ki-chi/matplotlib_hokkaido.ipynb

## matplotlib_hokkaido.ipynb
{
  "cells": [
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "# Pandas+Matplotlibで市町村の人口を可視化する"
    },
    {
      "metadata": {
        "ExecuteTime": {
          "start_time": "2017-01-22T19:24:46.056215",
          "end_time": "2017-01-22T19:24:46.059418"
        }
      },
      "cell_type": "markdown",
      "source": "今回は以下のような図をPythonで作ってみたいと思います。"
    },
    {
      "metadata": {
        "ExecuteTime": {
          "start_time": "2017-01-22T19:24:36.681282",
          "end_time": "2017-01-22T19:24:36.685024"
        }
      },
      "cell_type": "markdown",
      "source": "<blockquote class=\"twitter-tweet\" data-lang=\"ja\"><p lang=\"ja\" dir=\"ltr\">試しに北海道の全人口（平成27年で538万3579人）が二等分されるように分けてみたんだが、たったこれだけでJR北海道が死にかけてる理由が察せるのが哀しい。 <a href=\"https://t.co/z3EivEkvXM\">pic.twitter.com/z3EivEkvXM</a></p>&mdash; 道民の人＠冬コミ廃墟本委託中 (@Tusk_act2) <a href=\"https://twitter.com/Tusk_act2/status/802477053970817024\">2016年11月26日</a></blockquote>\n<script async src=\"//platform.twitter.com/widgets.js\" charset=\"utf-8\"></script>"
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "## シェープファイルを取り込む\n\n地図のような境界や領域を保持しているファイルをシェープファイルといいます。シェープファイルの可視化はRでは結構情報が多いものの、Pythonだとなかなか活用例が少ない印象です。今回は[こちらのサイト](https://sites.google.com/site/rbookvisjp/)で配布されている平成25年度のシェープファイル及びその中の人口データを用いて、都道府県の人口を2分割するプログラムをPythonで書いてみました。  （たぶんもっとスマートな書き方があるような気がします…）  \nなお、Pythonでシェープファイルを扱うにはpyshpというモジュールをインストールする必要があります。"
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": false,
        "ExecuteTime": {
          "start_time": "2017-01-22T19:21:31.965839",
          "end_time": "2017-01-22T19:21:32.540378"
        }
      },
      "cell_type": "code",
      "source": "%matplotlib inline\nfrom itertools import chain\nimport pandas as pd\nimport numpy as np\nimport shapefile\nimport matplotlib.pyplot as plt\nfrom matplotlib.patches import Polygon\nfrom matplotlib.collections import PatchCollection\nimport seaborn as sns",
      "execution_count": 1,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": true,
        "ExecuteTime": {
          "start_time": "2017-01-22T19:21:32.541792",
          "end_time": "2017-01-22T19:21:32.545818"
        }
      },
      "cell_type": "code",
      "source": "def list_to_dict(lst):\n    return dict(zip(range(0, len(lst)), lst))\n\ndef list_flatten(lst):\n    # 2重リストを1重にする\n    return list(chain.from_iterable(lst))\n\ndef list_combine(lst, *args):\n    for l in args:\n        lst.extend(l)\n    return tuple(lst)",
      "execution_count": 2,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": true,
        "ExecuteTime": {
          "start_time": "2017-01-22T19:21:32.547360",
          "end_time": "2017-01-22T19:21:32.552946"
        }
      },
      "cell_type": "code",
      "source": "# 点列と分割点のリストからPolygonのリストを作る\ndef make_polygons(row):\n    row = row.tolist()\n    axis = row[0]\n    parts = list(row[1])\n    parts.append(len(axis))\n    axis_list = [axis[parts[i]:parts[i + 1]] for i in range(len(parts) - 1)]\n    Polygons_list = [Polygon(x) for x in axis_list]\n    return Polygons_list",
      "execution_count": 3,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": true,
        "ExecuteTime": {
          "start_time": "2017-01-22T19:21:32.554475",
          "end_time": "2017-01-22T19:21:32.557674"
        }
      },
      "cell_type": "code",
      "source": "# データの読み込み\nsf = shapefile.Reader(\"japan_rvis_h25/japan_rvis_h25\")",
      "execution_count": 4,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": false,
        "ExecuteTime": {
          "start_time": "2017-01-22T19:21:32.559356",
          "end_time": "2017-01-22T19:21:32.868586"
        },
        "scrolled": true
      },
      "cell_type": "code",
      "source": "sf.shapes()[:10] # これら１つ１つがポリゴンデータ",
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": "[<shapefile._Shape at 0x10cfaccf8>,\n <shapefile._Shape at 0x10cfacda0>,\n <shapefile._Shape at 0x10cfac550>,\n <shapefile._Shape at 0x10cfac518>,\n <shapefile._Shape at 0x10cfac630>,\n <shapefile._Shape at 0x10cfac5f8>,\n <shapefile._Shape at 0x10cfacd68>,\n <shapefile._Shape at 0x10cfac860>,\n <shapefile._Shape at 0x10cfac8d0>,\n <shapefile._Shape at 0x10cfac978>]"
          },
          "metadata": {},
          "execution_count": 5
        }
      ]
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "データにはRecordとFieldが含まれており、前者はいわゆるポリゴンデータ、後者はその境界・領域についての属性データ（県名、市区町村名、人口など）になっています。\nポリゴンデータの中には市区町村の領域を結ぶための点列``sf.shapes()[i].points``があるのですが、一部の市区町村は飛び地などによって境界が一筆書き出来ない地域があります。そのため、分割点のリスト``sf.shapes()[i].parts``でそれらの点列をどこで分割するのかが明示されています。\n"
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": false,
        "ExecuteTime": {
          "start_time": "2017-01-22T19:21:32.869609",
          "end_time": "2017-01-22T19:21:33.456147"
        }
      },
      "cell_type": "code",
      "source": "field_name = [x[0] for x in sf.fields[1:]] # 属性データの項目\nrecords = [[x.decode(\"shift-jis\") if isinstance(x, bytes) else x for x in y]\n                   for y in sf.iterRecords()]  #属性データのSHIFT-JISをデコード\n\nsr_points = pd.Series(\n    [i.shape.points for i in sf.shapeRecords()]).to_frame().rename(\n        columns={0: \"AXIS\"})  # ポリゴンデータ\nsr_parts = pd.Series([s.parts for s in sf.shapes()]).to_frame().rename(\n    columns={0: \"PARTS\"})  # ポリゴンの分割点",
      "execution_count": 6,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": false,
        "ExecuteTime": {
          "start_time": "2017-01-22T19:21:33.457371",
          "end_time": "2017-01-22T19:21:33.460335"
        }
      },
      "cell_type": "code",
      "source": "field_name # 属性データの項目",
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": "['KEN', 'SICHO', 'GUN', 'SEIREI', 'SIKUCHOSON', 'JCODE', 'P_NUM', 'H_NUM']"
          },
          "metadata": {},
          "execution_count": 7
        }
      ]
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": false,
        "ExecuteTime": {
          "start_time": "2017-01-22T19:21:33.461941",
          "end_time": "2017-01-22T19:21:33.539896"
        },
        "scrolled": false
      },
      "cell_type": "code",
      "source": "#　ポリゴンデータ（1行が1つの市区町村に対応）\nsr_points.head(5)",
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": "                                                AXIS\n0  [(141.389636, 43.068598000000065), (141.387047...\n1  [(141.405346, 43.18949900000007), (141.4073640...\n2  [(141.4493920000001, 43.162633000000085), (141...\n3  [(141.47346200000004, 43.096119000000044), (14...\n4  [(141.43406900000002, 43.026091000000065), (14...",
            "text/html": "<div>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>AXIS</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>[(141.389636, 43.068598000000065), (141.387047...</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>[(141.405346, 43.18949900000007), (141.4073640...</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>[(141.4493920000001, 43.162633000000085), (141...</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>[(141.47346200000004, 43.096119000000044), (14...</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>[(141.43406900000002, 43.026091000000065), (14...</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
          },
          "metadata": {},
          "execution_count": 8
        }
      ]
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": false,
        "ExecuteTime": {
          "start_time": "2017-01-22T19:21:33.540924",
          "end_time": "2017-01-22T19:21:33.550003"
        }
      },
      "cell_type": "code",
      "source": "# 分割点のリスト\nsr_parts.head(15)",
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": "                                                PARTS\n0                                                 [0]\n1                                                 [0]\n2                                                 [0]\n3                                                 [0]\n4                                                 [0]\n5                                                 [0]\n6                                                 [0]\n7                                                 [0]\n8                                                 [0]\n9                                                 [0]\n10  [0, 1549, 1553, 1557, 1562, 1567, 1571, 1576, ...\n11  [0, 8, 13, 17, 21, 25, 29, 34, 1071, 1075, 107...\n12                                                [0]\n13  [0, 664, 675, 680, 686, 693, 700, 712, 716, 72...\n14  [0, 1672, 2599, 2604, 2609, 2615, 2619, 2623, ...",
            "text/html": "<div>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>PARTS</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>[0]</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>[0]</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>[0]</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>[0]</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>[0]</td>\n    </tr>\n    <tr>\n      <th>5</th>\n      <td>[0]</td>\n    </tr>\n    <tr>\n      <th>6</th>\n      <td>[0]</td>\n    </tr>\n    <tr>\n      <th>7</th>\n      <td>[0]</td>\n    </tr>\n    <tr>\n      <th>8</th>\n      <td>[0]</td>\n    </tr>\n    <tr>\n      <th>9</th>\n      <td>[0]</td>\n    </tr>\n    <tr>\n      <th>10</th>\n      <td>[0, 1549, 1553, 1557, 1562, 1567, 1571, 1576, ...</td>\n    </tr>\n    <tr>\n      <th>11</th>\n      <td>[0, 8, 13, 17, 21, 25, 29, 34, 1071, 1075, 107...</td>\n    </tr>\n    <tr>\n      <th>12</th>\n      <td>[0]</td>\n    </tr>\n    <tr>\n      <th>13</th>\n      <td>[0, 664, 675, 680, 686, 693, 700, 712, 716, 72...</td>\n    </tr>\n    <tr>\n      <th>14</th>\n      <td>[0, 1672, 2599, 2604, 2609, 2615, 2619, 2623, ...</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
          },
          "metadata": {},
          "execution_count": 9
        }
      ]
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "## Dataframeに統合"
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "これらをPandasのDataframeとしてまとめます。この段階で点列と分割点のリストからMatplotlibのPolygonオブジェクトを作り、その列をDataframe内に作っておいてしまいます。（少し計算に時間がかかるかも）  "
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": false,
        "ExecuteTime": {
          "start_time": "2017-01-22T19:21:33.551553",
          "end_time": "2017-01-22T19:21:35.840199"
        }
      },
      "cell_type": "code",
      "source": "# Dataframeでまとめる\ndf = pd.DataFrame(records).rename(\n            columns = list_to_dict(field_name)\n        )[[\"KEN\", \"SEIREI\", \"SIKUCHOSON\",\"JCODE\",\"P_NUM\"]].assign(\n            # 空白の数値データを0で埋める\n            P_NUM = lambda df: df[\"P_NUM\"].apply(lambda x: 0 if isinstance(x, str) else x),\n        ).applymap(\n            # 文字列のスペースを消去\n            lambda x: x.strip() if isinstance(x, str) else x\n        ).applymap(\n            # 文字数ゼロをNaNにする\n            lambda x: np.nan if x == \"\" else x\n        ).join(\n            # ポリゴンと分割点を統合\n            [sr_points, sr_parts]\n        ).assign(\n            # MatplotlibのPolygonオブジェクトのインスタンスの列をつくる\n            POLYGON = lambda df: df[[\"AXIS\", \"PARTS\"]].apply(lambda x: make_polygons(x), axis=1)\n        ).drop(\n            # いらなくなったポリゴンと分割点を除去\n            [\"AXIS\", \"PARTS\"], axis=1\n        )",
      "execution_count": 10,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": false,
        "ExecuteTime": {
          "start_time": "2017-01-22T19:21:35.841190",
          "end_time": "2017-01-22T19:21:35.854702"
        },
        "scrolled": false
      },
      "cell_type": "code",
      "source": "# データの確認。札幌市が区ごとに別のデータになっているのが分かる。\ndf.head(10)",
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": "   KEN SEIREI SIKUCHOSON  JCODE     P_NUM                         POLYGON\n0  北海道    札幌市        中央区  01101  220189.0   [Poly((141.39, 43.0686) ...)]\n1  北海道    札幌市         北区  01102  278781.0  [Poly((141.405, 43.1895) ...)]\n2  北海道    札幌市         東区  01103  255873.0  [Poly((141.449, 43.1626) ...)]\n3  北海道    札幌市        白石区  01104  204259.0  [Poly((141.473, 43.0961) ...)]\n4  北海道    札幌市        豊平区  01105  212118.0  [Poly((141.434, 43.0261) ...)]\n5  北海道    札幌市         南区  01106  146341.0  [Poly((141.164, 43.0851) ...)]\n6  北海道    札幌市         西区  01107  211229.0  [Poly((141.328, 43.0861) ...)]\n7  北海道    札幌市        厚別区  01108  128492.0  [Poly((141.473, 43.0961) ...)]\n8  北海道    札幌市        手稲区  01109  139644.0  [Poly((141.283, 43.1336) ...)]\n9  北海道    札幌市        清田区  01110  116619.0  [Poly((141.444, 43.0223) ...)]",
            "text/html": "<div>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>KEN</th>\n      <th>SEIREI</th>\n      <th>SIKUCHOSON</th>\n      <th>JCODE</th>\n      <th>P_NUM</th>\n      <th>POLYGON</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>北海道</td>\n      <td>札幌市</td>\n      <td>中央区</td>\n      <td>01101</td>\n      <td>220189.0</td>\n      <td>[Poly((141.39, 43.0686) ...)]</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>北海道</td>\n      <td>札幌市</td>\n      <td>北区</td>\n      <td>01102</td>\n      <td>278781.0</td>\n      <td>[Poly((141.405, 43.1895) ...)]</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>北海道</td>\n      <td>札幌市</td>\n      <td>東区</td>\n      <td>01103</td>\n      <td>255873.0</td>\n      <td>[Poly((141.449, 43.1626) ...)]</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>北海道</td>\n      <td>札幌市</td>\n      <td>白石区</td>\n      <td>01104</td>\n      <td>204259.0</td>\n      <td>[Poly((141.473, 43.0961) ...)]</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>北海道</td>\n      <td>札幌市</td>\n      <td>豊平区</td>\n      <td>01105</td>\n      <td>212118.0</td>\n      <td>[Poly((141.434, 43.0261) ...)]</td>\n    </tr>\n    <tr>\n      <th>5</th>\n      <td>北海道</td>\n      <td>札幌市</td>\n      <td>南区</td>\n      <td>01106</td>\n      <td>146341.0</td>\n      <td>[Poly((141.164, 43.0851) ...)]</td>\n    </tr>\n    <tr>\n      <th>6</th>\n      <td>北海道</td>\n      <td>札幌市</td>\n      <td>西区</td>\n      <td>01107</td>\n      <td>211229.0</td>\n      <td>[Poly((141.328, 43.0861) ...)]</td>\n    </tr>\n    <tr>\n      <th>7</th>\n      <td>北海道</td>\n      <td>札幌市</td>\n      <td>厚別区</td>\n      <td>01108</td>\n      <td>128492.0</td>\n      <td>[Poly((141.473, 43.0961) ...)]</td>\n    </tr>\n    <tr>\n      <th>8</th>\n      <td>北海道</td>\n      <td>札幌市</td>\n      <td>手稲区</td>\n      <td>01109</td>\n      <td>139644.0</td>\n      <td>[Poly((141.283, 43.1336) ...)]</td>\n    </tr>\n    <tr>\n      <th>9</th>\n      <td>北海道</td>\n      <td>札幌市</td>\n      <td>清田区</td>\n      <td>01110</td>\n      <td>116619.0</td>\n      <td>[Poly((141.444, 43.0223) ...)]</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
          },
          "metadata": {},
          "execution_count": 11
        }
      ]
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "政令指定都市は区としてバラバラの行として登録されています。今回はこれを統合して集計することにします。  （例：札幌市はそれぞれ北区、西区etc..として領域も人口もバラバラに登録されているが、これを札幌市1つとして統合）ちなみに東京の特別区（23区）は最初から市町村として入っているので、そのままになります。"
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": false,
        "ExecuteTime": {
          "start_time": "2017-01-22T19:21:35.856412",
          "end_time": "2017-01-22T19:21:35.861409"
        }
      },
      "cell_type": "code",
      "source": "# 政令指定都市一覧\ndf[\"SEIREI\"].dropna().unique()",
      "execution_count": 12,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": "array(['札幌市', '仙台市', 'さいたま市', '千葉市', '横浜市', '川崎市', '相模原市', '新潟市', '静岡市',\n       '浜松市', '名古屋市', '京都市', '大阪市', '堺市', '神戸市', '岡山市', '広島市', '北九州市',\n       '福岡市', '熊本市'], dtype=object)"
          },
          "metadata": {},
          "execution_count": 12
        }
      ]
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": false,
        "ExecuteTime": {
          "start_time": "2017-01-22T19:21:35.862387",
          "end_time": "2017-01-22T19:21:35.886047"
        }
      },
      "cell_type": "code",
      "source": "df_agg = df.drop(\n                df.ix[df[\"SEIREI\"].notnull()].index  # 政令指定都市である地域を削除\n            ).append(\n                # 政令指定都市を統合したデータを追加\n                df.groupby([\"KEN\",\"SEIREI\"]).agg(\n                    {\"P_NUM\": np.sum ,\n                     \"POLYGON\": list_combine,\n                     \"JCODE\": lambda sr: sr.iloc[0]}\n            ).reset_index().assign(\n                # ポリゴンデータも統合\n                POLYGON = lambda df: df[\"POLYGON\"].apply(list).apply(list_flatten)\n            )\n        ).drop(\"SEIREI\", axis=1).sort_values(\"JCODE\").reset_index(drop=True)",
      "execution_count": 13,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": false,
        "ExecuteTime": {
          "start_time": "2017-01-22T19:21:35.887702",
          "end_time": "2017-01-22T19:21:35.905389"
        },
        "scrolled": false
      },
      "cell_type": "code",
      "source": "# 札幌市をまとめた。（SIKUCHOSONがNaNになってしまってはいるが）\ndf_agg.head(10)",
      "execution_count": 14,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": "   JCODE  KEN                                            POLYGON      P_NUM  \\\n0  01101  北海道  [Poly((141.39, 43.0686) ...), Poly((141.405, 4...  1913545.0   \n1  01202  北海道  [Poly((140.865, 42.0094) ...), Poly((140.935, ...   279127.0   \n2  01203  北海道  [Poly((141.01, 43.2417) ...), Poly((140.987, 4...   131928.0   \n3  01204  北海道                     [Poly((142.432, 43.9473) ...)]   347095.0   \n4  01205  北海道  [Poly((140.99, 42.4373) ...), Poly((140.944, 4...    94535.0   \n5  01206  北海道  [Poly((144.222, 43.5211) ...), Poly((143.77, 4...   181169.0   \n6  01207  北海道                     [Poly((143.147, 42.9507) ...)]   168057.0   \n7  01208  北海道                     [Poly((143.776, 44.1847) ...)]   125689.0   \n8  01209  北海道                     [Poly((142.279, 43.2253) ...)]    10922.0   \n9  01210  北海道                     [Poly((141.694, 43.3315) ...)]    90145.0   \n\n  SIKUCHOSON  \n0        NaN  \n1        函館市  \n2        小樽市  \n3        旭川市  \n4        室蘭市  \n5        釧路市  \n6        帯広市  \n7        北見市  \n8        夕張市  \n9       岩見沢市  ",
            "text/html": "<div>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>JCODE</th>\n      <th>KEN</th>\n      <th>POLYGON</th>\n      <th>P_NUM</th>\n      <th>SIKUCHOSON</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>01101</td>\n      <td>北海道</td>\n      <td>[Poly((141.39, 43.0686) ...), Poly((141.405, 4...</td>\n      <td>1913545.0</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>01202</td>\n      <td>北海道</td>\n      <td>[Poly((140.865, 42.0094) ...), Poly((140.935, ...</td>\n      <td>279127.0</td>\n      <td>函館市</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>01203</td>\n      <td>北海道</td>\n      <td>[Poly((141.01, 43.2417) ...), Poly((140.987, 4...</td>\n      <td>131928.0</td>\n      <td>小樽市</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>01204</td>\n      <td>北海道</td>\n      <td>[Poly((142.432, 43.9473) ...)]</td>\n      <td>347095.0</td>\n      <td>旭川市</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>01205</td>\n      <td>北海道</td>\n      <td>[Poly((140.99, 42.4373) ...), Poly((140.944, 4...</td>\n      <td>94535.0</td>\n      <td>室蘭市</td>\n    </tr>\n    <tr>\n      <th>5</th>\n      <td>01206</td>\n      <td>北海道</td>\n      <td>[Poly((144.222, 43.5211) ...), Poly((143.77, 4...</td>\n      <td>181169.0</td>\n      <td>釧路市</td>\n    </tr>\n    <tr>\n      <th>6</th>\n      <td>01207</td>\n      <td>北海道</td>\n      <td>[Poly((143.147, 42.9507) ...)]</td>\n      <td>168057.0</td>\n      <td>帯広市</td>\n    </tr>\n    <tr>\n      <th>7</th>\n      <td>01208</td>\n      <td>北海道</td>\n      <td>[Poly((143.776, 44.1847) ...)]</td>\n      <td>125689.0</td>\n      <td>北見市</td>\n    </tr>\n    <tr>\n      <th>8</th>\n      <td>01209</td>\n      <td>北海道</td>\n      <td>[Poly((142.279, 43.2253) ...)]</td>\n      <td>10922.0</td>\n      <td>夕張市</td>\n    </tr>\n    <tr>\n      <th>9</th>\n      <td>01210</td>\n      <td>北海道</td>\n      <td>[Poly((141.694, 43.3315) ...)]</td>\n      <td>90145.0</td>\n      <td>岩見沢市</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
          },
          "metadata": {},
          "execution_count": 14
        }
      ]
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "## 人口で塗り分け"
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "人口2分割を今回は冒頭の図と同じく北海道でやってみます。  \nなお、地域の分割の方法は単純に人口の多い市区町村から順に塗っていくものとします。"
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": true,
        "ExecuteTime": {
          "start_time": "2017-01-22T19:21:35.906714",
