andrew-blake/PyDataRangeQueries.ipynb

## PyDataRangeQueries.ipynb
{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Experiments with Spatial Radius Queries\n",
    "\n",
    "This notebook gives an overview of what we can easily implement to tackle the problem of "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import pygeohash as pgh\n",
    "from collections import defaultdict\n",
    "import proximitypyhash\n",
    "import numpy as np\n",
    "import random\n",
    "import time\n",
    "from collections import defaultdict\n",
    "from sklearn.neighbors import BallTree\n",
    "from sklearn.neighbors import DistanceMetric\n",
    "import folium\n",
    "\n",
    "# Constants\n",
    "RADIANT_TO_KM_CONSTANT = 6367\n",
    "radius = 0.1"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## The Problem"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "n_samples_min = int(1e3)\n",
    "n_samples_max = int(1e4)\n",
    "\n",
    "lat_longs = np.array([[random.uniform(50.5, 50.51),random.uniform(10, 10.01) ] for i in range(n_samples_max)])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "map_ = folium.Map(location=[50.504, 10.005], tiles='OpenStreetMap',\n",
    "                   zoom_start=17)\n",
    "\n",
    "for lat_long in lat_longs[0:1000]:\n",
    "    folium.RegularPolygonMarker(location=lat_long,\n",
    "                           fill_color='#132b5e',\n",
    "                            number_of_sides=4,\n",
    "                            radius=1).add_to(map_)\n",
    "\n",
    "folium.Marker(location=[50.504, 10.005]).add_to(map_)\n",
    "folium.features.Circle(location=[50.504, 10.005], radius=100,  color='#3186cc',fill_color='#3186cc').add_to(map_)\n",
    "map_.save('map.html')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The Problem is illustrated above we simple want to have all geopoints that are in the radius of a point"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Geohash based implementation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import pygeohash as pgh\n",
    "from collections import defaultdict\n",
    "import proximitypyhash\n",
    "import numpy as np\n",
    "import random\n",
    "import time\n",
    "from collections import defaultdict\n",
    "from sklearn.neighbors import BallTree\n",
    "from sklearn.neighbors import DistanceMetric\n",
    "RADIANT_TO_KM_CONSTANT = 6367"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Small initial dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "radius = 0.1"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Geohash-based indexer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "class GeoHashIndexer:\n",
    "    \n",
    "    def __init__(self,precision,lat_longs):\n",
    "        self.index = defaultdict(list)\n",
    "        # build the index\n",
    "        for lat_long in lat_longs:\n",
    "            lat = lat_long[0]\n",
    "            long = lat_long[1]\n",
    "            geo_hash = pgh.encode(lat, long, precision=precision )\n",
    "            lat_long_radian = np.radians(np.array(lat_long))\n",
    "            self.index[geo_hash].append(lat_long_radian)\n",
    "        self.precision = precision\n",
    "        self.haversine =DistanceMetric.get_metric('haversine')\n",
    "        self.lat_longs = lat_longs\n",
    "    \n",
    "    def query_radius(self,query,radius):\n",
    "        candidate_geohashes = proximitypyhash.get_geohash_radius_approximation(latitude=query[0],longitude=query[1],radius=radius,precision=self.precision,georaptor_flag=False)\n",
    "        candidate_points = []\n",
    "        for geohash in candidate_geohashes:\n",
    "            if geohash in self.index.keys():\n",
    "                candidate_points.extend(self.index[geohash])\n",
    "        \n",
    "        if not candidate_points:\n",
    "            return []\n",
    "        \n",
    "        query = np.radians(np.array([query]))\n",
    "        result=self.haversine.pairwise(candidate_points,query)\n",
    "        # convert radiant radius to meters\n",
    "        radius_km = radius/1e3\n",
    "        radius_radiant = radius_km / RADIANT_TO_KM_CONSTANT\n",
    "        result = result[result<radius_radiant]\n",
    "        return result*RADIANT_TO_KM_CONSTANT*1000 # get meters again"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "## geo hash indexer Usage\n",
    "geo_hash_indexer = GeoHashIndexer(5,lat_longs)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "5.75 ms ± 445 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n"
     ]
    }
   ],
   "source": [
    "%timeit geo_hash_indexer.query_radius(lat_longs[10],radius=500)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Brute Force Approach implementation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "class BruteForce:\n",
    "    def __init__(self,lat_longs):\n",
    "        self.haversine =DistanceMetric.get_metric('haversine')\n",
    "        self.lat_longs = np.radians(lat_longs)\n",
    "        \n",
    "    def query_radius(self,query,radius):\n",
    "        radius_km = radius/1e3\n",
    "        radius_radiant = radius_km / RADIANT_TO_KM_CONSTANT\n",
    "        query = np.radians(np.array([query]))\n",
    "        result=self.haversine.pairwise(self.lat_longs,query)\n",
    "        result =result[result<radius_radiant]\n",
    "        return result*RADIANT_TO_KM_CONSTANT*1000"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "brute_force_search = BruteForce(lat_longs)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "5013"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(brute_force_search.query_radius(lat_longs[10],radius=500))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Ball-Tree-based indexer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "class BallTreeIndex:\n",
    "    def __init__(self,lat_longs):\n",
    "        self.lat_longs = np.radians(lat_longs)\n",
    "        self.ball_tree_index =BallTree(self.lat_longs, metric='haversine')\n",
    "        \n",
    "    def query_radius(self,query,radius):\n",
    "        radius_km = radius/1e3\n",
    "        radius_radiant = radius_km / RADIANT_TO_KM_CONSTANT \n",
    "        query = np.radians(np.array([query]))\n",
    "        indices = self.ball_tree_index.query_radius(query,\n",
    "                                                    r=radius_radiant)     \n",
    "        return indices[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "ball_tree_index = BallTreeIndex(lat_longs)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<MemoryView of 'array' at 0x7f7ce3f8f048>"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ball_tree_index.ball_tree_index.node_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "5013"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(ball_tree_index.query_radius(lat_longs[10],radius=500))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Quick Test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "ball_tree_index = BallTreeIndex(lat_longs)\n",
    "brute_force_search = BruteForce(lat_longs)\n",
    "geo_hash_indexer = GeoHashIndexer(5,lat_longs)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(ball_tree_index.query_radius(lat_longs[10],radius=500)) ==  len(brute_force_search.query_radius(lat_longs[10],radius=500)) == len(geo_hash_indexer.query_radius(lat_longs[10],radius=500)) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(ball_tree_index.query_radius(lat_longs[10],radius=300)) ==  len(brute_force_search.query_radius(lat_longs[10],radius=300)) == len(geo_hash_indexer.query_radius(lat_longs[10],radius=300)) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(ball_tree_index.query_radius(lat_longs[10],radius=1000)) ==  len(brute_force_search.query_radius(lat_longs[10],radius=1000)) == len(geo_hash_indexer.query_radius(lat_longs[10],radius=1000)) "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Okay they all seem to return the same stuff, time for some benchmarking"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "n_samples_min = int(1e3)\n",
    "n_samples_max = int(5e6)\n",
    "\n",
    "radius = 0.1\n",
    "lat_longs = np.array([[random.uniform(50, 52),random.uniform(8, 15) ] for i in range(n_samples_max)])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[   1000    2576    6637   17099   44054  113496  292401  753315 1940766\n",
      " 4999999]\n"
     ]
    }
   ],
   "source": [
    "n_steps = 10\n",
    "n_iter = 5\n",
    "\n",
    "# Initialize the range of `n_samples`\n",
    "n_samples_values = np.logspace(np.log10(n_samples_min),\n",
    "                               np.log10(n_samples_max),\n",
    "                               n_steps).astype(np.int)\n",
    "\n",
    "lat_longs_radians = np.radians(lat_longs)\n",
    "\n",
    "\n",
    "rng = np.random.RandomState(42)\n",
    "\n",
    "times_ball_tree = defaultdict(list)\n",
    "times_bf = defaultdict(list)\n",
    "times_geohash = defaultdict(list)\n",
    "train_times_ball_tree = {}\n",
    "train_times_geohash = {}\n",
    "print(n_samples_values)\n",
    "for n in n_samples_values:\n",
    "    sub_set = lat_longs[:n]\n",
    "    \n",
    "    # Train Ball Tree\n",
    "    start = time.perf_counter()\n",
    "    ball_tree_index =BallTreeIndex(sub_set)\n",
    "    end = time.perf_counter()\n",
    "    duration = end - start\n",
    "    train_times_ball_tree[n]=duration\n",
