{"cells":[{"metadata":{},"cell_type":"markdown","source":"<h1><center><font size=\"6\">LANL Earthquake New Approach EDA</font></center></h1>\n\n<br>\n\n# <a id='0'>Content</a>\n\n- <a href='#1'>Introduction</a>  \n- <a href='#2'>Prepare the data analysis</a>  \n- <a href='#3'>Calculate aggregated features</a>\n- <a href='#4'>New features exploration</a>  \n- <a href='#5'>Conclusions</a>  \n- <a href='#6'>References</a>  \n"},{"metadata":{},"cell_type":"markdown","source":"# <a id='1'>Introduction</a>  \n\n## Simulated earthquake experiment\nThe data are from an experiment conducted on rock in a double direct shear geometry subjected to bi-axial loading, a classic laboratory earthquake model.\n\nTwo fault gouge layers are sheared simultaneously while subjected to a constant normal load and a prescribed shear velocity. The laboratory faults fail in repetitive cycles of stick and slip that is meant to mimic the cycle of loading and failure on tectonic faults. While the experiment is considerably simpler than a fault in Earth, it shares many physical characteristics.\n\nLos Alamos' initial work showed that the prediction of laboratory earthquakes from continuous seismic data is possible in the case of quasi-periodic laboratory seismic cycles.\n\n## Competition\nIn this competition, the team has provided a much more challenging dataset with considerably more aperiodic earthquake failures.\nObjective of the competition is to predict the failures for each test set."},{"metadata":{},"cell_type":"markdown","source":"# <a id='2'>Prepare the data analysis</a>  \n\n## Load packages"},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"import gc\nimport os\nimport time\nimport logging\nimport datetime\nimport warnings\nimport numpy as np\nimport pandas as pd\nimport seaborn as sns\nimport xgboost as xgb\nimport lightgbm as lgb\nfrom scipy import stats\nfrom tqdm import tqdm_notebook\nimport matplotlib.pyplot as plt\nfrom sklearn.preprocessing import StandardScaler\nwarnings.filterwarnings('ignore')","execution_count":1,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Load data"},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"PATH=\"../input/\"\nos.listdir(PATH)","execution_count":2,"outputs":[{"output_type":"execute_result","execution_count":2,"data":{"text/plain":"['test', 'train.csv', 'sample_submission.csv']"},"metadata":{}}]},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"print(\"There are {} files in test folder\".format(len(os.listdir(os.path.join(PATH, 'test' )))))","execution_count":3,"outputs":[{"output_type":"stream","text":"There are 2624 files in test folder\n","name":"stdout"}]},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"%%time\ntrain_df = pd.read_csv(os.path.join(PATH,'train.csv'), dtype={'acoustic_data': np.int16, 'time_to_failure': np.float32})","execution_count":4,"outputs":[{"output_type":"stream","text":"CPU times: user 2min 26s, sys: 31.2 s, total: 2min 57s\nWall time: 2min 57s\n","name":"stdout"}]},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"print(\"Train: rows:{} cols:{}\".format(train_df.shape[0], train_df.shape[1]))","execution_count":5,"outputs":[{"output_type":"stream","text":"Train: rows:629145480 cols:2\n","name":"stdout"}]},{"metadata":{},"cell_type":"markdown","source":"# <a id='3'>Calculate aggregated features</a>  "},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"rows = 150000\nsegments = int(np.floor(train_df.shape[0] / rows))\nprint(\"Number of segments: \", segments)","execution_count":6,"outputs":[{"output_type":"stream","text":"Number of segments:  4194\n","name":"stdout"}]},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"train_X = pd.DataFrame(index=range(segments), dtype=np.float64)\ntrain_y = pd.DataFrame(index=range(segments), dtype=np.float64, columns=['time_to_failure'])","execution_count":7,"outputs":[]},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"def create_features(seg_id, seg, X):\n    xc = pd.Series(seg['acoustic_data'].values)   \n    zc = np.fft.fft(xc)\n    realFFT = np.real(zc)\n    imagFFT = np.imag(zc)\n    X.loc[seg_id, 'mean'] = xc.mean()\n    X.loc[seg_id, 'std'] = xc.std()\n    X.loc[seg_id, 'max'] = xc.max()\n    X.loc[seg_id, 'min'] = xc.min()\n    X.loc[seg_id, 'sum'] = xc.sum()\n    X.loc[seg_id, 'mad'] = xc.mad()\n    X.loc[seg_id, 'kurt'] = xc.kurtosis()\n    X.loc[seg_id, 'skew'] = xc.skew()\n    X.loc[seg_id, 'med'] = xc.median()\n    X.loc[seg_id, 'abs_mean'] = np.abs(xc).mean()\n    X.loc[seg_id, 'q95'] = np.quantile(xc, 0.95)\n    X.loc[seg_id, 'q99'] = np.quantile(xc, 0.99)\n    X.loc[seg_id, 'q05'] = np.quantile(xc, 0.05)\n    X.loc[seg_id, 'q01'] = np.quantile(xc, 0.01)\n    X.loc[seg_id, 'Rmean'] = realFFT.mean()\n    X.loc[seg_id, 'Rstd'] = realFFT.std()\n    X.loc[seg_id, 'Rmax'] = realFFT.max()\n    X.loc[seg_id, 'Rmin'] = realFFT.min()\n    X.loc[seg_id, 'Imean'] = imagFFT.mean()\n    X.loc[seg_id, 'Istd'] = imagFFT.std()\n    X.loc[seg_id, 'Imax'] = imagFFT.max()\n    X.loc[seg_id, 'Imin'] = imagFFT.min()\n    X.loc[seg_id, 'std_first_50000'] = xc[:50000].std()\n    X.loc[seg_id, 'std_last_50000'] = xc[-50000:].std()\n    X.loc[seg_id, 'std_first_25000'] = xc[:25000].std()\n    X.loc[seg_id, 'std_last_25000'] = xc[-25000:].std()\n    X.loc[seg_id, 'std_first_10000'] = xc[:10000].std()\n    X.loc[seg_id, 'std_last_10000'] = xc[-10000:].std()\n","execution_count":9,"outputs":[]},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"# iterate over all segments\nfor seg_id in tqdm_notebook(range(segments)):\n    seg = train_df.iloc[seg_id*rows:seg_id*rows+rows]\n    create_features(seg_id, seg, train_X)\n    train_y.loc[seg_id, 'time_to_failure'] = seg['time_to_failure'].values[-1]","execution_count":10,"outputs":[{"output_type":"display_data","data":{"text/plain":"HBox(children=(IntProgress(value=0, max=4194), HTML(value='')))","application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"949da61c8e594e2d96b2218afdef662f"}},"metadata":{}},{"output_type":"stream","text":"\n","name":"stdout"}]},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"submission = pd.read_csv('../input/sample_submission.csv', index_col='seg_id')\ntest_X = pd.DataFrame(columns=train_X.columns, dtype=np.float64, index=submission.index)","execution_count":11,"outputs":[]},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"for seg_id in tqdm_notebook(test_X.index):\n    seg = pd.read_csv('../input/test/' + seg_id + '.csv')\n    create_features(seg_id, seg, test_X)","execution_count":12,"outputs":[{"output_type":"display_data","data":{"text/plain":"HBox(children=(IntProgress(value=0, max=2624), HTML(value='')))","application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"da0bda9b8498405f83c95cb1f014b099"}},"metadata":{}},{"output_type":"stream","text":"\n","name":"stdout"}]},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"print(\"Train X: {} y: {} Test X: {}\".format(train_X.shape, train_y.shape, test_X.shape))","execution_count":13,"outputs":[{"output_type":"stream","text":"Train X: (4194, 28) y: (4194, 1) Test X: (2624, 28)\n","name":"stdout"}]},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"train_X.head()","execution_count":14,"outputs":[{"output_type":"execute_result","execution_count":14,"data":{"text/plain":"       mean       std       ...        std_first_10000  std_last_10000\n0  4.884113  5.101106       ...              11.207151        4.361407\n1  4.725767  6.588824       ...               3.976750        3.667890\n2  4.906393  6.967397       ...               8.454717        9.493983\n3  4.902240  6.922305       ...               6.866177        4.364430\n4  4.908720  7.301110       ...               5.164594       11.404900\n\n[5 rows x 28 columns]","text/html":"<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>mean</th>\n      <th>std</th>\n      <th>max</th>\n      <th>min</th>\n      <th>sum</th>\n      <th>mad</th>\n      <th>kurt</th>\n      <th>skew</th>\n      <th>med</th>\n      <th>abs_mean</th>\n      <th>q95</th>\n      <th>q99</th>\n      <th>q05</th>\n      <th>q01</th>\n      <th>Rmean</th>\n      <th>Rstd</th>\n      <th>Rmax</th>\n      <th>Rmin</th>\n      <th>Imean</th>\n      <th>Istd</th>\n      <th>Imax</th>\n      <th>Imin</th>\n      <th>std_first_50000</th>\n      <th>std_last_50000</th>\n      <th>std_first_25000</th>\n      <th>std_last_25000</th>\n      <th>std_first_10000</th>\n      <th>std_last_10000</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>4.884113</td>\n      <td>5.101106</td>\n      <td>104.0</td>\n      <td>-98.0</td>\n      <td>732617.0</td>\n      <td>3.263401</td>\n      <td>33.662481</td>\n      <td>-0.024061</td>\n      <td>5.0</td>\n      <td>5.576567</td>\n      <td>11.0</td>\n      <td>18.0</td>\n      <td>-2.0</td>\n      <td>-8.0</td>\n      <td>12.0</td>\n      <td>2349.811482</td>\n      <td>732617.0</td>\n      <td>-20121.154171</td>\n      <td>-1.067140e-15</td>\n      <td>1399.854635</td>\n      <td>23432.719433</td>\n      <td>-23432.719433</td>\n      <td>6.488552</td>\n      <td>3.664663</td>\n      <td>7.929184</td>\n      <td>3.791314</td>\n      <td>11.207151</td>\n      <td>4.361407</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>4.725767</td>\n      <td>6.588824</td>\n      <td>181.0</td>\n      <td>-154.0</td>\n      <td>708865.0</td>\n      <td>3.574302</td>\n      <td>98.758517</td>\n      <td>0.390561</td>\n      <td>5.0</td>\n      <td>5.734167</td>\n      <td>12.0</td>\n      <td>21.0</td>\n      <td>-2.0</td>\n      <td>-11.0</td>\n      <td>5.0</td>\n      <td>2566.032248</td>\n      <td>708865.0</td>\n      <td>-31056.675076</td>\n      <td>7.033426e-16</td>\n      <td>1810.312266</td>\n      <td>27236.180586</td>\n      <td>-27236.180586</td>\n      <td>7.305233</td>\n      <td>5.493071</td>\n      <td>8.767468</td>\n      <td>4.485858</td>\n      <td>3.976750</td>\n      <td>3.667890</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>4.906393</td>\n      <td>6.967397</td>\n      <td>140.0</td>\n      <td>-106.0</td>\n      <td>735959.0</td>\n      <td>3.948411</td>\n      <td>33.555211</td>\n      <td>0.217391</td>\n      <td>5.0</td>\n      <td>6.152647</td>\n      <td>13.0</td>\n      <td>26.0</td>\n      <td>-3.0</td>\n      <td>-15.0</td>\n      <td>5.0</td>\n      <td>2683.549049</td>\n      <td>735959.0</td>\n      <td>-27654.557067</td>\n      <td>-1.261166e-15</td>\n      <td>1921.220576</td>\n      <td>30073.497066</td>\n      <td>-30073.497066</td>\n      <td>6.104836</td>\n      <td>8.603696</td>\n      <td>6.976451</td>\n      <td>11.057212</td>\n      <td>8.454717</td>\n      <td>9.493983</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>4.902240</td>\n      <td>6.922305</td>\n      <td>197.0</td>\n      <td>-199.0</td>\n      <td>735336.0</td>\n      <td>3.647117</td>\n      <td>116.548172</td>\n      <td>0.757278</td>\n      <td>5.0</td>\n      <td>5.933960</td>\n      <td>12.0</td>\n      <td>22.0</td>\n      <td>-2.0</td>\n      <td>-12.0</td>\n      <td>5.0</td>\n      <td>2685.788525</td>\n      <td>735336.0</td>\n      <td>-25622.393604</td>\n      <td>-9.701277e-16</td>\n      <td>1891.826366</td>\n      <td>27380.321471</td>\n      <td>-27380.321471</td>\n      <td>6.238109</td>\n      <td>5.652442</td>\n      <td>6.086580</td>\n      <td>6.156603</td>\n      <td>6.866177</td>\n      <td>4.364430</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>4.908720</td>\n      <td>7.301110</td>\n      <td>145.0</td>\n      <td>-126.0</td>\n      <td>736308.0</td>\n      <td>3.826052</td>\n      <td>52.977905</td>\n      <td>0.064531</td>\n      <td>5.0</td>\n      <td>6.110587</td>\n      <td>12.0</td>\n      <td>26.0</td>\n      <td>-2.0</td>\n      <td>-15.0</td>\n      <td>12.0</td>\n      <td>2761.715771</td>\n      <td>736308.0</td>\n      <td>-26271.075117</td>\n      <td>2.910383e-16</td>\n      <td>1995.742969</td>\n      <td>27503.045280</td>\n      <td>-27503.045280</td>\n      <td>5.323830</td>\n      <td>7.694506</td>\n      <td>6.336576</td>\n      <td>8.136564</td>\n      <td>5.164594</td>\n      <td>11.404900</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"test_X.head()","execution_count":15,"outputs":[{"output_type":"execute_result","execution_count":15,"data":{"text/plain":"                mean       std       ...        std_first_10000  std_last_10000\nseg_id                               ...                                       \nseg_00030f  4.491780  4.893690       ...               5.226846        6.019017\nseg_0012b5  4.171153  5.922839       ...               3.523253        3.605147\nseg_00184e  4.610260  6.946990       ...               3.950119        3.063057\nseg_003339  4.531473  4.114147       ...               4.001275        2.771185\nseg_0042cc  4.128340  5.797164       ...               5.214578        6.871187\n\n[5 rows x 28 columns]","text/html":"<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>mean</th>\n      <th>std</th>\n      <th>max</th>\n      <th>min</th>\n      <th>sum</th>\n      <th>mad</th>\n      <th>kurt</th>\n      <th>skew</th>\n      <th>med</th>\n      <th>abs_mean</th>\n      <th>q95</th>\n      <th>q99</th>\n      <th>q05</th>\n      <th>q01</th>\n      <th>Rmean</th>\n      <th>Rstd</th>\n      <th>Rmax</th>\n      <th>Rmin</th>\n      <th>Imean</th>\n      <th>Istd</th>\n      <th>Imax</th>\n      <th>Imin</th>\n      <th>std_first_50000</th>\n      <th>std_last_50000</th>\n      <th>std_first_25000</th>\n      <th>std_last_25000</th>\n      <th>std_first_10000</th>\n      <th>std_last_10000</th>\n    </tr>\n    <tr>\n      <th>seg_id</th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>seg_00030f</th>\n      <td>4.491780</td>\n      <td>4.893690</td>\n      <td>115.0</td>\n      <td>-75.0</td>\n      <td>673767.0</td>\n      <td>3.248521</td>\n      <td>28.837568</td>\n      <td>0.327908</td>\n      <td>4.0</td>\n      <td>5.224607</td>\n      <td>11.0</td>\n      <td>18.0</td>\n      <td>-2.0</td>\n      <td>-8.0</td>\n      <td>4.0</td>\n      <td>2198.344036</td>\n      <td>673767.0</td>\n      <td>-14758.442559</td>\n      <td>-4.850638e-16</td>\n      <td>1336.370645</td>\n      <td>17561.332021</td>\n      <td>-17561.332021</td>\n      <td>5.350451</td>\n      <td>4.793876</td>\n      <td>6.626625</td>\n      <td>5.542450</td>\n      <td>5.226846</td>\n      <td>6.019017</td>\n    </tr>\n    <tr>\n      <th>seg_0012b5</th>\n      <td>4.171153</td>\n      <td>5.922839</td>\n      <td>152.0</td>\n      <td>-140.0</td>\n      <td>625673.0</td>\n      <td>3.429208</td>\n      <td>56.218955</td>\n      <td>0.295708</td>\n      <td>4.0</td>\n      <td>5.198340</td>\n      <td>11.0</td>\n      <td>20.0</td>\n      <td>-2.0</td>\n      <td>-12.0</td>\n      <td>5.0</td>\n      <td>2289.922379</td>\n      <td>625673.0</td>\n      <td>-22626.387706</td>\n      <td>3.637979e-16</td>\n      <td>1621.103791</td>\n      <td>24935.932861</td>\n      <td>-24935.932861</td>\n      <td>6.249515</td>\n      <td>4.147562</td>\n      <td>3.490479</td>\n      <td>4.406340</td>\n      <td>3.523253</td>\n      <td>3.605147</td>\n    </tr>\n    <tr>\n      <th>seg_00184e</th>\n      <td>4.610260</td>\n      <td>6.946990</td>\n      <td>248.0</td>\n      <td>-193.0</td>\n      <td>691539.0</td>\n      <td>3.461984</td>\n      <td>162.118284</td>\n      <td>0.428688</td>\n      <td>5.0</td>\n      <td>5.597193</td>\n      <td>11.0</td>\n      <td>20.0</td>\n      <td>-2.0</td>\n      <td>-11.0</td>\n      <td>8.0</td>\n      <td>2611.055629</td>\n      <td>691539.0</td>\n      <td>-23593.939294</td>\n      <td>6.790894e-16</td>\n      <td>1899.881970</td>\n      <td>25121.856730</td>\n      <td>-25121.856730</td>\n      <td>9.793473</td>\n      <td>5.225913</td>\n      <td>3.974593</td>\n      <td>3.070449</td>\n      <td>3.950119</td>\n      <td>3.063057</td>\n    </tr>\n    <tr>\n      <th>seg_003339</th>\n      <td>4.531473</td>\n      <td>4.114147</td>\n      <td>85.0</td>\n      <td>-93.0</td>\n      <td>679721.0</td>\n      <td>2.678503</td>\n      <td>41.241827</td>\n      <td>0.061889</td>\n      <td>5.0</td>\n      <td>4.961487</td>\n      <td>10.0</td>\n      <td>14.0</td>\n      <td>-1.0</td>\n      <td>-5.0</td>\n      <td>2.0</td>\n      <td>2085.543454</td>\n      <td>679721.0</td>\n      <td>-11908.537959</td>\n      <td>-8.488617e-16</td>\n      <td>1126.745535</td>\n      <td>14075.675064</td>\n      <td>-14075.675064</td>\n      <td>3.664088</td>\n      <td>3.480840</td>\n      <td>3.867598</td>\n      <td>3.026629</td>\n      <td>4.001275</td>\n      <td>2.771185</td>\n    </tr>\n    <tr>\n      <th>seg_0042cc</th>\n      <td>4.128340</td>\n      <td>5.797164</td>\n      <td>177.0</td>\n      <td>-147.0</td>\n      <td>619251.0</td>\n      <td>3.283856</td>\n      <td>79.539708</td>\n      <td>0.073898</td>\n      <td>4.0</td>\n      <td>5.070900</td>\n      <td>10.0</td>\n      <td>19.0</td>\n      <td>-2.0</td>\n      <td>-10.0</td>\n      <td>5.0</td>\n      <td>2243.929923</td>\n      <td>619251.0</td>\n      <td>-24048.055870</td>\n      <td>3.880511e-16</td>\n      <td>1600.707500</td>\n      <td>24201.768989</td>\n      <td>-24201.768989</td>\n      <td>5.321133</td>\n      <td>7.486142</td>\n      <td>4.170309</td>\n      <td>5.217881</td>\n      <td>5.214578</td>\n      <td>6.871187</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{},"cell_type":"markdown","source":"# <a id='4'>New features exploration</a> \n\n\n## Aggregated features\n\nLet's visualize the new features distributions. The graphs below shows the distplot (histograms and density plots) for all the new features, for train (<font color=\"green\">green</font>) and test (<font color=\"blue\">blue</font>) data."},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"def plot_distplot(feature):\n    plt.figure(figsize=(16,6))\n    plt.title(\"Distribution of {} values in the train and test set\".format(feature))\n    sns.distplot(train_X[feature],color=\"green\", kde=True,bins=120, label='train')\n    sns.distplot(test_X[feature],color=\"blue\", kde=True,bins=120, label='test')\n    plt.legend()\n    plt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"def plot_distplot_features(features, nlines=4, colors=['green', 'blue'], df1=train_X, df2=test_X):\n    i = 0\n    plt.figure()\n    fig, ax = plt.subplots(nlines,2,figsize=(16,4*nlines))\n    for feature in features:\n        i += 1\n        plt.subplot(nlines,2,i)\n        sns.distplot(df1[feature],color=colors[0], kde=True,bins=40, label='train')\n        sns.distplot(df2[feature],color=colors[1], kde=True,bins=40, label='test')\n    plt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"features = ['mean', 'std', 'max', 'min', 'sum', 'mad', 'kurt', 'skew']\nplot_distplot_features(features)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"features = ['med','abs_mean', 'q95', 'q99', 'q05', 'q01']\nplot_distplot_features(features,3)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"features = ['Rmean', 'Rstd', 'Rmax','Rmin', 'Imean', 'Istd', 'Imax', 'Imin']\nplot_distplot_features(features)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"features = ['std_first_50000', 'std_last_50000', 'std_first_25000','std_last_25000', 'std_first_10000','std_last_10000']\nplot_distplot_features(features,3)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Scaled features\n\nLet's scale now the aggregated features and show again the resulting graphs.   \nWe are fiting the scaler with both train and test data.\nWe use <font color=\"red\">red</font> from train and <font color=\"magenta\">magenta</font> for test data."},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"scaler = StandardScaler()\nscaler.fit(pd.concat([train_X, test_X]))\nscaled_train_X = pd.DataFrame(scaler.transform(train_X), columns=train_X.columns)\nscaled_test_X = pd.DataFrame(scaler.transform(test_X), columns=test_X.columns)","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"features = ['mean', 'std', 'max', 'min', 'sum', 'mad', 'kurt', 'skew']\nplot_distplot_features(features, nlines=4, colors=['red', 'magenta'], df1=scaled_train_X, df2=scaled_test_X)","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"features = ['med','abs_mean', 'q95', 'q99', 'q05', 'q01']\nplot_distplot_features(features, nlines=3, colors=['red', 'magenta'], df1=scaled_train_X, df2=scaled_test_X)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"features = ['Rmean', 'Rstd', 'Rmax','Rmin', 'Imean', 'Istd', 'Imax', 'Imin']\nplot_distplot_features(features, nlines=4, colors=['red', 'magenta'], df1=scaled_train_X, df2=scaled_test_X)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"features = ['std_first_50000', 'std_last_50000', 'std_first_25000','std_last_25000', 'std_first_10000','std_last_10000']\nplot_distplot_features(features, nlines=3, colors=['red', 'magenta'], df1=scaled_train_X, df2=scaled_test_X)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Aggregated features and time to failure\n\nLet's also show aggregated features and time to failure on the same graph. "},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"def plot_acc_agg_ttf_data(feature, title=\"Averaged accoustic data and ttf\"):\n    fig, ax1 = plt.subplots(figsize=(16, 8))\n    plt.title('Averaged accoustic data ({}) and time to failure'.format(feature))\n    plt.plot(train_X[feature], color='r')\n    ax1.set_xlabel('training samples')\n    ax1.set_ylabel('acoustic data ({})'.format(feature), color='r')\n    plt.legend(['acoustic data ({})'.format(feature)], loc=(0.01, 0.95))\n    ax2 = ax1.twinx()\n    plt.plot(train_y, color='b')\n    ax2.set_ylabel('time to failure', color='b')\n    plt.legend(['time to failure'], loc=(0.01, 0.9))\n    plt.grid(True)","execution_count":16,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"plot_acc_agg_ttf_data('mean')","execution_count":17,"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 1152x576 with 2 Axes>","image/png":"iVBORw0KGgoAAAANSUhEUgAAA9gAAAHwCAYAAABdSscDAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDMuMC4zLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvnQurowAAIABJREFUeJzs3Xl8FOX9B/DPNxDuG0SloOCFEAiBrEi1KqBVrFqPqq31turPWlttFbUeqLVW6w/rhRVR1Kp4oeItFX+I1HqGUw7lUIQAciScIYFAnt8fz0wyO5nZndmd2dndfN6vV1672Z2Z59nZ2ZnnO88lSikQERERERERUXoKos4AERERERERUT5ggE1EREREREQUAAbYRERERERERAFggE1EREREREQUAAbYRERERERERAFggE1EREREREQUAAbYRETkiYhcJCIfR52PoInIeBG5NYDtPC0ifw0iTx7TO0FEXs9Uel6JyKsicmIG01shIsf5WH6hiAwPMUuBEJHWIvKWiGwRkckelq//XCJyu4g8F3omiYioEQbYREQhEZEZIrJJRFpGnRfSnG4SKKWuUErdmeF8zBCRS9PczF0A7gkiPwH7O4CM3WhIxOmmh1KqSCk1IwNppxvknglgbwBdlVJnJVs4U5+LiIgSY4BNRBQCEekN4CgACsDPQ0qjeRjbpewnIocB6KiU+izqvNgppb4A0EFEYlHnJcftD2CJUmp3JhPleYWIKD0MsImIwnEBgM8APA3gQvNFETlcRH4QkWaW104XkfnG8wIRuVFElotIhYi8LCJdjPd6i4gSkd+IyEoA043XJxvb3CIiM0WkyLLtrkYz060i8qWI/NVagysih4rINBGpFJFvRORs27pvGut+AeDARB84ST5ai8h9IvK98f7HItLaeO8nIvKJiGwWkVUicpHxekcReUZENhjr3SIiBcZ7cbWDln3T3Pj/IhH5VkS2ich3InKuiPQDMB7Aj0Vku4hsNpaNq+UUkVNFZK7xuZeLyCiXzztYRGYbabwEoJXlvc4i8raR903G857Ge3dB33wZZ+RjnPH6g8bn3yois0TkqAS7+0QAH9nyo0TkShFZauTpThE50Ni3W41jqYVl+ZONz7nZWKbY8p55DG4TkUUicrrlvYuM72+s8dm+k8ZNwmcAOMllv7nuG+P9GUbe/2uk/76IdLO8f75xPFSIyM1uO0hELgdwLoDrjf38lvF6fZNy4ziaLCLPGWl9JSKHiMifRWS98X0cb9lmRxGZKCJrRWS16N9TM4e0RwG4CcAvjbTnGa/3EP2bqhSRZSJymUve7wAwxrL+b4zvcrrxuTeKyCQR6WRZx7GpvIgMF5Fy22v2ffCKsQ+2ArhIEpyHiIgoMQbYREThuADAJOPvBBHZGwCUUp8DqAIw0rLsrwE8bzz/PYDTABwDoAeATQAesW37GAD9AJxg/P8egIMBdAcw20jT9IiR3j7Qgb412G8LYJqRdncAvwLwTxHpb1m3BsC+AC4x/hJJlI+xAEoBHAGgC4DrAdSJyP7Geg8D2AtACYC5xjoPA+gI4ADjM18A4OIkeTA/10MATlRKtTfSnKuUWgzgCgCfKqXaKaU6Oaw7FMAzAEYD6ATgaAArHJZrAeB1AM8an2cygF9YFikA8BR0LeR+AKoBjAMApdTNAP4D4CojH1cZ63xpfP4u0N/JZBFpBWcDAXzj8PoJ0Pt5GPQ+ngDgPAC9AAwAcI6R/8EAngTwPwC6AngMwJvS0J1hOfRNgI4A7gDwnIjsa0nncCP9bgDuBTBRRMTy/mIAg1zy7rpvLH4N/V13B9ACwHVGvvsDeBTA+dC/j64AesKBUmoC9DF4r7GfT3HJzynQ32NnAHMA/NvI448A/AV635ieBrAbwEEABgM4HkCjpv5KqakA/gbgJSNtc1+8CKDcyPuZAP4mIiMd1r/Ntv5EAALgbmPdftDf6e0un8mvUwG8An3MT4K38xARETlggE1EFDAR+Ql08PCyUmoWdLDya8siL6Ah0GkP4GfGa4AOAG9WSpUrpXZCF6DPlPhmm7crpaqUUtUAoJR6Uim1zbL8IKOmrRl00HebUmqHUmoRgH9ZtnMygBVKqaeUUruVUnMAvArgLMu6Y4y0FtjWbSRBPgqgg/OrlVKrlVJ7lFKfGMv9GsAHSqkXlFK1SqkKpdRcI/1fAfizsc0VAO6DDqy8qAMwQERaK6XWKqUWelzvNwCeVEpNU0rVGfn92mG5YQAKATxg5PsV6ADZ3BcVSqlXjf2+Dbq/9DGJElZKPWest1spdR+AlgD6uizeCcA2h9fvVUptNT7vAgDvK6W+VUptgb6RMdhY7nIAjymlPje+j38B2Gl8LiilJiul1hj74CUASwEMtaTzvVLqcaXUHujjYl/o/sKmbUYenT6nl33zlFJqiXGMvwx94wHQQenbSqmZxvFzK/R3nY7/KKX+bTTFngx9o+cepVQtdEDcW0Q6GTfJfgbgGuM3sR7A/dDHaVIi0gvAkQBuUErVKKXmAngC+sZRUkqpZcZxuVMptQHAP5DkmPLhU6XU68b3XQ1v5yEiInLAAJuIKHgXQgc2G43/n4el5tj4/wyjtvAMALOVUt8b7+0PYIrRbHczdE3gHsQHL6vMJyLSTETuMZpybkVDbWs36EChuXV52/P9ARxupmWkdy50bbfTut/DRZJ8dINuPr3cYdVeLq93gw5grWl+D12rmJBSqgrAL6GDhLUi8o6IHJpsvST5sesBYLVSStnyBwAQkTYi8pjRlHkrgJkAOjk1J7asc52ILBbdhH4zdO1xN5fFNwFo7/D6Osvzaof/2xnP9wdwre2772V8LojIBdLQfHwzdO23NS8/mE+UUjuMp+0s77cHsNnlc3rZNz9Ynu+wbLsHLMek8V1XOKXjg30fbTRuHJj/w0h/f+hjcq1lvzwGXcvuRQ8AlcZNBZOnYxoARGRvEXnRaJq+FcBzcD8+/Fpl+9/LeYiIiBwwwCYiCpDofsVnAzhGdH/kHwD8Ebo2dxAAGDXJ30P3o7U2Dwd0QfdEpVQny18rpdRqyzLWoO7X0M07j4MOyHqbWQGwAbo5q7UJbS9bWh/Z0mqnlPqtZV3r8vsl+OiJ8rERuqm5Ux/uVS6vbwRQC13Qt6Zv7ocqAG0s7+1jXdmokfwpdM3q1wAeN99K8BkS5cduLYAf2ZpFW/fPtdC1z4crpTpANzUH9P5olA/R/a2vhz52OhvN17dYlrebD+AQD/l0swrAXbbvvo1S6gWj2f7jAK6CHsG6E3RtuFtenPQDMM/lvWT7JpG1sByTItIGupm4m2Tftx+roGv5u1n2WQelVJHL8va01wDoYrRaMVmP6WT+ZmxzoLHfzoO3fRb3WzFuZOyVJK9ezkNEROSAATYRUbBOg67p6Q/drLUEOtj4D+Kbgj4P4Gro4MI6x+14AHcZQQ5EZC8ROTVBeu2hC/0V0IXov5lvGLVwrwG43ag1PNSWh7cBHCJ60KhC4+8wEennsG5/xNfC+8lHHXR/33+IHuSpmYj82KjBnwTgOBE5W0Saix5YrcRI/2VjX7Q39sefoGvtAN1P+2gR2U9EOgL4s5meUdN3qtEXeyeA7WhoRrwOQE+xDPZlMxHAxSJyrDHQ049car8/hb4B8Qdjv52B+CbU7aFrPzcbg0PdZlt/HXTfcuvyu6FvbDQXkTEAOrjkEQDeRXrNgx8HcIXoQfdERNqKyElG8NcWOuDaAAAicjF0DbYfx0A3SXeSbN8k8gqAk0UPjNcCuo90orKMfT+nTCm1FsD7AO4TkQ7G8XGgiLh9D+ugm5cXGOuvAvAJgLtFpJXoQeV+g4ZjOpn20MfyFhH5EfQ4AV4sAdDK+H4LAdwC3f0gEb/nISIiMjDAJiIK1oXQ/UdXKqV+MP+gB3E619KH8QXoIGS6pSk5ADwI4E0A74vINuiRyA9PkN4z0LXhqwEsMpa3ugq6RvkH6IGcXoAOOmE0VT0eug/pGmOZv6Oh8H0VdNPYH6AHd3oqjXxcB+Ar6H7KlUY6BUqpldD9Wq81Xp+LhsGxfg9d+/YtgI+hb0o8aeR9GoCXoGtyZ0HfLDAVQAfja4xtHgPgt8Z70wEsBPCDiFj3O4ztfgE9uNb90DXIHyG+Ft1cbhd08/6LjDR+CX1DwvQAgNbQNfGfAZhq28SD0H1aN4nIQ9ADa02FDoa+h67xtzfbtaY/GzrQSnRsuFJKlQG4DPq43ARgmfFZzBYW90HfRFgHPaDaf71uW/QUYtuNfekk2b5JlO+FAH4HfSysNfJenmCViQD6G02dX/eaTgIXQA+6tshI+xXoVhJOzBtnFSIy23h+DnTrjjUApkCPj/CBx7TvADAE+rh8B/HHmyuj//2V0P29V0P/phLtM8D/eYiIiAwS332MiIjymYj8HcA+SqlEtdGUA0RPH3WlUuq0qPNiJSKvApiolHo36rwQERFlGgNsIqI8ZjRvbgFde3wYdNPiS5VSQdTmEREREZEFp1sgIspv7aGbhfeAbu57H4A3Is0RERERUZ5iDTYRERERERFRADjIGREREREREVEAGGATERERERERBSCv+mAXFBSo1q1bR50NIiIiIiIiCtiOHTuUUiqrK4nzKsBu3bo1qqqqos4GERERERERBUxEqqPOQzJZHf0TERERERER5QoG2EREREREREQByKsm4l7U1taivLwcNTU1UWeFckSrVq3Qs2dPFBYWRp0VIiIiIiLKYk0uwC4vL0f79u3Ru3dviEjU2aEsp5RCRUUFysvL0adPn6izQ0REREREWazJNRGvqalB165dGVyTJyKCrl27ssUDEREREREl1eQCbAAMrskXHi9ERERERORFkwywm6IHHngAO3bsqP//Zz/7GTZv3pzStnr37o2NGzcmXOZvf/tbSts+88wz8e2336a0brquu+46TJ8+PZK0iYiIiIgo9zHAbiLsAfa7776LTp06hZZeKgH2woULsWfPHhxwwAEh5Ci53//+97jnnnsiSZuIiIiIiHIfA+wInHbaaSgtLUVRUREmTJhQ//rUqVMxZMgQDBo0CMceeywAoLKyEqeddhqKi4sxbNgwzJ8/HwBw++23Y+zYsfXrDhgwACtWrEBVVRVOOukkDBo0CAMGDMBLL72Ehx56CGvWrMGIESMwYsQIAPG10M888wyKi4sxaNAgnH/++Y3yW1FRgeOPPx5FRUW49NJLoZRK+FluvPFGVFdXo6SkBOeee27Cz2w1adIknHrqqfX/t2vXDqNHj0ZRURGOO+44fPHFFxg+fDgOOOAAvPnmmwCAPXv2YPTo0TjssMNQXFyMxx57DACwfft2HHvssRgyZAgGDhyIN954AwCwYsUK9OvXD5dddhmKiopw/PHHo7paz1e///77o6KiAj/88IO3L5KIiIiIiMhCrMFSrmvbtq2qqqpKuMzixYvRr18//c811wBz5wabiZIS4IEHEi5SWVmJLl26oLq6Gocddhg++ugj1NXVYciQIZg5cyb69OlTv8zvf/97dOvWDbfddhumT5+OP/3pT5g7dy5uv/12tGvXDtdddx0AHWC//fbbmDVrFqZOnYrHH38cALBlyxZ07NgRvXv3RllZGbp16wYA9f+vW7cOp59+Oj755BN069atPl2rP/zhD+jWrRvGjBmDd955ByeffDI2bNgQt7z1s3Tt2hXt2rXD9u3bE37mrl27xqVzzDHHYNy4cRg4cCAA3ff53XffxYknnojTTz8dVVVVeOedd7Bo0SJceOGFmDt3LiZMmID169fjlltuwc6dO3HkkUdi8uTJ6NWrF3bs2IEOHTpg48aNGDZsGJYuXYrvv/8eBx10EMrKylBSUoKzzz4bP//5z3HeeecBAC677DKMGjUKv/jFL+LyFnfcEBERERFRxonIDqVU26jzkUiTm6YrGzz00EOYMmUKAGDVqlVYunQpNmzYgKOPPrp+KigzyP3444/x6quvAgBGjhyJiooKbN261XXbAwcOxLXXXosbbrgBJ598Mo466qiEeZk+fTrOOuus+sDbHlwDwMyZM/Haa68BAE466SR07tw54WexB85el1u7di322muv+v9btGiBUaNG1X+uli1borCwEAMHDsSKFSsAAO+//z7mz5+PV155BYC+obB06VL07NkTN910E2bOnImCggKsXr0a69atAwD06dMHJSUlAIDS0tL6bQFA9+7dsWbNmoT7jIiIiIiIyEnTDrCT1DSHYcaMGfjggw/w6aefok2bNhg+fHhKU0A1b94cdXV19f+b2zjkkEMwe/ZsvPvuu7jllltw7LHHYsyYMYHl38rrZ/G6XOvWreNeLywsrB/Bu6CgAC1btqx/vnv3bgB6nuqHH34YJ5xwQty2nn76aWzYsAGzZs1CYWEhevfuXb9tczsA0KxZs/om4oDej61bt051lxARERERURPGPtgZtmXLFnTu3Blt2rTB119/jc8++wwAMGzYMMycORPfffcdAN2kGgCOOuooTJo0CYAOVLt164YOHTqgd+/emD17NgBg9uzZ9eutWbMGbdq0wXnnnYfRo0fXL9O+fXts27atUX5GjhyJyZMno6KiIi5dq6OPPhrPP/88AOC9997Dpk2bEn4WQAfHtbW1SZez6tevH5YtW+Z5XwLACSecgEcffbQ+rSVLlqCqqgpbtmxB9+7dUVhYiA8//BDff/+9p+0tWbIEAwYM8JUHIiIiIiIioKnXYEdg1KhRGD9+PPr164e+ffti2LBhAIC99toLEyZMwBlnnIG6ujp0794d06ZNw+23345LLrkExcXFaNOmDf71r38BAH7xi1/gmWeeQVFREQ4//HAccsghAICvvvoKo0ePRkFBAQoLC/Hoo48CAC6//HKMGjUKPXr0wIcfflifn6KiItx888045phj0KxZMwwePBhPP/10XJ5vu+02nHPOOSgqKsIRRxyB/fbbL+FnMdMrLi7GkCFD8OSTT7ouZ3XSSSdhxowZOO644zzvz0svvRQrVqzAkCFDoJTCXnvthddffx3nnnsuTjnlFAwcOBCxWAyHHnpo0m3V1tZi2bJliMVintMnIiIiIiIyNe1BziirVFdXY8SIEfjvf/+LZs2aZTz9KVOmYPbs2bjzzjsbvcfjhoiIiIgoWrkwyBmbiFPWaN26Ne644w6sXr06kvR3796Na6+9NpK0iYiIiIgo97GJOGUV+2BlmXTWWWdFljZRPlIKMMYpJCIiImoSWINNZLdwIbBgQdS5IMppjz8O9OsHWCY7ICIiIgqdiDwpIutFZIHt9d+LyNcislBE7g0r/SYZYOdTv3MKQXU1YJkujMcLkX/LlwPffAP4nBiAiIiIKF1PAxhlfUFERgA4FcAgpVQRgLFhJd7kAuxWrVqhoqKCQRN5opRCRUUFWrVqFXVWiHJSWVnUOSAiIqKmRCk1E4B97uHfArhHKbXTWGZ9WOnnVR/sLl26YMaMGQmXUUqhtrYWdWy3SG527dKPU6cCQP2UZ17n0iYiYOXKAwDshylTVqFHj+VRZ4eIiIjyQ3MRsd6+n6CUmuBhvUMAHCUidwGoAXCdUurLUDIYxkajUllZieHDh0edDcp15qhMXlo51NYCVVVAp07h5okoxxj3p7BuXS8MH94r2swQERFRvtitlIqlsF5zAF0ADANwGICXReQAFUKz5ibXRJwoUOefD3TuHHUuiLLWnDnAnj1R54KIiIiauHIAryntCwB1ALqFkVBe1WB7UVtbi/LyctRYBrGi7NKqVSv07NkThYWFUWcluZdeijoHRFlt+3ZgyRI9ojgRERFRRF4HMALAhyJyCIAWADaGkVCTC7DLy8vRvn179O7dG8IJWrOOOahYeXk5+vTpE3V2vOOEv0SuysoYYBMREVFmiMgLAIYD6CYi5QBuA/AkgCeNqbt2AbgwjObhQBMMsGtqahhcZzERQdeuXbFhw4aos+LPnj1A8yb3cyJypRRQWKj/ysp0bwoiIiKisCmlznF567xMpN8k+2AzuM5uOfn9sJMpUSPNmgFDhnCqLiIiImo6mmSATRQ4TvtG5Ki0FJg7F9i9O+qcEBEREYWPAXaGbd68Gf/85z/r/1+zZg3OPPPMwNOZMWMGPvnkE1/r7Ny5E8cddxxKSkrwUoLBu8aMGYMPPvgAADB8+HCUsXqKNdhELmIxYMcO4Ouvo84JERERUfjYaTTDzAD7yiuvBAD06NEDr7zySuDpzJgxA+3atcMRRxzheZ05c+YAAObOnZtwub/85S8p52v37t1onk99lQsKdO01A2wiRzFjpsqyMmDAgGjzQkRERBQ21mBn2I033ojly5ejpKQEo0ePxooVKzDAKHU+/fTTOO200/DTn/4UvXv3xrhx4/CPf/wDgwcPxrBhw1BZWQkAWL58OUaNGoXS0lIcddRR+NpWNbRixQqMHz8e999/P0pKSvCf//wHK1aswMiRI1FcXIxjjz0WK1eujFtn/fr1OO+88/Dll1+ipKQEy5cvx1/+8hccdthhGDBgAC6//HKYA+1ddNFFjjcF2rVrV//8lVdewUUXXVS//BVXXIHDDz8c119/PaqqqnDJJZdg6NChGDx4MN54443A9m/GFRg/IQbYRI4OOQRo1479sImIiKhpyKOqRP+uuUb3DQxSSQnwwAPu799zzz1YsGBBfS3xihUr4t5fsGAB5syZg5qaGhx00EH4+9//jjlz5uCPf/wjnnnmGVxzzTW4/PLLMX78eBx88MH4/PPPceWVV2L69On12+jduzeuuOIKtGvXDtdddx0A4JRTTsGFF16ICy+8EE8++ST+8Ic/4PXXX69fp3v37njiiScwduxYvP322wCAq666CmPGjAEAnH/++Xj77bdxyimnpLRfysvL8cknn6BZs2a46aabMHLkSDz55JPYvHkzhg4diuOOOw5t27ZNaduRMgdkYx9sIkcFBXqgs1mzos4JERERUfiadICdjUaMGIH27dujffv26NixY31AO3DgQMyfPx/bt2/HJ598grPOOqt+nZ07dybd7qefforXXnsNgA6Wr7/++qTrfPjhh7j33nuxY8cOVFZWoqioKOUA+6yzzkKzZs0AAO+//z7efPNNjB07FoCeOm3lypXol4sT5bIGmyipWAz45z+B2lo9bRcRERFRvmrSAXaimuaotGzZsv55QUFB/f8FBQXYvXs36urq0KlTp6T9pNNVU1ODK6+8EmVlZejVqxduv/121NTUJFzHOr2WfVlr7bRSCq+++ir69u0bbKajwACbyJHRowSADrBraoBFi4BBg6LLExEREVHY2Ac7w9q3b49t27alvH6HDh3Qp08fTJ48GYAOVufNm5c0nSOOOAIvvvgiAGDSpEk46qijEqZjBsjdunXD9u3bPQ3Etvfee2Px4sWoq6vDlClTXJc74YQT8PDDD9f36TYHV8tJbCJO5Mr8eVgHOiMiIiLKZwywM6xr16448sgjMWDAAIwePTqlbUyaNAkTJ07EoEGDUFRU5DhI2CmnnIIpU6bUD3L28MMP46mnnkJxcTGeffZZPPjggwnT6NSpEy677DIMGDAAJ5xwAg477LCk+brnnntw8skn44gjjsC+++7rutytt96K2tpaFBcXo6ioCLfeemvyD50NHnsMsO8H1mATJXXggUCHDuyHTURERPlPlLUdX45r27atqqqqSrjM4sWLc7OvbxMT6fdkVrvZfxtOr3fsCGzdCixfDhxwQGbyR5QDrr8eGDdOz4ENACNHAtu3A198EW2+iIiIKHeJyA6lVFaPjMwabKJUbdmig2uANdhEScRiwLx5wK5dUeeEiIiIKDwMsIlStWxZw3P2wSZKKBbTwfWCBVHnhIiIiCg8TTLAzqdm8fkoJ78f1mATJVRaqh850BkRERHlsyYXYLdq1QoVFRW5GcQ1AUopVFRUoFWrVlFnJTnLtGQMsIkSO+AAoFMnDnRGRERE+a3JzYPds2dPlJeXY8OGDVFnhVy0atUKPXv2jDob7pSKD67N14iontMYgbEYa7CJiIgovzW5ALuwsBB9+vSJOhuUyxhgE3li/5nEYsB99wE1NUAuNFIhIiIi8qvJNREnSptTc3AG2ERJlZYCtbXAV19FnRMiIiKicDDAJvLLHDHcWj3HAJsoqVhMP7IfNhEREeWrUJuIi8gKANsA7AGwWykVs71/LoAbAIix3G+VUvO8rEsUGacpuRhgEyW1//5A167sh01ERET5KxN9sEcopTa6vPcdgGOUUptE5EQAEwAc7nFdomiwBpsoJRzojIiIiPJdpE3ElVKfKKU2Gf9+BiCLh44mMkyb1vg1BthEnpSWAgsWANXVUeeEiIiIKHhhB9gKwPsiMktELk+y7G8AvJfiukSZc/rp+pE12ES+xWJ6nMD586POCREREVHwwm4i/hOl1GoR6Q5gmoh8rZSaaV9IREZAB9g/SWHdywFcDgAtWrQI51MQJRN1gF1VBTRvDrRsGW0+iAxuPwlzoLOyMuDww52XISIiIspVodZgK6VWG4/rAUwBMNS+jIgUA3gCwKlKqQo/6xrvT1BKxZRSsebNm9y03pQtog6w27UDioqizQORjX0ebADo2RPo3p39sImIso3TGK5E5F9oAbaItBWR9uZzAMcDWGBbZj8ArwE4Xym1xM+6RFkl6gAbAJYvjzoHREmJ6H7YDLCJiLLH11/re/WLFkWdE6LcF2aV794ApoiuwmgO4Hml1FQRuQIAlFLjAYwB0BXAP43lzOm4HNcNMa9E6cmGAJsoR8RiwL//rXs2tG0bdW6IiKi8XA8+OX060L9/1Lkhym2hBdhKqW8BDHJ4fbzl+aUALvW6LlFW4SBnRCmJxXRTxHnzgCOOiDo3RERkYusiovRFOk0XUd5QSv9x7iGipKwDnRERUfaYNSvqHBDlPgbYRF45jdhkUgq46y6gTRtg8+bM5YkoB/XoAeyzDwNsIqJss2iR7r5DRKljgE3klT3AtjYLVwp45BH9fPv2zOUpaitWAOvWRZ0LykGxGANsIqJsU1cHzJ0bdS6IchsDbCKvCmw/F+t8FkoBW7Y4L5fP+vTRVZFEPsVietTapnQ/iogoF/DmJ1F6mlAkQJTE+vXAr37l/r61BltENwk3WfvU7APZAAAgAElEQVRfcyJJIiiVuFdFLKaXmTMnc3kiIqLkGGATpYcBNpHp9tuBl15yf98eLbz6asNza3PxPXsCzRZRPiot1Y8syBERRc8sxnTtyvMyUboYYBOZElW3JXvfWmvNGmyipPbZB/jRj1iQIyLKJqWlwDffANu2RZ0TotzFAJvIlCzATtS3WqmG91mDTeRJLMYpYYiIsgm77xCljwE2kYkBNlFGxWK6pmTr1qhzQkREALvvEAWBATaRKZ0m4tYAu6k0Ed+1K+ocUI4zC3KzZ0ebDyIi0vbeG+jViwE2UToYYFNG1NYCF14ILF8edU4SCCrAbio12BMnRp0DynGsKSEiyj6xGM/LROlggE0ZsXIl8MwzwAsvRJ2TBNINsM33s6EGe/16oEcP4Kuvwkujtja8bVOT0L07sN9+LMgREWWT0lJg6VJgy5aoc0KUmxhgU0ZlVUH60ksbz22dSC7VYL/7LrB2LXDffeGlkahPOjV5yebBNnGgMyKi6FlnG43F9CO771CuEpEnRWS9iCxweO9aEVEi0i2s9FlCpozKqgDb3sQ53UHOsqkGOxP9wRlgUwBiMWDZMmDTpqhzQkREIuy+Q3nhaQCj7C+KSC8AxwNYGWbiLCFTRq1eDfzwQ9S5cBHFKOKXXAIcfLD35b3KRLDfrFl426YmgwOdERFll27dgN69GWBT7lJKzQRQ6fDW/QCuB6Ac3gtM8zA3nmldunTBjBkzos4GOVi9uhWAYQCAp56ajx//2OmYz7CxY/WjecwMHtzwmvV10623Art3O2+rtha44w4dXG/Y0HhdN0VF+i/d49b+Wdq21a916ZL+tt107do4XSLDqlUHYs+efTFjxscJl6uubg7gJ3j55eVo1mxVZjJHRERx5s3rDGAQZs+ejV27tmL//fvj44/bY8aMz6POGpFdcxGx3v6ZoJSakGwlETkVwGql1Dzx0octDXkVYFdWVmL48OFRZ4McWEcP37WrGFnxNY0YoR/HjgWuvRYYPTo+wFa2m1tnn62DZydvvQXceSdQWQl8/DFw5JH+8mBPyy/7dp5/HrjuOuCcc/TzMEycqNOwpktkePNN3cjByzm5Tx+gsvJADB9+YPgZIyKiRsyZN4cMGYIjjgBGjQI++ggoLh6OLl2izRuRzW6lVMzPCiLSBsBN0M3DQ8cm4pQR1vgr65ocffaZfkzWpziMJuJhCbuJ+IcfAnffHc62qcnhQGdERNnFHOiM52bKEwcC6ANgnoisANATwGwR2SeMxBhgU0a1aJGFJ2szGM2nabrMYN9es7xgQTBzpY0cmeWTmlMuKS0FvvsOqKiIOidERAQ0jI+RdWU2ohQopb5SSnVXSvVWSvUGUA5giFIqlJGhGGBTRg0apGePWrMmgsS/+Qa46qrGAXBQAXZUNdhVVY1fcxtFfOBA4Ne/Dj9PRD6wpoSIKFr2+/GdOwMHHpiFrQ6JPBCRFwB8CqCviJSLyG8ymT4DbMoosyAdyQn7tNOARx7RgbaToKbpynSAfckljV/Lptp0yl47dwL/8z/A+vWBb9rrPNgAMGSIfmRBjogoWtbzdizG8zLlJqXUOUqpfZVShUqpnkqpibb3eyulNoaVPgNsyqiSEh2nRnLCNq8a9tu05uvJ+mAnihZ27szM3NNOFi5s/JpbE3Eiq1dfBSZMaBisLiKdOwMHHcQabCKibFJaCnz/vfv4rkTkjAE2ZVTbtkD//hEF2G5NuM0gNJ0a7F/9qmFe6EzXYDvlmzXY5IXbtHMRYE0JEVF2YfcdotQwwKaMM0cMznjlqhkAuwWd9kDVrabbTVRBbaIAmzXYlIh5rCZrvZEBsRiwcmUordWJiCgFZvcdBthE/kRfqqImwRrnlZbqQnR5eYYz4daE260G22+AHdUgZ07BUVTN1Sm3ZFGAzRFriYiyS8eOwCGHsHURkV/Rl6qoyYlsoDO/TcRzuQY7kwG22TKAck8WBdgc6IwC9+GHwNatUeeCKKex+w6Rf9GXqqhJEdFTdTVrFsEJ262JuBlIL13q/Lp9fTdR1WCziTilKosC7A4dgL59WYNNAVm/Hhg5Uo+PQfG2bgXOPpv9MTJhyhRdDVxdHXVOUhaL6RaHP4QyWzBRfoq+VEVNTuvWwIABERSkkzURf/5559dNLVt62342BNgcRZy8MH8LXufTChlrSigwO3boR6dZFpq6J54AJk8G/va3qHOS/66/Xt/QyHifOP/cigvsvkPkHwNsioRZkM5o/Oc3ALZnrlWrxst07tx4+6k0y05nmqRENdhTp6a+Xcp/IXYl8DMPtikWA1avBtauDTw71FRlyc2jrFJTox9bt442H5SV7D+ZwYP1a7z5SeQdA2yKRGkpUFGh51fMmGQ12HbW17dvd759a10mnRrs++7zv4493WSvhe2dd4BlyzKfLqXO7PaQJdN1cUoYCgxb77gzA2ynm8YUjhw+Htu3Bw49lOdlIj8YYFMkQhvobPVq4OabnWvk0gmwR492Xsa6LT+DnI0ZA9xzT/LlvEjURBwApk0LJp1kTj4ZOPjgzKRFwdqxIytGnC8pYU0JUegYYJNPsRjw5ZdR54IodzDApoywx7DFxUBhYQgF6fPO0/3KnDacToC9ebPzMtZtea3BnjkTuPNO4M9/TrycV4maiAPA8ccHkw7lH/P4ffll4Oqro80LgHbtgH79WFNC0Dd9xo3Lihs/eccccItNxMmjWEwPcrZmTdQ5IcoNDLApEi1bAgMHhlCQ3rlTP9bWNn4v2Sjidl6adFmX8VqDfcwxybfrR7IAm8iN9fidMCG6fFhEMj4DZZ+bbgJ+/3s9CnM6eC5szLw+FhZGm4+mIE+OP3OgM7YuIvKGATZllPVaE0pBOtGgTanWYNfVAdOnOy+TSg120Jwu4IxOyIssrB1kTQkBACor9WNVVWrr8xzoLk+CPsqckhJdxGGATeQNA2yKTGmpbnn97bcBbjTR9FRuAbBbkGFu4+GH3ecLZYBNucx6nGTJMRPa+AyUm1I9Ls31GEy6M/dRpq9ZlJUS/dTatgX692f3HSKvGGBTZEIpSCcKclNtIp7oDsCQIfrxwANDnfIoIacRwzMZLGVJYEYpsB6rWfI9Dhqkf6oMsJs4MzDOkuMyr1j37S23AM2bM8gOWw4dx273pNh9h8g7BtgUmQEDgBYtAr4jmijINZsa+p0Hu3lz92W6dAH23hs49tjsqsHOpCxsZkwehVhSSmUebABo04Y1JYToz2v5zLpvJ07Uj6tWRZMXyhmlpboxX3l51Dkhyn4MsCkyLVro2qpQarDtQV9dnR692+m9ZDXYZs23W3pmYcXPNF1BYhNxSlWW3hxhTQkFhoF6Yl276kezz3umvfWW/o42bIgmffKM3XeIvGOATRnhVlAuLdU1VYGV891qkROV1JMF2IlqsK1N7bKpBpuRCXmRpcdJLKbL26xUa8LSbSKepcd2VnDat1E1Eb//fv04f3406Yctj27wmN132LqIKDkG2BSpWAzYuhVYtszjCuvXJ47GzSB39273ZewFr3QDbNZgB2PrVuDLL6PORdOSxTXYAGtKmrSg+mDnUYATGKd9G9W5oKkMRpeL12Sb1q111z6el4mSY4BNGWW/hpoFaU93RFev1v2d77wz+bKJarC9BthmgSNRgG0dtTyqGuyoBzkDgK++Sn8bv/oVMHQosH178mWffx7485/TT7Opy9JCX3Gx/tmxIEcpy9JjO+uYF+WoarCbSoCdJ0pL2X2HyAsG2BSp/v2BVq08FqTNiXHfest9GTMoTtbP2sv0RF76YFtrsM3lmmIT8eLi9LdhNhHcvDn5sueeC9xzT/ppNnVZOIo4oM8JAweyKWKTxlHEw6EUMG5cw3NT1K1ZGGBHzstPLRYDKiqA778PPz9EuYwBNkWqsBAoKfEYYHspcLkF2FZK+Quws70Pdr7o0EE/3nFHtPloSqIuVCfAmpIcsGEDUFOjW58EHSAxwA6HddrJVPpgV1QA1dXB5Sffv98cPI4T/ZR9tTokasIYYFPkSkuB2bM9XN+9XKjM95LVWHsJLLwE2E5zEWVD0JJDF/N6ZoD9xBPR5qMp8XKjKSKxmB7YeMWKqHNCrrp3B447Dnjppahz4o41o/G2bWt4br1+eQ2wu3UDDjssuPywiXhOKS7WFSPsvkOUGANsilwsprvdLlmSZEEvF+BUmoh/8AFw+umNt+WlifhrrzUsay7fFJuIJ3Lttd6+u0Q3MigcId4MSnUebBMHOssR//1vONvlKOLhcLup5udcsHBhcPkxeT1ZfPkl8OabqadTUwOMH58dN8JzUMuWuvsOz8tEiTHApoxIVNbx3OTIT4ErWRNx+/uvv+68HJA88BOJNsBu3brxa8n2USYLn//4h7flnAZro3BlcRAyYADQogULck2W/Xz/ySd6cMNUt0Oa228+6kHOvBo6FDj1VGDpUv3/nDm6SrW83Nv6d9wB/Pa3wMsv+0s3VXl4/JnTq2bx5YMocqGWaEVkhYh8JSJzRaRRMUm0h0RkmYjMF5EhlvcuFJGlxt+FYeaTonXooUCbNh4K0ukE2Pa79l624aUG25ovU6YLKm3bNn4t2Ujp2XhlzMOCSNbL4lqcli11c0T29SMAwJFH6sENvZ67svEclw3s18L16/XzqANsv+f/Vav04yOP6Gk533vP23obN+rHrVv9pUf1YjFg0ybgu++izglR9spEldEIpVSJUirm8N6JAA42/i4H8CgAiEgXALcBOBzAUAC3iUjnDOSV7F55RV/4zLvFaXK6hjZvDgwe7KOmKogA208fbC81q9agPdNBi5cAO8A8ffcd8AZ+Htj26jHAzrws7oMNcKAzQuMvv6rK3/o8r8Sz/+bXrdPPo77Zlu735HV9Hg9pY/cdouSibpN5KoBnlPYZgE4isi+AEwBMU0pVKqU2AZgGYFSUGW2yzGZUc+eGmkxpqW7plfAmupcLo7mM3ybibssByQNse816pmsCunRJvkyyPuk+PPYYcAZeQxXapLwNRyz4ZF7UheokYjFgyxZg+fKoc0IZ59ZiibM0pCdbm4j7Pf+LALt2ARMnBp+nMOTRXUJ23yFKLuwAWwF4X0RmicjlDu//CMAqy//lxmtur1NUQr44xGLAjh3A118nWCioJuJet+G1ibi5bFQBdsuW8f/v2gX83//Fv5Zsfyxc6Pk73r0bqEMzzEWJz4wmwT7YmZflhT6zpuTLL6PNB0XALeBiE/H0BDHIWZDSCbDHjvW27M6dwNVXA5s3+0sjFUoBF14IfPxx+GkFzOtPpkUL3X2HATaRu7BLtD9RSg2Bbgr+OxE5OugERORyESkTkbLdu3cHvXnKEE9NjoLsgx1mDXYqBZXjj/e/jsn62U48EbjpJuDhh+OXsQf91nVWrtS3pK+6yleyZXDq9eExn05Yg515WV6DXVSk7x+xH3YTlm53F55X4rkF2LnWMkDEez/qZ54BHnoIuOWWhtfCugHzz3/q9I46KpztZ4CXn0wsps/LWX4JIYpMqAG2Umq18bgewBTo/tRWqwH0svzf03jN7XWnNCYopWJKqVhzTvMTvAwVTg45BGjXLoA7om5Brv1OvZ8abL99sFMpqKRzsbeuO3UqsGhR42USXQW3b9eP77zjK9nAA2zWYGdeltfyFRYCJSUMsJsktxuqrMFOTz41EbdeMxKtb3622trwyzTz58f/n6c3eGIxfX+D3XeInIVWohWRtiLS3nwO4HgAC2yLvQngAmM08WEAtiil1gL4N4DjRaSzMbjZ8cZrlKOSlXWaNQOGDAmwBjvRMtaRU71sI1Hgt+++zn2wr7jCeW7tZGmFJVENthl8+ywI+A6wk93qztOCSFazficBH4PpzoNtMqeEYU1JE5NuE/Fk22mq8qWJOOCt+1aq205VEzneONAZUWJhVhntDeBjEZkH4AsA7yilporIFSJyhbHMuwC+BbAMwOMArgQApVQlgDsBfGn8/cV4jfJYaakeS821pb+XANttkDPrOi++CPTt676NM8+MX8caYB96aPI87dmjRwJzmlvbTVA12G6SNZlPwTfoi21o530FazoVFUB1dfz7uV4wmTFDH1u5JAei1lgM2LYtsIkMKNfkwhSDuSRba7BTWc9rqyen63RYx5HbdeynP829ZvgJ9O8PtGrFAJvITWgBtlLqW6XUIOOvSCl1l/H6eKXUeOO5Ukr9Til1oFJqoFKqzLL+k0qpg4y/p8LKJ3kU0MUoUQwViwE1Nc4tnH3nJVFA+cEHidf96U/j18lEH+wgA2ynbXkJsD0GuObiCgWYg8EeM2nLQ7duwLBh8e97KSxdcEH2BuIjRgDnnBN1LvzJgWCFNSU5JMgbNuk2ESdn+VKDvXu39ybi1hvvYV8/3La/Zg3w0kvAG2+Em36GFBYCgwbxvEzkhp0eKbEMBjNJC9LpDHJmlewusnnRVgooLwcmTEieXrp9sNMp3HjZH4nylEITcYFex1czcftnTKWv2rPPek+PksuBGux+/YDWrVmQywlhBNippsFA3Fm2DnLmt6xx3HFJph1x2HbQx8T99wMzZ3pLGwDOPRc47bRg8xChWAyYPTsnLiNEGccAm7xJdmF69VXgk0/SSuKgg4AOHUIKsK3rJBtt3prOz38OfPhh4/es/4tkfpCzW27R/by9ruu0P5TS8x+lUIPQFlXoiVXpBdh2Tp/jqaeA997zngb5kwNBSPPmHOgsZ4QRpKVbg52tLV6i4rb/7Ofn8eOBTp2iy48XXrvkhNVE/E9/Ao45xjmtROrqgDZt9D7OIgl3iYguD1nEYnqM1CVLws0XUS5igE3BOPNM4Mgj09pEQYHuh10fYP/73/qkbg5I5uXC5aUPdrILqzkavVKN5820N2O2juSUySbid92l+3l75bQ/HnsMGDoUePtt/ZrPgmgMZcEG2E4uuQT42c/8r0fe5EjVg1lTEnUlGyWRiRpsjiKeHrdm4fb99dvfAlu2hP+j83uD121gMy9NxIMaeTERL9vftUuPQXL11eHmJUWuH+Gtt+L+ZfcdIncMsCmrlJbqlsO7dgF44AH9ov3snW4T8UTuvrshwK6r021TrRIV+lKpwY7FgOHD9bo7d+rBv/xKpYm4UsDChfr5smX6MYUAeykOwRZ08JYfpYDPPgtudGBKX47s81gMqKoCvvkm6pxQQqzBzn5urbns10wzkE3W4isoXr+nVKZjDauJeKK0EjH3aY5PLXvooey+Q+SGATY5+/vfGwKvAHi9rsViOs5cuBANFx/zYhRUE/FErHNrKtU4wHZa3n5B9XMRtzYxP/VUPfiXX6kMcmZdLsVBZmLQV9XZGJI8fTMPbs29V6zQXzxlVg7VYAMsyGU9DnKW/dwCbPt+Na+/tbWZy48XqdwwybZpusx96nWasSzVvDkweDC77xA5YYBNjW3cCNx4ox5EJMPiCtLmBd6sFfESYJvv2UcK93oRLyhoCLBTrcFONcD+dwpTvd96K/Dxx/GvrV3beLlE82CnOIp4KfRV1XMz8bo655HCd+4E+vSJ7+tOmWE/LsrLA9t0kK0x+/YF2rZlQS7rBVmDzUHOwuE2sJl9f2WqBjudebCtvDYRt6cbBTPAzvEabIDdd4jcMMCmxswCzI4dgd/5Tba5Aw7Q46rEBdj2C/zmzcCDDya+QE6dGv9/KjXYTgG20/L2i7c1rTvv1M2ik62f6sX+r39tvH376NxAKPNgd0MF9seKxgF2ohps+wGwbRtrrqNk3/e9ekWTjySaNdM1JazBznJhtIhItQY7qMAt32RrDbbX7ymdGuwopulySm/XLv2YJwH2jh3eB3QnyhQReVJE1ovIAstr/ysiX4vIfBGZIiKhjeTIAJsai/DOrog+YZeVoeEO+saN8QWBjRuBa64BPvrIeQPpZsAMsNet81eDbRYuX3ut4fUxY4Af/9g9verq9AJsrxIF2ClM02VyHOjMT4Bt3VdWL7/MgnEm5NDNjVgMmDMnc11Cc9rkyamN55CuMGqw0w2wKZ51v7z5pvPrQPb2wbZyahHlddthHR+pNBGvq9M3yzduDCdPISot1Df0efOTstDTAEbZXpsGYIBSqhjAEgB/DitxBtjkznqhyGBhpbQU+OorYKe00i9ceaUe0dSeh5oa7xtNpYn4scfGF0DcmPvJvCvtx/z5jQPsMPa1U8HXPuK6r3mwdR5jKMO3OBCV6Jx8Jac2w26fddy4xnm94ALP+QvEI480bgmRy/bsAdasiX8txwLs6mpg8eKoc5LlVq0Czj4bOOuszKdt3kQ744z0txXUKOK8URfPuv+s1Y72m7CZrsH208rMZA2wwxxFvLYW2LTJf/4SbQ9o2McffaS7e11+uf+8RazvOYPRFtvZfYeyjlJqJoBK22vvK6XMu4afAegZVvqi8ugub69evdSzzz4bdTZy3+7dwLx5+uTfoQNQWan7yHbp4r6OeXYtLXV8e8WKNrj44qG47baFGD58Q8LkP/poL9x+exHGj3kLfTsYEywWFAD9+wMLFjQsePDBOn9WS5boZsfWvOzZA8ydmzDNer16AS1bug/w1rq1LuWbWrTQeWvdWreTcgtYrPvFfiXq0EHnsaqq8bJu/F7NioqAVq0a1isp0cHW+vVA58668NCqlV4uiUceORDvvtUd79w1DrOW7IfrJpyFsZdPRukhK/UCQ4bEFzLMNIuLda3a6tUN7/XurfsE2L+f9u0bvsdEvOyrVCU5ptNePtPWrNH984uLgcJC/dry5Y2nogso/w8+eDCmT++ON974byDbW7myDS68cChuuOFrjBr1QyDbzEs7d+rzZMuWwIAB4aZlPw8VFzd0UUn3OCov162IevYE9t67Ia2BA/V5N5nqamDRIn1u7t8/vbzkk61bgaVL9fM2bfR1C9DXvu7dG5abP18Hgvb9nep5btcuXaaw1zovWqS/q379dH6SmTMn/qawWYbt3Rvo2tV5ncpK4LvvdBmmWTNgwwZgv/2AvfbylnfzPGn/zE77wjxuzdfNz2dVVKRHcm3RQu/fbdt02aVDB12uicgnn3TFzTcPxPjxs9C3r+366/a9z5qFqx/5Jfa0aY9x4+ZkJqPU5I0YMWIXgK8sL01QSk2wLycivQG8rZRqdDEUkbcAvKSUei6UTCql8uavTZs2igKwdq0esqt7d6XOOUc/nzQp8TrmMF8uFi7Ub7/8cvLkv/tOL/voEf9q2G737kotXtzwP6DUu+82XnnkyMZ5eeWV+PUS/T3wgFJvveX+/uDB8f/37KlU375KnX22Uj16uK/ntK/MvxNOUGro0Ib/q6uT7ySvn8f8mzcvfr1Nm5T63e/087PO0o9FRcnTVUr98Y9KtccWpQBViU4KUOpu3NCw7Z07nfO6aJFSF18cn6+nnlJq8+bG+R0xwtvnCpPfNDKRp3QMGqTzN3t2w2s/+1lo+/R3v1Oqa9fANqf27FGqXTu9XUrAPE/27etvvZoa/2nZj52VK4M7jv74R72dsWPj01q61Nv6c+bo5QcMSD8v+WTq1IZ9edhhDc8ffDB+uZ499etffx3/eqrfL6BUaWnj14uL9XtlZd6207ZtQx7atGl4/vTT8ct9+62+viilyy/mcmZ648b5y7v9M+/Z4/z61VfHv15U1Ph3Mnu2fjzwQL3MtGn6/5EjvecpBG++meCrcPveAfVH3KdatVKqtjb0LBIppZQCUKVU8rgQQG8ACxxevxnAFBgVzWH8sYk4uQuwaZ0+nr3Zf399I7qs4oCGF5MNNmYy89zZ0mTZrK1z0qpV/P/WJuJeiehmmfbmt04mTXJe37qDwhiO08sgZyl8352xGQdgubeRxK+5BnjqqcavOx0cfr8DSk0ONREvKNCVJ+zrl4T5W/fzG3r/fX0u/OIL7+s4/W4zMYq4Pd2dO3Vt/QsvJF6ONOt+sV4X7PsrjD7YTi2v0vmeEnU5Oukk4OKLG7eEchoENBXpDOhn/k7M32iiGVIeeMDf7zICMZShpkZX1hNlOxG5CMDJAM41gvVQsBRLWUdEF6RnVewf/4b9d+D0uzAvetamX4kC7JYtGyfup2BqXhg//TT5srNmAeed57yNTAfYTu/5nKbL1GigM7fzlVOTb/O+uNWIEQywMyXs/pUBi8V0b4Icy3Zm2QvvXvznP/rRbZ56rzIxr7r9fPHDD7r58Q03OC/HPtjx3K419v2aa32wL7pI/3/iiXoZc0yU8nLn30K65Wq367R9u07Hn/k7M99LFGD/8Y/A4YenlscMMafsZD9synYiMgrA9QB+rpTaEWZaLMVm0tSpwEMP+V/v0EOBP/0p+Py4yYI7/7EYsKCyB6ph1DA73UVPFGBba+YSBdj2vnzJAmyni6XXAtyKFe7bDDvAdpoHO6DvOYYyfI/e2IiuDdt24tZv0r58mzYMsMNkPV5DDIiUCj62KS3VP23WlCRgfqdmDaQX5g3JDYnHx4iTqRrsRK1vrMt5uQFL7tca+3522/9hSTfANpkDU7Zvrx+rqsK5yeK2X7x8jjFj4v83P0eOHrMHYynat2frIsouIvICgE8B9BWRchH5DYBxANoDmCYic0VkfFjpsxSbSSeeCFx9tf/1vvkGuP/+4POTTAgXJa+bjMWA3XXNMB/F+oU9e7xdfMyLnnVEbz8BdrIm4unsE7cLckFB/GcLY1oUe9ovvtjwPIWaHnMUcUAH2AAwC0kGvfEaYCvFADtTcqxAFzMaSrAgl0AqNdhmSx4/tZWJbnAGwaxBtZ8P/QbYrMGO57UGO9nrYeQnDG5zX2eqBtuLTN/MCFgBFLvvUNZRSp2jlNpXKVWolOqplJqolDpIKdVLKVVi/F0RVvosxWaKdfTrbOdUMMnwib++IG02PXYq+CUq4FkDbLOg5sReCA2zBtttOZH4/ZuJJuK/+13DSOlpzIMNAEMwG4Dlu3IrYLjd6HCqoWKAnRk5FmAfeCDQsSMLclSho34AACAASURBVAmlUoMdVDAa5LnLvCFnn/7QraY1x47lyHjtg53s9VTt2RPfUiKoJuJuy7kF2OnyUiZ6/31vZb+warDr6hpGiQ9ZLKYnn2H3nSxw9tn6QkmRYik2U8xpG3KBtbDl9+IXkJ49ge6ttzUEbbt3e8uDuYy1iXiiKV3sF16/fbD9cLvyRNFEHGiYFizNALsjtuJgLEkeYLsNVMca7MzIgwCEA515kMogZ6mcA8KuwTbP2/aB+NhEPD1R12CPHq2nA7PPK51OzW8iYQXYXmqwb77Z27a81GAfe6y3bVndeCPQtq3nIDudr9rsvrNwYerboIBMnqyn46NIsRSbKW3bRp0D/9asaWhKnOHCighQuveqhmbHXgNspxrsRDU59kJosibiTu95uXjPnOne9NseYGeiiTjQEPAHUHvVaKAzq7599eOJJ3rLGwPscDiNnpuDQUhpqf4o9orNvFZXB/zhD3o+Xi/LAqn9htINsIO8OWg2W7d/0Qyw0xN1gD1lin7cvDm17VuP0UwH2K+9Fr9dJ04zdCTjpRXG9OnetmVlztph3kz3KJXdxe47RPFYis2UXLrYh5DXVDYZ27scC1GEHWjtvAHztSuvbLiQWANsEX22T5S43xpsp+W9OOaY5DXY5rYyVYNtTv3x9tu+NqW2Nh4NPIYylKMX1qF74/1tDqDktl9Zgx2dXDovGWIx/fPOpV43aZszB3j4YeCXv0y+bCp9sFM5DsKuwTa7lKQbYLMPdryoA2y37ymVdDLdRPwXv2h4HkYf7LDOx6lud+tWYPt2T4uy+05ueO45f2NZUupYis2Ub76JOgfpiaAgHtunHHVohrkocR712vz/0UeBSy7Rz+0FvGnTgg2wvWzDTbIA20w309N0WfPhxQ8/NHopbqAzpfRnNQvGiZq/uX2vDLDDY/2eczTABppYQc5P4JovfbDNvKTbRJwBdjy3PtjpjIqdilSDSq812LNnN2w/jEHO3FqTpHOjIOh9ne6x37GjHo398889JRWLNbHzco7Ztg04/3zgwQejzknTwFJspowd6/rWokXAVVeFE1f5smyZPktam0GZogiw914FwBg8y2v6iWq6ndgvQMmaiHvZhhuvNdhhDCgXZIBdVxc3ijgADMYcCOoavqsf/7jxHONu3wObiIcvqhGCQ9CnD9C5cxMryJnfk5ffRSpNxFMJRsNuIu40ngbg/fyYg8d2RkRdg+0mlUHO0mkinu7nmjQpvfWBxvNgZ+so4sOGeVosFtPdd+w/WcoO5uHF+cozg6XYLDBtGvDII1nQ5NH81VmncAqYn/Jbj/bbsC/WuA+e5aWJor1/s10qo4jffDPQtav7Mm6S9cEO8yLrpeDrI8C2a4/t6Itv9HdVV+d8BvdagGOAHbwgmzN6FGbFV5Mb6MzPIGTpBNiPPAI8+6y/dayCHD/C3H6yebAjGogzZwUVYCulb8b7HQwhyEDez+8haOagY9bBOzdsAF5/3fs27DfOsq2JuE+lpboeIfKyLCWUrOckBYOl2Ci4HNmRFxiTNeXNNBGUYlZDs2Mv/AbYqfTB/utf4wPIoGqwTTlQg+2kfqAz++3rZE0BnQrMbNYZrIhqRsL6GmMxXYirqQln+1nHTw1zun2w//Uv7+vZhRFgJ7ux6nU50tyuNX4D3/ff132Sb7sttXykenLwOk2Xqa4u3Bu23bs3PD/ppPguVH5r5YM+T2f4Opo33Xeqq4GbbsrbC8zGjcDKlVHnIv8xwI6CS21SZCel6mp969HsZ5MtzZQKChBDGRajH7bXtfF2sfJ7cyDVebBTKbxF2UQ85BpsQAfYa9EDa1b7LKixiXj4rN9/jvfBBnRBrrYW+OqrqHOSIX6aiKcbYHs9DzgdO5mYBNdvgO3weTZuBC64oGEg6yblzDMbnqdTg71xo370UlL3cp5JpYm41wA7jEDTKb9eRvm3sjcRj/h87Cn5BAv17g106ZIHAfZ99wF3353XnZVz/jvKASzFZor1BO9ylz+yfhFz5+oBQf7xD/2/UzCWqRP/Z58BS5bo5yKIoQwKBZhTN8g5T/Z8pdtEvKAgcYDrVOOdL32wv/gC6N8/6WKqznl/1g90NtdlcCU/Ndh+Bmii5DI9gFHI8qamxCs/Ndh+gvF0ZKqJeLLXU6jB/vJL3RL+/ffTyF8+sF7rUz1H+A2eM33OCasGO8iuCWFPNedzOwlPMw88kHC9WCwP+viaNdd5Nhek9TBoMtfOCDHAjoJLIWTevIh+z/YLawgBtufVf/zjhnmTAZRCn6nLlEMzcaUaB61+Bzlr3jz+f5HE01Kkcyfc6zzYUQXYALB4ceL39+wBPv644f+OHeuflmAuCrAHZXMd9qlbHpRyrsHO5Sbi2Ri0Ov2mJ0/O2ZLQfvvpYRCaTCEhrP6pTtv3GoyEXYPtp8VLovUT7IfADv/164Frrw32BkMmpFODne6AeKksk4pM1mCnm04udHN47rmEb5eW6pZFOd26OpVBH3OM47mvulqPw5EtrVhzHAPsKNguwuZv2dfcrnPn6h9/ENN/2Qvf2fLjEsE+WIcfoRyz6kqcl7EX6Pw2EXcKsLc1nuc5WT49yfYm4on8+9/6jPzRR8Du2oZRxC37ti12oB8Wo+ydxtN42ZdN+LqfJuK//rXeX5WV3pb34g9/AO64I/X1s7FQ5NTX8uyzo8lLAPKmpsSrsGulU2ki7iSMJuIh9sEO7AZNUZFuAfbeewFtMEMyNYp4omDUb/Nov8fngw/6v/HuhXX98nLglltS36a5ntebR3azZwPvvuv+/po1qeXLSZL9H4vpIu78+cElmXF5HmCLuAx0dvPNekojp5mEyDcG2FFIcNL0fME37yK+9Vb6+fESYEc0yBlgGTzLfjNBqcZV/ukOclZQAPz0p96X9yPbm4gnMmqUvnKa/e5Mtn0bQxnKlneG4x4Po4n4Cy8A//u/ujrz66+9rZPMww8Dt9+e+vrZcoPKystgRjnGHOisujrqnGSAn1HEU5HKMRFVDXaAgeCsWQH9XM3zYjb+9hNJZ5AzP4I85/gdQ2LatPAD7HPPBe66q/GN3h9cbja7bSvVGuzSUj3AWqL3rS3P0uEhwAZyvHVRngfYhx4KbNoEfPed7Q3z+PVbyUSOGGBHweWk2aKFjxqZIAtcGazB9pVdS4D9DQ7F1hUOtZT2vKZ7c0AEaNXKRyaRfg12QUH4TcSDmp/2l79M+HYMZViPvVGOno3f9NPkc+JE73l69VX9uGyZ93VSccABwNFHJ18uGwvZXvpa5phYTH+sefOizkkGhF3gy+Ym4l5rsFOo/duyxf+4VAnlWoE8ihpst2M5zBt/Ttv+y1+C26bTxM9Dh3qvOfZ6DPud/8q6j80RIVu3BgYP9rcdqyTnh169gL32YoCdzVxvgmTJYHv5ggF2pni46zpokI+TUipznSbbltv/QOQ12AAwe3Hr+PfnzEme92Q12C5pJn0/lSaVTv3z3npLr2/tJ5aNNdhuHGqwAeip1Ux+p+n68kt/eTCrMO3N/YN05pn6du9//pN82WwMYCOowQ47mVLjEMvpgpxXfpqIp1sbnc4o4mH0QVYqfrt+m4g7fB7rooF2M8i1Arl1v4Y5EGKQAXZQ+zjdIeST3ZTyM1Cn2zFs/04GDgTWrfO+XSc1NbqLYaqS7H8RfW7O6e47Zpki137PHg0Y4FKhF/Z87E0MA+ws4mtwCPPEG8Roy1neRNwc6GzWmn3j3//rX5PXbqTSRNxDnlz/T8SpdqdXL72N6mpgxw79WpgB9sEHA7/6VfDbNwzCPDTDbt2k385rDbZTbUAi5n4rLPS3nh9mLbkX2Xhxsv7G//73jOUxzPJJz556CtqcLsh55afFUiq1L9nYB9uaJ+vc3G61fCk2r037Bs2+lutSLhfIc7GJeBTpm6zHYboVHX6O4USDsGaJWAxYuLDh0pxzHnpIP+by79mBeTi1aOFSocca7EAxwI6Cy8GbdG7XVasanudoE/FU7IWN2A/fo2ztjxq/6VSDnU7TM6812H7WMTkVPs1pvqx9tcJsIm7t650iBffWGK1RgwFYgC9xWMOLFRX60e3GTbonc/OOVJg12H5k48XJuu8nTwa+/z66vATEHOisSdVg+wmwU5UtNdjW7VdVOb++cycwYkTi9RN8nhYtAjh+rOfuXC6Qewmw/bYuctpGmIG8l/SD8MADut+1ySnATuU6bv/9OOXbnlaiG9I++6t72k0iesyBBAOL5k33nVz+PSdhDhIad5gywA4UA+wo2A5e81+zX4RrjczBBzc8j6KJeF1dyn15U/q9Wk5uMZShzF6D7bThurrGtfphBNj77Qecfjrw4ovet+0UYBcUZKYvmvndBT1lScuWjV4qxSzMQmnDQGfmHaM//cl5G9keYPvNXyYvTmed5fgdNGL/3QbVJz9isRiwaFF8/JWX/ATYqdx8DaqJeFh9sK2/bWu6Eyc23CxK4Xc3aFCAA50BWVUgr6vzOVXSPfc4v27dr0OHppYZp+/mySeB//43te1Fzd5/26kloZeDyh7Q2AdtddpvY8YA553X8L/fMWM8kH8+4n4si+hO1l27uq6fFwOdAVn1ew5aaanDGBRmPJFllWy5igF2Ftl/f6BrlzqUfe5S+LXeqfTTJy8ZL4VvpYDjj89sLeHatfVPYyjDssqu2IRO8cs43RywXuz89sFOtj9vvlk/NmumpzI4/PD0+mCbNdhWYTURb94c+PbbQC4aAqVv+DgUymIoQwW64Xvs7z1v6TDvpIc1hZHf/GUywH7llcaFMiepTv+S5UpL9UdLp0thTvAaYG/fDlxyif/tW4+PbGkibmU9p1vPo9b0UmgiHovpXbZkSZr5M9lrDO+9F9iwIaCN+3PvvbrLbto/9WQb8JKA0zK33Qb85Cf+tgP4H0UcAE47rfFrBx3kbV0n9nRTrcG2B9j22minz/fcc8CkScm3nY4nHk9r9R49gH32aSLdd3KQ2foLsN0EYQ12oBhgZ4qHi4IIUFo5DWUvexjWNIom4v/3f+mn5ccTT9Q/rR/oDEPil3EqVIVZg33ssd63ZecUYDvVYIc9inhQd2WnTQM6d270suNAZ26CaCJuCqtW1u92s/HilKcBdt7UlCTj9Ybq+PGNp9LzK9tqsIH4c7q1uUKi66qHmxJJW435ZU3r88+BG24ALr44oI37s2aNnlgh7d4gbueKVFtIuG0nzADbSUmJfqyq8jZ4pZW9ybtTDbaf7hJ+Amw/wqiB/fTThufTp7smW1rqcF4uLQUuvzz4PIUlj2uw+/fXjR/izn0MsAPFADuLiOjgZMGOA5LP7RpkE/EMDnKW6vlqCGYDcAjanGqw7bXsQQbY6azjtF8zWYNtTdOLH35IPEqJU94BFGM+CrHLeaCzZHlLR1gBtt9+pdl4ccrycRZS1aOHHmMq72tKvN5QTfXYy8ZRxK1NxK0BjHWQJy8BdoJN9+unZy0K7AaNNT9msLR1a0AbT03any2sUcSDkE4AZObjggv09IuWFnNJOc1WkmwZJ8maiGf7efqFF1zfisWAxYttY7LNng08nl7teEblcYBdWKjvMTnWYGf7cZcjGGBHIcEFJoYy7EHz5INDmNsIokDjpQ92xLqiEn06VTYO2pL1wQ56FPF0OOUjUwG2NcDy+hn33dd9ACFA59thWy2xCwOwwHuAHVSBK6zjNh8C7DytwQaayEBnqYwMnut9sK3puAXY1vNPCjXYzZs7FDKDEmQ3rjRkXYCdzjJBnuM3bdKPc+boRz9DXgfVRNw+LVLQNdgRisWaSPedHGI/nMzp1OoPVdZgB4oBdhRcBjkDLM1rk9XImL+I3/0u/aEa063BXrw4vfQ9iu27unHQlqwGO+h5sNNZx2m/ZnsT8S++aPRS3CjiLtuKoUwPdJZs1+dCE/F8CLAjqMHO1G4oLQW+/hrYti0z6UUilQA7le2nm0ZYo4h7aSKeaP0EYjFdsRbI6cOanyC7caUh5QDb2oIgXUFs45579HHgp6Y5EbN5cxC/Lacm4l4OKHtAY18nyCbiGT4OS43GhjnduiiXarAHDfI9rkCjMSgYYAeKAXamePyh9kQ5umNd8ouitYCc7hnMb4A9ZkzDnda6Ot2ZIwNie5fjOxyACnRxzpeZnzD7YKezTpQ12NaapaAuGi412IAOsDehC777zsN2cq2JeF0dcN11tuE3LbLx4hRRDXYmyiexmP44ZkVUVtiyBVi9OrjteQ0C7O8vWqQnpPW6fS9pOK1jykQfbOvvMVENtgfmYD87dgDffJNCHu1OOAH46KP4/ERcSJ81K82fe6aaiCdL589/Tj8fTvx2t6urazwXtdO6QVyPMnwt8Z1cgmN73311F56cbl2USwH2/PnuZRIb82M1GsPE3qKC0sIAO1M89kES6GmOkp6UrNsoLEwra77vmt55J/Doo/q5x+AoiN9r6d56HvC4ftjW9Ldt0yNK2+clDXIU8XQ45SNTNdjW5m9BjSLu0gcbaGiJkfQ4Xr069alf7DIVYC9eDNx3H3DGGc7LZ+PFKU/7YANZWlNSVAT07Bnc9lJtIl5UBAwY4H37XtLYuRO4+27n+Xetv5WgfgdKxZ+XrWmk2AfbKq2B8pzSmDAh/r2ImoibyW/e/P/sfXecXUX5/jO7m03b9N5ISEjv2UNTkKJYgICACIIKKKhIF0SJIkhRUDqoX0L/AdIFIhZ6FUHupveeQHonZZPs7p3fH3Nn75y5U885t2yyz+eze+89Z8p75kx7520seETsgpIgJul6kqBt5Ur26Tq2ZEZf5+Qsig22jCTXEo+yCJKpt8mb7zQlBptDPvwxYNgwoE0bYe1slmAnimYGuxgweBEHGHNije0qTt5xQ2fJC4EuTJcIj0GcFCZ0ZxKhEIMt0vXyy+qMSUmwb7zRP4+NjkJJsF3VKn1gkGCPwmxUYo99cX3jjWRoAQrHYPN6dO+pFBcnHwl2KdJvQM+ejJctqY1cktJrIP/Mms87v/NOYNIk4N57c++JEuy46uI6mni5tbXmEHWGQwmx6KFDgbZtI/Yf1RzA6SsRFXEg5ti44IL4z1Cqc8orr2S/uz7jPfe4pUuCwW7iB6FBwDRDmqz5TgmMXW949JmKCmD8eGF+aGawE0Uzg10oeAzUACmk0xbTanEQJS3BVjEqr70W/n3ttezTdSDydDEY806VO3EQFoXtsMV20DkpSYrBvugie/6//AW47DL1vWLaYOeLwdaUVYk6jMFM+8YuCsOgy1NIFXETHaW4OPloqTTBTZ0yJMy+BJFZ27MnHCpHRBJj2zYm+VyiCgcmMtgu8dlNEPtoq1bZ73w8tmkDXHpp9no6HclbdXm5tMn0gWrO4W1QAiriVVVAy5Yxx4aoEaZCUtLpYsybc+f659m9O/xbpyVXahJsLzj2WUvfLknzHR/s4ww2wNbORh8UzV7EE0Uzg10MWCZNJ/VasYy4EmwXBvvvf7fTYcJUFmaL/N9fPAiTkE4jQCrMYIv1q1QW5TQ2xLXBNjCdSjooTY7BrqrS3/NREU9IpT5AClOnAmnTYh2lvQ8+WH290Ay2Si0QKE0G2ydSQBNcXIOAOWrZtk1x8z//AZ57ruA0JQpRgn3FFcAXvmA3GnYdW7t3A9df756P33/oodx7+WCwKQ0fIuvGeUMDcPfdufkd2iEImLdjb6G7C4NdRC/ilZXM91Ek8wmbPaePtMt08MHL2bGDjdVCQlwX48zbqrxRnJy5lFsIJMRYcvOdTz5JpLhmxISqO3EfFPPno1mCnTCaGexCwWArJvfl3liDnj0tDLY4eSetIp6kJ1gOzvwa9d4tSKdRjRqsRH+sR7fGa41QtYN8uqzaFIowbYbiqILrrldV5dYZlcExTYqbN2e/x2SwG72Imw4TwBjsbduAJRikLyzKQq7T2MgXY6hjTpuSBNtHRbyJMtiARlJyxBHAt79dUHoShyjB5g8pjuk4WLcumXKA8NqRlMMzSsN90rQ+PfpoOJ8ForOf2toIATFUTFSJqYgHgRSKR0ZZGXDssSxeGYdL7G7uhdsFLnPieeexsZqUl3AXiAx2nHW3VBnsqH3P9VDIUn737kC/fiXmH8MHTVGCrfJFcdttmtPn7NpZU4NmJ2cJo5nBLlFYnUMkqSIuh2LyYbB9B2Kc+YrSbBgzboct1l9ZqahPYrBbt7bQF0HaKkuwXRbLiy9mhw1duxZGRVy0T7ctGq71G2ywAeasD4B7PGxX6Pp7viTYKk/1gJ+mgi8++ohJKl3xxBPm+z5Ozpogg80lJfu0mjiQnw2frIlh21yLTKyMfEmwxTFlWp9U7aO6xo1Ca2sBxOg/JSzB5tVXVzN+efFiTcJWrdi6KPaDTLsY8cAD/sSYwJn6TZvU9888070+VyTBYANqDT8fFXEdSl2C7agdss/Py6UEWVvk1VeBn/88ZE4jvrYhQ5icJ5VCswQ7YTQz2MWAQ+cNAkts1yRVxB9/PPzbZ6HxtcGOg3QaE8BUzRsZbBWtPXvq67bREXcDa8ov0kopsyG0pQOAK68E/vnPeHSJcFnULe1k8yIOACMxBy2x28xgR2lv3SFJoRhs28Y5ib5++OHAXXe5l3Xlleb7RXByVsg1uls34IAD9uGNHNcAsh2mRhlPMoNtK+PTT/X3ROY3SQbbVYKtyq/CU0+xzxdfBCBtMn3QRCTYgOHZOJNJKWNyd+5MfvD6rME6XyoDBpjLjYKkGGwVSkGC7YnG6hI8FAoCYNEirQC1tFHKjObu3cDll+dqm6xfn/1OabaPa5iJkA+KZgY7UeSdwSaElBNCphFCXlHcu5MQMj3zt5AQslW41yDcm5JvOgsKixdxIOscYvp0TRlJehFPEppno2l+3WOzIT9XOo322I6hmJ9l2sT6eJvcdFP2mixRtk0cUVTEZfV/l8VS/P5//xdOJy/0d9wBnHCCni5fuEiw5cMAXTmG9mqBeozD9LDXd19afPLki8Eupoq4WFaPHsBpp6nT2Z69SE7OCslb7FOSkmuvBd58M/ubO4c0+VmQ4dr4Ol8CUZCkBJtDnlNNfd0xLnbo1qZNKCuL6CivxJ2cAcCId/+CVi3TZjVdvk526MD0en3msGeftafxKU8nPc/Hpl90WFaKDHZcmkxh7Azmekl2WX7Ak3HD07RQytpcDzzAfE7ccEP4uujHQNzLmfzlBMzyqJ6WZ/M1IzYKIcG+DIDSsolSegWldByldByAewH8Tbhdy+9RSk8qAJ35heeMZVRZa2gIe/YsJoOtk+7p0vm0g1zWn/8MAGFHZ+JEwL/L7aFiwjlkeuIyfFEYbFkiM3s2K/Pjj/3ocN2AuEiwXRhsh7ICpFCDar2jsxUrzLTo6FOh0CrihWCwxfewfj3wt7+p09mefR93cgawTcKSJcCWLcWmJAHcdBPwla9kf/PNcFUVMx9wgetcJvfjONIrse8UW0XcZc15/nlmpjN/PoKARe7wMh1X0VJCDDYBRcWlP8V4TDMfHog07tpVXAm27KXbNV8UiPNm0uW7zKOffMJU34shwTYd1iXYZ5u0+U4pS3J539U5YQXCezkLg717NzB3U49svmbERl4ZbEJIXwAnAHjQIfl3ADyVT3qKCp8FBkzLuU8fzaR09dXhMC1JSiB8oWM+dPCZuDVlVaMGq9AXa9CT6bbI6eX2MDHYMkxt6UK7HCpGR4epD/zjH+zTRTIQBb4SbF2bWSTYAGOwd6AdFmKIOsGyZWZadDjmmNxr+5INtm+4DF8Jtvj74IOBDz7I/m7CDDbQRCUlNrhKsJPYGMcpI8kxGEVF3CSxU6VbmTngW7QI1dVME3/OHA8aI8bhLhwYDdWYmg3F07u3JqnfHsWPDEPZ8vtMIhqIK1zWORviSp+feaZkVMQbkaANdpcuTLu/STLYTXEtlMeawGDrulOjo7P1fXPLaEZk5FuCfReAqwEYeykhpD+AAwGIbilbEUJShJCPCCHfzCONhYfUebWdfuAmpF5QSPhEh1XFhiuDnUnnvNcwSIJzHJ3JdYsSbF8V8SgMtryp4wyyDFepsG2TGiV2pwhfCfaDmvMxiw02kCdHZ4SoQ3W5bO537wYmTvRzF1wMFXFfW6g4EuxPPgn3+6a4qUBCkpLvfY+1/cqVidCUGDiDLcaDzheSYrDjjgOuiiCvBSbnWp4SbIJsuVZbZQC48Uamvs+hYrA/+YSpbZYCg50hIdjzAXbsYKHsUFUFnHEGMGECu9mmTS6Nqnd37rkx6DAcci9caM+fTgOvvRa9flO5HNyWdf58YOtWxvivXm0vIwmNqnwx2La+pzusSrjPNlnznYULowsBigX50MhBgn3QQUD79kBqTd/cMpoRGXljsAkhJwJYTyl1cdB/JoDnKaXijNSfUhoAOAvAXYQQZawfQsiPMox4qj4f4aWSQoQJK1g1BQv39MfnaBe7rIIhqYFpWFjGYxoI0noGW2QWpk4Nn4jbFizOnEdVk6QUWL5cf88FNgnpvfd6kxWCiwRb3BxceGHodihMl6WdhmMeWmOX3g67UycbtWqonsGl7733HvDKKyGPmlYUw8lZ0hLsiy82p98HGOzOnYEDD/TcyL31VjhGNvfGnjFHKRnECW9og9xfS4XB3rAhW05S5i+GdIMGMRNkY//5zW/CPj50EuzrrsuqihfVizhrN34onUplbhCSVfUQnZxxqOaAxx6LS4y+bBkzZgD33JP9ff/97Jqp3CgQaTn8cPY5fDhw5JHAVVcxNUJbbO4k7Kf5AZpr2UlBpy2QcJ8NAmDpUmAzIq73hcbgwexz8mRg4MDi0mKDScilURGXp7+yMnbellrbR11mMyIhnzP/FwGcRAhZDuBpAMcSQnSxZM6EpB5OKV2V+VwK4B0A43OzAZTSyZTSgFIaVJSSsy8THDtv0I1Jr6diQviGy2lzoSDXrdvou9DouAhXYSeGY16uVFQlwX744TAz5aoiMI3vpgAAIABJREFUrlpgXCTYpvLffz/7PY6TKZ+DpD/9KVcl0BaCRVYR18FBgl2BBmb/l3SoLhVcJAZbM34UO3Z0L7cYNti+DLZuo8SxZEn4t6xivw8w2EAEScmXv6yOkV1MsxsR06czKYpuA54PJMVgb93qFk9ZB/7M4nxUUcFOUnTYto2dskyd6u7kDAB+9jOU0QZUV3vG7DWpiHMJfFEl2OxBh2E+2mAnezbOYIvI957Cl8EeNw647LLsb92hdVzo1ozZs7OaaKK/Gx/obMlV+NOf1NfzZfbEYXJg6gLHdI0qyCaHp6WEUhZicei03CLYYAPsHc1Y1xN1qGhmsBNC3hhsSuk1lNK+lNIBYAz0W5TS78rpCCHDAHQC8F/hWidCSMvM965gzHpMvdgSgqbzymO6uh1TncphTkpp8MvPoguxYZP6yWVZFuFq1CCFAKHadU7ONm5U16EC31hH3WC7TkxxVMR1DLaqzJ/+NPcEVqfyLZZjaf/GMF0OJ90BUpiKCWhQTTdJnpS//DKwapU5Dd/wd+jgXm4xGewkynIpQ3yWJs5gL1+uD6XrjFJhsMePB4YOzTKbtncZZW3IlwT7mGP8DrJkqJycjRzJjDp1WLCAdYCbbnKzweZYvBj44INGR2e286pGmBhsPqaK6uSMoRzprKMzFYMNFM4GO8r8kq/xKK+1Im38/dlC4yXRVro2kSOM+CJqnO2E+yy3RmgyDHZTgIsPGE8Ge09DC8zByGYGOyEUXHeJEHIDIUT0Cn4mgKcpDb3R4QBShJAZAN4GcAuldN9hsGfPdkrWrWILDsCKXAZbHiilNBg0O1snEj0cjgRIYS16YTUE6azOyZkIeXMmT1JxJdi+auCme7r6fL3z+i6WrhJsx7KrUYNdaIv5GBafNp5Hle+NN7JqfjrwDZXPhk1nv1xKTs5McJF+5oHBLsa01Cgp8ZFCqlAqDDZHFI/cLvajKjzyCHDyydHy+sRbN2HXrmxZIoNdUeHWP8vK/G2g6+pQXc00ux2XaPN74XNNkVTEGQQbc6RYKJ50mVqCnQSD/c1vqg9w4zLY+WpDmRbRhTyv0zYX5PMQdP78ZMpxTN/4M+H27tQJGDSIFkaTLQmUkhDLFwYbbFP3aPRBgaC0eIomjILM/JTSdyilJ2a+/4ZSOkW4dz2l9JdS+g8ppaMppWMznw8Vgs68Qhyw0uZF25cbGhrDHDXinXf8J918QiZ+82a3dCpMEcKdW9I32pSJEzaXTppMBYYpmDwRJhtsl0k3CQm2baPjFUfGgyYxvauKuKMEG9CcXie9kH36qfk+p9dnk9cUVMRNEJ0y6ZAnCXair/ell6yMJpeUxHaoU2oMNodP33JtBFWZU6ZEc/SWhErrW28BbdsCb7/NfovzUUWFWx0ig62CqmPW17s5OhNR6iriAgKksGsXML9O4c4mKRXxl18GLrgg93qpSrBlWkTVBT4n2kyykpgvde191FHJlKO756hNmQSC6ibEYDclvPqqfnx5SLAHDgQ6tqptZrAThBuDTUh3EHIKCLkIhPwAhBwCQop5LNv0cM45/nnSaQRIYTEGYwsyqnaq8ETFhK8NtmnmFtV7LYvWOExHGRrCTNsNN7BP3WL89NPMgYkJJgm2Dq422K6wOQqKG1/WhgRtsAFgKBagLXaoF9eoK3nUfPy9+iwg35SCGPANV0UFcMcdWa6O4+yzo9EmwqQivmcPYzZdsXSpPU2pq4i/8QZwyinWw4KOHZl/mtgMdhQJDqVuHpHjwNRv+/QBrrgiubr69wfWrfPLk0Tfeecd9inGk+bPXV7uLsF2gOhFHHV1OPBAJm1z1oAwHXZOmuRYSH4gd5XGg87dI4urIm5jWFV1F0qCzRns8vJsnb4RGqJA1959+viVI9OSbxVxj3U4GJ/GCgzABnR1ztMMByxcyLSOOMR3evbZTk7O+LXq3mv2KQabEPIwIWQ9IWS2cK0zIeR1QsiizGfePO+ZZy1CjgEhrwL4B4BvAOgFYASAXwOYBUJ+C0La54u4fQqXXGK3fZXR0NAY5ijH0ZmIpjAYMjQa5+P2QleyLFptUIsRmKtm2nQS7LFjLUTCbIOdpIq4i5MzQtTtoNvUyWWef34ufS4YPtzY/j5exAFm/zcBU5NlsKMiimR4zZrwb+7RuW1b4MorgWnTwvfFGPVRIdMp0jtpEmM2uYTPBpfQTqXOYK9fzz4dpKrV1UWSYN91F7OXjq2froDLvBJVJdwEnUaSDklIsFUmUKKKuEsd5eX+62JdHQjxdJTnMlacDbrzAKEJhmAhqqqA1J7RxXVy5uOkUzxYsZUbBXJ+fnhdWenOYBfKT0aUcmzrc4FssAEgmMDGSrMddkIQ35HoBFCck155xVmCDQBB7zWYiTHYU7fPyE8fBfB16dovAbxJKR0M4M3M77zA1orHA7gAlB4MSn8ESn8NSq8CpScBGAtgGoDj8kXcPgVC/BYWIMRgl6xqjTxBx3HC06NH9rvDxiVAKtfRGaBnsOW6BwzITRNFgi2mTZLBlr9zuPajyZPZp+9iuWlTohJsgNlhT8c41EPaKEXZWMRZ/KNIsGVs384+q6qil2GDzGDzkDpANi4nV0FVYdKkrD36EUfY6yt1L+IuThIzCAJmKcB58kiIwmDzAw+bo704yMdhqq8qtQlJhMpUMXuiirjr3GTQmmo8JBSRob26Gpg1y9EJtMv70Dn+LAiy9JWBYkL7RUhtH1JcCbYPPJiDSJDp4ochLVpk67SFdMyngMO3bJMEu8imChPGsPFVsnvZpgbxfYqHQHIf8PAFEfRdizpUYva6bgkQWHxQSt8DIJ8SnwyAxxx8DICkopgczC1O6c9BqVpkQGk9KH0JlL6QD8L2SVgmy5z5r6EBXbAZB2KpeVIqpgTblcF2obF16+x3RwZ7A7rjU/QL33BlsGXJo5hXp0NjKzeddovt7OpF3NYO3bvr73G6ZLpdPJO6eBEHnDc+AVKoRRvMg6SiH5ULiqsiHoeJ5E7D2raNXoYNsor4CSdk77mMpd//HvjoI/bdFNaII8ohUSHhcwofxdGZ/MxRGGwe/k7WGHjlFeDZZ/3LEyF61JZx+eXxy7fV64okDmfkd5xOhyWZvjbYrnN5RjMoCBivPXOmA60lzmDLjxmsnsIOOmm5OWGSc8CPfwx87WvR8ro4Lo0DnYlbRUW2H9rCdOVTgh3TaZnVIW5c2j3W4fZVaQzBgmYJdj5gEsr4rJ19WV9PrfE0TWha6EEp5WqJawH0MCWOA0JdBhgLmXUagAEAstwLpTfkia5I6NevH3388ceLTYYeGzZkVRyrs5PM00/3w/33D8K//vUeWs35JHt//nxg505c//9OxMLPeuCvkzS+3oYOjSdNi6rSWF3NFqTp0620LKpJ40dXHYubLnkdXzxVE/Zixw4WZgVgcTDFchWYu6InLrr3bNxwzss4cvTi7I3hw4F583IzjBoFtGyZfV6hjRsxdixbXGfMyJXGTJigXlAWLco6WOvThy3Itk1gly5ZCbrc/hUVrO6ePVkMa1F6OW4cs6nl9fXvD6xg8dJRVRX2GM372MKFWakrAAwZYrcVHT2aiXEUuPOFL+O9mUPw4pSP2In/XLuD/5UbOuOcW8/D1d/+N75xyBxreiM6dADatMlV3eaoNizgmzczCXDnzixeroy6OvvOuk8fJqXs0SNroyoH0DXR4IJp09jCqOqPHTuyGMODBoXjW4t1in180yZ7HFnxffNxEhO33TYEH33UBc8/n4DKPH8GcdxosHNnOSZOPALnnrsc3//+inBbyJDv8d/9+pkPr1RYsICNv6FDs/OY2C98+oQ8J3TowGI89+qV7ffDhrFDHpf521S3qc+PHJl7YGCqr3Xr7EGDS90qrFkTVndv14699+XLWTvs3MnGhYmOLl2YydGyZWxeHDo0dPuDl4Fr7zoak694HIP7ZA75BgwAunTB2rUt8Z3vHI7LL1+Ik0+W1O7ld7ltGwvxZYKi/sTw6afsORVhB++8czDee7crXrz2vsZrb04bhpuePAEP3vAyBrUR6O7Uib03LrYfNcrDlTpyx49qLnKFOK/xNXfdOuCzz3LT8rUyKtq1C6+N/LkrKpiauMvhiOuhjwlt22b3IWLb8fVKBbnNARbWT2SkxHsHHAB06xa+Nm5c6PDi3Xe74vrrR+GhXzyJgd0c4n937549JLeN84YG3PTz3pi5tC+efSkPZjRJYs6csApL3PU8HxD5iZ49swdBfH/C0a8fmye6d8eWqoE49dQv4tJLF+KUU3JNiuiatfjm+SfjyENW4arrFOOthHDMMcfsBSBuUidTSifL6QghAwC8Qikdlfm9lVLaUbi/hVKaHztsSqn9D/g3BZ6hwNUUuLLxzyVvAf/atGlDSxp//jO3JmO/ly+n9NVX6a23sks7d6TD94OAUoDeip9TgNKN6Jy9L/699150mtJpdZkuf5RSumlT7vVzzsmppuaW1yhA6ctfuCV8o6GB0uuvp3T9ekrfeitbxoYN7LN1a0ovvFBZ/y60ohXYSyfhpvC9mho1vQsXsjpF+k84IZxmwwZ2vWfP3Px79qjb8IgjsmluvJHStm3tbfe972Xzy/e6dGGfV19N6Y4d4XsffEDpV7+a/f3II9nvW7aw++LzUUrpMceEy3jjDTt9y5Zp712IP9FuWEfpzp2Uzpzp1FcaWram7bCN/hT3Re9v/G/iREp/9Sv9/aFD9f39iSdYmrPPVt9/9ll7/TffzD6vuirc1vLYUCGdpnTjRv19jnbtWDmrVrHfnYWxf9JJ7PPFF/V1itcefdT+TMuXZ7/Pn2+nzwEXXEBpr16JFEXpww8z2hRziwrDhrFmopSa3wm/V1cX/n3fff40TpjA8v7vf+p+4QP5/XzjG+zz2muz1z78UJ1W9WfC6tX6fPPm2WkT/4YP96tbhZuk+fzooyl96KHs2O/c2U7HeedR+uST7PtRR+VU8dI3H6EApdMwNpvngQcopWyIdu1K6Q9+oKBNfqaXX7a3/a23+reBKwxt/JOfUNqt454QLQtxEAUofeiLD4Vp/Na3KB0xIvzeXfqVWH99vXkucv3729+y32trWRm3365O2727f/ly3xJ/L1jAPjt1ovSQQ9zKqKqKRwNA6aGHZr+n09m2e/xxc5vL7btjR/b6xo3he/fdx+Y58Rrf72Tw3HPs8swuR7vRffHFxj4YwubN9A5cTgFK16yxJy8qhg1Tt3Up4d57s/RdeWX2uzx/3nEH+7z8crpuXbYrKPH739Ov4t90XPfPCvooUQBgJ6V2vhBMMDxb+L0AQK/M914AFriUE+XP1bClLyg9A5T+AZTe3vjXDD+wF5rFsGFh1Sn5fuZUlNth50W1Jq5Kn0wzADz2mFs6AHjvPeD667MOuWS6brsNuPFGZdbW2I2RmJOrPu+iys3x6KPA3Xdnf5tssHXPIEqNGxrcTrN1ZfEyOGxeQUXVuY4dgS9+Mbc8Ux4dErbBLiNU7+gsaXDpoZIQi4p4u3b28vm7M9WjU9m94w6ga1e9VIJDVhFX9RdX9TxTX+Mo9TjYvDBXkwQfR1Vi+RxRbD65g6R82Dqq+oGo2ZJE2UkgHyrifKsI+Dk547Cp+EogxMNRnkvbFTPkm0TeICxBe2xDapNCe0d8lih9IgkHd4Ba3bVQNtjib9c6kxg/Yhmi5NS3bLHt5OgW8n1e/rZtwKGHAvfc03g5L+bamag4QH78QO530EWvkfuMoxdxfiNACrM39nTzQdE0MQXAOZnv5wB4OV8Vuc5aH4KQ0fkiYr+F3IM1A2MC2EbKizn5wx+y4U5MyAeDbYI8sLl6144d4bLEScEw2ysdnekWRlU5XbuGnZiY4mDrIKqYNzTkhnVSwdRuNi/iIlzolJ/bJU+CXsQ5AqQwA2NRd/5Pwh7joyBueK84DDbH3/+uv3fGGeY8ssr2rbcCH3+c/W3yIh5n06VDqcfB9txoV1czLWOdFUEOdJsSH/A8iZ4sQF/mxRcnX09c5MuLuK+TM9EGe8GCnNCG1OLkKwiYlqhVQ9jlXfM0e/aw+eWZZ+x5EkOYvjJQVKMGqY39w8lEp3BAtP6fhIM7QL8PUCGWJ0OprqFDs7991rakx7toYuFbtphejrggjiPx2rPPAv/7H3DZZX51+SKdxnhMA0E6fpSHfKNEYtcboWOwTTbYvG+9/762zAAp1KfL3XxQlDgIIU8B+C+AoYSQzwghPwRwC4DjCCGLAHwl8zsvcN0dHwGgBoQsACEzQcgsELIPNH9pQeXkDAA6YSsOwiK9BFs1Cf/iF24xswvsMTjnGUVJXUQGezO6YAWEDYOPBFtGFC/iYtis+nomwX/9dXMeFwZb/g5Ek0ar8tjawrVf+MTBRAp70ApzNvdW29MVAjYG26U9Ve+O28T70sHxy18Chx2W/S1L2lUMdolLsBOFJ4Pt7ehMbqM33nDMKED1rpKCTpMhnzF4Af+NZhL0qBxuiRLs7dvtdMkMoyletVhPBkHAlt8ZM9zzWNOsX88Okq+6yp4nIaiaKUAKM7f0w1600Cf0nWOA5CTYKkm6SIeoMZZkXZWV4XvFkmDHYbBt40/2TTNlitrfhut793nnDQ2owk4Mw/zSZ7CbGkxaj+LaycMu/vvf6nLKyrKRi/aBd0Qp/Q6ltBeltAWltC+l9CFK6SZK6ZcppYMppV+hlHrGonSHKxfxDQCDAXwVwEQAJ2Y+m+EDcbLcutV8X/rNJbWJo1AS7MZ0hvibERlsQJLu+0iwZejiYJ96au4CzCFObg0NLF3fvuZ6oqqIy4gqwW6hcTSnokFVJKj3KX/ju9o4wE9SnA/I7b9kCXNuE1W9/847k6GLQz4IyLeKeDchLEcpM9iO6rbjxrGu6bxJkNvopZfcaeMotAQbcGMcC4lCxME2oWPHbBlGlWe7BBtwOKAp5FipqwN+9Sv13sEDAVLY09ACc8rGhG+o2stHvT2fEmwRPtEbfNLW10dTEU/6kKu2Fvjud1kUiDgSbBVktfHLLlPnca3X59kzaQOkmlXEk4anirgWhKAfPkWvtttCfiabEQ1uMwilK0DpCgC1YDpH/K8ZUfGd7zR+bRwPBga7GjVYif5YD0V8ujgbunww2KqNv6j2LIKf1pomBcPEMBqz0AJ7wwx20hLsL3wBeOEFfX6xDfkG01ZXVBXxpCTYNgY7YRtsgNn/dcBWpDb0tyc2YezY+Cpc8vMddBDzpB2VQVC1l+pa1A2TjlkQPV3fl/UW7F1nRUWWqSxlBtvxvVdVsWACIQbbtKvjMazjoBgS7CQY7CQPBPIVB3vRIvbdxmCLMV/F5/I8OOvThwUJsB7Q+Eiw4+Lpp4Hf/Q749a9jFdMoobr4UXahb1+9BNtHkyspCbZocuU57nNgW+dkZr4UbLA3bgSefBKYGEGG5Tv3yJqD+axPYLDlQAHNiAlHFXHrqyYEBMCKH96Im25KksD9E24zCCEngemrLwPwLoDlAP6VP7L2A4jhdTgsEmwgD47OkloURSgWQ6q7d+KJ7FNe3MSF1bC4tsRejMas5CXYYhm2Taw4ofENpg+DHUiaCT4q4lEl2LaN6p49buV6bMAI2OauZuMBznmUuO666Hl5u+s2Bi4bBtUqpcpnYjZs/UNWEddpdwwalL2ui2/uuglKIkZ4vhDB2RFzdEazc49J7fv444F3383+7trVm8S8SrA55LIl22ItfE0YokIMDxMV8thIp4Hbb1ffk8HHnCODTTRyAmdHZ/l81zK45FrVBq+8kjPfUI0YZCCWomPlTqTW9EZuBul7MSTY4vwedy6y0W/ScigWgy1eS1qC7VqH64FGRAYb2DdUkIsK8R25qojbkEnTgiQ0lvdzuO5WbgRwGICFoPRAAF8G8FHeqNpXYVRZU1wTfhsdnZWaBFuZzqEcVftYVMSBjMoRqlkVxx8fT4LN04gLs43BllXEATcGlUPw3omyMj8V8XxJsEWaTOV6qikHSGHGpr5ezZODioroEg3er3RqllFVxFX5bBvO9ev13sRNKuKiXaJ4fc4c4L+KmNOuY3QfY7Crq4F16whWI8NI2PrMmjXZNIcc4k+j7fAmDuKqiP/nP/5lW/A3nILtqIqU1wj5HYt92nbwodMgOv/88HNanJwB7IBm3rywQNWWJ3IaF3DbY5Xa88SJwG9/q6o85woBEHRbidSc1sJFjQTbZX3h5j5JHdaLcanjtl3v3ub78rxqkmALWochJPHcqjKiMNgxJdjeze2TIUPbOEz3M99phho6J2e/+132+4gRai/iug25HL2kGbHgulupA6WbAJSBkDJQ+jZQiHg7+zBc1EeF3+2xHUMxXy/Bvv124Mgjk6HDB7qBuGZNeAa1DVh5MXFUEQcY07YVnbAUA1kZcSTYHGIZNimRSoItOipRQXxWcRNTVmZWEY9yyq6SYNs2Ti52fp4SbIC9q7p0BWbP9sqWPN55hzGkMqJKsFUbpIYGdtAiOpYR8/boAQwcaB4bOtVgIJfBBpg5gwu9KvB3uW2bW/pCIqIEGxAOJW15n38+21ZRpHG+EmzO0Lt4ldb1g3zHUpHnjuefBwBsRBechr/hL7gw+TpN76l1a/09QH/49OKLIa0x5StSMNjpNDB9uqauTz8F7rrLTI+2sgjgnL7OrlhxWKdb8oLuKzBrYSvsgeBXRHeI54qkGOwkHS7qtHo4TPbecj/UMetJHKjpykhSgq061S6kinimf7RBLUaMKHEGuyl4ERehew89e3rbYANoZrATgutuZSsIqQLwPoAnQcjdAEznus2wQTEgck6VpE5ejRq9o7OrrgI++CAROryg2/gPGQIcfLD6nktZ4qRgkbaGHJ1RGk+CrUrroyLONxk+DLZYlzwJyu+noSGsFhyFwXbxIm54Zio6CPJciIquHia2u0ram6QNdn098OMfs1PkTZvC93TO/eT76TSjSRcb1WUh9PUIf9xxycVYTgoRbDHHjgXKy2l2zrTlfeGF7Pc4DLZre/NTpgcesKfVMdjWOFIZuM67Nlx7LQCgLuOBOi+ON0202g4GTc5+/iVYtTlIsKszZ9nauerEE9VzSL7A52TdeqjUilMnDbqtRF09wSyMzq6ZvvOKS/1RoDKRisrw9OrlntYmwc5XLG6gMBJslfd6TR1aCadPfYa0zHynxPi41atZP3vttWJT4g/dviWdbmawiwjXGeNkALsAXA7g3wCWoNmLuD/ETivHwbWlB2NOVqEv1qCnMV1kmpKEHEojU492nZTp4O3jwGCPxBxUYk+WwS6mBPvLX2afQcCcZrnk8WWwRQ/cUVTEXSZaFwYjggR7AJajU8ud8b2IJnHCrIqhmqSKeENDNha9yQZWtUkRGWxZ8qCT0ungK8EGEmGwTWddkQoDvPpbmzbAyGEN7gy2iCjOw3wl2Dp6XMyHOIz6ywnA8ix5YbBN79jHaZVM+6WXuucFE1j26mVgsF01Pf7+d7f13gZfx5nLlgF71BoO1d1YjGTt2ODzlgtMWjZRYPJB4ovOnc33fVTEk2Swr746/Ftcb3kIy2LaYLvC50BaYrA3bChetE4lPv6Yff7lL8WlIwp042TXLjR6K2tmsAsOVy/iOwH0A3A0KH0MwIMAHL2rNMOGxr5sUBEHHB2dffKJ2oGatfKIMEnfQuksJ9HyRM89aDpMCpWow1jMSFaCLTKuNgabLzKvvw6ccQb73rYtMNMQKt5Fgq1ioBoazJsAFWwS7Ntuy81jYbAbw3R5clAEQNB9ZWlIsFXPmLSTM/5+TJtQE4NtYrZ0DPYvfpH9vnMncMkluWlEDBnCPsU+X2p22K6n8Dt2ADfc0PhugzF1SCFg8hifDXIUCTZ/F/nQCiqWBFu+J5WzDAOxCRYmxhcmWrspomiIcJXCOs5bXNKmhGt/+vBDYIwQEitfm1epXPraa1oTgv7tt6BLx4bwAYmY/8or2adoD+1Zf2TYtHtc8Mgj7JCwQwfge9/TpzP1F/n9+jh8s6Fa2sOJc8bpp7PPrVuTlWDr0rvu4eLWJzHYQBE02V59FVi40J7O8PzpNHDFFcDixQnSFQUijU88oU7zv/9lvzt6EQdQeut/E4WrF/ELADwP4P7MlT4AIgQK3c/hYoes+11ejvGYBoJ0LoMtpjvkEBZyyIZ//IMdHxaMweb3NOXIEz2X2rluhJDCVExAmhqkqlEl2K4q4l26uJcfR0Vc6hdWyM/dooV6MyXX41JuBE+rQbeVmDUL2I2Wbnl1dUeBrt05klQRb2jQOw7TOSiR7+s2QDyN6t4f/pD9PmOGnmYOblqSpO1j0nCNg33NNcwLccauORi7FxvRDZ+in1+fKYSKOIePFkI+GGyXeqVyRDORxCNb6Gg999zkGGxeFczpgwBYsEDDZ/oc2GzfbnY05wPdc3ms5aSMIBi9O/vuklA1SYrBFmM1R1URr6oCxo9n3ydN0qfzkWAnyWDL0K07hZZg+/bRCDbYADtvqqgoAoP99a8DQ4ea09TXG0Xr69Yx1wuPPposad7wHRPNTs4igRC0JgSWTqOG6wpxEYAvAmB6jpQuAtDdlKEZCvgy2OLkVVaGKuzEcMxLRi3vxBOBww6LX44jnMarKpHjJiZACp+jAxbv7GWXYL/2GvDXv5oLFOsVJYIq8IXDFvpKhzgMdhQJdps29jyuDEaEjVnQfSXq64GZGGNPXGjweLsmuKqI19e7nQjbGGxT/baB5bIB6tiRfTYFCbatv3G1/8y4qB7JDupSCArHYIvvxBTsNQkV8SRCI/lIsBVIZD0ihPkrAPRz2k9+AlRWqu+5IvM8VHXSq2GwKQWmTVOU5asyrPNC7QpfFXFLWcHovZiNUailrfzz+2D4cL/0SaiIi23lGemiEXFUxEVHdA8+yPquCbpxbBubpj2jC+Qy7jY47TvnnOz3Tp3YZ9++7nUJtLVuDYwcWURfLGecAaxYob73yitO5h8l7aT8BQz7AAAgAElEQVRNBZdxIGvc7ecgBBMBTAczjQYhGEcIprjmd50x9oDSrJ4sIRWAqxeEZjjDIsEGso7OqC6dC/hEt2pVfiTYxnQem0ogO+Blm24Jjc6zPh9sl2Afd5x9s8PL+O9/1c5BRPD29GGwXVXE588P55MZuSgS7Nat7ZNtUjFNFaju/imAPEi+XGCTYMu2cbYyOHQ22OKCRanaEaGvBNumIm6jVVeX2PdKbYHl9Ng2uVyim9ngjhm6BxWoKyyDLb7Po4/2L8dHRTzK3O+TxyFtYuN48mT2qXvHFRV+UkRXcwwORWgDo6OzfDq9UsEmXVJcN0mqqkfvRT1aYGbd8HgSbNumvH17v/LEuZQzOoVQq7