          "end_time": "2017-01-22T19:21:35.914675"
        }
      },
      "cell_type": "code",
      "source": "def make_majority_index(df):\n    half_total_P_NUM = df.query(\"KEN == @prefecture\")[\"P_NUM\"].sum() / 2  # 県の人口の半分\n    max_index = df.query(\"KEN == @prefecture\")[\"P_NUM\"].idxmax()  # 最大の人口を抱える市区町村のインデックス\n    # 人口の多い地区を上から順番に、人口の半分を超えるまで選択する\n    majority_index = df.query(\"KEN == @prefecture\").sort_values(\n        \"P_NUM\", ascending=False).assign(\n            cum_P_NUM=lambda df: df[\"P_NUM\"].cumsum()).query(\n                \"cum_P_NUM < @half_total_P_NUM\").index\n    if majority_index.size == 0:\n        # 1つの地域だけで半分を超えた場合はその最大地域を採用\n        majority_index = [max_index]\n    return majority_index",
      "execution_count": 15,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": false,
        "ExecuteTime": {
          "start_time": "2017-01-22T19:21:35.916115",
          "end_time": "2017-01-22T19:21:35.934573"
        }
      },
      "cell_type": "code",
      "source": "prefecture = \"北海道\"\nmajority_index = make_majority_index(df_agg)  # 人口が多い方(分割で赤く塗る方)の市区町村のインデックスの列",
      "execution_count": 16,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": false,
        "ExecuteTime": {
          "start_time": "2017-01-22T19:21:35.937342",
          "end_time": "2017-01-22T19:21:35.961486"
        }
      },
      "cell_type": "code",
      "source": "# 県人口の半数を占める市町村\ndf_agg.query(\"index in @majority_index\")",
      "execution_count": 17,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": "   JCODE  KEN                                            POLYGON      P_NUM  \\\n0  01101  北海道  [Poly((141.39, 43.0686) ...), Poly((141.405, 4...  1913545.0   \n1  01202  北海道  [Poly((140.865, 42.0094) ...), Poly((140.935, ...   279127.0   \n3  01204  北海道                     [Poly((142.432, 43.9473) ...)]   347095.0   \n5  01206  北海道  [Poly((144.222, 43.5211) ...), Poly((143.77, 4...   181169.0   \n\n  SIKUCHOSON  \n0        NaN  \n1        函館市  \n3        旭川市  \n5        釧路市  ",
            "text/html": "<div>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>JCODE</th>\n      <th>KEN</th>\n      <th>POLYGON</th>\n      <th>P_NUM</th>\n      <th>SIKUCHOSON</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>01101</td>\n      <td>北海道</td>\n      <td>[Poly((141.39, 43.0686) ...), Poly((141.405, 4...</td>\n      <td>1913545.0</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>01202</td>\n      <td>北海道</td>\n      <td>[Poly((140.865, 42.0094) ...), Poly((140.935, ...</td>\n      <td>279127.0</td>\n      <td>函館市</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>01204</td>\n      <td>北海道</td>\n      <td>[Poly((142.432, 43.9473) ...)]</td>\n      <td>347095.0</td>\n      <td>旭川市</td>\n    </tr>\n    <tr>\n      <th>5</th>\n      <td>01206</td>\n      <td>北海道</td>\n      <td>[Poly((144.222, 43.5211) ...), Poly((143.77, 4...</td>\n      <td>181169.0</td>\n      <td>釧路市</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
          },
          "metadata": {},
          "execution_count": 17
        }
      ]
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": false,
        "ExecuteTime": {
          "start_time": "2017-01-22T19:21:35.963125",
          "end_time": "2017-01-22T19:21:35.970750"
        }
      },
      "cell_type": "code",
      "source": "# 上で選択したmajority_indexを用いてPolygonの塗り分けを選ぶ\nPolygon_red = df_agg.query(\"index in @majority_index\")[\"POLYGON\"]\nPolygon_blue = df_agg.query(\"KEN == @prefecture and not index in @majority_index\")[\"POLYGON\"]",
      "execution_count": 18,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": false,
        "ExecuteTime": {
          "start_time": "2017-01-22T19:21:35.972790",
          "end_time": "2017-01-22T19:21:36.500035"
        }
      },
      "cell_type": "code",
      "source": "# プロット\nwith sns.axes_style('white'):\n    fig = plt.figure(figsize=(15,10))\n    ax = fig.add_subplot(111)\n\n    ax.add_collection(PatchCollection(list_flatten(Polygon_red.tolist()), facecolor=\"red\", edgecolor='k', linewidths=.2))\n    ax.add_collection(PatchCollection(list_flatten(Polygon_blue.tolist()), facecolor=\"blue\", edgecolor='k', linewidths=.2))\n    ax.tick_params(axis='x', which='both', top='off', bottom='off', labelbottom='off')\n    ax.tick_params(axis='y', which='both', left='off', right='off', labelleft='off')\n    ax.set_aspect('auto')\n    ax.autoscale_view()\n    plt.show()",
      "execution_count": 19,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": "<matplotlib.figure.Figure at 0x1180df2b0>",
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAA1MAAAIuCAYAAABac1I3AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAIABJREFUeJzs3XeAVNX58PHvtO2990YvAkqTroIiNkDEBgo2jMSub+yx\nxJjkpyTGWCOoGBABkSIK2Oi997q9951tU3Zn5v1j6WyZmZ3Z2WGfzz9m7z3l2STO7HPvOc9RWCwW\nC0IIIYQQQgghbKJ0dQBCCCGEEEII4Y4kmRJCCCGEEEIIO0gyJYQQQgghhBB2kGRKCCGEEEIIIewg\nyZQQQgghhBBC2EHd1A29Xs+hQ4cIDw9HpVK1ZUxCCCGEEEII4XImk4ni4mJ69+6Nl5fXJfebTKYO\nHTrElClTnBqcEEIIIYQQQrR38+fPZ8CAAZdcbzKZCg8PP9sxKirKeZEJIYQQQgghRDtUUFDAlClT\nzuZGF2symTqztC8qKoq4uDjnRCeEEEIIIYQQ7VxT256kAIUQQgghhBBC2EGSKSGEEEIIIYSwgyRT\nQgghhBBCCGEHSaaEEEIIIYQQwg6STAkhhBBCCCGEHSSZEkIIIYQQQgg7SDIlhBBCCCGEEHaQZEoI\nIYQQQggh7CDJlBBCCCGEEELYQZIpIYQQQgghhLCDJFNCCCGEEEIIYQdJpoQQQgghhBDCDpJMCSGE\nEEIIIYQdJJkSQgghhBBCCDtIMiWEEEIIIYQQdpBkSgghhBBCCCHsIMmUEEIIIYQQQthBkikhhBBC\nCCGEsIMkU0IIIYQQQghhB0mmhBBCCCGEEMIOkkwJIYQQQgghhB0kmRJCCCGEEEI4XHFxKUajEYD8\n/EIXR+McalcHIIQQQgghhLi85OcX88ILP5OVFU99vZ7ycgsTJwZSUwM33+yHh4eZkSP7uDrMVpNk\nSgghhBBCCGGXQ4eO0bt3dyorq9iw4SBHjug4cMCbH34IoLLyHs5fCHfkSMM/33+/msTE/bz44g4m\nTepKeHiQa4J3AEmmhBBCCCGEEDb76qtdvP12NV26lHLkiJGsrEGArxU9/cjMHMZjj8H//reTd98N\nY+jQZGeH6xSSTAnRAdTW6tDpDPj6emEymfH19XF1SEIIIYRwY8XFWt5/X0Fq6jWkpto/zpYtA3n5\n5V9ZuTISPz/3+/tEClAIcZnLzy/jgw/28cYb+0hO/pLJk5/FbDa7OiwhhBBCuLETJ3LYv7+rQ8Za\nv340TzyxySFjtTV5MyXEZWzbtoNMnXqC1NRJp69cw6pVev71r50899xgl8YmhBBCCPe1Z08h0MtB\noymYP78nTz55giuvdEyC1lbkzZRwS2lpWa4OwS1s2FB2XiJ1hhe//KJzSTxCCCGEcG+7dh3l00/X\n85e/xDp0XD+/Mrp1i3fomG1B3kwJt5SSkuDqENq977/fy+uvd2703tGj1mwOFUIIIYQAg8HIwoW7\nyc83sH27mqVLRzl8jtBQHT4+3g4f19kkmRJuyWAwkp9fSFKS+z3BaCtlZdXo9Vc2cS+ErKxiEhLC\n2zgqIYQQQribt95ayzvvjAFUTprBQq9eWYD7bUGQZX7CLX3xxUJee+0jV4fRrv3+e9MfeNXVnfjj\nH49gNNa1YURCCCGEcDcWi4Uff/TEWYmUUlnO5Mm/M3fujU4Z39kkmRJu6bHH7uORR253dRjtWkVF\nUbP3V64cwZNPumflHCGEEEK0jbff3sz+/QOdMLKOAQO2sWxZLosWjSYw0N8JczifJFPCLZlMJh58\n8HXKyysuuP7qq99x6lSOi6JqX664oqXTxJXMnt2fG29cy+7dJ9skJiGEEEK4j717M1mxwhvrDuK1\nhZH33tvEjh2DufXW3g4eu21JMiXckkql4p57pvP00/MvuF5RoeGOO46j1xtcFFnr6PV65sz5pdXj\n1NbqWb265Q8+kymANWuuZehQb9atO9bqeYUQQgjh3sxmM7/8soeJEz/m3ntz2bWrv8PnSEw8xFNP\nXYtCoXD42G1NkinhlvLyCjl0KJu1a6/i1Kncs9cjInzYv/8avv12rwujs196egkvvujNwoXbWjXO\nxx/v4cCBAVa3Nxrj2LmzslVzCiGEEKKBxWLBYrG4Ogy76HR6pk2rYNmymRw7NtQpc8TFmVGrL486\neJJMCbcUHR3BX/86icmTdYwdm8WMGTu59dat/PWvVwEqfvrJPd9MLV6cT0nJcJ54woO0tEK7xvj9\n95O8+24UYNvTnpUrFaSlNb/PSgghhBDNO3WqkHHjNvDAA7+xaZP7LaN/55015Oc7vvT5+bRa90w0\nGyPJlHBLCoWCnj2TmTXrOuLjVXz++UBWrhyC0RgKwJo1IezcedzFUdruwIGGfxYXX8UHHxzHbDbb\n1H/p0kPce6+KoqIUm+fesKE7WVkFNvcTQgghRIPiYi13353FmjWjmDt3DE8/XUZaWr5bVM/NzS3g\n7be/4733+uO8EugNjh7tyogRy6iqqnHqPG1Bkinh1v72t685fPjS6i8pKbvo18/2hMLVas77TPni\nCw+WLPn1kjbZ2Ze+scrMLOLRRzdxzz2RFBba+3v7sW+f+3+oCSGEEK7y8cdH2b37XOW73bsHM2DA\nIcrK2v9S+kcf/Z3XXhuP0Zjg9LlMpkA2bbqNnj03kp/v3qtiJJkSbi0xMRiD4dIPqNGjE9BoNC6I\nqHWMxnNL8wICjrN48SZ+/nnn2WsWi4Vx475n9uyNbNlymPnzdzJjxjYGDtTy3/8Ox2BozSG8Cv7z\nnwDS0937Q00IIYRwhaKiCr75xueS69XVXQHbVpq0tVWrDrNp01CgLf92UpKTM5a3397ttvvLAC6P\nnV+iw9q6tZCqqpsuuV5b6+mCaFovOvrch0lu7j0sX57Br78W8Ze//ABE8dtvRg4ffoBHHvEA9IA3\ntu6Nak5aWi9uvPFJ1q59g5iYEIeNK4QQQlzONmw4ybRpWjIyLi3+VFcXz+bNe5g0qTUPPJ1r9uxs\ntFpXHJqr4OOPryE0dAVvvTXeBfO3nryZEm6tV69A1OriS67X1WW0fTAOkJJSCZxJqDwwGrtSXj6c\nxx+/lccfH8jSpcMALxr+1fXBkYnUGbW1V3PDDVmsX3/K4WMLIYQQlxuLxcL8+dmNJlINlLz3XiU6\nnb5N47LF5MlxeHm5amWKN8eOXfpGz11IMiXc2g8/HKO+PuCS6wpFpAuiab3nn7+a5OR9Lowglaqq\nBA4f7sf48V786U+/U1VV68J4hBBCiPbt118PMXduYrNtwsPVeHm1z1Uzqan5REaCxWJyUQQFdOtW\n5aK5W0+SKeHWunaNorH1vceOlbR9MA4QEODLO++YUSq1bT53TMw84uI2o9UOAUCrjePdd69l6tQd\nVFRUt3k8QgghhDv4/PMaDIZOzbY5dMgfo9HYRhHZZubMw4wf74XBEO2S+fv338ybb05wydyOIMmU\ncGsvv3w7UVFfXXI9ICCw7YNxkLvv7k98fFueS2HE23s+KlUAOTn3c2E5VAUrVlzDddcdY8OGc8v+\n3HmjqBBCCOEoWm0lq1dfWlX4YunpPdiwof0d2bJ//wlOndJRVdXZJfN7epbw3HPRKJXum5K4b+RC\nAOHhoVx/ffAl1z08HL+XqK3U1NRSXu7t9Hn8/H4jPv5LQkM3oNPdQnb2bU223bt3ALfd5sVbb23G\nbDZfFudCCCGEEK0VGBjAsGHWrN7wYsmS9rds/u23C8jOHuSi2Q2MH7+We+4Z6qL5HUOSKeH2EhMv\n/cM+Pt5935ysXn2MysquTp0jNPQnzOZksrOnU1o6Bmj5TZ5WG8frrw/ipps2YDS6al21EEII0b54\ne1v3AHfhwigOHsx2cjTWWbfuMLfc8hNLllxJXZ1r9pl7eZUwfXqyS+Z2JEmmhNsbNKgTGk3a2Z+j\nojbw0EPdXBhR63z7rQFnn/MQFFRPbW0KtlcD1LBmzTWMGPEzWVmXHh4shBBCdDTl5dZ9l1ZUJHHb\nbakcPZrj5Iha9vbbBfz4401YLC0vUWyeCSgHQKksBGqBLLy89hARsQsvr/RG+lTSs+daQkIOEhR0\n6eoidyPnTAm3N3hwN7y8dlNXlwJAaWk0Pj7ts2JOS1avPsry5V2cPo/ZrKXhA1DVUtNGHTs2mSee\nWM/y5e5ZNVEIIYRwlD59LKxbZ13bqCgNlZWuK5FuNpuZNWsxhYVRrRiljn79vmHs2DgMhgrGj+9K\nSUkqycl+ZGdncsUVYfj7xxMeHsbJkzm89tpmVq7sDJh5+OFU7rorlCFDrqGsrILQUEmmhHC5iIhw\nhg/PZtUqC6Cgrq4L3333My++GOfq0GxSVlbFCy/UUlcX5vS50tPHEh29k/z8q+0e48cf+7Js2UEm\nTLjCgZEJIYQQ7sXX1/qFXjqdF926RTgxmqbt35/Kn/+8kxUrbsa+FTAmfHwyGDBgLcuW3UVw8KVv\ntfr3v/Dnrl3jWbgwnuXLjxAcrGbkyOFn710OiRTIMj9xmXj33Wvo0eP70z8ZiY11r39Bly1bx8MP\n7+HAgf4tN3aICLy981s1gskUxJ//XIdWK2XThRBCdFxXXGECrDsnaf/+q/jgg13ODegiBw/mMmnS\nFgYP9mXFirsAf8DLhhHqSUjYzEcf7WTrVhW//Ta90USqOePH92TkSOfuB3cVSabEZaFXry7079+Q\nHERH/8ydd/ZxcUS28fdXs2pV271JCwnZQGlp31aPc/DgVTz55FYHRCSEEEK4p1tv7U1y8l4rWysw\nGlu7T8l6Bw+e4oYbCvn++6EYDFHYuldaoajm+uvnceTIlcyceTV9+iShVsvCtvNJMiUuG/fcMxgw\nMHKkBk9P99ozNXr0cKKiyttsPk/PLWi1jqmgM2/eIObO3eOQsYQQQgh34+fnywMPeFjdPi+vbSoO\nGwxGbrttJwUFV9rVPzz8BA888BM//zwdX18fB0d3+ZBkSlwWzGYzs2cfBjxRKoNcHY7NcnKKKChw\n/l6pM/Lz76dTp4XExf3W6rHM5kBefDGAgwddX51ICCGEcIXaWuvf+Gzb5se7765zXjCAVlvNe+/t\noqDgWmyv3AtqdQH/93/5zJlzp+ODu8xIMiUuC0ajkdRUJWBBo6lwdTg2W7gwDb0+qQ1njCE19W6U\nyhKHjFZQ0JmnnkrFbDY7ZDwhhBDCnRw/Xm9126NHezJ3bgGbN590aAwGg5ElS/bw4IPb6NYtg1df\nHYJeb2vVPiODBq3g888zmD59lEPju1zJokdxWfDy8mL+/NFs2bKZIUN6uTocmxgMRubPt/a5hp7o\n6B9QKLLIy3uG1j4Pqa01ADrAu1XjAKxdO5THHlvAZ59NafVYQgghhDtRqaxf5gdw+PDdLFnyO0OH\ndkahsP3NEUB9fT1btx5jxw4du3bB5s0asrOvoDVnVSYkHGHGDH+mT7e/2m9HI8mUuGz07h1L796x\nNvcrKSkjLCzECRFZ55VXtrN37zCr2sbHf0129mT8/E4C1UBAq+b28VHjiESqgYbvvx/K44/ncMUV\n7lWWXgghhGiNqKhqvLwybFpl8q9/DWH79h1cf72CwYM9GDasEwEBlxanqK+vJzMzj/z8Kg4erOX4\ncQtHjyo4ckRFTk43wLfV8fv75xEUVEJ1tZGRIxNaPV5HIsmU6LAMBiNTp77E5s3juO++Sl555QYC\nAvzaNIalS4/wySedsfYNk4dHCBBMdXVfoqLmUVDwUKvmz8kZRkLCXLKyprVqnDNKSpJ55plNrFkT\njUpl34HAQgghhLv5z3+uxWD4jc8/T7KhlzdbtgxmyxaAOnx8UgkJqSYgQIFGY0GpBJ0OiotVlJcH\nYzan4LgHoODpmU9gYAFabSiffFLO8OExrF59AKMx0GFzdASSTIkOa86c71m6dCom05X83/9Z2L79\nW6ZP92b69AltMn9RUQUvvFBHbW20Ve01mi1kZw85/ZMnnp4egJnWLPUzmxMdXuL0t9+u5m9/28ar\nr1r3tk0IIYRwd2azmX37WvNAVkNtbXdqax0WUjMsDBq0gTffjGTkyB7s2nWckSMbjkt59NHRbRHA\nZUUKUIgO6a231vPJJ10xmc6UC1WwceM1KJU+rFy5l6ysEtas2eHUGJ577hAnTzZ21pOZhIQFdOq0\niqSkZSQnf4OHx1YiIrZTV3fuX9mSkqEEBq5oZRQVaLWOe8rVQM177yWwceMpB48rhBBCtE9vv72N\nnTuvcnUYVrnhht9Yv/5qbryxOz4+XmcTKWEfeTMlOpxt2w7x5pudMZsv3F9lNkczbVoooKBz50Pk\n5XmxZMlubryxv1PiSE1t6vRxPVptJ7TaQWevBAfvIjf3mQtahYb+TFbWIzbOmoO39w5ASUSEF0aj\nGovF8SXNtdp4Hn98F+vWVdl8SroQQgjhbkwmM60p/OA8pYA3Pj6nGDOmkltuMdGzZzReXu51Hmd7\nJsmU6FDWrNnLtGkH8PEZRnV1Yy0aqvGcOtXwxuqFF3aTlrabmTMdn1D5NHL+nUKRTkrKTjIybrjg\nenn5gEZGSKahEp+1yUotiYnbyMy8DqgjMzMSsBAff8KmuK114MAApk1by9KlI2X/lBBCiMvK5s2H\nSUyMJC4ujH37svj222BXh3RWdPRR7r5bi79/ERMn9qSmJp+ePRMICgq0u3KgaJokU6JD+eKLPAoL\npxEdPZ+AgJNotRHU1PQDGv9j/8CB/jz1VCmxsQcYP76PQ2PJzr7w55CQ+QQEeJKaat0BeVlZY0lJ\nWUBa2r1oNEcJDMygpGRcE63NJCUtICPjAc6t7rUQGfkj2dm32PsrtOiHH0bw2mtbeOedEU6bQwgh\nhHC2+vp6NmzYTW5uFVu3WpgzpxOdOx/htdcsfPyxBydODGl5EKfTMXXqNv7v//oSHd3D1cF0GJJM\niQ6lS5cCwEJ+/pmzkMqIivofFRVj0OsbL+ddXx/KnDknGD/ecXGYzWbKyhqeDvn6fktkpIqMjFsp\nK7Ol1LmCvLzriIn5NybTcDSaPIKCfqei4rpLWiYmLiIj407O3yYZErKd8vIQwJklUNXMmtWTrl33\nMn36lS03F0IIIdqhTz5Zx5NP9qFhNUjDXuMjR5KZOrUQk8nWg3GdwcTTT6/nn/8cK2+f2pgUoBAd\nyujR/fD3P3TelRAKCqYTE7Ox2X6rVvXku+8cV5BCqVQSFmYGqvH0DCMtbTJms+1nRun1UeTlPUFh\nYX/U6mB0OgtRUV+h0Rw72yYw8E1KSoZy8XLAsrKriYzc3crf5GJF+PpuvuCK0RjKn/4UyI4dGQ6e\nSwghhHCetLRCHntsM5MmbWDePD8gggtLkyvaSSJloV+/TdxwQ4IkUi4gyZToMLTaKv74x7epqbn0\nTUx6+gg6dVrcZHJRXx/IDz9YHBpPv34WwA+NprVJWsO/xtXVSfj6BlNQMJ2kpONn74aE9Gz0dwao\nrLwKjeZQo/fsERX1E56eESQnfwOcq+9aXJzCjBmllJZWOmwuIYQQwpnmzMni00+H8f33I9mx42pX\nh9OIOiZPXs/LL6/g9de9GTeup6sD6pBkmZ/oMAID/XnmmaeZMePSyg8WSxypqZNRq48SELCfyspL\ny4Smpzv22cPAgVX8/vtCPDyCAAPQuso6JSXnSrIajUoSE79HpVJhsZia7KPVDiMi4juKinrbPW9S\n0gIUCjMWixG9fgBlZV0oK+tEQsJv6HQ6iotvAZTs39+f6dNXsmLFzfLkTAghRLuWk1PC4cONVqpq\nF7y9i3juueO8+eYIlEp5N+JKkkyJDsXfX01zL2Tr63sQErKm0WTq0CFP9Ho9Xl5NlTS3zQMPDOQv\nf9kPKPH0LMBgSHTIuACZmbda3baysj8q1QFMJtsLbISHf0V29nhMpourGCnJyroeqCQlZT5paXfh\n57eXffu8ee21Tbz9thSkEEII0T7Nn7+P+fOrWLXqGleH0iiVqpSPP85k+nT5Lm0PJJUVHcr48f3p\n23dhs20UirJGr5eXh1FUVOqwWIKDA+jTx4uioskOTaRspdcnExV12I6e9ahUXo0kUucLIC3tHlJS\nVuLh4U9OzmhmzerOsmWOW1oohBBCONL69XpWrRoBtMdVFLVMnHiUYcMaL5ol2p4kU6JD8fb24pNP\n+uDjk91km7o6gLpG7qjRanUOjWfECLNDx7OXl5c9Bw2qsVjCrWqXlnY7ZWUNa7n1+nCefVZBenqR\nHXMKIYQQzpWRYXR1CI2wEBKyk1GjfmLRomF06RLt6oDEaZJMiQ5nyJDevPtuKlDf6P2cnNEEB19c\niELHyy8folevFIfGMm1aPAEBmQ4d0x7l5ZGA9WvDFYosEhK+RK9Psmu+9PRezJhxHKOxsaRVCCGE\ncI2PPtrF5s3dXR3GeSx07XqIZ5+dy4kTXVm+XEqftzeSTIkO6b77BnLllbuauFtFTc2FS9duvfUb\n3n77Wodv8uzSJYbbbstz6Ji28vA4hcVSAvhZ3UejOYJWeyVabSe75/3112FMmfKz3f2FEEIIR1u+\nvI7a2ghXh3GakUcf/Z033yxj1qzphIYGEhjo33I30aYkmRIdkr+/L8uWdWbKlC0EBl6YzHh7H8Zo\nPLMW2UL37qt58skhTnsSNG1aIAqFa0qGR0ZuxtNzP+XlE23qZzTeiIfHfKA1SyGULFkykk8/bSqp\nFUIIIdrW0KHVQNNVcNuKRlPG5MnL+eST67j77pGuDkc0Q5Ip0WElJIQxb95QnnxyL1Bx9rpCYQZU\nAAQGHmfevBTGjHHe2Q2jR/dg2LCjThu/OYGBFVRVTbKrb3Hxg0RGrmnV/BaLPy+/HMHGjadaNY4Q\nQghxxubNR6isrLGrr0bjh6v/PO7RYx+LFuUxY0asLOlzA1IaXXR4b7wxDo1mMR9+mExR0SCio/WU\nlWXTp88RYmJ09O9/t1PnVygU3H47bNpkoa0rB9XXV7Widw/8/Y9TWNi6GMrLE3jwwUMsW5ZLr16x\nrRtMCCFEh5aTk88jj/xCVFRPxo71oX//QHJzaxk+PIZOnaypgFeO66r4mRk7dj3z5l1FWFigi2IQ\ntpI3U6LDUyqVvPbaXSxYYCEo6EeSk7M4ciSEdevG8803zk2kzpgxow8pKfvbZK7zVVb2IDHxqybv\ne3oWERTU9Fujysp8NJryVsdx6lRvpkwp5NSpglaPJYQQouOKi4tmyZI7CQ2t589/jub66+OZPv0K\n+vQp58iRlgs+6XS+gMX5gTZi0KAtLF8+TBIpNyPJlBCnXXfdYDIzR/LLL38iKiq0Tef29fXmrrsc\nW3bdGiUlfTEaY0hMnAtcvCTCgp/fL3h7L26yf1HRIwQGHnBILPv3X8WkSTnk5TV+zpcQQghhjR49\nolm06EbGjDkOBALeqFTB7NnT9P5ki8XCBx9s5euvY3HNmyktzzwDnp4eLphbtIYkU0KcJyDAdVVy\npk6Nbfb8qwalqFTFLY4VHn6I2NgtNDxdM6NSZRAZuYmAgF2ceeKm0RSTlDQbD49SMjOnEB29iMjI\nz8+OkZS0gNLSceTnP0Jk5OdERLzVyEynMJsd9zFy4MAAHnvsACaT6zf/CiGEcF8KhYLevYPO/lxV\nFcef/+zJiy/u4LPPdrF06S5qa/UArF27l/79f+Cpp64kO7uzC6LV8vnnB7nrrmEumFu0luyZEqKd\n6NkzgYkTtzJ/fnwjd80kJv5IYaEX4eEFKBThZGXd2MRIejw9D5OTM4zQ0DmoVL4UFfWgsLAr3t4b\nSUw8gMViQKn0ICPj4bO98vMfwNd3DgpFAWFheeTmXgmEAFBY+AhhYavQaAqoq4s6G1NIyB7Kyu51\n5H8NrFgxnBdf3Mi7717j0HGFEEJ0LErlhedJpqd35R//OPOThQkT1gE+rFmTiE53ZRtHd06nTqcY\nN667FJtwU5JMCdGOPPRQMAsWVGA2n3uaplaXER//E+nptwM+ZGeDr+93gB7wumSMlJTVpKVNBpSU\nlj58wT2dbhKZzSwZr6l5iNjYWUAidXV3XHCvpGQYCQk/kpV1J6AiMHAZZWW32vurNkPNv//dh+7d\nd/PQQ/2dML4QQojLXVlZBXPnVjTTQsGyZde2WTyNM9Oz525efllBbGyYi2MR9pJlfkK0I9de252R\nI4+f/Tkk5Ajh4etJT58K+Jy9rtcnERb2+yX9g4KOU1AQT2v+1c7NfY7c3DsauRNAVtZ4EhO/BixY\nLDqc9Tymri6EZ5+N4tpr/8vEiS84ZQ4hhBCXr+3b08jPH+fqMJo1ePAGtm/vyZQpA1wdimgFeTMl\nRDtz++2wbp2F+PjtlJWpKCu79EBdk2kA5eUnSUr6GoXCB6hFodBgMvmRmemMt0Vn+JCZOZm4uPcp\nLx8BOGejrIfHFgICytm69Qb+9reW9pEJIYQQF9JqTbTnP3N9fbN57DHw8/N1dSiildrv/8uE6KAe\neOAK/vGP/Vgs6dTU3NNkO5OpCxkZXdowsgY+PhspKxtAbe2VnDnc2NGMxkEoFKsxGJL497+30bfv\nZq67TjbmCiGEsM7evXmuDqEZtbz++jGmTbve1YEIB5BlfkK0M35+PgwevIOcnLGuDqVRtbWj0OsL\n8PA43nJju6kxm40oleVkZt7Fc8/lkJ2dh8XimrM/hBBCuA+LxcKqVe33jc8tt+zm+efHuDoM4SCS\nTAnRDv2//3ctKlV7TRx8iIurxWjs0UK7HOLjF9G582I8PY/aPEtu7o1ERKwDFOzbdyfDhv2ETqe3\nJ2AhhBAdiEKhQK2uc3UYjerTZx8PPxwmlfsuI7LMT4h26OqruzBy5HbWrm3bw4OtERCwgqKiMTR9\nqKEZqCA5eSPp6Q3LFKOiNuPvv5rS0ho0mjp0uhgqK0c2O098/FcUFk46/ZOC0NCe+Ph4O+rXEEII\ncRkLCfF0dQiXUCoruOaaTMaPH+/qUIQDyZspIdqpW2+FMwfstif+/iXo9TFN3o+M/A9+fqmkp999\n9lpBwTBOnryRsrJrKSy8E7U6kk6dFpKYOK+JUfTU1BRjNJ4rFXv0aBRz5vzsqF9DCCHEZcxksieZ\nqickZD9xcbvw9j6Fo7+DQ0P3MWvWzQ4dU7ieJFNCtFPTp/ckIsL25XHOVlDQDZWq8Y29sbHzUKlS\nqK4eSOPNlH72AAAgAElEQVRvrkIAJWVl3UhNvYuamq5Aztm7wcH/A8xERCykrOwxzv+IMhhSOHIk\n5+IBhRBCiAvs3n0Mlarc6vZqdTmTJm1m2bL95OV1Jzt7ABkZIQwcuMMh8fj47OaWWxby0kvFqNWy\nKOxyI/+LCtFOBQf7c/31Vcyf31QLE0lJv6BWGzCZzCgU9ahUanS6etTqCDIyRjklLpNpCHFxq8jJ\niT17LSrqLby8rqaw8Dp0uqbfWl2spKQ/AQELqKycSnLyAnJyriMhYQ5KZQIQcUn7rKwQLBaLrDUX\nQghxib17c1izJoeNG/P57TfrltKFhGTy4Yfl3HPPhRVjIyJCCAtr7TsHC337/sSzzwZw//13tXIs\n0V5JMiVEOzZ+vIb5841ceJ6ThZSUb9Dp1GRkTKSxs566dv3BiVEp0euLaVj+0JDU1NeHk5ExDLC1\nepICHx8tdXW/oNPFUFcXS1bWI022XrZsBFOm/MrXX18rT/eEEEKctXjxAV59tYgTJ6yvkufrm8ec\nOdVMmNCv0ftabWuW+dUwcuSPLFo0msjI9rf/WTiOLPMToh2bOLEP3boduOBaUtIPpKXdTH7+XTR1\naG5xcQC+vs5bEqdWl6NWH8TffyFBQXPQ6W7D9kQKQElx8d2EhqZTUDCoxdb19aEsWHAt//rXFjvm\nEkIIcTlauPAgf/hDgE2JFNTzzDOpTJjQq8kW996rAGrtiMhMp07/YO3aOySR6gAkmRKiHVOr1dxw\ngwmA4OBTJCcvJjOzHxDUbL/y8lFERR1zSkyRkcupqroeDw8/qqpuprr6empqYlvu2ASTKZS8vGFE\nROyysoeaWbM8mTVrMWaz2e55hRBCuL/c3GL+9CcoK0uyqV/nzrt4442hzbaZOXMAzz23C7W6ookW\nFrp1282dd25l9OgVBAS8wY03/j9iYg7y8stXo1TKn9kdgayTEaKdu+02X2bPTsXH5wjp6ZOt7qdS\nOf5MJk/PI3h4KKmp6X32Wn29X6vHVSiUVFWFW92+sHAwK1aUct99ZUREhLXcQQghxGXHZDJx3337\nyMq63ua+11wDKpWq2TYKhYL33htJv377mTUrjX37rjp9x0zPnru5444inn/+Wvz9fQA4caI3CoWS\n6moTV155k80xCfckyZQQ7dzo0b1ISvoHR48+bVM/i8Xxb22Cg/eQnX2nw8c1mRIJCNiBTtfd6j6+\nvoGSSAkhRAf25JPrWbv2Wjt6mrjxRo3VradO7cvYsVpeemkzhYV6brjBjwcf7IOv74VnH3btmmJH\nLMLdSTIlRDunUCgYO3YE1dUrbEpklErH/+ttMilp+rDe1vAhMLCKwkLre6xZcwUPPfQKc+b81Qnx\nCCGEaM+++GIHs2f3xb4/Zc0oFCabeoSHBzJ79rCWG4oORxZzCuEGxo8PxtPG8wfr6soBnUPj8PY2\nANY/zbOFwVBiU3uz2YeysnyysrKdEo8QQoj2aeXKA8ycGYPRaG9xBw1PPx3EggV7HRqX6JgkmRLC\nDYwa1QONJs2mPmlp9xAevoquXX8kJqb11e8iIpZQVOScNeCxsSspKhprY6867r57KgkJ8U6JSQgh\nRPtz5EgOzz1nwmCIa9U42dldmTKlM7GxO/n118MOik50RJJMCeEGFAoFSUkKoNKGXkqKi2/nxImb\nUamOAPWAHk/PPADi47eQmPjZ6bYGPDzymx3Nz8+MXh9pR/QtU6vVNh3228CbefM0WCytOQdECCGE\nu9i8OY1x46o4ceJKh4xnsXgwcaKWgQOTHDKe6JgkmRLCTUyfPpKgoB/t6qvR+BARMRcfn9UkJOwi\nMHAHZWUa6uvr8PM7TkLC14SEfH26tR4wARUoFPn4+h4EoKgoHC+vEw75XS5Ui15vzxlVsHLlIGbN\n2ubgeIQQQrQndXX1/PWvW7jjDjNZWT0cNu6YMbv4z39GExho33eQECDJlBBuY9KkQYSG2nd2VFra\nvej1AdTWTqC8XI1O50lNzUC02kB8fJZjNOrQ6/vQqdMSwsM/JCxsAR4eO4AMTCY9ycnf4e+fQ2jo\nDsCxb4JiYpZQWHi1nb09eeedWNascc6ZWkIIIVxry5ZT3HjjNl599WoKCjo7cORqZs70RaFwRlEl\n0ZFINT8h3IRKpSIiwkxqqn39KysbzqgqKTm376m6+j4iIxeRmtpQJbCikXMJ9XpITx94+qcCoqPX\nkZ9vTynaxphPF9awv6hFeXkCU6akc/vtK/nss5vli1EIIdycxWJh4cJdfPddGb/91pOKiuEOn+MP\nf9jBhAmO+i4THZkkU0K4ES8vx74V8vbORaertaFHFF5eax0aQ3V1QqvHKC1N5osv4I03ComJiXJA\nVEIIIdqaVlvNxx//ztKlvuzcOQTwcco8Gk0J998fJw/fhENIMiWEGxkyZBBrHZjLhIdvIitruk19\nMjOvJjDwIFrtFXbN6el5FH//XBSKOnx8CsnOnmDXOBczmRL4xz9+5d//lmRKCCHczc6daTzwQBGH\nD48FbDwLxEaPPHKMIUMc/7ZLdEyyZ0oIN/KHPwwhOPikw8bLyxtNbOynNvWJijqIXh9h54x6oqP3\nYTbHATFkZk7HbA6yc6yLqZg3L5LaWseerSWEEML5nngik8OHr8bZiRSU8+CD9n6HCXEpSaaEcCPx\n8eEMHFjusPHq68MoLx8AFFndR6OpJCTEvoNy4+PnkJFxO2Vl3Sku7mvXGM0pK+vDJ5/scfi4Qggh\nnMvDw69N5omKyqJ799adUSXE+SSZEsLNDBjQ/BpvjaaEsLAdVo9nsXjg47Pb6vaZmVPx9bU9mQoP\n/4Xi4kk496mjkiVLqp04vhBCCEdLSyskPT3Q6fOoVOW8844JX1/n7MUSHZMkU0K4mauuUtFwDlTj\nIiL2ERycZ/V4UVEHqK293qYY6upsfzumUOxw2qG/59u5czDPP7+J9PRip88lhBCi9b7+OpOcnK5O\nnkXHzJl7mD7dMQf+CnGGJFNCuJkxY7oQEND04bm1tVBRUYG150EplZ7YWotGqfS66IoJT88C/Pxy\nGm0fG7uQ8vJHAedXTqqvD2LWrOG8/PIRp88lhBCicdnZxbz44nreeGMNNTXN72XdssWxlWovZWHG\njM38+9/XSQU/4XBSzU8INxMY6E+3btXs3HnumlJZRGTkYTw8sjAY/CkqGkFQ0D4qKlp+AmcwBNsc\ng1p9/hKJGqKjP6OyshuBgQbCwjZiNIagVB4hJ+cpQInFUkldXZjN87TG2rUxHDqUR+/eMW06rxBC\ndHQrVhzgoYc0lJSMAur48svVvPqqF/feOxxfX+8L2tbW6ti507vxgVqtDlAxZsw63n57gCRSwikk\nmRLCDSUmlpGbux5//1pqa6spLIwiP3/U6bsNL5yDg79GpdJRWjq02bF8fGytfldGcfG5zbvBwRvI\nz58B+FFTc66VSuWLWp1FfX0SHh72H8prr8LCLsycuZ1vv/UkJia0zecXQoiO6vPPdZSU9Dn9k4as\nrFuZMcPC779/x4IFky9ou3jxXioqBjl0fo2mnOnTD3HXXf6UlhoZNeoqwsMdVTlWiAtJMiWEG+rT\nx5PvvhtBcyt109PvJyFhKaWlzY+l15fZOHsA/v7bqKjoibd3Od7eWsrLL63CFBqaQVHRMAAMBj2g\nA5z19LFxGzcO5uuvf+HFF23bEyaEEMJ+/v6qRq4qWLToerp338qf/3w1GzceY+5cLYsXJ+LYP0d1\nvPHGIV5+eYQDxxSiabJnSgg31L9/EM0VoThDrbZmSYOt1fXUZGc/SFDQmwQH7yIv7+5GW9XXGwED\nAOXlnVAqK22cxzF27lRTW6t3ydxCCNER9e3b+PeT2RzEu++m0K/fTkaNiuaLL66mqirWoXNHRBzh\nxReHOXRMIZojyZQQbmj48E74+aW22K6lqnuBgfspKuph8/zh4VupqHidvLzxTbYpK5tAfPwCwsJ2\nExtbidns/Ep+jfn++2t47LGNLplbCCE6onvvTSE+/lij92pqIjlwYBDgnGV3yck1sjdKtClJpoRw\nQwEB/nTpUtViu4KCXvj4HL7gmr//dpKSlpGSMh9f39Xo9VfYPL+fXxHQ0jkdIWRnP4BWa6a62pVn\neihYvLg3u3enuTAGIYToOOLjw3nsMS1BQfYd8G4LtbqE0aM38Npr25k9ezuLFvWUZEq0KdkzJYSb\n6t5dwd69zbcJCEjFYAjH2zsUhaKWkJB95Od3o6pqAgBduizFnmcqarX1e5/q6vwoLw+xeQ5H0umi\n+fzzzfTvn+LSOIQQoqN46aXBeHhs5NdfdwOV7N6dQnHxcAfOYEGtzufrr/Po2zeWnj07OXBsIawn\nyZQQbqpz55bblJaORa0+hb//XnQ6JTk5I4FzJcrr66vtmFlPba3R6tbx8fvJzr7Ljnkc66uvujJy\n5F7uvVcObBRCiLbw3HMjeO65hv+8atU2Dh78lcLCSv75z/FAY0