    "    print('Done Training Ball Tree')\n",
    "    # Train Geohash based indexer\n",
    "    start = time.perf_counter()\n",
    "    geohash_index = GeoHashIndexer(5,sub_set)\n",
    "    end = time.perf_counter()\n",
    "    duration = end - start\n",
    "    train_times_geohash[n]=duration\n",
    "    print('Done Training Geohash ')\n",
    "    \n",
    "    # create BruteFroce Object (no training or indexing time)\n",
    "    brute_force_search = BruteForce(sub_set)\n",
    "    print('Done creating Brute Force')\n",
    "    # now perform the queryies\n",
    "    for i in range(n_iter):\n",
    "        # Get the query\n",
    "        query = lat_longs[[rng.randint(0, n_samples_max)]]\n",
    "        query=query[0]\n",
    "        start = time.perf_counter()\n",
    "        ball_tree_index.query_radius(query,radius)\n",
    "        end = time.perf_counter()\n",
    "        duration = (end - start)*1e3\n",
    "        print('Ball Tree {}'.format(duration))\n",
    "        times_ball_tree[n].append(duration)\n",
    "        \n",
    "        # Brute Force\n",
    "        start = time.perf_counter()\n",
    "        brute_force_search.query_radius(query, radius)\n",
    "        end = time.perf_counter()\n",
    "        duration = (end - start)*1e3\n",
    "        print('Brute Force {}'.format(duration))\n",
    "        times_bf[n].append(duration)\n",
    "        \n",
    "        # Geohash\n",
    "        start = time.perf_counter()\n",
    "        geohash_index.query_radius(query, radius)\n",
    "        end = time.perf_counter()\n",
    "        duration = (end - start)*1e3\n",
    "        print('Geohash {}'.format(duration))\n",
    "        times_geohash[n].append(duration)\n",
    "    print('Done with {}'.format(n))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Metrics intended for two-dimensional vector spaces: Note that the haversine distance metric requires data in the form of [latitude, longitude] and both inputs and outputs are in units of radians."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "run_times_agg_ball_tree = pd.DataFrame.from_dict(times_ball_tree).mean()\n",
    "run_times_agg_bf = pd.DataFrame.from_dict(times_bf).mean()\n",
    "run_times_agg_geohash = pd.DataFrame.from_dict(times_geohash).mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "plot_df =pd.DataFrame({'BallTree(metric=haversine,radius=100m)':run_times_agg_ball_tree,\n",
    "                       'BruteForce(metric=haversine,radius=100m)':run_times_agg_bf,\n",
    "                       'GeoHash(precision=5,radius=100m)':run_times_agg_geohash})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>BallTree(metric=haversine,radius=100m)</th>\n",
       "      <th>BruteForce(metric=haversine,radius=100m)</th>\n",
       "      <th>GeoHash(precision=5,radius=100m)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1000</th>\n",
       "      <td>0.219437</td>\n",
       "      <td>0.250962</td>\n",
       "      <td>0.145079</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2576</th>\n",
       "      <td>0.269482</td>\n",
       "      <td>0.408587</td>\n",
       "      <td>0.174466</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6637</th>\n",
       "      <td>0.211366</td>\n",
       "      <td>1.078405</td>\n",
       "      <td>0.191448</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17099</th>\n",
       "      <td>0.418656</td>\n",
       "      <td>4.207179</td>\n",
       "      <td>0.599496</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>44054</th>\n",
       "      <td>0.969226</td>\n",
       "      <td>21.542674</td>\n",
       "      <td>1.509088</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>113496</th>\n",
       "      <td>3.171023</td>\n",
       "      <td>33.763789</td>\n",
       "      <td>2.687839</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>292401</th>\n",
       "      <td>1.904687</td>\n",
       "      <td>64.033281</td>\n",
       "      <td>1.665992</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>753315</th>\n",
       "      <td>3.090432</td>\n",
       "      <td>124.185637</td>\n",
       "      <td>1.269571</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1940766</th>\n",
       "      <td>6.353265</td>\n",
       "      <td>263.001137</td>\n",
       "      <td>2.200996</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4999999</th>\n",
       "      <td>7.232197</td>\n",
       "      <td>611.874671</td>\n",
       "      <td>3.364019</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         BallTree(metric=haversine,radius=100m)  \\\n",
       "1000                                   0.219437   \n",
       "2576                                   0.269482   \n",
       "6637                                   0.211366   \n",
       "17099                                  0.418656   \n",
       "44054                                  0.969226   \n",
       "113496                                 3.171023   \n",
       "292401                                 1.904687   \n",
       "753315                                 3.090432   \n",
       "1940766                                6.353265   \n",
       "4999999                                7.232197   \n",
       "\n",
       "         BruteForce(metric=haversine,radius=100m)  \\\n",
       "1000                                     0.250962   \n",
       "2576                                     0.408587   \n",
       "6637                                     1.078405   \n",
       "17099                                    4.207179   \n",
       "44054                                   21.542674   \n",
       "113496                                  33.763789   \n",
       "292401                                  64.033281   \n",
       "753315                                 124.185637   \n",
       "1940766                                263.001137   \n",
       "4999999                                611.874671   \n",
       "\n",
       "         GeoHash(precision=5,radius=100m)  \n",
       "1000                             0.145079  \n",
       "2576                             0.174466  \n",
       "6637                             0.191448  \n",
       "17099                            0.599496  \n",
       "44054                            1.509088  \n",
       "113496                           2.687839  \n",
       "292401                           1.665992  \n",
       "753315                           1.269571  \n",
       "1940766                          2.200996  \n",
       "4999999                          3.364019  "
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "plot_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAuYAAAGKCAYAAABAR4TvAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAIABJREFUeJzs3XdYFMf/wPH30ZsNG6ixG2tUULABKtLBji1KFHvBgiV2\nY/mhxqgolth71Nh7wx5jjNFETCwRsNJtKB3u2N8ffFk5OIpE0Zh5PQ/Pw93sznx2dm5vbnZ2VyFJ\nkoQgCIIgCIIgCB+U1ocOQBAEQRAEQRAE0TEXBEEQBEEQhI+C6JgLgiAIgiAIwkdAdMwFQRAEQRAE\n4SMgOuaCIAiCIAiC8BEQHXNBEARBEARB+AiIjrnwn3fo0CEGDBiQ73LffPMNK1euLIKI1G3fvp2W\nLVtiaWnJq1evirz8TB4eHvz2228FWrZOnTo8efLkvcWSNf8PtV/eN3t7e3755ZcPHYasoJ8TQcjO\ny8uL3bt3A7Bv3z6+/PLLDxzRx0fUi5BJ50MHIHw6Dh8+zMaNG3nw4AHGxsbUrVuXoUOH0qRJkw8d\nWp46dOhAhw4d8l1u1qxZRRCNurS0NL799lt2797N559/XmTlTpo0CTMzM8aMGSO/d+TIkSIr/218\niP3yqQsLC8PBwYHbt2+jpZUxflPQz8n7NGnSJI4cOYKuri4KhYKqVasyefJkrKysCp2nl5cXHTp0\noFu3boVePygoCG1tbfm9TZs20ahRo0LH9LFZtmwZq1atQk9PDwBzc3PGjBmDk5NTgfNQKBR5pl+7\ndo1BgwbJr5OSkjA0NJTXPXbsGGZmZoWIPm+ZbT2zLCMjI5ycnJg6dSo6OqKLJBQ90eqEd2Ljxo2s\nXbuW2bNnY2Njg66uLj/99BNnz579qDvmKpVK7Qv1Y/Ps2TNSUlKoUaPGhw7lvch8vll+X9qfIqVS\n+d6++N9Vu/7Ynj+nUCgYNGgQo0ePBmD37t34+Phw5coVjW2oqD7fM2bMwNPTs9Drv8+28C4oFArc\n3d1ZsGABAJcuXWLEiBE0bdoUU1PTd1JG06ZN+eOPPwAIDw+nXbt2XL9+Xf5hmNX72K+ZZb148YIB\nAwbwww8/0Ldv33dahiAUhJjKIvxjcXFxBAQE8M033+Dg4ICBgQHa2tq0adOGCRMmAJCamoqfnx+2\ntrbY2toyd+5cUlNTAfj111+xs7Nj3bp1tGjRAhsbG06fPs2FCxdwdnamWbNmrFmzRi5v2bJljBo1\nCl9fXywtLenSpQt3796V09esWYOjoyOWlpa4u7tz+vRpOW3fvn307NmTefPm0axZM5YtW6Z2ClGS\nJObOnUvLli1p0qQJ7du3JyQkBMgYrVuyZImc165du3BycqJZs2YMGzaMmJgYOa1OnTrs3LkTZ2dn\nrKysmD17dq71l1vdPHjwADc3NyDjS6tfv3451k1JSWH8+PE0a9YMKysrPD09efHiBZAxkrdo0SK6\ndetGkyZNGD58uNpUmFGjRmFjY0PTpk3p06ePvJ0//vgjR44cYd26dVhYWDBs2DBAfWrFzZs36dGj\nB1ZWVtjY2DBnzhzS0tJy3casvLy88Pf3p2fPnjRu3JgnT56wd+9e3NzcsLS0xMHBgR9//FFtnXXr\n1mFjY4OdnR179uxRS8u6XzSdDs467eXChQu4u7tjaWmJnZ0dGzZs0Bjjo0eP6NOnD02bNqV58+b4\n+vrKaaGhoXh7e9OsWTNcXFw4fvy4nHb+/Hk6depEkyZNaNOmDcuXL5fTwsLCqFOnDnv27KFt27Z4\ne3sDGe0oc9vd3d25c+eOvM6dO3fo0KEDTZs2xdfXV/7MZKepXS9btkz+/GUtPz09Xd4PS5cupVev\nXlhaWjJgwABevnwJQJ8+fYCMdmdpacmNGzdy1G2dOnXYvn07Tk5OWFpasnTpUh4/fkyPHj3keLO2\niXPnztGxY0esrKzo2bMnf//9t5y2Zs0a7OzssLS0xMXFpcBTeDw8PHj16hXPnj1763pQqVT4+/tz\n/fp15syZg4WFBf/3f/+X7z4uKEmSWLlyJfb29rRs2ZKJEycSHx+vFkN+beH27dsAREdHM3LkSFq0\naEG7du3YunWrxjKDgoKwsbFR+0EVGBgon+m4efMmXbp0oUmTJrRq1Yr58+cXeFuy5mljY4OxsTGP\nHz8G4PXr1wwZMoQWLVpgbW3N0KFDiY6OfssaUy8vq8xj/oQJE2jSpAn79+8nLi6OKVOmyMeFJUuW\nyG0bYM+ePbi5uWFtbc2AAQOIiIgoUNmmpqa0bNmS0NBQ+b28vlMKe6x4+fKlfEa5W7ducl0KApIg\n/EMXLlyQ6tWrJ6lUqlyXWbJkidSjRw/p+fPn0vPnz6UePXpIS5YskSRJkq5cuSLVq1dPWrFihaRU\nKqVdu3ZJ1tbW0tixY6WEhAQpODhYatiwoRQWFiZJkiQFBARI9evXl06ePCkplUpp/fr1kr29vaRU\nKiVJkqTjx49LMTExkiRJ0tGjR6XGjRtLT58+lSRJkvbu3SvVq1dP2rZtm6RSqaTk5GRp7969Uq9e\nvSRJkqSLFy9KnTt3luLi4iRJkqTQ0FA5r0mTJskxX758WWrWrJl0+/ZtKSUlRZozZ47Uu3dveXtr\n164tDRkyRIqLi5MiIiKk5s2bSxcvXnzrugkLC5Nq166da93u2LFDGjJkiJScnCylp6dLt27dkmPv\n06ePZGtrKwUHB0uJiYnSyJEjpfHjx