/5hnnnnmsB3rb3/72+nj9t5//33eeustPJ4jTy386le/yv79+znnnHMOO1bv6aefZurUqcyYMYNvfOMbPPHEEySfK036zne+ww9/+EMArr/+ehYtWsTZZ5/NHXfc0TtfloiIiJxUnL7kb70T0RYAskdeiTd3PADGOMgeeSWe3HGEG7fg8Obj9BUfNt7hzSceridU9xGtla8f38X3gOkoH/dENXv2bLtq1arD6jZt2nTMFAnpe/o3EBERkbqP/oP6Db/GkzeZUVe9fNR+Fa/9Hcbpo+ySxYfV7351AU5vPolIE7FgNWOuebevl3xUxpgPrLWzO9NXNy+KiIiISK8K1H4AQLR5GzbR/ilt1iYIN318WBrIAU5vHpGmjwnVrSERae7TtfYmBdYiIiIi0qsiDcncaZuIEG3d3W6faGsFNhbAkzfxiDanN59YoAqARKwVm4gd0edEpMBaRERERHqVw1uAM6MEgEhTebt9wvXrAPC2F1h78g8rH8jVPtGddIH1QM0ZPxnouxcRERFrLfHgPvylyUtfIk0fH9EnWPMB1Su/gyuzFE/ekc9mOVJnWbsySwGID5B0kJMqsPb5fNTV1SnA6wfWWurq6vD5fP29FBEREelHseB+bCyAw52DK7OUSNPWT7RXs+evX8TpLaDs0idxuI6MHVwZyVNFcsZeC0Ai0tT3C+8F3b0g5oRUVlZGZWUlNTU1/b2UQcnn81FWVtbfyxAREZF+FK5PnqhsEzE8uRMIf2LHOrDvPWw8SMm5D+L2tx83ZI9agCtzOA6Xj/r1vyQRHRg71idVYO12uxkzZkx/L0NERERk0DKOZHiZNeIy2va+RXD/e9hELF0fqv0A4/LjbScF5ACH24+/9ALCjZsBpYKIiIiIyCAUC+4DwJ01Am/+qdhEhHDDxnR7qPZDfIWnpQPtY3G4c4CBkwqiwFpEREREes2Ba8yd3mIyS+am6t4BIBFtI9y4mYziWZ2ay+k5EFhrx1pEREREBplI48eAA4fLi8tXhDf/VAJVSwEI1X0ENoGv6PROzWVcfjBOpYKIiIiIyODjyizBk39qupw57HyCNR+SiLYSSt3I6Cua2am5jDE4PDkD5uFFBdYiIiIi0mtigX24/cPS5cxh54GNEdi/nGDNh3hyJ6RTPDrD6c7VjrWIiIiIDC6Rll1EmreCTaTrfEWzMM4Maj74PoGqt8kYclaX5nR4cvTwooiIiIgMLnVr/wNsnOwxn0nXOZxeMksvIBbcT97EhRSe9u0uzen05AyYhxdPqnOsRURERKR/RFt301rxKtljP0f2yCsPaxt69r9jYyFcGcVdntfhySEa2Ntby+xTCqxFREREpMdq1zwAOCmafscRbU53NrizuzWvwz1wdqyVCiIiIiIiPdZa8Soubx6uzKG9Oq/Tk6vAWkREREQGh1ioAWyMjNILen1uhycHm4iQiIV6fe7epsBaRERERHok3LAOgJxRn+71uR2eXIABcZa1AmsRERER6ZHA3rcB8BZM6/W5ne6Bc625AmsRERER6ZGWXX8G4+rSxS+d5UjNGR8AZ1krsBYRERGRHkqQUXxGn8x8IFjXjrWIiIiInNRiwRrioVr8ZRf3yfzasRYRERGRQaG18g0AvHlT+mR+PbwoIiIiIoNCy/anAfDkntIn8+vhRREREREZFOKxAJ68Kd26rrwzjNODcWYoFURERERETl6xwH6iTVvIHt3z86vjCcuWPVF+/XILf3yvLV2/4uMw74W/MiBSQVz9vQARERERGZgaNj8KQObQuT2e6+cvtrBlTwyAnAzDtXP8AGytirHN8TnyJpwEO9bGmMeMMdXGmPXttN1hjLHGmKJU2RhjHjTGbDXGrDXGzDqk783GmPLUn5sPqT/dGLMuNeZBY4zprQ8nIiIiIn2nteJ1wIEn/9QezVPXEmfLnhinj/MAcMkMX7rtxgv8fP8Lw/Hm983Dkb2pM6kgi4ArPllpjBkBXArsPqT6SmB86s+twG9SfQuA7wJnAWcC3zXG5KfG/CbV98C4I95LRERERE4sNhEjHq4na/R8HI6eZRev3RUFYHiBA68bmgOJ3ljicdfht2CtXQrUt9P0c+BOwB5StwB43CYtB/KMMcOAy4E3rLX11toG4A3gilRbjrV2mbXWAo8D1/TsI4mIiIhIXwvVrsbGWskq6/meaCIVR5890UtOhoPmoD32gBNUt/57YYy5Gthjrf3oE03DgYpDypWpumPVV7ZTLyIiIiInsLr1DwKGjKFzejxXRW2M7AxDUbaDnAwHLcGBuWPd5YcXjTGZwHeAy9prbqfOdqP+aO99K8m0EUaOHNnhWkVERESkb0QaNuJwZ+Py5vZ4rvW7o+RmGowxZGcaapoGZmDdnR3rccAY4CNjzE6gDPjQGFNCcsd5xCF9y4C9HdSXtVPfLmvtI9ba2dba2cXFfXNWooiIiIgcWyxYQzxcT97kW3s8VzSeoClgcTqS+63JVJBBElhba9dZa4dYa0dba0eTDI5nWWv3AS8AN6VOBzkbaLLWVgGvAZcZY/JTDy1eBryWamsxxpydOg3kJuD5XvpsIiIiItIHAlVLAcgaPq/Hc1WndqfnTfUCkJNpaA1ZEomBl2fdmeP2FgPLgInGmEpjzC3H6P4ysB3YCvwWuA3AWlsP/AB4P/Xn/lQdwD8Cj6bGbANe6d5HEREREZHjoW7dLzAOL568yT2eq7I2DsCoIckM5ZwMB9ZCa2jgBdYd5lhba6/voH30Ia8t8LWj9HsMeKyd+lXA1I7WISIiIiL9K9ywkfr1vyLWtgdP3iR64/qR9zaHMUBJnhOAnMzkvm9zMJF+PVDo5kURERER6VAikWDv0q8QjzSTN+Fm8qf+U6/Mu78pjscNLmcySM/OSP7dHLBQ2CtvcdwosBYRERGRDrVVvEysrZKs0Qsonv3dXpkzYS2BMMxO3bgIyVQQYEA+wDiw9tdFREREpF+EatcADgpP/UaHfQPhBN97solXPgym636/pI23N4TS5cfebGXdrijBiGVciTtdn5OZ3LFuGYCXxCiwFhEREZFjsjZBa8UrZJZeiCd3bIf9N1dG2VMX56OdkXTdvsY4jW0Hd6GrGxO8+H4y8B4zxJmuz/AYXI6Bea25AmsREREROaamrU8QC+wla0Tnri8PRpN/l+YfzDr+9jU5LDgzM12+67M5nDLMhccFwwoOBtbGGLJTZ1mHo3ZA3cKowFpEREREjioRC1K39j8Ag7+T51bvb4gBsKs2dsx+O6vjjCxypS+HOSAn09ASsDz2Ziu/eLGlW+vuD3p4UURERETaZa2leuXdJML1DDnrAVy+ok6NW7UtuWW9py5OLG7TJ34cKp6wVNTGOH+K94i27AwHe+qTqSM+T8+P9DtetGMtIiIiIu2qW/tzWnY+T8G0b5E77nOdHudKZXbEE7C3Pt5un731cSIxGD3kyH3enExDfWuChIVA2BIfILcwKrAWERERkSPEgjU0bPhPHO5sCk5t9/6/owpFYNzQZMC8u/bIwDoas7y6OnlCyJih7QTWGYeHqIGwAmsRERERGaDqPvopAEPPfgDjcHbQ+6BwNEFDW4JJZU58bthdc3iedSRmeeD5ZlaWR5g/28eQ3CPnPnBJzLRRyWP4WgfI0XvKsRYRERGRw7TtXUrz9qfIn/wVskZc3qWxW6uSgXRTwDKy2MXumsN3rDdWRNmxP87N8/ycO/nI/GqAaaM87K2PM3Osh3W7orSGE0Dng/v+oh1rEREREUmLR1rYu/QfcLhzKZh2e5fHByPJ3eVJZW5GFjmpqIsdliO9qTKKxwVnTfAcbQqG5Tv50kVZ5PmToWpbaGDsWCuwFhERERFioVqati5m33vfhESUvEm34HBldHmetlQ+9PgSF+NK3ERisG3fwXSQTZVRxg9z427npJBPyvIl+7QOkMBaqSAiIiIiwr6/fYNg9TJwZpA/+VYKp329W/NU1MZxGMjzO5g60oHLCR9ujzCh1E1Da4KqhgRzJ7WfAvJJfl9yD7g1NDAuiVFgLSIiIiJEW3djnF7GXbuuSw8rftK6XVGMAYfD4PPAqSPcrN4e5fNzLZsqk+dbTx7h7tRcXhe4HANnx1qpICIiIiKDnLUWmwjhHzm/R0E1gNcNpfkHQ8xZYz3UtybYWR1n854oWT5DWWHn3sMYQ1aGUY61iIiIiAwMseA+4qE6Mgqm9WieUNTS2GYZM/TgjvSM0W6cDvjfd9r4YFuEyWVuHKbztyn6vY4BkwqiwFpERERkkGve9hQALn9Zj+Z58M/NBCOWcyYePPHD73MwpczNzuo4U0e6+ew5XXsgMstnBkwqiHKsRURERAa5cMMmAHxFM7s9x8aKCOVVcYYXOjhl2OE51Ldc4icQsRTndD3NxO8zVDW0fy36iUaBtYiIiMggZ+NhPHkTcfkKuj3H62vC5GbCt+bnHNHm9znw+7o3b5bPQWso1nHHE4BSQUREREQGMWst4YZ1eHuQXx1PWLZWRZk51kuuv3fDyyxf8uFFa0/8dBAF1iIiIiKDWKh+LfFQHQ5nZrfnWPFxhHAMCvydfyixs/w+Q8IevNHxRKbAWkRERGQQC+xdCoCv+PRuz7GrJpmqMWXk0a8p766s9CUxCqxFRERE5AQWqHobT+4Eskd9uttz1LcmKM5xMKq49x/f86euNR8IZ1krsBYREREZpIK1HxGq/YCcsZ/FdOFs6UPFEwnK90YZX9o3Z2JkDaBrzRVYi4iIiAxStR/eD4C/7PJuz7FuV4y2MGR6ej+/GpIPL4JSQURERETkBGUTMaItu3DnjMeTParb8+yuTeZXzxjd+/nVcDCwViqIiIiIiJyQ2va8STxcR9GMf+nRPFurYgzJdTBxeN+kgmR4DcYoFURERERETlC1ax7A6RuKf/jF3Z6juinO5soYp4/zdDtHuyMOY/B7zcmxY22MecwYU22MWX9I3QPGmM3GmLXGmOeMMXmHtN1tjNlqjNlijLn8kPorUnVbjTF3HVI/xhizwhhTbox50hjTN79HEBEREREA2va9S7RlG968iRhH93eaX1gZxAKjhnT9qvKuOHuih1FDTvwLwzuzY70IuOITdW8AU62104GPgbsBjDFTgOuAU1NjHjLGOI0xTuA/gSuBKcD1qb4APwF+bq0dDzQAt/ToE4mIiIjIMbVVvAbGTfHs7/donrrWONk+w8zR7l5aWfs+P9fPuZO9ffoevaHDwNpauxSo/0Td69baA5e2LwfKUq8XAE9Ya8PW2h3AVuDM1J+t1trt1toI8ASwwCR/Z3AR8HRq/H8D1/TwM4mIiIjIMQT3L8Nfej6enNHdnqMlmGD7vjjnTvHicCi7GHonx3oh8Erq9XCg4pC2ylTd0eoLgcZDgvQD9e0yxtxqjFlljFlVU1PTC0sXERERGVyCNR8Sad6Gy1/WcedjeHV1kISF08f17W71QNKjwNoY8x0gBvzhQFU73Ww36ttlrX3EWjvbWju7uLi4q8sVERERGfSCNe8DFm/e5B7N897mCE4HjCjs2/zqgaTbWeDGmJuB+cDF1toDwXAlMOKQbmXA3tTr9uprgTxjjCu1a31ofxERERHpZa7MEgB8RTO7PUdLMEFbyHLuFI/SQA7RrW/CGHMF8K/A1dbawCFNLwDXGWO8xpgxwHhgJfA+MD51AoiH5AOOL6QC8reAz6XG3ww8372PIiIiIiIdiTR+DA43nuzR3Z5j9Y4IFrhwqq/X1nUy6HDH2hizGLgQKDLGVALfJXkKiBd4I3Vm4XJr7VettRuMMU8BG0mmiHzNWhtPzfNPwGuAE3jMWrsh9Rb/CjxhjPkhsBr4XS9+PhEREZFBK5FI0LDxP4kF9hFt3oors5S2PW/izhqFcXbvhOPmQII/LQ+Sk2GUBvIJHQbW1trr26k+avBrrf0R8KN26l8GXm6nfjvJU0NEREREpJfEgjXs+esXiTRtwbj82HiIzGF+LODJm9StOZ9bEeCVD0JYYNooV59dCjNQnfgnbYuIiIhIl+1f9s9EWnbgH3EFJef8nP3LvkVg/zJstAVf3sQuz1fTFOe11SGmjXJz+Wk+Thmm3epPUra5iIiIyEkmEQsRqH6fvPFfoPS83+Bw+cgdfyOJSBMAnrwJXZ5z8TttxBNwyWleJgx366HFdugbERERETnJtOx4FhJhHJ7cdF3G0Dm4s0YD4Mnt2o51wloq6uIU5ziYPLx7udmDgQJrERERkZNMLFQNgH/4Jek6Yxzkn3ob3vwpuLt4OcxHO6I0tln+7qyMXl3nyUY51iIiIiInmVhgHw5PHt78wy+ByR13Lbnjru3SXB9sDfPIG20MyTHMHKvd6mPRjrWIiIjIScTGIwSr38dbML3Hp3bUtyZ4fEkbAAsvycLl1Ckgx6LAWkRERKQfJOIRrE0kXyfiJOLhdNl2uRxLlS2B6uVEW7bj9Oa2866dF09YHn2jlXgC7vlcNuNK3D2abzBQYC0iIiJynNWt/TnbnpxI847nsNZS8eqn2fbkJEK1awBo2/sW256cRLgheZ9ea+VrbHtyEpGmcgBadv+ZbU9OItqyE4DmHc8ly60V2FgIAH/ZpT1a4y//3EJ5VYwvXOBnVLGC6s5QjrWIiIhIH4oFa4i17cHaBNHW3WSNuJym7U8D0LLzBZxuP5HGTTh9Q3D7SwHw5IyjcMaduDJKAPDmTqRwxp04fUXJct7kZNlbAICvYCo5p1zPrhcvwjiS50tnDjm722veUBFhU2WM4lwHZ0/0dnuewUaBtYjT28J5AAAgAElEQVSIiEgfqlv3c5q3/ZGsEZcR2L+MaPM24oG9+IdfQtuevxBp2gKAjQdxZgwFwJMzhoJT/xGARDyMK6ssXQbw5k3Ae8hZ1J685G62M6OQrLLLcfoKcWUUd2u9LcEE//VmG0NzDXd+Jqe7H3tQUmAtIiIi0kcS8TBte/4KNkaoYQM5466jftPDZI++hiFn/ICdL1xAPLgfX/FsQjWrSIQbcPoK0uNbK16jeuV38BXPovT8R476PoGqpYRqVlF8xg/IG/+Fbq11V02M377RSnVTAoeB2+fnkJOhrOGu0LclIiIi0kcijVuIB/fjyhxOrGUXjRt/g790HsWzv4fDnUXRrHvJHn0N+ZO/nOzfuis9tmnbU1S981VsPExb5V+ItlW2+x6JeJi6tT/DlVlK7ti/7/Za394Qpq45QXGOg9uuyGJEkfZfu0rfmIiIiEgf8eSMBSDnlM/jziwFh4vsUVenj8HLGXMNOWOuIZx6KDHasouMopkABPcvw5VRwvCL/5ddf76Y5u3PUDjt9sPmj0dbqFr6VcL1aymZ80uMs/vnTG+tijJ5hJtvfCq723MMdtqxFhEREekjkZbkDrQnZxw5Yz9LzugF7Z4t7faPACDaujtdF23bgzt7JJ6cMWSWzKV521PYRPywcdXL7yRYvZKh5/wH2aOv7vY6qxpiVDUkyMnQOdU9oR1rERERkV6y+7XPYBxO3P4yXFkjad31AgCe7NHHHOdw+XBllBA9JBUkFthLRvEZAOSM+zz73v06gf3v4h92frpPqHYN2aOvJmfMZ3q07s2VMQDGDFVo2BPasRYRERHpBeGmrYTrVhNp3k7LrheJNG7GOH0AuDsIrJN9RhFN7XDbRJxYYB+u1PF7/rJLwbgI7l+e7p+IhYgF9+HOGtXjtde2JHA5YI6O1usRBdYiIiIivSC4fwUAJXN+QcaQM4m27sabPwVnxlAcrswOx7uzRqV3rGOharBx3P7hADicXtzZI4m27Ej3j6UeZnRnjezx2sv3Rhg9xIXbpVSQnlBgLSIiItILWitexp0zjsySc8kcdj6Rxs2EalbhyR7TqfHu7JHEQ7Ukom3E2vYA4Mocnm73ZI8hckhgfeAEEXd2z3asW4IJdlQn8OpyxR5TYC0iIiLSQ+GGzQT3v0dmyfkYY9J50NHW3Z1KAwHSKR3R1t3E2vYCpFNBANzZY4i27MTaBACx1IOO7qwRPVr7lsooAKeUKL+6pxRYi4iIiPRQY/nvAcgYmrxG3JM3CaevMPm6s4F19sHAOhpIBtbuzIOBtSdnDDYeJhaoSvZr2Y1x+XF6C3u09nc2h8nNNFwxK6NH84gCaxEREZEuszZB9fv3UvXu7cSC1UQat+DOGUtW2aUAGOMgs+Q8ILnT3BnJHWtDuHELsbY9ODx5ONz+g+3ZyTOxI83bgdRueNaIdo/v66wNFRE2VsSYN82Hy6n86p5SYC0iIiLSReH69TSV/w9tla8TbthCqPYDcsZee1iQmzzJw4E3f1Kn5nR6cvAWTCNQtZRo217ch6SBAOlc7QMPMCYD657lVz/xtwAAZ47v/sUycpACaxEREZEuCtWtAcAmYrTseh6Mg5zR1xzWJ2vElYy+emmXTu3wDzufUN1qIo2bcWUeHlg7M4ZgXH6izTuwNkG0raJH+dVNgQS1TQmmjHBRnOPs9jxykAJrERERkS6INO+gYePDGFcyTaNlxzNkDp2LK7PksH7GmPRxeZ2VWXoh2ASxwF5cnxhrjEmfDBIPVmPj4R6dCPLa6hAJCzee7++4s3SKAmsRERGRToiF6og0byPSvI1YcD++olnpa8Szx362V97DV3gaDk8uwBGpIADunDFEW3akrz4/cBV6V+2pi/GXtSGmjXIzJFe71b1F56qIiIiIdELl658lFtzPqPl/ARsnc+hZZI++Bqcnn6wRV/TKexiHk8yS82jd/ecjUkEgmWfduvslIs1bge6fYf3nD4JYCxdO1U2LvUk71iIiIiIdiLZUEG3dhY2HqF75b0Byd9ntH07x6f+Gw9l7Aaq/9EKg/aDZnT0GbIKaVd8H4zzsOL6uqKyNM3WEi6kj9dBib9KOtYiIiEgHWipeAsCVPZpA1RLA4C2c3ifvlT36GpwZQ/DmTz2izV96Ibmn3IhxevAWzsA4ux4YNwcS7G9McNYE7Vb3tg53rI0xjxljqo0x6w+pKzDGvGGMKU/9nZ+qN8aYB40xW40xa40xsw4Zc3Oqf7kx5uZD6k83xqxLjXnQ9OQwRhEREZFelkgkaNr6JL7i2RTPvBsAT+4pON3ZffJ+xuHEP+y8ds+ndnrzGHLmDyk+/T5yRi/o1vy/e7MVC4wsUuJCb+vMN7oI+GTi0F3Am9ba8cCbqTLAlcD41J9bgd9AMhAHvgucBZwJfPdAMJ7qc+sh43onSUlERESkFzRv/QOx1p1kDD0Xf+nFePOnkDnsgv5eVrdlepIB++gh7n5eycmnw1QQa+1SY8zoT1QvAC5Mvf5vYAnwr6n6x621FlhujMkzxgxL9X3DWlsPYIx5A7jCGLMEyLHWLkvVPw5cA7zSkw8lIiIi0ltaKl4B4yJv/A0Yh5MRl78AZuDs9lbWxfhoR5QV5WE+PTsDh8NQkOUgJ3PgfIaBors51kOttVUA1toqY8yQVP1woOKQfpWpumPVV7ZTLyIiItLvIs3bCO1fTv6pt+HKKAaSqRoDwc7qGM8uD7CpMpauW7YlzP6mBKOKB8ZnGGh6++HF9vKjbTfq25/cmFtJpo0wcmTnbzESERER6Y6aD+4Hh5u8iV/q76V0ibWWnz7fTDgKnzrdywWnZvDE39rYVBkjGLHMmagHF/tCd38HsD+V4kHq7+pUfSVw6EnlZcDeDurL2qlvl7X2EWvtbGvt7OLi4m4uXUREROToWiteY9dLl1O+eAKBqqV4csbi8hX197K6JByDSBTmTvJwzVl+8rMcXDkrg2AkuX85aoh2rPtCdwPrF4ADJ3vcDDx/SP1NqdNBzgaaUikjrwGXGWPyUw8tXga8lmprMcacnToN5KZD5hIRERE5rir/ehNV73yVRCxI/qSFZA67gJI5v+z190lYy566ZIrG+t0R1u6M0BRIALB2Z4TK2oPpGx/tjFBZd7C8ZkeEvfXxdHn19ghVDfH0vKu3RyjfE8UCZ5xycGd69BAXU0YkkxVGFevE5b7Q4bdqjFlM8uHDImNMJcnTPf4v8JQx5hZgN3BtqvvLwFXAViAA/H8A1tp6Y8wPgPdT/e4/8CAj8I8kTx7JIPnQoh5cFBERkX4RC+zD6RvCiCv/jMuT0yfv0RxI8PslbazZGeXWS/088bcAwYjl1JFuvnZlNo+92caZEzzccF4yTPvtG62cP8XH389Nlv/fa61cdpqPz5ydCcBDr7by6dk+rj4zk0QiWR5e4MAA44YdHup94Xw/H1fFyM7Qg4t9wSQP8Bh4Zs+ebVetWtXfyxAREZEBLB5uYNfLV+H05lN2yZNsf/Z08icupGjmXR0P7qT/erOV97dGuOdzOZQVuvjju228/lEYh4GcTMOoIU4+2hGjKMfB//lCHpV1MTK9DgqyksFvZW0Mv89BfqpcUZsMjPP8yfLu2hi5mQ5yMx0krKWyLs7/LGkDA/d8NrfXPsdgZYz5wFo7uzN99d8VERERGbRaK14jHtyHjbURadwEiSi+otN69T1qWxJE4/DCyiC7qmMsL4+Q5zfcPj+bxjbLRztiZHgMdc0JIjFLWaErHVQDlBW50kE1wIgiVzqoBhhZ5CI3dXSewxiG5jrZXRtnQqnOqT7eFFiLiIjIoNW841kAjDODcMMGALyFM3r1PepbE2R4DKt3RPnh081g4R+vyGbKCDcXT/NSmO3gs+dkYIH9jfEjxlc3xWlsS3T4PtZayquirCyPEE/AxFLlUR9v+sZFRERkUArsX06o5n2cGUOING2hteJVnBlDcGWU9Np7LN8SprY5wdVnZBCIJHBg+NRsH5ne5N7mdef5+dwcy77Uw4f7GuKMKEqGZ8GI5dnlAd7eEGZEoZN/uzan3WvOD3h7Q5g/LA0A4HTAuBKFecebvnEREREZlJq3/RGAohl3sX/5PxOsXom/7LJjBq8dsdYSi1scDoMx8NS7yUB3eIGTWeMy2h3jchqG5DkxkD7dA+DlD4K8vT7M+FIXH++NsXlPjMll7ad3tAQTPLciyIRSFxdP8+H3mXTwLsePvnEREREZdKy1hGpX4Rsyh+wx1+DKLAXA14M0kOSlLC3c9kgj33i0gfK9MT59RjKYHlZw7HOjPS5DUY6DqoaDKR8VtXFGFDv55vxssjMMb6wJHXX8M8sChKOWG8/3M2uch4nDlV/dHxRYi4iIyKATqltDtHU3OWOuxhhDZumFAPgKu//g4u6aOB/vjTG8MHnU3dKNYepbE7gcMCS345CrJN/JvkNyrPc1xinJc+J2GS6a5mPd7uhh51cDRGOWx5e08e7mCBdP91HaQQAvfUuBtYiIiAw6tR/8EAD/sAsByD3lOjJLzsNXNLPbc/55VRCXA+68JoczxntZtyvK7toYQ/OcOB0dp5cMy0sG1omEJRKz1LckGJqXDJQvONWLMbBqa/iwMf/11zbe2Rjmylk+PnN2+6kmcvwosBYREZFBxVpLtK0Cl78MV+ZQAHwF0xh+0eM4XN0LTltDCdbsjJKf5SDT62DmGDfBiGVTRazTu8gl+U5icahrSVDdGMcCw/KSoVp2hoPiHAd7DtmxttayoSLK3EkePnN2ZqeCd+lbCqxFRERkUIk0biYeqqFgyj/22pzrdkYA+NTpPgAml7nxusFCpwPrYfnJsKyqIU5VKiVkaP7BsWWFzsNSQepbEwTCllFDdBbFiUL/EiIiIjKoNJX/ATD4yy7t9hzxhOX5lUFyMgz7mxJU1MYZkutgziQvAG6XYfooD+9vjVCa39nAOtlvV02cAweTDM09OLa0wMnqHVEiMYvHZaisSwbZIwqVV32i0I61iIiIDCrNO57F4c7ClVHc7Tl27I/xyoch3t4QZnNllG37Ysyb6jvsqL6zJ3hwOWDUkM4Fvn6fg3FDXazZEWFfQ5yCLAde98H5hhe4sJb0mdcVtcm/ywq1T3qiUGAtIiIig0Y80oyNh/CXzuv2HAlreXZ5EIB9jQk8LoPXBXMmeQ7rN320h5/fkk9hdud3lGeNc7O7Ns7mPVFK8g8P04anUkoO5FlX1sUoznHg8yi3+kShwFpEREQGjWDN+4Al55Truj3H3ro4W/fFyM005PkNu2vjnDPR2+6FLD5314LeWWOTwXlTwFKSd3hAPiTPgcsBe+oO7liXKQ3khKLAWkRERAaNlh3PgXHhK5rV5bG/eLGZ+59qoiTfidsBM8e4+buzMnE54KJpvl5ZX1GOk1HFyWC55BO52U6HoSTfyZ76OOGopaYpQVmR0kBOJPrXEBERkUGjbc+bOFyZOJzeLo0LhBNsrIhhgeeWB4nEYVKZh9PHeZg11tOr6Rinj/OwqyZ4xI41JNNByqtiVNYlj+PTg4snFgXWIiIiMijEw43YeIjsMZ/r8thlWyJYIMsHr3+UvFp8/LBkGNXbOc7nT/ESidn0/IcaXuhkRXmEdzYm11BWpMD6RKJUEBERERkUAvveBSBn9Ke7NC4eT/CXj4KMK3HxhQuygOSZ0zmZfRNG+X0OFpyZict5ZMA+OnVm9bubIxRmOyjKVih3ItGOtYiIiJy0YoH9ODw5tOx6kdoPfwDOTHyFp3VpjudWhKhtsVx2moeZY91MHeludzf5eJg03MX3rsvB6zLk+R2HHe8n/U+BtYiIiJyUEvEYu179NP5h55E7/iZsIkbm0LkYp6fjwSnxhOX9rWE8Lpg72YPDGG6fn92Hqz42YwzDCxS+naj0+wMRERE5KQWq3iIRqqFl5wvYeAAbD5E14rIuzbFsS4T6VsstF2fhcSlskmPTf3lERETkpBQNVCVf2BjVK+4C6NTFMM2BBK+vCbFlb5S99XFGD3Ewc6y7L5cqJwkF1iIiInJSirftxTg8eHLHE27YgLdgWofXmP/h7Tbe2xwmloAsXzJ/+dLpGcpllk5RYC0iIiInHRuPENi/DHfuRHLH30D1yrs73K2uboqzZEOYnAzDnX+Xw9B2zpEWORYlC4mIiMhJJ1i3hnD9WlzefLJHLyB3wk3tXmO+tz7GbQ/Xs2VPlNxMBw4D50z0KKiWbtGOtYiIiJw0Is07aN7xDP7hlwCQOXweDlcGQ2Z/v93+r60JEY3D2xvCxBOQsDCpTPnU0j0KrEVEROSkUfW324g0bqZtz1sAZA4586h9Y3HLxoooABsrohRlJ3esTylRYC3do1QQEREROSkkYiGiLbsxTh+Rxo3pBxePZsXHYRrbLOdN9tIWtizZEGZksbPXryiXwUM71iIiInJSaK14BRsPMPyi/6Fl90vYWAjjOPru8xN/C+B1wefPzWTl1jDBiGVCqXarpft6tGNtjPmWMWaDMWa9MWaxMcZnjBljjFlhjCk3xjxpjPGk+npT5a2p9tGHzHN3qn6LMebynn0kERERGYzq1/8KV+YIMobOYeiZP6Zkzs+O2ndvfYxQFKaPduN1G6aPSt7GOKFUe47Sfd0OrI0xw4FvALOttVMBJ3Ad8BPg59ba8UADcEtqyC1Ag7X2FODnqX4YY6akxp0KXAE8ZIzRo7giIiLSaa0VbxBt2YEnd2ynzpxeviWCw8Dfz/UDcOFULyOLndqxlh7paY61C8gwxriATKAKuAh4OtX+38A1qdcLUmVS7Reb5E/+AuAJa23YWrsD2Aoc/UkDERERkUPEQrVUr7oXZ0YJQ876Px33jyVYujHElBEu8vzJUGhCqZt7r80lQ/nV0gPdDqyttXuAnwK7SQbUTcAHQKO1NpbqVgkMT70eDlSkxsZS/QsPrW9njIiIiMgx7Xv3myQijQy/8He4M4d12P/VNSHawlBaoLQP6V09SQXJJ7nbPAYoBfzAle10tQeGHKXtaPXtveetxphVxphVNTU1XV+0iIiInFQC1e8T3P8u/tKL8OZP6dSYPfVxvC741GxfH69OBpuepIJcAuyw1tZYa6PAs8AcIC+VGgJQBuxNva4ERgCk2nOB+kPr2xlzGGvtI9ba2dba2cXFxT1YuoiIiJwMQtUrAMg55cZO9Y8nLBsrYswa5yHTo1OHpXf15CdqN3C2MSYzlSt9MbAReAv4XKrPzcDzqdcvpMqk2v9qrbWp+utSp4aMAcYDK3uwLhERERkkAtXL8eScgn/Y3E71X7YlTCBsmaiHFKUPdDu5yFq7whjzNPAhEANWA48ALwFPGGN+mKr7XWrI74DfG2O2ktypvi41zwZjzFMkg/IY8DVrbby76xIREZHBIdpWRXDfcvIm/0OnxyzfEgFgUpnyq6X39einylr7XeC7n6jeTjunelhrQ8C1R5nnR8CPerIWERERGVwaNj0MxHFnjeiw7wGtIcu4oU4Ks3Wyr/Q+JReJiIjIgGPjEUJ1azHuLHLGtLtvd4S6ljh76uPMHOvp49XJYKXfg4iIiMiAkkjEqHr364TrVjP07AdwuDoOlOMJy29ebQVgcpnyq6VvaMdaREREBpTqFXcTqHyd/FP/iZyxnztm3+890ci7m0I4HYbmQILsDMOIIqWBSN9QYC0iIiIDSiywB+PMpGDat47Zr7I2xp76BH98L0BdS5zGNsuFp3o7deW5SHcosBYREZEBJdqyC//weTgcxw5jaluSh4y1heG3b7RhgTNO8R6HFcpgpcBaREREBoxw01Zigb1kFJ/eYd9t++I4HVCS52DbvhjDC5wMK1AaiPQdBdYiIiIyYDR9/D8AOHyFx+wXjlqWfxymNN/BlbMyAJh9ik4Dkb6lU0FERERkwIhHm8HhJmv4Zcfst6M6RmObZdxQF2eO9xAIW86ZqMBa+pYCaxERERkwok0fk1F8Bg6Xr932F98P8s6mEPNPP7hL7XIaLpnRfn+R3qRUEBERETkhxSNNxAL7sIkYAG373yPcsBFf4Yx2+1treX1NkIZWy+/fDgAwoVRnVsvxox1rEREROeE0bllE7Zp/x8aDjF7wNxzODKqX3wVYXP7h7Y7ZvCdGKArnT/GwoSJGhseQk6k9RDl+FFiLiIjICSURC1K//tfYeBBnxhDCDZup/fB+YoF9DDnrJ+SO+/t2x722OkhOhuG6c/0kLETj9jivXAY7/TdORERETij7lt1BPFxHwdTbiQerqVr6D1iboOySJ44aVL/4foANFTFmjfPgdhm8bkOWT2GOHF/asRYREZHjwlpL/bpfYFwZhGpXUzD16/gKphJu/Ji6tf9B4bRv4soeQ9ueN3B48ymc/k2c3nyirRUUTv8mDndWu/PuqonxyochfG6YPzvjOH8qkYMUWIuIiMhxEaxeQf36BwEwzgxyT7kBAJsIE23djY2Had76v5CIMuSMHwOQN/HmY86ZSFh+82or2RkO7v5sDrnKqZZ+pJ8+EREROS72L78D48qkaNa92HiQeKgWAF/BNEZd9Qru7NHUr3+QzJJzyRpxeafm/Ou6MHUtCa45K4M8v8Ia6V/6CRQREZE+F27cTKxtD978qeRN/BIOdzbB2g8P61O//kESkWaKZt6DMaZT8y77OAzA9FE6Vk/6n1JBREREpM81lf8B4/BQMveXGOPAV3gaoVRgHW4qp2bV9wnuf5eccdfhzZ/cqTkjMUt1Y5wzx7vx60FFOQHop1BERAat1so3iLZV0lr5Ok3l/3uwvuJVmrY+kS637H6Jpm1/PFje+SLN259Jl5t3/InmHX86WN7+DC07X0yXm7b9kZbdLx0sb32C1opX0+XG8j/QWvn6wfLHv6d1z5sHy1v+i7a9S9Llhs2/o61q6cHypt8S2Pduuly/8f8R2L/8YHnDQwSrVwJgE7FkueYDABLxMPUbHiJUuzpZjoWS5bq1yXK0lZoPf0yobj0A8Ugz9RseItywKVkONyTLjR8DEAvVUr/hISJN25LlwH72/PUmmnc+T9aIK3FnlgDgK5pFpOljEtFW9r37dcINGyiadS/Fs79HZ63bFSUUhbmTdKuinBgUWIuIyKBUv/FhqpbeSu2aB2jZ9WcaNj+abmve+TyNWxalyy3bn6Xp48cPtm9/iqatBwPx5m1P0LztYCDeVP4HmrcfDMSbPn6clu3PpsuNWxbRvPP5g+XNj9Ky62Dg3bDpYVp3v3JwrRt+c1jgXb/+17QdEnjXrfslbXvfOlhe+zMCVe8cLH/0AIF97wFgbZy6jx4gWL0i2ZiIJss1q5Lt8SB1Hz2Q3k1u2vEsjZt/S80H38PGIyQizdR99ADhhg0AxMP11H30AJHGzclyqDbZ3nQg0K4mVLcGG20ha9Sn0mvyFc0Em6Cp/A9EGrdQNOPb5E9aiMPppTNqm+M89mYrHhdMGq5fwMuJwVg7MA9Pnz17tl21alV/L0NERE5Qobp1hBs3pc89DjdsJBqoImv4xYTq1lHx2tUAONzZjLlmGcbhxjg9ANhEFKw9ejkeAeha2Rj+f/buO8yq6lzg8G/t09v0PsMwQ+9NOgg2wIJiiTEaS6JejUlu1JhcozGmemOKmphcNUZjiRJrVFRUEEEQpEpnYGCA6Y0pp/e97h97nGECCNLB9T4Pz8x39tr7rH0Yhu+ss9a3hGY5pFhPRhFC+5KxCaGZDxpLKZF67BBiMwhB5TvTSUSakXEfjtwJ5E95GqFpCGFGaCak1JF6/AvjxhV3E6x6n9IrVncmzsmYj52vDUeYnaAnKL18FSZryiH93frDOn9800d9u87Fo+1cPMZ5SOcpyuEQQqyRUo4+lLZqxFpRFEU57UgpqfnomzStuJtIqzGy6t3xEo3LfwxA65bHQLOSMfR29Lif8J7POpNgoFuSvd/YZP3ysWY55Fgz2Q4jNh9SLIQ4xNhEoPoD4v4Kcsf8htzxfyTc+ClNK35svB6aqaO91tl+fzEySbDmQ1yF53YbjTZZU7Cm9EEmQrh6zDjkpBpgwYYIDe06d17sUUm1clJRibWiKIpy2onsWYuM+0GYqVt4PTFvBRmDv0vRuS8RD9YQrJlH+sCbSR/4HYTJQXCvaRaK8cYk0rqJ1o1/wuIpwV18ISm9riBzxN0Eqt6ldeOjh3ytUOOn6LF23MUX7nPMnjUKgJTSKw75esGIzoINEfLTTQwsUpVAlJOLSqwVRVGU00779hcRZhfF57+FlDp71j2I2ZmHLa0f3u3/AiC1zzVoZjvOgqkEaz5ESv0E9/rk0bj8x1S/fzFx/26yRvykc/Q5feCteEoupXXz/xHtmFN9MIHqDxBmJ878KfscS+l9JZ7SK3DmTT7kvtW0JIjEoXee6ZDPUZTjRSXWiqIoymkl5t9FYPe/cWSPwZY+iNS+3yRYu4B4oBo9GcVX8TKuwnOxuAqZty5MjfXrJMINNK5+kA/XNFDVnAAgnpQs3BSheo8RR+NGXNtixJGYEde3JgEIRXUWborQ0GbEwYgRN3mN2B824uaO2Bcy4ha/EbcHjbg1YCT4rQEjbg8acYs/ycJNEXwhI272GrE/bMSN7UYcjBhxQ5sRh6JGXN9qxJGYsbaqtiXBwk0RonEjrt5jxMG2Cvy7XieQ/wMqByzHUTgdgN1NCRZtjpI56mdoVg+fLX6ahRvDna/7jvo4izdHOuPt9XEWbw4TrF2AK38K2xtNLC2Ldh4vq4mztmUoeRP+iNBMbKmOs3xb1/FNVTFWbO+KN1bGWLU9StiYvs7Yvoe2yFFRjieVWCuKoiinlc/L4KX0vhKA1L7fBKHRvv2ftG99mmS0hdS+17F8W4RXl4WZu2sE7h4X0Lr9BV5eYWVTZQCAeEIye3GIbbVdifXsxSG21xtxKKoze3GIHQ1GHIgYx3c1GbE3ZMSVHYl6W9BoX9NiJNJ7/EZc15GYN3mTzF4corHdiBvbjfjzxLyu1Yhb/DTe3rkAACAASURBVEaiXNNixG0diXdVc4LZi0P4QkaivKvJiAMRI97RYMSfJ9rl9Ub8eWK9rdaI92x7CaFZqXNdx0vLJMmOgfxNVXFmLw5hsqaTPfJeypqz+deSUOfrvm5XnJeXdsVrKmK8tixIMtyIq/A8Vu2I8fryruMryqO8uaIrMf90W5Q5q7riT8pivLu6K168JcrczyKU1cSxmqFXnqoEopx8VFUQRVEU5bRS9d7FgMQ1+S3iCcnOxiTO6gdx7XmBpA473T+k58gb+fv8EMGoxG6Bh29MJ1q/kB2LfkTxlEfIKJ6KLiWBsMRmEdgsYt9YlwQiErtVYDULkrokGJE4rALLfuJEUhKKShw2gcV04NhpE5j3E8eTkvAXxQlJOCZx2QUmbd84lpBEYhK3XaBpgmhcEo1L3A6BJow4FPaz571JeHpMI33MQ0TjEo9DIERXe4/D2BGx/I3z0DJG0/es3wEQiUticUmK0xizi8QkjRsfI1b+ML0uX01cpBFPSjwO43g4JknsFYeiOroEt/3AsZTwuzd8ZHpM3D7Tczx/rJSvsC9TFUS93VMURVFOG8G6j4m2bSJz5P386R0/e3w68STMHHItg3gBd9+beGP1VeQFwyR1yTcmO3npkxBba+IMLpyAy+RHb10JxVPRhCDF2bWt9j6x1j02HSQ2m44stpgEli+KzUYCf6DYajbeAHzu8zcIe8fB7bMhGSCt/w37Pb53nJo3nFDDAqSUCCGwW4w/n7NbBTS+gyN7NCZbOibATtdxh1XAXrHT1v1D9EQSttXFGd3bihACp01jR32c+jadyQPVNBDl5KSmgiiKoiinjebV9wOwLnIx9W06Jg0sJuhT0oPeV66nYMzd3D7TQ0O7zoyRDqYOtuGwCtZUxNDMDuyZwwg3rzzg9ePBGqLe7cfrdo6rSOtGWjc8grPgHOyZww/a3pE7nmSkhbivovOxRKSFSOtGEuFmvNtnE2vfiqtw2mH15/lFQZ6cF2TumghJXTJvXZg/vuUn06Mxpo9KrJWT0xEl1kKINCHEa0KIrUKIMiHEBCFEhhBivhBie8fX9I62QgjxqBBihxBigxBi1F7XuaGj/XYhxA1HelOKoijK6U9KScvGR6l6byaNK+9D6gmScT+2jGHMXW9CAD/7egoeh8Y7ayJoZieaEKzdGcNigqmDbZhNguElFtbuipNIShzZY4i0rEdPRPZ5vmS0nZr5V1G/5Lbjf7PHWDLup37J9zDZM8kb/4dux4IRnbdXhTsXUX7OkTMOgFBT19bpDUtvp/r9S9j1xliaVv0Ua9oAPCWzup23sTLWuQD0QLbWxlm/O06mR+PNlWHu/5eXV5eFGdrTws+uTCHdrcYFlZPTkf5k/hl4X0o5ABgOlAE/ARZIKfsCCzpigAuAvh1/bgEeBxBCZAA/B8YBY4Gff56MK4qiKMqBeMufpXXjI0TbNhNt3UDDsjvQo21QeifekGR8fys5qWamDbezoz7BrsYEgYjO8vIo4/vZOuf2ntHbSigqeXiOnwr9PNDjRFrWdXsuKSWNK+4mEaoj7tuJHg+eiFs+ZgJV75MIVpM74SFM9oxux95eFWbOqjC/fsXLttp45+MWdzFmZz7hxq7EOta+FUfeJLJG/pSi816m+IK5mB3ZnccrmxM8+m6AX77s4+kPA8QT+67z0qXk1WUhMtwa9389hQGFZhJJ+M4MN989343LrpJq5eR12D+dQogUYArwNICUMialbAdmAc91NHsOuLTj+1nA89KwHEgTQuQDM4D5UspWKWUbMB84/3D7pSiKopz+mlb/kuY1v8ZVNI3UvtcRbd1IoPp9Mof/D6tbx6IJuHSsA4DJA43pHu+uCfPsR0FiCTh3WNdUgmElFq6c6KAtqPP0il749RzCTd2ng/gr5xCsmddRb1kSbd92PG/3mAs3r0SzpePIGd/t8WZvkkWbowwvseC0CR5528+mqo7t2oXAkTOOcNNypJQkY16S0RZc+VNIH3gzjpyxCCG6Xe/NFWGcNsG5w2wsL4+xakdsn74s3hylqjnJZeMcOG0ad17i4bfXpXJGx1xrRTmZHcnbvl5AM/CMEGKtEOIpIYQLyJVS1gN0fM3paF8IVO91fk3HYwd6XFEURVG6kXqSpjW/wVv+LMLsJHfc78ke/Quyz/g5Paa9irXXrczfEKF3npkMj7GBiN0qOHOQjfW742ysjPONyU4KM/fa7lsIpo9wcNsMNxKos11CqOGTbs/r2/kqFndPcsb+FoBo+5bjds/HQ6RpFY7s0d0S13hS8vryMJqAb05xcc8VKRRkmHj8/QA76o2R673nWcd9uwCweEr3+xzldXE2VcW5YJSdKyc5cdsF2+ri3do0+5K8tizEoCIz4/oZW8JrwqhaoiingiNJrM3AKOBxKeVIIEjXtI/92d+/CvkFj+97ASFuEUKsFkKsbm5u/rL9VRRFUU5xLRv/hHfb06T0vorSSz/FZEtDCI20/t/CnjWSpVujJJIworT7VtfThtsZUWrhjos9nDvMvt9rF2WZcNoEtaYZRJpXEW5eA0Ai3Ey48VPcPWdidhWiWVKItpUd83s9XhKhRuKBShzZYzsf+2BtmLueaWdNRYxpI+ykuzWcNo07ZnpId2s8/n4Af1jHkWVUIAvvWUvMbyTWVk+v/T7PnFVhUp2Cs4fY0YSgX4G5s0Y4GBvQ/H1+ACHg+rNdanRaOSUdSWJdA9RIKVd0xK9hJNqNHVM86PjatFf7HnudXwTUfcHj+5BSPimlHC2lHJ2dnb2/JoqiKMppqq3s77Rt/iuu4ovIHfcgJquHYEQnGNFpaE9S0ZBge32CFAf7JM9pLo3vXeBhYJHlAFenM9nbHeyNyZ5Fy/o/IKUkUP0eSB1Pz4sRQmBLH0jsNEqsw82rAHDkjAGMHRlfXx6mNMfEf1/oZlbHlBqAFKfGrdPdBKOSFxcHMXtK0Cweoq0biPt3gdCwuHvs8xyVTQm21SaYPsLeWbKvf6GFFr/OHl+S2UuCPPCaj7rWJNef5SLTo7YrV05Nh13HWkrZIISoFkL0l1JuA84FtnT8uQF4sOPrWx2nzAG+L4R4CWOholdKWS+E+AD4370WLE4H7jncfimKoiinHz0RoWXT/4FmJeeMnwPQ6E3y0Jt+dCnpk2+mvDZBMCqZMcKOSTu80c4BhRbW7YrD0B8T3nI3vh3/wr/7Layp/bCk9OOZjwKEWn7ADG5G6kmEduongOGmlQizE1v6YABeXx7GYRXcMn3/CwV7ZJmZNdbBv5eHWdsnSW7GUCIt67G4i7G4eiBM1n3Ombc+gt1Ct/rT/QuMFOTDDREWbowyaYCVr09y7lPPWlFOJUf60/vfwItCiA3ACOB/MRLqaUKI7cC0jhhgLrAT2AH8HfgugJSyFfg1sKrjz686HlMURVEUAHy7XkPGvRSc9QxmRzat/iS/eMmLP2zszldWHScYNXYFnDrk8Gsc9y80kr1ay4VY0wbQtOqnRPZ8hrt4Ji8sDrFsa4xNbX2JJxLEA5VH6/ZOqHDzShxZoxCambIaYx76haPsX1h9Y8YIO5kejaVbo9gzhxNtKyPavnW/86tb/ElW74gxZZC9W9JckGHC4xAs2BDFaRNcOVEl1cqp74h2XpRSrgP2t8XjuftpK4HvHeA6/wD+cSR9URRFUU5PeiJG68a/YMsYgTN3AlV7Ejz5gZ9kEi4b72BYiYVH3wkwsIeZa6c6O7fAPhwFGSbcdkF5PUw+/21CDUsJNy5jXeKbLNkSpU+emR0N0JTsT1F7GdaUXoSbVuDb9SY5Y36N0E6dDY2DdR/TuvHPxNq34Rk+i52NCR5/P0B2isY5Q/c/D/1zmiYYUWLh4y1RxKCRIBPEfRW48qfs0/bD9UZN8HOGdX/DI4SgX4GFNRUxzh/5xYm8opwq1E+xoiiKclJr2fB7kpEmXAVnsmRLlP99zUc0AXfN8nDBKAeFGWYevC6V78xwH1FSDcY866E9jWSvrh1cBVPxDPkJc9cZ869vme4GoC45DO/22XgrXqV24Q34Kl4idhLsyJiM+/HtfgtjLOvA9HiQhqX/TTLaQtbIe4nmfZtH5vhw2wV3zfJ02wr9QIaXWkkkoSIyrPOx/xyx9oZ0Pt4cZXx/637nTU/sb6VfgfmgibyinCpUYq0oiqKctPREmEDtQkz2LBJFt/HC4hBmDe7/eir9C7sWIh7NChJXTHBitwqemh8knpQs2hTBF5ZcOs5Bulsjw62xx30lkT2f0bTifzDZMgFOeG1rqcdpWPJdGpfdQWTPmi9s69v9JnrcT+6Eh0kf+F98uDFJUocfzfIc8sLBvvlmnDbBploXJodRWdea0r0iyLx1ERI6XDjKsb9LMKzEyo8vTelc0KgopzqVWCuKctJrL38ef9VcgrULqV10I8mYF4BAzXxqF92IHg8A4K96z4iTUSOufIfaRTcidaOkl2/XG9Quuqnzut6KV6lbfEtXvONf3barbi//J/VLf9AVb3uGhmU/7Izbyv5O4/K7O+PWLU/QuPLernjTX2ha9bPOuGXDn2he86vOeM/6P9D82QNd8drfsmfd7zvj5jW/oWX9Q51x0+pf0LLx0a545X20bn6sM25c8RPatvytM2749Ee0be2aZdew9A7atz3XGdd/8n3at7/YGdct/g7eipe74o9vxrfzdQCk1KlddCO+3cZ6dJmMUbvoRvxV7wJGAly76EYC1R8AkIz5jLh2gRFHWqlddCPBuo8BSISbqPnwamoX3UjNgmuItG2h4rWRBGrmAxBt28LO10fT8OldJPy7yJnwCM9+HMeswc3T3J27Jh4LqU6NG852UdOS5L4XvbyzOszgHhb65huJfGmumdpICSWzPiFn7AP0OH8OaBZi7VuPWZ8ORfOaX3XW3460rD9gOykl3vLnsaUPwZ41ilDU2I1ybF9rZ+3vQ2E2CYb1tLChMo4lfQQACVspNS0J6luTfFIWZdGmCGP7WMlNO/UXeSrKoTh1JoMpinJaklKix32YrKkA6PEAUuqYrClIPU7j8rsJVL2HyZ5B1qifkoy0gJ40zk1ESEZakFI34mTYON7xMbieCBlxByPe0/XciRDJSGv349G2veIgyehex+PB7sfjge7HY35jS+29j3e8CTBiX/c45kMmu3aeS8Z8CNGVgCTjXqRM7NW+HSHMe7VvR7N6uuJoO7o9sFfc1vmmw2jfhp4Idjsuu8Ut6PFQVxxpQU90j2UiDIBEdouRekf7jvjz48lIR6R3i6PtW4060dLYICRQ/T6ekkswOwsA0Kxp2DIGE6x+j/RB36U8NIYd9UGuP8vFiNJ9q04cbcNLrNx0not1u+I0+5JcMaFrxLV3npk1FTECyXTS+lwDgDWl9wkdsY55K/BufwF/4T2s3m1hRtNG0gfsv2248VNi3nJyx/8BIQSfbosSS8DZQ778dIwRpVaWl8docn6NrNRKnljkYnu9r/N4VorGJWP3P1qtKKcjcbB5WCer0aNHy9WrV5/obiiKcoSq511BtHUTva8qQwiN2oXfJhltpfj8t0jGfFR/cKlRHxcomvYqjuz9rZdWTiUx305q5n8dYbKRf+ZjtGz4E5E9n1FyySJMNqPyajxQRdV7M7Gm9qXgnNnc/o8gZpPgoW+nHXYpvaOloiHOg//2c9v5bkaWWthYGWfjmrmM1/5I78s+OfgFjoG2sqeY+2kli6N3oEvBxel/4pKrf7Xfto0r7yVQ+Q4FF69kW73GK0tDuO2Ce7+W+qWfNxqX3PVMG2P72bhglJ17X/AyeaCN/gVmCjNNFGWa1EYvyilPCLFGSnlI//moEWtFUU6oRKgRqccINy7DmTeZ1L5Xd47imqwppPS+ipZ1DyI0K/7dc1RifQpr/uwBAlVzjZF2k4PCc/6JNaUXWSPvoeq9C6h6bybCZMWa2p94oAoQ5E38MxuqIZqA0X0sJzypBijOMmPW4MWPg8xdo1HZnASmkOd6gZKYt/PTl+Pps/I9LIrcychSC7vq2tnsH82FkRbM9sx92kZbN5NMmcBvXo/Q5NWxmuHqM92H9bw2i2BEqZU1FTHSXMb0nJmj7WqDF+UrS82xVhTlhElGWkmEagFjvjOAu2g6np4zO9tE9nyGxd0TV9F5BKrmds6XVk4t4aaVtG99CounlJSSyyg898XOhW62tH5kjbwXa9oAbGkDibZuJNa+lZxxDxIS+by9KkK6S+Paqa4TfBcGi1nwrXNd9CuwIIErJjiwaDrl8XOInYDpIJFwgPfqLyLb0cot092MLomyOzGelrpN+7SVepxQ205eafoBrQGd285386eb0hna8/Cn14zrZyUUlbz/WZjeeWaVVCtfaWrEWlGUE6Z9+z8BsGUMJVjzAcmYz5hbLSWJYDVmVxHh5lW4C8/DVXgugaq5BGs/wt1j+gnuufJlSCnZs/ZBzI48CqY+hWY25vI2exM88UEQhw1un3kjm+W1vLE8xC++kYLTFGBxuY1X3/MST8L3LnBjNp340erPjetrY1zfrrrM22sCbK85i0jbGhw5Y4/pc9e3Jlm5I8q04caGK3OWVuLVC/neGVWYTYLxg3P5cFuc1dsDXNRRpENPRhGalZh3O4tCt1AZzeeW6S5G9Try+eoDiyy47YJARDK277Gf/64oJzOVWCuKctwkY370mBeTPQMQtG76KwgT2Wf8gpr5V+CvfJu0vt/EV/Evmlb+lJReV6JH23DkjMVZcBYWTymNy3+E2fUv7BmDT/TtKAeRjHlp2/wY8UA1kZa15Ix7sDOprmhI8Od3fIQ71m5+uD5Caa6ZEaVWLGYNkyWVPb4Q8SRMG2Y7LgsWj8SoPh42VJvYVddOev9j9zxLy6LMXhwglhR8VhFlQJGVj8rzGWSbx/DBlwNQnOsm07KJNXW5XCglkbCX519+mQnDeuK2JlkbvYpJfaKM6ZNxVPpkNglG97aypCzK6N4n99+TohxraiqIoijHTdXc86mcO4NA1XsIkx2zqxB75gjsWSOxpQ+ivexJ9ESYti1PIjQrvp3G9BBHzlg0k43Cc/6JZvFQt/D6btU5lJNT25YnaCt7kvCez3D3OJ+U0itI6jrb6uL8+R0/HofGf1/kZkSphXdXh8lLM3HdWS7sFkFNS4JFmyL0LzRzxUTnib6VgxpRakWQZEND+lG/9udFBuatC/PswiAF1q1c7LyHFl+UjzZGGeV4iyv6fIIwGUmtEILxeVupDvdiwfoQLy5oYHX4Sv62ciiz1xZjIs6sidlHtY+XjXdwz+UppDhVWqF8takRa0VRjot4sJZEqA7QMLvy0aNtJAKVpPa+EiEEmSN+Qt3C66lb9C3igUryJv2FYP3HxH27MLt6AGBxFZI74SFqF1xNuHk17qJpJ/amFBLhZtq2PIGn9FKsKX0JVL+HxV2MNbUv3vIXcBfPJH/yX5BS8tj7AdbtMsrrpToFd13iIcNjIj/NxP0vebnnhXakhPx0E6GoxGEV3DLNfVIsWDwYl12j1FNNmW/oUbtmiz/JPxYEqWpO0DvPwubqOMNy65keuQGLM4v82K1Es64gt/FX5Ax5q9u55wxPobxhIa8sOwtJDiOsr7IrMZHKQCFTMt4h3X39UesngNOm0TNHJdWKohJrRVGOi2Dtoo7vdII1HxHZsw4AR844AFz5Z+Iqmk6wZh4WdwnuHhfg6TkTKSXxJLQHkljMgtSMoYCgob6KrHS9sxLBHl8Ss0l0iy1mQWrHCFqzL4nNLDpH1Jq9SWyWrrjJm8RhFZ0bj/xn3NiexGUXuO0aUkqavDpuu8Bl19ClpHnvWJc0+7ripC7Z49PxOAROm0YiKWnx7xunODUcVkE8KWn166Q6Nex7xy4Nu0UQT0haA8a92yyCWELStlccjUvagzrpbg2ruSvOcGtYzIJIXOIN6mR4NCwmQSQm8YZ0Mj0aZpMgHJP49opDUR1/WO4TZ6VotG56lMZtb7Fzy3wyrF5I+oiQBZnnYIsHSR/0HdoCOkvLIqzbFWdkLwuxuOTScc7OzUiyU03cdK6b7fVxLGZBZVMCb8hYWHcqjYAOzWngrYrx1LVEKci0HfyEA4gnJYs3R5mzKkxSl4wosbKlJs7wnoLpwetw5o0nc9gdJOdfCY0b8PSchT1zWLdruAvO5CL3ZF6ODsGlVzKzcD5NzS+yMTqTs0rjR3qriqIcwKnzG0tRlFNa25YnQJhx97wE7/Z/0rL+D7iKZmDPGtXZJnvUT9EsHjKGfB+hGUmXEIKH3vLxwOs+nl8URLO4sHh68tzG8by4uGtzkz+/4+flT7o2M3l4jp/XlnXFv3/Dxxsrwp3xb//t4+1VXfFvXvXx7pqu+BcveflgXaQz/tm/vHy43oh1CffN9rJwk7HDYzxhxEvKjDgSl9w328un24wJxMGIEa/cbsS+kM59s72sqTASnNaAEa/fZRxv9hrxxiojrm9Lct9sL2XVRvvqFiMurzPi3U0J7pvtZWejUTGlosGIK5uNuLwuzn2zvdS0GBvrlFUbcX2bEW+sjHHfbC/NXmOjnXW7jLg1YMRrKozYFzamJKzYbsRebyu+na9S7v4JT/nfxFx4MQVT/8Fm7b94tOJurHnnYs8YzKLNEd5aFSE/XeM7093ccXEKJTndx3VG97Fy9ZkuvjbByV2zUnj42+mdOx2eKoYVGj8/q8u9B2l5YDvq4/xstpeXPgnRI9PE/V9P5eZpbh7+djrX9p+PSLSRNfxHOLJH48idgNCsZA7/0T7X0cxO0gtGcZ3rai6z3UpqyUwKe/TjTMfjpGYfw0ngivIVp0asFUU55qSUJOPt2NIHkD7wvwhUvo2z4GzyJz3Kyu1xttYmGNvHwuwlKXxn+mpSsqxsqorx8ichbjjHxc7GJAKYPNCYQ2pLH8TU0FP0GNa1/fclQ5tJScvvjL8+yYnb3jWF4OrJLlJdXWMJ35ziIsPdFV93lpPslK4yYd86x0XeXtsw33Sui4KMz5N9uOk8F0WZRmw2GXFxlvEr1WoW3HSei57ZRmy3GvHnyaTLrnHTeS565RpxisOIe+cZcZpLdDue6dY6rtcxwptixD06ni8vzcRN53X1ryDDiHNTjbgo08xN57nISjHut2e2cTyz4/575RnHU10CKSW9c43rp3SM1vcvtHDTeS5cNuP1HFhkxLHKJ5DJKGNGjadwkIsevX+N2SSYfPZoMjd8gOx9L7951Uuzz0jgr5niQjsFpnUcrsz0dApMG1i3uz+XTDj089qDOuV1cSqbkyzYECHDrXHnxR4GFpm7ba4SqJqDxd0TW+ZwAPImPEIiVI/FXbTf67qKphOsXYAQ4Mw7E4u7mGDdx9izzjii+1QU5cDUzouKohxz0fatVM29gJxxvye195XEfDuxuHsghZmfveilyafzrXNcbKqMc/l4B9mpJioa4ny4PkrvfBMvf2KMBH5tgoMZIx20bvorLRseoteVGzBZPERa1lP9waVkjribjEHfOcF3e2prXvMbgvWL6DHtNYTZQfu2Z3AXTsOa2ruzTSLSgn/X67Ru+iuOnHEUTP37fq/117l+yusSnNHbSq9cE2cO+vJbZp9Kom1bePWNl/k4cjsPXpd60HrOlU0J5q+PsLoiRtL4cIAzelu4/iwXTpvxpqZ18+ME6z4id9zvqHx3GhmDvkvm8LsOqT+JyB52/XssZmceJbOWIoToLGmpKMqhUzsvKopyUvFXvgOAM28iQOfGIOt2RmnyGRnFtto4t87o2v2td56F3nkW/rEggNsuyE018UlZlOkj7FjTBwIQa9uKI2cMe9b/ATA2k1EOX7S9nPbyZ0DqNK74CUIzEaiaS9vmxymY+iSOnHHoySg1864gHqjEnjmC5tz7ePCpNsb0sVKSY2Z5eZS8NBOTB9pYvzvOJWMcXDzGcaJv7bgwOXLpa1nIx5Hbmb04RN8CMy1+HW/QmK+ek2oiK0WjsV1nzc4YO+oT2Cxw1hAbEwfYyEszYTV3jVAnI620bvoLMhmmev7XQOq4Sy455P6Y7Vl4el2BxdWjc+RbJdWKcmypxFpRlGMqGfPTtuUJhMmOxVXY7VjCmCFAcbbGqh0xrpyody4W9IWMxX1lNXEGFFoYXGzhuYVByusS9EofBEC0vQypRwk3LEUzu4m0bDiu93a62bPud2hmF6l9r6Nty2MApA+6jUDNPGo/up7Cc18k2rqZeKCS/Cl/w1U4jede8yGEzrKtURZviZLh1iivS7C8PIrDKjh32OEv4jvVmGwZZFoaGZZZwbba3myojGO3QJpLY3N1nNhem4bmp2tcOdHB5IG2ztHp/9Re/iwyGSZ94C20lT2JNa0/ttS+X6pPeeP/cCS3pCjKl6QSa0VRjorPp5V9PjL2edy+9e8gk2SN+hWN7UalDbMJymoSrNsVx2EVfPtsN798xceSLVEuPMPBki1Rnl8UZMogG+1BycAeZkb3sfLWyhBPfBDg9plZaNY0QvVLaC9/DrOzgNR+19Gy7nckQo2Ynbkn7HU4VYWbVhKq+4i0YT/B3vsmUuM+zK5CMgZ9h/SB/0X1B5dTv+S7gMSRMw5X4TQ2VBrzgr91tovBxRbagzo9s41PFv75cYgLRtkPmDSejoQQmBw5XJn9Irlff4RIHOwW43EpJd6QpNmXJM2ldZvPvz96PED7tudwFU0na+Q9WFP7YfGUHJ8bURTlsKnEWlGUIxKs/YimlT/FmjGYuLeCkksWAtDwyXeJtm8lEazDUzILd+9v8Ktn28lJM3PdVCdPfGBM8RhYZKYoy8yQYgvvr410JtBWMyzeYlTZGFhkwW4R/PjSFB6e4+fhOQG+22Mceu0HCLOTwrP+AcJIVCKtG3A7VX3rL6ut7O9o1gxm77qKnSv83Pe1X+Bxabz3WZgRJSnkT3mC6nmXIxMhMs98goY2nTdXhMlO0RjXz9qt1OGZg+yMKLV2Wzz6VWF25pEINSKEwLHXgNMYmAAAIABJREFUJoRCCNJcXa/RwbSVPYke95Ex6DYAUnpdcSy6qyjKUfbVGUpQFOWoS8Z8tG76PxLhBhKBWlL739B5zF18EWZnIVLqZI38KSu2xfFHjFJwrQGd713gJhCRDOphlFS7+kwniaTkt6/78IYkt8/0MGOEnVG9LJ2jezmpJm6Z7iYck9RbL0KzpFB49j9x5IzDlj4YhImomg7ypcX8lQRrF1CZdi+bqnXCMckT8wI8+q6ffy8P88DrXsraSimY+hQZI+/n6VX9uP8lL7UtSS4b78Bs2jeB9ji0bhUtvirMjlwS4YYjukbMt5O2LX/DUzILe9aIo9QzRVGOB5VYK4rypUndmBzdvOZXRFo+w5o6gJh3K5q5a5Gau/gi4oHdOPPPxOzIpq6jZrLbDm+vDjNnVRiTBkOKjcQ6J9XEJWMdBCKSoT0t9Cuw8LWJTm4739PtuYuzTJhN0Gw9m16Xr8KRbdTB1swOrKl9ibRu7NZeT4Tx7niJmH/3sXo5ThqJSAv7q/QkpSTU+CkyGdvved7y54jIVN6tPoue2SZum+GmqjlJeV2CqyY5yUsz8X/vBdjQPop18atZvzvOBaPs/P6GNMb0+erMoT4UZocxYn24FbeklDStuh9hspE18qdHuXeKohxraiqIoihfip4IUTn3QiyuAjSLB9AoPOd56j/5Hk0rfkKgai5ZI+5GJqMkgrVkDr0TMDYp6ZVrYmxfGy99Ykz1+P6F7m4lyaYNtyMwNgs5ELNJ0CPLRGWzjjB1b2fPGEagdj5SSoQQBGsX0rTyXhLhBoTZRc6YX5NSetmxeFlOKD0RoWX972nf9gyOnPFkj/4FtjRjExApdZpW/QzfjtmkD/oOWSPu7nZutK0MX8WrLDf/Eb9P8IOLXPTMMXPzNKOO9cAiC1MG23j0XT/PfBTEbDLeDF02zvGVHJE+GLMzD5kMo8f9h1WBI9q2mXDjUrJG3Y/ZkX0MeqgoyrGkRqwVRflSmtf8kkSgknDjCoI183AXn4/ZkU3B1KfIHHYX0bbN1Hx0La1lTyI0K66iadS3JtjdlGRQDwtTBtk4e4iNOy/2MKS4e2Js0gQzRjoOWv+3JMdMZVMCXe8+KmjLHIYebSMRrEZKSePKexAWF/lnPoEtfRCNn/6Q5rX/i5T6UX9dTpREuJnqDy416k0XX2TUDH9vJt4dL5GItNCw9L/x7ZiN2VlA+7bnSISbO8/17fo31fMup06OYlXLaM4ZaqNnxyY24/raGFhkfJpgNQu+f4GH4mwTZpPgurNcKqk+ALMzD4BE6PCmg4TqjDUKnpKLj1qfFEU5flRirSjKIZNSJ9y8BpM9h6Lp/8aRN4mMwd8DjPq4GUO+T9G01xAIgtXv48yfgsmawryOrcBz00xYzIJrprjocwTbVZdkm4kmoKG9K0Fu9iWxZ40HIFi3iJh3G8lwI+kDb8XdYwZF584mte91tJf9ncblPz78F+Ekkgg1UrPgG8SD1cSHv8xC/XfUD1iAOXsqTSvvYfecKfir5rEr93Ge8L7F1sgk2rb8jWTcT9Oqn9H46V1EU87iw+TDpLo0Lh3rPOBz2a2C/7kshd9ck9ptx0qlO7PDqEiTCNUf1vnBuo+xZQzDbM86mt1SFOU4UVNBFEU5IKknCFTNxVV4DsG6RYQalxP3VZA74REcWcMpOueFfc6xekrIn/Ik9YtvJbXPNSR1SVVzArdNMLbP4SfTeyvtGFXd3ZSgIMPE8vIoT38Y5PLxBQxM6U2geh4yYezW6Mo/EwChmcke/Us0s4O2sifJGHQb1tQ+R6U/J0rD8rto8QuW2N5n88cuTFqUpA5O6++ZnLeCLLmRNfHr2bbNitUM7+u/JHfLlbRve5qwnsI619N8WjUCJNx2vgu79YtHoS0mgcWhRqq/SOeIdbjxS5+bjLYTaVlLxuDvH+1uKYpynKjEWlGUA9qz9gHatz1LSu9vkIy2EqpbhNnVA0/Pmd3a6VKiCUEiKUkkwZ41itLLV5HQ4c0VYar26Nw63Y2mHZ2Rztx0DbvFSKztVsGzHwUBWFEeY8yAGbSV/Q091o41rX9nogMdJc8G3Ezb1qfwV84hc9gPD/k5ZTJGItKExVV0VO7hSIWbVrK6KoX50YcRmpnLxzs4e4idqj0J5q2LMG/3OGAcKQ7BVZMcDC+18OtXJG8lnyfP4ae8rZCIz8T4/lZmjT349Bvl0JgcOcDhTQUJ1S8BqeMsOOso90pRlONFJdaKouxXzLuT9m3PgjDhq3gZT6+vIfUY2aN+itC6fnW8/1mY+evD3HlJCluq47y6LMxfbk7HbhW8sjTIok1Rhva0fOGCxC9LE4Ke2WaWlEVZuClKz2wTI0qtvLUyTDD1QpCPEW3bTPrAW/Y51+zIxpEzAf/ut8kYeuc+c4WlnqCt7G9IPUn6oFvRTEbVi+a1D+CreJmSS5acFIvKlixbxNzQL+mbb+HG8zydiXG/AqOiSkVDAm9IZ1hPS2c5vG+f42H2Eo26SCYDe5i4eIyDokz138DRpJlsmOxZxANVX+q8ZNxPoHoumi0de8awY9Q7RVGONfUbVVGU/WrZ9GcQZvIn/5Wmlffi3/kqzvyzcBVN72wTiCT594owUsJT84NcO9XJlRMdmDsGP71BHZMGN5x94Lm7h2toTwu1rUnOH2vn7KF2AhHJWyvDbGwpZbAzn0SoHmf+1P2e6ym5mKYVPyHauhF7ZlcSk4jsoX7Jd4k0rzLur/Jt8ib9Gc2SgnfHv0CP49v5Sue88hOhoS3BxyvWs7DueopT2vnBzD7YLPtOz+idt++v95G9rIzsdfTe4Cj758geQ7hhaWd1moNp3fRXWjY8BICn9HKEpj49UJRT1RF/LiuEMAkh1goh3umIS4UQK4QQ24UQLwshrB2P2zriHR3HS/a6xj0dj28TQsw40j4pinJkEqEGApVvkz7wZtw9ZpA16qeYHLlkj/45QghWbo/y2c4oNS06UsLwEiPJXbwlyvh+NswmQTwh2VaXYHRvK6nOo58ozBjp4JEb05kx0oHVLMhwa/TONfPZzjju4ouMkb/sM4glJNvr4zT7kp21hd09zgfNgn/3nG7XbN34Z6It68md8AgFZz1LMu6n5sOraVzxEwQCW/oQvNtnd9bxPt5WbAty/7/a+XBnT3o5y7j90qL9JtXKieUsmEoi3EDMW37QtsloO62bH8ORN4mCqU+TM+bXx6GHiqIcK0djxPp2oAz4vGDn74BHpJQvCSGeAG4CHu/42ial7COE+EZHu6uEEIOAbwCDgQLgQyFEPynlifmfS1EUmtb8ApB4So1tlFNKL8dTcilCaDS2J/n7/CCaMKp8eByCW6e7eWtlmA/WRVi5PcZFZzjITzcRikomDjh+G4ic0cfKK0tDtE28k5L+t/DikgTLtgVJdPw2yXBr9CswM7LUQW7uRIL1C8nmPsDYmCNYuwBnwdmklF4KQI9pr1Gz4BrCjUtJG3ATjuzR1C+5jWDdQtxF5x3z+0kkJRsq47T4dQTw6rIwhaZ1XD+mhpIR16mRzZOUM38KAKH6xZ31xA/Eu+NfyGSY7JH3YksfdDy6pyjKMXREibUQogi4CHgA+KEwPvM6B7imo8lzwC8wEutZHd8DvAb8taP9LOAlKWUU2CWE2AGMBT49kr4pinJ4pJSEG1cizG5se1XNEML4gGvBhgiagMIME9UtSWaOtmMxC7420cmkAbbOXRU9DkGaSzCg8PjNOJvY38rCjREenxelf6GDNRVRJg+0MbzEQltAZ1tdgs3VcZaXx5heciMjfDeQCDdhduQQbdtCIlRP+tAfUtmUIByXZLrzKTj3ZdrKX2R18iZ2bzYxzjIMy2e/Ruox3D3O73xdjqZWf5IlZVGWbIniDXXV6s63VfONrIcpGfmuqiN9ErM487Gm9iNY/zGpfa8jHqjcb4ItkzHay5/DkTdJJdWKcpo40v/x/gT8D/D5nsOZQLuUMtER1wCFHd8XAtUAUsqEEMLb0b4QWL7XNfc+R1GU4yzatgU91kbW6F8CEE9ILGYjiSuvi/HxZiNZvWaKk01VcQb16Cqhl59h4uZpLjQBK7bHuGCUHU07fgmgy65xx8Uefvu6jzUVMS46w86l47rmd589FHRd8uzCIPO2DcFvu43chuWklF6Cv+ZDVkauZfXHZxOI+DrPsVlsOKw30R6UmLUEW7SnGOl8G9uHnzJueAt9zrjuqPQ9GNF577MIGyrj1LclERg7HE4dYqNXrpnmpiqin1xFdt8fqqT6FODMn4K3/Hmq511GrH0bPWd+iDWlV7c2gdr5Rq31sb89Qb1UFOVoO+zEWggxE2iSUq4RQpz1+cP7aSoPcuyLzvnP57wFuAWguLj4S/VXURRIxkOE6hbiLr4QIQTxQA2JUC2OnHGAsTlF66a/gGYhpeclfLQxzCtLw1xzppMpg+384c0AQsBFox2YNMHwkn0XwmlC8K1zXAzsYWHUCVgol5Nq4kezPOxqSjJpwH76pxn9M2uSJWU3Y/psFWMtceasGcaOyHCGFFsY19dKqktjjy9JdUuSPT6da6faKMo08cxHQZbXXooElq0Mc40zysQB1sNOdnVdsqQsypsrwgSjksE9LEzob2VMHysZrgQNS79Py4btWF2FJDVJSsf0HOXk5syfQvvWp0gE6wBJsPajfRLrUP1iNEtK59QRRVFOfUcyYj0JuEQIcSFgx5hj/ScgTQhh7hi1LgLqOtrXAD2AGiGEGUgFWvd6/HN7n9ONlPJJ4EmA0aNH7zf5VhSli64naNvyBK6Cs7FnDKZm/teItZeREfgxGYNuw1fxMq1bHqPv1RUAhBo+IbLnM1xF00hoqfx7eRtJHV5dFup8Czx1kPWgO++ZTYJJx3Fu9X8qzDRT+AVl5DQhuPYsN9GGd/ikcRKfzPFjpj+z+qzhomnn7ZUk77uhzY9mpaBLyc51rzB7ZTrPLhzNx1siTB1sJxjRSXVpnNHLSlKHtbtiLN8Wo641yYAiMz2zzVjNxusjBLT6ddZUxKjak6RfgZmrz3R2lr/TExHqF99KqH4x1tR+hBuX4upx/klR6k85OGfuRLLH/BpX/lnULb6ZYN1HpA+8uVubcONyHLnj1Fx5RTmNHHZiLaW8B7gHoGPE+kdSym8KIV4Fvga8BNwAvNVxypyO+NOO4x9JKaUQYg4wWwjxMMbixb7AysPtl6IohnDTChqW3UUiVIt327NkDLsDf1s1G5L/hVhRzbT4H0ntcxW1pnP4YG3YqK6R2p9d8fGE9DuILA8RjcPl4x28vSrMPxeFKMwwcdVk14m+taNCE4IrhjeQv/J/sLuzKUi8T58Jbx7SyLMmBD37TeaqLVPYmfs4i+rGdm5SA/C6K0wophONGwsmS3NNrN8d59NtsX2ulZOqcct0F6N7d41664kw9YtvIdSwlJxxvyOl15VE9qzF4ul59F4A5ZgSmom0vtcC4Co4l7ayJ0nGfJisxjr/eLCWeKCK1H7fOoG9VBTlaDsWq4ruBl4SQvwGWAs83fH408A/OxYntmJUAkFKuVkI8QqwBUgA31MVQRTlyOiJCPVLbyekZ7BY+w3B9namLv8DH8X/TEVkBACjdswka8SP2RHIYt46I7H2736DKnEun5XnkkxGmTrYxgWjHJg0eGtlmG+f4+rcbOR04MwbT3/r/0JcI//Mv2H9EomrxVWII3MIQ5KPc943p9HUniTNpVHRkGDRpiipLgvj+1npW2BGEwJdlwSjknjSqPah65Du1vYpl5cIN9Ow7A7CjZ+SO/4PpPQypn44skcd1XtXjh9X4dm0bXmMUP3izl1Lw43G0iJn7vgT2TVFUY6yo5JYSykXAYs6vt+JUdXjP9tEgCsPcP4DGJVFFEU5CppW3c+a9oksit1LLKkBEiwZVESGMLjIzOaaBHNab+eHMS+XjElh5mgHMf9uwo3LuGzkBPJjDt5cEea84XYApo9wMHWw/bSrmWxLG4S7+CJcheceVvk8d4/ptKz/IyLaSGGmsXX6sBIrw/Y391wTeBxf/Pq1b3uWPev/gNTj5E74Iymll3/pPiknH3vmSDRrGsHajzoT61Djp2i2dKwHKcenKMqp5ejXiVIU5YRKxkNU7FjPh+GfUJRl4e7LPBRnmSkPDGFIsYXbL/YwvngPuxMTiHp3YjYJrGaBb+erIDQ8va5kyZYo/QvN5KV1zf083ZJqMD6uz5/8V1JKLzus891F5wMQqJl3xH2J+XfTvOZX2LNG0vPCD1RSfRoRmglXwVRC9YuRUu8oafkpzpzxx6Rco6IoJ476F60opxn/zldZFPo+OiYuGeOgT76Fu2Z5uHScgxvPdSGEoDjXRQw3e5qqAZBSx7/7LZx5kylvSafFrzN10IlbfHiqsKb2xpLSm0D1B0d8LW/58yBM5E14GGtK6VHonXIyceZNJhltIda+jbh/F4lQHY7cCSe6W4qiHGUqsVaU00x1+UdUJ8cyvq+NwcXGlASnTeOiMxx4HMY/+aK8TADqmrwARJpXkQjW4im5jAUborjtghEnoFTeqcjdYwbhphUko237PZ6M+Qg1LP3Ca+jxAL6KV/EUX4TZkXMsuqmcYI7ciQCEGpd1fsLhKjznRHZJUZRjQCXWinIa8Ve+yyeNY5DCxKXjHQdsV5BpJM11bXEAfLveRJid1JvPY1NVnBkj7VhOo0WKx5K7x/kgkwRrF+z3+J61D1D70bVEWjcf8Bq+na+jJwKk9f/WMeqlcqJZXAVYPCWEG5YRrP4AW8YwLC61F5qinG5UYq0op5GWnR+yNvYNclMkmZ4D18ZNcQjsWphGvwM9GSVQ9S6uwhm8uUonzSU4e4j9OPb61GZLH4LZWYBv52u0bX2GYP2SzmOJUCP+XW8C0Fb2twNew1vxMraMYdizRhzz/ionjjN3EqHGZURa1uHuMeNEd0dRlGNAJdaKchrQEzGC9Z+woc6MRGNc/y+uNS2EINflozmahX/X6+hxP1WOG9jRkGDmaMdpuVDxWBFC4O5xPuGmFez57Fc0rbgbKY39q9rLn0XKBO7iCwlUvUs8ULXP+VHvdmLtZaSUXnq8u64cZ468ichkBEAl1opymlKJtaKc4gK1C6h4bRh1C69jS3ASKfY454868DSQz+WmSlqSJbSsfwiRMpQ3NvckP107oTsmnqoyhv6AvMmPkTH0ThKheuL+XSTjfrzbX8Td43yyR92PEGZaN/3fPucGds8BoeEunnkCeq4cT86OxYrW1L5YU3qf4N4oinIsHIsNYhRFOUbiwQb2rP0NnpJLadnwEBZPLwJVc6kwf4Nl0etpTOQwY4gdk3bwEefCLAcra1IJhJNscf2CFr/Oj2Z5TqsNYI4XkzUVT/EFxPyDaN34CKGGpQhhQo/7SRtwM2ZnLql9r6N929OY7FlkDv8RQgiklPgr38aRO0FtVf4VYLKlk9bvW9gyh57oriiKcoyoxFpRTnL+ynfQE0FC9YuJB2po2tNEeuMqAlpPapqCbDC9wc6WYjQBLrtgfP9DG3EuyssC4mzUr2XJ7hIm9LfSv9BybG/mNGdxF2N2FRFqWEoy3Ig1tR/2TGPedNaoe9GTIdq2PEY8WE32GT8n0rKOeKCS9MHfPcE9V46X7NE/P9FdUBTlGFKJtaKcxPREhNoVv0TGvURcE3m94cc06oMYH38Bi2xnSeR7WM2Cb05xMmWwDU0c+mhzYbYT8LIocCN5aRpfn+Q8djfyFSGEwJk3Cf/uN5HJKFkj70V0/J0IoZEz5gEszgJaNj1KoPp90OOY7JlGZRFFURTllKcSa0U5iTWv+RWvtP2aIAVcmLiXJr0fmpAsD1+LyxzAYhL890VuBhR++ZrT6W4Nu8WocX3nxR7cdrXk4mhw5k3GV/EyCBOeku4LEoUQZAz5Pq6i6XjLn8eWMRh38YWYrCknqLeKoijK0aQSa0U5ia3ZpVOdHAvAW+GHkJj5znQ3n2yNsrnKzfcvPLykGkATgttnesj0mEh3q6T6aHHmTuT/27vz6Dqrco/j3+cMSTOnaTPR0KYjpUBboLRlrszTpVRkVESuV1C8S70iCMhaukS5ioBw1QuXe1FwQlFQkMVcRUBLoRRKSwdIoXOapEmbeTjDc/84L1hpS5vmZP591srKm332u7NPnrznfc5+97sPGDkHzNvjvOnMwimUzP5O33ZMRER6nRJrkQGqc8dqVjcfhpHkzCOyeWJpMRPLIhw+IcqM8VF2tCY/cq3qfTGpXHOq0y08ooiyY+4ks0g3qImIDDdKrEUGoGQyzoaXbqIq9kPmTg5x3pwsyovCTCqLYGaEjR4n1dJ78irP7e8uiIhIP1BiLTIA1S66hierzyJGDh+bno+ZMXeK1pcWEREZyDSxUmSA6dyxhreqtrA8Np/8bGN8qd7/ioiIDAY6Y4sMMJvfuIcn279FQZZx3YK8/u6OiIiI7CONWIsMIM0bn+HZqkoak+V8/ow8Sgr03ldERGSw0FlbpB94MkHr5oUkOuvBIuBx8irns+6tJ1nSdRNlBQmt2CEiIjLIKLEW6WPuzqaFF1O3dT0JMsgKNdLpuZTFsnl50xjAWDBXHxgiIiIy2CixFukjbVsXQSiMJ7p4bP0pvNF1PhAi09qIWgtlL73NhvglHDE+zBETtQKIiIjIYKPEWqQPxNvrWPvcVXR4LpFQnBVdfyQ7I8QFx2bzh5edRGcbtYlJZGSM4MLjcvu7uyIiIrIflFiL9IGty+/mv5ueJEEm+dEmLJTBtQvyqRgVoaQgzO2Ppup99Yx8ffCLiIjIIKXEWqSXdW5fw99WdhAni7HFYTpjRcyfmUXFqNThN+WAKFefmVpW76AxumFRRERksFJiLdJLYm3VbHruYhobm3mp/WGmlCX42oKRmNkudWdUZvRDD0VERCSdlFiL9MCOqgdpePNORoyaQe7Ys8gcOZVtS29h1PRr2PDKrfyx5ktUxU7EMS45sWC3SbWIiIgMDUqsRfZDoqOB+uU/ZNWq13iy7cfk1Tdw1Lr7mXXUiTyz9TQKGpexuu4S1sfnMjo/wkmHZX4w9UNERESGJp3pRfaRJ2O0171Gw4of0bB1JUs6L2Vx5wNAmPrYRNbFjoKl17E18W+sbYpTk5zGZSdmc8IhI/q76yIiItIHlFiL7EVX83pqX7mR9u1VbGkrYVnneayI3YUTYu6UDC46Lpto2PjP32/j8R3fYFxkMe8mT+O4qRkcP03rUYuIiAwX+51Ym9mBwM+BMiAJ3Ovud5lZEfBboBJYB1zo7tstNbn0LuAsoA34jLsvDdq6HLgpaPo77v7A/vZLJF2S8Q6a1z9K1eJ7eLz5BhqYTFuiAICcTONTJ2Yza9I/EufPn1HEzb8z1sRP5V+OyuLsI0doTrWIiMgw0pMR6zhwjbsvNbM84DUzexb4DLDQ3b9nZtcD1wNfB84EJgdfc4C7gTlBIv5NYBbgQTuPufv2HvRNZL8lulrZvPBimrZvZFXnSbzYcT/tnktpQZhLZ2cxrSJKXlZol/3KRoa57rxCMBhXrItBIiIiw81+n/3dvRqoDrabzWwVMAaYD8wLqj0APE8qsZ4P/NzdHXjZzArNrDyo+6y7NwAEyfkZwIP72zeR7urYvpL6ZbdROOXTNFT9jnvXX09N8iAgxMSyMOcfnc3k8r2vMT2uRAm1iIjIcJWWLMDMKoHDgcVAaZB04+7VZlYSVBsDbNxpt01B2Z7Kd/d7rgSuBBg7dmw6ui7DnLvTUbeERc/cwfOtVzH53b+wKX46NcmDKS0M8ckTspk6JqopHSIiIrJXPU6szSwXeBj4irs3fUQCsrsH/CPKdy10vxe4F2DWrFm7rSOyL+IdO9i88CLaWraxtn0mT7bdShc5VCemYziXzcvmhGlazUNERET2XY8SazOLkkqqf+XujwTFNWZWHoxWlwO1Qfkm4MCddq8AtgTl8z5U/nxP+iXyUWJt1byz8Kv876Y7afFiIMSBo+Czp+STSEI4DGOKNKVDREREuqcnq4IYcB+wyt3v2Omhx4DLge8F3x/dqfzfzew3pG5ebAyS76eBW8xsZFDvNOCG/e2XyJ4k4x1sXXQNVetrebTlW7RSzPiSKKcfnsX0cVGiEU33EBERkf3Xk2G5Y4HLgOVm9kZQdiOphPohM/sssAG4IHjsCVJL7VWRWm7vCgB3bzCzm4FXg3rffv9GRpF0aa9byuoXbuE3dTfQkBxHYTbccGYh40s1Mi0iIiLpYalFOgafWbNm+ZIlS/q7GzKAuTvbV/4PDWsfZWn9YbzYfjUd5DGpLMKXzsknK0Mj1CIiIvLRzOw1d5+1L3U1XCdDUuuW59m49G4er17AO7EHSBJhSrlx0fG5jB2992XzRERERLpLibX0C3envWYRbTWLiDW/R8GkS8kuO4ZErJn6N24lb9w5ZJXMIdHVSP2y28irPI/MkYfQWPUr2mtfofCgK/BkF8muJtprF5M/8UJGFB1Ge/0yVi/8Bq82nczrsTuJeya5mXDJ8TkcNTlDy+aJiIhIr1FiLb0m3l5HMtZMe83LtNe+QjhrNFnFs6lfdR8NLcbihuPYlJhDe/J0KqvW8PkLq7FQlJ+8cToTa6Jceso2SMb50etnc9DWNg6KX82L205hXfxaxq55lfxQDSGSrIl9giM2rGZ2/h28uTmHJ9ruB0LMnhTmrFk5WuFDRERE+oTmWEtaJJNJPN4GyS66Wjez+dU7eK26mA7PZ11sDjWJqWSFmqgIv866+BzavAjDOXAUbKgPEaaTM/J+yGHlTTy+8VQssYOy8BpmjGnhhYZz2NHcwtrYiUQiITrjIcAIWzK1ELrHyLVaWryMBFGyos4Fx+ZwvNahFhERkR7qzhxrJdayT5JdLcQ76kjGW9m+5pe8/k49Y0oLmXDwPKpef4TFdYeTE6ojQozGZBlLuy7GgwsiIUuQnRFi8gFh1lZ3EQkbJYWZXHp8NuWK5odSAAALbklEQVRFEWp2JLj/uXqqancdWQ4RI2JddHkOM8fBp08qBGBLQ4JxJRG2NSV4ZFELnTFnfFkmMyujTCyLaMqHiIiIpIUSa+mxZDJJ66ZnaNz0Ims2NLC8+WiMBFHr4N3YsTR6BSFiVEYWsz5+FAky/2n/jHCCK07OZ+b4DMIh9proJpPOS6s7ae1wygrDlBWGSeK8+FYH7V1J5h2araXxREREpM8psZZ9FmvdQiiaS7x1MxaKEsospL3mFf76wpO82raAmsQ0EmQEtZNkR5OUFkBJUTaWjLNqUydTK6JMH59DZXGEnBFGPOHkZRmhUKhfn5uIiIhIT2m5vWEqGW+nae1DuMdprVnC5voYpaUVjB53DFvefoodjc0UFI4GT+LxFtZtz2NjSykjrJV2itgWH0tZeCVb4wfxXuJbhEhyyowspozJICfTqCwOE4koWRYRERHZHSXWQ0SsdQuP/vGnLGo6FydCu59OnGzYGqdixZs0JL5AG0VQnZqSkUEzXeRiJHHCH7SzPjGXktwYs0tCnDe3gOIC/YuIiIiI7AtlTQNYvK2WWMs6skpmA7Cj6rc0bH6d9fVh8rONtTVJWr2YiYXbSERLebrxarLCbRw+MYeWdicSjVKSF2HlhmmUhMIU5kU5ZGwGiSQsrYqTGYVLThhJRjTEezVxivJClI8MEw3rxj8RERGR7tIc6wEk0dlE49oHiYwYzfZtG/nlG5NpSRZz6ZRn6YwlePDdBTR5ObDrdIwIrSTJ5OsLCphQnrlr4yIiIiLSbZpj3U9iXR0AhCNRQqEwiUScZCK+159DBlWv3sujb43hvdg5jLAm2v0YEmRiJPnR6itxwoQtzvhiZ8HRebR2ONuaEowvDVPXGOf5ZW2cPCNDSbWIiIhIP1FinQadHe3c8/BiVjQeCoTIC9VSmrWNicVdPL1uJjeetZ3xlRN5YdEr/PrNqXzz3GYqKsbx578t4qEVh3B60S/4c8MniJHJiHCc6eOLyB4R5eiD8xiZG+aZpTuIhkOccvhosjN3Ha0+aEwGx03L7vsnLiIiIiIfUGLdDdvqa3l+8Qqa252mjjCbWkpoTowkP1zP9sR0Di1czo6ObLIjnWxpK2H9uixmFy+joGA6AJUVJZze9CZ5edNp3/42scYqRodG8HTDZYwf2cRV55QxKi+8y+89/9iivn6qIiIiItJNSqy74TfPrGTZ9pkA5IXqODC3lrXNOTQmRnPZ4Ws44egTP6hbW7eVHzzSwLJtE8n9+9sce9RMCkZPoHR0M/c8vISNnVPo9PmMCLdz5mFdnHvMOCK6aVBERERk0NLNi93wzto1rN9cy6TKCsYdWPnBpwkmEgnC4V1HmrfWbOEXT73D262HsPMNh/nhbUwrb2fq+HJmTS0mM6qEWkRERGQg0icvDjCb3l3M6neqaG3vpHx0PkfMPYdIZER/d0tERERE9kKrggwwFRPmUDFhTn93Q0RERER6kT6fWkREREQkDZRYi4iIiIikgRJrEREREZE0UGItIiIiIpIGSqxFRERERNJAibWIiIiISBoosRYRERERSQMl1iIiIiIiaaDEWkREREQkDZRYi4iIiIikgRJrEREREZE0UGItIiIiIpIGSqxFRERERNLA3L2/+7BfzKwOWL+XamOBDWn+1QVAo9pMG8Uo/RSn4dmmYjTw21SMBn6bwzlGvdXuUIjTOHcv3qdW3H3IfgF1vdDmvWpTMRqobSpOw7pNxWjgt6kYDfw2h22MBlNfB3KchvpUkB290Oaf1GZaKUaDo13FaeC3qRgN/DYVo4Hf5nCOUW+1O6ziNGinguwLM1vi7rP6ux+yZ4rR4KA4DXyK0cCnGA18itHgMJDjNNRHrO/t7w7IXilGg4PiNPApRgOfYjTwKUaDw4CN05AesRYRERER6StDfcRaRERERKRPDLrE2sx+ama1ZrZip7IZZrbIzJab2Z/MLD8oj5rZA0H5KjO7Yad9vmxmK8zsLTP7Sn88l6GqmzHKMLOfBeXLzGzebtp7bOe2pOfSFSMzu8jM3gyOo1v74akMWWZ2oJn9JXjtesvMvhyUF5nZs2b2TvB9ZFBuZvZfZlYVxOSID7WXb2abzezH/fF8hqJ0xsjMvh+ck1aY2UX99ZyGmv2I0dTgdbDTzL62m/bCZva6mT3e189lKEtnnPo7vxt0iTVwP3DGh8r+D7je3Q8D/gBcG5RfAGQG5UcCV5lZpZkdCnwOmA3MAM4xs8l90flh4n72PUafAwjKTwVuN7MP/i/N7ONAS293eBi6nx7GyMxGAT8ATnb3Q4BSMzu5Lzo/TMSBa9z9YGAu8EUzmwZcDyx098nAwuBngDOBycHXlcDdH2rvZuCvfdHxYSQtMTKzs4EjgJnAHODa99/YSo91N0YNwJeA2/bQ3peBVb3b5WEpLXEaCPndoEus3f0FUn/QnR0EvBBsPwuc/351IMfMIkAW0AU0AQcDL7t7m7vHSZ1sFvR234eLbsZoGqmDBXevJbWEziwAM8sFvgp8p5e7POykKUYTgLfdvS6o99xO+0gPuXu1uy8NtptJnczHAPOBB4JqDwDnBdvzgZ97ystAoZmVA5jZkUAp8EwfPoUhL40xmgb81d3j7t4KLGPXN76yH7obI3evdfdXgdiH2zKzCuBsUoMQkkZpjFO/53eDLrHegxXAucH2BcCBwfbvgVagmtQn9Nzm7g1B/RPMbJSZZQNn7bSP9I49xWgZMN/MImY2ntSVhfcfuxm4HWjry44OY92NURUwNbgKFCH1gqfjqBeYWSVwOLAYKHX3akidjICSoNoYYONOu20CxgRXgG7nH1cgpBf0JEakjrEzzSzbzEYDH0PHUtrtY4w+yp3AdUCyl7oo9DhO/Z7fDZXE+l9JXTZ4DcgjNTINqUsBCeAAYDxwjZlNcPdVwPdJjco9RepFLd7nvR5e9hSjn5I6uSwh9aL1dyBuZjOBSe7+h/7o7DDVrRi5+3bgC8BvgReBdeg4Srvgys3DwFfcvemjqu6mzIGrgSfcfeNuHpc06GmM3P0Z4AlSx9aDwCJ0LKVVN2K0p/3PAWrd/bW0d04+0NM4DYT8LtKXv6y3uPtq4DQAM5tC6lINwKXAU+4eA2rN7G+kLmG/6+73AfcF+9xCKnGQXrKnGAWXav7j/Xpm9nfgHeBE4EgzW0fq/7TEzJ5393l92/PhYz9ihLv/ieDTqszsSlJvZCVNzCxK6iTzK3d/JCiuMbNyd68OphHUBuWb+OeRmQpgC3A0cLyZXQ3kAhlm1uLu1yM9lqYY4e7fBb4btPlrgmNMeq6bMdqTY4FzzewsYASQb2a/dPdP9V7Ph5c0xYn+zu+GxIi1mZUE30PATcA9wUMbgJOCO7FzSE2IX/2hfcYCHyc1SiC9ZE8xCi595gTbp5IaCV3p7ne7+wHuXgkcR2ou77x+6fww0d0YfWifkaRGRjX3ME3MzEidHFa5+x07PfQYcHmwfTnw6E7lnw5e7+YCjcG8xU+6+9jgWPoaqTm+SqrTIF0xstRKE6OCNqcD09F8+LTYjxjtlrvf4O4VwXF0MfBnJdXpk644BW31a3436EaszexBYB4w2sw2Ad8Ecs3si0GVR4CfBds/CbZXkLoE9zN3fzN47OHghSwGfDG4rC1p0M0YlQBPm1kS2Axc1sfdHZbSGKO7zGxGsP1td3+71zs/fBxL6m+93MzeCMpuBL4HPGRmnyU1eHBB8NgTpOYTVpG6L+GKvu3usJSuGEWBF1O5BU3Ap4IrRdJz3YqRmZWRmvaWDyQttVzbtP2ZliDdks449Wt+p09eFBERERFJgyExFUREREREpL8psRYRERERSQMl1iIiIiIiaaDEWkREREQkDZRYi4iIiIikgRJrEREREZE0UGItIiIiIpIGSqxFRERERNLg/wFAtwYXgYq5DgAAAABJRU5ErkJggg==\n",