UqrKNQVPL443uYMCGQ664b4Jhg\nhbCTJFNCuKnYWGsOOQyhvn4Q5Y1snfLzO0FOTk+b542P/5ns7Nutbu/hoaItDutticEQziOPmCgv\n380f/9jf1eEIIUSHMm7c1YwbB0ZjHd98c4CCAnsfbBl55JGV/P3vE/HxadsKsUI0RvZMCeGm4uJU\nWFPRrymBgceoq+trYy8LGk0ttjyHKSiIIyTkoI3zOEdtbRSvvRbGb78dd3UoQgjRIXl4aIiIsO+7\nq3PnIyxYsIfXX79OEinRbkgyJYSbuuqqODQa+zf35uYOBHbb1EepLMFiqcPLa4fVfWpqhhAU1D6S\nKYDy8kQmTVKwbt0+V4cihBAdUqVdJ2XUMmNGDnfffTUxMVGODkkIu0kyJYTbsuDnt6kV/SNJTDyE\nt/c2q3uYzeHk5l5PZKRtb3bS0q4jMnKnrQE6jVbblT//WUtOTqGrQxFCiA6luLiMgoJgm/sNGfIT\nzz8vB7CL9keSKSHcmEpl64G751OSmXkfnp6nbOhjJDR0NZmZ99k4VxTe3mU29nGujRtH8ve/H8Ji\nsWbvmRBCCEfYsiUDvT7JytYmQkNX8+abi5kzZ4CUPBftkhSgEMJNRUdH0qNHEhtbcR6tr+9BKipu\nsLp9RMQ28vPvt2sus7mKiIif8fCwUFbWg9raBLvGcRwFH300DIPhR/r0qeSJJ+51cTxCCHH527XL\nhLWV/AYO3Mo33/QhIiKQgABf5wYmhJ3kzZQQbiwqqnVP6Wpq+pCYuMzq9j4+Ouz92MjKuoOioqHk\n5FyPWn2IlJRviI//jNYU0Wg9L2bPvoUNG6LJyMh1YRxCCNExbN5s7WqAWoYOraVz5xhJpES7JsmU\nEG4sqtV7cOupr9db3Vqr7USXLj/g6Wl9AYoL+QFKKitvIi3tXrKzJ5KUtNrOsRznu+9G8corR0lN\nLXB1KEIIcdnasyedLVvirWp75537eO+965wckRCtJ8mUEG4sNLR1/ePiVpGba/2yvfLyzhQVxWEw\nxLVu4rMiyMi4grAw26oKOp6ShQs7MXnyckpLtS6ORQghLj+zZ+9l2rRKDIboFtsGBOQybpwParXs\nRhHtnyRTQrixYNsLIl2gqGgIAQEbbOrj738KcGRZ2gT8/A47cDz7xMfvZe/eGdx55yFSU/NdHY4Q\nQlw2Vq8+xjPPRHHokHVnGw4Zksn06f2cHJUQjiHJlBBuLCSkdf2NxlDU6lqb+qhUJuz96AgOPkaX\nLivp1Ok7EhO/BMx4emZiNIbbNZ7jnKS6OgJQ8PvvQ/noI1sqHAohhGjKli3p/OEPSqqrW34jBdCt\n22FGj5ZjK4T7kPenQrgxP7/WjuCBr28pZWX1WPtxYDaXA9a0ryQmZhtGoyd1dUpCQsooKori5Mlb\nTt/XExu7iKKievLyRtn/K7SSSnWSmJg0srPHnr6i4L//7YrB8Bt///sQ/P19XBabEEK0R0uXHmTJ\nEj3Z2ZVcdZUvXbsWMWXK6EsKRVRV1fLCCwVkZg6xatykpKMsXRpMjx4TnRG2EE4hyZQQbswRy8nL\nyq7Dx2cTtbXXWNU+O/thYmM/JDf3D4BXo218fDLx8dlIXt4dgAdQj1brcVErL3Jz7yYs7GtKSqx7\nYuloCkUmMTEHyc6+/YLrNTWRfPxxBKWlG/j2W9clekII0Z784x/f8OijN6NQKPnuu2QMhjA2bAC1\n+jA9ex5j5Mirzp4FVVqq5bHHdrNp07VWjm5m2rRyevTo4bxfQAgnkGRKCDeWlnYSjUZNXV08YF81\nCn//AgoKbPny0uDp2Z2mEimAqKjNpKVNPe/KxYnUOSUlNxEcvJ/y8v42xGA7b+9NREZmUFLSE0/P\nPDw9q9FoTGRmTmmih4IVK7qxePE+Jk+WtftCCPHCCw3n8U2YEMgHH+zlww8zOXiwP/X1vRg7Np1/\n/nMdSUkBHDhg5KOPvMnJuRaw7giPrl1389JLA5wYvRDOIcmUEG4sIaELZnM+UVErKC5+ApPJ9ooU\nBkMASmUNZrP1fSorvYGTQJez18LCdqBS1eLjU0ZRUZcm+14qDLN5AyEhKsrKHJ+0+PuvJDi4mPLy\nUWRkDCck5BA6XV9KS1suz6vTRTFzpp7IyJMMGZKERqNxeHxCCNGelZdX8dNPR5gyZfAF12fMuJKI\niN1MnNiw7NtgSObJJ70wmUJp+PPStr21N91kwdOz6QdvQrRXUoBCCDem14PJNI6CgleJiLCtKt8Z\nXl4GlEqjTX1KSkaSkFBAUND602MUoNOVUlg4kvT026muHmjTeFrt7ZhMh4Hy01esPdSxeb6+P1NX\nN4isrAeoqkoBoKysN7W11p1zAlBSksQtt2h47LHfHBKTEEK4k6+/PsSSJY3/uZiRYeb85/ImUzQN\nKxFs/fOynmHDVPaGKIRLSTIlhBurrj7zn5QoldmAweYx8vOHEhe3zcZeCrKyRhAWVgZARMRqamrG\n0ZqPFK32HqKjfyIlZTFRUXPw9j52wX2Npojo6N+JifmdgIAMK0Y8ire3Hr0+wu6YzqiqSqKw0B+L\nxTFJnhBCuIuff4bKysaX6vk4rD6Plp49W3nWhxAuIsmUEG7sXDIFubkPExz8FRERH+HltQcw0ZBc\ntZRgGTCZ7HsiaDAUExS0E7PZtjdbjVOSnz+FtLTJFBTcT1RU6nn3qgkM/In8/OvIy7sGT89MK8br\nhoeHdWv1rbFyZX8ef/w7h40nhBDtnU6n5/BhBfv2eVJbq7vkfmpqI53scOede8jJKXDMYEK0Mdkz\nJYQbq6w8/ycvyssfBSAiYg7+/ssxmWKBQEJCPKmv9yMjY0wjo2gwmy/9krSGWh1MRUUnKipsW9bX\nMg88PM496wkP30tx8f2nf1Li7V1A164ryc3tTlBQNnq9H1ptFIGBhZhMRgIDc1Ao1GRmNvb72suL\nH37oQd++u5gxQzZJCyEuf15ennh6qsjM7MXy5Xu4555zn30Wi4WdO02tnqNz5wOMGaPmhhuGtnos\nIVxBkikh3FhZWePXi4oeuqRdSso3TYyixGAYSkrKtxQWdqamxrpEISzsIPn5KUArTw5uQk2NhYSE\ntWRlXYufXw7FxeeSq6ysuwDw919Kbu54oAKFIoO6uqMEBHQlM/NOp8SUnd2bf/1rO9267WDUqEFO\nmUMIIdqLgwdTOXGiM6Dk44/13HabDl9fbwBee20ja9e27nOwV699fPaZF8OGWVs+XYj2R5b5CeHG\n0tNtKMFHYJN3SkquIC3tbkJCsqweTaGoQa+3vpCDrXJybgJSSUxcQ15e90bbVFVNpOFjLASL5So8\nPTWUlYU7LSaAY8cGsnZtrVPnEEKI9kClUqLRNKwn37RpGH/601ZMJhOvvLKed965kuaOyGhJQMAm\nXn+9jmHDGv98F8JdSDIlhJsyGuvYu9f6l8s1NTlA88mXThcFWJcoFBcPJjFxA9DE6zEHyMq6nczM\n6zEYrrQypruJjt7ltHgaKPnww3iOHMl28jxCCOFavXql8Ic/nHnIpuDjj4cRFbWfd94ZgsXi30xP\nC01XZa3HxyeV996zMGGCdZ/tQrRnkkwJ4aaef/4nsrN7W92+oiIBlaqk2TYlJYMJDra2yIKCzMxJ\nJCSsoaUkzX4h2PIx5eFxnKqqSCfFck5paSemT8+kvLzK6XMJIYQrPfVUCv7+Z4r+eFJSchVNH8Ru\nZtCgrXzxxQ5eeWUTfn4ZAKhUJfTuvZFnn93KTz/t54MPjvDIIyPQaGS3iXB/8v9iIdzQ0aOZ/Pe/\nA2n6C+1SBkNXvL2z0OmaKxWuIjhYTXl5M00uoDj9Nqs9MBITc4CMjMltMtvOncO5/fZNzJ3bjYQE\n5y4tFEIIV+nUKZrbb9/K3LmJLbTU8eijW/nggxF4eDQccD5lSjY//7yNTp0s3HLLiPPa9ndavEK0\nNUmmhHBDR48WYzDYVlEuLm4rOTn3ttjOYvG0adyAgOILikO4Ti5lZV3adMZ164Yzdux+vvyymquv\nTm7TuYUQoq2YTC2dsWfhwQe38skn16JQnDuSokePeHr0cN7eWiHag/bwF5AQwkalpfU29/H0tPZU\netvOjNLpuuLvv9nmeBzNw+MkdXW+bT7vsWN9ueMOE//73742n1sIIZzt00938803zS0pt9Cjxzb+\n9KfOFyRSQnQUkkwJ4YZSU23fo2Q0tlwoIiJiA+npI1psd768vH4EBBy3OR5HMxrHEBCwwCVz5+Z2\n5qGHErnvvt/4+9+Xsnv3EZfEIYQQjrRxYypvvRWE2RzQZJtrr93M9u196dYtoQ0jE6L9kGV+Qrgh\nPz/r90o1qMBsbrlYQkVFd8LCfqOk5B6bRq+s7AMcAPrYGJfjpKR8S0nJ/S03dJK6umDmzRtNYOBe\n7r9f9lAJIdyTXm/g/fdXUVUVwVdfhZOf3/Ty6ejoE/z3v53x9/dpwwiFaF8kmRLCDdm2kqKexMTv\nycx8vsWWRmMEanUIGs1R6up6WD1DVVVnvLw2oNe7JpkKCVlBdvZY6upCXTL/+bTafkydupn589VE\nRwe7OhwhRCvl5xfx7bd7OHjQQKdOXrzyylhXh+RUU6Ys5Pvv7wE0LbQ089RTJXTu3LUtwhKi3ZJl\nfkK4IYPB+rZxcfPIzJwEWJeBFRSMJTh4D2D9viwPj1IMhiTrg3Kw4GBTu0ikGihYu3Y4N92Uxp49\nmS03F0K0W599toPk5BqeffYGvvxyPN9+Cy+/vNLVYTnNzz8fY9Wq62k5kYLOnffy9NO2FUIS4nIk\nyZQQbkins6W1EVDZNH5R0QRiYmZZ1ValKiU+ficKRdsXf2hgRqFofx9l+/b159Zb0/nkE9cX5xBC\n2G79+pO8+mowBkMyZ/5cOnRoLLNm9WfHjlTXBucEFouFl15KQ6eLtqY1Dz6oP13YSIiOrf39BSKE\naFGVDWfF5uTcTkzMfBtn8CU/fyYpKUvp3Hk5QUGrmmypVOrIykrBbO5k4xyOkZy8gFOnbmimhR5o\nufiGM5hMav74x2488sg6DAbbqiQKIVxnyZKDzJxppKTk0v1CRmM0kyfX8eqrG6moqHRBdM5RUaHl\n+HFrEimIiTnCY4+5bo+sEO2JJFNCuCGt1pbWPuj1STbPYbH4k5Y2kVOnxhMUVImXVzYBAXsIC1t7\nQbvAwBPU1Q2yeXwAL68ckpPnk5S06KI71r56K6O0tAfg3ejd+PhfiImZR1zcTrviax0T3t6ZWCxh\nzJ49inHjtnH8eI4L4hBC2GLFikNMnRrKkSO9mmyTldWdv/51GIMGbaK21qalAu3W/v3ZGI2RVrUd\nNkxLUJC/kyMSwj1IMiWEGyoutqW1EYslFbBho9VFzGYjFks2lZXelJRcQVzc16cTFCMaTb6do1YQ\nGbmG9PQp1NX5Eh29lM6dF5OSMh9//5VERbW8PC44eAWVlY2ff5KQsI7i4mjy8h7Gy6vmorstHUB5\ncVubsle8vfNJSVlERsak01cUrF07kptv1rJ48QGbxhJCtB29Xs/MmXr0+hgrWis5eXIsH3+8x+lx\ntYUvvyyirq7l39vbO4+XX45tg4iEcA+STAnhhvLybGkdRHn5zcTEzMPehMrT0xeDYSjQAwgjJ+d+\nysqUREf/k/z8yTaP5+2dS1DQT2RmTgMgN/dm8vMncurUZNLSplBVNRlPzzRaSnrq6sKBukbu1KLX\nl6LXNyRa1dVlhIX9TGzsFvz9U4mN/Tfh4T+eHr8OMAFmPDwyuLjwRkzMzyQmftdsHJ6eBTS8TbMQ\nG7uSsLBdpKXdA3hd0C41tRf33hvHE0/Isj8h2qMVK46Qm9vXhh4qlixRYbHY8oCmddLTbfoCsNqB\nA9a9YRsxIod+/RKdEoMQ7kiSKSHcTE5OIWlptp5jlEhe3q1ERMwmJqb5xKAx9fWXHhJcW9sfrXYE\n8fG/EB29tcUxfH1TiYv7D8nJ8wkP/5GKintp7nSGzMzxJCQswMenoMk2UVEG4OLCF3UkJn5PUdHE\ns1cKCh6mpOQ6tFoFISE7yc19mrKyeFJSviE0dAXx8d8QGvolQUELOT+B8/dveKNXXh6GQlGJWn1p\nLImJvxMUtIvExAUEBa2juDiE7Oxbm4y5vj6EDz8cxZgxO9m3L6vJdkKItrd+vRFrKtmdb9u2vrzx\nxhbnBHSerKwS/vKX2QQF+Tl87Pr6empri6xqq1CccPj8QrgzOWdKCCuVlJQTEhKIUnnhMwiDwcD/\n/reXnTvzef/9cXh7ezUxgmOsWJGJwWDrHiULYWHp1NV1obw8kU6dFlFa2o+KipbPB1GpCigoiGr0\nXm3tMGprwdt7BQ1L4QIbbRcUdAq1+iQ5OU/YEHMAWVn3EhX1I1FRtSiVvlgs1dTUmDGZzHh5Gais\nvHRPQ6dOP5CaejeXPitSU109hOrqIQCYTH1IS2vYQF1a2tAiJWURRUUaGiogGvHzW0he3ssAxMR8\nRVVVCJGRFnQ6NWq1J/X1FVRUxKHVXnfmvxHAmsMrFWzaNIwxY9J55ZVtPPnkQFQq2youCiEcy2Kx\nsLQUC40AACAASURBVGWLPW+YvFm/Xs2nn26luDidV165+5LvidaaO3c/n356goULJxAcHODQsQHU\najX9+tVy4oSZ5p6zBwev56WXejp8fiHcmSRTQlghP7+cm25azBtvDGD8+KuAhi/eZ5/9mYULNRQW\nDsDHR8e77xqdnkxt327bl71Gk0tc3DoyMwdhNg8GIDW1G506rWg2mVKpKkhI+AmTqYasrIeanUOn\nu5GEhG/IyprGxedZxcZuoqLCQEXFOJviPqOg4OZGr2s031NXl0x8/G+AArNZgZdXPTU1ftj70VZZ\nqScu7nNqaooICupMevo9Z+/l5U0HzlRSPPMHx8V/eFiTSJ1TWprMs89G89FHy/nyy96MGCGHXwrh\nKl9+uZN9+66yq+/69YNZvx4iIrx44olqgoIcl/Bs2HCS//ynnvvuSyAhIcxh417s/ffvxM9vAadO\nmdm3L4XKymEXtajkySe1jBo1ymkxCOGOJJkSogX79x/nj3/cxr59j7Bu3S+MH3/unrd3DbfeCqWl\n28nNzUOptK+qnbVqa3Vs3ryHiIg6ioqG0twTRIWilKSklZSWhpOePuWS+0ZjIf7+6VRVJTfaPzp6\nF+np91oZmQdZWUPw9j6ITndhuVydzo+amiQrx7FWJZGRFiorN5CdPR5HfJR5eOxGo+lETU09Fksg\n6el3NtNaedE/W8OL1NSJLFr0viRTQriI2Wzmk0/MgGerxikq6keXLofo3l3PgAElTJoUyfDhtiVo\nFouFXbtOsXp1BZs3W9iwIZHu3ct54omBrYqtJdHREcyZ0/BdkZFRwKxZy4mI8Gb7dgvHj/9/9u47\nvs3qXvz4R9OSLS9Z3pZl2RkQEhJGIMywNySsQtijtGW0P+7tHtyOS3tvd3vbMlo2NOyZhE0gCWTv\nQUgcW9b0kGxZlqw9fn84IXFsWbIs2wLO+/Xi9ULPOM+xY0nP9znnfL9qbr7Zw09/mnwKsyB8VYlg\nShBG4HR2M3/+H/B4/snJJ6/m178+/fN9EomE3/zmigntz8MPb6Ol5VtAN42Nr9PaevkIRyfo7i6l\nr++iYfdarXfQ2LgYr1fP4R8FJSU78HpHmyBhOpWVT2A2N5BIHHwq6/FUU1j4MV5v3SjbS66xcRmt\nrddy+ChYpmpqXqW7ezbt7Y0AlJZuQyZrIRabqNpZEtatm8/27VaOPlo/QdcUBOGADz7YwcaN2aib\nJMHlmsXHH8PHH8d58EETf/vb+1RUlBKJJLDbob09zs6d/fj9bk45pZbqahnBIHi9CUwm2LYtwbZt\nU0gkDta4OuYYS9anDo6koaGKv/3t4JPDaDSKXC5uGQVhOOKdIQgj0GpLuPPOheh073PppUeSnz++\nU/hG4nJ5ePhhFQMBhA6fT4lM1k0sVjbs8XJ5ApUqQt8INSVbW6/AaHwLk+ng00adbgUymYfOzstG\n3ce2thvQ6x+lt/cCvN6BbE+xWCXl5ZFRFRoeiVy+G6/3KLIVSAHk5UUIhRo/f+12z8ZofAqTaeIK\nEW/YcCwXXriX//7vzdx2W2ZTjQRBGL1IJMoPfuBhtNN0U5MSCjXxjW8k/xz58MOkuwY54ogsdSlD\nIpAShORENj9BGIFMJuN//udivvvdc5k2LXsjK6MVj8e5887N7Nkz5/NtXV0XYjCsTHpOTc0ngzLa\nDU+F4pDEVTU1v6enpzijQGqAHKv1m6hUO6mtHcjwp9NtIx7vybC9oaLRAhSK7BbJtNlmU1W1adC2\n3t65KJUfIJXuyuq1RuJwTOOOO6awaNFS7PZRFRMTBCEDkUiUu+76kK1bT53sriQ1deoOrr22MfWB\ngiBMChFMCcIXwA9/+AkvvXTaYVul2O3V6PWPMmXKMmpq3qaoaCvgp7R0PYlElHTe4v39PiBGff0j\ntLd/jXh8TspzUnE6LyYQSGAwPI7HIx80XWXs6pHJRldEN5VIZDqFhfZB29zuI1GrtRQVxTEa/71/\na5zKyheoqfkXKtVbGAzPUVu7hNLS5VnrSzxexEcfFXL22TZee21n1toVBGGoxYs38sgjI68/nWxn\nn+1Drx9+BoIgCJNPjNsKwhfA+++rGO7tGgrNw2qdt/9VFHBQUvJ33O7rcLvTS4bR1TWLoqI9JBIa\nEonsFWLs6TmZnp6TAfB4ekk/bXhqCkV3Vto5qIWuruohWz2eYwDo69PT0LAYiaQIk2kBA3VoejGb\nSwEJRuNS3O6RUwqPRiQSZ8+e2Vx9dS+33LKK3/xmFuXlJVlpWxCEAe++u4Nf/1rN0Fp1uWWGyEQu\nCDktdx/FCIIAwKefttDWls5aLTlQT2/vD4D0pyRGIjPJy+smHs9jIODJPr+/HDBnsb1I1toa0ERB\ngSvp3ni8hLa26zCZLmEg25cU0HJg3ZbJdA41NS9npScqlYO8vHZASjSq5ZFHTmPevGZefHFbVtoX\nBGHAffd5aW6ePal9kEg8zJu3nosuWo9SOfQhUVVVC7Nnl05CzwRBSJcIpgQhh7ndXm67bTG9vbPG\n9TpFRT7C4VJAOS7th8O1qNV7s9Zef38JUmlv1tqrrFxGMDiWUTkVanU2fnceqqo+wOEYnJK+tXUu\nixY1cPbZ7+DzjU/AKwhfNbNnT+bknARHH72eV181s2bNCSxbdgL337+X/PxOAGQyN3r9Up5+OsTp\np09y9glBEEYkgilByGGPPPIp69bdN+7XkUj8eDw1ZHP0aDAleXnBrLXm9V6GXv9C1trLz3fT0zO2\nuTTR6AhpE9PU2PghbW1Da4IBxGLFLF9+Hj/5ycdjvo4gCLBjR/Yygo6GVmvhZz9bzdq1R7NgwcF0\n7N///kn89rctSCTd3HnnUlpazuecc8QcP0HIdWLNlCDksHXrJubLvqVlLmVlK5FI5Did2U8HrtN9\nitt9VFbbVCqrstKORGIiHi9KfWAKcnmmafP9KBReSkv3EIsFGPkZl4S33nqXffuOYMqU+gyvJwiC\n1eris88mfh2iRtPOY495WbDglGH33333SbS1PcHvfnfzhNaVEgQhc+KdKgg5KhKJsH37Rioqxn+t\nTCJRj8t1AwUFZdTUPAnEs9a2VvsO0aiXWGxm1toECAazs2i8sXEDZvP5Y2wlRn9/ZkkxDIZ/o1Ds\noqvrdMzmRSmP93jOQ6GQZXQtQRitjRt3M2/eT3j22aWT3ZWsWrHCRG9vNrOMpuf22/exYEHyB0sS\niYQ//OFWEUgJwheIeLcKQo7asKGZ5uab6OuTodcnryeVTW1t5+JwXEN5+XNZazMYrKS3d1rW2hsQ\nJhDIzvquQMCDWm0aYysyQiF1mse6UKmaqah4B4XCRSCgxu8/K+0rOZ0ncckli2lpacuop4IwGrfc\n8gBO50yee+7LVfesuTnbSWxSk0o7+frXJ69eoSAI40MEU4KQox57rBvQEAzOpKOjEr1+1YRct6pq\nE05n+jf3qVRUtAK6rLWXl7cBo3ExLtdJWWnP4bgS2A24x9ROSUk6o0VhamufIB630NV1DKWl/6ar\n64ZRXqmQ5uZbePXV9ky6KQhpe+edDezefSl+fw319RWT3Z2sicViPPmkIvWBWaZS9aHVaib8uoIg\njC+xZkoQcswzz7zG9u1yHn/89M+3RSLTUav3Tcj1/X4tSuU+wuGxrUkqK9tHUdEarNbjyd5zGxsF\nBXFMpluy1B6AlkBgBmq1g0Ag8xTEfn8F0AcMt/4qCvRTV/ckNts9wMD6qq6u/5fRtUKhcr7//Xw+\n++xD/vrXeRQUpDsqJgjp27mzj3j8LOLxj/n732s599xVXHbZ4cXDv3gefHA9ZvOxE3jFOFdeuQqd\nDny+vAm8riAIE0GMTAlCjnn2WR2///0lQ5IiuFwF1Nc/CMTG9fqFhbsJh+eMuR2lchMm0/lEo0dm\noVcDjMbV9PScmLX2DiogP79/TC10dp6FTrcSiWTPkH0NDc+gUn2CzfYtDgRSY1fAo4+ewdlnb2X9\n+rFOUxSEwb773ad56aUSQI5CEWfKFB9nn338ZHdrzFat2sd//Vc1A/XiJobBsJw//3kaDz00n2nT\nROIYQfiyEcGUIOSYwsLhv+R7es7AYllETc0TlJTsGLfrd3SchkaTSfrtMAMjMAPa27+GXv961voF\nfkKhyiy2d6h8ImNeQiGnv38mOt2Gw7ZH6OuLEQxeRPbreElYt+4kzjtPxn33rSQUCme5feGrqK/P\ny5NPGlm79jhKS1/A4ZhLS4uMnTuHPij4IonFYtx9twu3u2HCrllaupUVK2ah11dP2DUFQZhYIpgS\nhBwjH3HybQkOx+0EAg4UCss4XNtJff17xOOjm9ff0PA4xcVLqKv7G3AgKpEQjeYxMPVt7IqLn8br\njVJYuBWlcvch18kGLVptz5hbCQQa8HpPoLj4FaqqViGR9KJWmwgGx/dGyuOp5/77T+XUU7fw+us7\nx/Vawpfff/zHG3R3zwOgpERCIlFIItGE2z2+o+LjqbfXx8UXr2LHjokaXUswY8YKHnnET11d9taM\nCoKQe0QwJQg5prg49TGh0JlotW8BgaxdVyJxUlLyIibTdfj9p6Z1Tnn5eqqr1yOVKvF4rsRmu5u6\nuieorHyTqqoPsjo65fHcgdd7HF6vlnA4n4qKV2hoWJKVtiFOLDb2USOFooOqqo/xeGbR1VVFdfWD\nBAJB/P6LstDHVKRs3HgiV11Vy/XXf8yePY4JuKbwZfPww6t5442TOLCkWvJ5qbsKHn1072R1a8we\nfngH77wzn4laKn7kkVtYs+Z4rrjiZGQyUcpAEL7MRAIKQcgxTWnVzFXS2Xk91dUvkZ+fRyBQgcNx\nDAPrADJbk5NIlKJUakdxRoj8/K309MwiFjvwUaLEZrsDCFJUtJKysj309JxFefkDSKWzgUNvztj/\nOrH//6K0t58IJEumIAVK9v8HXV0GmpqWjaK/I+nF48m8blVBgYXy8vX09JTQ1nYbAPE4OBz3UFm5\nnM7Oo7PUz9Si0VIWLz6Vd95p5eabV/PDH86gomLii5MKXzyrV7fw4x/rcbv1n29LJA5OHd2ypY7X\nXnufhQvPmYzuZaSlpZNvfauZLVvqgbEWQT8wMidjoBafF5nMSyxWi0TioqGhlerqBGVlUebPV1FU\nlJ1aeIIg5DYRTAlCjmlokAIJUn/xa2hvv3H//4cpLl5KLCahtDRMXl4e4XAZFkv6mbeUSg8KRZyB\ndU+pPxrq61dgNn8NKMHrPTxNuYq+vvOoq/sXgcBspNIyOjtPSdHiLuTyDqJRY9p9jsd7kEp7icfH\nGixoSSTcNDQ8QVvb1UC6N0Exqqo2EAp10dZ21TD7C8nLi1JYuGaY39H46u5u5E9/auSFF3Zy9927\nuPfe41GpRCYxYXidnb386lcO3O7BnxlS6cEU4i0tp7B06aMsXDjRvcvM1q1WbrvNyZYt6Y20H06p\n7GbatFZUqgQSSZRLL41jMCjZt0+CwZDgqKMKqKwsYevWjdTWFlJVVUt9vagjJQhfNSKYEoQcU1Oj\nBvykf0MPoMTjuQIAn29gS3HxWmprXycczsPpPI9Us3oTCUgkpOj1T2O1LgRSpQl3ACoKC1/F610w\nbPs22wKgH78/nXUKempqnsfvP5JEQkJ393GkGmUzmW6kvv5tLJYL0mh/ZF7vBXi9cerrH8diuT2t\ncxobX6e19QRgXtJjLJYrqaraQlnZ67S1LRhzP0fLZpvJj38c55lnNvPNb8a4667jxbQjYZCWljZu\nvXUbq1Yd/ve5h0Dg0KQvftrbd01k1zL2zjt7+PrXE9hsmaVALy9v5YEHfFx11dyUxxqNtRldQxCE\nLwexZkoQcsycOY0UFY091bXHMw+7/QKcztMxGF6gquqTEY+PRMqwWK6lq+sCqqtXpHGFUhoaXsDr\nPZPKygeSHFMBGEnvo6YIi+UOXK5T6e6ehUazLY1zmvF6u9I4Ll1SLJYz0Ok2pnW0XK4AUj+J7ug4\nhkDAiEq1aWzdy5iUXbuO5zvfqWXu3MU8+OBaYrEvbjIBIbtuvvlDVq267LCtcXS693E4Do5UHXnk\n2/zznz+a2M5l4O2393LLLTJstiMyOr+ubi/PPRfjqqsmbnquIAhfXCKYEoQcE43GKS7uzVJreUA+\nZvO1hMNO8vJaU54RClWTn586xbbFsoC2tptQqfxIpWVZ6Ouhiigt3cLAdMeRTCUU0qFQZDPZQhPF\nxell9guFOtNutbPzaMrKLAystZh4SuUuDIZdbNlyI3fddRxz5mzij39cg98fnJT+CLlh3bod7N59\nHIdPK66pWYrHcxUHbhPKynbx/vtnUFs7tmLe483r9fO97/XR0TElo/MrKlr497+lnHXW1Cz3TBCE\nLysRTAlCjpHLpfT1pZHSb5R6ehZSUrIcqdQ57H6t9jP0+reprX2DYDD9ekXFxbtob1+UrW5+zmY7\nDoUidfDn9x9Laak9q9eOx3s4mHrdO+wxRuM79PSM7oaro+NUqqt/Q1PT8yiV41cr7HBFRWvQ6fow\nm8/fv0XBzp0n8L3vzWP27E8544xF7N3bMmH9EXLHkiU99PTMOmyrg3i8jEjk4BS/SMRPPJ77dcz+\n6782smvXcRmdK5e7+ctfvJx+emaBmCAIX00imBKEHPPpp2Y8nvFZxNzZeQMGw1sYjW9RVrZ90L6y\nsk9xOnV0dkqx229Iu02lcuz1mYaTSMylqmolqUenqlCr95HNNPGJBBgML9DU9DwazZuUlOzmYCYv\nqK9fRVdXAV7v/FG1G4uV097+U1parqG0NE5V1VNZ63My5eXvoFRqcDiGS4AhYd++Y1mx4hluvLGd\nhx9eL6b/fYXE43HefFPN4aNSjY0f0dExZ9C2ysoeampye1Tqgw/28uCDR5Bp1r7LLtvDokVzUh8o\nCIJwCJGAQhByTGlpASpVC8XFfiQSGR0dqbLgjYYKk+kmAOrq/gUYUShClJdvpL8/SjA4jerqHbS3\np9+icuzlmZKyWq+ktvY17PbLRzzObL6a2tp3sNsvztKVtZjN533+qr7+UfLzN6BWK/enPJ9JKDQz\nw7YHbvQ6O2czbZqNjo4sdDcJne59IhEjvb3TUhwpY/36U1m/Pso//rGJW2+Ncdddx5GXN47/uMKk\ne/bZjWzZMnRdUDyuY3ACnDB33VWEVJrbz19ff91DKJTqbz2ZMFdfrUh9mCAIwmFEMCUIOaamppyi\nojfo7LwLmawZvf4pvN6T6O3N7hx+m+12GhqeJhxW4XBcs39rH15v+mtoVKoW+vvH82OkiPb2mRQW\n7sLrPWqE4+QkEr2kl1I+NZnMPeh1utn9RisbhYKTUSp3IpercblGc3MpZ8eOE/jP/4zz8MObWbQo\nyje+MZXq6myviRMmWyKR4O9/72O4jJmx2OA1m0ccsZ177kmd1W6ybd2a+bmVlZtZuFCMSgmCMHq5\n/ZhJEL6C8vLykMtPACAWm4rVehOlpRtIPd1ttKS0td18SCAFUEQodDplZX9AItkKJF8jUVi4m8LC\ndXR0XJnlfg0Wj0+luDj1UJnDcSpVVW9l5Zp+f/amDCYXJh4fv2GpurptYxjVlLJnz/H84hfzOOqo\nbr7+9bWsXt2c1f4Jk+uf/9zA2rUnJ9nrG/Sqvj6OXJ7bz143bDCxaVPmKcqnTw8Qi2X7M1YQhK8C\nEUwJQg5SqQZ/qZtMl1Fb+xcUCsu4XzsSOYru7m8jlxdTW/tC0uPU6pdwOtOt3jm2hetqdR+NjW9i\nNC6mvv5thgssjcaP6eg4//PXUmkfEkkfAFrtbozGlzAYHmWgKHEq/cNeI3tiGAzPYDJlP3EHgE73\nFk5nshvl0XG7p/Hoo/M444xSzj9/HQ88sI5gMEQwGMpK+8LEcrk83HjjW9xzTxmQP+wx0WgvB9YI\n1tTsYeHC3F5Hl0gk+MlPbPj9NRm3odd7iMdFMCUIwuiJYEoQctDQh8AaEolCIpH6CepBHpGIAak0\nkvSIrq57qa5OHmwdqqzsJ4Ar497s23ccdnslJtN12O16CgtXMThA6yAalQIyZLJuDIZHqap6m8bG\n5VRUvE1BwTpMpqswm8+ipuZZdLotI16vvf1mKivfy7i/qdTULMdsvoHxmGmtVm8gL68Mr9eY1XYj\nER3vvnsid989l6OOep077niA9vbxST4ijI8nntjOOee08swzFxKNNiU5yoFaXcPA+yvOzTe7uPPO\n4ZKX5I4nntjI++9nlsFPo2nloYfW0NTko7Bw+OBSEARhJLk9bi8IX1HxYUoRKRQTlQwgAijQardh\ntZ4wwnGFqFQFI+wHiFJT8yeczhuBDkCXUY8SCQOhkAGAWOwovN4WampeID9fRSTSTzRqw2r9MRCn\nrOwFzOZvAlIaGp4hHA7T1XXL/paMOBxG8vM3odNtweU6JskVNRQUjN9TarW6F8j2v2cPRuNb+HxT\nsdtH+ncbKymhUDXPPPM13n57D6ed1swFF0i47rqj0GhS/T0Ik8Hr9fPHP67n//6vCbdbP+KxWu0a\nWlsXAirmzFnLL34xnn9LY7dixT5++EMdyUbZhlNXtxej0UVFhZTzz5dwxx0nkUjMG79OCoLwpSaC\nKUHIQSrV0CQKVut8GhsX4/HMoLt7/BZKNzS8TiQSQy5vp6fn3hGOTBCJjDwyodM9isPxHUBBY+OL\nOJ09eL2nZ6GXTTgchz5Z76O+/l8EgwV0dS3iwKB7W9s5gHbI2X7/cVRWPovLNZtkA/RS6fD1pcYu\nQSSS+ShdMo2N79Laeh3ZSMCRimT/JVyu6bz6Krz6apxf/nIX557r56KLFFx++SwUCpEZLResWbOd\nP/+5mRdfvIKR/jYqKp6iqKiE/v4SQEZlpYnvfEeJUpm7/45bt1r51rf8OJ1DMxImU1m5m6VL85k9\ne/A0WIlk/N83giB8OYlgShByzLp12+nsHPqUNR430NpqQKtdhVa7i56ekbLbZUYudxMKKWlvvwyd\nbuQaSMXFG7DbzxrhiDCx2DQOZAtrbb2W6up38Y5LjFKExfLNYbYnr4tjMp2PwbAYs/kG1Op2KipW\nE4t1I5Xm7a/LdOp4dJTa2lVYLBdktU21ei12+0lMRCA14PBROykOxyyefBKefDJCY+MOzjsvyvnn\nK7nkkpk5n7zgy+yNN5wjBlIKxS7q6nbS1nYpXV2l+7cmuP56K7femo0HH+Nj8eLt/PjHeVgs6QVS\ncrkDo9HC7bfHmD37yHHunSAIXyXiG04QcozdHsbpnJV0f0/PadTWPg4cSSbLHuvq3sflOoLCQjsa\njYO+Pi15eZ1IJBbk8jrM5msByM8feZqbx3MCtbXPYbcnS9neRTBYOmhLT880NJpP8PlOAeIole9T\nUdGH211Pf/9ETyfSMjClsY/S0g8wm2+gvv5NLJaLxu2KOt3HyOUWIJs3qXvIz99Bd/fETVNKJKKA\nn+GnVilobT2Whx6Chx4KMWXKNk47LcLpp0u45prZqNVDU3EL2bdjh5V777Xz4YdzSR5I7aS2dh0m\n06Gp/6NceukqfvWr3J32tnLlHu66S5t2cfOmpk957jklM2ceg0IhbnsEQcgu8akiCDlGIhlmwdRh\n7Parqa39ALv93FG3L5c7USgkOJ3TcTpPZGCh+dD1O+Fw6uk9eXnJ+6rTvY3LdeOgbaFQA5WVn1FR\n8T4+Xx4+n56urgrKy5dPQjAFZvP1lJS8isNxHcC4Tk0rKtqL36/E5bohq+2Wlu7A7b4iq22ORKl0\nAZ2Ulu6itNSLQuEnEAjicuXj95/D4L+lPPbtO459++Dxx+P85Cc7Of74IMceK+Hkk5WcddZRYtRq\nHHzyyTZ++tN2VqwYfgS0qGg1lZVOPJ5G2toODaRifPObH/LAA2fndIHeRx7pxONJ74FEcbGF3/42\nxvHHTxnnXgmC8FUlvsUEIccYDMWAFyga4SgNeXmZzpeL4PWefcjr4RMh5OWlLt7b1XU6Wu3r9PQs\nGLKvuLgIlytvyPahU9wCuN2TlZJYSW/vwTpbiUT21zIdUFxswmo9P/WBo5RIKInH1VlvdzhyeQ9V\nVR9gsQykdHcPqm3sQ6vdTGlpP3J5cH+ApcLvP5uBqZ5S2tuPZskSWLIEIERd3XaOPjrGzJkwYwac\ndZYevb5qf9seWlqsHH/8zAn52b4sTKZ2vvOddjZvTjaVNI5O10pz89Cgfvr0Lfzf/52R04HUH/+4\nmsWL05vap1D08NhjHq64IvlIvyAIwliJYEoQcsyRR9ZTVNRKX9/Ia6JisfTr/JSV7UGj+RCz+Rqk\n0nRGX4L4fKlHyHy+OqZMWU/PMHko4vH0Pl7kch8lJb34/X0M3HRPVNbCoXp6KtFqd9PTk/01FV5v\nMcmnxmWut/ccCgt34vWO98helJqaN7BYbkmyX0NPz7zD/hZ81NS8S3v7HBKJw9P652GzHYvNBm++\nCZBALrfS2LiBhgYJmzapUSg28cYbBcydm900719W7777Gffdt5PNm5MX0jYan6O1dejDD4D582M5\nnXCipaWD3/2uhFisJK3jb7xxO1dcccb4dkoQhK+83H38JAhfUWq1msrKQMrjJJLDb8qD1NT8FqNx\nMRUVH3MgSUB+fisFBZswm79OdfWLdHUlW+N0kMGwlO7u29LqbzTal6R/6d2URaPlOBy3UFe3ivLy\nZygvfzWt88ZDb+9ZlJZuH5e2vd4j0Oufz1JrUWSyPahUmwAlMlnqwHfsEni9ox0B0+BwXIbRuBZI\n1UcJ0Wg9e/fO5d13j6e/P0wk4uXMM7dy1llP8r//u55t21qTnr1ixT42bTKPsn9fHsuW7eT222Os\nX38Vw6+R8lNV9RjBoAEoHGZ/gtNOy+2Mdt/4RjNdXTPSOlattvHDH6b+rBMEQRgrMTIlCDlIp4Pm\n5pGPkUj6AB+gAcBgeBqz+bsMvK1d1Nf/C5Wqju7uOBbLwJqg9vZvpLx2be06HI6jSOdZS0PDUmy2\n4afcxOP9Kc8/SInNdjFG41P09DSi0WzG5zt2FOdnT3+/m4FANLs3lrFYCeHwVMAGpLdwPhmt7hZk\n/wAAIABJREFU9nmgELm8Hq32/+jrOzvlOWMnQyrtzujM1taFNDQ8R1vbdWmfo9ebaW6+A+jhww8L\n+fBDDT/7mZOZMzcwZw7U1Pg59lgNen0+n3zi4emnCzAae3jlFUNGffyi+vRTOz/60TK2b5+X9L0I\nUF39Ou3t1wNDp94ClJXt5Mwzc3cE8Je/XMmKFbPTPn7mTAtTp+Z2sWFBEL4cRDAlCDlIO7Q00hAm\n09UYDM8Ri1Vhs51KIqHi4Ftah8WSOnAaTjTqJxJJVsz2oPz8NtzuEqLR4YOecHjkGlSHq6jYQGdn\nE8GgnrKylZMWTKlUasYrxXhn5yzy8lYRCo0tmNLpitm795L9rxrR6d6hurqNaFRDe3sDwWDTkHMq\nKzehVjsIBNRIpQW0t4/2RlNKcbGO7oziKSWdnfMpL38Xp/O8lEeXly/Zn6Y7D6j+fHssVs62beVs\n23ZgSxwIMDB1UkJf34ZMOveF5XC4uPba99ixI/V7PT+/gGSBFMAll3iprc3dtUWLF6uJxYrTPDqC\nTOZh27ZW5swZ+l4QBEHIJjHNTxByUElaSwJUmM23YLOdRUnJa1gs12fl2p2dcygoWJ7yOK12Dx5P\nslpMPchko0kqkUCl2offfwrxeAEFBamnOY6XcLicsrId49K2QmEjFqscUxvV1e/sHzk8oAiX62qa\nmxdgMp1NKBSitvYFpk9/k5qaFUgkbvT6t3C7C2hru5TOznOIRoNUVq4b1XVlsg6czuQ346kEArWA\nHoPhOUae8mdBKi3B45mfRqtSoIADwa/FUszWrXsy7uMXzdatVnbsSD3ap1Tuoq9v5FEnozG3n62W\nlaX/eTJ37nusWHG2CKQEQZgQIpgShBxUONyShqSU9PbeQPbezqVUVLhTHhWJKEl2U1xZuRSrNf2R\nsaqqlVgsZ+5/lUcslp+07fHmcFxEaenecWg5SHn5WqLRuRm3oFTuRqHox+dLfmOcSMzAbv8ae/Zc\nhMNxGirVZnp6tITDR3x+THd3DV7v6BJhxGJyAoGRMkym5nQeiURSOuIx1dWv0dl5YkbtFxVFaWqq\nzejcLxqfz89vfvMskGptYh+1tXtHrF0H0NsbzVrfxoNhFLM3L70UlMrJS2QjCMJXiwimBCEHjWO5\no7T4fFUMZJ5LLi8vSrKPkFAoH0h+c1ZTsxatdjMQoL7+XaLRBFD1+X6bbT6VlY+Out/ZIJHsobs7\n+zVpKio+wOFInmUttQ5qatZjsYymppSUQOBs+vsHBydVVWvx+0c3pUutthONjpxhMrUwoZCX5F89\nfUQiR5NpRsfKSg8aTUGmnfvCsNu7mDt3EZ98chuppqQaDMswmRambHPPntSlECZTdXV6D1fmzXuJ\n666bnCnCgiB8NYlgShBy0GQHUxpNB6lSeCuVyetc9fYupLr6o6T78/O7UattGAwvY7Gcg8t1xqD9\niUQJeXl6RgrIxksi0URh4XYGihlnSz95eSYOJAvJRGPjh7S13ZSV3mRSR0ir7QQqxnRdo3Ep7e3J\nb+zr6/+Ny5XO9L7hqdVRIpHcHmEZq2AwxBVXfILJ9E/giJTHK5VlpLMG8JRTJmckOH3pvB9jfOc7\nDTQ1VaU+VBAEIUtEMCUIOUg+icsXZLJmbLZ0jhzpBk2OWt07ZGtBgY2Skg/o7VVht1+G2Zx8eqLP\np2ZycuTIsVgWUVv7cfZalIeIRuvI7OeJo9U+RThcSrYSY8hko137lECp7BzzdSWSICP9DvLyKhnL\nz7h58yn89rdrMj4/17W3d3LaaStZv34BoVDqtXeNjS9gtaZOJqPTtXLFFdmvrZYtsViMZctSB8k6\n3S4WLhRFngVBmFi5veJUEL6iEonRJG/IrlisicrK15BIniA/v5TW1tOIxYamF3S5plBa+h5u97nD\ntuP1OhlY9zQQLFVWriMU6qK390zSGaEZKPp78PyJVFT0AX5/9havR6NaCgrSDRIG/8y1tYtpb19I\nT8/Y1isdSqEY3e9UobBhNo91ih/09ZUBQQaKMw8Vj491dMTD6aenm/HtiyMajbJvn4P779/Mxo2X\nMdJ7oqxsGQpFLwpFL11dCwkGy1O0nmDRIgdHHpksmczk6u318e1vb2Dv3tQjloWFYdTq4f+2BEEQ\nxosIpgQhB7lck5fNDiJ4vfV4vdcAYcrK1tDdPfRGprd3FsXFCSoqnsHtPoZIZOBmWyZrxmDYhs9X\nSGPjK3i9AQoKotjtJxOJpJ9YoLTUQ2/v5Ayea7V22tqyeXOZIBpNldQjiNH4CpGIGqnUQzBYicdT\nit9/LPF49gIpgFhsdMG6wbCVffsuHeNVEygU7UAfyYOpyJiukJfnR60eVfaWL4Rnn13NT38qw2q9\nmJEDqaX4fCcQCqU7HTPO9Olv84tfnJKVfmZTV5eL5csd/PWvQdauPTP1CUBfn4xYLIZMJhvn3gmC\nIBwkgilByEGhUOYpqMdKqXQilw9cv67uMWy25Ot0PJ6jkUjqqKj4jFjsXXp6plNXt5HW1kUAdHUN\nHOd0jr4f6S3r6aeychmJRIKurmtGf5Ek2tquoKjoM/r6jstam1Jp8o/b2trniEQqMJmuAQZuBDWa\nvVRVbcFqPSdrfQCoqHiDjo7TRnFGiN7e0Jivq9e/jdV6BZAsMPTh8aRVEyCpUKiW731vLS+/rMXp\ndDJjxtQxtZcrli9XYbWekPK4kpII3d3pr2u78MKlPPXU6Wi1uTOaZ7e7WLWqhd/9rp+tW48nkRj5\nQYJOZ+Luu7uoroYf/EDGW2/t5pJLxFQ/QRAmjgimBCEHpT8lLPvU6s9wu08HQKWqIFUiikRCS2fn\nyZSWfkpNzSeYzanr3qRDJoulPKa8/Hk6OxehUPRTU/MgDsflgJaSkqXodOB2B+juzqT+ViclJXtR\nqWR0dc3J4PzDSYDDA4UwUulapNIIUmkxXV1nDdrr803D55uWhWsPJpf3EQikXqCvVn9GIDAFrXYd\nLtdFY7xqApmsm+SBVJza2uew228d43Vg1ap5zJr1Djfd5OB3v/viB1OBQJBPPkkvI00olP7nRmXl\nX9m8+XfodPZMuzYugsEwd99dSk9P6lFsqbSPP/zBzc03n0gikWDjxjd57z0nZ53VRH6+egJ6KwiC\nIBJQCEJO6u6enGBKrbZTXNyMVLobAI9HiVSauuYUgNs9I60AKF3x+HDpseNIJBvQal+nqelV+vsv\nAtREIjocjjsxGFbR0LCM3t4L2bfvCjSaTKdLTsdiWYRavYvs1LsK4fEcOrrTQWXlMuLxGUSjc7Ba\nL8zCNdLT1TUdpbI16f6iolaaml4gFArT2PgcMtlOxpJVUa22YzS+gdU6cn0tubwAnW53xtc5VFfX\nCWg01Vlpa7L94hfraW5OJ6Dfjdeban3UgOJiEw89dCZms2lsncuyeDzO2rXthMPp1UCbP38HN944\n8LuRSCT8618X89e/3iICKUEQJpQYmRKEHON2e9m2bTxzo4eQy3uIRqvJy3NQXv46Umk+kYiWWKwX\ni+WbHHjO4nQeiUplIRgcudDqAf39eQzceI/9o0UqHRqYVVW9iNN5Mj09M+jpGVpPyGy+etBrm+0q\n9PoHsdvPIx4ffUKJSGRsa3gGRNFq15NImMjPX47ffxaVlR/Q2bmIyXieFY1WU1jYQTjcOMzeIKWl\nH9LScjsAra1HI5XuJPmIUioJysqWYTKlKuAsxWxeRFPTS7hcY5+ilUiU0tLyxa839eyz2/nXvwyM\nlOFQqdxCeXkLgUAtPT3pFYS++WYnCxemnjY4kRKJBJddtoRly84l1Wj4ASecIMkozb8gCEI2iWBK\nEHLMd7/7HC0td4xL20VFrSgUbxIINFFf/xGJRAST6c79e1vIy/uQwTf4TVRX/xuTaXZa7btc56HT\nfYDLdf6Y+9rbezAVt0azkeLinSQSRmIxfdptxGIlWK13otc/hdVqZLTBS0fHSeTnN+P3Tx/VeQfo\n9R8RCDhxu6cTi/0narUVg+FpBqb8TdZNYIzy8maKivz09dVSWbmdYDBBLCbD7Z5BR8fgFNnxeGbB\nTUGBGY3mJWy2RWmfEwxmr0bUyy9P4YortrBgQerU4LkmHo/z+99/wq9+NQ2/f+QU6NXVNszmq9Ju\ne8qUz7j99twatUskEvzlL5+wbNk5pBtISaUejjgi12tjCYLwVSCCKUHIMVarD41mDz5fZjfwyfWj\n1a6mre0eAFoPm+lVW2vBbr92yFl9fXKgH0j9pL+wcBl9fdnJgqdWD4yGFRUtRastoK3tBmpqMqv9\nZLUuRK1+g0AgecHY4cTjlSgUezO6JoBCYcZqvfnz14GAYX9trclkoLXVgE63hFgswr59l+/fbqK6\n+l3a229Ps50oCoWT2tptQIRg0EdHxyVAIRClvPwj2tq+O6qexWKdZCsdfn9/Na2t2Zk2OJESiQT3\n3/8hP//5acBwU10Pqqp6E5st/Ux8dXXN/P73Po4+OnWx34myebOFO+6wsGXLHNL5jDng0ku3ctNN\no0mkIgiCMD7E+Lgg5Ihdu3bz5ptrsFpPIj9/D0qlI6vtFxZ+SlvbJUn3q1Rhhqv/1N19OTU1q9O6\nhtd7PXr9uky7yKHrk2y2M6mt/T1e78m0tZ2JSvUZcnmmKY+LqKhwAuFRndXQ8AoeT3qjcsMJhWZQ\nUHB4EVkJ2Sq+OxZqtRy//9CU00ba279Jus/Y9PqHKC19h66uEtraLqaj4xrq69+gqekl9PpnaWsb\nfeIPqXQq2fxa+sc/qnjjjV1Za2+8bdnSzAUXrOTnPz+FVIEUQFFRbNgacMlceaWbhQuPH0MPsyeR\nSPD661u5+eZeNm8+lUQide25A2QyJz/5Sa2Y4icIQk4Qn0SCkCOWL1+O3R7A6y2gq+syampWAL2j\naiM/34ZGswMYut5IJosw0hSaQCA27Hkq1VbC4dpR9SMzMfT6v1FQ8BEyWSexWDEFBdNJJAZuFuvr\nW7FYMn8SbTZfgVz+ySjP0gOZp6m32+dSWtqc8fnjJ0IslvmIG4BMpqWr6xb8/nkMfJVIsViup6Xl\nKqzWGxndxAc/FRV/pL8/nRGTOGVlTzNQr2pkLS0zuOaacu65ZxVO5+jeSxPttdd2cPzxBbz77nyS\n1eE6lEazko6OWWm3P2/eJr79bcMYephdd965koULp7Nz59GjPreiwszcudkrqi0IgjAWIpgShBwx\nb948rNYNtLcP1Ilpa5tPRcUzlJa+zXBBzgHl5etoanqD+vonKCv7BJ9PSUPDUxwY5ZFIetBo1lNc\nvJuRMtNpNBIO1Dg6VDBYhULRk9bPIJOtHqYeTgidbgVKpZOGhreYOvU1jMbnyMszA4cmeAjgdlfR\n31+ERrMevX4ZkYgXiFNQ8C6hUHp9SE5LUVH6aaDV6iVYLMeO8ZqgVI5nMpHMNDYuweG4kdF+Bcjl\nDiBKfr4Vl6sma/2pq3uUrq578HiGS4pxqChG49N0d3+NqqodNDS8lrLtYLCCf/zjNObOtfGrX63G\n7U4dhE00t7uX732vm3g8/d9pJBKgry/d+lBhLrxwJ01NI6+/mkibNuUDmWbdk9LS0pHN7giCIGRM\nrJkShBxx9NEzufDCy0kk/nP/lhq6uu4B/BgMT+JwXEokcnjqYz/RqJWWlsEL0NvaajEa/43JdAN1\ndYuxWm/C5xs5e1d/f0uSPfVoNJuTnieR9KFSWYnFlBi0q/DHj8De1fD5fp1uNS7XcZSUfERb22Wf\nb1coVlNevgqNRkUsVklnZxPhsB44Fo/nWDyeOGAG/CgUMszmW0bsf2oSFAonAyMaI2enq6h4D7Xa\nitlcNqYr1tWtxGYbe0CWfXIGppEdCK7TC6rq61eSSMSIRCLYbLdkrTexWC2pRwDDGI3PYTJdD8jp\n6DgFjcZKRcUzdHWlXodmNs/k5z9P8MwzD3Deecdw440VnHjilGx0f8w2b7bjcDSM6pxQaBpabRs9\nPakzbZ588iZ+9KPs1H/LhjVrWti7N7007sOJxXqprs6ddV+CIHy1iZEpQcgRe/bYqK6+j+Lifx+2\nJx+z+SYqK5eQl9c+aI/R+B5u9xXDtKbBaj2Z+vqHaG8/kXRSWycSyW9mbbYYcvlwozp9fLfycj4L\nzGR7eBqfdvyIt3pu4Oymv5CXtwu9/gHy8rqAInp7Lxt0ZiRyMk7nDZhMVxEJWjlP92OKNYd+JEkB\nI6BBrU6k7H86Ojv/H3r9YsA/7P6KineYOvV1ZLJSotEiqqrWD3ucUumkvv7NEa8ll/cgl5sIh7Od\nSGTsWlsvorz8RYqL/4JGswmAgoLPUp6XSGgwma7PaiAFEI87ge5B2woL30Au37P/VXBQIHWAz6cH\nQqRPgsNxAm+/7eD00xWceuo6fv7zdaxbt5dEIjt/Y6Px3nv7mD9/DeedV0Mg0DCKM+NUVCwnkUgv\nYcOVV8pyYoT04Yc3ct55GzjvPBV9fQ0Zt3P88RJUqsyn3wqCIGSTGJkShBwxfbqeaLQSj+eyYfbK\nsdluw2B4FI/nVOTyDhSKKF1dNSR7JhKNNqFQ6IhG06s9o1AknzIUCFxOWdlyursHr526qOkv/LZl\n+aAezIr6eL/lP/iHvJR7rLuBVFOLolyU/x6PtD3FnIYFOIeZzadWu9L6GVKTYrXeQV3dY9hst3Lo\nR2BBwRYUCg3NzQNp3SWSQsrLD08CEqWu7k1CIT8WyxkYDG9hNg8tuFtYaEOnW4vJdGOW+p1tcny+\n2QQChVRXb6KysgOXy0N+fh9+f/IRzFgs9VqeTLhccykocNPfPzAS2NDwAp2d01Grfeh0S4lGTZhM\ndzHcNFS5/DgqKt6nq+uctK7V3z+XlpbjqKp6A5dLwVNPqfnTn6Q0Nm7ghBPghBPgoosaqK2tyOaP\nOITL5ebuu/tobj5p1OdWVDxLV9cVQOpRqcJCK2ecMbnT+0KhMI89to3/+q9yXK6GMbWlVu/j8stl\nyGSZJqMRBEHILhFMCUKOeO+9DXz22chpxS2Wo6msXENHx3WADxgpk5cDtzv9RdpK5Ug3ylLy8hxA\ngIF1DnFqK1dwt/PJpMPbwWIjkh4ZqR74H2t8lgdMTxAGnP3D3xy2tp6B0fgMJtN1ZDKgLpNtJT/f\nhNd7OSDD56ugru5BuruPIxA4GYCaGhvNzZd+fk4iMR2FYi2VlZsoLnYCcfz+Xmy2hRxI5OFy6aiv\nX4bDMQ+D4X08nmpcrhMpKfkwhwOpAQUFTgKBRtrbD6bDNxj+SUdHCfn5dgoKQthsFww6p719Dlrt\nM/T0ZDe9eyx2LCUlb9DfPwWpdBtu90wCgRkAeL0jn+twzKGh4RUgSDqJGwZI6ehYSMf+ZTd1dc+y\nffsitm+HRx5JoFabmTFjA0ceCdOmSZgyBY49tpypU/UZZ5DzePr46KMWtmyJsGEDrF9fgMs1+hpY\nOt0HSKUNpBNIARxzTAfHHpveA5Xx8pe/bOBHPzqesSRzyc9vY8ECE3/60yyKiiYiIY4gCEJ6RDAl\nCDnA6+3nl7/cAoxcMyaRmEtHx4Ebo1QpkUtQqTYC6a3Z6eo6mpqaf+Bw3MlwAYvDcQONjS/Q2noN\n02uf4kP7rSQr/RkH/qX+HomELuV1Lww8gZKBpOWlqmYcnDnMUVWYTFeg17+H1Tq6gsB6/WJcrnkE\ngyfT1LSEWKyHvr5Z2GwLKC9fSWnp08hkUXp75w05124/G6k0RGfnccO23d8/l/7+PvLz19HScg1y\n+W7Ky9+iszP1zz3ZtNoQLlfJoG1O5wzicS/5+XZ8vqEp4RWKMDLZ+IxOxeMJjMZnCId7sNu/M6pz\n29ouoabmFRyOoXXS0mG3H4VSuY9weAogIRBoYNOmBjZtOnBEAnAxdeqzlJZOp6IiQXm5hLIy0Ggg\nLw+k0oFiu7t2WampqSccluB2Q0cHWCxgsRTS3z+L0X/tNmMwLCcWqwekdHfPJBBIN5jwctNNk5eG\nPx6P87e/reGppwrJPJAKcdFF6/nzn5uYNm24zwZBEITJJYIpQcgB//zndjZuvDvLrebj9SpRKNqJ\nRJKFPQd5PA0EAucjl68mGh1uhExKV5eB6bV/4EP7D5IGUgdIJMnTsB9QpPmMBa6BdUlK4MrQv9nF\nN5IcnY9M1p1kX3IqlYZAYCBLXEvLpYP2OZ2n7/+/BMPXfqojnjwB4n5F+P3nAiCTdROJSAmHzx11\nPydaPD40k5rfP/DvrlTuxG4fnHZbqeyirOwdrNZbx6U/7e0LAKivfyiDs5WoVJmvCaqp2Y3d/rUR\njpAA5fj99TQ3p6rTNHKil9ExU1f3Jmbzd8ikNtmMGZ9y223Z7E96EokEb765jb//3cXbb59BOrca\nFRUmLr3UxbvvFlFe3kd9PZSWJjj3XCnXXnsqEsnk12YTBEEYjgimBGGSBYMhHnvsUyorLXR2XpPV\ntr3e86ivfxGLJb12w+EpVFc76O9/n76+oWtQfL6TmFX4x5SBVBTwhlIX4Ty2YhlzW32fv67zmxlI\nKDD0KXZBwUq6u0efjjsU6mQgtfxIayzGfqOWn78cqbSO3t6Rp2rmikgkefDhcBxJSclWenvnAKBS\n2SgtXTVugdQBOt07dHYuyOhcr3caBQUb6O8f/ZQ2pVJOOn8DodDErtOpr38Pi+VOyss/ID/fQyzW\nT2/vHHy+dGozxbn88tCEByE9PV5uuWUTS5bMBeakdU5ZmZkXXogxf/5cmpsd1NcbyctLXbRYEAQh\nF4hsfoIwyZ57biOffnozLtd5VFdn8lR+eFJpMwbD83i9o1uX0d5+Ojpd8ppOL3f8k/+pHLl4rh9I\nJFKPFFRI3YNel0Z8DKx9GUyp7EKt3oVWa0EuNzOwdis9Hk8+2QiWRtZLZaUbn2/aOF8ne6RSW9J9\nodAJaDQfcSB1ekXFFtrbsxvoD0ej6UahsFBVtWHU5zqds6ipGZwwxGB4lpqa5xnub+pQMll6X4Wx\n5OXexkGEYLCCioqncDqnYTZfic12E9DDlCkvUVn58Yhnz5q1ifvuGzp1dTwlEgluu20jS5acAaSX\naRDgmmtszJ8/kKZ+6tQaEUhNoL4+H/39fiKR6GR3RRC+sEQwJQiTaPXqNh5+OA+QE4uV0tV1OVrt\n62NuVyIxUV1tw2y+Frd79Df4Dsc8NJqVw+5LJApRh5wjnl8CnFKyPOV12jEOfq0sZmDK3WAGw1pc\nrjsxm28CrBQXP05d3XMUFLQhl9soLt6DQuGisfFNior2DTpXq5Uy3h91ev3LmEzDpajPTXJ5J37/\nyNMwOzrOpbx81/7jo0zE10Vnp4JIJEQgEKG6evi09CMZyBR3MKCSyVQ4HFdSW7seo/FFpNLmYc8L\nhdIrfhsOqygoeAad7nlqa1/GaHyN2tqXRt3P1HyUlX0LhaKTrq7bgPqDe3xnsG/fVXR21mM0vsJw\n7xeAaDQx4UHJ449v4vXXR5OdMMDFFy/lvvtEzaiJdKAMwLp1nzF9+k6OOGI3P/vZiknulSB8cYlg\nShAmSSKR4Hvfc7B27cE1GLFYJdHoEdTXvzymtisqVmC3n0mmIzLBYD3l5dYke+VYlBWkWkp0sncF\nlbqtIx6jjA2+xt3eVmboPxy0rbx8Fx0dBycWRqOn4vHchc12LZGIAzBRVLSe8vLHaW29iKqqwcWH\npdLUa7fGLsT4j35lj073Ip2dIwd/0ehRqFTNNDU9j9OpH/c+SSRmqqr8RCKz8HhORqNxHLLPQ3Hx\nrpRtuN1HU1u7kry8jykvf4Ng0ArIsdtPx2S6muLiCFOnvoJave7zc4qLV9HdnV7Wy2CwjP7+2bhc\n12C3X4nJtBClcmyFnYdTWvoD/P5bsdvvIPnXdD0m0/HU1Pw1SV83Zr1fqTz2WIT0MyrGOfvszSxZ\ncjFVVdn/HQpDtbZ28aMfrePSSx/mZz9bwWOPvUNxcRSb7Tg++iifhx5KXpxdEITkxJopQZgEK1a0\ncP/97axZM3Qxe1/fdHS6lmHOSl9+/tgLdFqt51JY+Or+dOKHkvBo4AleqPiUE4s3okz4OTawje/b\n3xl01L0dH7F06mo6XcOvmzhS/wKPm341aJsUKJQdOv0sQUnJPpqbh19HEw6fvL+vB6cdRiKDc2kH\ng+mNOoyFTJZ6fVgukcnSq6FktU7MaJtO9xYSSTkm082fb3O5ClEonEQihdTXv4zVehpNTS/j89XQ\n2TmP4YNXCYHAEcTjlXg804lEBk9Hdbtn4HbPoKnpJVpaTgR6UKkSeDyGtPoZi5WgUOwjEjm4LRLJ\n/teo2/13amtfQSJ5C5ttaB2zg+rp7j6bhoYl+Hx5BINBfL5LAClFRceTSCQmbM2U1epk69b0sljm\n5bn43//dTGNjtUgsMUG6u/u48UYTq1efiMGwllWryjj66JnodPns2QPr15+EyWQmL28bt946NJOn\nIAjJiWBKECbAa69tZelSJzNmtLJyZTl+fzXvv588UYFMFh7T9cLh8jGdD6BWm/B6h18b1ec10uc1\n8krXxQBs0S/h27wz6Jn0nytPYX37xcOeL5F0cpPvfvTDTFEqOORTqbR0Ja2t6dfKAnC7IxyanS8a\nTVHoaoxKSp6nvX3klPa5JUogkKJ40wRTq9uwWgcHDW73dKqr30ap9GM23w7IaWmZCvRSX/88sVg1\ndvv8IW319KROejBQKyoOOIlGU6ZrPEQhKpVrUDAVCsWBDqBqFO2k7CF2+1VMm/Z2yiNDoVm0tR3I\nvLid8vIHkMvl9PTEcDjqqa3NZr+SW7aslf7+E9M69rLL9nHvveeNc4+EAzweH3fdtZnVq88AwGz+\nJkbjm3z88eCHJU6ngV//upsrr+ynqCj9NW+C8FUnpvkJwjgzmTr4+tcLefTRefzzn4W8/vpFvPfe\nyOsKzOa5VFY+l9H1ysruI5GIpD4whcpKO5Dek+ZITD7kyUw0kUAhG35RcyJRyT+Uj/CRaugIiT7+\nGZDAaHydYDCfWGzmqPrd13cCJSUD0wslkl14veNb86m3dwHFxfZxvUZ2ydBocuc5WkNT0t/PAAAg\nAElEQVTDM3R0DFcfqo729hsxm7/J4Od+JVgs1+4vIp2Zvr4KKioeR6Xqp7t75GQqg0lRHrYMyek8\nGa32g4z7MpJ4vH+UZxyN03kP7e3fQqs9YUICqXg8zmuvbeXxx9Ndn5Vg/nwxGjVR1qzZxwUX7OKF\nFw598KBKusazpeUYrrzyEyKRCE89tWRiOikIX3AimBKEcRIODwQ0f/vbvv1rMgrZs+c60llTEA7X\nolKVAMmz6h1OrV5Obe2b9PXdS15e5iNbBQVt1Nc/jt2ebuKKOBdLHh4STH2/azXnFP9P0rP8oUJe\n0g0d0Tmy821qah7BZDqNQGD0aa7j8SY0mi0MjDxoKC4efW2q0VCr9xGN5v5HqULRhV7/BAbDY4TD\nubNGRS5XEYmUjvq8eFyCStU56vNKS1soKLARifgIBucwcsr8oVSqw/+tFahUmRakTa6o6ClaW8/O\n+Pxp08Z3RBbgBz/4iGnTNnP55Uewfn16WUMLCvZw7bUi4cREueGGTtauPZH013RKeP/9s5g6dSXL\nlm0mnrrQniB85eXO40lB+BJIJBL8618f8dJLXlQqGZ99VozFcmRGbZnN52M0PovJdF2KI9vQ698l\nEunAbv9PQIPbXYJKZSMYrBvVNfX6dXg8QSyW0dQTkvCp/AhgaBbC4njfkG1SqYfTjY9zv+2/OaV3\naLB4T38rL1dIcKAdRR8Gs9mupa7uT8jlM2hruyjjdtJRUrKb9varx/UaY9dPaenzWK13k2vP0BKJ\nocWD09HWdi1G40uYTFeN6jyt1kRLy7VMnfoabnc6vwsPRuMbSKVFhEJhXK4ZQ47IywsAXUB6a9FS\nqal5FTiSvr6SjNs4YZxr9ba0OHjwwUZ8vvrUBx9CofBTUvLFWmP4RRGLxQgEwvT2eti2rZ3e3ghV\nVSuYMcPH0qVnMFz9vuHJaW+fTVvbbmKx2P5psYIgJCOCKUHIkg0b9vHtb29h27aTCQZrs9CiBJ9v\nFgUFH9Dfn/wJdX39ciyWW4CD02x6e89Er38PqzXdYCoKBJFKzfT1fW3U/fwscCEOfsvhJXVb1WcM\nei2TuZlXfg8ftCxOektfADxmuZcFNVNodZyR5KhU8onHa8c9kALo66unsnIbnZ25u2hbqWynr28K\nuRZIlZS8QFvbuRmfb7PNprHxWVpbF6V9zkBW6DihUDrT0vowGN7HZDoGSD7d1GS6gerqtchkq7HZ\nFqbdl+EFUavDtLSMflT2gMLCVr72tYYx9mNkMpkMjcaNz5f62EMpFJLPU3ML2bFtm4WlS9t5/vkg\niYSXvXtnEA5Po6HhQ9ra7uW449YyffrH7NmT/kjn7NkreO+9m1Eoxp7MSBC+7HLrm1UQvoBcrl7+\n/OdPWLBAwrp1V2cpkBrgdDYSj4+cLMDtLma4IrbBYOqbxYICGwpFDwbDv8nLW4nZnNmNoL3rdO5o\n/NmQ7cWSg32XyXq5pe4/+LgjeSB1wMxYP/cH7qakePi6QOmIxyXA2BJ5pKO//0QSCRf19R9QWrpl\n3K83sgiFhRvRaHaiUnUikTgpL38LjeYDgsHMg5bxUFCwhqIiiMVGP8XvgEhk6v4EEOnr7KxHJttK\nMJjO6Eg/ZrOBkQKpARLa20+is/NUamrGts7EYHgRs3loYo10lZRY+cUv/j97bx7eVnXt/X80y7Ys\n2bI8SLYl2c5AgBDKDIGGlCGEGQI0BCjQcuktdLidLrfDr29v574db7ktv5a2QJlDAglTSphCSBgS\nCNAkQAZbo2VZliVZsjVL5/1DGexYtkaH6XyeR0+ic/beZx9Zw157rfVdQ5jN1fGSTYXV2sqvfx2G\ngkUSJtLVlUEuF/dxK2XrVgfXXLOFiy9+nQsvDPH975/M9u2L2LHjQpLJbqAOu/1CoJY331yMzdZa\nxKgC7e2vIpXa6O/PsGXLjhm+CxGRjwfiN5qISAU8/vibfP/7SbZvnyk1tzqamqK43VO3UKnGiEQm\ny39ns/l3fyWSYbq7X0QqVeDzNWAwDKFWt5JInFfBPCVs8N7Cj4yv84OBZw8cbU2+f+D/Cy1/4699\n9xQ94tXBd9nZ8S1+MXoPmUzp4U5e7xWYzWtxOpeV3LdUfL6j6O7egEw2s2IX05PFbP4LTufVwBDN\nza8jl8PQ0MUf4JymJpWK4vUWl2czHem0HMhQbO7T2NgcurtXIpPJ8fkKtdZTU/MqsdjkEgb5SKUM\nJJNWamvfJBo9vqg+h6JQGEinyxWOSPL733u4/vriVPUq5eKLj6GjYydu9/zCjffRWsyaXmRavve9\nF3nsMT3vvVdsLKeEZHKqDYE4Z5yxCrU6iFw+wooV89i7919EIgrOPLN876iIyCcJ0ZgSESmTt992\nctNNNQwNlbdoKhaZLAFE9z0OXawHUCrzq5rpdEMMH6K90NX1JAMDKnp7L2e/YzqTeYHGRnvF85TL\nogzJJxp1XYFXgQRNDa/zpdDdJY/5E/fjDLffwFPpm3ANXljqjFCpShMXKI84nZ2v09eXT5FuphjF\nZNpMKqUinVah14cQhCB9fTcCtYCeoaG5h3E+paPX2xgcrDyxZ3BwKSbTXchk3bhcnymqTyLRhEJR\n0JICVNTWpohNdvxOid8/H4vlnzgcYUBbsL1a/Qo63U4EQY/PtwxBqES2XopcHq+gf2nU19dx6qkx\nHnmk+D51ouJ2xWzZoua996oTVnz++Ru5+WYTF120QsyNEhEpE/GTIyJSJj/7mYOhocnJ6NUmmxUw\nGrfQ1LSLtrafAbnFklr9JmbzE3g838rbTy6fGMakVO4lkwnuC/c6+NEfHf0MiUTlCeFXNv6Q212r\nJhwzpMK0NK7hN9HLWB4oL2Tkjv619NT+C0hRakiRw2FCpaqsAHJhsiST5QsFlIpG48RqfRSPZwFD\nQ8cRDC6gt3cpfX0ryBlSHwVCJJNHIQj1VRhLi8dzEwpFfhn+fHi9R5NKFafyqFCULuPtcCyhu/vx\nIlp6aGsLMzh4JfX1UurqVpNIVKK0mKKm5vCKOxx9dGmvTyYzQxP5BLFoURRIVDhKkuOPX8sbbxi4\n774AX/nK7dWYmojIJxLRMyUiUiZ79xazs105UqmUgYEzAVAqW4HdwDHodHtwOq+fsl8qddArYzZv\nIpHYTDabb6c8QDBYeZHfWsnkRdV1sQGujy2veNfmIdv3+Zt+Jau0X+ddz1moVAnCkWKK+arQaOIk\nKl13TIuSePzwJWmr1buw2y+lGK9H5YwikWxHo3FSVydBpZKjVMqQShUIgoJYLIjLVapgCVgsK3E4\n/q2qM81k7Iwv1jwdzc1rUSiKq4ukUJTz7pVgt19ER8dq3O6pw0zr6nYyONgDNNDbez4SyQhjY+Xn\nkNXUeDn55NLU9Srlwgsb+eEP/QhCcSGug6Wr2Yscwq23Hs/DDz/Ljh0XULzk+UGOPPIJjMZ3+PKX\nzyCRSPHaawq+/vXD6VkXEfl4IRpTIiJlsGePE6fz8HgjlMqDi+ZkchYWy704HMeg0UinWZhkicVe\no7XVTTrdQiolZ3Dw2+z3ao1Hp+tlZGT6IsKFaG95GXNqcrhhtb5gWhH4buAdOrM/p0b9U/7Y+l9s\nKMKYSiYXoNU+zfDwUVWayWQ6O+/D5bpmxsbPGQhRQEZ39/NEIllmypDS6Tah0bxAKtWJRBJFIpmD\n17uASOQkIpHJIZNz5z5dwuhJjMbfEgwuQak0Us4icDocjqswGF7H7z+lYFuf7wIslteKGlcuLy9U\nNJvVMTo6H632VcLh/J8vhcJLKLQ/H0uFIFQmGhGLdfHcc1u5/vrKN0eKpaenlZoaN9FoccZUqep/\nIpNpbGzgV79qZenSEaD03yGNZoSHHroFgyFXfuKzn63yBEVEPmGIxpSISBk8/riL4eHyC2pOTZLx\nEucA2ezEJINAYCF1da+SyUyXfCDF6/0BAB0df8Dt/uq+45PDwOrrY4yMFC4kPBU6rZ0fJP+dm33v\nlj1GsVwX2gXAI4adyOU+0uk47S3v0+87i6kECLJ5al1VE5lMDRTnmWpo2I5cHsfvL5zYrVIN0di4\nm0TChlKZoaYmTV/f9VTra1upfIdkUkJOqU6KybSWWGweGs2J7Np1NjlRh0Lvi+I9clrtWgYHb6Kj\nYwuRSP7Fvlb7NHr9KD7fXKLRUnNCGtDpIvj9hVsqFDIGB4sLp5PJyverhkJzMJvXkUo9SCx2EtBF\nLsQ2SX3942g0zYRC5Xui8hGPV9dILcQrr/QRjRZfhLf58Nl5H1sEQWDdureRybpKDJsMMmfOBkZH\nW0nMrLteROQThWhMiYiUyMsv7+F//qfaeQkZLJa1BIMRmprkxGICSmULTuc5RKOQyxXKLeoikW4s\nlj78/tlFjCuQTE5f/LamphL5cIHLG37Azc6ZN6TGc3ffb1lRcz8aIcIRvhg3WG/jOfvPUal6EQQl\nyWTngbY+Xy0wRq6CVfWJRLRotbsJh+dM2aah4R202kGi0SyhUBdm8ys4nadN2b621ktr64vYbEuQ\nyxWk09WtwGoyPUYsNpdsVoPRuBqptB6P53RSqSZaWuzkjKTChlI6XbyhoVZnSCbjOJ1T1f7y09Cg\nwG6/ivb2V8lm3yUeLy0nMRYrLnTPaHwXu72QWMUoXV2PEQh0Fmg3PYODkEgsRqEYpaPjWeRyCAa1\n+P0XEImUV7B4Omy20vIKK2XDhhjFF4OFri6xxlSl3H77C/zhD1dy6aX/4v33Vbz/fmH1RqNxJZHI\niVx7bRaXq59Fi2zs3Hk9KlXxfzsREZH8iMaUiEgJxOMJ/vAHNy7X4qqNKZGEUat34HAcD1gIH3Ck\n+LFa7yUa9QJLJvRxOM4ucnQBQbBjsTyLUilBKk0DAonECDKZEkGQEQqV75WCMGd5n6qg//Rc3PVt\n9qSOYZH0Gb7kWcOCdC5GqAa4JHYwxvEe+6/4S8smlvleZ1O9me/V/JPgyCwArAYJUuEudrpvpdqh\nZQDDw+djMt2HwfAO6XQ9sZgKpVJFf/8pyOUDdHZuZGBgAaHQuQf6CMKDwFTGVAqjcQO9vblCtNUz\npPoAA93dj+N0nk86nTOyXa6JOTbpdPFhbclkMW3jdHU9gsNxAdlsfsNeKnVgNm/Fbs/lF/X3n0pP\nz2P09pZmTBUrQiGVFs53lMuHsNmOAyoLEU0mtYCUVGoWNtusisYqhk2bBARBQJInh3Em8PtLC4Oc\nM/Weg0iRPPWUDY3GwqJFY7z22mSDXCIZpb19F273cdTX21i48A1mz4YFC1x84QvL+PKX/5djj0U0\npEREqoRoTImIFEk4PMp3v/sHnnrqknFHI3R2vsHw8Dyi0dJrw6hUg7S2Pkc4rEajUaDVbkUQUiST\nSsbGQqTTUQThaKzW9YRCGpJJBdHocRRbUwekDA39FwbDozgc44UC0rS1rcbrvbzkOU9Ex1uti7nG\ntbrCcSZzivmHbLF/HUHQ8j4reLnzEV5xLWdyRS0wkeGHvk0AzI/0Umv4LI9ZT6dFGOEWz2P8S17H\njdJryWZnJs/N47l23//SQJSammcxm//OwEAPNtsyDg3dHBg4loaGdwmFJhoLUqmf1tYnDhhS1SNN\na+ubpNP6fap/U3uUEonifxbi8cJtzeZV2GwrmPo9m8Vi2YjNdt2Eo07nidTWriMaXVr0fJTKaFHt\nIpFUwTYtLX14PJVvmkgkBtTqMLHYzBbR3c/mzcfwpz9t4dZbD0+tKYulUIvxoiBxFiwQF/CVcvXV\nbbz55h955pl5DA93TTp/4olv8dJLJ/GZzzzA9u0WfvzjoznhhIPfNbfffuthM7ZFRD4JiMaUiEiR\naLUaAoHjqKvbhcnkYGxMjUo1iMNx9b5d9MtKGs9keo1Ewkk6baS2tg+PZyFDQ/tzadJAnGAwF044\nNAS5fCoHnZ33IwhaRkePIBQqJldBjk6nPCSXRI5GU4mIQYaTu+5GJ0+w2PtmBePAvxvP57sDz2Bm\nYvD/qOQEBGH/HKW867qST7WluH/4Vk5NTZ8Hdb1/G9f7tx14fmwqzGPtX2ZN/30VzbUwckBLLLYM\np3OaVnIfqVT3pOM1NT4GBk6ncK5SqfiJx7sYGSlcfDYWkzM+rHQ64nE1OXGM6STZQ1itK/F6u6iv\nHyESGaW5eZhEQkFdnZJsNobNNtl4zGbrUKtT+8Jci2N0dIzCBXzDhMOFxRIUChnVqB6SzVpQKv9V\nUq2qyqjhhz9sZv78vXz60zPvCTv11FpgFNAAKbTa95g3L8oFF0iZPVuKRgMul8C6dSk2barntNNE\n11SlXHbZmZx11gl4vWGGh99g69bxvwMRYrFn+fWvx7jtttmoVBmOP37ehP6iISUiUl1EY0pEpEhC\noTBr1yqIRi/fZ5gcXHBmMqXlHbW3b0YQthKJdDM8fBJwaP6GnNziZDxKYDYuVy5Xqrb2NSyWv+N2\nX04ms9/jEsVgeBuVKoAgSBkamoVGs5VAYHKSezCoAvxMLgRcDCmOjK/h7wNPltH3IP/VdhZ/HniI\nFzpf53zJ3/i58yH2B63E04fmv0ixea9leZuJ+bUv4kwa+If7m9iUWt7RzeNLQ6/SytT5GFZpJblh\n1aW11YXDsWjS8bGxeZhM9+LxFJMPVzxq9TZGRk4vqm0oNI+urvuw2T5XsG1DQ5BIZOo8pZqaV/D7\nLyAa7UKne5dkspl4XI/Ltd+/OLWxksk00tiYJBAoatoADAxcjMn0Mh7PmVO0iGG1PoXdfkHBsQSh\nWrk9curqYoyMVGm4IvD7u/n611/hzTdn3pg6++wjOfvszej1aa65Rse55x6JWj3Z+ySXb8HhSKBW\nV3uj4JOHTqdBp9PQ2dnG174W5Mtf3kQolPt8SyQ+PvUpHaOjES655LwPeKYiIp8MRGNKRKRIkskU\nTPCeHFwIhkJaamreIJnsIpPJrxLW0PAIen0DEkmAYBCi0YUkk4VV3aYiGj0Fh+MU2truQS7vJBxu\nRCZ7Er//6+QMsTjQTyRyInL5ZImzmpphyjOkANSsDp/BV1nHsZRfhfOkyC7k8jh7XGfzPyzm2c6r\n+WLmD3zV8zzxVP5FutP7GZz7jM/Tas4mHm9BGDLwavdPWNf3gymX51/qf5KnOh5nj/visudbLZTK\nfMGKABIEoTgRhVJoaQnhdBbnicxk9CgUxYWsqtVjTP4ZObjJoFbvJRjMSZWPjJRe4HpkpBtwAsXW\nTqpFKnUxWXBEQKt10tj4Knb7ZynG46RSBUud7hTs9/QdXrZvn8Mrr+zltNNm1qCSSCTceeccWlt1\n1NRMHcL3/vsS5HLRI1JtrrnmZPz+J/jd757B4VjCkUfu4Pe/v5nGxmoUxBYRESkG0ZgSESmSlpYm\njMbd9PaeO+lcKLQU8NDW9hix2IlEInqyWSP7P2JKpR+Vag/BoILGxg6yWRPxeKmGVP6CpF7v9eRC\nAAeA/2/cGTXQQzoNFssOensn9lOrK/ux1WmO5Nix8g0pgMvH3BzT9TzbbMsBGe+6LuZXrZ34TN8j\nFi389RSLHRQHWN/3n/ys5Rm+79uct61NpsA+mO81D3N4CuDmMBq3kUoN0N39EH1956JQhEmlrECc\n7u7V9PVVQ9wkDciRy9/DYtlJKpUTHilOgMNHODy5ZthkYgwNjTcSsjQ1/QOptAG1WkkmM4hSqSIY\nLD9Uzu8/DovlzzgcXyy6j9t9DS0tj6HRSJDL1SQSw0Qi7yCX64jFjia3yTBdWGKOeHys7HkfilJ5\nqFtqfBhlllyoZHUVQlMpA3/60+4ZN6YArNbC+WD9/aBSiUp+M4FUqiOVGuXb336Sk0/uFg0pEZHD\njGhMiYiUwJIlrfzpT1OdNeH13gR4AA8Wy9s4HBfR2fkSiYSbwcHvYjavQqHQ0Nw8hly+Fb//UxT6\nGMpkI3R2rmZszMvo6AXEYvnq7yiBqTPBvd4uIMT4Ao8Ox7G0tf0Jr/eWaa8/FVbtMExZNLh4zsiu\nYRufZf9C3z34KX7Karqsa9A1jtHffwzJZDGeEhW/Td7BMz2vYM1s4x77Xyb4H/TpBMiSaLUv09zc\njyDUk0pJSaWypNNx/P5l1NZuoaVlJ3J5G6lUGIejutUsFQof2ewAdvvNQBaV6p9IpTra2zcTiyX3\n1ZEqz/iQyXaQySQxm3cRDneh1caIRg309l5R4kgawuHCxmVj4zaCwQsPPK+vf4x4/GTGxvbnZxTK\nXSqOTKYLicSBIBRUOtiHFJ9vGT4fQJaurnsJBH5OTuo9SkPDv5BKfQQCFwNZ9PrbaWhoRRBSDA52\nEY2eAKhRKgsbXMWSzeZUBlUqDy0t24nH36G21kA8biGb3YggmNFq64jFWhkYOINq/TQ/+mg3L7+8\nhzPOqG7YaKkIgsCuXQKzP9hpfGy59dbTuemmJDU1YgiliMgHgWhMiYiUwIIFxVScNAEmAoGXaGpa\ni89XTyJxDQBO5/iFrRuz+a84nV9kKo+BVrsbvf417PbPA1na2+/F4+lGEIrfeezsfB1wMDb2qQnH\nU6k2stkeDiaPl0YmW51d5m86VvJU+w3s7R8f31+DzZ4TJaivf4nOztfo7V0CTF+XJxiaz6bQfDaR\nYMjayN32XyIg4S8tp2GJ9NFR/wci2Zvo7T1jQr/Ozo309DyG378Au/1GQKCr64Gq3N94Wlrepr9/\nf76OlEQiV3PJbl9Y8dgmkxOP5yiczqsAGaFQuSPV0tqaxmabvlUweCIWy304HJ/HYHiUZPI4xsbG\nK4tVbkgBuN2fobv7Mfr6ijWmQC7fQ0fHO0iltfvUC/fXzKolFDoFi+VVmpoeIx5X4XJ9iUAgF1qp\n0bxHe/v/Mjy8AKm0cvGJ/Xi9OmCQpqb1uFw3cLDUQRZYDEj35WGmaWlZhVrdgtNZqA5WYWKxNn7+\nc9sHbkxt3bqLt98+gqVLd3+g8/i4IpVKRUNKROQDRDSmRERK4KyzZlNXt5uxscKKVJHIIsBLR8d6\nAgEP0ajpkBYdOJ1XYLU+gN1+TZ4RBAyGN+nr2y8EIKW//xIslgeJRE4nECguB0UqTROLTc7jamjY\nRW1t+eFFmZSjrH6H0onA3cPX8XnT/8UfXUggNPG1jUQWEYlksVgewOM5j1SqmDwvFc/Yf8anDKcj\nCAYGfScDcSTxKIIw+bVwuT494Xlj43ZstjOodgigUumt2lgTSRKPy8lkijc4piOdLkZCT4nHcymN\njfchl+vx+ydLNFcHOZnMVDlm+bFad7B379QeOYfj1LzHR0fnMTo6j/b2tYyMVEewRK/fSF3dGJHI\n83g8h5YiONRgk+PzLcdqvZ/iwzKnZ+PGNpxOH2bz4ZFmz8fevaOAlrqZqZstIiIi8oFSva03EZFP\nAD097SxbVoK8GG243Z+jufkVyKs0Z2B01ERPz1OoVAP7jo2hUvViNv85T/5MAw7HzYyNZejufgyN\n5k00mtfHnQ/DIYIQDsdCVCopcnkIi+VZZs9+HJPpPqJRH3Z7aXLu4wlmj6NaAmUL4362eT7PjxSf\no1GXb/daisNxLQbDP8nllxSDFK//QgaHTyG3KK3Ja0jlQxDUzJr1JkbjRkymXxZ5vcIkEvGqjZUj\njV7/TWprn2Fk5FOFmxdFDKm0cB0mgFRKj0bTTCazm1ze3sygVJamKy4Ixc1/Kvr7P0M8rijcsAAa\nzYtks424XJcSCq2gWMPcbl9Kd/cjqFSVG99jY1189rM/JJs9/CIY+9kvC19TI+ZMiYiIfPwQjSkR\nkRIxGqevcZQPh2M+Gs2/8p7z+xfT23sBOt1GrNZVGAz3kMm4cTr/HcifK5RIzKev7zJGR40kk3F6\netbQ3n4fzc3rMBhemtQ+lfLS0fEUDsc57NlzMR7P2bS2vlfyfYxnt/sCvtF106Tjm2ta+L3+2KLG\n+EXDUZzScz/nzrmDn5qv4Nah1/mR6gYatHvyth8YWEFPz/qK5l0ModAc9u69jLGxBFJp6cWYpyIc\nXozZfFfVxrNYHiIU+k+02lqSyWJCUKdGpXJiMj2P1boGh+P6ovu5XEsYGvoyLS13VnT96ShFplyr\nfQ6vt7PCK9aj0TioVIWvvn4vodD8Mnrq6eu7CpVqF7NnP45CMVTRPIaHzyQWq7YhXzwGgxSDYReX\nXVasKqOIiIjIRwcxzE9EpETa2yfXbCrMXIzGJ9izJ594RA6frxyxAxPJpGmCUp/BcDeHFlKNx7sJ\nhRLj+rXR338OPT0P4fEsJBYrZ/EpZd3oZ4nyV2qBrdIa7m9eyDrFt7D7TmCX5Rvc4fjHtCMoVHre\ndi0hkWziBdmVJDsFfu1aTbb1Rv4PdxMKH6pEJmVwsJ3Zs//J4GAn4fBRecetDmmamiQMD88nJypy\naJhm6YyOziYWq0Otfph4fPq/d2Pjs2g0w/T3n0o2e2j4nheL5SmGhs4lm23F622taF4yWYi2tudw\nOG6gnD02rbaXRGJyEeLqUZxRI5E40GoVuN35w/hKweO5Gav1GQRhGIfj2pL66nTPoNPF8PmWFG48\nDeHwIsJhaGh4lqamODbbQrJZfcnj7NlzJq+/vp3PfObkiuZTLosWzWbVKg9dXZW9Tz9qDA76aW0t\nt/yEiIjIRwXRMyUiUiKNjeXtVvv9TbS1banybPJd51qMxvGhfwkkkjeJxycWbc1mu+jtXU5t7bPk\nD52L09FxOxbLI/ueCxwaqjgUnMNt+hM5xfpHzlDs5Kn6W9ntXkIy2cTLwoW8op5+IXG+bwt63V4A\nMpkm/hb+AbtR8NXBzfyw5kYatHuBLFJpP6bmFzmp5xHmGTazZ895jI5K6e5+AJmslLDL4unsfBi7\n/Sx0uhGm8hCWQyZjwmjMV0sqTU59bhU9PU8Rix2Dy7Uck8lFV9cqTKacR6ulZTXd3ZtwOD5PNFqp\nByZHR8cjOByfp/ifhBQNDdswm9fS3f0w9fXbGRlZWpW55COdLqbmUxSjcStu9+RiyOVRh92+FCjN\n49fe/gQwG6fzUuLx6nhiQqFz6O29iIaG1+nufhKIlDhCCz/6kcCWLX1VmU+pNCLc5CkAACAASURB\nVDTUs2jR3A/k2h8k1133PNde+/t9NQpFREQ+roieKRGREjn77DnMnr2dPXtKC98JBk9DqdxKR8c6\n3O7zqEZyeX7kyGS+cc9V1Nfrp6z3Mzx8LWbz3SSTXchkUoaGjiGZbKSj437CYQOjoydgNt9LPC5B\nqZRTU6NDELJIpQLRqJ3Hsl8nHjkSvf4l7PaDKnk7nVfyy9l9rN3zX1PO9Ebr7xiwHdwtD43M4Uld\nD98YeZ+vDW5C1Xwd7qYkFwbf5aShONIhWK1q4go+j0wWpK9vBSbTWkZHjyI8yYtVPirVdsCEIOhQ\nqyNUd99JIJn0TThisTzI6Ggr6XQNXu8pxGIdB8653TkjWCoNYzSuwe9fiM9XPeMOIJWSMmvWM6RS\n/Tgc55MzHqO0t/8RhaKNTAYkkjhO57/tm8sQ2exruN1LyWZnSnjiIEND59LQ8ASh0EVTtBjFYnmw\npPDEYhkctAA2IP99qtUvEI8bgR46OlYRjR6/r9hw9QkElhIIZGlpeZLaWiV2+5nk6skBJOjqegSp\nVEEoNJfh4Ymhti+9dAqLF3u4+OJX+cIXGjj77HmHDi9SRbZscWC3H8mmTQsJhzcgl4+wevUyJBKx\ncLGIyMcN0ZgSESmRtrZGli9