8vr7t27V0pISJBSU1MlPz8/qWPHjnJa1m3N1LZtW+ny5cuS\nJEnSX3/9JQUFBUkqlUoKCwuTXF1dpU2bNqlt/+PHjzXG3KdPH6lt27ZSSEiIpFKppLS0NOn8+fPy\n8levXpUaNWok3bp1S5KkjPbVsmVLeTvGjh2rln/WWLPuS02xtGrVSrp27ZokSZL0+vVruYzsfH19\npVWrVkmSJEkpKSnS9evXJUmSpISEBMnOzk7at2+fpFKppNu3b0vNmjWTQkJCJEmSpF9//VW6d++e\nJEmSdPfuXally5ZSYGCgJEmS9OTJE6l27drSxIkTpaSkJCk5OVk6duyYZGtrK/3555+SJEnSo0eP\npPDwcLm+u3XrJsXExEixsbGSq6urtGPHDo3xamrXy5YtU9vfmeVntqU+ffpIjo6O0sOHD6Xk5GSp\nT58+0sKFCyVJ0tzustdt7dq1peHDh0vx8fFScHCwVL9+fcnLy0t68uSJFBcXJ7m5uUn79++XJEmS\nbt26JbVo0UIKCgqS0tPTpf3790tt27aVUlNTpdDQUKl169by5yw8PDzXtjNp0iTJ399fkiRJUiqV\n0vbt2yUHBwcpPT39H9XD7t275fT89nF2ffr0kXbt2pXj/d27d0uOjo7SkydPpISEBMnHx0eaMGGC\nWgwFaQsqlUrq3LmztGLFCiktLU16/Pix1K5dO+mnn37SGI+Dg4P0888/y69HjhwprVmzRpIkSere\nvbt08OBBSZIkKTExUbpx44bGPLILCAiQ6zA9PV06e/asZGVlJR9rXr58KZ06dUpKTk6W4uPjpVGj\nRknDhw9Xq6PMOtb0Gc0u+z7KPOafPn1akiRJSk5OloYPHy7NmDFDSkpKkp4/fy55enpKO3fulCRJ\nkgIDAyVHR0cpNDRUUqlU0sqVK6UePXrkWVbm90dUVJTUoUMHae/evfIyeX2nFPZYMWbMGGnMmDFS\nUlKSdO/ePcnW1lb68ssv898ZwidPjJgL/1hsbCylSpXSeMox05EjRxg+fDimpqaYmpri4+PDwYMH\n5XQdHR2GDRuGtrY2rq6uvHr1ir59+2JkZETNmjWpUaOG2qh4gwYNcHJyQltbG29vb1JSUuTToC4u\nLpQtWxYANzc3qlSpQlBQkLxuuXLl6N27N1paWujr66vFqaOjQ0JCAqGhoaSnp1O9enU5r6wOHz6M\np6cndevWRU9Pj7Fjx3Ljxg21UZnBgwdjYmKCubk5zZo1UxsJLWjdSPlMJdDV1SU2NpaHDx+iUCio\nV68eJiYmcnqnTp2oWbMmhoaGjB49muPHj8t5dunSBSMjI3R1dfHx8eHu3bvyiF5+ZdevX5+GDRui\npaVFxYoV6d69e4EvDAXo3LkzNWrUQEtLCx0dHVq3bs1nn30GgJWVFa1ateLatWsAHD9+nK5du8rb\nMXLkyAKXk52uri4hISHEx8dTrFgx6tWrl+ty4eHhREdHo6enh6WlJZAxIl6pUiU6d+6MlpYWdevW\nxcnJSR4Js7a2platWgDUrl0bNze3HPXi4+ODgYEB+vr67Nmzh0GDBtGgQQMAKleuTIUKFeRlvby8\nKFu2LCVKlKBt27a5tiHI2a7zazuQ0QaqVKmCvr4+rq6ucv4FWRdg4MCBGBsbU7NmTT7//HPs7Oyo\nVKkSJiYm2NnZySO+P/74Iz169KBhw4YoFAo6deqEnp4eN27cQEdHh9TUVEJCQkhLS6NChQpyW8hO\nkiQ2bNiAlZUVlpaWzJ8/n1GjRqlNYylMPWRdJr99rImfnx9WVlZYWVnRpUsXIOMY4e3tTaVKlTAy\nMmLs2LEcO3ZMbVS3IG3hzz//5OXLlwwfPhwdHR0+++wzunXrxtGjRzXG4u7uLl8PEh8fz08//YSH\nhweQ0a4fPXrEixcvMDQ0fKt58MePH5frfcSIEQwZMkQ+1pQsWRJHR0f09fUxNjZm6NChb3U8KAgL\nCwvatWsHZJylvXjxIlOmTMHAwABTU1P69u0r18nOnTsZPHgw1atXR0tLiyFDhnD37l0iIyNzzb95\n8+ZYWVnRunVreZ55Jk3fKTdv3gQKd6xQqVQEBgYyatQoDAwMqFWrFp07d/7opo4JH8bHO6lN+Nco\nWbIkL1++JD09PdfOeUxMDBUrVpRfm5ubq039KFmypPzlamBgAECZMmXkdAMDAxITE+XX5cuXl/9X\nKBSYmZnx9OlTAA4cOMCmTZsIDw8HIDExkdjYWHn5vC4gatGiBX369GHWrFlERETg5OTE119/rdbZ\nBXj69Kn8BQoZFwyVLFmS6OhouWOVtUNvaGioFv/b1E1eOnbsSGRkJGPHjuX169d06NABX19feb5q\n1m01NzdHqVTy8uVLSpQogb+/PydPnuTFixfyfnv58mWObdXkwYMHzJ8/n1u3bpGUlIRKpVKrj/xk\n3wcXLlxgxYoVPHr0iPT0dJKSkqhduzaQUddffPGFvGzWjuvbCggI4Pvvv2fRokXUrl2bcePG0bhx\n4xzLTZgwgaVLl+Lp6UmJEiXw9vama9euhIeHExQUpHaxoVKppFOnTkDGVIKFCxfKnczU1FRcXV3V\n8jY3N5f/j4qKonLlyrnGm/0zkFe7KMyFcXl9xgqzftbXenp68rSqiIgIDh48yLZt2+R0pVLJ06dP\nsbKyYsqUKSxbtoyQkBBsbGyYNGkS5cqVy1GeQqFgwIAB8hzz4OBg+vfvT4kSJbCzswMKVw9ZO/b5\n7WNNpk2blmOO+dOnT9XaaoUKFVAqlfK0GyhYWwgPDycmJkYtHpVKlesFr+3bt6dnz57MnDmTwMBA\n6tevL5fj5+dHQEAAbm5uVKpUCR8fH9q0aZPrdmXl5uYmzzEPDw9n6NChmJiY0KNHD5KSkpg3bx6X\nLl2Sp8slJiYiSdI7u34k6zE/IiICpVKJjY2N/F56erpc3xEREfj5+fHtt9+q5REdHa1W51n9+uuv\naGlpkZKSwtKlSxk4cCA7d+4ENH+nZE77Ksyx4uXLlyiVSrVYcotL+O8RHXPhH7OwsEBPT4/AwECc\nnZ01LlOuXDnCwsLkixgjIyM1fvEWVFRUlPx/eno6UVFRlCtXjvDwcKZPn87mzZuxsLCQR+eyjkTk\n90Xh5eWFl5cXL168YPTo0axfv17uCGTdnsyDNLzp/Gf98iiof1I3Ojo6+Pj44OPjQ3h4OIMHD6Za\ntWpyJyHrCFFkZCQ6OjqUKlWKgwcPcvbsWTZt2kTFihV5/fo11tbWBY555syZ1K9fH39/f4yMjNi0\naROnTp0q8PpZ90FqaiqjRo3iu+++o127dmhrazNixAh5n5UtW1ZtO/KaK2poaEhycrL8OvPHWqYv\nvviClStXolKp2Lp1K2PGjOH8+fM58ilTpgxz5swBMi4K8/b2xsrKigoVKmBtbZ3r3PRx48bh5eXF\n+vXr0dPTY+7cufIXuKZtNzMz49GjR7luT27rFSTdyMhIrS6ydgj/aVlvm4e5uTlDhw5l6NChGpf1\n8PDAw8OD+Ph4vvnmGxYuXCh3AvNSq1YtLC0tuXDhgtwxf9t6yL58fvu4oLIfIyIiItDR0aFMmTJy\nGy5IW6hQoQKVKlXi5MmTBSq3Ro0aVKhQgYsXL3LkyBF5tBygSpUqLFq0CICTJ08yatQorl69Kg+G\n5EahUKgdQytWrIiNjQ3nzp2jR48ebNiwgQcPHrB7925Kly7NnTt35BHgd9WWsteVnp6e3JnOztzc\nnOHDh6tte0Hp6+vTuXNnNmzYQGxsLAkJCXl+pxTmWKFSqdDR0SEiIoLq1asD5DmaL/y3iKkswj9W\nrFgxRo0axezZszl9+jRJSUmkpaVx4cIFvvvuOyDj9Or333/PixcvePHiBStWrKBjx46FLvPWrVsE\nBgaiVCrZvHkz+vr6NG7cmKSkJBQKBaVKlSI9PZ29e/cSHBxc4Hz//PNPgoKCSEtLk08xZ179L2W5\nAMrDw4N9+/Zx9+5dUlNTWbx4MY0aNcp1NDevU5T/pG5+/fVX/v77b1QqFcbGxujo6KjdreDQoUOE\nhoaSlJTE0qVLcXFxQaFQkJiYiJ6eHiVKlCAxMZHFixer5VumTJk870OemJiIsbExhoaGhIaGsmPH\njgLFmylrfaSmppKWliZPh7pw4QI///yznO7q6sr+/fvl7ch6QWVmXpn51alTh+DgYO7evUtKSgrL\nli2Tl0tLS+PQoUPExcWhra2NsbFxrmd4jh8/Lv/4K168OAqFAi0tLdq0acPDhw85ePAgaWlppKWl\ncfPmTflCscTEREqUKIGenh43b97kyJEjeXZMunXrxoYNG7h16xaSJPHo0aNcf3i87WnuunXr8ttv\nvxEZGUlcXByrV68ucJ6mpqZoaWm99QVpWfPLul+6d+/Ozp07uXnzJpIkkZiYyPnz50lISODBgwf8\n8ssvpKamoqenh56eXq533JCyXYQYGhrK9evX5elDmuRXD9nben77OL/tzuTu7s7mzZsJCwsjISEB\nf39/3Nzccm1zubWFhg0bYmxszNq1a0lOTkalUnHv3j3+/PPPXOPx8PBg8+bNXLt2DRcXF/n9gwcP\nymcxihUrJrfr/GTfvqioKC5duiTXe2JiIgYGBhQrVozY2Ngcn9F/Knv55cqVo1WrVsybN4/4+HjS\n09N5/PixPH2mV69erF69Wr6gPS4uLt8LeDPLSE1N5eDBg5QtW5aSJUvm+51SmGOFtrY2jo6OLF++\nnOTkZEJCQti/f/9/8u5UQk6iYy68E97e3kyaNInvv/+eli1b0rZtW3bs2IGjoyMAw4cPp0GDBvK9\nkBs0aCDf7QNyjlrldYBSKBTY29tz7NgxrK2tOXz4MMuXL0dbW5uaNWvi7e1Nz549adWqFcHBwfKc\nv8x1NZWV+V58fDzTp0/H2toae3t7SpUqJT9UJetyLVq0YPTo0YwcORJbW1vCwsLUOrd5lZHd29ZN\nVs+ePWP06NE0bdoUd3d3rK2t1Tr1HTt2ZNKkSdjY2JCWlsa0adOAjLnnFSpUwM7ODg8PDxo3bqxW\njqenJ6GhoVhZWeHj45Oj3IkTJ3LkyBEsLS2ZMWMG7u7uauu/zeiuiYkJU6dOZcyYMVhbW3P06FF5\nLimAnZ0dX331FX379sXZ2ZkWLVrkKCvzdbVq1RgxYgT9+vXDxcWFpk2bqi176NAh2rVrR5MmTdi1\naxcLFy7UGN9ff/1F9+7dsbCwYPjw4UybNo1KlSphbGzM+vXrOXbsGHZ2dtjY2LB48WL57iPffPMN\nAQEBWFpasnLlSvmuOrnVi4uLC0OHDmXcuHFYWlri4+PD69evc62z3OpVU1rLli1xc3OjQ4cOeHp6\nYm9vn+fnLGsehoaGDB06lF69emFtbU1QUFCOMjTFklt+DRo0YM6cOcyePRtra2ucnJw4cOAAgPzD\ntnnz5tja2vLy5UvGjh2b63Zm3i3IwsKCgQMH0rVrV3r27Fnoevjqq684ceIE1tbW+Pn55buPc4sr\nO09PTzp06ECfPn3ku1VNnz4913VyawtaWlqsWrWKu3fv4uDgQIsWLZgxY4ba9SDZeXh4cO3aNVq0\naEHJkiXl9y9duoSHhwcWFhbMmzePxYsXy/cmt7Cw4Pr167lu3/Hjx+V69/T0pEmTJvKxoW/fviQn\nJ9OsWTN69uyJnZ3dW7XV3JbLa50FCxaQlpYmH/dGjx4tnyFzcHBg4MCB+Pr6ynfXunTpUp7lNW3a\nFAsLC1q1akVQUBDff/89QL7fKYU9VkyfPp3ExERatWrFlClT6Nq1a751Ivw3KKT3eLXB/fv31Q6w\nT548YfTo0fI82IiICCpWrMiSJUsoXrw4AKtXr2bv3r1oaWkxbdo0tTlkggCwfPlyHj16JI/GC5p5\neXnRsWPHf3R/ZUEQBEEQis57HTGvXr06Bw4c4MCBA+zbtw9DQ0McHR1Zs2YNLVu25OTJkzRv3ly+\nR3VISAjHjh3j6NGjrFu3jlmzZqldwS4I8PE99ORjJupKEARBEP49imwqy+XLl6lcuTLm5uacPXuW\nzp07Axm3Tcu8Wf+ZM2dwd3dHV1eXSpUqUblyZfmWRIKQqaCnQoX/5hM1BUEQBOHfqsjuynL06FHc\n3d0BeP78uXxbrTJlyvD8+XMg47ZxWe+ramZm9o+eHiZ8mjTNeRZyyu3pgIIgCIIgfJyKZMQ8NTWV\nc+fO5bifL+Q/+ilG/ARBEARBEIT/giIZMb948SL169fH1NQUgNKlS/P06VPKli1LTEyM/H758uXV\n7k8dFRWV477Qr14loaMjbiYjqNPW1kKlEtcjCOpEuxA0Ee1C0ES0C0ETY2P9/Bd6h4qkY3706FG1\nG/3b29uzf/9+Bg8ezIEDB3BwcJDfHzduHP369SM6OppHjx7RsGFDtbxSU5WkphZF1MK/iZGRHomJ\nomEI6kS7EDQR7ULQRLQLQZOi7pi/96HnxMRELl++LN/PGmDw4MFcvnwZZ2dnrly5wuDBg4GM+4W6\nurri7u7OoEGD+Oabb8RUFkEQBEEQBOE/4b3ex/x9ePo07kOHIHyExEiHoIloF4Imol0Imoh2IWhS\ntmyxIi1PTNYWBEEQBEEQhI+A6JgLgiAIgiAIwkdAdMwFQRAEQRAE4SMgOuaCIAiCIAiC8BEQHXNB\nEARBEARB+AiIjrkgCIIgCIIgfAREx1wQBEEQBEEQPgKiY/4Ri4yMwNbWivT0jEcE+/gM5siRA0Ua\nQ2pqKn36dOfFi+dFWm5W48eP4sSJo+8sP0/P9ly7dvWd5fc+eHl158aN3z90GBrZ2loRHh4GwMKF\n89i0ad0HjqjoLV++hAMH9nzoMARBEIRPjM6HDuC/wNOzPS9fvkBLSxsdHR2++KIh48dPply58m+V\nT+ZTULdu3ciWLRsBUKlUqFRK9PQyHhlrbm7Oli0/vrPYDx3aR+PGlpialn5neWZav341ERFhTJ8+\nJ8/lFi4MeKflKhSKj/6Jslu37vrQIRTI+PGTi6wspVLJzJlT+Pvvu0RFRRIQsAoLiyZqy6xcGcDR\nowcB8PDoxLhx4+S0yMgI5s6dxZ07tyhf3gxf369p2tS6ULH06tWHQYP64uHRCR0dcRgVBEEQ3g0x\nYl4EFAoFCxYsITDwIgcPnqBUKVP8/b8rbG54eXkTGHiRwMCLTJgwmQYNGsqvs3bKJUninz7Y9eDB\nfbi4uP2jPArrXcT/sVIqlR86hH9l/TZqZMn06bMxNS2d48fVgQN7uXTpAps372Tz5p38/PNP7Nmz\nW06fOXMqtWvX5dixswwePJxp0yYSGxtbqDhKly5DlSpVuXTpwj/aHkEQBEHISgz1FDE9PT3atLEn\nIGAxAJcvX2Lt2pVERIRjbGyCh0dH+vcfXOD8sneufHwG07BhY/744xr37v3Nli0/olQq8fdfwL17\nf1OyZEkGDhyGvb0DkDFVZc2alZw7d5q0tDTs7NowcuRY9PX1iYqKIiIinHr1Gsj5+/nNRF/fgKio\nCIKCblCr1ufMmTOfrVs3ceLEUUqXLs3MmX7UqlUbgGfPnuLvv4CgoBsYGhrRo0cvPD17cuXKZbZt\n24QkSVy8eIFKlSqxceN2tfiDg++xefNO5s2bjYuLGx4enQA4dGg/u3ZtJyYmhnLlyjNjxmwaN274\nVvvh3r2/CQhYTHR0JM2atWDq1Fno6ekRFxfHnDnTuX37FiqVii++aMSECZMpW7YcZ86cYseObaxb\nt0XO58cff+CPP64zf/7iPOvy99+vMWfODDw9e7Br13asrJozcqQvfn4zuXkzCC0tLapVq86KFWuB\njLMskyfPoEkTK9avX83Dhw/Q19fn4sXzlC9fnqlTZ1GnTt0861gTTe3jxo3f2bFjKzExMZQsWZLe\nvfvSsWMXeZ3t27fw44/b0dLSYsCAIWr5+fnNpFy58gwaNIxjxw5z5MhBVq58M7XF1taKnTv3U7Fi\nJX755RIrVgQQExONsbEx3bt/Sa9efQq8z3R0dOjWLWO7tLW1c6SfOHGUXr28KFOmLJAxqn348AHc\n3Dry+PEjgoP/ZsmSlejp6dG6tT27d+/k/PkzdOrUlWPHDnP48H7q1WvA0aOHKVGiBNOmzeLx40es\nX7+atLQ0hg8fhaurh1yehUUTLl++RJs27Qq8DYIgCIKQF9ExLyKZnefk5GTOnAmkQYOMjqShoSHT\np8+hevUahIaG4Os7glq1PsfWtk2hyzp16jgLFwZQuXIVEhMT+eqrHgwaNIzFi5cTGhqMr+8Iqlev\nQdWq1Vi1ahmRkRFs2rQDbW1tZs2ayqZN6xgyZAT374dQoUJFtLTUT6ycP3+axYuXU7VqdSZMGM2Q\nId4MGjSM0aPHsW7dKpYt8ycgYBXp6el8/bUvdnZtmDVrHjEx0YwZM5zKlavSvHlLvLy8CQ8PY/r0\n2bnGn561x/j4AAAgAElEQVSe/r+R0YzR0bNnT7Nx41rmzVtEnTp1CQ8PQ1s7oxl//fUYbt4M0lgn\njRo15ttv/eV9ce7caRYvXoaurh7Dhw/g2LHDdOrUFUlKx929I3PmfItKpWLevNksXryAefMW0qqV\nHd9+60dY2BMqVfoMgMDAk/Tq5QWQZ10CvHjxnLi4OPbuPYpKpWLjxrWUK1eeo0dPA3Dr1p9yvNlH\ng3/++Sfmzv2OqVNnsmbNSvz9F7B69cY869jaunm+7SM9PR1TU1MWLFhChQoVuXHjd8aPH0XduvX4\n/PM6XLlymZ07f2Dp0u8xN6/A/Pnq047eZlrQ/PlzmDPnWxo2bEx8fDwRERnz1KOioujXr1eu640f\nPwkHB+d883/48D41a9aSX9eoUYv790MBePDgPhUqVMTQ0FBOr1mzFg8f3pdf3759iw4dunD8+FnW\nrVvFjBmTsbNrw65dB/njj2tMnTqRtm0dMDAwAKBKlaqcP3+2QNsuCIIgCAUhOuZFQJIkJk8ej7a2\nNsnJSZQqZcqiRRnzprPOka1Roybt2jlx48bvhe6YKxQKXF09qFq1GgC//noZc/MK8khfrVq1sbNr\ny7lzp+nXbyCHDx9g06YdFCtWDAAvL29mzZrOkCEjiI+Pw8jIOEf+dnZt+fzzOgDY2bVh//69ODtn\nTHext3dk796M+dF37tzm1atY+vUbCECFChVp374Tp0+fxNq6+f9+rEg58s8af/YfBUeOHKB376/k\n0eKKFSvJaQsWLClwHXl69qR06TIAtGxpS0jIPQCKFy9B69Zt5WW/+sqbUaOGAWBgYICtrR2nT5+k\nX7+BPHnymMePH2FjY4ckSXnWZea2DBgwBB0dHXR0dNDV1eX582dERUVSsWIlGjZsnGvMjRo1pnnz\nlgA4Obmya9f2AtWxpm3PXr8tWtjI6Y0bW2Jl1ZygoBt8/nkdzp4NxN29A9WqVQdgwIAhnDlzqkD1\nnJ2Oji4PHtynRo2amJiYyG3IzMyMEyfOFSrPrJKSkjA2NpFfGxsbk5iY+L+0RLU0AENDI54/fya/\nNjevKH9O7O0d2bJlA/36DUJHRwcrq+bo6uoQFvZE7vwbGRkRHx/3j+MWBEEQhEyfdMfczs6Iu3dz\nnvJ+V+rUUXHxYmK+yykUCubPX0STJlb/m7pxHh+fIWzbtovIyEhWrVrGgwf3USrTSE1Nk6eZFFb5\n8m8uKo2KiuT27b9wcXnT2VSpVLi4uBMbG0tycjIDBnhlWVsiPT2js1ysWDESExNy5F+qlKn8v56e\nPqVKlZJf6+vrk5SUKJf97NlTtbLT09Np3NiiwPFnFxMTo9YZL6zSpd9czKqvr8/z50+BjDMaAQGL\nuHr1CnFxr4GMDp8kSSgUChwcXFixYgn9+g0kMPAEdnZt0NfX5+XLF3nWJUDJkqXQ1dWVX/fq5cWG\nDWvw9c3ouHfo0Jk+ffppjNfU9E2dGxgYkJqaSnp6eqHqOHv9/vLLz2zcuJawsCekp6eTkpIsdz6f\nP39O3br1s6xrlmu++fHzW8DmzetZtWo5NWrUZOjQkTRo8EWh88vO0NBQrb0mJMRjZGT0vzQjEhLU\n23JG+psfnlnrWF8/42Jq9bZtILdtgMTERExMir2z+AVBEAThk+6YF6TTXNQUCgWtW7flu+/mcvPm\nDVauDMDTsyeLFy9HV1eXgIBFvHpVuAvSspQi/1e+vBmNG1vi778ix1Lp6eno6+uzbdtuypQpkyO9\nRo1aREZGkJ6enmPkuiDKly+PuXlFdu7cpzE99zxznxpRrlx5wsLCNKaNGzeKmzdvaExr3NiC775b\nmme8ADt3buPJk8esXbuZUqVMCQ7+m/79+8gdcyurZsTGviQ4+B5nzpxi1KiMu36UKFEyz7qEnNNT\njIyM8PEZg4/PGO7fD2X06GHUq9cAS8um+caZKb861uxNHKmpqUyb9jUzZszBxqY12traTJ48Xp56\nVbp0aaKjo+Tls/6fnYGBIcnJyfLrrKPRAHXq1GPevEWoVCr27v2RGTMmsW/fUaKiovDy6p5rvl9/\nPQVHR5d8t6pateoEB9+jTp16AISE3KNGjZpyWkREOImJiXJnPSQkWD7TUxgPHz6gVq3PC72+IAiC\nIGQn7spSRDI7OpIk8dNP54mPj6NKlWokJSVRrFgxdHV1uX37LwIDT5JXxzT71I/8lmnZ0pYnTx5z\n8uQxlEolSqWSO3du8ejRQ7S0tGjfvjMBAYt4+fIlAE+fxnD16hUgoxNcseJn3L79V47tKIi6detj\nZGTEDz9sJiUlGZVKxf37Idy9exvIGHmPjIzUkGfuZbRv35EdO7by9993kSSJsLAnREVldBYXLQqQ\n706T/a8gnXLIGAXV19fH2NiE169fsWHDWrV0HR0d2rRxYMWKJcTFxWFl1Qwg37rU5PLlS4SFPUGS\nJIyNjdHS0nrr2zjmV8e//34NW1urbGu9qV+lMg2lUkmJEiXR0tLil19+5rff3sRsb+/I8eOHefjw\nAcnJyWzcqF4fWS8+zpyzHRx8j5SUFDZsWJOlHCWnTh0nPj4ebW1tjIyM5As4zczMct1vgYEX1Trl\nqamppKSkAJCW9uZ/AGdnd3788QeePXvK06cx7Ny5nfbtOwJQuXIVatX6nI0b15KSksKFC2e5fz+U\nNm3s36q+s7px43d5epEgCIIgvAuf9Ij5x2TiRF+0tLRRKBSYm5szdepMqlWrzrhxE1m+fAn+/t/R\nuLEl7do5Ehf3Zt5qzo6a+mvNF9+9eW1kZMTixctZvtyfZcv8kaR0ataszciRvgAMGzaSjRvXMmRI\nP169iqVs2XJ07uwpz0/u2LELJ04cky9WzV6eQpEzxszX2traLFiwhOXL/enevSOpqWlUqVKVQYMy\n5mzb2ztw6tRx3NzaUaFCRdav36pxG7Nq29aBV69eMWvWVJ4+fUqFChWYNm12rssXRNaLS7t3/5JZ\ns6bi7u5A2bJl6dGjNz//fFFteUdHF3x8BtGlSze1Uf/86jK7sLDH+PsvIDb2JcWKFadLl2457sud\nPT719/Kv45iYaL74olH2HOX/jIyMGT16PDNmTCY1NZVWrWyxsWktpzdv3pJu3XoxevRQtLS0GThw\nKKdPn1SLIzOWypWr0K/fQHx9h6Ovb8CQISM4fPjNA7FOnjyOv/93pKerqFy5KjNm5H3/ek2+/LIr\n0dFRKBQKxo4diUKhYNeuQ5iZmdGpU1ciIsL56quMO7e0b9+Jrl09SUxMBWDWrLn4+c3Ezc0eMzNz\n/PwWUKJEyRzbkb2ONXn27BmPHj38RxdpC4IgCEJ2CulfdiPjp0/FxVZFKS0tDW/v3gQEfP9eHjL0\nrhgZ6ckdMOGNb7/9P+ztHbCy0vzj4FP3vtrF8uVLqFSpEp06eb7zvIX3TxwvBE1EuxA0KVu2aK8l\nEh1z4ZMgDqiCJqJdCJqIdiFoItqFoElRd8zFHHNBEARBEARB+AiIjrkgCIIgCIIgfAREx1wQBEEQ\nBEEQPgKiYy4IgiAIgiAIHwHRMRcEQRAEQRCEj4DomAuCIAiCIAjCR0B0zAVBEARBEAThIyA65kKR\n+PXXX5g8efwHKz8qKgpHRzve1W37f//9Gl26uL+TvN6XoKA/+PLLrh86DI2OHTvM8OED5deOjnZE\nRkZ8wIiKXmpqKr17exIbG/uhQxEEQRA+EqJjXgQ8PdvTrl0rHB3tcHW15+uvxxATE13o/GxtrQgP\nDytU+Y6Odjg5teb582eFLr8w1qxZiZdXv/eSt6dne65e/TXPZczMzAgMvJjnY9Y/NY0aWbB9+94P\nHUaBBAZexNy8QpGU9fvv1xg5cgguLm3o1q1DjvTIyAhGjhyCg4MNvXt7cu3aVbX0U6dO0LWrB46O\ntkyePJ7Xr18XKg49PT3c3TuwbdumQq0vCIIgfHpEx7wIKBQKFixYQmDgRQ4ePEGpUqb4+3+ncdn0\n9PT3Wn5g4EVOnbpA6dJl3ioPpVJZ6PLv3LlFQkIC9eo1KHQeeVEoFHmOhP+T2D9276O9vK1/W/0a\nGhrSvn0nhg8frTF95syp1K5dl2PHzjJ48HCmTZsoj2rfvx/KwoXzmDHj/zh06BQGBgYsWjS/0LE4\nODhz4sSRf10dCoIgCO+H6JgXMT09Pdq0sefhw/sA+PnNZOHCeYwfPwpHR1t+//0aPj6DOXLkgLxO\n1tP+I0YMAqBfv144Otpx9uxpAH7++Sf69fsSF5e2DBvWn9DQkHxjSU1NZenSRXTq5EqnTq4EBCwi\nLS0NyBhV7NzZjR9+2EzHjs7Mnz+H9PR0tmzZQI8enXByas2AAV7yyP+jRw8ZM2Y4bm7t+PLLrnJc\nAFeuXMbCoola2ba2Vuzfv4eePTvj5NSadetWER4expAh3ri4tOGbbyardVZy2745c6YTHR2Fr+8o\nHB3t2L59K5GREdjaWnHkyEG6dvVgzJjhREVFYmtrJXdkX79+xdy5s+jUyRVXV/tCT7PZuXMb7ds7\n0bGjC8eOHZbfv3z5Et7eX+Ls3JouXdzZsGGNnDZu3Cj27t2llk/fvr24ePF8vnWZvb388cd1fvnl\nEn36dMPJqTWdO7uxY8c2eR9mnW7j6dmeHTu20bdvL7mOU1PfPH66oG1IU/0CTJs2kY4dnXFxaYOP\nz2AePLgvr/PqVSwTJ/ri7NyaQYP65jjjk/UsUF7tX5IkAgIW0b69E87Orenbtyf374fmtns0qlu3\nPk5OrhpH6B8/fkRw8N8MGDAEPT09Wre2p2bNWpw/fwaAwMAT2NjY0ahRYwwNDRk4cCgXL54jKSlJ\njn3t2u8ZNqw/jo52TJzoS2xsLLNmTfvftn9FVFSkXF65cuUxMSnOX3/dfKttEARBED5NOh86gP+K\nzBHd5ORkzpwJpEGDhnLa6dMnWbgwgAYNGpKamvq/6Raap1ysWLEWW1srNm3aQcWKlQC4d+8u8+fP\nYcECf+rUqceJE0eZNGksO3bsQ0dHR638rLZs2cCdO7fYtGkHAJMnj2Xz5vUMHDgUgBcvnhMXF8fe\nvUdRqVTs3LmNM2dOsXBhAJ99VpnQ0BAMDAxISkrC13cEgwYNY/Hi5YSGBuPrO4IaNWpSpUpV7t8P\n1ThafvXqFTZs+IHo6Cj69+/NzZs3mDnTj+LFizNkSH8CA0/g6uqR5/ZNnz6HmzeD+OabWTRoYAEg\nz1UOCvqD7dv3oFBo5Zi6M2fODIyMjNm2bTcGBgbcuvUnkDEXvV+/Xrnux/HjJ+Hg4AzA8+fPSEhI\n4MCB41y9eoXp0ydiZ9cWExMTDA0NmT59DtWr1yA0NARf3xHUqvU5trZtcHR05uDBfXTt2h2ABw/u\nEx0dRcuWNrnWZfXqNahatVqO9pKSkkL37h2YM+dbGjZsTHx8PBERmqc5KRQKzp07zeLFy9DV1WP4\n8AEcO3aYTp265lrH27fvRVdXV2N+WesXoGVLG6ZOnYmuri4rVy5l9uxpbNy4HYDFi7/FwMCAQ4dO\nEh4ezrhxI6lQoWKucebW/q9evUJQ0A127tyHsbEJjx8/xNjYBICtWzfxww+bs+UFkpSR5/HjZ3Pb\nrbIHD+5ToUJFDA0N5fdq1qwl/5B+8CCUhg0by2kVK1ZCV1ePJ08e8fnndQA4cyaQxYuXUaJECYYM\n6c/Qod5MmDCFadNmMW/ebDZsWMOUKd/IeVStWpWQkHs0bmyZb3yCIAjCp02MmBcBSZKYPHk8Li5t\ncXFpw/Xrv9GrVx853da2jdxR19PTe+v8Dx3aT8eOXahbtz4KhQJXVw90dXXlzqZ6+W2ZMmUCAKdO\nHadfv4GULFmSkiVL4u09mJMnj8n5amlpMWDAEHR0dNDX1+fIkYMMGjSczz6rDECNGjUpXrwEly//\nhLl5BVxdPdDS0qJWrdrY2bXl7NlAAOLj4zAyMsoRd+/eX2FkZES1atWpXr0mzZu3xNy8AsbGJjRv\n3pLg4L8LtH256d9/MPr6Bjnq9NmzZ/z66y9MmDAFExMTdHR0aNQoo1NvZmbGiRPncv3L7JQD6Ojo\n4O09CG1tbVq0aIWhoRGPHz8EwMKiCdWr15DrqV07J27c+B0AO7s2hITcIzo6St4PbdrYo6Ojk2td\nnjv3ZtQ8a3vR19dHR0eXBw/uk5AQj4mJidxB1MTTsyelS5ehePHitGxpS0jIvULXcfb6dXNrj6Gh\n4f/qZTAhIcEkJiagUqm4cOEcAwYMRV/fgOrVa+Di4l6oC3F1dHRITEzg4cOHpKenU7lyVXlalpdX\nvxz768KFnzlx4lyBOuUASUmJckc/k6GhEYmJif9LT86RbmxsLKcrFArc3dtToUJFuR1/9lllmjSx\nQltbm7ZtHeR2ncnIyJj4+Pi3rgtBEATh0/NJj5jb7WzG3Rd33lv+dUzrcrFn3hcdQsaX9fz5i2jS\nxApJkrh48Tw+PkPYtm0XCoWCMmXK/qM4oqIiOXHiKHv2/Ci/p1IpefbsaY7ys3r+/BlmZuby6/Ll\nzeR1AEqWLKU2WhoTEy2P0mcv//btv3BxaZulfBUuLhnTKIoVK05CQkKO9UqVMpX/19fXV3utp6fH\ny5cvC7R9uSlXrrzG92NioihevDgmJiYa0wuqRImSaGm9+W2befYA4Natv1i1ahkPHtxHqUwjNTUN\ne3sHIKMj1qKFDadPn6R3776cOXOKSZOmy9uaV10qFArKli2nFoef3wI2b17PqlXLqVGjJkOHjqRB\ngy80xly6dGn5f319fZ4/fyqXq6mO87pIOGv9pqens3r1Cs6fP0Ns7EsUCi0UCgWxsbHo6+ujUqko\nX/7N8uXLm+Wab16aNLGia9fuLF78LdHRkdjZtcXHZwxGRsaFyi87Q0OjHG01ISFezt/IyJCEBPVO\ndHx8vNoPz+ztOPvrzDaSKTExgWLFir2T+AVBEIR/t0+6Y16QTnNRUygUtG7dlu++m8vNmzfk97Iy\nNDQkOfnNl/fz58/zzLN8eTO++qo/X33V/61iKVOmLJGREfIUiejoKLUfCdnjKleuPOHhT6hWrXqO\n8hs3tsTff4XGcmrUqMmTJ4/fKrasZee/fZqnPeR2B5Zy5cx4/fo18fHxOTrnUVFReHl1zzWur7+e\ngqOjS97BA7NmTcXTsyeLFy9HV1eXgIBFvHr15rZ4Dg7ObNy4hkaNLEhNTcXSsimQf11qUqdOPebN\nW4RKpWLv3h+ZMWMS+/YdLeDaCrnct21DWev31Knj/PzzRZYu/R4zM3Pi4uJwc7NHkiRKliyFtrY2\n0dFRVK5cFUA+W6BJfu3f07Mnnp49efnyJTNmTGL79q0MHDiULVs2sHXrpmwxvpnKcurUhXy3qVq1\n6kREhJOYmCh3tkNCgnF2dgOgatXqhIQEy8uHh4ehVKbx2WdV8q2j3Dx8+JBevbzyXU4QBEH49Imp\nLEUk87S9JEn89NN54uPjqFq1usbT+TVrfs6FC+dISUkmLOwJR48eVEs3NTVVm0fcvn1nDhzYy+3b\nfyFJEklJSVy+fEk+vZ4bBwdntmxZT2xsLLGxsWzcuFbugGji4dGJtWtXERb2BEmSCAkJ5vXrV7Rs\nacuTJ485efIYSqUSpVLJnTu3ePToIQAtWrTixo3rBa0qILO+pAJtn6mpKWFhTwqcd5kyZWjevCWL\nFs0nLi4OpVIpTzPJvK1ibn8F6ZQDJCUlUaxYMXR1dbl9+y8CA0+S9QdEixatiIqKYv361bRr5yS/\nn19dZm8vSqWSU6eOEx8fj7a2NkZGRmhraxe4Lgpax35+M5k7d1ae26urq0vx4sVJSkpi9eo3Pyy0\ntbVp3bot69evISUlmQcP7nPiRO4/HDS1/8wO7t27t7l16y+USiUGBgbo6enLZy2++qp/jv116dIV\n+U5E8hZLEikpKSiVSiRJIjU1Vb7ouXLlKtSq9TkbN64lJSWFCxfOcv9+KG3a2APg5OTKzz9fJCjo\nBklJSaxd+z2tW9urzUnPrNPMsvLy9GkMcXGvqF9f8xkOQRAE4b/lkx4x/5hMnOiLlpY2CoUCc3Nz\npk6dSdWq1VAoFDlG1Xr0+JK7d2/Tvr0zNWvWwsnJlevXf5PTvb0H83//N5OUlBQmTpxK27YOTJw4\nDX//BTx58gR9fX0aNbLIcSeU7Pr2HUBCQgJ9+/YEwN7ekb59B+S6fM+evUlLS8XX14dXr2KpUqUq\n8+YtpHjxEixevJzly/1ZtswfSUqnZs3ajBzpC8Dnn9fBxMSE27f/ki8CzW8kMesFgHXq1NW4fZkX\ny3l59WPJkoUsWeJPv34DaN3aXmP+Wd+bNm02y5YtpndvT9LS0mjSpOk7vfhu3LiJLF++BH//72jc\n2JJ27RyJi4uT03V1dWndui3Hjh1myBAf+X0jI6M861JTezl58jj+/t+Rnq6icuWqzJgxp0AxFqSO\nM9tQTEw0jo7O2dZ9w8XFnatXf6FTJzdKlCjBgAFDOHRon5zu6zuRuXNn0aGDM1WqVMPdvQN//HFd\nY355tf+EhAQCAhYTERGOvr4ezZq14MsvvyrQ9mb644/rjB49TC63XbtWWFg0ISBgFQCzZs3Fz28m\nbm72mJmZ4+e3gBIlSgIZI+rjx09m9uxpvH79iqZNm6ldyPm/rcm1nrKnZ1zg3F6+SFsQBEH4b1NI\n7+pRiEXk6dO4/BcSPjq//XaFffv2MG/ewveSv5GRHomJqfkvKLy1tLQ0vL17s3nzjrccjf/wPuZ2\nkZqairf3l6xYsY6SJUt+6HD+Uz7mdiF8OKJdCJqULVu01wCJjrnwSRAHVEET0S4ETUS7EDQR7ULI\n7n5sCM1qWRRpmeL8qSAIgiAIgiAACWkJHAjey+Zb63mR/IJHYx8Wafnv/eLP169fM2rUKFxdXXFz\ncyMoKIjY2Fi8vb1xdnamf//+vH79Wl5+9erVODk54eLiwqVLl953eIIgCIIgCMJ/3N0Xd5j803gs\nt9Tj5MNjTLSeyq+9bxR5HO99KsvEiROxsrLC09MTpVJJUlIS33//PaVKlWLQoEGsWbOG169fM378\neEJCQhg3bhx79uwhOjoab29vTp48qXavaDGVRdBEnIIUNBHtQtBEtAtBE9Eu/ntSVCkcCT3I5lsb\nePDqPr3rfUWfun2pVOwzeZminmP+XkfM4+LiuHbtGp6enkDGU/uKFSvG2bNn6dy5MwCdO3fm9OmM\npxqeOXMGd3d3dHV1qVSpEpUrV+bmzZvvM0RBEARBEAThP+TBq/vM/mUGFlvqsfPuDwxuOJzfvW4x\nyXqaWqf8Q3ivc8zDwsIwNTVl8uTJ3L17l/r16zNlyhSeP39OmTIZj9EuU6aM/ACRmJgYGjVqJK9v\nZmZGdHT0+wxREARBEARB+MQp05WcfHiczbfW8+fTIHrU6c2RziepXrLmhw5NzXvtmCuVSm7fvs30\n6dNp2LAhfn5+rFmzRm0ZTfdlzp4uCIIgCIIgCG8rIj6cbbc388OdLXxWrDJ96/dni+tODHQMPnRo\nGr3XjrmZmRnly5enYcOGADg7O7NmzRrKlCnD06dPKVu2LDExMZiamgJQvnx5oqLePKo7KiqK8uXL\nq+Wpp6eDjo54YKmgTldXGyMjvQ8dhvCREe1C0ES0C0ET0S4+HelSOmcfnmFd0Bp+DrtEtzo92O95\niAZlG3zo0PL1XjvmZcuWxdzcnAcPHlCtWjV++eUXatasSc2aNdm/fz+DBw/mwIEDODg4AGBvb8+4\ncePo168f0dHRPHr0SO7UZ0pNVZIqrs0oEpGREXTv3pELF35VuwA3qwcP7uPnN5N167YUaWwLF86j\nTJmy9Os3EMj9oh0vr+6MGzfpnT7V82Oyfv1qIiLCmD59DlFRUXh5defUqQv/qTNNL148Z9SooWzc\nuB1dXV21NHExl6CJaBeCJqJd/Ps9TXzKjrvb2HJ7IyX0StCvwQAC2q7GRNcEoFD719hY/12Hmaf3\nfh/z6dOnM378eNLS0qhcuTLz5s1DpVIxZswY9u7dS8WKFVmyZAkANWvWxNXVFXd3d7S1tfnmm28+\nqQ7G6dMn+fHH7Tx8eB8DA0PMzSvg6upB586e/yhfW1srdu7cT8WKleT3snbY3qd1676nVy+v91qG\nJuPHTy7Qclu37nrPkahbv341W7ZsQE8v44OsUCjYvHkH5uYV3kt5WT8fZmZmBAZefC/laHLmTCC7\nd+8