    905       "text/plain": [
    906        "<Figure size 864x432 with 1 Axes>"
    907       ]
    908      },
    909      "metadata": {
    910       "needs_background": "light"
    911      },
    912      "output_type": "display_data"
    913     }
    914    ],
    915    "source": [
    916     "cashrate = 0.03\n",
    917     "monthly_cashreturn = (1+cashrate)**(1/12) - 1\n",
    918     "rets_cash = pd.DataFrame(data= monthly_cashreturn, index=rets_tmi.index, columns=[0]) # 1 column dataframe\n",
    919     "rets_maxdd25 = erk.bt_mix(pd.DataFrame(rets_tmi), rets_cash, allocator=erk.drawdown_allocator, maxdd=.25, m=5)\n",
    920     "dd_25 = erk.drawdown(rets_maxdd25[0])\n",
    921     "\n",
    922     "ax = dd_tmi[\"Wealth\"].plot(figsize=(12,6), ls=\"-\", color=\"goldenrod\", label=\"Market\", legend=True)\n",
    923     "dd_tmi[\"Previous Peak\"].plot(ax=ax, ls=\":\", color=\"goldenrod\")\n",
    924     "dd_25[\"Wealth\"].plot(ax=ax, label=\"MaxDD 25%\", color=\"cornflowerblue\", legend=True)\n",
    925     "dd_25[\"Previous Peak\"].plot(ax=ax, color=\"cornflowerblue\", ls=\":\")"
    926    ]
    927   },
    928   {
    929    "cell_type": "code",
    930    "execution_count": 13,
    931    "metadata": {},
    932    "outputs": [
    933     {
    934      "data": {
    935       "text/html": [
    936        "<div>\n",
    937        "<style scoped>\n",
    938        "    .dataframe tbody tr th:only-of-type {\n",
    939        "        vertical-align: middle;\n",
    940        "    }\n",
    941        "\n",
    942        "    .dataframe tbody tr th {\n",
    943        "        vertical-align: top;\n",
    944        "    }\n",
    945        "\n",
    946        "    .dataframe thead th {\n",
    947        "        text-align: right;\n",
    948        "    }\n",
    949        "</style>\n",
    950        "<table border=\"1\" class=\"dataframe\">\n",
    951        "  <thead>\n",
    952        "    <tr style=\"text-align: right;\">\n",
    953        "      <th></th>\n",
    954        "      <th>Annualized Return</th>\n",
    955        "      <th>Annualized Vol</th>\n",
    956        "      <th>Skewness</th>\n",
    957        "      <th>Kurtosis</th>\n",
    958        "      <th>Cornish-Fisher VaR (5%)</th>\n",
    959        "      <th>Historic CVaR (5%)</th>\n",
    960        "      <th>Sharpe Ratio</th>\n",
    961        "      <th>Max Drawdown</th>\n",
    962        "    </tr>\n",
    963        "  </thead>\n",
    964        "  <tbody>\n",
    965        "    <tr>\n",
    966        "      <th>Market</th>\n",
    967        "      <td>0.096058</td>\n",
    968        "      <td>0.145419</td>\n",
    969        "      <td>-0.668827</td>\n",
    970        "      <td>4.247282</td>\n",
    971        "      <td>0.066949</td>\n",
    972        "      <td>0.094633</td>\n",
    973        "      <td>0.441951</td>\n",
    974        "      <td>-0.499943</td>\n",
    975        "    </tr>\n",
    976        "    <tr>\n",
    977        "      <th>MaxDD</th>\n",
    978        "      <td>0.090062</td>\n",
    979        "      <td>0.112755</td>\n",
    980        "      <td>-0.630463</td>\n",
    981        "      <td>5.015334</td>\n",
    982        "      <td>0.049978</td>\n",
    983        "      <td>0.071074</td>\n",
    984        "      <td>0.518327</td>\n",
    985        "      <td>-0.244212</td>\n",
    986        "    </tr>\n",
    987        "  </tbody>\n",
    988        "</table>\n",
    989        "</div>"
    990       ],
    991       "text/plain": [
    992        "        Annualized Return  Annualized Vol  Skewness  Kurtosis  \\\n",
    993        "Market           0.096058        0.145419 -0.668827  4.247282   \n",
    994        "MaxDD            0.090062        0.112755 -0.630463  5.015334   \n",
    995        "\n",
    996        "        Cornish-Fisher VaR (5%)  Historic CVaR (5%)  Sharpe Ratio  \\\n",
    997        "Market                 0.066949            0.094633      0.441951   \n",
    998        "MaxDD                  0.049978            0.071074      0.518327   \n",
    999        "\n",
   1000        "        Max Drawdown  \n",
   1001        "Market     -0.499943  \n",
   1002        "MaxDD      -0.244212  "
   1003       ]
   1004      },
   1005      "execution_count": 13,
   1006      "metadata": {},
   1007      "output_type": "execute_result"
   1008     }
   1009    ],
   1010    "source": [
   1011     "erk.summary_stats(pd.concat([rets_tmi.rename(\"Market\"), rets_maxdd25[0].rename(\"MaxDD\")], axis=1))"
   1012    ]
   1013   },
   1014   {
   1015    "cell_type": "code",
   1016    "execution_count": null,
   1017    "metadata": {},
   1018    "outputs": [],
   1019    "source": []
   1020   }
   1021  ],
   1022  "metadata": {
   1023   "kernelspec": {
   1024    "display_name": "Python 3",
   1025    "language": "python",
   1026    "name": "python3"
   1027   },
   1028   "language_info": {
   1029    "codemirror_mode": {
   1030     "name": "ipython",
   1031     "version": 3
   1032    },
   1033    "file_extension": ".py",
   1034    "mimetype": "text/x-python",
   1035    "name": "python",
   1036    "nbconvert_exporter": "python",
   1037    "pygments_lexer": "ipython3",
   1038    "version": "3.8.8"
   1039   }
   1040  },
   1041  "nbformat": 4,
   1042  "nbformat_minor": 2
   1043 }