/nx//uPS+yeSJuN0BTKbn8XjOrv7kDpABBKzW9SgUUTKZ6YwBJU7n\nzQf6tbSsQSbrRSptJBzOyZOnUpvx+aYKdbIhlcbIZm+YdMaV7pl2lirZoQsLNb+U/4PO+uVcGenj\n5qHXkAJ7gJWqJh7quJVBYRatY28wNqbDYnkUp1ODQvE0er0WqVSFWi1FoZAhlUqRyVQIQhqfT8HI\nyKfJhT4e+lok0esfIhC4EK12J3V1dtTqOmy2nPJaLFaa+EEhurpWYbNdCaRpa1tFbW0tNtsFCML0\n4gTZrJaBgUurOpf9+HwL0WgEQqElWCx/J+eBlOJwfIP9Eud6/cvsLzarUHgJh89kKgOj2oyNddLZ\nuQmZ7H+JxWqIRq9mfBhrZ+eTOBxfYCaCLQRBilw+Qjo9+ZxavYPa2gaUSh8KxVO43bdSSL6/cqT4\nfLkaWW1tj6JQyJFKR/H7a7HZLgU0zJ792CRjCiAaNfHQQyZWrgzx6U+/wg03KFix4lgUisrFNkRy\n/OQnL+DzyXnppcYDG25PPNHBvHkbEARBNKZERD6GiMaUiEgZzJkjI6deli9cqxB6FIoAjY17CQar\n500Zz9DQezQ2rsbjmU0yOXWe1ng0mt00NW1BIkmRSJhwOg8aTyrVdDVMuphKKEwvbJ90bCcyfqc/\nnqxMzWbbZOPAN3wiX2xYyx2zNuKJG0lma+j3d5NMtELvRInsvXuPBwL7ahypgTrye/xG0Gjew2AI\noFRmGBvzoVTKiEaNpFIqwuHz6ez8J3J5GpvtugO9lMrduN3HTXPvpaFQDOD3GwA9zc2r8HovYeYX\n34WRStMoFDkVyFy432TGxoy0tNxBPF6DWr0Ln696KofF4HJdTe4zF8FieWhCfldNjYaZilpPJOZg\nNt+N0znRONFqN2EwjNLXdx4gIJd3c3j/llK83sny70rlm/j904fUZbMN7NkDXm8/3/vem4yMqPn2\nt5cwa5Zxpib7ieHUUztwucJoNCHOOON5urrUPP64lIEBOXff/SJXXnkq9fXVKwgtIiLywSMaUyIi\nZXDNNSeyZcsL3H77GZRjUDkcV9HQ8Dx6fYpAoPrhNonEjzEYfkswWEzdIQGL5WFcriMZHb2WnPdh\nonUUjZoBJ1BaDohSOlmF7eaOr/CK+6fkvGf5iw8HQ0fzYujoIq9STEK+jtHRExkdnbqFy7UcmWyY\n8caYRjNEIFC5mAGARDKKyfQsDkeubphK5eJgiNYHi8m0G7v90BpIE0kkZuHzzQLigKdA2N1MoQSa\ncDiuxWx+CKfzPEBPOq2a0avGYvMwGO5Ao1Hj9R5NPH4iOp2Nvr79hreEdLo6+WuV0tGxh76+5dO2\nUavdpFLPoNefxm23/Tvr1u1g5cqXgACJRC1LlpzCqafOFb0oZXDWWZNrEH7zm7l/E4kkMll1ilmL\niIh8eBCNKRGRMpBIJPzP/3yGDRueZfv2c8saIxQ6i1mz1s+IMQXQ338NjY3rCQZPnKaVgMWyEofj\nPKBh3zEph+7yh0JNwFhJ15dI/Fw/8JcJxx7RzuKdwBcYH6L14UFKJjNRbEAuz4W1VYOmprfGqcI5\nkcvbqzJuaexXeczS2roKna6WVErGwMAZhTqOQ0043E1Ly+YZmmMxKPH5Tsdkep3h4VpisZmtBjs0\ndDLwKfx+JSbTMyiVdxMInF6w3+EnSiJRuJaVTvcgBsM5XHtt7rth6dKjWbr0aAYGhjj77Bv4zW90\ntLX9k9NOq+Xb317C/PnVKQb9SUelyr/xtn37bubPL1wIXkRE5MOJaEyJiJSJRCJh7lwd2ydHshVN\nIhFCKh0mmy2umGwp6PV7CQSWTdtGLrfhcMzloCGVH7XaTzJZWlFYQWhil9oIscEDx9Y0ncOYrViP\n0wePWl2aATkdfv9RtLf/BEGwIJEEsdtXMHMiJJPRaDaiUsVoaBDIZOLY7RcyOFi+URsMHg+8AZxQ\ntTmWQjxuxuMxo9P9noGBrxyGK+YWwh7POXR0vFRVwZPqUUsk0ohe/940mzRRUql69uyZx9/+9g5f\n/vJJADzwwGPs3NmH2XwkGs0DzJ37H8jlj3D11U9x7rmn89vffvvw3cYnjCOOODy5hyIiIjODaEyJ\niFSAXp+pqL/LdQlG4+8ZGLitSjM6SCBwCg0NqwmFrpqyTTrdSk3NDmKx6YvsRqPN5BTNSpE3lpBS\naA48iwO70jNZi2gmSBRuUgTNzX+jrq4Fu/277Bd06Oj4I7FYPRJJLX7/lVW5znSYTCPs3n0Rw8PV\nGS+Vmkdr66MMDjZxuIQo8hGJXIRO9z4jIzNZc2w8UhSKD6/UdTh8Kq2tT1NToyUWO9T7mUKj+QqB\nwJ2AlP/4DxkvvvgnVq++hWXLLmDFipzBuF8oweebw9e+9h1+97v/ZPfuPTz55F8mXU+kckQBEBGR\njzZinSkRkQpwOIrZj8iSMyUmo9M9yNDQElpafgxMk9BTFhGSSd20Lbq6/kksdn7BkSSSDOXsvbxT\ne9BrcZHl27zp+lrJY3yQSKXJCkfIYrHcRTB4CXb7ReReQwkgwe2+keHh60ilZtPSci8Qrni+U5Mm\nGKz2gk3C4OAy6utHsVhWVXns4slmezAYdh/WawqCi66udUgkM1PjrFIGB8/HYNiEVDoy7mgavf6H\njI5+jf0//ZlMA8cee0zubDrNW2/t2Hc8t0nU0tKMTKbiG9/4FUND1dlYEJnI22+/Ryg0UrihiIjI\nhxbRmBIRKZN0Os3OnYUNDIPhPgyG12lvfwGrdS0m093kCrT6aWzMkk4fy9jYachk1TWmjMa3iEbP\nmbZNNBqjGCMplepBr3+9YLtDsWVPOZBpNSCcBHwUdmCTSKXrMJvvJJnciUSyq4wxQkgkO+nquh+X\naxnpdL7ixXWAlJGRY4nFTkaptFU47+nwMDY2Mzlakch8lMpyVC2rRzZbqdFbPApFgGTSgM22lNra\nN+jpeYT6+pn825WHy/VZzOa1KBR9KJWP0tLyC6LRM4FjJrS7885hXnllK7/+9V+YPTvnYUwmU7hc\n/QwNDXP66RfhcMgYHPwMkUi1N3w+ufzgB39i69Z3WbDgCPbssX/Q0xEREakAMcxPRKRM1q17G7e7\ncGjRyMgx1NXV4vfnEoyl0iBtbeuIRk3Y7TlBgrGxxfT0PEpv72Sp43Lxeo/HaFzDwMB4lTY3PT1b\nGRvbDrQSDBZXeNhofIGBgU+XPIcdziv5fvv9/K7/Ceaq3mNnySMcfmprnyCZnLtPKS5DQ8N7yOX/\nxO8/b9p+Gs3ztLaO4Pfr0Ol6GR4+fYLM+nRIpcP7JOzjNDa+QDB4NJOVEz2AqYw7go6ON/B4ziqr\nbzEMDnYhkexBEGbP2DWmw+frRq/fRiBQPRn7/IzS3v70uM/tufT2Qn39Zrq6dmKzLeHDs2GQJhaL\noVY/Rix2Mj7fAmBy3bd4vJ25c7s57bScGMXAwCD33LMKhyPBtm2wZcvXgPPo6XkDuVxcMlSLFSvO\n44gjcmHPJ55YXPkKERGRDyfiN6OISJn8/vdjFFNXJpU6Fq32HkKhbkBONtuI13uopLSUVKp6YgcA\ngqBFLt8vPT5Ka+uTaDRqensvAy5l1qwn8XpPKzhOa+v9RKMWoKOMWUh5W3Uad9e8gS1tnbZlc/PT\nDA/PJZudvtDvzJLFYJDgdO4XyZATCs2npUVCS8vj+4ql5sOHweCkt/dGamt7cTrPZH9uVDGMjR2B\n1Xo30IXLdSJm8w4Uilfx+1sYGVlMc/PTyOUDKJW1+Hyt6HTvkUpZGR6+YNpxlcpNJJPHolLVks1O\nH/JZCeHwfCyWO3E4mihOqr66jI0dj0Lx2oxfp63tNez2ybLjkchCIpE0FssjhMMLCAaPnPG55EdA\no9mKRvMSEomSgYF/o5By5tDQETz++PvceGPu72Y0tvKtb32Rtra5NDffwHHHbcNkyvKd77RQU/Ph\nkPI/nAiCQF+fm66udqTS6gXz7DekREREPvqIxpSISBls2PAumzcXL2nudF5De/sG+vvPnrKNXF79\n+iO53IcBWlpeZXDwKgYH9y8GJBRTQkalciGVumlu1tPa+hSJRHCcvHdxbOj7Nu82HUdkYKowMy8S\niZ/6+jG02m309n6QxhQkk5OVDX2+o5HLTRgMj+P3X8zBWly5r9D29mew228EIBotff7pdCNyeRt7\n9y4FwOlcDEBNTT8tLRsJhU4gmWwBoLZ2F17vYjSafozGp5BK4/T351Nt9GEy+QiFduDxzPzOt8Nx\nEx0dd+N2XwTkC2ucSaRoNFFCoZm9itd7Jlbryn1KjIcix+G4mpqaLbS1vYnXe/zMTmYcDQ2PUFNj\nIx53k80uxOstRXlPw29/m+G669IHPE9yuRy/v3dmJvsRYudOG6tXO/jxjy38538+w09/uvSDnpKI\niMiHENGYEhEpgzvueI1E4vMl9JCjUg1O28LpPILW1q0MDk5XF6o05PIMzc1/wOf7MYemSGaz0QnP\n6+vvoqZGjlRai9ebW5wnEgYymUXs3XsKAHV1durq1jM2VkptLRlDgU6UyvxfNz09G0kmoyQSdcTj\nC9DrNxIIlB5SWD5ZcjlsSkCKWp3O2yqd1lNfD36/D6PxaRQKGSMjTYyMnEcqVWnOTpxweLIBEou1\nT1Jki0Zzioqjox2MjnbQ0rIdvX4DgcCZE+7Jal2H3X59hfMqBQlu9w1YLP/A4VgCtAEBquepSpDz\n9uV7H2UZHS3sJa4cOaHQcdTVvcrYWP5izrHYSajVL6LT9TIyMtMbA2M0NHyDWOxaQqHyFSF37DiK\nX/ziLr7//X+r4tw+mkQiUdav38lDDyV47LHZZDKfBqT8+tc6/P5XOO00JaOj4PfD5Ze3MH9+aYXM\nRUREPn6IxpSISBnE49PXZcqHVDr9bn06fQIKxUMolZYDXohKcbtPQavNLzLhcp1FR8d9uN1n0Nn5\nEj7fp4lEeqip6aO7+35isSxjY134fAeLk2o0exkcPLPkeQiClebmZ3C78+XUaHC5Dsq3m839BALl\n5weVSmPjSpTKNNlsGoVCSSCQf5EMYLNdjMWyhqGhc4lGTUgkIxiN64jHK13IK5FKs2X19Pnm097+\nIuNzqrq7H6Svb/oaYzODBIfjc7S2/hmptJFkUk9t7V5crusATcHe03GR9TaMQpCXs1fwnusiIIGp\n+VU8Q2diNj+K2z2117eahEJHMHv24+zZM3WbYHAxJtMaYrH6qn2W81OHTncZoVClhb813H//qk+8\nMfXcczv4zncivPHGKRxaAy6Z1POXv5zGX/apw19xxYvcdltxOaciIiIfb0Q1PxGRMshmS08yT6WG\nkEgi07Zxu5fT2fkicrm73KkdoL19G7NmbaOubiDv+WTSgM9nQKtdi9t9IYlEbhc9Fuumr+8aBgau\nQacbv2KMo1L1sr94aWnUEIsNI5XmK3I0MbzR6VxMd/dLBcaLk/MoVU4weBUymYmhoevweC4kHJ6+\nZpLDcSnRaM5oEQQd2aySYPDSCmchpb6+/Jy5/v7F6PV96PXrgOy+ItCVGS/lI2Fw8Eb8/jMYHj4H\nl+taWltXkvNSFYtAXe02GnXvAmmk0hBnj27mz45/8Gj/Zzmh+z7O7LmDdaFLuMFyI7Oyz2E0vD9D\n9zOZkZE2wDttG4/nUkym9UBsRuficCyhu/tZct7V8qmv/2l1JvQRZsECE8uXx4DpP4vz52/lzjtP\nRK1WHZ6JiYiIfKgRjSkRkTI4/3wlarW/pD4Ox4p9i0ph2nZ9fSeh129GLq+sho1CESSdHkImm3pR\n3do6RDj8VQQhXyhWlLGxnNFYV+ems/PvOJ1fKHs+w8PXodM9BEwseCqVTi6A6vV+GrP5fnLeliRt\nbX+ju3sN7e1raW+/C6v1abq6HqAatbms1nvweE4mZ9RpS+4/OLgYs3kVU9USK57KCsEGAqeTSs2m\no+N/cLk+aHUwFanUfs9iPcHgWchk9qJ7tzS9zjvR43kyfga/1J/ATxsW81X/GwAckY3xi8H/4oee\nX3JMKsxdjrt53v1nfhJdjr7h1erfSh58vhOLMPjBbl9Bd/cqqmX4T8XYmItKjalMZfXHPxY0N+v5\nxjcWc/rpO6ZpJfCNbwg0NHxQmxUiIiIfNkRjSkSkDL70pSWcfPLGEntJ8XqX0dHxR2DqlYsgdOHz\nXUZz82qMxmfJt8ju6HjikIKck7Hbz6KvbwVQn/d8be2rCIJ1mhE0NDXVAdDc/AIu1y1UFhmsJBi8\nDovlPnL5LwBZYrHJY0aj7TidK9Bq/XR0rMHrvY6+vksZGjqN/v7l2O2XY7Ndg9W6lkoWkR0df6W/\n/zxyNZ/KRY7TuQytdn0FY4DPJ1BoR7wQkcgsYjETmYyxonGqjSBo6OwcQqUqTnHvPN399ACnJQL8\nZ+Ad/ivw9oTzZ431syg20TP0RPMVBEJTh2hWjzRtbbeTTPoobCRJ6eu7nK6uNTM2m9paD1LpPKAy\npb3Ah7P+8GFHIpFw/fVK2tqmiuMMYjCISycREZGDiN8IIiJlctJJBkpfyDcwNLSIhobdBdrlZI0H\nBhbT1bWKhoaDylo63S6Gh020tz/A9N6QFGbzWpzOk/Kcc6LXB3G7z5iyt1w+TCiU875FItN704pH\ni8NxHd3dT+x7HmdkZCqBAgnh8DG43VexP7QwmWzmoBy9BIlERrlfY2bzXQwMXEEqVQ3Do47W1kq2\n9j2o1WNUuiAGUKurrwpZCJ3uXTo67tyXuzX5vZJKNTE42E4i0VzUeHZmlTyH3nQ50v3lIKe2tg23\n+ysU996rw24/HrN5Ay0tL1PNsL/aWjcNDW8yMHBoqYXS8Xj0+Hyleds/rtx003GsXSujvt6V56ye\nL3whw4MPvnzY5yUiIvLhRDSmRETK5Oc/X8i5524uuV8ioSaRKNwuhxyb7Wqy2W378qhG0ek2Eosd\nj8v1b5jND5NbvGYwGp+nvf25ff2ymM134XRewMTir1ms1rvo7HwWhSLK7NmPYTL9nZqaDZOubDI9\nRjIpx2K5j+HhJSXf53T3JJHsN0JHSafLNyBSqTagdD1ss3k1gcA5ZDKlC4lMRThsRal8r6y+nZ0b\nGRy8llJqU02FUnn4jalwuJlYrJX+/qP2eR5jHDSqBHS6d2hu7qWzcw1abWHvVKOstPDNXcjoH11U\n8rzLpdScSUGwkM3+i2Cwha6uR2lqehqt9gVynsgUIKBWb0CnewIIU1Ozkfb2v2E2/5Gpwj/r6lw0\nNGzD45mq9llpJJNWXnhBlEPfz0kndXP00b48ZwTmzdvFOeccc9jnJCIi8uFEVPMTESkTmUzG9ddH\neeml3gPiDcVhQaHYRqyEDepw+Eqs1n8AAnb7/rylXHhZR8cdJJM6BgaWoVA46OhYi9u9ELd7HpM/\n4lJAQjbbg9t9xD5jZIyGhnXEYnH2e0ba2t5icPBEEokFjEwfTVgyra2P43SeCySRSh3IKlj7u92L\nsFofwm6/uug+nZ0P4fGcSzpd3eKyg4OfoqfnEXp7S1dWU6vzh2KWg0JRujhKpXR0vEcioQJacDjO\nQq9/mLq6GGq1iZGRKD7faYyMXAKkaW7+v0ilGbLZhXlGEuhse5mTw8+UdP0eMnToduIPfqoat1MQ\nqbQ075LVej8u1+fIZBqw2eaS8ygHqK39GRqNlmSygZGR2cTj56BWP0ksdgr9/acDWbq7H6Gvbznj\n1eXq6+1oNNurZkjtuys2b5awfHJN4k8sCxYEefXVJDnP+ACzZz/MLbecyHXXXUJT08wVwRYREflo\nIRpTIiIVcPXV57F27WZWrizemJJI3iceLy7c6ZCe+4qFjncoa3C7bznwLJWaSyAwQlPTj4hGz8xr\nsNntNwABOjrexO1uA+oIhc6ntXUdg4OXAVBb23eg1lS1EYRhLJaNRCJJMhkXfv83KxhNQiBwMlbr\nP+jvn08qNd1iOkx395MMDi6quiG1n3S6vKqxiUTl4X37kUhKCThIYbU+iEzWisNxHOl0Oe/LNBJJ\nHz7fDfuemwgEbpgiB0fO0NDXkUgCdHU9SSIWYWDwbAShCb3uWW5Q/YzbvBspVUx8da2JXv/hMaQA\n4nFn0W0tlntxOC5BEMaLm6gBE9HoT4lOLPdGPH7FuGdS+vrOoavraZzOYzEaV5LNakkm26sS2nco\nb79dRCXvjwCCICAppip5AX7xi5O4//73Oe44O9/8ZgsXXPBVpFIxoEdERGQiojElIlIBEomEK65Q\ns3r1MJlMU1F9BOEI2ttXY7MVZ4Dp9RsAF4KQoJiPbDR6Eq2t76NS7aS9HSKR5L5CwD37xtuESrUd\nj2e8N6cWtboBmcxGJtNFKjUzxgZAMHgSY2MqxsZmIZGE6elZSV/fyQiCpazxwuFuwuFuDIZ3kEqf\nx+c7K2+77u6n6eu7mkPrx1QLo3Ez/f2fKaNnFomk0qK/BxGE8a6+LGr1HpqbPdTUxBGEBOFwC4OD\np6DVOtBqn8Vu/zwgp67uWdrbB3A4rqK03C05Uml74WYHqEEQ2rHZ2lk46x7+FDqK1xqP47sDz0wh\nlVKYZVEPP+rcxrujc4CZ9czV1+8gFismPy6L1XofDsflCEIlym8GnM4jUShew+3+egXjFOb995Uk\nk0mUynLKH3zwvPWWizfe8PD006/x8MO3oFDICQQirFz5HvPn13D66aWF5vX3B/nWt/q57bbzUKk+\nmq+JiIjIzCMaUyIiFXLllSfw17++zPr1U4s5TESJXF7cYlWpfBOZrIHh4fkIwjuoVAMkEoUFE7JZ\nADN7915OLh9jL62tG1CpRhkZ2czw8FXo9U8SCJxNNtsGgMOxGKv1Hux2C9lstQQnJpNKHUVj48uM\njc1CELT09l6F0fg62ewOBgcvKHtcv38BbW2vIZHYEISJtaIslrvwepcwU4YUQG1tlHS6lHDPHErl\nS/T3Vy//IpGwM2fOerLZGKFQAr//RFyuxeNahOjsXAmocLluPnB0bOwcxsay9PSsorf3qnHtx4Ba\npnrt6ur6SCTKk6h/2zOf4+JDXDJQWljfoQwjIRIfoKXlZ/h832Mmf9oUij8TCNw+xdleoB1Q0tV1\nHzbbMipTisyRyXSRyUxf/6wa+P0teDw+rNbDJeZRXWy2IM8+G6KvT8f3v7+GtjY1776rZONGMzff\n7Of00wuPsZ8NG3Zw5plH84MflLfJIyIi8slBNKZERKrApZcqWb8+S7GaLvF44Z1qhWILLS1h3O6z\nAdDpXASDpxUxeoB0ehCP5yv7nkuIx2fjcMze9/xCAPx+PWq1nXi87UBPu305XV0PMDDQTl3d84yN\n5ffyVIpCMbF48cDAySgUfnp6HqS39xzAUNa4Xu8pdHXdg802fuHpxOc7gVjMNGW/aiAI5dWJSiYX\nYTbfhct1FYJQee6Uw/HFAi0acLmmSoyR0tt7Gp2da/D5jsRofItwOEZ9fZJUaj4ez2TpcZPpPfbs\nuaysuXbonXRGC7crRAIpCvnRCLIMJtMfSaXmk0hkCIfPRiIJIQiNlV9kH3L5VGMFaGt7i3TaTl3d\nWNUMqcOLFp/PidX6Qc+jPC6//Bguv/wYEokEK1a8za9+dTIA//3fr/CtbxW72QUrVjzJs8/WsnFj\nH/Pmdc/UdEVERD4miMG/IiJV4MYbj2XWrLeKbp/NTh/WZbE8RFNT6oAhlUNC4bo2AkbjSvr7v0Th\nUK06JJJD26iw2a5Fr3+dZHLmwlpkssk5J6mUgd7e5XR27qSx8YWyx3Y4LqWr6172v1YtLTsRhJlP\nFi8/VE+K0/mFfTWzPgx04HKdRyKRwW6/kkDgBsbGZjM6ms8jGiUYLL82lt13Kj9qX0qlQY5btV1I\npDLc7ouAowE/4bCRlpZ7sVieoHpFc+NIpfkVIA2Gp/B6L8TvPwuH42I+eoYUQC3vvVd5IewPGkGA\naPSgZOpvfmPgvvs2TNtn924X3/veSrzeYYxGAwaDhoce2japXTyeIJWqrECyiIjIxwvRmBIRqQJq\ntYprrila7xyZbOqcC7V6B8lkB17vRLUzu/1aLJbnpuiVw2jcwsDAhUBhz5fJ9DSx2BEAKBQumpqe\nYvbsNVitq4lGTyKVKn4ntzSS04QRSnC5FqHVli8hmM3qsNmW0dJyJwbDesBCPG4u2K8yMoRC5YlP\n7Ecq/TDlZKiBeez/idBq+wmHrZNa6XTv4vcX4y3NTyLZys+H/0aX4c/TVkybjhjwf3Tfo7c/J9/v\n8ZxFJHI6HR078Pk+h91+Hp2dD9Ld/QDt7b9hqoLZnZ0v0NLyGlNJkQNoNJvwepdOcS6FRFKed/LD\ng4RNm2YuxPdwsXr1c0Qib3HllRu49tqXaGoa5i9/6SOdzm8E7d3bz0UXciWaowAAIABJREFUvcX6\n9QGuu24rGza8w6pVTfz3f18xod2OHR7++tcnyGarZZyLiIh8HBCNKRGRKnHJJQagsBFQV7eVcHjO\nFGeT6PXrGBjIF9wvRSKpyXN8/NgeoLh8h0xGT01NH62tz9DUdC/gYmjIhFJZRyhUjpBCcXR0PIrb\nffOU55XKQSKRSsPdapHLIZvtxOc7ssKxikGGRlNZ1HQ8LgGC1ZlOFenquo9wOF/hZxgZWYDRuL6i\n8eNxI5HYcSWXv4acv+kcy0/Y6brukDFNSCT7/x4tuFzX0Ne3gv7+W+ns3DBpnKam7+HzNeL3q+ns\nvG+fET5xc0Sr3Utz8xCQP4dGEJQIQm0Zd/Hh4o03cmp4H2WWL1/KpZea+M53Wrj33kX09Z3Kxo2f\nRy6f/Bl99dX3uOyyt9m9+zw6O+dy7LFxZs3KMjDgndAuHo9z662389nPni2KUYiIiExAzJkSEakS\nZrMBhWKYVGr6kLK2Nge9vVfkPdfc/Fc8nm9M07t/yjM9PY9jsx1XzFQByGb7icWOIpE4HpMpgNd7\nNbW1mxkZeQk4r+hxSkWtljNdcdqWljdxu4+t6Bpy+atEo0cRCpVe86n8a1a2wOrvX4bF8hQOR/Ul\nryshm23C789v/BuN6xkY+FzF12jSBqktI1rwN82nsNlxC/neT8HgMdTUbCYWG+/hVZNOB8gZSqoD\nR+vqjmJ4OCet7nIdC0SxWu8jleomEJhLLKZBJtuEzXbDlHPp77cilXrJZktRNvzw8fbbR/LMM//i\nvPMWfNBTKRuZTMq3vnVlUW09nijQTHf3Jh54YCFqtSqvtPo//rGen/zkczQ3V6/Qt4iIyMcD0TMl\nIlIl6us1aDTeAq2SBIP5hRAaG58nnT6D6QyNVEqNSuXIey6bHaCraxcGw6tYLHditT6OUmkH8u8y\nDw19EbDS3r4Stzsnkx6NLkSlOqLAPZSPSvUmkcj0ITJu9/m0t9swGP457mgcCBccX6EYxGh8kdbW\nl9Hpdu/rd3ioPPJHikKhKtzssJFFrX6SYLA171mj8UnCYQPV2JObo9lR8o/RfU2f4g7F74H8ghCj\no3MwGifn5g0MLKOz835MpheQyQbp6XkYp/PMQ1rVYrd/gf7+xTQ1PQdIMBimF7FIp0/Han25xLv4\nMKJh3brSihIfDgKBEDfd9P9X3Wu2bNnxPPWUmT/9qRG1Ovf5y1ej6uabL+aMMw7f5oyIiMhHB9Ez\nJSJSJeRyOTU1MoLTRGrpdE8TCJw76bhevx65vBmfb/601+jvX05d3esYje9jty8ZdyZELGbA6z0X\niOP3Hw8okUh2YDI9jEwWZXj4XKLR8SGAAZqb/47LdcOEa6hUlSvKTUVz8wv4fJcXbNffvxC12ktH\nx0skEnJiMSUqlYBWa8NmOwswoNPtprn5fYaGjiEW02AyrWNoyMTAwFl0dg7jcFxIT886envLU5or\nlXB4GKv1buz2i1GpvBiNOxkYsJBI5A+ROxSl8kUcjg+LJHWIrq4n8HpPJRzOF9YWRybrZWzswgqv\nE0epGCGdnNrjmo81dR38R+YBhj3TG/7xeD4RCCku1+eBLDrdSnp7p1I2zOH3z8Ni2UA8nn8TYzwO\nx5HU1u4lGp1VsO2HmZUr9dxySz9z5x4+L9uaNdv44x8T9PTsZunSo1i6dAFKZa5m2FVX/YFQyMD2\n7Wdx0UUrmT8/wMKFC1AoalmyZKIX2+MZxGTKvwEwFWZzG2ZzW+GGIiIiIvkQpsDlcglz5swRXC7X\nVE1ERETGsWnTbkGh8As5Lan8j9bWeyYdM5v/LKjVzmn7HfrQap8VmpreEiAiGI2bBb1+jQCZaft0\ndv5dUCgGBKWyVwBBsFofydvHar1PgFRJ8yn2odO9Kuj1Py0416kfWaGl5XnBbL5DUCq37Xv9HhSM\nxkcntOvpeXjf9TYLRuOWGbmX8Y//x955h7dVnv3/oy3ZGra85CWvhA2BhpASQtgQmgAJI2GUWdq+\nbYHSH910QaHQ/dL2baGLEVYSQgKEHXZIgIRASEiAxJYlS7YlWdOytnR+fyiJl6btUGjO57p8XdY5\nzzqSztFzP899f++amlcE6BEgLdTUvCXU1b295/N+WQB3ke0EhKqqXwsQ3+/jzf8XEWpr7xEkkmDW\n8+3tzwhG44op+Y4olU7hwupThGCJFX9Ud1IR/acEs/nvn/r719b23H/485uav1/8YuOn9uyMx+PC\nnDnP7Ok7KkilHmH69HXCnDlvCMcd95Igk/nGjG9IgJjQ0vKk8NJLb49rb/PmncKmTZ8U7Dccjgrv\nvbd9f1ySiIjIfxGFbCLRzU8kK11d3cyYcQkGwxJmzfoKmzZ9+J8e0meed97xk0hU5S1TVjY+rkYq\nnUY02lxSX7FYHen03ahUb9DX14rXex6FvHZ7es5BLv8EQRiguflu+vsPy1qnu/sczOb8qoEToazs\nPbTaDfj9l9LSsoKWln9SUfFxia3ESSQi2O3HEo9nYlxstovp6xvefaqsfIW+vsxuUCAwh1TKhVzu\nnarLGEdLyxp8vmoywh8S3O7ZOJ2Z/p3Ok2ltLVagQY/Hcw0m0/20tz9FXd37+2vIeTGbH8Hl+grZ\ncl61tj7N4KAar/ciJu/YEKS29jV2a7/MOsPBRddarm3hEa4v2L9Gsw2b7ZhJjrF0Ji6R/9li1Srp\npyIBHovFue++l9mwYe8Orop02siuXaexYcNc3nnnVFKpsXFKZYCS2bMdnHrq+J3fmTMP4dhjp487\nvpe1az9i0aIHWbr0X7z7bmm7oiIiIiJjEd38RLLi8QQJBhsIBn/P5s0CN9zwMBs3Ho4gjA/MFckg\nk6UBgUw+qOzI5eNzP00k2avR+BR9fTcBuScM46kmEpkHQE9PbtczrXYzXm8utcGJkKam5kkEoQOH\nIyOuYbW2ZkZUvZza2ggu19FAgubmvyEITSSTEhQKAzIZKJVx0ukIwaCCRMKGz3cVmclUdiorw3R1\nte577XItYPr01RNOLFsIuRySySNynJUQDE4DeoBiDOZq+vuvBaC19WFgckIcE0EmU1BXtx6n86QR\nRyPU1b1LKuXC7b56kj0M0NDwHFKpAbv9POwo+VWrlPmBq8mvVZmRQb9Z/0e6excV7CUSOZLGxmXI\n5duJRmM4nV/h0/jJE4TJSeR/Vti2bSZ/+tM73HTT+ETNU8nf/vYqN910HLli37KTxmzehMFgnFCf\nFssADkc9zc11fOUrZ0yoDREREZG9iMaUSFbkchn9/XtXAyXs2HE8Rx31O2bPTvKPf/zwPzq2zyrB\n4DbgWPIJSAzLNQOkaWq6F6ez+LgTmcxFTc1OFAoNpRlS+VEottPYuBlBkOF0VqJWu4H2KWg5THPz\nMnp7F5NK1Y47OzCwFIViJ21tj5FKSbDZvknux1KUQomIpdIPiMfH76jYbIcwbdrjRKN1pFIBQqFD\nGByciutLEovll8MfGjLR3PwWPT2l7T76fGYMhi4CgakYZ/FYLGeiUn2IQtFLIpERS2lsvBuH4xIg\nm2R/8dTVrUalkmGzLWJkLrTN3Vfwp6o/8wPP+CSpI7mzcgadveeQb8FiGCkOx5V7/h+iqenv2O3f\nnOjQi2Zw8L9lsUnG//2fjksv9VJfPzGjJR/PP7+dZcs8PPzw8Vl3QfPR3v4wb711NtXVxcUjjuX6\n6+dyzTVDKBSKCdUXERERGYno5ieSlfvue55odNhoCgbb2bbtu7zyig+v979j5XWqcTgOJ58hlUEY\n9UoikRKN5g+W1uuttLevpK5uBXL5Tvr7Z+D1Hju5wY7BaNxId/dVWK2XYzTa8Punxj2qrW01PT1f\nzWpI7SWROBSL5Xxsti+Qf30nvyFlMq1CodBit88bdy4WO5Tdu8/H6dQxOKhEr3+6yCsoTCEVv1jM\nTG/vGZhMq0pqNxCYS0XFm2i1XZMY3USoJRY7hYaGZ2huXkFHx3J6ey8AJhegr1K9i0ZThs12LmOT\nSrc3vsbsSCElTLDoj2Via4DlxOPHotW+PYG6pSGV6jGb/0lGfv3z7fJnsRzB9763DUEQChcugX/+\n82WuvFLNQw+dVKIhlWD27NWsXTuPmpqqSXlJlJeXo1SK+aJEREQmj2hMHYCsX//2uB/HeHz4R//t\nt3fy0ktHAuNX7To7b2f+/F8RDA7u72F+7nC5Cq9yCsLIiaCUnp4zaGl5MmtZrbYTqdSHyfQBXV0X\n4XQuIRY7CaggFDpxaga9B7XavO//vr5LMZken5J2i4+5kAJtk+pLKk0Ti9XkLZNKSZHJGnA4vjWp\nvoaRI5M1UUi2PZWqoKwsvzGYDav1cgyGdxibQPbTwGq9lp6eJXR2LkUQzIUr5MRFff0fqKraPUaB\nchijdD0nh3sLtAIWycR36Vyu46iqsgHhCbdRDOl0NTbbPOrr/4HZvAyYQAKtzxAPPTSbO+7YMGXt\nWa0Oli3bgNNZjOJhFJ1uO3q9nS9+8TnOPPMX/OtfR1Bbq5+y8YiIiIhMFtGYOgCx2fo5/vjvsmDB\nX1m8+G4OPfTbHH74X7j66if58Y83sGRJig8/zOVHLmfTplv58pf/8KmO+fOAyZQqWCYSGbsS2oTf\nHwbGG6dKZYKqqvsJh3uA0uOqSiGRGM5vJAgVyGRTM3n3eBJIJK4paasQvb3HYzTmF0rRaD4hEOhg\nKh99TqcZ6C5Yrr//aEym7IZzPhyOJbS1vVT6wD4DyGSdNDS8hNN5Nb29S3OUinBp8KGCbW2TlbG+\n+6pJjcdqXUht7d8m1UYhBgamIZM56Ou7DpvtatraHmPsjvRnlebm1+joWEd7+8u0tb2KXt8JqLnt\ntuksWzZ5QZR0Os2DD3axceP/FCgZo67udW655VnefVfHiSc+zl13NfDUU7+gr8+F0Zg/MbqIiIjI\np4kYM3UAcuml5/HJJ7XccsvowOLdu4ttQc2zz36NOXOu5803/yQKUgCRSJSXX87v4ldW9tIeBb3R\nxOO1SCThce4uXu9BtLRswGq9gqamx0mlzPT1zaa4eJHiMRpX43SevO+12fwyNttpk263svJlJJJj\niEQ+rfwtTWg0H9LQsJne3mxukElqa8NYLFOZGDdEXd3r9PQUFmUIhxuprS3dKNLrNxGLZU/0/Fmn\nuflNuruvyFtmdtvDnN6TX1FtNwr+0vJtdM7XGBy6ZBIj0iAIM4Ak++vnTy4PIZFESaUApFgsizGZ\nNtDfP4epvnenmnTaSWfnkn2vy8vfprX1Q7q7z+bGGyOUlW3nggtyia3kJxQKM3fuA+zcuZREYqTY\nhEBt7Q6OOipCLCbw1lvN/OAH2/ne92aj1ZYjlUpZu/aGfaVPP/2EiV6eiIiIyH5B3Jk6QHG7tzGZ\n1dJksp633rqJO++8f+oG9TnmBz/YyEcfzcxbxmTykkzWjztuMHgQhLEB3kna2h7Cal0CyLHbl9DX\n10Z7+3IMhlLlxPNhQ6uVkErtndwIgI2MzPfkMBo9eL3535OpxuE4C7W6J+f5oaHJuKuNRaC+/t49\nhlThR2lz8zL6+/MnZc5OgrKyAUymN1AqO4ECQVqfEerrVxOPF1aFPDrxLEcmQ3nLbCqrYU3X9yZp\nSGWIxYbYn+9hMtlOZaUWqXTvTo6ecNhDY+PDmEzv7te+J4tGM9pVeWhoNt3dX8JsXkk6HeWaayr5\nwx/eKjmG6p57nuaGGzaxffslxOPDhpRG4+KHP1zPJ5+08OKLx/L667O47bb3kUj60et1SKXiFEVE\nROSzj7gzdQASDkcYGmpjsqukgtDKbbcdybp1P2Tx4qO57rqLp2aAnzO2b7ezbFm+9zNMff1y3O7x\nwggA/f3n0dT0Enb7/H3HFAoXbnczowP16+jqupiysrcxmbbQ3/+FCY9ZIrFhNr9KMlmGzXbhqHOC\nMBUxJXGi0VKkjqeOnp5DaGpaj90+VnnORTQ6lY88P35/K8UYUlVV7+NyHUwsVrqwRzA4l+C+kKyP\nqapahcEgRyJJY7fPKxgn9mmj16+npmaQQKCDgYGjcpar0H/ERRW3c4GnsCiETVMP4dIU33KRmaDH\ngf0nPuByHYFa/SrRaEbaPhg8l2AQlMoPMZnuQKWaRX9/O7FYK5+ln2GpNFtcnxyb7VLKyjZRV7eD\nm246BZfrNe688+Si2ly+fD3f/vYXiMXGLyQdddQ6vvGNkzAYhp9zRx+tZ/ZscfdJRETk84O47HMA\nIpFI2LmzfEraCodn8vLLt/DEEzauumoZl11285S0+3niV7+y7JlUZ6excSX9/YsYHOzIUUJJWdno\nCVUiYaK62pO1dDg8m3jcj15fisrbx2SkxaGh4T4aG3djtV6Bw3HhmHISfL4zqah4sYS2syFFEP4z\nK/CJxKH4fAr0+vdGHZfJOgkGJydyMZKmpleJRE4pqmxlZSex2MRknEdzMB7PRXR1Laaz8wJqalbz\n2VCMSwL9wAAGwyCdnWfnNaQAmip38nfbg5wxZC/Y+o2edzmv7cfIZJNXEo3FKoD9nai1ktra8aIk\n8fjh9PffjNV6JqmUg5qax2ho+A2NjQ8ik7n385gKk0jkFtEJh2dhsZyD2fwsy5YFWLnyTZLJ/AIz\nfv8gDz/sJxYb7+qr11vR6/upqRmd6HzTpi0YDFNjOIuIiIh8GojG1AHIjh02tm6dytw1Ktat+z4v\nvVTG7t1f5K67SpOA/jxzzz2befTR/IlVFYpaBCH/Lk0wGKeu7v9QKj+msvIhGhr+TTrty1ne6z0V\nne4DlMqBvO2q1Vtpb38UtTqG2bwWs/k++vvPxW4/NWedUGgaEkkzLS3/ztt2fuSEQgbq6rZOoo2J\no1Z3Ew6PzuuUSjXsyZ81FUQYGkozVuI7F6nU/nnU2u3XYDZP5nOaGpqb/0Vz8+O0tDxOT8/8guU1\naitLE3cX3b4KWGP5LXPblk9ilBni8Spksql0lc1OIDCD2tpfIpXuyno+mTwJt/tienu/j8NxKnV1\nj/CfFqpIpbKPdRg5NtsluFxtXHNNNXV1H3DeeRtZtmxzVte/P/3pLZ588mxG79pH0ek2ola/wQMP\nfBmNZvRu2M03Xzfp6xARERH5NBGNqQMMm62XE0+8BJlsan+029oeIRQ6nHfeOYs33yycL+a/gVde\n2cVPflKdN0+KRvMmfX2F4mR60Wg8hEItxOMafL6zCQZbsNmuzVvL4Vi0J3dRrs/Sj8m0la6ui4lG\nj8JmuxCb7SrS6cIJOH2+Q4CqguXyEQzORqHIHb+0P/F4ltLY+MGYo23U10/VjoQag6FYd0iBwcH9\ntXskRy7Pn6fs00FLT883sVq/TGH34UG+qzyTn/S+UHIvx0afY7IxR6mUGYMhv5T9VBAIHI3L9VPq\n6y3U1q4hs3uXiwZ6ey+lre1BmppW0tT0yn4f3zCDGI3PYjavwG5fUFSNZPIoQqGD8Xq/wJNPHs8V\nVxzF4sUbePDBzUQimR3wWCzO88+XMTb33qxZV3PGGcu56KI4JlPu/HMiIiIinxdEY+oAw2xuYN68\n72IwrGSqVkF1uldwu+fi9x+CQmFj3rypVEv7bJJKpfjZz1wMDLTmLVdbu5NYrJCYgwOncwZDQwsB\nMy0tTxCLFbdzaLMtxmR6Peu51tZVdHd/uah2shGNVmEyrZlwfYB0uridm6knTCo1dlIvRSqdqpw/\nKVKpwnnFMrjx+5sLF5sgcvl/PvGoIOzdIS0rWLa26k1+HPxkQv383L6GI833TqjuMFrkcj0q1XuF\ni04BDseZDA62YjL9A4ViXZ6S1Vgsl2O3X4TXq6ahYf2nMj6z+Tm83tOw2S4knZ6oQIuSJ544gcsv\n/wIzZrzCggXP8JOfPMuGDXPGlBvi0ksv4LjjWvjznwsrYIqIiIh8HhCNqQOMr3/95+zceSgez3Tk\ncuuUtFlR0U0olJksJhLTWLnycG6//XEcDueUtP9Z5De/eYv162fnLWM0/hK3O39MTX39cnS6JOHw\nIfuODQ5+kaqqYiebtchkfQwnBk0C79PYeC8+36lM5hZ3OudSXl5s0t3xqFQb8Hqn0p20eFpbH8Fu\nP2nc8YEB7xT1IC16d7ep6UOSyS9OUb/jSSb/84sX6XTxedAO0m+bsPSDDnjA8W2mm+4k/05Pflyu\nc6mq2oJKtXPCbZRCJHI0/f3XFn1fh8PH4/PpMJtL370rTAKlcjgPRuZ7rGRqpgNSdu06m2eeOZW/\n/GUmY3cpDztsM1//+kK+//0bxZQaIiIi/zWIxtQBRlNTGzbbNMrL+0mlNJNuTyrdhUzWOOrY668f\nz09+ch4HH+zk3HNf5/e/f4J16zbR1/ffYVx99FEvf/yjiewqXBnXr8rKV4lELiUcziU6AdCPIOgY\nHDyekcpiXu+hqFTF76AMDLTT2HgvKtU2ampWIpMZ6O1dTCAwebGF3t7pQKE4iuzU1OwmGp1KKfLi\nkUhUjH+8BamomBrlO7XaTjBY3ONToxnMMpapY2joP2tM1devpK+vUBLWYfqi9ZNy1Ds6NcSO/h9x\nYct1lJd1T7id3t6vTCjv18RRIJcXb3RGIjOw2Q7BZNo4ZSPQ659Cp/s5cvnHVFf/AbV6CdHoxO7v\n/KiJRsfvyM+cqUGjUYuGlIiIyH8VojF1wFEGaPH5ltLcvJZcrn5lZf1UVz9ToK0BzOZtdHefmeWc\njKGho3jqqXnccUeURYvinH76Y2zZsmOS48+O37//YyAg4973ne904naPN5Jqal6kqWkFjY33IpMZ\niETyGVLQ0fEa/f1fynqulPQq1dVWHI6vUl4ew+2+hFSqDUGoKL6BPEQiR9La+s6E6iqVU6MYOREG\nBxOM3blQqy34/QdPSfvxuAG1upg4qCg+3xamT3+SlpaXUak6mVqRgSAy2cc0Nb2O0fgmSuUnDO9S\n7n+qq+8jlapGEEpw55S18pAxv9JfIeTASus9XGb8HpNRM3S7z6eu7q+o1SsmNZ7iKTW+zYxGswWz\n+RFqa++ntfWpgjV0uhfIFldWXf1vlMoNDA7+inB4AQMD36GiYjZ9fVeWOKaJU18vGlEiIiL/fXx2\nElyIfCq8997eH9kybLaz6ehYRSKhxmY7Dbk8SDJppKZmA+Xl/YDAQBaxuIqKp6ipSRKLVdDdvbhg\nn1Kpi6GhpezYMYfzz3+UG298nxtvvHRS15FKpfjFLzby6qtyZDIBv38rt956COeee/Kk2i3EL36x\ngeeeO37c8bKy50mny7DbryqqHan0fZzO3CqAGSlhF1A4QDuTaFOJ13tsUX2XhpREoqnosYwkEtlN\ne/vD9PQcRiKRX/Fw6khSU/MgQ0PHMPbxlkqVodW6CQQm30s6bdjjHtULNOQpmSCVOoZdu87d83on\nTU2PUVZWjs+nx+3+AsXEGeVGj1rdSFfXPDIT6B7U6tcoK/uEysoOwmErweAihoaa0Gq3EQodQT6B\nCKPxIzSadTgc1wLZcg6NRqVS4HAUJw+/l077XG6pv4OLWDCpKwe42f4YD2q+Tzgya0L1o9EGotFv\nUlV1G9HoJAdTBH5/NZnd6+KvPJ020t9/OvF4DRKJldbW+xkcbMfjOY6MzuFePNTV3UsgcCz19Xch\nk0EyqUYigVhMRihUQzR6x4jyEjSaI5iKBN3FIVBfP7yQMDg4RDqdJplMUVU1NYs/IiIiIv8RhBz0\n9PQIBx10kNDT05OriMjnjEgkKhx66BsCCGP+IoJe/6hgNv9DqKt7QgCPAIJQU/OYoFS6R5VtbX1I\nkMsHsrSR/c