gJOQedevWZ9my1WrpwcF/M2/eHB4/fkiVKtWYNGk6tWp9Lqf/+OMPbN++heTkZNq0acf48ZNz\ndKwLwtS0NBYWTTl0aB9du/b4x9slCIIg/HtIksSVyMts+msdZx6fxr16e9Y6bqRxOct/ZR/yvXfM\n69Spw969e3O8v2nTJo3LDx06lKFDh77nqIrejh3b2LFjK+PGTcTaugWGhoYEB//Njh3b8PDoWKgO\nSV6KojE+e/aMP/74nZkz5xZqfaVSiY7Op/WMK4VCgYODM9Onz37rdf9t9VGiRAl69PiSR48ecv36\nb2ppaWlpTJo0jh49etOlSzcOHNjD5Mnj2LlzPzo6Ovz66y/88MMWAgJWUbp0GaZMGc/69asZOtSn\nULE4Obnw3XdzRcdcEAThP+JVSiy7/t7B5lsbAOhbvz/f2i2mpEGpDxzZPyMmaxeB+Ph4NmxYzbhx\nk2jd2h5DQ0MAatWqzYwZc9DV1SU1NZXly5fQtasHHTo4s3DhPFJSUuQ8Dh3aT8+enXFza8ekSWN5\n9uzZW8WwZMlCunRxx9m5NQMGeBEU9Oam+bdv/8WAAV44O7emQwdnli3zV1v35MljdO3qgYeHA1u2\nbJDf/+23K9SuXUftR4WnZ3u2bt1Enz7dcXW1Z+7cWaT+b+7R779fo3NnN374YTMdOzozf/4cJEli\n69ZN9OjRCXf3dsyYMVntgVNBQTcYOrQ/Li5t6dLFnePHjwDg5zeTtWu/ByA2NpZRo3xwcWmLm1s7\nRowYpBbPtWtXAUhNTWXp0kV06uRKp06uBAQsIi0tTS22nTu30b69Ex07unDs2OG3qmPI+OUOBXs0\ngENK4e4AACAASURBVKb6iIuL4+uvx+Dh4Yirqz1ff+3L06cx8joREeH4+AzGyak1vr4jePUqVk6L\njIzA1taK9PT0HNsOGaP5c+ZMByAlJYXZs6fj7t4OF5e2DBr0FS9fvnirbW3a1Jq2bR0oXbpMjrQ/\n/rhOeno63bv3QkdHB0/PnkiSxO+/XwPg+PEjeHh0pGrVahQrVgxv70EcP/6mvj0927N9+1b69u2J\no6Md8+bN5sWL54wbNwpn59aMGTOcuLg3zzSoW7c+ERHhREdH5YhFEARB+DRIksQf0dcZc3YETbc1\n5Hr0b3zXegk/9bzKoIbD/vWdciiCEXMB/vrrJqmpqdjats51mVWrlhEZGcGmTTvQ1tZm1qypbNq0\njiFDRnD9+m+sWbMCf/8VVK1anRUrljBz5hSWL1+Ta37ZnxtVr159+vcfjImJCbt2bWfGjIns2XME\nXV1dli5dRI8eX+Lk5EpycjKhoSFq6/75ZxA7duzj8eNHDB7clzZt7KlcuSr374dSuXKVHGWfPn0C\nf//l6OsbMHGiL5s3r2fQoGFAxnzguLg49u49ikqlYvfunfz880VWrFhLyZKl8PdfwOLF3zJzph9R\nUZFMmDCaiROn0qZNOxIS4uXbZ2a9m8/OndswMyvP0aMZ98O/detPOZasy23ZsoE7d26xadMOACZP\nHsvmzesZOHCoHFtCQgIHDhzn6tUrTJ8+ETu7tpiYmLB16yZ++H/27js6yjp9//h7UiGhkwKhSG8J\nTV2KINIhBKQJIgIhQbCs6+oK/lxlF91V2KIulnVpmWQSem+hSFVARBEUMgm9lxQCISQhpM3vD75G\no4MTkMxMkut1judk6nMl3jy588ynLDBZ/VkbDAY2btxe+PWePbsYMKAXNWvWZPjwkQwZcuehSj//\nedy6lU1IyGD+/vd/kp+fz4wZf+ODD/7FjBnvAfD221Np3botM2d+itl8mClTXr5jXf18xaPbX9++\nvXHjejIzM1i5cgMeHh4cP34UT8/bw2/ee+8fbN262ep71qpVm6iohXf8fn5w+vRJGjcuugRVkyZN\nOX36JB06dOLMmdN069aj8LHGjZtw9epV0tPTqVKlCgaDgS++2MHMmf8jPz+PsLCnOX78KH/+8zQe\neKABU6b8keXLFxMWdvuPMDc3N+rUqcfx48fw969lM5+IiJQembmZrDy+DJPZSNqtNMa1CuPLp77F\n18vX0dHuOzXmdnD9ehrVqlUrMoHyuefCOXPmNLm5Obz//sesW7eaqKhFVK58e4epsWPDePvtv/Ds\ns7/ns882EhIymKZNmwPw7LMvEhzcg8TERGrVut2EhIc/jcHw4/vn5OTQo0evwtt9+wYXfj1q1BhM\nJiPnzp2lceMmuLu7c/78OdLSbucMDCw6azk8fBIeHh40adKUxo2bcvz4cerXb0BGRgZVq1Yt8lyD\nwcCwYSPx9fUDYNy4cGbO/HdhY+7i4sKECc/i5uaGm5sba9eu5JVXXsPH5/Y/rrCwSTzxxEDy8//G\nli2b+N3vOtCrV18AqlSpSpUqRY8H4O7uzoULV0hMvEydOnVp06ad1f8PW7Zs4pVXXqNatWqFx/r3\nv6cXNuZubm6EhU3ExcWFzp27ULGiF+fOnaFVqyDGjh3P2LHjrb7vT/Xs2YfBg4dRo0ZNzObDvPnm\na1SqVJnevftZff7Pfx6enp489tiPDeu4cWG89NLtn11iYiJHjsTz0Uf/w83NjbZt29Oly6MU9wr9\nT6/mu7u7k55+nQsXztO4cROaNWtR+LzJk19n8uTXi/Wed3Lz5k28vSsVuc/buxJZWVn/93gWlSpV\nKvIYQFZWFlWqVAFg+PCRVK9+++pH27btqF69ZuEY9W7durN/f9HhM15eXmRmZvym3CIi4jwSUuMx\nmSNYeXwZnQK68EbHv9C9Xi9cDGV3wEeZbsyrd+uI25GEEnv/vBYtufbFPpvPq1KlKmlpaRQUFBQ2\n57Nm3R4SMmxYCFevXiU7O5sJE346idJCQcHtJio19QotWrQqfKRixYpUrVqVK1eSCxtzo3FBkcmf\nRuMcLl48X3h74cIYNmxYy5UrKYCBrKzMwmEQr7/+F+bNm8WYMU9Qu3YAYWGTeOSRroWvrVGjZuHX\nFSpU4ObN281V5cqVycrK/MX36+f34xKX/v61/u+Yt1WrVr3I0JfLly/xxhuTi/xR4erqyrVrV0lO\nTiYg4Mfv6ed++FTgqafGEhMzj1de+T0Ajz8+lDFjxv/i+VeupFCrVu07ZqtategfT7e/15t3PL41\nDRo0LPw6KKgNI0aMYufObXdszH/+88jOzuajj97n66+/4saN20N6bt68icVi4cqVFCpXroKn549r\nr9aqVZvk5OIN3/jp1fN+/QaQnJzEtGlvkJFxg759g5k06YX7Nsbdy8vrF7WRkXEDLy8vACpWLNpE\nZ2RkFL7uBz+tO09Pz8JlVQE8PDwL6/AHWVlZVKpk362TRUTk/srOy2b9qTVExUVw7sZZxrQMZeeT\newmoVMfR0eyiTDfmxWma7SEoqA0eHh7s2rWTxx7r+YvHq1WrhqenJ/PnLyvcEfWnfHx8uXz5UuHt\nmzdvcv36dXx8/O54zJ8OZfn++4MsWhTDhx/+j0aNGgMQHNyz8Dl169bjrbfeBWDnzm1Mnfr/2Lhx\nm83vq0mTpoVjvn/qp+N8k5ISC6+Gwy8npfr71+KNN6YRFFR0WUy43eAnJJht5vDy8uKVVybz7LMv\ncerUSf74x+dp1SqIBx98uMjzfvg5/tA8/zzbr4mONhITE2X1MYPBwGeffV6s97H22p9avHg+58+f\nY+5cE9Wr1+D48aOEh4/BYrHg4+PDjRvpZGdnU6HC7eY8MfHyHZey/PkfFqmpP85L+OHTgbCwiSQm\nXmby5D9Sv/4DDBw4mH//ezqffbbJ6nvWrl2b6OglP/sefvm8hg0bsXjxgiL3nTx5gieeGFX4+PHj\nx+jR4/ZSqSdOHKNGjRqFV8ut+fnwrJ/Ky8vj4sXzNGnS9I7PERER53Xq+kmizZEsPbqQIJ82PN/u\nD/RrEIybS5luVX+h7H4W4ER+mNz2/vv/ZOfObWRlZVJQUMDx40e5efMmBoOBQYOG8tFH73Pt2jUA\nUlKS+frrrwDo3bsfGzas4/jxY+Tk5DB79n8JDGxdeLXclqysTFxdXalWrRq5ublERs4tcjVz8+YN\nhcf19q6EwUCRK9i/dLtBevjhDhw7dqRwAiXcbp5WrVpOSkoy6enXiY42Fg5FsWbIkOHMnv3fwo2l\nrl27xu7dt5vcvn37s3//12zfvpW8vDyuX0/j+PFjhcf5wZ49uzh37hwWiwVvb29cXFysrkrTu3c/\noqMjSEtLIy0tjcjIufTrN8DGT++2cePC2bLlC6v//bQp37VrJ+np6VgsFuLj41i+fAldu/44BvzF\nFydhNN55bkBWVhaenp54e1ciPf06RuPcwsdq1apNixatiIiYTV5eHt9//x1ffrnrju/VtGlztm37\njLy8PI4ciefzz7fzwxjzAwf2c/LkCfLz8/Hy8sLNzQ1XV1cApkx5447f60+b8oKCAm7dukVeXh4W\ni4WcnBzy8vIAaN/+YVxcXFi2bDE5OTksW7YYFxeXwj+W+vcPITZ2DWfOnCY9PZ2oqHkMGPB4sf5f\nWJOQYKZWrQCNLxcRKUVy83NZf3ItI9YOZuDKPhgwsH7YFpYOWk1Io0HlrimHMn7F3JmMHj0OHx8/\nFiyI5p13plGhQkUCAurwwgsv0bp1WwIDWxMZOZdnnx3P9etp+Pr6MXToE3To0ImHH+7AM888x9Sp\nr3Hjxg1at27D22//uEShtSb0pxP9OnZ8hI4dO/PUU8OoUKEiTz45Gj+/HxuYr7/eyyefzCQ7O5va\ntWvz9tvT8fDwuON7//C+NWrU5MEHf8cXX+ykV68+hc/v06cfr7zyIleupNCtW3dCQyfc8ecyYsRT\nWCwW/vSn33PlyhWqV69Or1596dr1Mfz9a/Hvf3/If/87k3/+8+94e1di0qQXaNq0WZGJjRcvnufD\nD//NtWvXqFy5CsOGjaB9+4d+cazQ0AlkZmYSGnr7qm3Pnn1+Ndu92LZtC//4x9/JycnFz8+PsWPH\n079/SOHjKSnJdxwDDzBy5GjefvtNQkJ64+vry5NPPs2ePT+uTT5t2ju8++5bBAf3JCioNcHBA4us\nTvLT/1/PPPMcb731JsHBPWnf/kH69AkmPf06cHvS6XvvzSAlJZmKFb3o1atvsf9I+cGmTbHMmPHj\nspC9enUhOHggb7wxDTc3N2bMeI9//OMdZs36mAYNGjF9+nuFQ2U6duzM6NHjeOml57h16/Y65hMm\nPPurxys6kbXo7c8+28TQocPvKr+IiDjGxRsXiEmIYmFCDA2qNCQ0MJyBjQfj6WrfzXyckcHya58P\nO6GUlBu2nyR2c+bMad59dxpz597e+XPEiMd5/fW/8NBDv7NrjtKwY9sPY7r/978IR0cpU65du8of\n/vCsdv6UYlNdiDWqi5JVYClgx7mtmMxG9l3ey7BmIwgNnECLGi0dHe1X+frad+6SGnO5r9SYizNR\nXYg1qguxRnVRMpKzkll8ZD7R5kiqV6jB+MAJDGk6HG93b0dHKxZ7N+YayiIiIiIi943FYuHLS7sx\nmSPYcX47Axs9zrx+Jtr5PejoaE5PV8ylTNCVDrFGdSHWqC7EGtXFb5eWfY2lRxdhMhtxMbgQGhjO\niOajqOpZzdHR7pmumIuIiIhIqWCxWDiY/C1R5gg2no6lV/0+vN/9IzrW7nyHBSTk16gxFxEREZG7\nkpGbwcpjyzCZjaTnXGdcYDh/7fx3fCr+cj8WKT415iIiIiJSLOYrcZjMEaw+sYLOAV2Z2uktHqvX\nA5df3f9EikuNuYiIiIjcUXZeNmtPrsJkNnLhxnnGtApl55N7CahUx9HRyhw15iIiIiLyC6fSTmAy\nR7L06ELa+LbjxfYv0+eBfuVyR0570U9WRERERADIzc9l05lYosxGElLNPNViDBuHb6dB1YaOjlYu\nqDEXERERKecu3DjP/PgoFiTE0KhaY0IDwwlp9Dierp6OjlauqDEXERERKYfyC/LZcX4rJrORry9/\nxRPNnmT542tpXqOFo6OVW2rMRURERMqRpKwkFiXEEBMfhU9FH0IDJzC7TyRe7l6OjlbuqTEXERER\nKeMsFgt7Lu3CFGdk54XtDGo0GGO/GNr6tXd0NPkJNeYiIiIiZdS17KssObqQaHMkbi5uhAZO4P3u\nH1LFs6qjo4kVasxFREREyhCLxcK3Sd9gMhvZdGYDvev35T89/kuHWh0xGAyOjie/Qo25iIiISBmQ\nkXOD5ceWYjIbyczNIDRwAm898i41K9Z0dDQpJjXmIiIiIqVY3JXDmMxG1pxYQZc63Zj2yN/pVrc7\nLgYXR0eTu6TGXERERKSUuZl3k7UnVmEyG7mUcZGxgeP5YtQ+annXdnQ0+Q3UmIuIiIiUEieuHccU\nb2TZ0UW093uIlx78E70f6Iubi1q6skD/F0VEREScWE5+DptOx2IyG0m4Gs/oFmPZNHwHDao2dHQ0\nuc9sNub79++nZcuWeHt7s3r1ahISEhg3bhx16tSxRz4RERGRcun8jXPMj49iQUIMTas1IzQwnAGN\nBuHh6uHoaFJCbM4KePvtt/Hy8uLIkSNERUVRv359/t//+3/2yCYiIiJSruQX5PPZmY08HTuC3ksf\nJTM3k5WPr2fVkFiGNB2upryMs3nF3NXVFYPBwNatW3n66acZMWIEy5cvt0c2ERERkXIhKSuJhfHR\nxMRH4eflx/igZ5jb14SXu5ejo4kd2WzMvb29mTVrFmvXrmXBggXk5+eTl5dnj2wiIiIiZZbFYmHX\nxc8xmY18cWEnjzceSlTwAtr4tnN0NHEQg8VisfzaE5KTk1m/fj1t2rTh4Ycf5tKlS+zbt4+hQ4fa\nK2MRKSk3HHJccW5eXh5kZeU4OoY4GdWFWKO6EGvsWRdXs1NZcmQR0fFGPFw8CA2awIhmT1LZo4pd\nji/F5+tb2a7Hs9mYOxs15mKNftGKNaoLsUZ1IdaUdF1YLBb2J31NVFwEm89spF+DYEIDJ/C7Wh0w\nGAwldlz5bezdmN9xKEv79u3v+CKDwcCBAwdKJJCIiIhIWXEjJ53lx5ZiMhu5mZdFaOAE/tZlBjUr\n1nR0NHFCd2zMDx48CMB//vMf/Pz8GDx4MABr164lOTnZPulERERESqHDVw5hijOy9uRKHq3bnb91\nmU7XOt1wMdhcEE/KMZuTP7dv3866desKb48ePZpBgwbx8ssvl2gwERERkdIkKzeLtSdXYTJHkJiZ\nyNhW49k16mv8vWs5OpqUEjYbcy8vL9asWcPAgQMBiI2Nxdvbu8SDiYiIiJQGx68dI9psZNmxxTzo\n9zAvPzSF3vX74uri6uhoUsrYnPx5/vx53n333cKhLQ8++CBvvvkmdevWtUvAn9PkT7FGk7nEGtWF\nWKO6EGvuti5y8nPYeHo9UXERHLt2lKdbjmNMq1DqV3mgBFOKvZW5VVl69uyJt7c3rq6uuLm5sXz5\nctLS0njllVe4dOkSderUYebMmVSpcnuJoNmzZ7NixQpcXFyYOnUqXbt2LfJ+aszFGv2iFWtUF2KN\n6kKsKW5dnE0/w/x4EwsTYmheowWhgeEENxyoHTnLKKdZleUHqampLF26lIsXL5Kfn194/4wZM4p9\nkJiYGKpVq1Z4e86cOTzyyCNMnDiROXPmMGfOHCZPnsyJEyfYsGEDsbGxJCUlERYWxubNm3Fx0UQJ\nERERcYz8gny2nvuMqLh5HEz+lhHNn2L1kA00rd7M0dGkjLHZmL/wwgs8/PDDPPLII4UN8t2ut/nz\ni/Lbt29n/vz5AAwdOpSxY8cyefJktm3bRkhICO7u7tStW5f69etz6NAh2rXTDlgiIiJiX4mZl1mQ\nEM38eBO1vGsTGhiOsf98KrpVdHQ0KaNsNubZ2dlMmTLlng9gMBgICwvDxcWFUaNGMXLkSFJTU/Hx\n8QHAx8eH1NRU4PYuo23bti18ba1atUhKSrrnY4uIiIjcjQJLAbsufI7JbGTXxc8Z3HgY0QMW09qn\njaOjSTlgszHv3r07O3fupHv37vd0gEWLFuHn58fVq1cJCwujUaNGRR43GAy/egVeu2GJiIhISUu9\nmYrxYCTR8UYqunkxPnACH/b8L5U9qjg6mpQjNhvz6OhoZs+ejbu7O25ut59+Nzt/+vn5AVCjRg36\n9OnDoUOHqFmzJikpKfj6+pKcnEyNGjUA8Pf3JzExsfC1iYmJ+Pv7F3k/Dw833Nw05lyKcnd3xctL\nE2+kKNWFWKO6kB9YLBa+urSXiO/nsvHkBkIaD2ReiJEOtTvqwqA4hM3G/IdlEu/FzZs3yc/Pp1Kl\nSmRlZbF7925efPFFevbsyapVq5g0aRKrV6+md+/ewO0VXF599VXGjx9PUlISZ8+epU2boh8d5eTk\nkaPJ9PIzWmVBrFFdiDWqC7mRk86yY0swxRnJKbhFaGA4/3rmfSpYKgFw82augxOKs/D29rTr8Ww2\n5gBbt25l//79GAwGfve739GzZ89ivfmVK1d48cUXAcjPz2fQoEF07dqVoKAgXn75ZVasWFG4XCJA\nkyZNCA4OJiQkBFdXV6ZNm6a/WEVEROS+OJTyHSazkbUnV/NY3R680/UfdK3TDYPBgFdF/cEmjmdz\nHfP33nuPw4cPM2jQICwWCxs2bCAoKIhXX33VXhmL0DrmYo2ugIk1qguxRnVRvmTlZrHmxEpM5giS\ns5IZ22o8o1uNw9+r6FBZ1YVY43QbDA0aNIjVq1fj6np7W9n8/HyGDBnCunXr7BLw59SYizU6oYo1\nqguxRnVRPhy7ehSTOYLlx5bwu1odCQ0Mp2f9Pri6uFp9vupCrHG6DYYA0tPTqV69euHXIiIiIs7m\nVv4tNpxah8ls5ETacZ5uOZatI3dRr3J9R0cTKRabjfmzzz7LsGHD6NixIxaLhW+++cZhw1hERERE\nfu5s+hlizFEsOjKfFjVbMaH1JPo3CMHd1d3R0UTuis2hLABJSUkcPnwYg8FAmzZt8PX1tUc2qzSU\nRazRR5BijepCrFFdlA15BXlsObsZkzmC75MPMqL5U4xrFUaT6k3v6f1UF2KN0w1l2bJlCx07dixc\n0jA9PZ2tW7cW3hYRERGxl8sZl1iQEM38eBMBleoQGhhOZP8FVHSr6OhoIr+ZzZ16Pv74Y6pU+XHX\nqypVqvDxxx+XaCgRERGRHxRYCthxbhvjNz7NY0s6kZyVxPyQpWwYvpUnW4xWUy5lhs0r5tZGuhQU\nFJRIGBEREZEfXLl5hcVHFhBtNuLtXonxQRP4pNcsKnnYd3iBiL3YbMyDgoKYMWMGTz/9NBaLhQUL\nFhAYGGiPbCIiIlLOWCwW9iV+RVTcPLae/YwBjQbyvz7zeNDvYW06KGWezcmfmZmZfPrpp+zduxeA\nLl268Pzzz+Pl5WWXgD+nyZ9ijSbtiDWqC7FGdeGc0m9dZ9mxxZjMRvIK8ggNDGdk86eoXqGGXY6v\nuhBrnG6DoR9kZWU5rBn/KTXmYo1OqGKN6kKsUV04l++TD2IyG1l3ag096vUkNHACjwR0tfvVcdWF\nWON0q7IcOHCAqVOnkpmZyeeff86RI0dYvHgxb731lh3iiYiISFmTmZvJ6uMrMJkjSM1OZVyrMPY8\ntR8/Lz9HRxNxKJuN+fTp05k3bx4vvPACAC1atOCbb74p8WAiIiJSthy5mkC02ciKY0vpULsTr3V4\ngx71euPq4uroaCJOwWZjDhAQEFDktqur/gGJiIiIbbfybxF7ai1RcRGcvn6Kp1uNY9vI3dStXM/R\n0UScjs3GPCAggG+//RaAnJwcYmJiaNy4cYkHExERkdLr9PVTxMRHsfjIAlrVDGJim+fp32AA7q7u\njo4m4rRsTv68evUq7777Ll9++SUWi4UuXbowdepUqlevbq+MRWjyp1ijSTtijepCrFFdlJy8gjw+\nO7OJKPM8Dqd8z8jmowkNDKNRtSaOjmaT6kKscdpVWZyFGnOxRidUsUZ1IdaoLu6/yxmXiImPYkFC\nNPUq1yc0MJxBjYdQwa2Co6MVm+pCrLF3Y+5i6wn//Oc/ycjIIDc3l9DQUDp27Mjq1avtkU1ERESc\nVIGlgO3nthK6cTSPLelEavYVFoYsZ/2wzxjRfFSpaspFnIXNxnzPnj1UqlSJnTt3UqdOHbZu3UpE\nRIQ9somIiIiTuXLzCh8d+A8dF7Tj3a/epvcDfTkwLp5/dvuAQJ8gR8cTKdVsTv7Mz88HYMeOHfTr\n14/KlStrS1wREZFyxGKx8NXlLzGZI9h2bisDGg5kdh8j7f0eUk8gch/ZbMx79OhB//798fT05K23\n3iI1NRVPT097ZBMREREHun4rjWVHF2MyGymwFBAaGM4/Hn2fahUcswCESFlXrMmf165do0qVKri6\nupKVlUVmZia+vr72yPcLmvwp1mjSjlijuhBrVBe2HUz6FpPZSOzpdfSs14vQwAl0DuhSpq+Oqy7E\nGntP/rzjFfO9e/fSuXNnNm/eXPgP8Yce3mAw0LdvX/skFBERkRKXmZvJquPLMZmNXMu+yrjAML58\n6lt8vRxzIU6kPLpjY/7NN9/QuXNnduzYYfUvZDXmIiIipV9CajwmcwQrjy+jU+1H+HPHqXSv1wsX\ng831IUTkPtM65lIm6CNIsUZ1IdaoLiA7L5v1p9ZgMhs5m36Gp1uOY0zLUOpUruvoaA6juhBrnGYo\ni9Fo/MV9BoMBi8WCwWAgLCysRIOJiIjI/XXq+klizFEsObqAwJqtea7ti/R9oD/uru6OjiYi/Epj\nnpmZaXUIyw+NuYiIiDi/3PxcNp/ZiMkcgTn1ME82f5r1w7bQqGpjR0cTkZ/RUBYpE/QRpFijuhBr\nyktdXLxxgfkJJhYkRPNAlQaEBoYzsNFg7ch5B+WlLuTuOM1Qlr///e93fJHBYGDq1KklEkhERETu\nTYGlgJ3ntxEVF8FXl79keLORLBm4ipY1Wzk6mogUwx0b88DAwMIx5T+noSwiIiLOIyUrhUVHYoiO\nj6KaZzXGB07g0z7zqOReydHRROQu3LExHzZsmD1ziIiIyF2wWCzsvbQHkzmC7ee3EdJwEPP6RtHO\n70FHRxORe3THxvydd95h6tSpPPfcc1YfnzVrVomFEhEREevSsq+x9OgiTGYjLgYXQgPD+ddj/6Gq\nZzVHRxOR3+iOjfmQIUMAtCyiiIiIg1ksFg4mf4vJbGTD6fX0qt+b97t/RMfanTW8VKQMuWNjHhQU\nBEDHjh3tFkZERER+lJGbwcpjyzCZjaTnXGdcYDhfdvoWXy9fR0cTkRJwx8b8B9u3b+ejjz7i4sWL\n5OXlAbcnfx44cKDEw4mIiJRH8almTOYIVh1fTueArrzZaRrd6/XExeDi6GgiUoJsNubTp0/nk08+\noVmzZri46IQgIiJSErLzsll3cjVR5ggu3DjPmFah7HxyLwGV6jg6mojYic3GvFatWjRt2lRNuYiI\nSAk4lXYCkzmSpUcX0sa3Hb9v90f6NuiPm4vNX9EiUsbY/Fc/efJkJk6cSMeOHXF3dwduD2XRpFAR\nEZF7k5ufy6YzGzCZjcSnHmZUizFsGL6NhlUbOTqaiDiQzcb8ww8/xNvbm1u3bpGbm2uPTCIiImXS\nhRvnmR8fxYKEGBpVa0xoYDghjR7H09XT0dFExAnYbMxTUlKIjIy0RxYREZEyJ78gnx3nt2IyG/n6\n8lcMbzaSZY+voUWNlo6OJiJOxubA8W7durFr1657PkB+fj5Dhgwp3KgoLS2NsLAw+vXrR3h4OOnp\n6YXPnT17Nn379qV///7s3r37no8pIiLiaMlZyXz47ft0XNCOf309neCGAzkwLp7pj/5bTbmIWGXz\nivmiRYswGo24u7vj5nb76XezXGJ0dDSNGzcmMzMTgDlz5vDII48wceJE5syZw5w5c5g8eTInucc2\nyAAAIABJREFUTpxgw4YNxMbGkpSURFhYGJs3b9akUxERKTUsFgt7Lu3CFGdk54XtDGo0mHn9TLTz\ne9DR0USkFLDZmB88ePCe3zwxMZHPP/+c5557jqioKOD2uujz588HYOjQoYwdO5bJkyezbds2QkJC\ncHd3p27dutSvX59Dhw7Rrl27ez6+iIiIPVzLvsrSo4swmY24ubgRGjiB97t/SBXPqo6OJiKlSImu\nxTR9+nRee+01MjIyCu9LTU3Fx8cHAB8fH1JTUwFITk6mbdu2hc+rVasWSUlJJRlPRETknlksFr5N\n+gaT2cjG07H0eaAfH/T4hI61OmEwGBwdT0RKoRJrzHfs2EHNmjVp1aoV+/bts/ocg8HwqycvndhE\nRMTZZOTcYMXxZZjMRjJybjAuMJxpj7yDT0UfR0cTkVKuxBrzgwcPsn37dj7//HNycnLIyMhgypQp\n1KxZk5SUFHx9fUlOTqZGjRoA+Pv7k5iYWPj6xMRE/P39f/G+Hh5uuLlp3LkU5e7uipeXh6NjiJNR\nXYg191oXcSmHmfvdHFYeXc6j9R5jevfpdH+gJy4G/U4qC3S+EGdgsFgsFltPys/P58qVK+Tn5xfe\nFxAQUOyDfP311xiNRmbNmsW//vUvqlWrxqRJk5gzZw7p6emFkz9fffVVli1bVjj5c8uWLb+4ap6S\ncuMuvj0pL7y8PMjKynF0DHEyqgux5m7q4mbeTdaeWIXJbORSxkXGtArl6ZbjqF2p+L8DpXTQ+UKs\n8fWtbNfj2bxiHhMTwyeffELNmjVxdXUtvH/dunX3dMBJkybx8ssvs2LFCurUqcPMmTMBaNKkCcHB\nwYSEhODq6sq0adM0lEVERBziZNpxTOZIlh1dRFu/9vzhwVfo80A/3FxKdGqWiJRzNq+Y9+7dm2XL\nllG9enV7ZfpVumIu1uhKh1ijuhBr7lQXufm5bDy9HpPZSMLVeEa3GMuYVqE0qNrQASnF3nS+EGuc\n7op57dq1qVSpkj2yiIiI2N35G+eYHx/FgoQYmlRrSmhgOAMaDcLT1dPR0USknLHZmNetW5dx48bR\nvXt33N3dgdurpYSFhZV4OBERkZKQX5DP9nNbiDJHsD/xa0Y0H8XKx9fTrEZzR0cTkXLMZmMeEBBA\nQEAAubm55ObmYrFYNPZbRERKpaSsJJYdWoDxuwj8vPwIDZzA3L4mvNy9HB1NRKR4q7I4E40xF2s0\nNlCsUV0I3N4IaPfFLzCZjXx+YQdDmw9jTPPxtPHVztLyI50vxBqnGWP+zjvvMHXqVJ577jmrj8+a\nNavEQomIiPxWV7NTWXJkEdHxRjxcPAgNmsAH3T+iVnVfNWAi4pTu2JgPGTIEwOpYcg1lERERZ2Sx\nWNif9DUms5FNpzfQt0F/Zvb4lA61Oup3l4g4PQ1lkTJBH0GKNaqL8iMj5wbLjy3FZDaSlZdJaOAE\nnmw+mpoVa/7iuaoLsUZ1IdY4zVAWERERZ3f4yiFMcUbWnFzJo3Ue461H3uHRuo/hYnBxdDQRkbum\nxlxEREqVm3k3WXNiJSZzBImZiYxpFcquUfuo5V3b0dFERH6TYjfmN2/epGLFiiWZRURE5I5OXDuO\nyRzBsmOLedDvYV5+aAq96vfBzUXXmESkbLD5Wd+BAwcYMGAA/fv3ByAhIYG33nqrpHOJiIiQk5/D\nmhMrGbZmIINXB1PBrSKbn9jJwoHL6dcgWE25iJQpNs9o06dPZ968ebzwwgsAtGzZkm+++abEg4mI\nSPl1Lv0sMfFRLEyIoXmNFoQGhhPccCAerh6OjiYiUmKKdakhICCgyG1XV9cSCSMiIuVXfkE+W899\nhikuggPJ+xnRbBSrh2ygafVmjo4mImIXNhvzgIAAvv32WwBycnKIiYmhcePGJR5MRETKh6TMRBYk\nRBMTH0Ut71qEBk4gon8MFd00r0lEyheb65hfvXqVd999ly+//BKLxUKXLl2YOnUq1atXt1fGIrSO\nuVij9WfFGtWF8yqwFLDrwueYzEZ2XfycwY2HERoYRmvftiV+bNWFWKO6EGvsvY65NhiSMkEnVLFG\ndeF8rmansvjIQqLNRjxdKzA+aAJPNBtJZY8qdsuguhBrVBdijdNtMHT+/HliYmK4ePEi+fn5hffP\nmjWrRIOJiEjZYLFY+Cbxa6LM8/jszCb6NQjm416zeNi/AwaDwdHxRESchs3G/IUXXmDEiBH06NED\nF5fbqyvqRCoiIrbcyEln2bElmOKM3MrPJjRwAu90/Qc1KtR0dDQREadkszH39PRk3Lhx9sgiIiJl\nwOGU74kyR7D25Gq61e3OO13/Qdc63XRRR0TEBpuN+ZgxY/j444/p2rUrHh4/rh8bGBhYosFERKT0\nyMrNYs2JlZjMESRnJTO21Xh2j/oaf+9ajo4mIlJq2GzMT5w4wZo1a9i3b1+Rqx0xMTElGkxERJzf\nsatHiY43svzYEh7y/x1/evg1etXvi6uL9rsQEblbNhvzTZs2sW3btiJXy0VEpPzKyc8h9tRaTGYj\nJ9KO83TLsWwZ8QX1Ktd3dDQRkVLNZmPerFkz0tPT8fHxsUceERFxUmfTzxBjjmLRkfm0qNGS8KCJ\n9G8YgoerLtyIiNwPNhvz9PR0goODad26dZGr5louUUSk7MsryGPr2c+IMs/ju+QDjGj+FGuGbKRJ\n9aaOjiYiUubYbMz/8Ic/2COHiIg4kcsZl1iQEM38eBMBleoQGhhOZP8FVHSr6OhoIiJlls3GvGPH\njvbIISIiDlZgKeCLCzuJiotgz6VdDGkynPkhSwnyae3oaCIi5cIdG/NRo0axePFi2rdv/4vHDAYD\nBw4cKNFgIiJiH6k3U1l0ZD7RZiPe7pUYHzSBT3rNopKHfbeiFhEp7wwWi8Xi6BB3IyXlhqMjiBPy\n8vIgKyvH0THEyagu7sxisbAv8StMcRFsObuZ4IYhhAaG85D/78r8RkCqC7FGdSHW+Pra9wKFi60n\nTJkypVj3iYiI80u/dZ2Iw3PovqQzr+z4PW392vHNmO/5uNcsHq7Vocw35SIizszmGPPjx48XuZ2X\nl4fZbC6xQCIicv99n3wQk9nIulNr6F63J+8++i+6BDyqRlxExIncsTGfNWsWs2fP5tatW0XGmbu7\nuzNy5Ei7hBMRkXuXmZvJmhMrMZkjuHLzCmNbjWf3U9/g7+Xv6GgiImKFzTHm7733HpMnT7ZXHps0\nxlys0dhAsaa81sXRq0cwmSNYcWwpHWp3IjQwnB71euPq4uroaE6hvNaF/DrVhVhj7zHmmvwpZYJO\nqGJNeaqLW/m3iD21FpPZyMm0E4xpOY4xrcZTt3I9R0dzOuWpLqT4VBdijb0bc5tjzEVExHmduX6a\n6PhIFh9ZQMuagTzT+jn6NxiAu6u7o6OJiMhdUmMuIlLK5BXk8dmZTZjMERxK+Y6RzUezbugmGldr\n6uhoIiLyG9hszGfMmMETTzxB06Y64YuIONLljEvMTzAxP95E3cr1CA0MxxS8iApuFRwdTURE7gOb\njXnjxo35y1/+Ql5eHsOHD2fgwIFUrqzd4ERE7KHAUsDO89sxmY3svbSboU2fYGHIcgJ9ghwdTURE\n7rNiT/48efIkq1atYv369Tz00EOMGDGCTp06lXS+X9DkT7FGk3bEmtJcF1duXmHRkflEm41U9qjC\n+MAJDGv6BJU8dGHktyrNdSElR3Uh1jjl5M/8/HxOnz7NyZMnqVGjBs2bNycqKorFixczc+bMks4o\nIlIuWCwW9l3eS5R5HlvPbmFAo4HM7mOkvd9D2ghIRKQcsNmYT58+nR07dtCpUyeef/552rRpU/hY\nv3797vi6W7duMWbMGHJycsjNzaVXr168+uqrpKWl8corr3Dp0iXq1KnDzJkzqVKlCgCzZ89mxYoV\nuLi4MHXqVLp27XofvkUREed2/VYay44uxmQ2UmApIDQwnH88+j7VKlR3dDQREbGjX23MLRYLVapU\nYc2aNXh5ef3i8WXLlt3xtZ6enkRHR1OxYkXy8vIYPXo0+/fvZ/v27TzyyCNMnDiROXPmMGfOHCZP\nnsyJEyfYsGEDsbGxJCUlERYWxubNm3Fxcfnt36WIiBP6LvkAJrOR9afW0qNeT/7Z7QM6B3TR1XER\nkXLKZte7adMmq005UHil+04qVqwIQG5uLvn5+VStWpXt27czdOhQAIYOHcrWrVsB2LZtGyEhIbi7\nu1O3bl3q16/PoUOH7uqbERFxdpm5mcyPN9Fn2WM8szmUhlUbseep/czpG8UjdbqqKRcRKcd+9Yq5\nwWAgMDCQQ4cOFRnCUlwFBQUMHTqUc+fO8dRTT9G0aVNSU1Px8fEBwMfHh9TUVACSk5Np27Zt4Wtr\n1apFUlLSXR9TRMQZJaTGEx1vZOWxZXSs3ZnXO7xJ93q9cHVxdXQ0ERFxEjbHmH/33XesXbuWgICA\nIlfO161bZ/PNXVxcWLNmDTdu3GDChAl89dVXRR43GAy/enXI2mMeHm64uWl4ixTl7u6Kl5eHo2OI\nk3F0XdzKu8XqYyuZ9/1czlw/Q2jr8ewN/Zq6Veo5LJM4vi7EOakuxBnYbMwjIiJ+80EqV67MY489\nhtlspmbNmqSkpODr60tycjI1atQAwN/fn8TExMLXJCYm4u/v/4v3ysnJI0erGcnPaJkrscZRdXHq\n+klizFEsObqAwJqtmRj0Av0aBOPu6g6gWnUwnS/EGtWFWOPt7WnX49m89Fy3bl0SExPZt28fdevW\nxcvLi+IsfX716lXS09MByM7O5ssvv6RVq1b07NmTVatWAbB69Wp69+4NQM+ePYmNjSUnJ4fz589z\n9uzZexo+IyLiCHkFecSeWsfIdUMIWdEbCxbWD/2MZY+vYWDjxwubchERkTuxecX8448/xmw2c/r0\naYYPH05ubi5Tpkxh8eLFv/q6lJQUXn/9dQoKCigoKGDw4MF07tyZli1b8vLLL7NixYrC5RIBmjRp\nQnBwMCEhIbi6ujJt2jRNghIRp3fxxgXmJ5hYkBDNA1UaEBoYTnTwYiq4VXB0NBERKWVs7vz5+OOP\ns3r1aoYNG8bq1asBGDRoULHGmJcE7fwp1ugjSLGmpOqiwFLAzvPbiDIb+erSHoY1HcG4wHBa1Qy8\n78eS+0/nC7FGdSHWON3Onx4eHkXWEs/KyirRQCIiziolK4VFR+YTHR9JNc9qjA+cwKe951LJvZKj\no4mISBlgszHv378/f/3rX0lPT2fJkiWsWLGCESNG2CObiIjDWSwW9l7ag8kcwfbz2whpOIi5fSJp\n5/eghtuJiMh9ZXMoC8Du3bvZs2cPAF27dqVLly4lHuxONJRFrNFHkGLNb6mLtOxrLDu2GJPZCMD4\nwAmMaD6Kqp7V7mdEcQCdL8Qa1YVYY++hLMVqzJ2JGnOxRidUseZu68JisXAw+VtMZiOxp9bR+4E+\nhAZOoFPtR3R1vAzR+UKsUV2INU43xrx9+/aFX+fm5pKXl4eXlxcHDhwo0WAiIvaSkZvBquPLMZmN\npN1KY1yrMPaOPoCvl6+jo4mISDliszE/ePBg4dcFBQVs376d7777rkRDiYjYQ3yqGZM5glXHl9M5\noCtvdPwr3ev1xMWg3YVFRMT+7uq3j4uLC71792bXrl0llUdEpERl52Wz7OhiBq7sy6j1w6hZwYed\nT+7FFLyQnvV7qykXERGHsXnFfPPmzYVfFxQUYDabqVBBG2eISOlyKu0E0fFRLD26kCCfNjzf7g/0\naxCMm4vN06CIiIhd2PyNtGPHjsJJT66urtSpU4dPP/20xIOJiPxWufm5rDu5BpPZSHzqYUa1GEPs\nsK00rNrI0dFERER+QauySJmg2fTyUxdvXCAmIYqFCTE0qNKQ0MBwBjYejKerp6OjiRPQ+UKsUV2I\nNU63Ksvf//53DAYDP/TvP/966tSpJZtQRKQY8gvy2Xl+G1HmCPZd3svwZiNZOyKWBl5NHB1NRESk\nWGw25rdu3eLkyZMMGDAAi8XCpk2baNKkSZFlFEVEHCU5K5lFCTHExEdRo0INQgMnMKuPEW93b10B\nExGRUsVmY3706FEWLlyIu7s7AE899RSjR4/mb3/7W4mHExGxxmKx8OWl3UTFRbDj/DYGNR7MvH4m\n2vk96OhoIiIi98xmY56enk5GRgbVq1cHIDMzk/T09BIPJiLycxk5N1h6bDFRcfMosBQwPnAC73Wf\nSVXPao6OJiIi8pvZbMwnTZrEsGHD6NixIxaLhW+++YYXX3zRHtlERAA4evUIkXFzWXl8GV3rPMb0\nR/9Nl4BHC1eMEhERKQuKtSpLcnIyhw4dAqBNmzb4+fmVeLA70aosYo3GEpc9ufm5bDoTi/HwXI6n\nHWNMq1DGtQojoFKdYr+H6kKsUV2INaoLscbpVmUB8PPzo3fv3iWdRUSEpMxEYuKjiImPon6VBwgP\nmkhIo8fxcPVwdDQREZESpS3vRMThLBYLX13+ksi4uew4v53BjYexMGQ5gT5Bjo4mIiJiN2rMRcRh\nMnIzWH50CZFx88gtyCEs6Bnee+xDqnhWdXQ0ERERuytWY75//37Onj3L8OHDuXr1KpmZmdSrV6+k\ns4lIGXX82jEi4+ay/NgSOgd05W9dptOtbndN5hQRkXLNZmP+8ccfYzabOX36NMOHDyc3N5cpU6aw\nePFie+QTkTIiryCPTac3EGmex5HUeMa0GseOkV9Sp3JdR0cTERFxCjYb8y1btrB69WqGDRsGgL+/\nP5mZmSUeTETKhuSsZObHRxFtjqRO5bqEB01kYOPBeLp6OjqaiIiIU7HZmHt4eODi4lJ4Oysrq0QD\niUjpZ7FY+DpxH5Fxc9h2biuPNx5CTMgSWvu0cXQ0ERERp2WzMe/fvz9//etfSU9PZ8mSJaxYsYIR\nI0bYI5uIlDKZuZmsOLaUyLh53MzLIizoGf7Z7QPtzCkiIlIMxdpgaPfu3ezZsweArl270qVLlxIP\ndifaYEis0cYQjnUy7TiRcfNYdnQxHWt3JixoIo/V64GLwcX2i0uQ6kKsUV2INaoLscbeGwwVqzF3\nJmrMxRqdUO0vryCPLWc3Yzw8B3NqHE+3HMe4wDDqVa7v6GiFVBdijepCrFFdiDVOt/Nn+/btf3Ff\n5cqVad26Na+//rqWTRQpZ1KyUliQYCLaHIm/dy3CgybyeJOhmswpIiLyG9lszMeNG0ft2rUZOHAg\nALGxsZw7d45WrVrxxhtvEBMTU+IhRcSxLBYL+5O+xnh4LlvPfUZIw0FEBS+gjW87R0cTEREpM2w2\n5tu3b2fdunWFt5988kkGDx7MlClTmD17domGExHHysrNYtXx5Rjj5nIjJ52woIlMf/RfVK9Qw9HR\nREREyhybjXnFihXZsGED/fv3B2DTpk14et7+yFq79ImUTaeunyQqLoKlRxfysH8H3uz0V7rX6+Xw\nyZwiIiJlmc3Jn+fOnePdd9/lu+++A6Bdu3a88cYb+Pv7ExcXx8MPP2yXoD/Q5E+xRpN2frv8gny2\nnvsM4+E5HL7yPaNajCE0MJwHqjRwdLR7proQa1QXYo3qQqzRqiw2qDEXa3RCvXepN1NZkBBNtNmI\nT0UfwoImMrjJMCq4VXB0tN9MdSHWqC7EGtWFWON0q7JkZ2ezfPlyTpw4wa1btwrvnzFjRokGE5GS\nY7FYOJC8n8i4eWw+s5HghiHM62eind+Djo4mIiJSbtkcMPraa69x5coVdu3aRYcOHUhMTMTb29se\n2UTkPruZd5NFCfPpu7w7z26ZQIsardj39EE+6vk/NeUiIiIOZvOK+dmzZ/noo4/Ytm0bQ4cOZeDA\ngYwePdoe2UTkPjlz/TRR5giWHFlAe7+HeO13f6Zn/T64urg6OpqIiIj8H5uNubu7O3B7U6GjR4/i\n6+vL1atXSzyYiPw2BZYCtp/bgvHwXA4mf8uTLZ5mw/BtNKzayNHRRERExAqbjfmTTz5JWloaL7/8\nMs8//zxZWVn88Y9/tEc2EbkHV7NTWZgwnyhzBNU9qxMeNJGI/jFUdKvo6GgiIiLyK361MS8oKMDb\n25tq1arRoUMHtm/fbq9cInKXvks+gDFuLhtPx9KvQTBz+hhp7/eQ9hsQEREpJX518qeLiwvz5s27\n5ze/fPkyY8eOJSQkhIEDBxIdHQ1AWloaYWFh9OvXj/DwcNLT0wtfM3v2bPr27Uv//v3ZvXv3PR9b\npDzIzstm8ZEF9F/egwmbx9GkWjO+Gn2QT3rN5kH/h9WUi4iIlCI21zF/7733qF69OgMGDKBixR8/\nCq9WrZrNN09JSeHKlSu0bNmSzMxMhg0bxqeffsqKFSuoXr06EydOZM6cOaSnpzN58mROnDjBq6++\nyvLly0lKSiIsLIzNmzfj4uLyk/fUOubyS+Vt/dmz6WcwmY0sPjKf1j5tCW89id71+2oy58+Ut7qQ\n4lFdiDWqC7HG6dYx37BhAwALFiwocn9xhrX4+vri6+sLgLe3N40bNyYpKYnt27czf/58AIYOHcrY\nsWOZPHky27ZtIyQkBHd3d+rWrUv9+vU5dOgQ7dq1u+tvTKSsKbAUsPP8NoyH57I/6WtGNh/N+mFb\naFS1saOjiYiIyH1gszG/X+PKL1y4QEJCAm3atCE1NRUfHx8AfHx8SE1NBSA5OZm2bdsWvqZWrVok\nJSXdl+OLlFbXsq+y6MgCouLmUdmjCuFBE5nTNwovdy9HRxMREZH7yGZjnpWVRWRkJJcvX+add97h\nzJkznD59mh49ehT7IJmZmbz00ku8+eabVKpUqchjBoPhV8fBaoyslFeHUr7DeHgusafX0bt+X/7b\new4P+3fQvwkREZEyymZj/uc//5nAwEAOHjwIgJ+fHy+99FKxG/Pc3FxeeuklHn/8cXr37g1AzZo1\nSUlJwdfXl+TkZGrUqAGAv78/iYmJha9NTEzE39+/yPt5eLjh5mZzw1IpZ9zdXfHy8nB0jN/sVt4t\nVh1bwZyDs7mccYkJ7SbyTo9D+Hn7OTpaqVRW6kLuL9WFWKO6EGdgszE/f/48H374YeFYcy+v4n98\nbrFYePPNN2ncuDHjx48vvL9nz56sWrWKSZMmsXr16sKGvWfPnrz66quMHz+epKQkzp49S5s2bYq8\nZ05OHjmamyE/U9on7Zy/cQ5TnJGFR2IIrBnE79u9TJ8H+uHmcvufaGn+3hyptNeFlAzVhVijuhBr\nvL097Xo8m425h4cH2dnZhbfPnTuHh0fx/qL89ttvWbt2Lc2bN2fIkCEA/OlPf2LSpEm8/PLLrFix\ngjp16jBz5kwAmjRpQnBwMCEhIbi6ujJt2jR9bC9lVoGlgM/P7yAybi77Lu9lRPNRrBu6icbVmjo6\nmoiIiDiAzeUSd+/ezaxZszhx4gRdunThwIEDzJgxg06dOtkrYxFaLlGsKU1XOq7fSmPxkQVExs2j\nopsX4a0nMqzpCLzdvR0drcwpTXUh9qO6EGtUF2KNvZdLtNmYA1y9epXvv/8egLZt2xaOCXcENeZi\nTWk4oR6+cojIw3NZd2oNver3JixoEh1qddSnQiWoNNSF2J/qQqxRXYg1TreO+XPPPUdISAi9evW6\nq/HlIgI5+TmsO7kaY9xcLt64wLjAMPY8tR8/L03mFBERkaJsNuZhYWFs2LCBDz74gNatWzNgwAB6\n9OiBp6d9B8OLlCYXb1wgOt7I/PhoWtRsxQvtXqJfg+DCyZwiIiIiP1esoSwAeXl57Nu3j6VLl7Jr\n1y4OHDhQ0tms0lAWscYZPoK0WCx8cWEnkXHz2HtpN8ObjSQsaCJNqzdzaK7yzBnqQpyP6kKsUV2I\nNU43lAUgOzub7du3s3HjRsxmM0OHDi3pXCKlRvqt6yw5upDIuHm4u7gTFjSRT3rPppJ7JdsvFhER\nEfk/NhvzP/7xjxw6dIhHH32Up59+mg4dOuDiog1+ROJTzRgPz2XNyZX0qNeTD7p/TMfanTWZU0RE\nRO6JzcZ8+PDhfPDBB7i6ugKwf/9+YmNjmTZtWomHE3E2Ofk5bDi1DmPcXM6kn2ZcqzB2j/oaf+9a\njo4mIiIipZzNxrxbt26YzWbWr1/Ppk2bqFu3Ln379rVHNhGncTnjEqZ4I/PjTTSr3pyJbZ6jf4MQ\n3F3dHR1NREREyog7NuanTp0iNjaWDRs2UKNGDfr374/FYiEmJsae+UQcxmKxsOfSLoyH57L74ucM\nazqCFY+vo3mNFo6OJiIiImXQHRvzAQMG0L17dyIiIggICAAgMjLSbsFEHOVGTjpLjy4mKm4eAGGt\nJ/JRz0+p5GHfmdkiIiJSvtyxMf/kk09Yv349Y8aMoWvXrgQHB9szl4jdHbmagPHwHFafWEG3uj34\nR7f3eSSgqyZzioiIiF3YXMc8MzOTbdu2ERsby759+xg8eDB9+vSha9eu9spYhNYxF2vudf3Z3Pxc\nNp5ejzFuLifTTjC21XjGBYZRy7t2CaQUe9O6xGKN6kKsUV2INfZex7zYGwwBpKWlsXnzZmJjY4mO\nji7JXHekxlysudsTamLmZWLio4iJj6Jh1UaEB01kQMNBmsxZxugXrVijuhBrVBdijVM35s5AjblY\nU5wTqsViYe+lPRjj5vLFhR0MaTKc8UHP0KpmoJ1Sir3pF61Yo7oQa1QXYo1T7vwpUppl5Nxg2bEl\nRMXNI68gj/DWE/lPj4+p7FHF0dFERERECqkxlzLr2NWjGOPmsPL4MrrU6cY7Xf9J1zrdNJlTRERE\nnJIacylT8gry2Hg6lsi4uRy7dpQxLcex88m9BFSq4+hoIiIiIr9KjbmUCUmZicz5di7R5kjqV3mA\n8KCJhDR6HA9XD0dHExERESkWNeZSalksFvZd3osxbg47z29nUOOhLAhZRpBPa0dHExEREblrasyl\n1MnIzWDFsaVExs3jVn42YYHP8En/T/Eo8HJ0NBEREZF7psZcSo0T144TGTeX5ceW0CmgC28/8i6P\n1n0MF4MLXhW0zJWIiIiUbmrMxanlFeSx+cxGIuPmkZBq5umW49g2cjd1K9dzdDQRERHS1nIeAAAa\np0lEQVSR+0qNuTil5KxkFsSbiI6PJKBSHcKCnmFQ4yF4uno6OpqIiIhIiVBjLk7DYrHwTeLXGOPm\nsO3cFgY1Gkx08CJa+7Z1dDQRERGREqfGXBwuMzeTlceXERk3j8zcDMKCnuEfj75HtQrVHR1NRERE\nxG7UmIvDnEo7QWTcPJYdW0yHWp2Y2uktutfriYvBxdHRREREROxOjbnYVX5BPlvObsYYN4e4K4cY\n3WIcnz3xOfWrPODoaCIiIiIOpcZc7OLKzSssTIjGZDbi5+VHWNBEooMXU8GtgqOjiYiIiDgFNeZS\nYiwWC98mfYMxbi5bzm4mpOEgjP1iaOvX3tHRRERERJyOGnO577Jys1h9YgXGuLlcv5VGWNBE3u36\nT6pXqOHoaCIiIiJOS4253Denrp/EFGdk6dGFPOj/MH/uMJUe9XtrMqeIiIhIMagxl98kvyCfbec+\nwxg3l0Mp3zGqxRg2PbGDB6o0cHQ0ERERkVJFjbnck+y8bJYcXcin331ENc9qhAVNJLL/Aiq6VXR0\nNBEREZFSSY253JXrt9KIiotg7uFZtPVtx4c9/0en2p0dHUtERESk1FNjLsWSmHmZ2d9/ysKEaHo/\n0I9lg9bQsmYrR8cSERERKTPUmMuvOpl2nP8e/Ij1p9Ywotkoto7cRb3K9R0dS0RERKTMUWMuVh1I\n2s/HB2ey7/KXjA98hr2jD1KzYk1HxxIREREps9SYSyGLxcKO89v45OBMzlw/zfPtXuSTXrPxdvd2\ndDQRERGRMk+NuZBXkMe6k6v5+OBM8gvy+H37PzK0yRO4u7o7OpqIiIhIuVGijfmf//xnPv/8c2rW\nrMm6desASEtL45VXXuHSpUvUqVPn/7d372FRlnkfwL/PwICiYB44VOTmuTIxXQpTV1fkoIEgKbXt\nXmaWWu/7XhHpppWapqtu66YdNBW9bDOrtTzQa9raqyjkCXE1KLU2ywQPgKFykMOcfu8fA8MMDMj5\nmWG+n+uaa577fu7nvn9zz+3Mj8dnZvDWW2/Bx8cHALB+/Xps374dGo0G8+fPx8iRI1szPJdXZijD\nJ99vwXvfvIvbO92OVx6aj7DfREJRFLVDIyIiInI5rfqTjJMmTcLGjRtt6pKSkjB8+HDs3bsXw4YN\nQ1JSEgDg3Llz2LNnD3bv3o2NGzfi9ddfh8lkas3wXNaN8utYdWIFgj8chIPZ+/He2A3YFbcX4XeP\nY1JOREREpJJWTcyDg4MtZ8OrpKSkIC4uDgAQFxeHffv2AQD279+PqKgoaLVaBAYGomfPnsjKymrN\n8FzO5ZJLeO3wq3joo8H4ufAnbI/dhc2P/BMP3R6idmhERERELq/NrzEvKChAjx49AAA9evRAQUEB\nACA/Px+DBw+2tAsICEBeXl5bh9cu/efaD1jzzdv48vwXeHzAH3HgsSO40ztQ7bCIiIiIyIqqH/5U\nFKXeSyd4WUXznMg9jndPvYWM3HQ8M2gm0v/0Dbp26KZ2WERERERkR5sn5t27d8fVq1fh6+uL/Px8\ndOtmThT9/f2Rm5traZebmwt/f/9ax3t4uMPdvVWvwHFqIoKvzu/FyuN/x8WiHDwfnIgPYjbDS+ul\ndmitSqt1g5eXh9phkIPhuiB7uC7IHq4LcgRtnpiHhoZi586dmDlzJpKTkxEWFmapnz17Np566ink\n5eXhwoULCAoKqnW8TmeATtfWUTs+g8mA5HPbsfrU2xARJAx9EbF9H4W7xh3QA6X69j1pXl4eKC1t\n34+RGo/rguzhuiB7uC7Ink6dPNt0vFZNzGfNmoXjx4/jxo0bGD16NBISEjBz5kwkJiZi+/btlq9L\nBIC+ffti/PjxiIqKgpubGxYuXMhLWRqgVF+Kj89uxtrM1bjLuycWDFuE0J7hnDsiIiIiJ6OIiKgd\nRGNcvVqsdggO4Vp5ATZ9uwGbvtuABwNC8PyQRAQHPKR2WKrhmQ6yh+uC7OG6IHu4LsgeX1/vNh2P\nv/zpZC4VX8S6zNXY+sPHGN8rGsmxe9C/2wC1wyIiIiKiZmJi7iS+v3YWq0+9ha9++RJP3DMFBx8/\nijs636l2WERERETUQpiYO7j0K8ew+tQqnMz7N6YPehbH/5SJ2zp0VTssIiIiImphTMwdkElM2Hdh\nL945uQq5pbn47weeR1LEP9DRvaPaoRERERFRK2Fi7kD0Rj12/PgZ1nzzNtw1Wjw/JBET+kw0f+Uh\nEREREbVrzPgcwE39TXx05gOsy1yDu7v0wqLhSzHmrrH8ykMiIiIiF8LEXEUFZQXY+O06/OO7jRh2\nxwhsjPwAQ/2D1Q6LiIiIiFTAxFwFOcXZWPvNu9j2n62I7h2LXXFfoW/XfmqHRUREREQqYmLehs4U\nnMa7J1chJfv/8Md7n0TaH9IR0Ol2tcMiIiIiIgfAxLyViQjSrxzFOydXIuvXTMwY9Bz+Ourv6OJ5\nm9qhEREREZEDYWLeSkxiwt5fvsS7J1fh17Kr+J8hL2DTuC3o4N5B7dCIiIiIyAExMW9hOqMOO378\nDKtPvYUO7h3x/JBERPeOhZvGTe3QiIiIiMiBMTFvIaX6UnxwehPWZ65Bn679sHTk3zAq8Pf8ykMi\nIiIiahAm5s0kIvjy/G4sOPwyBvUYjH+M/wgP+A1VOywiIiIicjJMzJvhfOHPmPf1HFwo+gWrxqzG\nqMDfqx0SERERETkpjdoBOKMyQxn+dnwZxm8PxbA7RuDA40eYlBMRERFRs/CMeSPtu7AXr3z9Egb1\nGIx98V8j0PsutUMiIiIionaAiXkDZRddwPzDL+OHa2fxxqg3EdozXO2QiIiIiKgd4aUst1BhrMCq\nEysQ/tkoPOA7BKmPH2NSTkREREQtjmfM63EwJwWvfP1n9LutP76KT8VvfO5WOyQiIiIiaqeYmNtx\nueQSXjv8Kr65egrLRr6BiLvHqx0SEREREbVzvJTFit6ox+pTbyP00xHo27Ufvv5DOpNyIiIiImoT\nPGNe6fClr/Fy2mzc6R2IPZP2o3eXPmqHREREREQuxOUT87ybuVh4ZB6OXzmGJSP/ikd6RUNRFLXD\nIiIiIiIX47KXshhMBqzPXIPRW4chsPNd+PqJ44jqPYFJORERERGpwiXPmKdfOYa5abPQvUN37Ir7\nCv269lc7JCIiIiJycS6VmF8tvYrFRxcg7eJBvD58KWL7Psoz5ERERETkEFziUhaTmPDB6U0YvTUE\n3Tp0x+EnMjCx3yQm5URERETkMNr9GfOzBWfw59QXICLYFrML93UfqHZIRERERES1tNvEvMxQhlUn\nVuDDM+9j7kPz8eTAadAoLvEfBERERETkhNplYp6acwAvpSYiyPcBHHz8KPw7BagdEhERERFRvdpV\nYv5r2a947fArSL9yFH/93d8Rfvc4tUMiIiIiImqQdnFth4jgk7NbMOqfIfDt6Ie0P6QzKSciIiIi\np9IuzpgvOPwy0q8cw9boHRjkO1jtcIiIiIiIGs3pE/OCsgJs/eETHHni3/D18lU7HCIiIiKiJnH6\nS1k+PPM+HukVzaSciIiIiJyaU58x1xv1eP+7jfgo6jO1QyEiIiIiahanPmO+6+dk9O7SB/f3GKR2\nKEREREREzeLUifmGrLWYEfRfaodBRERERNRsDncpS1paGpYtWwaTyYTJkydj5syZdtudyD2Oq2W/\nIvLu8W0cIREREVH7J1J3ub59jS235LE1NacvNzfAt40/wuhQibnRaMSSJUvw/vvvw9/fH5MnT8bY\nsWPRp0+fWm03ZK3F9EEz4aZxUyFSInWZTOab0Vh9L2JdVixtrNtVl5U6jgNMJqWe48z77R9XdVPq\nievW/Tcmdmv2Xmzd3DQwGjV17q/v2KaWb/0moTS5r7Z846uptd5Ea5cbPj/1xVhfWaNRYDK5q7gG\nmt5Xc+bLedZA0+Ns/nx5tEhcbbsGmtOX7Xw0hKKI1XbNfU0vN7ev1ohDqxVcvVr3OK3BoRLzrKws\n9OzZE4GBgQCAqKgo7N+/v1Zi/tONH3EgZz9WjH6rwX2XlACFhQq0WsDDQ+DhAXh4mP8aqu/JdWUi\ndSdHNZMkNRJA677d3TUoL9fWaKPYlFsyeTWXlXpjrz95Vuo4rnZyW7MPk8m8YN3cBBqNeQ1rNNU3\nc1lqlGvvr1r7Vftt20kdx5nHrXmcbVnsHlddllrHubtbtzPV07ftY9PUuBiv5r9lT0936HSGOvc3\n5k2hpua9wcgt9jemr/rLzTm2teJq/NzWPV9NiaNDBy3Ky/XN7qumlnzeWms91eQoa+CWMVdllJX3\nimJ/GwAU2GaiVX1V1SuK2G3fsYMW5eW6Osepr29U9W2nTa1jbfpG7f01+66x3eC46thf3zj2+r7V\ndl2P17q6Mf3ZbDfyuLpjaeI4Wi2A36EtOVRinpeXh9tvv91S9vf3R1ZWlk2bKyWX8fgXk7Dg4cXw\n0btB8/NZGH7KRsn5ApRcKkbZlULofy2G8XoRNIWFcC8tRIeyQnhLIfyUMuighR5alIgWFeIBPbQw\nKloYNFoYNe4waDxg0mhhdNPCZHUTdy1M7lqImxaiNZfhoTVnFOZsH4q7G4wCiGhgrEyeTKLAKApE\nFJhEgUlg2TaaFHPya9lXXScw92ESc9loUmCCYk74xOq+6mYCjJZ6WNoYTQoE5nuTCZYxzPea6r6t\nxjZWHmeq/AiCxg1QFAWKRgEUBRoNoGiqypUJkiJwr0rYNAKNIuZ7jfleQWWiV1WviOU4N41A0QBu\nSvVx5n5MtdvBumze76YAHloNPE1Gc2yoGsNkaatRzH1qNAINKssasYxpPq66rUYDKO4maFD9mMxj\nS+12Vf1ZxaZAoFS1qbwBNWKpaofqfszHmN84NJXlqvFs9kNsX1DETrlq26YtoDT0OOuynfFq9WPZ\nRnXZKOZbHePdMpY6x7caA1aPCbb1bhoFRqOpVn3dp5Ba4I2h0W9ADYyjObE0to9Gj9+EmJozfjPm\nBCKVZ8ylnlgaGEdzthsyJ80av2nHKU0dv4Xmx3Z8+6SuDL8ltuv866F6u3njN/E42K+/ZSwtNT+w\n8xis2rTZc1LHPDRqTmpt17PfXQukH0VbcqjEXGnAqesLkYPxvwW++E3hIngY5yJH6YkcpSeKOvjB\n5O0DdO0CbXd/eAb1h9cdPvC6ywdde3mj851dgI4d4KnXQzEYAL0eikEPU4UehlI9DGV6GMoMMJbr\nYSzTwVhugLHcAFOFHqYKA0zlOojOvC06PaRCB+grIHo9oNMDNw1QjAZL8lQrmYIAlQmVdcKlVCaI\nmsoEDQos2wqq/pKV6uNs6kyVf52jur1VPwpMUARW5cr9lcmaUlVXVUb1WFV1QOULpd0ErvLe8rwp\ntv+QlOqyKHXvM99b70PtttZ92OnHfMmC1DuGKIr5IVXViVXZVE9sNfuoY1/txw+7fdrvo44+6ylL\nzTHszf8txpdGjV/7eRHrcs0+GhBL7T5qj9GgfmD/xdjTwx0VOmOt+kZv23sRb2AfNnHd6k2lqfE1\nYFtuNXaN8FpmruqYkwbF0tJzVb3ZoaOn5czoLWNpxeek5eYE9bdpZH9NjqU156oNeHl5oLRU12bj\nkXNo61/JcajE3N/fH1euXLGUc3Nz4e/vb9Nmwn/KbcoDKm9EDrWYyWF0UDsAckheagdADqlTJ0+1\nQyAX51Bfl3j//ffjwoULuHjxInQ6Hfbs2YOxY8eqHRYRERERUatzqJOM7u7uWLBgAZ555hnL1yXa\n+0YWIiIiIqL2RhFpwCctiIiIiIioVTnUpSy3kpaWhnHjxiEiIgJJSUlqh0NN9Morr2D48OGYMGGC\npe7GjRuYNm0aIiMj8fTTT6OoqMiyb/369YiIiMC4ceNw6NAhS/13332HCRMmICIiAn/5y18s9Tqd\nDomJiYiIiMBjjz2GS5cuWfbt3LkTkZGRiIyMRHJysqU+JycH8fHxiIiIwIsvvgi9Xt9aD5/suHLl\nCqZMmYKoqChER0dj8+bNALguXF1FRQXi4+MRGxuLRx55BG+++SYArgsyMxqNmDhxIp577jkAXBcE\nhIaGYsKECZg4cSImT54MwAnXhTgJg8EgYWFhkpOTIzqdTmJiYuTcuXNqh0VNkJGRIadPn5bo6GhL\n3RtvvCFJSUkiIrJ+/XpZsWKFiIj8+OOPEhMTIzqdTnJyciQsLExMJpOIiEyaNEkyMzNFRGT69OmS\nmpoqIiJbtmyRhQsXiojI7t27JTExUURErl+/LmPHjpXCwkIpLCyUsWPHSlFRkYiIJCQkyO7du0VE\n5LXXXpOPP/64lWeBrOXn58uZM2dERKSkpEQiIiLk3LlzXBckpaWlIiKi1+slPj5eMjIyuC5IREQ2\nbdoks2bNkmeffVZE+D5CImPGjJHr16/b1DnbunCaM+bWPz6k1WotPz5Ezic4OBg+Pj42dSkpKYiL\niwMAxMXFYd++fQCA/fv3IyoqClqtFoGBgejZsycyMzORn5+PmzdvIigoCAAwceJEyzHWfUVERODo\nUfN3kB46dAgjRoyAj48PfHx8MHz4cKSlpUFEkJ6ejnHjxtUan9qGr68v7r33XgBAp06d0KdPH+Tl\n5XFdEDp27AgA0Ov1MBqN6NKlC9cFITc3F6mpqYiPj7fUcV0QAEiNK7SdbV04TWJu78eH8vLyVIyI\nWlJBQQF69OgBAOjRowcKCgoAAPn5+QgICLC0CwgIQF5eXq16f39/5Ofn1zrG3d0d3t7euH79ep19\n3bhxAz4+PtBU/oykdV/U9i5evIizZ88iKCiI64JgMpkQGxuL4cOHIyQkBP369eO6ICxbtgxz5syx\nPA8A30cIUBQF06ZNw6OPPopPP/0UgPOtC4f6Vpb6NOTHh6h9UBSlzZ5vrivHcvPmTSQkJGDevHno\n3LmzzT6uC9ek0Wjw+eefo7i4GM888wyOHTtms5/rwvUcOHAA3bt3x3333Yf09HS7bbguXNMnn3wC\nPz8/XLt2DdOmTUPv3r1t9jvDunCaM+YN+fEhcl7du3fH1atXAZj/Iu3WrRsA8/Oem5traZebm4uA\ngAC79VXrwc/Pz7JWDAYDiouL0bVr1zrX0G233YaioiKYTCZLvZ+fX+s+YKpFr9cjISEBMTExCAsL\nA8B1QdW8vb0xevRonD59muvCxZ06dQopKSkIDQ3F7NmzcezYMbz00ktcF2SZ827duiE8PBxZWVlO\nty6cJjHnjw+1b6Ghodi5cycAIDk52ZKYhYaGYvfu3dDpdMjJycGFCxcQFBQEX19fdO7cGZmZmRAR\nfP7555b1YN3X3r178fDDDwMARowYgcOHD6OoqAiFhYU4fPgwRo4cCUVREBISgn/9618AzJ+srhqf\n2oaIYN68eejTpw+eeuopSz3XhWu7du2a5RsUysvLceTIEdx3331cFy5u1qxZSE1NRUpKClauXIlh\nw4ZhxYoVXBcurqysDCUlJQCA0tJSHDp0CP3793e+ddGUT72q5eDBgxIRESFhYWGybt06tcOhJnrx\nxRdlxIgRMnDgQBk1apRs27ZNrl+/LlOnTpWIiAiZNm2aFBYWWtqvXbtWwsLCJDIyUtLS0iz13377\nrURHR0tYWJgsWbLEUl9RUSEJCQkSHh4u8fHxkpOTY9m3bds2CQ8Pl/DwcNmxY4elPjs7WyZPnizh\n4eHywgsviE6na+VZIGsZGRkyYMAAiYmJkdjYWImNjZXU1FSuCxf3/fffy8SJEyUmJkaio6Nlw4YN\nIiJcF2SRnp5u+VYWrgvXlp2dLTExMRITEyNRUVGWPNHZ1gV/YIiIiIiIyAE4zaUsRERERETtGRNz\nIiIiIiIHwMSciIiIiMgBMDEnIiIiInIATMyJiIiIiBwAE3MiIiIiIgfAxJyIiIiIyAEwMSciolp2\n7NiBJUuWqB0GEZFLYWJORES1KIqidghERC7HXe0AiIhc2cWLFzFjxgwEBwfj1KlT8Pf3x3vvvQdP\nT89abTdv3oytW7fCzc0Nffv2xcqVK5GVlYVly5ahoqICnp6eWL58OXr16oUdO3Zg3759KC8vxy+/\n/IKnn34aFRUV+OKLL+Dh4YGkpCR06dIFU6ZMwT333IOMjAwYjUYsXboUQUFBNuNeu3YNixYtwuXL\nlwEAr776KoYOHYrjx49j2bJlAMyJ/JYtW9CpU6fWnzQionaKiTkRkcqys7OxatUqLFmyBImJidi7\ndy9iYmJqtduwYQNSUlKg1WpRUlICAOjduzc++ugjuLm54ciRI1i1ahXeeecdAMC5c+eQnJyM8vJy\nhIeHY86cOdi5cyeWL1+O5ORkTJ06FQBQUVGB5ORknDhxAvPmzcOuXbsgIpZxly5diqlTp+K3v/0t\nLl++jOnTp2PPnj3YtGkTFi5ciCFDhqCsrAweHh5tMFtERO0XE3MiIpUFBgbinnvuAQAMHDgQly5d\nsttuwIABmD17NsLCwhAWFgYAKC4uxty5c5GdnQ0AMBqNlvYhISHw8vKCl5cXfHx8MGbMGABA//79\n8cMPP1jaRUVFAQCCg4NRUlKC4uJim3GPHDmCn376yVK+efMmSktLMXToUCxfvhwTJkxAREQE/P39\nmzsVREQujYk5EZHKrM80u7m5oaKiwm67pKQkZGRk4MCBA1i3bh127dqFt99+Gw8//DDWrFmDS5cu\nYcqUKXb7VRTFUtZoNDYJfE01ry8XEXz66ae1zojPnDkTY8aMwcGDB/HEE09g48aN6N27d8MfOBER\n2eCHP4mInICI4PLlywgJCcHs2bNRXFyM0tJSlJSUwM/PD4D5m1Qa2pe1PXv2AABOnDgBb29vdO7c\n2Wb/iBEj8OGHH1rKZ8+eBWC+BKdfv36YMWMG7r//fpw/f77Jj4+IiHjGnIjIKRiNRsyZM8dymcmT\nTz4Jb29vTJ8+HXPnzsXatWsxevRoy9luRVFsznzX3LYue3p6Ii4uDgaDwebDnFVt5s+fj8WLFyMm\nJgZGoxEPPvggFi1ahM2bNyM9PR2KoqBfv34YNWpUq88DEVF7pkjNUydEROQypkyZgpdffhkDBw5U\nOxQiIpfHS1mIiIiIiBwAz5gTETmYxYsX4+TJkzZ1U6dORVxcnEoRERFRW2BiTkRERETkAHgpCxER\nERGRA2BiTkRERETkAJiYExERERE5ACbmREREREQOgIk5EREREZED+H9GW273poliKgAAAABJRU5E\nrkJggg==\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7fc733263668>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.set_style(\"darkgrid\")\n",
    "f = plt.figure(figsize=(12, 6))\n",
    "plt.ticklabel_format(style = 'plain')\n",
    "ax=plot_df.plot(kind='line',ax=f.gca(),color=['b', 'g', 'r'])\n",
    "ax.set_title('Comparision of spatial radius search runtimes Brute Force vs. Ball Tree Based ')\n",
    "ax.set_xlabel('n_samples')\n",
    "ax.set_ylabel('Average query time in milliseconds')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "plot_df_2 =pd.DataFrame({'BallTree(metric=haversine,radius=100m)':run_times_agg_ball_tree,\n",
    "                       'GeoHash(precision=5,radius=100m)':run_times_agg_geohash})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAtkAAAGKCAYAAADZv11aAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nERERUZIxZBMRERERJRlDNhERERFRkv0P678siWpT53IAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7fc732907cc0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.set_style(\"darkgrid\")\n",
    "f = plt.figure(figsize=(12, 6))\n",
    "plt.ticklabel_format(style = 'plain')\n",
    "ax=plot_df_2.plot(kind='line',ax=f.gca(),color=['b','r'])\n",
    "ax.set_title('Comparision of spatial radius search runtimes Brute Force vs. Ball Tree Based ')\n",
    "ax.set_xlabel('n_samples')\n",
    "ax.set_ylabel('Average query time in milliseconds')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "### Plot training times"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "plot_times_df_geohash =pd.DataFrame.from_dict(train_times_geohash,orient='index')\n",
    "plot_times_df_geohash.columns = ['training time geohash in s']\n",
    "plot_times_df_ball_tree =pd.DataFrame.from_dict(train_times_ball_tree,orient='index')\n",
    "plot_times_df_ball_tree.columns = ['training time ball tree in s']\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>training time geohash in s</th>\n",
       "      <th>training time ball tree in s</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1000</th>\n",
       "      <td>0.033796</td>\n",
       "      <td>0.000856</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2576</th>\n",
       "      <td>0.135452</td>\n",
       "      <td>0.002997</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6637</th>\n",
       "      <td>0.223490</td>\n",
       "      <td>0.018270</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17099</th>\n",
       "      <td>0.615888</td>\n",
       "      <td>0.050174</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>44054</th>\n",
       "      <td>1.686306</td>\n",
       "      <td>0.147784</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>113496</th>\n",
       "      <td>8.142963</td>\n",
       "      <td>1.109179</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>292401</th>\n",
       "      <td>13.064235</td>\n",
       "      <td>6.093690</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>753315</th>\n",
       "      <td>26.356323</td>\n",
       "      <td>5.152371</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1940766</th>\n",
       "      <td>33.848245</td>\n",
       "      <td>12.067148</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4999999</th>\n",
       "      <td>89.868351</td>\n",
       "      <td>26.844131</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         training time geohash in s  training time ball tree in s\n",
       "1000                       0.033796                      0.000856\n",
       "2576                       0.135452                      0.002997\n",
       "6637                       0.223490                      0.018270\n",
       "17099                      0.615888                      0.050174\n",
       "44054                      1.686306                      0.147784\n",
       "113496                     8.142963                      1.109179\n",
       "292401                    13.064235                      6.093690\n",
       "753315                    26.356323                      5.152371\n",
       "1940766                   33.848245                     12.067148\n",
       "4999999                   89.868351                     26.844131"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "plot_time_df =plot_times_df_geohash.join(plot_times_df_ball_tree).sort_index()\n",
    "plot_time_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAuAAAAGACAYAAADswtfOAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nHIgJOBERERGRAzEBJyIiIiJyoP8Po5Xc0+r+aj8AAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7fc7328f0978>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.set_style(\"darkgrid\")\n",
    "f = plt.figure(figsize=(12, 6))\n",
    "plt.ticklabel_format(style = 'plain')\n",
    "ax=plot_time_df =plot_times_df_geohash.join(plot_times_df_ball_tree).sort_index().plot(kind='line',sort_columns=True,ax=f.gca(),color=['r','b'])\n",
    "ax.set_xlabel('n_samples')\n",
    "ax.set_ylabel('Training time in Seconds for Ball Tree based indexing')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.4.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}