9svl/QartGHEsLSuV6Yf78W4Xbb39U8PsHix7/9u2dwj//+bRwyy3PCV/84vMCJPe1\nq1D0CmvXrp/y92zLlq37/n/yye2CWu3Mca0xoa5uTdHvC3QLSuXHec6nhaamfxfVVk3N7UJ19U1C\nTU0p/ZfyFxWqq5cLIAha7Saho+Mxobz8/QJ10kJLyzJBLrcIsGk/jWv8n8n0iACRrOf0+qcFCExZ\nXy0tDxXV3vTpT+b8zuj1a4SOjseFjo4XhPLyDwVIlzQGqXSTIJPZ85apqFgnmM1/FbTaewSNJtfn\nlhDa2tYIZWWbBYgIzc33Ckqlq0D/Q0JT0/IJvn9x4UemU6fkg/hqw7k5P/Ni/4zGrYJe/8yUfTdy\n/anVWwWJ5N2S67W2LhtzzCO0tNwz4vuSEOrrfyVAKutnC4NZ25XLXYJW+9KIY7uF8vI/7pdrr6zc\nKgwODu17nlqtDmHevB8KQ0PhKX9ui4iIiEwlhWwi0c3vACIWi+N2P5HljJpgcCk226U4nScDGels\nt/sCGhufBXxkVr1D+P3tJJPFSmbb8PkOJRQaGbsjIR4/geee+yk337yEZ5/dlrXmK69sIhKJjTp2\n3XUruPba+fz852fx1ltnMlJyN5lUsXlzb5HjKp5nnnmG//3fv/K3vz3FjTdKiUZz7c4okcvz55Ia\nTTNabfacRzKZi/r6v2K3X1RUS273jxkY+B1a7f6S31ahVDYybdpqyssl9PScQGXlOlSq8eOXyZw0\nNv6FurplRCJ+kslWGhr6gcknW82PH7P5ERSKBnLtqASDx1FeXkqi49y0tDxFf//BgL7wyPwVQDbh\nCyXB4Hl0di6ms/MMhoa01NevoLV1ddHjUKl8yOVCgf5Pw2b7BqHQ16io+ICx7o86XTetrSuwWBYQ\nDs8E1PT0XEVDwzpMptyKd1rtM9jtC4se62gU+JTjE7lOhB/0Pkl52fZJteH1HkVZ2f7PiVZTsxFB\n+ELJ9Tye6TQ2joydMmK1LtqTC26Aiop/09d3Idk99+XkyoeWTNZgMgWANA0Nd2M0dpJMnohc/n7J\nYyxEINDCXXc9DYAgCNx665PccMPpyOWig4yIiMjnG9GYOoAwGHT8+c+L0etfzFGijLGTQ4vlEhSK\nLZjN/2L69BfR6ztL6NFMbW3uyatG8zE6XfaA7PPP/xYPPrgJrzfIL3+5mp/+9GXC4flk/8qmmTXr\ndf7f/zu7hLEVZsWKVSxevIhQSMqPfzxAV9ehecurVKkSWpdSVpam7kfKAAAgAElEQVRdjcxgGCCd\nrqXYhLDD5DOm8k+4C9HbewK7dy/G6ZxJff1O7PabqKx8Br2+k4qKV2lqWo3J9BJm83M4HNfhdF6B\nz9cBeOjtXUBb25NZ25VKrVRULEerzScZnZ+2tsdpbt6IzXYxPT3z8pSsprZ2GxpN34T72ks8niIW\nK5Q/LIPbPZeGhqeLKGmmr28pkUicgw9+mo6OddTVvYFcbifX51dWJsFgKD53Vl/fUlpb9y6oCJjN\nLyCR9NDdfSlj3SK7uy8BPkYqzfhFSqVB6utfoalpHQ0NjxEKHU9LyxtF9z2WXcqpUTjsAA6tnbwh\nFIsdhlS6f5P5hkKn0tJyT8n9DA7OxuUyUls7Ui69Fqv1alSqV/H7zwKmT2hMgUA9lZW/pLf3Erze\nM4nFZtLUNEBV1XMTai8bRxyxlW9/extf/erpAGza9AHLlp3A8uXdKJXFphgQERER+WwiLgkdYFx8\n8Rwee+xeVq0qtoacROI0bLbTADCZViKRBBAEQ1G1g0EFmV2J8T7xEkmaeFzBhx/u4vDDhycC27d/\nxLHH/pI77qjkpz/txulcCOT7wXVSW/sUOt2iYi+qIH19TjweLxqNljvuOIpweGy+lNGoVBsIhXYA\nxcePqFTZjSmj8SN27y5uV2okkYibhob7icUiVFa2EAjU43YfjUrVg0r1F4zGw+nrm0cs1lpy2yOR\nSDLBJf39V1JW9izh8Kw9sSBJRj5S5PIYiYQKkOBwnIBUupl0enRcV3X1Rlyupeh0XdTW/giX62tA\n8SqE5eVbCQQOwus9oqjyFsvlmM2P4XLNy7PLmB+p1I1CIYWiBb4lqNXFr1s5nUtx7hO+TCORfEBt\n7QZ0OiVyuZpYTI3XW0EweDR6vRuL5fQSRq/E6ZQBYdraHsNiOZds9+Ze+vuX0NR0H4mEEanUQl/f\nd/acCdPauoqhoeoS+h7Nx8GDxnxjJk6Top/Nk2zD55uPVvs7QqEfT8GIcvUxHZ9vGjrdFioq/kZP\nzzeKrmsyvU9Pz9idQCmx2IWTGpPbfRxKpQkYfqZ3d5+OSuWmpeV5BgYqGBrKnwaiEFdd5eOmm07e\n93ratFauueYhfv3ryyfVroiIiMhnAdGYOgA58UQ1q1YFGPnjWSwymZRSNjTd7kU0N6+ip2e8cRAO\nH8b557tYuPAFZs0KEAikcTgkbN78Kp2dN5LfgBpJPe+/fxBdXT20t09NctT6+jp27Gjk1VffQCIp\nPFGvqLDgdH69pD7k8mzGVJJ0emKR8P39N+773+MBheJ9pk1bQTgcpLf31wSD0NLyL9JpM5FIJQMD\npQpWhKmsfA8Y3tkJh0fuBo5+nNTUDGKzZVwx4/E2ams34nKN7lOhyOzmDQ52MDj4S9rbl9PVNd6Y\n0utfwmi00d/fQjR6MtCL2fwqicR0+vpKm+jZbOdTXf3GhI2p6ur7GRws1VXLOKG+QIogHI3LdTQu\n1/DRysq/AUchlcpy1sxFJLKQ6uoHiES05DOk9vZvt19Dxs135H1fRjCoIRQ6puT+96KSJ6fsB2i+\nZwVr5deSTJaqljdMQ8Oz9PZ+f4pGlA8Jg4MziURaMZv/js32tSLqJEmnJcD+UMiUEo+3jjsai9Vg\ntZ5Fa+tjkzCmBCDNvffuHmVMGY0G/va3b06wTREREZHPFqIxdQBy/fVLWbXqPt5445qS6yoUOgRB\nV7CcTrecwcHjaWl5ib6+c/OUrGXt2i+zdu3wkZYWL/kUx7Jht3+Lc855lt/9zsrZZ88tqW42Nm+2\n8sYb9fT16dBoPAzlUZs+xvwPBqIGSr+dRhtT1dVbgfcIhVpKHW5WEomj2b17tIqe1Xo1IKWi4kXa\n21cQj7ditx9XVHttbSuxWC7C5zuhYFmd7jn6+88E9uYyk6JSjTWO46hUWoY/azmZ3Z7RE3e9/hU0\nmmq6u09DIvFQVbWRRKIcm+0ySv2e7B2LXt+bVamyEBJJCInEvCchcvGUkl+oGMLhGTQ2PojfPxHX\nLjl+/0Ekk6XcJ6MXUOTy9SQSZuLxicc9dTsP431gKnQer/Z+wJ31b9Hdd94EW4ghCG7250+iSuXE\nZMqko0inq+npWYjPdyJG46N4vRcXqC1HLv/0JO9H9Swfe4950Wq7MZmiHHKIlI4OOQqFgF4PJpOE\nVAp6etI8/LCBqioHRxyxk8bGqYmPExEREfksIhpTByBSqZRf/nIG3/nOA7z33uWUMiFVKEJFlauo\nqCaRCGK1Xkm+nSyJxIcgjBZusFpPprHxIRyOK4seF2jZseNCLrqom5kzN1Fbm+Kyy8pZtKi4uJaR\n3HvvFm6+WYfPJ6Wqqh+HY7wxaDa9iN01C4U8TH3iFd5zLSu5n2Ry5AQ7hkKxk76+q0pupzQyn4Xf\nfwZ+PxiNr2MyraO//3Qyq8jZvws6XSd9fYdRrKSzTjfA4ODoXYJYbOT19mIwvEFX1wWjynR1fYmW\nln8iCEYGB6NUVakIhdrp758BgCBU4fEUNuYKEYvp0Ou7CQZbS6gVobHxX9jt3yq5v3R6cjFrY4nF\n5jAwECg6bmsspRlS4ykv/5hAYLLpDVq43PwQM6Rv8NPuf3AwpcQcjkYJzFS9RDcTNaZkpFIT778Q\nOl0nZWUfYbV+Zc+RKGbzPQwNzUGtLpzMvKbmeVyus/bb+PLh9bYjl69jyZIIFRVprrrqYFpbW6ip\nyS9EtHBhJ1dcYcNsNnLrrRfkLSsiIiLyeUY0pg5QTjppJqtXm5g//04++uiHFGtQRaOFFeMkku34\n/Q1Eo7kFGyQSFxrNLsrL1xONns/g4MgVdhWplAyj8SGk0gQDA+dTjGoaSBgaauP11zNuYmvXOmlr\ne46FCyX84hfzKCvT5K3d3+/jppu28eijR2M2P0VZWQcOx3j3RK32Yx53L2KLoYM0IEvrae64AXda\nzQeJRTgGGohEO4AEcrkDg8GBVptAoUgikyVIpxPE4wkiEdu+Ns3mx7HZSo+Tmixe7zzATlXV/Uil\nH+F2385eg0sm60Gr7cRgGMTvlxCNFqvclkSjUY07OjxXdVFd/QJSaRXjH0HlWK173Z6G8Pn2T+Lf\nUEiDVJo9Zi0X7e3P0tV1PcW5uUZRKAb25OgCm20O9fXL6etbWvpgc5Bx+9p/BkA+FIpKampex+2e\nzARfynbbpWznEhxtzbxiuXlSY1rU9zCrpd8nnZ5I3iQ5Go0WsAJTszM8EqWyF6dzwYgjamy2b1FV\n9TrJ5EEFaieRSj8iEvl0jCmpNMi5527n1FMjbNvWx+bNfXzta01cccWigs/QkezY0Uk8PpOVKzu5\n9db9OGARERGR/zCiMXUA09LSyIoVF3DLLf9m3bpTCQQKB/77/TU0Nj6Kw5HbLUWne5dgMPv5xsY3\nUKl66O2tIRw+knD4BKZPf3yMMQX9/ZcBCUBCY+MKEgk5LtcFlPKVjUbr2LlzPjt3plmzZjO//rWa\nxYuPGlcukUjypz9t4v/+uBaL42YaGx/Dbl9IMpktziWJuexPzAiFmekblnW/1vkmAOfXvk9zdTsf\npc5gcFBGKHQYHs/xeDzjJ+BG43Lq6taj0SSQSCQ0Nf0Ou/1aYOJB/ROjCY/nSqTS99HptjA4eCyN\njevxer0EAnMJBAKUIgqh16+ms/O0ccfLynQYDA8zNNSJ0/nTIlraP4YUQHX1IJ2d00qqEwoNUWy8\nYF3dJrxeNS0tG1Grtfj9OmKxg2lsfAqH45wJjHg8iUQdEGIisY+lotFso6ZmC8mkEYlERTQKAwNT\nNbmX8E7/lXy35ml+594w4VZOiXmZ2/xHXu/5/YTqW62X0Nx8Hz09pbs/52aAqqpnkEoTwInjzno8\n+dQn9yJHo6mZwjFlp6zMyYUXdnH55XpOPz2/4E4xfPxxP6edJuXaaw+ZgtGJiIiIfHYRjakDnCOP\nPIjHHjuIlSu38LWvOfH7c8sVV1a+hV7vwe8XyKyIZw9+VyrlQIyGho14vdOIRpsAgebmp3A4ZpBO\nj55U9PTIgQFGGxES9qqlORyXAVFaWx+gu3siEx0pu3Ydx2WXdXPOORu4+OIKFi8+jHg8wb//vYW/\n/z2G3r+BJ3t/z58atnGy7z1+1aDnQ9tIdUABiaSHRsPNvOh6MOeNc5biY17SzKNv15KCo/J6x+5S\nCDQ1PYLdPjn3qYmSTh9NXd3TDA5CPG4hEtmrtFWaeIJOFyUYHJ9zq6dnrwvW1MYPTQSZrFglvgwK\nRT/JZPb8VdnQ60M4nSditc7acySOwfAsEslHtLfLcbsbGRw8gsllpzCgVA4R31/pxQCT6SF0unIi\nkSpstmG32/b2R/F4pq6fcKSRaG0rMHFjqhGBKmVxbqjZkaJQFP8ZZ0egrW0F6bQen8+AUvkM0egn\nhEKPTrhFne4xnM5ZSKUB0mkVufKoFUeS2to38HiOJpUavkfLyrbxwx/u4qc/PX8SbY/mN7+5Ysra\nEhEREfksIxpTIgBcdNEXcDqf4Le/fQObLWPsNDf/Fbm8CovlXAyGToaGNPh8S4CPqap6K2fsysDA\n6VRU/JXe3huprX2exsaNJJNJrNZTgPGByPF4KzU1W3C7zyC3u6EaQZic+00k0sqKFa088YSbs89+\ni48+ktPV1cIFjbfzoOUvSIG/9z4FwCF9V3Jp03I+ts+nTLOd06r+wJV9yznbH84aNbROrydaUcFC\nlwtn4iVW8rM815ILCaHQNLTavxMKFaPwNdWkiUa30dExhNU68Zgan68alcpGLJbr8/os5JUpzYhJ\nJIykUsXXSaUiY44oCQTOIxDYa1D2Ule3AoOhnHC4HLv95JLHBHoUip79ZEyFMJsfpK9vCf392Yzp\nYtxuSyQx+cTOFensibCLYwivd/I/ifF4BIij1+/Cbr8NsDEZo3lw8HwaG1cjCKBSpbFYJuYOPG/e\nW1xzjZwLL5zNTTe9yj33nA1IqKzcxW23BfjmN6fOkBIRERE5kBCNKZF9XHfdedx111eBE4A4kUg5\nAwPnYTA8gSCUE4/vjZk5mMrKXXlWpuvQ6w/F71fjcp03StI5G+n0UbjdRkym5fT3j3UPTJLJU5UE\ndpHJ4+Qns2tValLbDLFYDWvWZNxmqo2buNH+wLipzjGJIFcHr+Xxpiu41fcAZ9mzJ0aNAyvb2qgJ\nBlloy8RAXRhdz22KLhKJjpLH5vcfR0WFBo3mXSKRmSXXH81YOev8KJWd2O1nAqXKfo9tJ41C0Yvb\nPXWxJ5WVL5NKhQgGDyeTpnVyJBKlTm4VlJenCASKKRvG7S70aG3A6bwYpxMUipeQyfpJpRpKHFM1\ntbXPYrEczcRUDbOj0bxDVdVGbLZc8WFRBgen3gVzo/JCPlCs56hEcMJtXGdbxuO6bxAYnFFy3ebm\nl+npmVzOJpCg0VRit6uJRvfu7Jon2aYUhyMj4KDXr6ejYw2QIhxup6+vsDS9TBbg7LPf5L775lJV\nlTGCf//7UzjssLdxOkMsWtTOrFmTV0AVEREROVARjSmRUTz88HWcfvo1qNXn43ItBdQEAqPd0VSq\nHQSD+YK8XQwOljoxbMLpnIXB8B6BwDFoNNsxGLYik/mQStuQSqX4fHMxm5/F7W7GaBwA3kcqPQaZ\nrIvu7q8U7CEbA95ZXFn/Xbb2/WxcCtbKSjmvWO8YtxP1ik7HNq2Wdp0OVyzGFRbLqBupGgG5LEJi\ngt5sfv+RdHSsobPzGCayol1d/RJqtYtYrAGFwkJv71VF1YvH26mrexinc3LGlFY7iN2+oHDBIpHL\nd1JWVo7DMRuDoRuj8UEsli9PokU/Ummpwg0SZLJ0USWrq99nYGB+0S0nEqdQW/saLlcDMIREEkIQ\nisuXZLEsoKJiC37/ZA3vDBUVjyOVdmC3fztnmZaWZVitGXdbmcxKKtXM5NwVM2zpvprzG83Mkj/C\n/dZ/FZ0SeSRfSIU5o/LPPDb4zxJqxWltfYSBgam5jmRSTTS6f8QigsG5BPfYmnr927S1rcViyS8M\ns3Dh+6xZ86VRx8rLNdxwQ26XbhERERGR4hGNKZFRzJo1g8MOK2PrVjO5ffNTKJUWtNohQqE5jF8V\n16NS+Urqt6npGZTKONFoL4FAMzU1m7HZrtjT9nD7wWAmga7DAZDJ9TN9enb3IGPFDo6oXo8s7cYe\nrWZX79fGjfWYtkf4veMP4yZuEuAaq5W/NjdzXU/P6ClWWRk39PVBXx/ZeEI/jUhwMrsnSeJxHw0N\ny+ntvaSkmlVVy0mnj8RuzwhANDZK0GrXEwo1UlhEQoZer8NZWKk5JyrVVqB94g2MQSrtxGx+n66u\nzPsQCBxOImGkqWkldvs5lBo/Ul7+Nmq1j66u0lbiW1qWkUwW2GLdQ2VliIGBUkwBB6FQJoFwff27\nuN1yqqtfQ6tVIZOpiEbVeDxGQqHx4ilgpLLyGcLhJuLxiSesBS91dU+STh+D251vV8dPW/wNLjQ9\nijoZ5ujADu5supN3rd+YRN/DdDpOo5OT+aS5nbd7bp7QD5RCkV+yezQBmpsfprv760AQo3Ej5eUh\nBCGFIHiIRNR4veeS+aksbvfP55uG0bgar3fxBEZfPKlUjGCwUOLpBIsWTa0sv4iIiIjIaERjSmQc\n119/Fpdffi9wV9bzsdiR2O1lgIrW1vvp7r5q1Hm9fjNy+Xhp7PEkqax8DL0eEommPRNcH3V1G/cY\nUsWtEjudR6FWv0M0Opx8ttKwnbP0v+Xh3Q8A0I2M69ttvOb6CoOhzGRfIglybnwZp8SzG2NdFRXM\nCAR4qK2Nyy2Wfcel8vy3zcaaBRAsXkJ4JDLZLszmD7BYvkxNzYfIZJ+QShWSTs5QWbmaoaET9gh+\nZHA45lFX9w5K5Zv4fD4EYfyuU1nZdsLhjJEaiSgo1T1wJAbDduz2yyZUNxvNzZv2GVJ7CYfriURO\no7l5FT09iyk29xWAIPgJhzuKSjw9EpnMiEpV3CRdEMIltV1buwGXKxOvUl4ep69vHv39o8tUVNxN\nxkgd79oqCDK02g3AIXi9udMR5EKvfx6FQo/TeSkU3A9ScHpqNze7Nu47skbyPu/myVFWOjI+GvgS\nfm6ekK7lUse9PK76FrFYYfe62to3kMuVNDQ8hsdTidd7El7vyPegl8bGh4EBHI7vUMx9EQh00Nj4\n9ARGXgppamvdWCz58zcpFA4WLDhiP49FRERE5MBm8j4NIv91XHrpefzxj6eQX3WtA2hCEGRIpSNj\nHIIIQhy7/aSC/ZjN/8DnW4zVejG9vXt3CipxOr9EKV/NcFgLxEYdk0mH+KvtgX2vW0nxVNevOK7+\nxX3Hjm25n184ns3a5hDwXnk5JwWDnGO18mjLcPxPUp1/N2RHqoPmuheBsSIE+ampeYHaWt+eCZIC\nt/toWls/KFArTVnZm3R0PIZUesgoQ2ovTudxeL1fRqfbQX39T+noeIrp01fT0bEcicRNRcU6GhqW\no9FsRS73MJnHgss1m7q6t/KWaWhYTWPjPZhMz1BfvzLndcHHSKXZjXJBMNLTcwnV1Y+Siacrjvp6\nH5HI9MIFxyCXCwQCjajV2wuUjOPxlOZCqNNp2CvKIZNlV5Pw+y9Gq90x7rhWuxGP5zi83sWkUh5a\nWh4j894Vh0azBqWyDI/neAobUgAyZLHRu863dv+Dxpq1ZO6aqUEQ1HRJJ7YgcV7UzSl1vy2qrFYb\nxGL5Cr29S4jFzmD8e9CAw3ElHs/xVFd/v2B7lZU7aG9fQTq9v9MbuIhExov5jEWhGCopN5SIiIiI\nSOmIxpRIVi644ItIpfnlfGtrt6NQlGEy3Y1Mlplg1dWtY3BwVt56AErlJpzOs4FidrDyI5GA0Th6\nd2kwbOIW0xnjyp4WXs2XzN+hqXYVP3PePuqcAKxsaeGh1lZWNDZyUcaXkIp0mtP7+ljVlDFU4jl2\nptLAo+3tXJL+Cz9JfZdDjcXGcSVpbX2IUOhw+vqOG3XGYjkDk+nJnDWbm/+ORFJDZ+eFeDy5dyVa\nWp4jHJ5FX9/P6ew8h127FtPZuZiKirX09v4Pvb3nEYlU0d09mVgkgGmUl2cX6wBQKrehUPjp71+E\n13ssAwNzqKl5iPLy5TQ0/IW9hpHZfDdqdQKLZVHOtkBKRYWJ4jfYkwQCpeRkSiOXv0NT00oiERlO\n5wzq6ix5a1RWfoDPN/57l68Pn29YGS+ZzCXNl0SpHLvzE6emxsvgYMalNBCYi9U6n4aG1wv2qtGs\nR6f7DSaTlIGB8fmPcqFUuJgRGb1t1o7AcwMXsbTxGmqMz1Fp2IZE0gdMXDs9Eq3nQ3Up7nqjuST0\nBmWa/J8VjEwknZ9odA5q9QwyT4ncGAw76epaQl/f/k5vYEKr7S1YKhxuZ+PGrpzng8HQVA5KRERE\n5IBEdPMTyUpjo4njjnPy9tsfIQjjky7W1X1AOu1k9+6Mm0lr6310dy9BqwWns7ALVSoVJZWaGkWw\nRKIOtXq0e5pR/wk/6H9xXNkfOZ7Hw/P8seYhGnWSfZtHSWBjeTnHW608YTAwPxgctdJQHY+jjEbZ\nodEwFIuNa9cPPNvQwHyrlcpUijW1tdRqL2WnN//YpVILLS3vYrEsIZtkeDptQBDUNDT8kXS6hkik\nnkDgRMBFe/sb2O0XEo8XXgVXKhMkkwePPYrPd/WI1/lERYqnu/toGhtfx+EYn5C0vv4DrNZMn3sn\nsm73eYCEoSEZbW2PIgg6bLZLSacriuhNQkZTETKPs9zrQxKJA602zcBAsVfipbzcj90+LEXtcs3E\nZHqO/v7sAhNVVb5RxlFhpCSTIczmh1Cp9Hg82a9ZpXKgUPiRSr1UVa1Hqw0DWiyWsePQkkwOoVS6\nicdzJXpNotN5cbm+xuBgMe/xMPFEJbv0NZw9xjX2CCHGo44VuFlBp1SNU67GozHyM/UjOFzH5Wgt\nHwaeqb+Yqzt/N4G6cIV3K8sa72CD7/uEw9OY0fIocqmUT9wHMRg6ir3fk0jkw6LbDARkSKV9pNPZ\nxXUUCidu9/5PoLwXqbSYeEE1y5Z9wsaNnzBtmokNG2Scf76Ok0/O5NmTycT1VBEREZHJIhpTIjnZ\nuPG7XHDBj3j88e8Cw6vEZWX9yOVWHI5z9h3r7j4Xg2E1fn+E1tYVyOUGHI6jiETqs7adShmQSodI\np3NN+Eqjq+skamvvweXKBMJXqMNZMlplqAKO1OsZ8vt5vK0NuVxONBzmcIeDJuBbOfSvh/R6unU6\nKnt78QN7p6FblUo8lZUs6e1FRsakU5aXI5cXnlhVV/8Li+W2vGWSSSXx+AJ8voMwmbagUj2KTOak\nq+t7Bdvfi98/9VLWuUinO9Bo3s16LpHIZvgNxwGVqtJntc5Gp3sfqVTAaOzB4zERDGYXl2hpeZvu\n7sLJlIeppq4uPkoOPRJpoKpqF2Anm/EplZYWLwUQDC7cp9CWi1hsBk5nkKam+/B4LsTtzq2W6XIt\noKnpEYLBgwkGR8fIlZdbqaxcgd1+PaUnfxWYbf4D37TtylmiBqhJRyEdhYSfV6ruY4WijniidJn8\nzuSRJdcZyYuOf/BAxRu8XXUE831bOCfYRS9wf/UX+bDyVD5KzWAgUbxox+DgCRgMXgKB7O99ff2H\n2GynT2rMxdLW9gjB4PhFrpF0dGznlltCrFu3lXvvPQyLZRbf/ObrPPTQWqZN+ybNzQ2oVBPRTBQR\nERERGYloTInk5ZFHbmXu3L+xadMN+47V179GZ+fSMSWNBAIZ4YG9+afa2pZhsVxC9q9ZKybTRnp7\nW6dopBoikXlUVKxCr2niEsl9OUt6gfJolLkeD3mSZe3DVl7OC1VVzLLbsVdXM9jczOpEgkg6jSSd\n5phkklNHSOA9WVPDaRYLD7V9QGbPK/dtptMdmzcPl8n0LBoNWCwZEYr+/i8AX6Cu7lbAB1QWHD+A\nXh/EPZl8piUSCKiz7I7EkUqnLh8SZJLpJhLH7elzNnV1LxIMZhfQCAZNNDS8S29vIRnxBJWVa6mu\nlhEKjTfJ7faTaGtbicWygLHiF0ND0Nh4Lw7H5Uz941VLOHwkkUjhtAN2+yWUl79Nc/Ob9PScAERp\nb38Bt7sKpbKR0g0pgARnBVaWdFW3W/6Ov97D2r77gNJid7Y5FnC/voMrg50l1RvJFf6PuML/0b7X\nDcCPBt6CgUxc348aF/KX8oWEhopRoGyhsvJ5AoHsgg4q1eSTDheDVrsOv/9gfL58OaYEbrrJz2WX\nzeX445tQKldRV/cKS5d2cPjh+RdvRERERERKQzSmRPKiVCo499xmNm0Ks3fimEhEi6prsSyloeHv\n9PZ+g2zy6YIgoa7uKZJJMx5P6Uk2xzI4eDjQxkmG7/FT65qc5YyALhZjY2Mjxztyx/cAdOl0bKuo\n4No9CXln9GbiFN5TKvlQr+fLWXzG5JWV6Nxu7rf8jWCblndDS+hzH5u1/Wg093spl79DNNpEf//4\nFXq//1gkEgGhSNVjqbR4xbupwO0+l+bmFQwMHE8k0oxGs5WGhk4sltP2a79O54m0tT2CxTJeUdDr\nnUdT0/1AfmMq8539Cj5fboPDYrmA1tbn8XoNBINz9h13OM4Domi1awiFJpsAdjxqdfET9qGh2cTj\nO2lvX0ksJtDVdSEgpby8p+R+q4w7aNeu5gZb8W5xAGZS3Nu3gsOrrsblKT73FkAyWcV3ZQ/ypOlO\nepSzmZt4jf5EhCXRbhaFbCW1lYs7HGvZ3FDBuqFlRZVPp7uBFCDbcySGTufCZNqK3V4o9cBI4hx1\n1FaOOUZCWRl0dqZ49dU24vFCUudQVeXAaj2lQKkEEknGHVmjUXHnnVdRWfnpuSCKiIiIHEiIDtMi\nBfnhD8+ho+MdAOrq3qWvb06BGntR0tu7hOrql7Ke7es7E6fzDGSy98mvHFg8Ekmaw9LZ8z+N5KSB\nATyhEHZp9lvAIZcTBT4wmTivZ/zk02o2c5REwhNG47hz4aEhUmRWKp6y/Jbjyv6dtY+WlieIx3OJ\nRqRRKGSk07KsZ9Xqx5FKx8du5SKdLhC8tR/o6VmCVruDabI1zTwAACAASURBVNNWUV39Ep2d55FO\n7+8JnRq3+yRaWlZlPety1ZPZm8yHjMLKdlK6u89Gp5Oj0bwzbgzl5cUr6hWPFIUiSiERhJEkEofS\n1XURDscS9j7ug8EmDIbijSKp1M+PZVfxju0nTEQSQgfMlvx+AjVhwPdFHu9fySbbj/hj31M8MrCO\n++u/PqG2cvFD3zqaatcVVdZmOxm5vBuA6urtmEy/RiLZwq5dC4lE8u0UjUTg4ouf4733ZnLffcfy\n178ey/PPz+bJJ90cccR7BWtbrUupqXkjbxmpNEJPj4U5c25nzZpNoiElIiIish8RjSmRgsjlco44\n4hMAysstJBKlSEtXk06nUSjsOc6rcbkuoaXlPkqRdM5OivnNP+FXPauLKj0/EOC55uZxxz1yOb81\nGHivooLspgyoJBKOcruZGQ6zrKWFkZEy8x0ONlUPxwbNiryfpYU4crk0Z4JUs3kFSmWaYPCwLGcH\nUKs7SKUKr2IDGI1v0dNT7ERvanG7z2L37gvo6bmK6uqxRsf+IRRqYmDgOOrr1447Jwg16HS5Ekon\nAT8ymUCxj0aH4zgMBtBoNo06rlbn+uZMDqv1CxgMWybVRjg8l/LyHRgMxbnPzWhezf9zbypcMAd/\nqjicpwYemXD9YWEWBaDgNdeFXN92FdsmKJ0+Fn3EjXewOFW7ysouQA/EKC9/j/7+nxEMnldSfyec\n8Bb//OcZSMcs5Dz44OPs3l1MDKmasjI32YxqjcbNJZe8yY9+tJ4FC47l6aev5xvf+FJJ4xMRERER\nKQ3RmBIpCpOpkyOPvJ9A4DUybi7F4/UeS0PDs+TOu6TEar2M1taJJroUOMy8mvPaf8IqW/ZEw9mQ\nA+ksfnJvtrTwvx4PxmAQs9UKwB0NDXy3qoo4GZNP783sbjRFo1xmtfJWUxNP1GaMm7UmExXJ4dxH\ndUN2hhXnMlRXP0JnZ3aXN5VqAxLJIIFAdol5tdpDPF6GXl+c0lkw2IzRmF0Q4tPDiFa7+1PrbWio\nmWBwBg0NT4w6nkgcs2dCPIzJ9Djt7S9QW7sBna4Tv79wjrSR9Pcfh9H4NhUVw+qRCsX+8qA+mKqq\n/sLFCtDbexE63QYgu9jKSOqVuYzP4qhMhpiKFAh78QUO4i+We5lT9h6nTP8nNzecxWRGeAwp6iqK\nE2IwGkMkkzU0Na3Aal1Qcl/NzR9z110NlJePNgQ/+cTKa699MWueuGxYrafQ3PzKvtcy2QBtbW/z\nrW9t4M9/PozbblvAnDlHU1lZirKkiIiIiMhEEGOmRIri7rt/jSAIzJ9fwwsvlLrqbsRqvZyWlkew\nWq9ifPwUZOKxindbG0ZgrvnHrLTdmVO9Lx+n9PbycFsb51ssqIEetRrFHmm1g9NpiMdZ1dTE2ZEI\nTR4PL9TWsnNoiK+PEK6QAqfa7diB/21upjYep9qfiW35v6qZbBU0SCO7Saczu0wVFU+jVqfQ618l\nGBxeNVYodlFR8SLx+BlYrblzVNXXb8Ri+TYNDWspK/sHCoWMcHgOHk92da9kshGNZn+4nRVLnNra\npwkGJ6fOVipDQ83IZEEaGv5CIDCboaGMcSqXDxvQra0PYrefTTI58ZxGAKlUHeHwEbS0/AurdQEy\n2f7ZmYIosdguRqYBmCihkBxy7r0Oc+hQcS5wufigfDo6oYfBoWy7rBMnFDqYV3cdzKtcTcx0Fr/r\nn9g431MZkUmKe/aEQtDS8iChUDmZ6MviKSvr5e6708ycOV7Z8KCDWqiu7iWLR3EOqlEo9hrVAuef\n/zSPPno5yWSKRKL4JNYiIiIiIpNHNKZEikYikaDRFOdaNh41VutZNDX9FYnkMHp7D8Jg+AilUk1/\n/wkAWK21QC8Zza2iR4VCpp2QIQUwPZlEbrXyf3V1HG4wEIpGudA2HNy+TqvlMJ+PQ4eGAFjocmE3\nGLijqgqTRsP1dvu+Ke37Gg1X9vTg02p5urGR0xwOViqm81r/g1RVbUGrXUEsVovLNQe/v5KyspdQ\nqSzEYpnA9ebmTXR1/Q+FJsmh0OGAn97ehWTeLxNtbY/j8RxMdkNVIBzOtSu4f5HJPqSx8WNstjPI\nRM98ugSDhxMMHkpDw2sMDWXkzJPJndTWeikr02CzLSwyn1U+QoRCncTj52O1XkN9/fNEIp9MxfCz\noMbjORSJxIsgFM4vlo+qKjl+v7ZAqSQ18YnLQH4oUbFG8r0pN6RGoi3/mG/0v1K4YBZeLWvgq8YH\n2G0vThjF6czkHOvoWF2MEOgoLrzQxpe+9MWs57Zu3UVd3QB1dV04ncUoC0IkEgKGADUdHUmkUilK\npRSlcny+OhERERGR/Yfo5idSEoODk6ndgN3+LSIRCSrVB+h0Dnw+I/X1dwH9mEyd1NSU7o7WFZk9\nmUHRlk5zhc9HJBZDolCwTqUiBNxXXU1Nefk+Q2ovXwkE+KXHw5ESyagbqN9opBJoD4W40uGg12Si\nM3UZIMPjmYXVuoT/z957B7hVXnn/H111jcpoiqZJmuICplcTWugdQ8AUE0pIDynsbkje3ey7YXeT\n3+672ZRNIYUlIYQWioFQgunNhGaKjTHGZUZtpJE06r3r94dm7BmPNCozdiDczz+27n3ala40z7nn\nnO/xek+mVKrImadSWpTKpwAwGv9MOLySRr6SyaQKmFYB7AcyJBJ++vtvpXoIpgS1ut6mee/Q3/8S\nTufF/DUMqd0IhMMdDA4+hsXyKwKBy/D7L8duv3DBhpTVejs63XYSic9T8fJImJg4m0jkLKzWW9Fq\nF+bVqUYmcwodHQvLmwIv8Xj90DuJxM+SaOuG4X9Y1uDyntly/0boN2zkA+3ArtdlwAe8azDwpsXC\ni729NeVt/qH7+w0bUjMRmszXkkhCXH117ZC7Qw9dxrp1q/jhD700KsaTSOip3HNS/P59V0dORERE\nRGQ2omdKpCFuu+0P+HwCW7cuvMhuIHAyEGZiYgO53AomJpbQ3n4vExNX0tt7F5XtUOP1iCzqrQte\nU3cux0VT+VFb5XJ+b7FwnctV9Qsy/dy3KNt9tgB0qWZLafsiRbyF+WS4j0anewa1+jfI5fszPr60\nobXqdDZSqZkhcxomJ7+KTPYgvb2P4/WumtOnXG4DnBiNLxAOX8W+eo6iVjeWA7J3yWAyeXA4vsLg\n4FqKRRnN3F/zIZFoicePmHO84hE7EL1+O93dzzA5uZjFXBW0t4eb9ozMpKPjEfz+L9RtVy5382Df\nRRzqvJNlTeZKAljzXpr9PjfLqO80/uegr2Ba9jaSZcvggAPoWrmS5VYrKpWKh++5h2/+4AccNzmJ\nATjN7d6VwXVg+SWWjrzPhuThjAdOolhs5H71E4nUN3hkMjddXaNotUk6OjZz2mn1i2yr1TKOPfZZ\nXn31DBoJwQQ5IyP3snp1M7LsIiIiIiKLiWhMiTSEIMh4+ukPKBYXJ4RkYGAjbvepU68URCJXA+D1\nrsZg+AXp9Dnkco2pBmokC3KXzWFFPs+KBpIXxou7N5cvq1SstNtnnRcEBVJpjkLNFAYBn+8y9PoA\n0WjjoY0qVfWwq0LhYmSyezEY7JTLEmKx3bkZDseZGI2bCYcvZXDw9/PmZC0OGSDaQBjZYpKi8pMm\nA0oMDd1NsQhyeRtjYxcA4HBcQm/vn0ilDiMWG1rwjLnc/LlosdhyBga8QABYWFjeTBKJ2IL6p1Kd\nCIKfUqlegKycl3Nf5cTOCzlF/wx/tP2qqXn+78STvDTyG14du671xVZBKg1x7LE7OOssCatWdXHI\nIf+ERFLdYLtwzRouXLMG986dqPV6/u7887lpwwZkwJ3OPwAVeZg1ls/xkOu31Df8ulCpZhuWguDF\nZNqOTpdBIskSiyXx+5fi9Z4ACPziF5011zeTSy5ZyVFHOTn99Jfw+XpYujTAxo2Hc+ihbzA6OkQi\nsQQAhWILZ54ZwWj8Bd/85qdYsWKo7tgiIiIiInsH0ZgSqcvmzQ5+/esi7757FhZLAr9/4WPK5Tmq\n3356otGv09OzFp+vljGVRKUaQ6/3oNXmeDcmsFGi5LByKwIWraPM7Vboe6uzk+P2KAD8u4Evkt0x\nN9l8JoXCMjSaB8nnj6en510cjrlepbl9ahsoPt8R6HRj6PXFWcYUqAiHKwIMSmVP3TkWyvDw/WSz\nGTyey/f6XBVSWK0PEo0uQaFI0dYWxW6/gt1+xN14vRdgMr28KMZUMllmdhHXubjdJ7JkyT2Mjl6x\n4PmmaWtbmIc4kzkMk2k7fn/9bEOXdyUA90dOodM8wU3jjZUegEpw52nRW3mVL7IYf27a2lxcfPE4\nX/pSJyec0Fx478DSiuf327//Pa+cdhqf9Pl2nVMAv3T9nh0DB/Ce+x+Y33MrEIv1smzZI0gkZeLx\nDJOTw3i9J+D1VuuX44ADGlczHBqy8pvfJMjlAhx99CE8/PCL9PdbyOeD3H//g2zbpmPVqgH+5V++\nNEdeXURERERk3yMaUyI1KZfL3Hzzm9x4o5HJyWumjj2x4HFNpkfx+ebLoRGIx7UsWXIfxWIBmayN\nQqEdu/0kIENPz6/w+c4nkzkNv18GnMt3lhRZN/ovC15bM0inXE4FQCcIvNbRwSenJNNHgac9Fzcw\nSpFCYZh4/AS6um5DoQiSy82vLFfJ16iu5pbPLyMWk6DR1JbPzmQWJnVdC6PxPgyGBJOTHbjdZ6FW\n76TiLdqb8swBhoefp1xWY7d/mun3ZHIezYTh4Tuw2RbHyIvFzEAQmE+YRYLffzRK5Ttks4tR72vh\nTzM6OzdSKOzXVJ9isZ11pc+Q46G6JY1n8s/BN3l68Ie87vgWlXwgTVPzAigUAS699AO+851BDjzw\n2Kb7z2TDI49wUDZLjNl3Zh9lXnN/i9WDHp7z/F/y+dpqfdHoJ4jWV5WfQs5DDzk57rj9UakaM6p0\nuhLHHPNJAL7whfN3Hb/wwpWNTioiIiIiso8QH2uJVCUYDHPNNU9x3XUHMzm5O5enVFrYLSOVhigW\nJaTTJ8/bLpU6l9HRy7DbP83OnRcC40CEoaH78PluAFaw+1mAlLciq/ns8JewN5RnsHBiEgmadEUh\n71dmM59xuXYZUgD3dx1DIrmi7jhdXW/h9Z4DgM12LQMD1Qr8ziYYNAOhmuclEiiVbKhUO6qeF4TF\nf49ksneRyXqw26+lrU1NLmdCLt/bn4WH3t5XsdkuwW4/n8Z+zkokEgOAqm7L+Ukgla7HYNiKWh2o\n2zoeX0pf3+aWZxOEHVitDzI0dC9arYOxsYUUYt2JQmEiFDqo6Z5jnvO4wvqFpsprq4HnHf/Mj/UH\n8t+GoxjsfbKpOS2Wbaxd6+POO0/gwAPnFtlullVf+xrJX/2KP373uwT3kLBvA55w/IRzBv5twfPs\nRsJNN53PF77wWkOto9E4Mtm++R0TEREREVk4ojElModnn32To49+jDvvPJM9N53l8sJuGYNhK8Hg\n2U33s9tX0939Xez26uIJk8H9uc32S04wrefv+le1VLGqGbbo9ZyXTLJNKuXEdHpOSdIxw0oacfx2\ndPiYqXQnCPUT28tlKfPV5Mrnl+LxXElvb3VhDolkYTWV9Pp16PV3YrHcjlL5BwyGn6NSlZicPAkQ\n8PvPAkCj2Q4ti9bXp7//abze82hO3ECgvX1h+UYKxSsYjY9TLB5ANPpZ0unGZL/9/pX097dWmFqn\new2n81PY7ZeTSBwNTfmG9sRIItGquqKMB5038lKTDy3UwDdjO/h2dCv/X/I6hvseqdMjhUy2ldNP\nf4U//UnFqlUHtrjeubTp9RxzxRV8+Xvfw3nrrbx62WW4BIGZmZdnBh5ht2LmYiDhsceW8OMfv0S5\nSqHwmfz+95v5wQ82LOLcIiIiIiJ7EzHMT2QXO3e6+M53XubFF49icvLqqm0WakwJQoFKYFyzt54S\ntfow5rf/Zbj9x3KL6vv8PY+yN/Wt5KUSCWBTTw+XeTxzzm+lfgiVWu0iFJr9PiQScszm1xkfr50P\nkk730tn5a+Lxr5DL1TJWBEql6ps2r/dAhofvxGY7l2YLj6pULyAIw2Szy3C5liCVOolGO6gmfV4u\n5+YOsGhEkMn6aeV5kM8Xp7V7sEIudxw63b1YrU/jdF5KI6prRuN7CMKTZLNhurv15PNqjMadZLNL\n8XiOqtu/q0tJNLpYz746MRj+SDx+MI0pxs3GoBtnWbx5Zb9prorb0Je+xlVaK/HEYXucLbFixdvc\ncEOZ00/vxWrdvyHhhlY5/Jpr4JprcI2O8vpTT9H2f/4PxmyWyxIOvqN9l3xhhAsuGOXII2Ok01q2\nbi1y2GFKpNIC0WgRnQ6Gh1XkckXuuCNJNKpjbMw4y5s/TTRq5lvfMvD++8/w85+fQFtbdXn17dvf\n45//eTHVH0VERERE9iaiMSUCVPKjLrnkBTZtqm5ETVMqLWxjI5W+AxzfQk8JgtCYl+MTA88wPNrC\nFE0QVashHkeQzxU4+F3XEXwQmr92TUfH25TLbgKB2YITPt9pDA7eA9Q2pgyGMYLByxkefhqb7Spq\neWZCoQGGh5/AZpvtCUynzdhsV6DT3Uo8/sV517knUukkkchxTHtGisXaAhte73kMDj4JhHE41jQ1\nTz1UqpdwOk+t37AKqdQnMJnW4fefT6uS3cHg5QSDGXp7/4TXu3retgpFEEF4hmDwBiq5bjkgRSRy\nBP39azEYBIzGAKWSlELBMGVcpZDLN5PPV+6DbNbF8uWPUioVkUgkRKMhyuUjmZw8pKX1u90no1Q6\nyGYbKxA7kx7DBJmEEhYg+HJBcpzP9X6LnyWeZvoz6Ovbwde/Psm3vnX0Pi88a1myBMt11/Gc2Yz1\noIMYffRRLnvtTVZfreeccxoTurjqqsq/77/v4cYbX8HrlTMxkWN83EAudyCV69Rx662ns2PHi9xx\nxwEMDs7NtfvVr760eBcmIiIiIrLXEY0pEQB++tMX2bz5grrtyuXWjSmNxkO5vB+N33Zl+vufJho9\nAChRLDYSnhXjWt8vWl5jo5zo9/PPnZ3sVygQUCjomlL22ypR8u+ynxAI7F+zr1Y7hla7Cafzs1XP\nK5XzFeDMo1ZvIxq9FptNxcjIWsplFaVSG6mUDJksj0bjJ5Xan4mJo2hru4/qdX4kSKUNZ9DvIplU\nIgheSiVr3bb5fC8ORy/9/Y9QyfGq7gWzWn+DTKZlYuJg0ulDG1qHTJaj4l1qnkJhP/x+NVrtZhKJ\nZo2REuAC5JhMT1IsbgPOpRLIVh2j8R18vuunXglUQmcr4bMez8VAiGj0CDSalzAYfFgsz5HJKCgW\nuzEa/8jo6CGEw6cyPj5bvMJsfhJozZgql6WUWzSG3KEhkvWb1aUgny6YXOK0017hpptG2H//xsoh\n7C1OXVV5uDFw/fV84vo6jWtwwAH9rF1bKXVQKpXweid5/fW3iETKJBJldDqBYlGC2bywcFsRERER\nkQ8HojElwvXX/5E77zyEUslQt22x2FyokdG4g/Z2J+UyFIsBXK5GVdTKmM2/YXz8Cjo7XyaXa8fl\nqi8tfcTwOq6xOZpaYyvIgf8OBskB7+r1dOVylIArzD/F5Tppj9ZlKnWGjPT3P0Uup6xpSAGk025U\nKg+ZzMzaU2UMhpcwGkenVOsAhhkbmxnMmGF6k97ZeQ+dnV58vjMZHr4Ll+s8CgXjjLZFpNJmakAF\n6O+/h2j0WJLJgSb6gcezis7OOwkGq3s9FYphdu48C7P5d4yP77frGozG9ajVW/B4PoXVuo5AYBmp\n1AkAdHXlSCTaq47XCDJZmra2HIlEc/3a2+8llfo9KtW3KZd3MDn5n9QLNVQoZPO0kTGtBNjdncTh\nOG/W2VBoOV1d6wkEqinYZdBoXKRSzYsyLFmyidHR1hQNk6lDudnyKX7purel/tP8vesRtg99m/1X\nnc2PfnTSPvdG7QsEQaC/v4eLLtr75QhERERERP46iMbUx5xgMMZjjxlJp2fLV8vlHvL5yma+u3sL\nGs0EDsdpDeRMlenp+QsaTQ5ByOD3t2OzzR/yVg1BcDI+fjzQTjB4ft32FRKsSvys6blaQcJuX09s\nKqfj/KEb2GS/do+WOczmm5mYOIj29jE8njOA2l4dhcJLMLgck2kjTmcfEkmIcrkTq/VmnM5PEY3u\naajNpGKEdHU9SFtbG/l8B21t72GzXcWSJfdObZ7TWCy3Uixm8Hguafh6rdZ1OJ1fo7WwOAlqtRWj\n8RnC4Wq5IBWLZnz8MwwO3opM1kkup6JUGsDt/iL9/bfhcl2GTvcynZ0/RaHowOFoRHa+NkND77Jz\n56VN94tELqW/vzD1OZ7RUJ98vhEjoUSxWE1hUEIg8MmqPcbHL8RofI7OzrEqBvx8TEzJfrfqZZZi\nk5pb7LubzLCZH/3XSg65TMwPEhERERH56CIaUx9zvvSl2/D5DkIud9HT8woyWZlCAUIhOVarlEjE\nQC4nEA6rkEj85HI5KkpySiq5HzNVxcoMD/8Rm+105q+7U5+BgS24XM3mxGh5U38GTL66oLmbQQXk\nOjt5Mg3Puv9u6sh0XowSq/V3OJ3XATKCwVPqjme1vkUkEsbpXENPz2sIwltMTFyNzzdIPWU8o/E5\ntNos4+OnEQhUvIwqlZ3h4T9gty/BYnkcmWwSm+06QMBqfR5BeAe7/VN1VhWjVOqm9c03jI+fhEaz\nHvAAMz1u41PXBiDD4ZibL+LxfL6yitjZwNkLWgeAUvkewWB92frqCKRSLwGXMF9o30ySSSWVelu1\n6yv19T3E+PiZTa8mHD6VSMSJxfICLtfJDfRIYLE8i9N5ZdNzzeQF3zf5ufFJrg+/13TfIvD8GWdw\n6C230D04f1FrERERERGRDzuiMfUxplQq8f77h5FKVZ58x+Ozz1deT+e6lOjpeYB4XI3F8ghyeZ54\nvIREsgS/vxKC1N6+EZvtcBZqSAmCl0Bgd15JM3iKzSfULxSZVMqr+v3Q48do3Eg6HSEel9Hensbh\nOJtGv2YSSYxwuIxaLQcEdDovdvsRDA8/zvj4fLkxRYzGm8nnz8XlGpp1JpMZwmaz0tt7Hy7XZVNH\nK95Fp/MUOjrWU/EM1Q75U6meammjvyednQlSqdl5U0NDT2K3X9PgCIuj6tbVtQm3u1XPVgKdbg2R\nSGOGFEA8bsFqvQeVykQuF6pyvYUpxbrW5MrLZSvx+CgqlZtMZv4QzO7u23C5vsqC38tygk3FZqpN\nVYgJAm99/euc8pOfIJWKtZRERERERD76iMbUx5g77nibDz5YWafV9OZXwOerhEWlUrvPms2Ps3z5\nE5RKKdLprRQK55BIJKmUv2yN4eFXGR29qKW+9rCW9ShIyBQk5W0cko2xtJReUEG1P2oGCKtNfDX4\nzq5jaeCo/u+TkxxCW2obvYYShD3s2LFbnS/apL7D0NAr2Gzn0t39LD09T+L3d1AoHIfNdty8/fr7\n78fj+Qy133OBePx4LJabp/LOducahULHoNP9lnj8qzX6lujrS2CztVqXqEJ39zMIQgC1ej3d3TZK\nJTPl8hY8ns9SyUDbd7jdV2CxPI/L1Wz4aYShoUemap01Qw9O5+cAWLr0oSrnZWSzIeZ6eptYWeQU\nli17hB07qhtTCsV7DA5uJxTqoLNzC8HgwS3NM006s5x12h/y845/4frQO/U7AM72dvz/9V+c8uUv\nL2huERERERGRDxOiMfUx5bXXNvHjH9uB+jVu5mN8/Nxd/1erN5DLZenpuYtk8gwSidYqPRUKGiqh\ncs2ZQIIQQa6E02TbyRf0UChz9MijJHIy/iX2r3w61rxe+v3aQb5QfB5JOsHpHMpyypSATw39E+/b\nv8N0nZ5NTY+8JznS6QQgMDl5Bo1ev0QyTqlkpp7xmkxaSCa/wvDwXVNy6tMoaG8vzfFKTmM234rN\ntoaFejIMhjQ7d16NTDaO03k6IMFi8ZDLdS1o3NYQUCqbK9yrVD6NVkvNotGNoNE48Hj6q54rFLQs\n9Od4clKNTBagUGgHdqBW70SvT6LXt+Hz7c+OHRVvnELxBlbrwzidFy5ovonAufyj6mDW9/8Dd3ke\nmNcMfG9kBOXvfsdRJ5+8oDlFREREREQ+bIjG1MeUBx+04/U2p8pWj3T6aNTq+wmHV9HR8RcKBQ2Z\nTPMqVg7HSWi1a0kkLqvfeAbDw88zOjq75s+Gsc+gUASYMN4MTRhTYeAfrVfwdP4aUhPDQIkrhm5h\nRDbKO6mVjNpPp5WCp7WwWl/E6ZyZu9TYhl2vfwGvt1FVNgk+30rU6g2k00fvOhqLHYxEso1yeZDp\n0EqL5WYKhSCh0GrmCwFslFKp4qYrFHYLF8hkrXsvF0okYsRqXYtUmqdUamNiopdcrraXNps9DY3m\nZ8hkB1Eo9LU0Z3//W+zcWT28MJdro+LvbOY9iTA8/DgKhYFyWUGhIKBSbSaTUZFI9JPNHo3P143P\nN/s+zeVWkk4/jdX6Ck7n/F7PemQyFtZ67mRb/4H8yfP/GCE/p83rK1diveMO+pYvX9BcIiIiIiIi\nH0ZEY+pjSCqV4eGHLUgkDwDVJJdbQ6t9nlLpAHK5PrzeSxgY+F/c7i/Q3JP8Mlbrk3i91Z/g16K9\nfRtu91DVcyM9r3KDa33DYxWAo3p+yJjzm+xeu8Db9s/zdlOranzGYtFPK1/HbLYbQQhTKjWWp5ZK\nLWfJkvsYHd1tTEWjJ9HTcxv5vA+N5iXy+W5isVOJRi2MjDzI2Nh+Ta9rTySSuaF8MlnzOXGLRSBw\nMlrt8xQKZjKZZeh0mxkYuHMPr91MBIrFIzCZxvF4mjemtNoxxsdriy10d2dxOps1LmVMTu5PInFE\n0+uJx00Ui63V6ZqLis2ef+fsznHeCt66K/OrDLx80kkcfN99tJsWlkcpIiIiIiLyYWUhqSQiH0FK\npRJf+crLbN9+OBKJloq21uLQ3u4mlTpw12u3+yr6+l5qagyz+QWczmPJ5U5ooleJ9va3yWQOr3pW\nIc00tQYZUJQcyr74enR3v4vB8O+43a2FXGm1EwjCX0fdAAAAIABJREFUXG/AfKTTKWC6FlcJKOHz\nXYtKZSMUugKf78tEo8sAFYmEEp1uoeqIW/B65xbjDYUOYGTkz2g0GxY4fnOo1c+i1a5Fp1OSyVSK\nxMbjBzM+fhZDQ3cil6+jor43TaUgcyx2IgpFqIUZy5hMr5PJHFmzhVLZuKDFbrRoNKn6zfagq+sR\nDIY0oVDt9bTCjuAtnGD6PHcrK8VoXzrjDI587DHRkBIRERER+ZtG9Ex9jCiXy5x55k949tm/BySo\nVGYWSyENQC7f09OgAbxMS6kbDJuIxwcolarnybS1OUgmJTSrBmixPI/dvqrm+WROghtoNKjxNZmW\neLY5z1grKJUuZDI7k5Pfb3mM9vYOAoHGwzUFIUgu10lf352EQudiNL6FQqFFIhHw+88gnZ593X7/\nKvr7byUe/wSt3ittbUGKxbmFZYPB/QgGl9PXdxep1NFVei4+w8N3Mj5+Bum0nkRitgGTz3dP5USF\n0Ok2o9dHkMsnSCbNlMtFZLIEdvt51Qeeh6GhJxgbq31/gp9AoLVQSqWyee+SVhvBbr+gpfnmR+Bd\n/y18b+AYpMvWcv7a+9FoFx4iKiIiIiIi8mFGNKY+JqTTWb797b/w7LNfZfpjT6cFFtP7ksnMfWo/\nMXHJlHLaGeh0G8nlwvT2BpHJtPj9JqLRaQ9Qnq6u9TgczSqlgSD4mS+vZ6jN37Ah5QQubr+DUODA\num0XRgm5/D0mJk5usX8As/lREonG81A6OzehUGxmYuIqYBUm02tks8fi9c53rQpUKh0LMbo1miCT\nk9W9hlJpDJlM2fLYzdDV9QRO5zkUi511WnYQjx8zS5RDpXLS1hajWbn+rq4t+Hy9zJ93JrQc8qhQ\nNO9Z9vu7Uau9pNPz1y1rDQmWFcs56/61tOkXpgApIiIiIiLyUUA0pj7iZDIZXnnlbU49df5E8iuu\n+Bcefvj7zNwMRiKH0dHxHqHQQYuylkSiE5ksSKEwc7MqA4K0tTlJpzeSTn8Gm236nJ+envsxGDSE\nw9uZmDibVlT8FIrqmzajcQORiBV7svFN4y96T2XCe35T88+HWu3GbH6LcrlAJpNFqZRSLEool5NM\nTBiAIKBvetzOzmcJhc4glTLXbzyFwbCNsbHdxqrf/4mG+nm9XchkLgqFud6lRpicPIX29g+IROZ6\nnzo63sHlWl2l1+JjMMQIBOoZUtXJZKxkmosWBbIolZsIBD49b6vBwadxONa0tC6ZrHnPVCp1DsPD\n67DZzmlpzvk49dT1PPDAUej1fz1xERERERERkX2JaEx9xLnnnpf5wQ/e5b33jpm3CGZPz6Xs+VQ9\nl1uBXP40sDjGVDy+GrP5McbHZxsjLtf5dHTcSDC4Zy0jEz7f5chkD5FInITJ9Azp9Eba29uQy5WU\nSjLCYQ2TkwcyszbSXKoVD82Sz7+PTBZFJ3kXFxIslOtew8vKlSgUIXK5RkMNy8hk48jlATKZQcpl\nLWbzLSiVw5TLESYmzOzYsfghVcHg5SxdupadOy9puE8+n21prlTqFAyG14hGWzOmlEoHxWL1z08m\nS7cwYgHYAaxoqpcg7Nufu/7+dbjd9T+fcjkO5GmlxlS53Fy+3DSRiBK9/j1iscX57gMcfvib/PGP\nB4uGlIiIiIjIxwrRmPqIc+utcT744Gt88Yu3cdNNn0ajqZ7InkhUMyQElMrJRV2PTFZtw64lFPpJ\n1fZm81qCweNJp/sYHz+CoaF78HhWzsjdyaDXP4NWWyYYPJLsrlymBBJJGKlUTj5fbUOeQqWSkEic\nzkb36ZzUdww/Tt/ARZGtNdf+jeFr2R7+HDrdc+h0afz+o2lry6FUbkepVAJlSqUSXu8RpNMjSKVh\nLJZHcLmWkk4vQ63+C21tTmKxw4nFFiY5XQ+pdCOlUuMbaZNpPS7XSS3OlkCpbMXoqaBSvUc0Wt07\no1ZHadwTmcNqvZd8vo9USkmh8A7JZPXwwbnECIUWtxTAfCgUo6RSUhoxkJzOz9Hbu5ZY7EhSqWUN\nz6HXv0IgMNLS+qLRHnS6xVLzg5GRLdx+ex8m03wPPURERERERP72EI2pjzC33fYWNlsMkPP731/J\nCy9s5sYbFVx77VzltKVLq+e8CIJhUdbS1/cgKlWWUqnx8SyWe/H5TpnhBRKw2z9Nd/cT6PU+fL7D\nARWx2PnEYiXU6hewWJ5FEGTEYmXC4QMQhCB2e7U6S0ZSqdPp6bkfn+9SbBPncH1PDy8O/Yyf2m+v\nuh6HYCYUWQYsIxiE9vZ/I5M5h8nJ2SFYGs3LjIy8Siikw25fybSHJJ1eRbp1m6MJClitNsbGLmqo\ndVfXBpLJHGBteiapdBtm82s4HFc33Xf3GGUq3sPZnlOVahSv19jQGArFJvr63sDh+CzTP1tDQ3c0\nbEyZTOvw+6vXeFpsOjreQq3+ALf7ygZ7yCiVJKRStaXT90Sh2IpWK+DxHNDSGkulA1Gp/oxOF2d8\nvBnlzLl0djq48srnOOigbyxoHBERERERkY8iojT6R5SJiUl+9KMy4+PnYDbfTH//Fmy2o7nxxtfY\nutU9p/3++xeoFg4nCItxC+TIZAzYbFfgcJzbUA+rdS1e7+lVw+kmJ88mGpUzNPQo7ArNE0inT8Xl\nuhqH4wrC4U8Dh5HLnVZzjlSqf5a4wbjvCJ4orK4aFAjwo9Ef0Gl8YdfrSOTfiMePqTLuCYyNXUmx\nmAIa9yQsFnL5gzgcK2lMDCFLsbiVZLL2+zQfCsU7uN0nsZCfCq1WRbUCx1qtk1TqeCAyb3+p9E3k\n8gIOxxeZ+fynWOwCYg2toRION7fW1eKSZ2TkIfL5UhOGVAW//xOMjDyMybS5kdb09dnweBrLeauF\nz3ceSmVroZ/TqFRefvjDIN/7nmhIiYiIiIh8PBE9Ux9Rbr55M1u2nAJIGB+/DrP5DuAIXK4vs3nz\n66xYMTukKRaTUX1D3FrOxWy8zJ/TtBulchtq9WPAEvL52mIAmcxB2O0jjIzcjcNxXs2cm3rEYt1U\nagZpANg2fgbHjdzK5+K/Jo3ARv0xtGUceDVHsD23gqCj8SLG8XhrogGtU2Bw8G4ikR6i0UZC1spY\nrffhdM4vgDAfvb1lbLahlvtDRZK/GoHA8ZhMT5LPa+jsTJBKZfF4DgeWMPNelUqjZLNzVQtdrrOw\nWp8lGo0Qja5mPoPPYNAwubgRrTPIY7E8gVweZWxsDa39rA4yNjbIkiVP4vcfPE+7HMPDz2KzLc69\nl8m0bmBqtW5uuSXAmjXNFw0WERERERH5W0E0pj6ClMtlnn5aw0y5aq+3HwgDHezYMVsuORiMsW5d\ncs44Gs1fmJhYeH0fo3EL8Xhj45hMTzE5eT6RSCOS3hrGxq7EbH6AROLgBvvMpqsrTDyumXFEzetj\nn+Vd1YmUSlqyk72MjNzH2I7Lmh57sVEqvWi1O1Eqs2SzKrJZNYnEIYAMhcJDZ+ejOBxX0N3dWJFb\nlcoxdV+0+jWfG5rXCvl8T40zCvz+Sv2lcBggj0Jhp7f3HpzOE1Cr30KrTZLPDxOJVBO/EHA6zwDC\nDA/fi91+HOVytVC5EpmMG0hQkSjPYzC8PyXLvzCGh58imw3hcl1MKwISM9FoXsbpnH9NKtVT2GwX\nsDj14UqkUq0ZU2q1n1/+cpI1aw5bhHWIiIiIiIh8dBGNqY8gPl+QLVtm55qUy0MMDr6Nw3E6a9eq\naG9/nUJBymuvbeeNNyZJJnuAEjLZK1MS1zmMRgdu9/ELXk97e5pwuHoh3j3JZo8gk9mvgZZBRkae\nQybTUigYUSo30d8fxuOZG3Y3H4WCr+rxdGYpAEqln2Cwsbyd+SnT6gbXbH6RUmmCeLyfYPCTM874\nMZnWolQWSSY7mZj4Mmr1n5icPLPumP39G1EoxrDbW88TGhz8AzZb42qBeyKVbsVieRWP58IGe8jJ\n5ZYRDsswGoOEw6eTTiuAenWojNhsV6DXb6StbQMTE7vXLJFEsFofwuG4Fp3uWYzGDKkUZLMmOjq2\nEwqZqRSV1tJsGKBcHiSVKuLzLY6XSKsNolbnmZjIk8tVV06USrMs1GjbjYNEorHv7WyK3HDDNq65\n5sRFWoeIiIiIiMhHF9GY+giiUCiQy2dn/hSLS0inXwaKbNx4BF//euW40fg4MtknmZxcSV/fegKB\nYbTaEPl8nHx+4cpbOt0TOJ2Nbaqk0i1ks414OkqMjDzB2NinmWmgKJXvMTj4FA5HfWNiGolkvmKp\nZQYGnpmaZ2H09Pw/NJr9kcvVZLNe/P7TSKfrCz4oFD4ymRSBQLUNuQm/f/bxdNqKVDpBsbhk3nEF\n4X3s9oVc1zjJ5ADQWuHVzs51yGRK7PbPNd03Hh9uac5Y7DBMpolZxwYH12O3Xw3IiMcvnFWIV6d7\nEbX6AwoFDf39TsrlPpzO4+ju3kostoRstnue2Ur09z84lce1OPj9FaNTJnub/v4P8HjOmNNGEPIs\n1s+2Wr2FdPrUpvoIQpxvfOMNbryxVWVIERERERGRvy1EY+ojRDabJRhM8u1vv00gcPqc80qlmj3D\nssLhG1my5FkmJzVMTFQ2QPm8Fa32OcLhIxe8ps7OEPH4fJvO3YyMbGfHjvpeiqGhexkbu5g9PT3Z\n7EE4HB0MD9+HzXYxjdy+mXkqrQ4MPIfdvvAwRwCd7nB27txdBLWj4ykslk1EIgYCgaVotX6SyX5U\nqixqdYBA4HAEIUJPz/O4XI17NkwmJ4FAvbyuAjXSlBpm2bLX2bGjMbXA2ZTo7n4Rudy4YIGEVvD7\nV7Bs2UMUCgBFstkEte6TeHy3QeBwAORQKJ5jcvIAjMY36O9PUyoFcTi+PKfv0NDjCzRWa1MomIhE\nqnvjpFIJixPiB2p1nHS6eimF6qT4x398h//8z9bETERERERERP4WEY2pjwgvvvgO1113E5HIN5iY\nmGtIAYTDJRSKTeRys/MuikXXnLaJxHKMRifhcK18lsaQyxtRlKuQySSotxE0mdbh830SqLXJ68dm\nu5jh4XsYHz9nXhGLgYFHcLtrb/zU6hyl0mKp8c3+KoVCZxIKAZQQhLeIxQZRqbZRLguEQmaWLn2Q\nUik/JVjQODpdHr9/vs8sj8XyK8bHWzGEKlgsd+L1rqQZBT9B2EBf33YKBT/5/FlMTrYm2b1QYrEh\nYrGhqVdlenruaqK3glzubADCYSvhMJhMd7FnCKfJtAmv1wrsneK03d1/YXLy0qrnFkV8c4pQ6BQ6\nOt4hFGpEQCLDt771Bv/xH6JHSkREREREZCaiMfUhZ3TUwbXX/pBE4hi2bv0N8+V19PS0kc8Hcbkc\nKJUx+vreY3zcQiBgRS73kM/3z2htRqt9lHD4CFoXGfASjfY23NrluojBwXtRKDTkciUcjguZuUlV\nqzcC/aTT9ZTqZNhsV9Hf/zCp1Io5whRW6wtIpW5stlOA/upDALmcjIrIwsJ3qIJQrHWGUqni/cpk\ndsvA79zZeE2hmYyOHoFev4VY7MAaLaSAgXK5+ZpSFRLE4/3E482JfbS3v4Lb/Q32bbWFCBbLo0il\nSrzeZWQye9ackqBS5aZqk6XweJaSz69oaga//zyGh/+IzXY5IEWp9CORjJPJnNfEKLvVJCGFVvs4\nicTJQLV8JQ9qdY5a76NOl58y0heDXgRhRwPtSnzxi3/hv//7VCSSxfGKiYiIiIiI/K0gGlMfYv7y\nl81cd91a3nvvB5TL8z8FHxh4ELf7ODKZXoaGHiWR2IjN9l06Ozeh072FwzHXU+ByXYnV+gBOZ2tK\ndkuWrGd0tPoT9OpocTgqnhhB2IbZfCt+/wXkcpUwwd5eFzbbqoZH83guRK9/GbPZP6vwaDLpIxis\nX+dnYmIQhWI9udzCn7bncnu7htE0S+joWEsm00MuN3cz3t6+lcnJWoZWfRSKV0ilmvHWlVAq30Sh\nsLAvDane3qdQqeLY7VcBEgYH70ChcFEqpREENdlsHKfzRKRSIw5HxTtpNt/BxIQMlSpCMtloeGc7\nNtvFWCw3E4sdREeHA5ut8QLGGs2r6PUuFIosxaIGqTSF03k5BsMWTKZKMeWZAh1dXeuIxw8CCsz9\neU6RybRmhNdCp7MRiRxIodBRo0WJCy54nF/+8mzRkBIREREREamCaEx9iLn99nfYvPnf67aTyd4g\nleojk6l4iez285HJKrVqgsFDCQZryS3rCQT60evfJxZrNizLRjT6DnAiMJ93KkR//8MolRqy2TS5\nnEAgcC6lkkAmo0WpTJHLTbdtXuwgFjuBRMLG4OBtpNN5ZLJ2AoHGFMry+eWMjLzJ2Fi1szkaVU1T\nqXyUy9GG17xQ7PZLsFrvx+s9ZZZBNTDwAsVimkjknHl618LPwMAjRCLHk0w2LgAxNHQ7fv+xU2GB\n+w6dLs+OHat3vXY49jRwCpjNd80SFwkETkGlitPT46/xmddChcv1VcBPNNpMHlgKk8mB3T4dyplA\nqUwCCqLRw4lGYfnyP8/qYTR2sWPHgXR2PoxOJ5mlxmixPILLtbgS/um0nmKx1p+BEqtXv8Ddd5+F\nXC7+qRAREREREamG+BfyQ4zbXTtEbSaFwkr0+t8RDk8LE0goFIYa6ptKnYDVeheQQSbLEQodSu18\npZkYKZVOprf3faTS51EqywhCO9msH6XSgCDIKJWKpNMduN3Xsjucr0xX11NIpRvw+f4vM8P8ZLLW\nCgiXSv1IJGX8/s/TrHckne6bc6yv7xEkkiKplJ5I5CTqfU0sltfZsaN1CfJWcDovxWq9B7f77F0F\njbXaLNu2tWJIFTCbn2BiYjXFYnMy8fm8hVSqEan7xcRLKlXvHpUxPv6ZWUcyGTMAEsl4i/Oa6jeZ\nwcjIQ3soRWrJZmerSyaTSQyGx0gkzBSLh1EstgFagsHVGAxPz2qrUmlZbO+fTFakXK54VRUKO7nc\nEHr9y2SzZoaH/8jvfvd1FIp95XUVERERERH56CEaUx9SfvObl/jLX/ZvuL1U2pqENYDTeSVa7e8I\nha6go+NBcrnjSCR2eye6ut7CYAjhcBw5IxyoHZ1OisPRnLQySAgEzmJgIA3kAQGj8VGk0ii53PQG\nOUZn58MEg5fTiHfIav0zdvtnaGWjGYl0AF7M5lfJ5/2ABrlcgdN5OW1tb2E238z4+OeBWkIbMfz+\nfZkntBuncw1DQ3fgch2PTucnk7G1NE5//48YH7+BZusstbc/SyZjaGnOhdDb+zRu91Ut98/n9/7P\nntG4Dq/3JOYXXHEhkXjR648kk2nHbH4Wv3/prrOJxGyDsVRKL/o6x8cvxGK5m2y2l2z2Fbq6BvF4\nzmH58sd45pkvYTC0/rsiIiIiIiLycUA0pvYxqVSKDz6w09/fxcsvO1Aq5YyOhrnkkhW8/voHDA31\n8NBDAf7nf5aTSjUu7hAI9KBWO0inW8upSCQ+D0AodCU63RMMDr5GsahHIvHi8x1GIHAGHR3rCYV2\n15SSSlsPbUunu4Acg4P34nSuplw2EAhUNp5DQ3/Cbl9Db++rqNVObLbzgA5mJ/LvJp+P0OoTe0Eo\nodG8QTK5H+HwRVSU2yq64snkkSSTh2E23z6ljje7LtfQ0IsUCu8zPj5XOntfYbdfCbxHJHIkbW2O\npvvLZBuJRC6hWUOqp+dRcrmlBIPNCToslLa2tyiVDmEh8uCVWk3Q2fkY7e1ZBEFKLpfA6TyIoaGd\nCIKA368mHm/Fy1chHD4ei+UZUilzzTZDQ89jt1+/67XDMTTjbIFsdvbPczzeSoHdeshwua6Z+v+Z\nRKOw//4beeCBcxkYqK2UKSIiIiIiIlJBNKb2ERs2fMBvf7uN++4bJBZrRyqNk88fCcSAA7jppg1M\nTCgoFJTkcifQ7GYxFtuPzs6xlo2pmcTjZ88qbgqg1T5AIjG7LlWxGKVVNTyj0U0odAKlkolyedpI\ncTIwsI5odCWgmHqyX0KrfROtNkYup6CrK0EuF8VuXwVo6ezcRDTaepiZ0ThGJmMlEJjOGduzjo+U\n8fHPMDT0FIIQQyKBbNZLLidQKAwyPn5dy3MvDgJwCADJZC1FwdoUCiYUCm/T/RSKIj7fvjWkAARh\nHL9/YXWOJiYOZnDwf/F4LiEYnPa0llGpdmCzXQLAkiUPzvkONINev4nJydp5ZBrNq3i9tb26CsWr\nxOOzPdM6XQG/v/U1NcKSJVu4//5uDjigsRBjERERERGRjzuiMbWXKRaL3HDDem666WCKxd2bo1Jp\n+n8VQ2J09PgFzuQnFqulyLVwEonVWCwP43IN7TrmcByHSrWRTKaROjV7Mm2wlIAYFssdJJOH4nZ/\ngdlS7QKJxEoSicqr6dpNQ0N/IB7vRxAUpFKntDA/GAwvUyhYCATqKbsJ2O1n71pvT8+v8fuvZE9P\n1V8bpTLRQq8C5XJzPwN6/f2k081Jpy8WhYIBhSJMLqet37gGOt0LU4IVM8PoJGQyu6+pUMi2vkig\nuzvE6OiJNc8PDEywY0ft4su9vT6cztn9BaFQta3Fso5SSY7bXb3+XKN0dY3x05/CQQfVK00gIiIi\nIiIiMs1fJ9njY8L69e9x6KHf42c/O45ice+GzAhCklKp9Q1mIyiVpT2O6FAoWsnjKJJOV7whmcw2\nOjvfwOX6CqHQCTRW80rAbv8sWq2bycnWDCm9/k2kUnULKnRlMplOPmyGVHf3n5BKj2qhpwmt1tNU\nD61WQyBQSyFy72I07iSXmysaUp9x+vr+iMVyJ21tauqLrChbmKNCZ+fj2GyfnKeFA79/ybxjqFRz\n1xeJuKhIpu+mrc1OJKLB7V7OwMCtSCSthd4aDOPcdVeO889vXVZfRERERETk44hoTO1Fvv/9F9iy\n5d9pVGJ7IZRKx9Ld3UgBztZJp0t0dr4OlNFoXqKr6z1isdpP12tTJJXaQnf3r0kkriIYPJ1WCgeX\nyy1MPUV39yih0JH1G+6BUjlGLLZncdi9h0bjxmCorz4nCDk8nlY8hCra21MNt+7tfWxO+Nm+xOM5\nm/b2txtqq1S+w5Ila1m27GGGhz9gYuIyXK6rEIR6N06ZRKLx92Qmev2raDQGSqXaqohLl75ONDq/\nMZrJVMsN7MJieZGurorKn1TqRatdTzx+EmDF7T4CqTTQ9Jolkjg33ujmzDP/ep+riIiIiIjIRxUx\nzG8vcdddT/Hyy/M9nV58JJIQGs0HpFJ7Z1Pkdq8GAgwOPsrExDCC4Ka1fKnXUSi+iM/XiiclD8gx\nGt/F52vFkJsaJd/TUj+1OkQ2u/ef3vf3v8SyZU40GimbNx9JtI7DQSrdN89F2tqkeL3ze1X2Jlbr\nCzidn67brrPzMdLp/RkdvWTOObm83sONHMViI+UB9mQLHR2jU4WEq9PW9ioTE8fUGWcMv39uqF0k\ncjGRSGWMvr7bUCjkTEzMzG06jP7+tTidzXw+Jb70pQ1885vNqnKKiIiIiIiIgGhM7TUee2wb6fSZ\n+3TOiYnVDA3djt2+N58wd5FKFejpeRWX60st9Hei0yXn5IPUo6PjAwThDbLZNrq7BYrFMG1tBsbH\nmxdB6On5M7HYsqb7AUQiR9DZeQvB4Fdb6j8fhx56N2NjKznooMfRaLrZvv1wXK7GDDdBqC9YIpNt\nZWhoFImkSCQSRquVUipBOHxIgyuMkE4vwB24CGSzYeob8DmUShnB4NKqZ+PxPFJpgGKxujqeVruV\nSKR5Q39k5F3Gxi6dt01vr4/R0fkfAhgMG4hGL6x5Ppk8Cp3uPRyOa+ecc7sPpLf3GSKR/clkTNTz\nip977np+8Yt9+9BHRERERETkbwnRmNoLPPromzz0UPNha4uBTFY9b0omc6FQJEilFq7ANjl5MRbL\nPS317ez8MU7nj5ruJ5f78PkqEs7TKmuCEGF4+A5stouAxvPFlMoMPl+rAgpytFolwWCL3WuSZsUK\nHQcddB9PPHEYMlk38bgBSFORLZ//qyo04JiyWt9h585pr06ByUkpzahGdnc/hsdzZd12KtUkhYKU\nQqEDq/U3lMvLcLlaU+Dr7HwIo7GNcrlAuZzC719Vp0eEwcFHcDiuqNliYuJTDA39Yao22VwSiUOx\nWB4jm30fv7+ePPo4AwN/QiodIhQ6itq5ViWGh+9mbKy2kTRNNHopQ0P3oVQayWbluFxH7CrMXEFS\n03guFleQTI7S3f0KgiDgcMz1zE2zYsVGfvvbg5HLxT8DIiIiIiIirSL+FV1kduzw8K//+mey2X/9\nK8xeIpGY+5G2tz+HwWAnk8mh03mIxXpJp1sPVRsYeBC/v7WwoFTqNCBLc3WN4mg0zjlHS6V2bLar\nGBr6Mz6fhXS6EVGEEtB8XslM/P4zMZsfYHx89QJGyWG1buaoo0occACsW/dndLoQxx9/Er/+9SfR\natt47bXtlMtREokcbneR0dEyb75ZZNs2GXb7fsDugqpy+Z7iIHMRBNOMV81/9XU6FZOT8xtfJtMG\n1OrNlMslSiUNTuf5KBSjtLVtIJk8kNl1wsqAj/b2d1EqE6jVSvJ5cLvPpWLkBVCpDOzc2ei9lmFo\n6AHs9s9Rz0gsFrNU7oMO5nq6JLhcq9BqxzGZHsHv/wTDw88ikZTJZGQkk/3I5X6MRhWZjAqX6+t1\nV6ZSrcfn+wTlciNFcAXs9jVT/0/R0bGZUGhmaKCsqkDFNPH4+cTj0NX1TM02er2Lm2/W0te39xRA\nRUREREREPg6IxtQic/nl/4vPdwqQBNoYGHgLqdSLUikllRJIp3WUSnoikYXl3QwPP4Ag5IlGuwkE\nTqGyISygVodntRMEP6lUmUjkc1NHcoCL4eG7sNkupVlxDJPpAUKhY8hmTfUbVyGdPh+r9Rmczvoh\nkCqVG7N5I+FwGZutlkdEgt1+Pt3dm9Dr/4zPd16NdhHU6pfp7Q1gs11To01jpNMWwmGBgYGf4nZf\nT6N5Y4IQ5oADtnLSSXJOO03KqlWHIpNVvoLXX7+E++67n898ZreBduyx1etnlctlXnnlA37+85fY\ntOkIPJ4soZCZipFazTMSo7v7aZLJoaauczZlLKAIAAAgAElEQVQJYrH5FSkHB2/F4TgbOJqK6lwJ\nUJDLmVEqb8dk2oRWayKb9SCXmyiXJ3G7h4lEpo0lgYpM/p0IQjvFYgCptPHN/vDwWmy2a2nE2+Zy\nfQG5fD1msxOb7erqV5wwo9X6sVg2YLOt2TWuWm0nkTiQQKC2yMRsSvT2OnC5mldAlMtfJhSarTgp\nkUSIRuvfc9lskMHBx3E4zt3jTJ5vftPJiScutByDiIiIiIiIiGhMLSLlchmv9zgmJk5kYOAhJJI8\n4fASksnpDX4KkDE8vHaBxlSCQADi8TXAu3R13YRGY6JUsmO3fxnIIpfb0WpdaDTv4nbPfHKuAJZg\ns1mwWp/E6ZwZNlXCZPoeOt0BZLMa8vk+fL7Zind+/ykMDT2L3T5/bkhtBAoFF1CkloJfe/sHdHd/\ngMfTzc6dtYyj2UxOHkpPj59aRYQ7O9cSDF6KzaatOW8zJJMDpFKfw2z+OePj1zKfVHpHx04uuijA\nNdcYOfHEY5FI5m72u7s7+NrXvtzQ3BKJhOOPX4Hd/i422xiFQoiDDnqHZ57JkUyeNKttW9sG2trS\n+P3nUl8OfD5KZDKqmmc1GjuJRA8wLYgw+6clHr+GeJwGis6243LtNm56e+9hvnulu/sx2tsL5PMx\nXK5za7abi0A+fxLJ5L3ztvJ65yokptNDDc5RYXj4niljrHlVz/b2d5mcPGOPo3mSyer5XjOJxy+n\ns/MeZLIQhcJuo/Tcc1/lu989oem1iIiIiIiIiMxFNKYWEYlEwrJlcSYmhCnluz3RIJVuxOdbqBqc\nnPb21FTu0CGo1W/jdK5BInEwMvI0pVIOm+1IwuFPEA6fTPWPWUEwaMVieQGX62QAurs3E42eht9f\nEYeQybbS3/8kHs9Zu3q1t4fJ510LWr3Hs5rOzhsIBv+Hal6EtrZN7NhxedPjBoOH0db2AsnkJ5gZ\nTtbT8xDZ7AmAofVFV6Fc1jM+/nV6em7F55srxtHXt5XLLotw/fUjjIxUF0NYCFdeeTmXX17guefe\n4ZlnPHz1qwbuuedV1q41E49bUCq3YjJNYLNdsAizlahlqEgkCbq7X503T6l5PGi1G1Cry3R0/IlQ\naPb3yWT6M0qlmmDwMCYnzS3PEggcRlvbBySTiynaEgO2Y7F8QKGQo1Qq0Gp5BL3eOie0slzupq/P\njc1Wv7/dvobBwd+RTu+H338CVuv73HTT/giNJNmJiIiIiIiI1EU0phaZTCY57/liUYfR+C5KZRip\n1Nhi8VMl0LvrlVRa8RiUy4OMjg42PEoyeShq9fMMDd1JsVgkkzGTze4WCpDLjZTLTzE8PIlEIieX\n20I+nyCVquctSqFS+SkUCmg0GVKpdgqF3Rtek+nPJBKfp5ohJZNN4PMNN3wNMykUDJhMfuTydzEY\nUgiCG4/nSAqFESKRvaVwKEMqtdLe/giRSMVo6e7eybXXuvn2tw+lu3vhgh97MjkZ4O677+FrX/sK\nMpmMUinCpZd+iqOPPowzz4R/+AcnN930Kk8++Qo22w0Lnk+vX4/RGMHhmBuaqdO9h1q9HofjugXP\nM5Ph4eew2S4kkaieY1QsenG5rqG53Lu5lEr70d192wKNqRIDA3cTjRbR6bwUCp8gHB7E5boSlWqC\nTKb5vCSDYR1dXRnC4epCKanU4Vit/wsYSaeVTE7WNpgdjksxGt9BEGL8279lGB5uLURXRERERERE\nZC6iMbXIdHWl67RYgtu9BCigUr3D8PDDTE72YTIFGR8/ilyuu+4cbW0uZDLPjCN9dHc/XSUcqD6B\nwCkEqugx9PSMccstaY4//rPcfvsrhMMx/umfvoNKpeKGGx7jl7+cIJfrm9GjTF/fBq6+ushhh6U4\n9tgDUSigo8OMy+XnG9/4MU8++U0kkjHU6jR+/8FV12MybcfjOanqufoo8HgqifuRCPT1bcRkegaX\n6/oWx2uMSiHZbfT2/oRjjjmc669Xc+qprV5Dfbq7u7j++q9xzz33Ew6H6evr4+ijd4djHnywlZtv\ntuJyLeHnP3+FW26xEo225r2xWH5FOHwuDkd1KfvOzg3Y7YtrSIGXUqmbmQIbe6LXKwkGF2ZITTMx\nYQISVBQhU1S8cLXUIWMIwgQyWQqzeQexWA6lMoTb/UWgjCC4aWurCL7kcka02hDB4FJyuROo5CvC\nfF4qrfZl+vtDOJ1HMDpa+zPz+Q4FKg9ili17mMnJ+a5Qj8EQZPXqt/nsZ0+er6GIiIiIiIhIk4jG\n1CKzfHmcxx+PAfo6LWVkMkdPhepESCTasVpvnSpIWjs3BWBg4D22b98t62y3n4RON4rV+iuKxQ7c\n7ktYyEfb2enkt7/Ncv75lXDEv//7s2ed/8lPVnHWWW9x/fUb2b79LM499xH0ehu/+MW1dHXNTcpf\ntszKd797PkuWPMkjj0xWrY8zjVZbzxhtnImJwxgeHlu08eajuzvD5Zd3873vnVw1J2qxkUgkXHHF\nZfO2sVhM/PCHJk47bStr1ow3YVCV6Ou7Ba22B5/vTBKJoaqturs3Egy2Vq+rFlLpKFbrG1M5RrWR\nSBbPu5LNns7g4J2k0zLa2oxEIr3o9WP4fMvJZA6f0bLAwMATFArLSKf/f/buO0DK8tz7+Hdmdme2\n9953YSnSi4hKFRARlWIjIoJGfdXEEhNNNycn9eSYqDHRE5XEWLGgohgrCIL0ooKitK1sY3vfmZ2Z\n9w9E2pbZKdv4ff5inucu17LDMtc+933dFg4fvoZjFQmbOL4frbY2m9raY0s6jcaj1NXFEBSUT2Li\nW9TUxGE0OomKqsNksgPgdBoAGzU15YSFRVFYOI79+7u2n6m5ufMlhNHRFTz00CWdthMREZGuUTLl\nZX/4w52sWLGbkpKJXeh1rHhBfv50LJY8WloG0V5FMn//EqzWMx8l1dUNoK7uDsLDPycqajXV1Yk4\nHOe1MULHAgPLeOSRSi67bHSH7WbPHsf69RX87W+vctddM4iLm99h+wsvHMyFFw5myJBN3H13I05n\n28lma2tjl2PuiM1m9+p4p/Pzq2Lp0j38z/+MIjranSWbvnfJJUO54YaPefTRZFypdJea+jwFBcto\n/8ykY8LCDnD0qLuFSE4wGr8gK+trDAYTdXUWcnI63ntlNu+kuNibe9DM5OUtIzFxIzk5xw6wrao6\nl8DAQyQlraelxY7RWEZIiO2b2E7+sWng1HLvx6+Bw3Es4WtszCAvL+Pbu5WVZ0aQnv4ceXkXYLV2\nXljidA6HgfYKrwCYzeX85jcXEhJyepwiIiLiKSVTXmaxmAkKanWzdyYJCX+npeVdzOZszOYWmptr\nMZvDyMu7CLs9nNTUdRw+3HYpZ4CampFABuHhr1BTk82xc3Rc1cCvfnWQxYsvcKl1QkI0v/1tx09H\nTnfnnRfQ1LSZBx9M4OjRM/dG1dfbujRex2y0th4gJmYt5eXTcLWEuavS07/kj3+0sWjRFK+O6wu/\n+c1YbLYNLF8+DJut/RLn6ekvAjY6WooWGfkFkZGfU1h4jhciKyI5+RMOHjyzgEd74uL2U1jozWIX\nAEYslpZTrjQ1DaCpacCxu8YKysvN+OpHZkHB+YSFFbuVTJWWjiMp6XGKir7X5v3Fi79izhxV7xMR\nEfEFJVNeZjAYSE2t5rCbq8vM5hTy8uadcT0z89/YbKEUF2e4MEoYdXWXk5b2Nvn57Sdep3Jy663b\n+PGPp3clXLfcf//5DB68l8WLj9DQkHzSnWKqq9s7u8eJ2VyC1RrOmU8C2tJKevq/ycv7EdBMevpT\n5OXdiKcFC46xMWfOZv7+9yF9ZjN/eHgIjz8+hYCAt3n44Zkce+pUS2Dgx7S0ZJKU9DWtrRHk588l\nKmojFksBLS1pbYxkIzBwO4cPL3MjiiJCQz8hKOhzrNYBVFefT3r6NnJzv9ulUSoqhpOQsJOSknGd\nN+4Cg6GChIR11NUlnFGQwuHo+IwtTzkcwcTE7MJiyaO0dBadPRU8WWtrLCUl1xIX9yxlZaf+e8/M\n/ILf/c4bSa+IiIi0RcmUDwwYEML69V3vl5r6EQUFbX2AhZycpW1eb4/DYaa62vVS4BdcsIWHHjq/\nS3N4Yt684dx66zoeeigZg6GGtLR3KS+3ExdnxGD4gOLirG+fClgsecTHv0ttbSohIU2EhDTS3DyO\nsrKOPiQ6qK52cuwJi5m8vJvIyHiB3FzPDuwNDCzj/vu/5oEHJvXJ8tJ/+culBARs4M9/TiMycgtl\nZZcRFFRCc3My5eXHloX6+9cTGfkRAQGh5OYu4MRhtUUkJKwlJ+c6t+YOCfkSGERp6VWYzeWEhhZQ\nUjKbrp771dQ0jLi4/7gVQ0eO7dNyYDDsIzh4Fw0NZ54x5TsJHDx4NccO+H2BkJAACgom0dJyrGqn\nxVJMauoO7HYjOTnHk+ETHI4YbLYhWCz7aGk5XkGyiR//uJHExK5XExQRERHXKJnygcsvD+af/6yj\no2pkp3KQnPwe5eUxp214d19q6gcUFCxwqW1AwKf87nchBAV1XPjC2yZNqueZZ1YQEGAnL28xwLdn\n5xiN+0hNfQWHo5WyskHk55840Lay8tiTOsim7SdNTaSlrcduD6Km5vg1P0ymzoqCdCw8PI+//72a\nxYvbrmzXFxgMBv7whynU1DzFW28NAEJobBxIY+OJPUglJdcArUAzmZkvUlIyDaPRRmzsui4n9Ser\nr7+I2Ng11NUZsFpjXapc2bZWHA7PD15umxGnMxmT6YCPxu98/pKS6wGIjFxLcvIO/PzsFBVFcvDg\n5Rw7WPt/gDmUlZ26r7Gq6txvzjxLB4KYP387t97ad9+rIiIifYGSKR8YMCASg6EJp9OVZMpJaupj\nFBTchGvL1zoXFHSYysoUXPv2tvKzn9UwbZrvSnm35/PPq3A4qjhy5MzS5Q7HUAoK2j+jKSdnFgkJ\nmykpOX2/kvWbzfzf5fQ9Uk1NJgYMWInd3oLJZCYvbzqtra4t30pO3o3NtpDFi104KbUPeOSRZZSU\nbKSwsL0WfkAIOTnXERf3In5+reTmup9IQTUxMU9SUeHeU61TmQkMdHdfYudiYrZQXd2dT6XaVlV1\nEVVVp181Ulb2U7KyVp6UTNWQkrKTwMA6SksTgABSU/fxl78M6ZbKkiIiImczJVM+8Mwz63A6b3ah\nZdM3H/yvx1uJFEBs7Fry8lyZH6ZM2cbPf94zv72+5555PP30Uqqq3DkHKomAgC8BiI/fSWhoGXZ7\nM83N9eTlXUtbxSaKii4/6VUtycnvcuRI5wU0JkzYwjPPpFNXt9KNOHsnf38/nnhiDH5+G1i5ciQO\nR/tLQsvKPC/2kJa2ivz8H+FKNcHOxMW9w9Gj3j8M+bjQ0BrKy3v3XrjS0lCCg7eRmFhFdXUNhYVX\nceI938xPf1pHZqbv/o5ERETkmL636aMPuPDC4UBLp+2io7eRl7eU46XRvaOFmpr2ijicKiCgjF/8\nIrLH9v5YLGbGjl0GNLjV32DIJzPzOazWBg4enENOzgKKi5fQ+RlfkJT0xjfncXXEzpw5H7Jq1WAG\nD05k/Pief1rhTTEx4bz88mT+9revCQ0t6ryDm4zGQ1itqXgjkQKIiDBQVeXN0uinysmZTkbGez4b\n3xsaGmbS0BDLwYOzKS+/hpN/lM+bt53bbju354ITERE5iyiZ8oGSkqMYDEc7bVdRMYbExCc4dvCn\nd8TGbqW6erZLba+77gCzZvXcb68DAwO4/voQPvjgMGPH7u5yf6MxhJyc66mqcqc0uZGOP9w7uPba\ndbz55nQSElxLTvuq22+fwP337+XYWUXeFxu7iZIS71SJNBoPUVPj66dGcZSXR5GZ+Sx+fhU+nstd\nRuDMowXi4g7ypz8N1PI+ERGRbqJkygcWLZqC2fy+Cy3DKC29hrCwt700cxMWSw4Q0mnLqKhD3HVX\nkpfmdd/ChTOYOXME993XwvDhe7rU1+l0P8kpKppGWFh789lYsmQtzz47FT8/XxU66F0WLMhk6tTN\neDOxP85ut3KsoIUnWklPX05Cwn5KS33/hLC+/lxycpaQmPipz+fyHjt3313KoEGJPR2IiIjIWUN7\npnxg9+4vsFo7X+YH4HDEERfXRG2tp7O2kpHxksulvxcvLmPUqO4rhd6ZRYsmEh29i0WLDlJZ6eoS\nLk+epKQQFfUltbUjT7tu5cYbP+appy7qk6XP3TVsWDYvvBDJpk072bXLwe7dBj76KIuWFs/PV7Ja\nLUAz7p7xlZq6CpPJSW7u9XTl/CVPGY25NDX1nbLiY8a8z333zerpMERERM4qZ8+nxW40adK5DB/u\n6oc+J83NjR7PaTQepbQ0FFe+pREROdxzz5lLhHrarFljeeSRSs45Zytg7bR9U1MIISFb3Z7PZrMR\nEHDyXqEWvve9DSxfPuOsSqSOS0qK4aqrxvP730/gnXfO5cYbNzFr1g5Gj95BRsYOAgP3A/Yujxse\n3ozrxwScKjJyHVZrBrm58+nORAogNHQD5eXeOarA9xwsXOiHv79+PyYiItKdzr5PjN3AYDCSlOTa\nb+Hj4t6gsHCax3M6HInExta71HbhwhKyshI8ntMXrr9+Anv2nMvs2UuZNGlbh22Liy8kKCjP7bmO\nHJlLdPT+b141cu+9m3j00Yu03+Qbjz9+Oe+/P57du8eTkzOeoqJ4Xn31U+64Yxvp6Z/h+pLADLdj\nCA+3UVo6yu3+7kpJ+ZCAgELcSR57wqhRO7j//mk9HYaIiMhZR8mUD/zsZ//Nxo2u/NXWYzDUA+le\nmrnzZW9mcxn/7//17rLPRqORd999kX/8I5no6I7PdQoJ8fTD7hqGDt3Ir3+9mwcfnKZEqgMREeFc\neeU4/v73CezZk833v7+BoKCOqwCmpj7vdjIUHv4xxcXnuNXXfQ1ERn6Mv38ppaW3EBe3vpvnd0cr\nN93kxGx2bxmliIiIuE9rQnxg6tRpPPxwcqft0tM/Ii/P8zN8jjOZOk/gZs48xIQJvWevVEfOOSeZ\nq67awj/+0f6SRKfT3d8HNDJkyEH+7/9uYOrUbDfHOHuFhgbx6KNTuPLKr1m2bB95eW1VhdxFcfH5\ntLbGujVHZGQxubnuVGrsuri4vfj778bhgOLixVRVHXtf1dcXYDRW4nD4cu/UfgICthMSYic42AhY\nsdv9CQqKpLHxIAZDLAUFx89OO/P9PmHCdr73vQk+jE9ERETao2TKB/z8/LB38sAkIKAUm60Kb34L\nioqmEhS0hsbGGe20sHHRRVVem6873HZbAv/+dzHNzW1XKKuvjyA19XXq6s6hunqwS2NmZ+/l979v\nYMyYDAYMiPdmuGedadMG84c/bOa666yA+dvrYWE7CAw8RGnptW6NGxX1Ok1Nvt7XZycubiMhIUep\nqoqhrGzJGS0aG5eSkfEhubkTMRodOBydn2HWFVlZr1BcnEVT08U0N0dSXn7mzwOTqZK4uA1YLF9Q\nUHADUA8cr8TZwF13BWAynR1VJ0VERHobJVM+EYLDkdJhi+Dgo1RVebeEcUtLBpmZG8lpZ2VcVtYe\n7rxzplfn9LXRozOYN28zL73U9t9VREQLBw4sICDgM8LCPqW2dnSH4w0atJdXX41gxIjhvgj3rDRj\nxmDmz/+YN94YRHj4ZiIjDdTWDnM7kUpNfYri4oW0tvq2kl5KyqMUFt5GWVlAh+1aWnIJD68nIsKK\n02khP39eh+2DgrYTFfUFhYXXAAGc+jSplfT0fwGxNDUFUlExjKamjpcy2u1RlJVNByYTG7sZq9WE\nxbKasrJbmTbtc667bqIrX66IiIj4gJIpH9i2rQUI6qBFCwEBn1BRcaXX57bZbO3eu+IKG2azud37\nvdWUKTZeeskOnPnbd6u1EgCjsR6rteO9Z5mZX/Lii2GMGNFxoitdExcXxSuvTGPw4P8mP//71NRE\n09b3yhWJiQ9SWjrP54kUgNEYz7Fkp2PFxTcDUFMDAQFrMRrLcThi2hgvj+TkD2hpGUlh4fXEx6/F\nbDbR2tpCUFA9BoM/NTWB5OUt5eSneK7z4+jRyQD4+6eQmvo48+cP1z4/ERGRHqRkygd2725vH4+T\nhITfYDIFUVubDZz5gcxTfn4BQBlwapEJo7GSq692/5DbnrRs2bn8/Of7qK4+/WmSFaPx2Id2i6WW\n+vr2PxgnJR3guecCGDs2zYeRnr38/Px47bXvctNNeeza5V6Bk7Cw92lquhirtXv2sBmNXS/Y0Nx8\nARkZb5Kbe80Z9zIzt3Do0M3fvi4tvdij+Dpis6URETGS228/12dziIiISOdUzc/Lamrq+Oij1nbu\nGqivX0Rrazx1dR0vFXJXbe1IQkK2n3F9/PiDXHDBIJ/M6WtBQYFkZjafcT0z8yVyco4V8KiqmkN0\n9Lv4+xef0S4m5jBPPWXngguyfB7r2WzUqHReey2DYcN2udE7Dz+/WKqrTz9E2XeczkgMhq6W1g+g\nuHg4cXFnlu13Orvzqa+T664z9cknzSIiIv2Jkikve/LJPVRXt18tr75+EOXll5KW9iTg+WG9J4uL\n24nFsp76+rln3JvSPUXRfCY+/uQzjZxkZDxDTs4MTn64WlJyPXFxe0/pFxRUyhNPNDJnzpDuCfQs\nl54ey4oV8QwYsLfzxt+qJj39Qyoru3cfW2lpNgEBpV3u19JyDmFhBadcCwzcg80W4a3QOpWY+CW3\n3trdZeNFRETkdEqmvOiaa37K734XBXS8h8Fuj6alZShw5tMW99SRlfU6DQ1f0do69ptrTlJTV5Gc\n/D7QyOzZHe3h6v0iIw2kpX1AVtYrZGa+SG7uFZyoaHZCUFDdSa9s/OhHB1iwQMUmulNaWjiPP27C\n3/+oC63zycxcS17eTUD3npPkcARgsXR8jll7Dh48j/T0NQAEBOwkJMRKQcF0b4bXoWuvrSUqyruV\nBUVERKTrtGfKi1paEqiudu0JSGhoKaWlkzyaz2gsIj5+D1DB4cNXAWb8/LaRkfEyNpuVgoIrMBiq\nyc5+iOnTf+LRXD3NbN5BYeH5OByzOmxXU3OiAMecOVv41a8u9HVocpqwsBBmzRrK9OnP8P77N7Tb\nLjh4O1FRVeTkLOzG6E6wWuNITYXqand6p9DS8in+/sUkJ+dy6JD3i8m0Jywsl+99L6Pb5hMREZH2\n6cmUlzz//CbWrh3mcnurtcKj+WJi1mMy7aO4eDbFxddxvDpYTc0EcnOv4ciR64EwnM40Ro+e0OfP\noXnqqZuZP/9LAgOLAWe77VpanICDhIQD/OUvAzAa9RbvKc8/P48lS9Zz5nJWB4mJzxMebqWgwHdF\nGjrj53eYQ4fc30dXUnIZFss2Kiu796yyiy8uZuBA7x6rICIiIu7RJ00vWLduMw88sIX6etfPcCov\nnwIccGO2GszmLwgOPozN1t7hvKeaNq1vL/GDY9XiVq78DuvW1XLbbX9j6tSPSUjYgcXy0Cntamou\nJSFhE3ffXcqQIWcuA5TuExMTzr//PYUHHthJfPzx93ojKSnLKS6+lKKinn1qmJ6+G/CsGl59/Txi\nYsq9E5BLHCxY0L3LIUVERKR9SqY89Nxzm/jOdz7h8OE7u9SvsXEwSUm7uzxfevoWrNYA8vKWuNTe\nbM5n7tz+UcXO4XAwenQWv/zlNaxdO4nVq4MYMqSZwYO3ERp65JtWYUREbGXgwJYejVWOMRgM/PrX\nk1m7NpDs7D1kZr5OYeGNQM+W6Y+P38PRo945mqC8PJrU1LV09MTUW+Li9jJ79kCfzyMiIiKuUTLl\noa1b/Sgp+RFd3zxvICjItbLGfn5VJCa+THb227S2WoEBuLrdbcCAUtLT+8eSIJutlfXrdzN37sss\nWHA7Y8cOZfr0kYSHG7Dbj32QHT16Jxs33sJVV7n21E66xznnpPDKK+FER/sB7R8s3V2CgvKprZ3q\nlbGqqiZTUDCIsLDPvDJeR268sY7o6O6rGigiIiIdUzLlocOHO67c1xG7va7zRtiJiXmY4uJrOHBg\nLkeOXN6lOQYMcC+23shiMfPww/v59NPvs337LH78439QVBTMtm3n0tiYQkzMYZYtKyM6WlXOeqNR\no9LYtu0aXnxxH8nJ7ixx9R6rtaDzRl2SQlTUZ/gyUQwNzeH22/VUSkREpDdRMuWBhoYGdu488/BO\nV1mtKS60MhEaOtrtOdLT3U/2eqNf/eo8AgP3Ulx8FW+/vYudO1/55k4zP/nJEe6+e06PxicdMxgM\nLFo0ll//uobAwPwei8PfP9zrY+bmXktCwp8Au9fHBpg+vYz09O4tdiEiIiIdUzLlgQ8/3Ep1tfsb\n2Gtr0wkN3dhpu6qqUszmnW7NkZrq+30c3WnChGwuvfQ9xo17l6+++l8OHfo7AMOHv8W993pWal66\nz3e/O55Vq2qYOPFNoL7b5zebQ30wagAlJT8kIaHzf9Nd5+Dcc8t8MK6IiIh4QsmUB778soKWlnFu\n96+ryyI8vKbDNkFBu6ipGYvVOsKtOfz8rG71681effVHrFlzIVlZ3ycq6liSmZrahMHQv57C9Xez\nZo1g8+YruOOOVcyd+x8mT95OYOCRzjt6KDV1PeXlvqpweewgYLO51KujBgd/xbhxvkgARURExBNK\npjwweHACUVH7PBrjyJHJBAe/2e59g8FCa6uZ4+dIdVVMjMXNyHq38PBQPv30Cf75zyquvvqfXHON\nlj/1VX/96yJWr76Ujz8+l48/tjFwoHtPYV3V2rqPysqLfDZ+Xt4ywsLeAGq9Nqbd7sejjz7Fww//\nneJi7yZqIiIi4j4lUx5YuHAyY8bs92gMpzOM2Ni2y3hHRn6Jv/8mnE7390wFB7vdtdcLDg5k3ryZ\nvPzyTSxbNrunwxE3nXyg9PjxGcyceRho9clcQUGFWK2+L+JQXj6NyMgdeKtc+oAB/+CKKy7iqqsW\nkJioXxyIiIj0FkqmPLRwYQQGgytV+TrS+O2foqM/JjHxQ8BGYOAmqqtv8WjkpiYPQxPpZn/720Iu\nuugtn4wdF7ebigrXD9d232CqqgaSlHxQDdUAACAASURBVPQiWVkv4mlS5XA0c9ttN5GSooOoRURE\nehMlUx665ZbJJCZu9WiMkpJLSEl5jPDwVRgMZRQXDyEu7nmKim7wOL6Cgv5VgEL6P5PJxIoV0xk7\n9jm8exBuJRUV3VnEIY2iouvIz48DKjwYx8m99y71VlAiIiLiRUqmPPSb37xKVdUwj8Zobo6nsPB2\nwsJaKS+/CkihrGwZ7u6TOtmWLc0ejyHS3WJjI3jttel85ztvcv3120hIOOzxmMHBdRgMGR6P01UG\nQyxBQe4/vbZYvmTu3HQvRiQiIiLeclYnU62tnu/L+PRTI01NiV6IxkBVVTYpKS95YawTPv88kJaW\n/lfRT/q/9PRkXnhhHs8+O4HVq03MmrUBd/dSmc3lREa+RW3tDO8G6QKTyUhc3EdkZf0Hs7mky/0v\nvLBO+6RERER6qbM2mfr44138+c8rPR7n6quTCA72bJnfcfX1IwkI8PPKWMfl5Y3h97//0KtjinS3\ncePSefvt83nkkR2MGbOa4OCCLvS2kpDwBoWF3/dZfG1zEBb2AtHRR8jNvYnDhy8lLKzrP3OMxgYf\nxCYiIiLecFYmUw6Hg2ef3Y/RmOHxWEuWTGbcuE88D+obVmsQ4PDaeGDiH/84h0cf3eHFMUW6n7+/\nH3fdNZFduy5jyxYnzz+/jSFDPmu3fVjYV6SnryQl5THy86/vxkghKGgNaWlvUVu7kCNHTlSadDqj\ngK49KW5pceBwePNngoiIiHjLWZNM2e12Pv/8ILfd9iwXX/wBTz11KWD3ythXXZWEv//HQL3HY+Xn\nX0hk5MueB3WS0tIM7r13AGPHbuWpp3bgdKoohfRtw4encd11E3j33STmzfuI0/8tR0QcxGL5nLy8\nKyksvAcI8HFEZYSEvA4cAhzExxeTnz/vjHkrKq4lPf2DLo28YcOFvP22fhkiIiLSG3l3TVkvUlVV\nQ1hYKD//+T9paRnIunUmvvgiC5ttMWAkKOgI550X45W57rxzEVOm7OOOO35BWVkEeXmzsNkuAAxd\nGsdiOYTR2IjZ7P09Tq2tkezefR633FLP8uUfMWpUKCkpTux2uPHGLNLSvPN3IdKd0tNjefXVKfzy\nl+t46aVQcnImAC2YTGs5evTWboigmfj4f2M2Q0HB9ZjNucTGrqGsbEo77Y3U1YWTmbma2toMKiqG\nuzBHEK+9tpfLL5/gzcBFRETEC/pdMuV0Opk37+9UVISRkhLNyy+PA8ac0e7KK/czZcp0r807atRQ\nPv74zzgcTlasWM2mTc8SFpbM44+fQ11d5wUq4uO3UFXlT1NTPE1Ni7wW15lC2LLlIrZsOXHlxRff\nYdWq0Qwe7I1CGiLdy8/PxB/+MIOZM7dyyy07sdu3k5/vu39Dfn4HMBiOkpx8kObmJkpKlgEWAKzW\nYRw50nF1z8rKSVRWQnz804AryRRERIzwKGYRERHxjX6XTD300Lu89da1QGwHrZxkZHi+JO90JpMJ\nkwmWLJnPkiXHrvn5vc3vfz+3zfbR0TupqBgMhBAaWkZp6RVej8kVX389h7/9bROPPqpkSvquGTPO\n4803C1myJJ78/Aivjx8XtxyzORh//xCKioaSm3uBR+NVVg7Cz+8Ira3JnbbduLGFdes+Zdq00R7N\nKSIiIt7Vr/ZMOZ1OVqz4jI4TqRZuumkNP/7xzG6JKT4+us3rMTH7sNkcpKa+xcCBb1FdbemWeNrz\nr38N4P77N2g/lfRpw4en8Oc/ZxAT035hCnfExr5AZeXlFBYuIifnMlpaBng8ps12AWlpn7rUdseO\nSdxzz+cezykiIiLe1a+eTP32t4+xffslHba57LItPPXUDAyGru1ncteECXGEhn5AXd2sb69FRHxN\nQMDXlJfPp7b23G6JozMNDfH87/+G8/XXy3nppSUEBPRscifirosuGsMzz+zn00+38sUXzTz//Cgg\nkONL8boqLu5trNaxtLbGeTVOgyEPm+0gMTG7KC8f22l7h6PJq/OLiIiI5/rNk6m6ujqeeuoI0NEy\nmFK+//3gbkukACZOzOKBByqBum+uNOLn9x6FhfO7LQbXBfDmmzfxk598RHHx0Z4ORsRtc+YM4qc/\nPY9//etCtm4t4u23v2T8+G1dHic19TGqqsZTXT3Eq/EZDF8THZ1DQcHd2GxWUlJeZtCg/xAVta/d\nPkajnhqLiIj0Nv0mmXr33Q2Ul3dc6jwpaR0XXzyumyI64eabLyE6+rVvXpkxmyO7PQbXGXnkkVlM\nnfqYlvxJn+fv78eECedw6aVj+M9/BrFy5XYef3wLoaG5nfYNC1tNaeksbLZ4r8cVHf0F5eXjAaip\nmUhh4UL2778Uq7WIwMBPgNYz+qSnd98vgURERMQ1/SaZmjJlAhbLrA7bBATEd+tTqeMiIsIZMuSr\nb15ZaWryzvlW3uckNvYNIiMf5cCBW/jjHz/u6YBEvCY2NoKFC8/lttsmcsEFDwO2DttHRVVitWb7\nJBarNZqAgOqTrhxbcV1fPx273Ulc3JNkZ79JQsKTREdvIjBwFz/8YXvl1kVERKSn9JtkKjo6gvT0\nkg7b1NWlsmnT/m6K6FRXXplNZOQuEhLWUFV1fY/E0JnU1Dc5enQKVVX3AEn84hejWbDgGcrLq3o6\nNBGveuON/+Gvf91JVlZ7hSoc2O3er/h5XG3tVMLD21rSZ8RqnURZ2VwOHLiCkpJbqKjIID19J5Mm\nDfZZPCIiIuKefpNM+fn5ce65FbS1POa4o0eDsNlquy+ok9xzz40kJ79FUJCR3lj3w2L5ksrKGiDq\n22sORzhvvLGEuXP3UFnZM39vIr4QEGDhzjsnsnVrBldfvQZwnHI/KekZCgqu82kMYWF1HdxNOzka\nwsIG0draW59oi4iInL36TTIF8Nhj32Pw4F3t3g8KKmfQoLR27/uSwWBg7FgzDkdxj8zfmYSEzTQ0\n3NDGHQPbtk3hT3/yrNT08uXbOXy4zKMxRLwtJiac556bwp//vI377tvOXXdtZ/z4rZjNYYD3z6o6\nWWFhBP7+R1xqO3KkH2azv0/jERERka7rfY9IPODn50d0dPtFEwYPbiAuru1zn7rDT35yDU1NrxEc\n/DscjuH4+5dQVhZLY+NAamtH9lhcYWE7yMub02GbRx+NY+LEHcyfP77T8ZxOJ6+//ilhYf5MnTqY\n5ct3cuedgxkx4iDvvONPfHxvLsAhZxuz2Z9775347WuHw8Hq1WYOHNhMS0sLW7fu4p13ZmGzjfDq\nvHFxh8jLm+BS24QER+eNREREpNv1q2SqqqqGffuC270/apQJk8nUjRGdaujQAbz88n3fvnY4HFRX\n15GfX8kPf7ieXbsGUF2d0u1xhYY2YrVW0Nyc1G6bxsbB3HJLLh9+uI5f/WoMsbHhZ7Sx2+0sX76L\n555rZsOGCYCdmJgdVFQMwemMZPfuc5kxYze33volN900hpCQIB9+VSLuMRqNXHHFmG9fl5WN4Ac/\n+CMLFlzD7t2tbNpkYP364TidIW7PER//GkVFVwKujREUZHV7LhEREfEdg7Od+teFhYXMmDGDNWvW\nkJLS/R/w3bFixWquvz4Tu31YG3dbefrpT1m6tPMnKz1l8+YD3HhjM19/7d3fgLsiNHQvFksB5eUd\nP6ECGDPmI66/PpjzzgvhgguG8sIL77NvXyBr1/qzefNYOj8c1Ul29nvs2zerR5NbEXc4nU6+850N\nvPSS+9X1/P33Eh+fR2XlKBobO//5evHFb/Lee1e4PZ+IiIi4p7OcqF/tmbryytlcemlNm/dCQ/cy\nf37vroZ1/vnZ/PWv/gQHF3X73HV1wwkNre68IbB793R++MMJTJ6cwoABO1i6dBS/+90UNm8+n84T\nKQADBw5MZv369g8oFemtDAYD//3f2URHf+n2GDbbcAoL52CxfILFkttp+7lzE9yeS0RERHynXyVT\n/v7+NDUdbfNeRkYNoaHtLwHsLS6+eAj333+Y06uLueaAR3M3N4d3aV6nM4ycnHOx27v6Qc9JXNwO\n1qzJ7WI/kd5h0KBE3n7bwZw5H7g5Qjnp6ctxOtfT0tJZUZwmkpK0Z0pERKQ36lfJVEuLlaCgxjbv\n3XqrBaOxb3y5P/3pRKZM2dKFHmVkZCwnNXUX8fGvuT1vcfFFREc/73Z/V6WlvU9Z2WC2bInG4dCH\nROmbzjtvOA88kIzZvLXLfePi3iEv77vU1NxHZz+GBwzYy5VXnudmlCIiIuJLfSO7cJHFYqa1NfmM\n68OGbeCKKwb2QETu8ff344477IBrh4ampLxPbu5NHD06nrq6QA9mbqShwbfVDkND91FdbQYSWLt2\nPHPmrGH37n1UVOgcK+l7Jk48hyefbGbBgnWYTKcvW20kOHglZvMajv9bNpk+JybmIQIDEwAjTmdm\np3OMGePEYDB4PXYRERHxXL+p5meztfKXv/wfLS1gNI7G4Qhk0qSdpKXZufPOZNLSYno6xC6ZO3cc\nkyatYePGucTFvURIiAmj0UhLSyt+fq20tEBlZQrh4Qc49jnLQHNzFklJO2lszAPSuzynyWTHaHRl\nz5PrgoIKSUnZi8HQitXazJEjA7Bap39z15/335/F++8f4dlnv+L6610rEy3Sm9xww1RuuAE+//wg\nDz30MStXZlFXl0Rq6koKCuZjNDYQEbEViwUaGqIpL7+H8nLXkyODwebD6EVERMQT/SaZ8vf3Y+nS\na7j//lheeGEzDz64g3fe+S4hIb1/n1RbQkKCGD48n6Ki5zl8eCFlZad+HTExOzEYoiktnQpUfnPV\nQFHR1URGrqK29jB2+2S68i2222NJTKzg0CGvfRmEha1g//4fddIqudceZiziqpEjB/Kvfw1k2bIv\nuPPON9mz50YgEIcjlOpq9wtI7NtX4r0gRURExKv61TK/hIQ4DAYDixdfwKRJtj6bSB13xx2zKS93\nAmd+HeXl42hqygAMwMlL8wxUVc3Hbh9GevoqLJbNwCekpT2D2dx59byamgTAtap+rggMTGbAgJex\nWHI6bLdmTb7X5hTpSVOnDuOFF+Zz++3bCA3N9Xg8i8X986xERETEt/pVMnWyRx/9YU+H4LERIway\nbFkDRmOFG73jyMu7koSEQ0A6+fnXk5CwkaSkZ4iOXo3BcICYmOWEh288rV8A4M0DQmM5dOga4AsS\nErYBbRcIeeWVIZSWuvN1ivQ+w4cn8dhjU3nvPQexsTvcHicm5iMmTXJt76SIiIh0v36bTPUXd911\nBWPGrHWrr9F4lKqqKCAFMJKfv5SiohtobBxOfPzLlJcvIzKygZPLoR87ayrOG6EDUFycAXxNS8tl\nVFVZSEt7p812TU1DWbbsn9jtdq/NLdLTzj8/iw0bEhgxYpMbvZv57W8DefjhK70el4iIiHiHkqle\nbsCAZB58MJv4+MNd7hsbu5na2ktOumIGoKkpg5KSnwMmcnOnkpHxL/z93yckZCV2e513Av9Gc/NA\nkpM/A6ClZRRQTmRkW7+pN/D++0u5445VtLYqoZL+Y/DgFN5/fygLFqwFnC73i4nZysyZZ560LiIi\nIr1Hv02mDh3Kp6bGu4lBT5kyZSQpKV0/kNdgqKbzb3EAubnfxekcTn39JVitoURFvetWnO0JDj6x\n5+Po0SRsttA22zkccTzxxDxuu229V+cX6WkJCZG8+OIkhg5d7VL7IUNe5NFH7QwYoGRKRESkN+u3\nydQf//g3wsPb/tDe1xiNRkaNqulyv8BA1zeut7YmAcGUlFyM3T6Y1NSVXZ6vPXV1Zo4vJbRYzBgM\nHZVfN7F8+QSuvfYdDuz90msxiPQ0i8XMz34WDzR32M5kyuOKK3JYtOii7glMRERE3NZvk6knn/xT\nT4fgVUuXZvODH7zLyfubOuPn5+/WXDU1mTQ1ZRMSsvmU60ZjMW0vU7KRkvIcqalPEhi4m6ioV0lL\ne57IyBdJTl6F1br7pLEzCA3dSGbmy8TG7mwnAgPN296jceIE3vrtb3E6XV8aJdKbLV58Llde2XFB\nismTi/mf//lZN0UkIiIinug350z1d1OmjGHkyFr++c+vqakZ6lKfpqZAt+crLx9JWtq/sFqzsFrj\nAUhMfAV//3jq6pqpqFgKgNFYTXz88xQWfhdwEBPzO8rLf0NlpRGo/KYAxglO52CKigYDEBW1CpMp\nBbs9/pQ2c7IeZNXhRwAY8stf8k5FBZc+9JDbX4tIb2EwGJg2rYmVHTz4veSSfvs7LhERkX5H/2v3\nIRERYWRluV4m2WDY79F8TmcQYWF7GDjwFTIzn6O5eTS5udcSHm7+to3RWE5x8fkcK6keRHn57zjx\ntopqY9QTKivnkZp6+v6sFmZXvvTtKwtwwV//ysaHH/boaxHpLSZPzgDaPgbAZCpj7lzvVdMUERER\n31Iy1cfMnNnxfgsAk6mClJSXsVojPJzNSXn5TA4evJqcnOupqJgCgM3WyoABK4iL+4jk5PXAaLdn\ncDjMnLp00A+D/dRzriIcDswffeT2HCK9yciRA7nvvi8JCCg/496wYbkMH57R/UGJiIiIW5RM9SGt\nrXZKSr5o935o6NdERr5LQsJ/MBprKS291qP5zOa23x4FBUs4dGgRAQHF1NWV48nbqKEBTk2mjNT7\nn1k4I+nDD9n3wQduzyPSWxgMBv70p8lcccXHnH6I9fDhhp4JSkRERNyiZKoPcTgc5OREkJ7+HgMH\nvs7AgW+QkfE2MTEbyMh4gZYWK1VVEzAa/amungaYPJqv46p7kJ9/HWZzNZmZzxIYmOPWHE6nnZPf\nhhZLIcmmM7fypTQ2Yv/BDyj++mu35hHpbVasWMDMmStOuZaSomRKRESkL1Ey1YeYzf4sWRJHUVEM\nBw8u4ODB+eTmXkh5+TByc6/Dah0BROF0FlFbO9CjucLCcrFaKzttV1LyB3JylhAR8Tr+/sVdnic8\nPODbP0eG7+WSmPtZerTtKn/Dv/iCPY8/3uU5RHojg8HA44/P5KabniQk5Nj+xsREVa4UERHpS5RM\n9TFXXTUOs/nk87MiOFHowQFsp6JiqoeztBAVtY78/Btd7lFcfC8xMe0vQWyPw2H75k/VLAn7NW8c\nWdFh+4Z9+7o8h0hvNXBgGsuX38K1164DanA6u36enIiIiPQcJVN9TFRUOBkZtW3eS0h4DrM5lKam\nsR7NER//HsXFQ7rcz2rtein21tYaoJGFGb/goYJXO20/dssWfnnppTgcrp+3JdLbPfHEzcya9Qrb\nth3t6VBERESkC5RM9UFpaRAV9SbZ2W+QkfEiQUHvkJ39Bv7+KVitQwDP9l2Uls4lLOzLLvcLDt6P\n2XyAtg/2bZujZQCLE6/j6dy/u/RmTK+t5bYPP6To0KEuxyfSWxmNRh58cCo7drxMQ0NTT4cjIiIi\nLlIy1QdFREBkpJUDB+aTm7uIpqbxHDgwn4KCi7w0g4GAAGvnzU6Tn38jVquVtLRXARuuJFUpYaU8\nV7yK0E5bnpBss7Hzl7/EZu16jCK91ciR2axf/zhvvHH62WsiIiLSWymZ6mOqq2vJzW3Bai0hPn4H\nYMDpjPXyLEYaG6cREbHJjb7DyM+fS0TE86SmvtJp60STe1UAL3/pJTYtWECu9lBJP5KUlMDixQt6\nOgwRERFxkZKpPsbPz8ShQ3UUFHyfqioHqamv4+9/xOvzVFQMISSkiGNFLboqiOrqZTidHR8wbDId\n4fu5D7oVnxGY+p//UDt5Muvvu4/ays4rD4qIiIiIeNOZB/pIr1ZTU0dw8LFy4lbrBAoKICBgPWlp\nW7BaI6ioyKKxMdMrczmdoXh2IO9WYAG0s4gvO2kXMwraLqbhqpEVFfDgg2xbtYovhw8nuqSEwPR0\n6iZO5NL/9/+wBAR0PoiIiIiIiBuUTPUxn39+hJycSadca26eyvF6DFlZz3P4sHeSKU+feAUGpuB0\nbqK6enab94cFfOa1R6MTDhxgwoEDx15s3kzjihWs+cMfaL39dub+4heYTJ4dYCwiIiIicjot8+tD\nvvpqP/v2NdF+DlxEXV22l2az0dho9miEY9UFMzl9qaDJVEVa/JtcXP2WR+N3JAi4tLSUi//rv3h3\nzBg2PvKIz+YSERERkbOTnkz1EXa7naFDBxMV1XYC4u+/hdDQao4evdgr8wUE7KSsbJxHY+TlTScu\n7hUMhuE0NMz65qqDK1J/xau5j3ZLJh8AzN2zh7of/IDHc3O5/aGHumFWERERETkb6MlUH2EwGKip\nqSU8PKnN+zabPw5HHdDi8VzBwbsIDNwCDPVwpBRCQlJoaJiIwVANQEbi2/y7mxKpk4U6ncz/299Y\nf/PNbHql8yqDIiIiIiKd0ZOpPsJoNBIUFEhAQNsFG6Kj91BRcSUpKa9SUTERuz0Cq9W9kukNDWMJ\nCKgAyoEY94MGmpshLu5/cdhiGRptZlHN0106U8qbEltbSVy+nP8UFcHVV/dQFCIiIiLSXyiZ6kP8\n/PwwmULavFdRMZv09PfJy1tCUNA7xMfX4HQmUFg4rcvzJCevxs+vlIqKWZ037kRR0dUkxoSzsv5a\nJlVVezyeN8TNbrsghoiIiIhIV2iZXx/T3O7RTYlUVpqAShob51BQsIiysliSkt4BXC8/npa2moqK\nCPLyvuuFaI8pLr+Yp1Ov89p4nmr56queDkFERERE+gElU31IUVEZ9fVftnu/uTkUcH772modRlHR\n+aSmPg3YXJrDaKymuXlS5w07ERPzFdnZOwgO/gpwsKZ5EQcMFo/H9YYRTzzBmoUL2f/ZZ9jt9p4O\nR0RERET6KCVTfcjKlTk4HEPIyHiFtLR/YjDsws/vQ6AIsJKQcBAIO61XBAUFd5CSspyOEiqzuYyQ\nkG1YreEexZiYeJCf/OR99u6NZ//+8RQWJvHYY9upt8bx68RLPRrbW8IcDma8/jqWceN472c/6+lw\nRERERKSP0p6pXiwvr4y7795ETU0TCxbE8sQTMZSVjQYmAE7M5sNYrSmEhhYTEHCAgoKlgH8bI/lR\nWHgTqan/pqDgRuDEAbaJiZsxmw9htVopLr6UiIi1wOVuxRsZmc/LLxuYNOlEefaIiDBuv/08agqf\n4LJ/fOzWuL6Sbrezb/v2ng5DRERERPooJVO9WE1NAx98MIrGxkzWrTv9rgGrdQAAdXVx1NV1NpqZ\nwsKLiYn5F4GBrRQWXoPTGYDDcZC8vCXftqqvn4bFso+Wlq6XRb/oomImTTqvzXs/+d2t/M+7/2B4\nRUWXx/WVz+LjCbnssp4OQ0RERET6KCVTvdjIkZmEhu6gsTHTK+M5nWmUl98MQGrqYxgMgeTnLz2l\nTXX1RFJT/w18Rl1dMtXVk10ePyDA2eH9cx94gG3XXsuEFs/PwuqqWoOBPYMGEVNVxeCyMrYOHMiA\n9euJSWr73C4RERERkc5oz1Qv5nA4aG31zbfIYLCQn38jbb0FCgqWUlCwCKcznqyslzAaD7k0ZnZ2\n+8UcJo4YQW19PSZj97/lmoBdv/kNF371FXUPPcTbv/89fo88okRKRERERDyiJ1O9WH5+CTU18T4Y\n2U5tbefV/WpqBlFTM4iUlPdwOvdx5EhHS+KamT697eN4t69fj6mkhKKNG5nd1MT+mBhqLrwQw6BB\nYLXSuncvI9asIdjNr6Yzmy+5hOnfFJoYf13vKdEuIiIiIn2bkqlebPXqg7S2TvHByCaCgkKodvEM\n3cLC2YSG5hEdvYqKinlttpk5cyvnn39hm/dsy5fzdnk5O196iU3f+Q5j/vIXBiUkfHvf6XTy+Ztv\ncuTppxm3ejVhra0EAIauflltqDUaqZoxA4PBG6OJiIiIiJygZKoXW7XKN2cgBQXlUFmZ2qU+dXXp\nREbWEhS0kcbGM8+hGjSoBn//tt9O9qYmIgBrQgIz/vUvzJZTz5syGAyMmjePUfPmsW/LFg4WFOBv\ns1H36KMM27qVBGfHe7Ha4wDe+fGPufZHP3Krv4iIiIhIR7Rnqpf68MNPWb/+HJ+MHRHxNc3N2V3u\nV1U1goCAQLKyngfKT7k3fXr7+49Ms2djB/bHx5+RSJ1u6MSJXHj11Uy47jomr19P0969fPT977Mn\nMbHL8X5lsTD5ttu63E9ERERExBVKpnqpn/3sC2w2X+yXgvLycYSG7narb2XlOBobB377OinpU+68\n8z9MmJDRbp+hl1/O2v/6L25ZvbpLc5nNZjLPOYfpjz5K4o4dbPzpTzkYHe1S37VRUXy+bBlJaWld\nmlNERERExFVa5tcLPfHEx+zceYXPxk9L28rBg+6fr2S1BmGxFDJx4gHuvTeCK664tMP2kfHxzPrV\nr9yeDyAmKYlJv/89G0aOxHHffQwqLGyz3VE/P/YGBZGwZg0XjR7t0ZwiIiIiIh1RMtXLVFfX8+ST\nfjgcbVfGc58DgLS0t2hu7rySX0caGxOYP/9tVqxY5oW4umbyokWsLS1l4D33nPJYNTc2lg+Tkwmf\nOpWkiy4iY+DAdscQEREREfEGJVO9zJ13bmLHjou9Pm5a2nKs1iby828AIjwYqYlf/GIPP//5Mi9F\n1nXDFy5k5b//TWRZGaXnnUfI0KFEDhzI1fPns3/PHs6d7PpBwyIiIiIi7lIy1Yt8/nkeH3zgmycq\nVquTkpK73Ojp5ESR8ioWLPiEn/6042V9vhaXmsqVO3bQ1NhIcEjIKfeUSImIiIhId1Ey1Us0NTVz\n220fUVq6zAejt1JfH9ilHuecs4epUxtJSanEZAqhpeUIl1wympSUCzAae75uidFoPCOREhERERHp\nTkqmeoktWz5l8+a5Phnbz68ei6WV+nrX2kdHH+DFFyMYOXKET+IREREREekPev4RgwCwe3cFEOmT\nsRMT11NRcaPL7W+5pYKRI7t2qK+IiIiIyNlGyVQvkZcXhC8eFEZHf0ZdXftnM/n55RMQkHPSlWrm\nz/dNUiciIiIi0p9omV8vYbH4Zv9PUNBBAgICiYh4h9zciwETfn55JCSsAvypqBhMcHArQUGNVFYO\nIzr6C8aPn+iTWERERERE+hMle1riNQAACLRJREFUU71Aa2sru3fnAed6bczw8FxiYrZRWppFff14\noJGMjGex2+OpqqqjsPBEZb+mJggIuJbwcD+io8/BZLrQa3GIiIiIiPRXSqZ6gb17D7Bhg8OLIzoJ\nDl7FoUN3n3QtiNzcZe32aG5+ieZmGDFihxfjEBERERHpv5RM9QIbN+Zht8/wylh+fodITd1MTs5S\nt/oHBrZ4JQ4RERERkf5OyVQvcORIEykpH2I0GrDZyigtvQarNa5LY4SHbyYsrJTCwiRychbh7rc2\nLMzsVj8RERERkbONkqleYOdOK7m51377OiPjDXJz57vcPy5uO+XlEYSE7MfpdL1fW0JDDR71FxER\nERE5W6g0eg/bseMLNm0afMq10tIIIiJc37tksZTjcCTR3JzucTzh4d7cuyUiIiIi0n8pmephOTml\nNDQMOuVaU9M0GhrMhId/7tIYdrsNCMffv9HjeMLC9JYQEREREXGFPjn3sMrKeuDMfUo220hCQwuA\nSozGXPz9S9sZoZ6mpmYATKZGYmPXn9EiIWE3ISGHXIrnWGImIiIiIiKdUTLVww4fPgBUtXmvtDQZ\ni2UjDkcpiYkbCA4+gslUjMWyj4iIPZhMFSQmPkdV1VUAHDlyFdXVKaSkrDlplHrM5k+Jjd3iUjwV\nFUc9/IpERERERM4OKkDRw2pqyoEiIPaMezbbaGA0APn555Gc/BCNjUOoqhqC0VhLauoKcnO/d1qf\nAdTWFpOevpLKynBCQ3PJz7+euLjXgFY6+5ZHRSV55esSEREREenvlEz1sOHDBwIHgVGdtj1y5Aff\n/rmpCWAv4AROrcBXWzuJ2lqAeurqZgJQVraQuLhNlJVN6XCO6mpnF6IXERERETl7aZlfDwsPj8Df\nv86tvrm5c4iM7Gj5XshJfw7AYvmKY8lX+z75pJqysgq34hEREREROZsomephl1wyFYdjnZu9IzCZ\nmlxuXVBwGSEhHVcI/Pzz0ezYsdfNeEREREREzh5KpnpYbGwM2dn1gDtlzUsIDKztYp8TT6YSEzeR\nnf0mERFffXtt8OCvmTHjfDdiERERERE5uyiZ6gXefPNBBg/e7kbPJCwWu+utkz6kvv743iwbdXWF\nHDhwBdHRnwEQFvYVs2cfwGI5s1S7iIiIiIicqk8WoHjnnd3U1FiJjoaYmBjGjBnQ0yF5JDs7g5SU\nXXz9ddf6RURspLY2y+X2dnskWVmv0tzcgJ+fiYKCSQCUlGSRmfkmMTF7eeSRn3UtCBERERGRs1Sf\nTKYeeKCAHTvmAE1kZh5gz54mgoMDezosj4weXc6aNQ668rAwPLyIvLxrXG5fWnr5Sa/qiIv7mNbW\nLWRlWWhsfIlnn/2j6wGLiIiIiJzl+uQyv5EjowB/IIycnBG8//4XPR2Sx4KCmgkJWd2lPjZbHeDo\n4kw1BAfv5Oabn6Og4GKOHr2W7dsX8sUXLzF4cGYXxxIREREROXv1ySdTiYlGIiP3MH16HWPG2Jk3\n78KeDsljv/zlHWzY8Brr1rnep6joO8TEfEJ5+WSX2sfE7OGee0pZtGgQGRm3YjKZ3AtWRERERET6\nZjI1a1Ywl11mZuLEC3o6FK8xmYyUlW0DXF+2B0GEhuZTXt5+C4OhjszMZ8jOjuPxxyeRmTnC01BF\nRERERIQ+mkxNnTqq80Z9jMFg4Oqrh/LrX38OjHS5X21t2ys1TaZyrr76CxYvjmDu3DswGAxeilRE\nRERERKCP7pnqjwwGA/fd9x1GjdrUpX7+/vVA6xnXU1Ke5rnnJnHZZaOUSImIiIiI+ICSqV4kODiI\n8eMHdalPSclSUlOfBBpOutrM6NGDtSdKRERERMSHlEz1MtnZJqCuCz3MFBRcTmjovm+vZGV9zGuv\nzfV6bCIiIiIicoKSqV7mvvsmM3Dgb2hr6V57QkI2UVd3/ImWk8mTKzEa9a0VEREREfElfeLuZZqb\nW3jjjZtZvHgNYHWpT0CAkePfyuDgAmbNCvddgCIiIiIiAiiZ6nWCggIZNmwQTz89kxtueAewf3vP\nz6+U8PBdp1wDaGgwkJr6CdDKrbceYPHiOd0as4iIiIjI2ahPlkY/G/j5mfi//5tNefkqDh+uYe7c\naKZPT2b48GQ++WQrr73WzMqVkwAzTU1X4uf3AgkJu/ntb/vP2VsiIiIiIr2ZkqleLDAwgNWrF/D6\n6++ycOGJp03p6QksWuRg8eJXWbHiSsCE1VrH5MmNBAUF9lzAIiIiIiJnES3z6+UMBsMpidRxRqOR\nZ55ZyIwZHwMQEtLE5Zf7d3d4IiIiIiJnLT2Z6sP8/f34618zeeihNYwfP5olS7TET0RERESkuyiZ\n6uPOOSeDJ5/M6OkwRERERETOOlrmJyIiIiIi4gYlUyIiIiIiIm5QMuUF+/Yd5u673+W3v/1nT4ci\nIiIiIiLdRMmUF5SUlPPSSytpaorv6VBERERERKSbqACFF0yfPoFNmxLIykrr6VBERERERKSb6MmU\nlyiREhERERE5uyiZEhERERERcYOSKRERERERETcomRIREREREXGDkikRERERERE3KJkSERERERFx\ng5IpERERERERNyiZEhERERERcYOSKRERERERETcomRIREREREXGDkikRERERERE3KJkSERERERFx\ng5IpERERERERNyiZEhERERERcYOSKRERERERETcomRIREREREXGDkikRERERERE3KJkSERERERFx\ng5IpERERERERNyiZEhERERERcYOSKRERERERETcomRIREREREXGDkikRERERERE3+LV3w263A1BS\nUtJtwYiIiIiIiPQWx3Oh47nR6dpNpo4ePQrA4sWLfRCWiIiIiIhI33D06FHS09PPuG5wOp3Otjo0\nNzezd+9eYmNjMZlMPg9QRERERESkN7Hb7Rw9epThw4cTEBBwxv12kykREZH/384dEgAAADAI69/6\nCW7QWwsMAMBnQAEAABCIKQAAgEBMAQAABGIKAAAgGJ+sdu1DYPn4AAAAAElFTkSuQmCC\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "collapsed": true
      },
      "cell_type": "markdown",
      "source": "このように北海道の人口の偏りを可視化することができました。今回は単純に人口の多い市区町村から順に塗っていますが、札幌市の隣接地域から順番に塗っていくと冒頭のような図ができるのではないかと思います。"
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": true
      },
      "cell_type": "code",
      "source": "",
      "execution_count": null,
      "outputs": []
    }
  ],
  "metadata": {
    "language_info": {
      "pygments_lexer": "ipython3",
      "codemirror_mode": {
        "version": 3,
        "name": "ipython"
      },
      "nbconvert_exporter": "python",
      "file_extension": ".py",
      "mimetype": "text/x-python",
      "name": "python",
      "version": "3.5.2"
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3",
      "language": "python"
    },
    "gist": {
      "id": "",
      "data": {
        "description": "matplotlib_hokkaido.ipynb",
        "public": true
      }
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}