dJsH3e9/HHZ7//8Id2u94oBwmU5s5TUdrJJc+WLeyggOPnP2efPXuq06sgPWPBHZ2JFT37LHD55bGKKzknbTb47AVK7YC9eLgewCEAtgIApZgO4EDXzK4zxrsgZBKA1iDkOADPAfi7H53NsHVwoxfxzOQeIIW16JWN7RoFospznBmirs7Dfoca7kF9GgtkFzVdaJIMRmAuWqEWqW1DkrHBvvlmdko7cqQ9Ld8QRN38mU7bJ0q+BC++GCEPYVEl2Lb3bmAwQtIf7wMW4IB2W9C1a0zJVxIqjVHLUC0+99+fe020wX7tNWCKcPDpqiIexQZbldYETqPYf0tt5+Bqgy2FMmpVmcZozPLva0lJsHVxzn3BD2Zkfwm+76m8nB0wupZhscEGYozj2lq1CYNuXJaX+zE5poMwVR0Kb+49ejAh3SefKMqPymBHnXfkOSHmYUswhslMUnvHRMrfiFYWCbjvZl0ce2PHMvtS3zJcJdj5UhH37Ru653vuOXMe2XwtKqPOv6oEIKefntVy4uDCBJ8+o2CwN29Oxv+fE2R/BDHXuE2bgJUrYxVRWISet1lF3BF1lEJWZ3BuHNdZ4JcANgCYBeDHAP4J4NeulTTDEQ4S7FBIqqjgk3JZWbyB9PWvu6fl1bz5hua+hcG2oAINGIfpqNnuIMF2wVe+wmZ/0WO3DvmSYKuwbFnYw2sUBtvmiReAs5vvCP2HlBF2ep0PD8Q22CTYLnDdxDQ0ZOu49FJmQ2orT2W6YGpjGy0utKok2KV0gk1peM4ygftuaJmx729oQIAU0/rx6apxYvqaQkWpEIdR8g3BBgBvvplY+UMxHyvRH+thsY1W4fvfB8aNy0quOUwS7KQYbA8EgWY6zKdNrgkuDPaqVeYy0mn07Z1Gd6xDTd1oZloR9TDIxmD7rhHyO/rXv9zL6NCBfZoY7Jqa7GGnaFxvUxH3ed+2eO0ydAd6b72lz1NXl8tgJ8QYKZdG8WIUBlt6rwV3dCb7q4jYVmK2oqqJ++5fKLU/sm5u2X8xhxCcBaCcEAwmBPcC+NA1s6sX8TQofQCUng5Kv5X53vwGEoK2JRUM9jhMRxkawmp5vq+CT8oVFfEG0ltv2SXYmzezz0w6rcpaTAYbyDg62z4YDekEJNg+4HRHZbBFyCriNkRREXct21QkHCZig71kEABzMBK1aBWRgAScNv3+99HKeMnRv6MowQaYV1gOMfSWyMScfTYwb172N6W5TI64CCapIl6qNtg/+QnzDA74v/d0GgFS2ILOWL7ZQ1U1zrwoS8V08LHBdqkrKiJIsLmkyymyhQ7coRK3vZbqyEEeGGyXeL9BNcWiRQqzzGKpiEtraiPE3z/8oVoayZFOs4NOpJDaOzYep8APs/IhwfYtw7bWbdrEnKjx8F0LFmTvJSnBtqkfy20V5UBvzhyzBHvMGDchSJQ5hLeFjwbbZZeFLo0ezc76Y4fsdIUcDSaBubOpMdhCZo+0+zUuATASwB4AfwWwDSxctRNcvYifCEKmgZDNIORzELIdhBgCuzZDCe0JryZ+qmKyb4NajMDceNI/PtHEZbABO4P9la/o08nlJMBg72hog4XLNBJa04TE41fHgYrB/tGP1GmjSrBlRJFgJ4kIKuIgTILdgArMwNhwugsuSI42Gyx2/VqImzITRBtsINw/TjstnE6EeNKuGhf8d22tH4Nt83KfsASb0oS6nijh9PVan5FgA0BqpYdfzijzosp+Ld8blUKXL9kp88gWkdYjHe35ZLBdVf//9z/glluAe+5BcC1jUnJCwxeawea48072qTt4A4C1a81lpNPMDhs1mFM/BLuop8RVhI3Z8u2j8jtyMYWRoZNgc8Za9e7q64EXX8zmiWODPXZs7jXRSZiMKAz2wQebJdiUuh36R5lDfCXYlDJ/NgJatmRMdsGYVJumUITFqqQdncnmjcLzGgVdUtr9FYSgHMANlOJXlOLgzN+vKYU69qECrjPGXQDOAdAFlLYHpe1AqafnimZo8f777NM0AQiDv1HlUZXOBXxSlsM15QNK96sZuGxEPSa9xo30TI3k1FTWG2/EbwvVYsZDhchIisGOKsFOCq5tdt552e+EZJ0HyRvzW25Jhi4dCrlwiF7EgbDaoCgOMzGzJin1ySfbn0csW5SMq1DKNtgctvEhM7nbt2MUZqMSe/wYbB/8+McsbktU+7U4KuKuaW19zOWeIl374w7DkLarC+Ow0NfJmQoZRoba5sRDD2Uh3x5+GNVgIrbUJxYV4nxDptn03jJMqnYjnWGwA6SQRjmm14+KTpdtU+5yWNdb8CmjYjbj2GC73l+/HrjxRvad0uTDdD36KPDtb6vvRTVJKSSDLbaZ6lCFUuasYNOm3Lya98fNLwqy3NjmWU8iuPS9VJfKnHdfaM2oJg5K0QDgiDhluK4QnwKY3awWniesyoRy8WCwN6A7i+0aBaKKeFw4dgllMnFR8ZFgt1KrFQ/DfLQpq0VqRgQJdhJQtaeLGqjJi7gNxZZgu3gR3bAhzGAD6NMH6IG1uQy2K635fpdJQJZgK4Ppwr55NM0LPgy2ra+UshdxDtdNLqf/3HNRiTqMwUx8ki8J9uTJwBVXABs3st+uEmwdQ+5Tt48/ABE8nJkNIi2qug48EEHHxXYJ9uuvs+cVD1xVY9ik9uAjwdZJPX0ZmRYt0BWb0L/XHqRSCTPYEycC3/pW9PymfmNb2zPt0Hgo3aA5CI5Ch+99IGxOJL8jQpJTETddkyG/3yT2S6ecwj5lCbesvuwKWdovt5P4DEdoeIU4KuKyFtghhwBHHpmbXn6nGROpIGCWU0uX+pMQGzHXuDFjmHP1pPxYOmPwYHYQZOvDcn81Oczj4G0iR6/ZfzGNEEwhBN8jBKfyP9fMrivE1QD+CUKuASE/a/xrhh8sA9roRVxisAGg5tirncrNQVI22Lq6dRsnGeKkO22aWp1aVdbcuUpSypHG+KpFqJmpWQibGoPtgiJIsEO2fS1bhuNJfqjw/0BIeAPRoQMIyWpi5JPWHBRagu3yPk2qnpTa75sgjjFbXylVG2wRvhLsOXMAZPwzfNbd/fXH6SeFbDtXOuUNrrjZskmw16xh3xXPRUARdFyMVeiLNVActvE+xf0WcLtrVzpF+DDYugNbXwY7M6cHQ3cgVSPNTXElmq+8Arzwgnt6mwTbl8EmBL2xBr3K1qKmfow7HTJsEmyXPiq+1ygq4jwUGG8jmxfxKAy2i3NQG848k3mzHjYsfJ3bsZugcriqkmB//DHQv3+u0wA5rZhHhq3NeP/63e9yy1FpSslzR4aWgjo6k58z4jzNiym4kzaOxYuB3/zGnk6eA2bOdK/jo4+A6dP96No30QrAJgDHApiY+TvRNbPrbv5mALsylbUT/pqRABrHvaMEewxmstiufb8ZrcJ822C7ppMX0g0b3PIdqA9DF1TNx7RZFaiHYvOTb+ZNteHKN4NdbAk2EH5u1caGkHCIjGuuAcCYnnkYjp1oo85vQlORYLvQaWKgDzssNxaIj42vjcH+4x+z35uCBNsVEv0BUthW2xJLfvangtetRRIS7Kgq4q75goCp777/fiiPeMgWdFgEQOPojOdRhVlTjQ2TjXQSNtjvvuuen9cJIBjyOZYuJdgCIVxRVAl21LElt5fpnabTZidnAu1Bi5lI1ScgwRYdN4oG6y6MjEh7FBXxdevCvit8GWyVD5Z8SLABNTPt0ie+853cayonZ9dey9aMTz8NP6cDg23sMyJUa4npHcnvNFPnyJFMeaEoDHZMjBpVQNpV8JVgw7MJChY/rXRBKc5T/P3ANb/rCtEblJ4KSq8Dpb9t/GtGMnCxXRIGU2vsxkjMQWq+OTa0FuJmJx8baVcJtotujSd9QbsF2LWLYD6G5d4shgSbO1WRUQwV8ZtuYqefCSCkbaFjsEXwzdfEiY0q/tWoQRrlmAZhc2d7Zl17uqKpSLDFdpCD8EaVYKtoCQQNgqYgwbY9r8rRGARV2LveT6YeE3RtJ29w43oRb9UqugRbVd8JJ+jTTJumfi5KMa7DMpShQa0mLks3beNb9lsgIgkGu5FJIZn/lvbLSC2DfzHb3NAhQrGcnHGYDmbkmL8yhMP16sqZmJcegh2IuJ/g9Yr+Rqo9o5yYGGxC7M7pWrUK+7iw9TN5nR0yJLfOuBLsk09mMbxdoGN+Raj6m0qCLbaf2A46NXTF+1GOC5UNtgjTO9IcBlVWMm35ojCplDJV6M8+i5S9spKpiRfMC7ovohwINfWD9YRBCB4hBA/Lf675XVeIf4KQr0aksRkcNhUqRwk2kFGvnV/FpsGog0KnRudbhgw53qCA0MQ9xkEtTSz/lVesai7V7Zg0RbnZKwaDfarGXKMYKuIDBgCDBvmVH4cGUYLNGWzBfl4Z4kf1jrhq3D//qdZy8IHcXzMqxHmBK4OtYn5Mtq+y7wITxLyq9yQ6F5K9iL/6KtCpU3Rv6/mAr8ZM5plHYC5aYre7t+s486Iur43p8cWQIdFtsFVQScg40mltXVUt9mAY5psl2PzTNh7kTXpbgenzZbCTQGZOr/6UeZcO9Z9Sc3Im/s7Mt9oDBGGtCipngqIsfNDpA585yAUqRs2FAQWi2WATok4Tl8F+6SUWdtEFovRfB1V/k8e1PE7F59IxwHFssEWYtEMM808QMIWHvJ/pqsbL8OFAv35szxphf8idtJXkebShv7qEJ2wGAOAVAP/I/L0JoD0A5w2R6wpxIYB/g5BaNIfpSh4RGezNn7fACvSPXp+qzjhlmRB1BhLznXACi+tgwJA2n6Gqiqo3e/lmsFULICHA0Ueb8xVKRTxfp5M2CTYhWca6X9YxXy+sRW+ssjM9XGpdV5d93qTeZT7VoGQnZ6Z0Imy2YuJmM66KuCi5kb2IT5rEPNC4hiUrBHwl2JlnaoF6jMP0wjDYurmuttatLp9DhCRUxF3K0DLYLG9OZAtd/b4q4nKYO1e7Z4vdrrMqbIYR7YStGDggXVwGW4bpneqiV3AIm++gBTu0jhz6k1Ljobq3BFvFCMrXevUyl+ejIi5rDHHYVMQPPRS4+GIzHUlCRaOqD+gk2LqxY3s/qvuqskwxtw19NQiAzz9PTLlOD9O62tZfe4MQRvu2bcCSJTFpi4IIKuJWJMkb7AOgFC8If08C+DbgPlG6rRAsLFcZKG2N5jBdeYOrkzNAUHlE4D8QijGIxHq6e3jz9WTMy0kaE8YKG6GTT87ezDeDrSvfojJ/6wOd8UM8yH74qoiXlwNTpgDvvGOny/SuVXE7XeHCYE+cyLwt33xz6FaOozNVfr5QRA1lIkJuA9PGMC5M6q4iVNILMZ88BsTNZlwVcRHi/fvuyzo5iThH6PatsRBRgg1kHJ1hQuElJRwygx1XRTydTkZF3EYPr0vj5AxgbbsWvbAavXPSNOa31QHkjhlxbklCRdwEVdkiIzq+PjtXUVoYBvuJJ4AePdT+HEwHM926mcsVNt89yjagL1kVPdRaOg2cdZb5vg9UKuKSBHvv1NnYO3uhvowkGGyZiZQZlssvZ/HSCwVVf5Pb1qBpor1ui5mugumgS3XPMP80huzMt5q47SDTcb4QkxXN0ZkLkvIZ0AwRgwE4MzDmFYKQAZb7BIT0da1sv0eCKuKjMQstKtL4BAfHoyPfEuwM3TQtpNuwIddxU9TyFQiq05iOcahDhX2hLRaExe7jGa3wV5zF6I0iwZ44ETjqqOy1P/whG1sdcGOwTz/dr15RguDi5IwQ4IILckKsBUhhAYZiO6py83PwNtGdzMfBzp3JlKNCQ4Nb/5WP7m+5hTmo4bAx2KbNrU+bie9x3brS1Huz0SRLsIVxESCF7WiPRYsc6smHBNtVRdznECEJFfEIEuyQBDidDh/4qspXqYj7SrDLy+N7ETchnc5lNsQDmprJWIEB2IguLG1SDHZNDYuRfP75ufPRhReykGo7d/ox2C7jRCivutxDu0MGpcDbb5vvu5TBoVIHl66d/uPOOO93g3PTua4L8rvTaZ+JkFVuzzwzvid5H6ieTaX9pJvzdXPAbbf512t6bhVjZ5BgjxjBtgUlyaRaMGIE81lXFNqbJdh5ByHYTgg+558A/g7gF675bSvEH0HICyDk+yBkJAjpDkIOACHHgpAbAfwHwPAY9O9f0HTYxssmFRZpMLXEXowetIudOseRYMeFr8omhyTJjFy+or7gkHLsRmvMxQh/iXAUTJxopSkHocMTqOl1gWqh+/nPwzEvXRhsj7Zhm2shvTiRu9rAZVCNmrD9n4nBToLhs6lfJwmbYx4OHgaJg4c04rDZYNskjxw+jn9KFaY+PGNG1g6QpzvssMbb1WDeaJw2Q/lgsF3sLH3rKbIEG5TdG4sZKEe9nsH2kWCL4PNbebna8ZQJUea7W28N/xZtlVeykFqNa25S60kQAOedBzz0EPDAA3o6fRjsyZPNavCHHhomoWIaFmAYPufBYTpmvKW7tHdSNthnnME+t28PX1c4OVuzBnjjDYC++x7wzDPhtOKn/F13LaoNdiHnTJWDT5sE26QJZYIs4Zdhem4XCbZQZosWwLhxBXAWFtUUx4CC0R4FKi/irqYxzQAAUIp2lKK98DmEUjjHVjTPDpSeDuBaAEMB/AnA+wBeBnA+gAUAjgWlr0emfn+DjwT73HONEmwACIbvRA2q/eeJqKdU11+fe23oUM/KPRFhEqw+mHXrGlQXRoL9wgvMVlUHsV6+SJ93npgAAFCDIL9exE1tGWej4KIirkEj08M35qbTch9prPysy5axmJ3y9XxKIFzDdNmk6CYb7KVLzXVElWCXKsT397Wvhb0Vi6F2eJsJbTcc89Aau4onKbHN/7Z0qny6tPK7Nm2u49hgZ5jnNqjFSMzROzpTSbBVqKtTq4jzzWLCKuIENOz40WB3OwEs9FQKAWuLqOvJqlX+eVTPEjX02vPPA9/6VuhSUM7MQaZiArvwk5+wTymdljbTYaKrBFs+XBChkGqvXw98duCRwLe/nZs+Hwy2SiJYSAa7spLFJxYhx5U3SbCTPEz2ZbB1Hswz4I7OkrAC0yLhw3XetCXr6MzwjpqdnJlBCCaY/lzLsc8OlM4Fpb8CpUeD0qGgdDwoPQuUPgFKE3aLup9CtQA99pidwR62E1vRCUvXtsm551yfDwMbh0GNOvtEYLAPOghoj21sI1QIBrtFC6BDB/19sd7evdkzffe7OclSMoPtgqQYbJ+2OerocHIbY2YouwfWox9Wmhls7kXcpw/Jz3r88cCvfhVWvQbyy1S6SrBtduDis7Rrl1uu/ExRaAD0famUVMVEWl57LRxvVzWvCX2mAg0Yj2mMwU6ngaeecqsnKchlxrXB9mGwbY70TPQAZml55no1atSOzkQJtuypXlWP6DGIp+fMjY+TMwNCkpwjjgDaZNbQ2lrmOZ9DkFp2wOcYggXxGWxAP+Z1jJ+q7R0OZpQb6a5dc+qpLpsGQIjoQIi7iimlZgbKlcE2tafGi3iO5ND1gLcpMthlZbl0TpoU/h1Tgu0s4fRlsL/xDamicJ8IAhasYqHBrD5xJDTHF4V2ID/72VJa64uL2w1/FpuKLJqATuB+ABcbbMXkHgxnkq/UQk9/c1EZ7CiLSeOzscnd++Qsgop4WVl2s1cQFXEbLO3GnzCF6vyG6UqKwR4s2b5FbePdu4H33w87OpPzv/xytj6f4235WbmUWN5k5HOD5EqvjwRbllAAwObN+rw+46cpSLBdJbEKBhtgdtjTpgENj/w/s+16nI2Gq6Q6LkwOjWwMtogYNtgEWeY5QAob0B2fop86v0yXivZdu8KaUjKDnYQEe9YsYPMmNX2LF4e1kaR1t3FdiasirnsfJsbPpiLuCl5Ojx7AIYcAjzyCbmWb0B/Lw07cXJ9PJ8Hmqt4uB6Om+kQV8cxBCH90rTZKXAn2pk0sLKQIlYp4sW2wVXtGXydnqqrEfZqvDbbqniUShZOjM9Xa5wO5reSwYo79XS6mYE7akoDPnLEfM9uU4hjD37Gu5TQz2IWEZeNl9CKumNxHDtrNYrsuMkhPbXQUTILtKL3Jyecp+c6UGyCFGRiLvWmLfXAhYK2X3Z+BsdiLSo98iC7BdjnBjwIfjYGWLYEjjkCAFBZhCLahfTjP1q3ASScloyKuO2QoBQm2r4q4XK6rDbYNcQ4bbrwRuOmm6Pld4TpfKVTEAcYg7dwJLJhjeTf52Fzo3kU+VMTld5lOh6WMvhLshgYr/VpHZyKdYh2qzbLsCE60wQb8+qiO3ttvZwa8Mo0qSAx2gBQ+Qz+sWxNTgm1iJl3zRO03vJyKCuDjj4GvfhWAcHjgQotLvVdfHY0u1fW6OmDAABYTSYATg62C3I9U6efPD//Olw22azurJNgy0uncdXJ4xk1SVOZU9f5Mz+2i+SCVOWwYOzvR2jKvWAFUVcXzjJ0nhnH4cKB16yLYYedbgr0fM9iEMCaaEJyq+nMtp5nBLgE09mOTGp9icq9sQTEGM/0ZbLH8fEuwxbqiIKJqeYAU9qIlZm/vn71Yqgx25vZetMTsPQrPqCZElWC7qqv6IkI53A57KiaE83O1+yhOzuS0vNyodotR4Lqh0ag/NkKkeceOXE/Hpja/7DI3GoB4hw2/+Q1w7bXR87vC9L4cJdgAkPqsZ9KUqekwXY+rIm5S21ZJsIMg/NunPofwP2MwExWoy2WwZ83yUxEXwdPLnzaYJHmPPaZOr4I0Jnj/qZlK8rOemFTEbXb10jP4OjQKkMJiDMYWdNRr1amga+cPPjC/BxE2iXl9PeNiJAYrldKQmIQNtoi1a9V9z7E/Ll8ObNwoXfzCF7zKAHHocyoV8blzgTFjojs5U8FEcxsHk0XppVVUsNDt2gOT00/Pb0jNGLDSni/YxqbqHe3HTLMnjsp8TlT8nehaiDvHREgnEHIICPlS418zkgHv9Dt2qK8D6pM7QhAghZrF7ZH2WUxFdZ2kGOzjjzdmpbIE2xURJwTOtNVsGZi9WKoMNoB2+BwAUFM7wq/sIthgG19JDAY7x2aeQ8VgR5VgF5LBdpVg2xhxGwNuagvX0FBA4jbYcbVolXBVEddIsIdiAdq2dWCwCynBjoKyMvMBqTwfNzQwRpfjyitz89g0IQxOzgCgFfZgNGblOjqrrlYz2Kp+r2OwOW0+DLZpXA1jUr1GrTHejq9LPlslBns8poEgjdS0svyYlyRsg62Eal6itPHwYCom+A1e3fw0ezbrZxYHV43QtSeXYCv2QJs2MeFmKK0qvwyZJtuz9ujhZqetwWmnARddJF18911m8+/aj1wk2IBa04uQwjk5O+aYSEUGATBtmmbZlDQXIsE2Pmz3P/oo1IbiqyiIkzYg9rpkzd4swQYAUIrrMp/nKf5+4FqO28gm5HwA7wF4FcBvM5/Xe1O9v8PWYeXwFDYGG5nYrrUtsBgHudPx/e/b08gbDcA8qYphoVSIOrkfeaRf+sysN/CZW9Cxqg6pzaXPYFNKcCCWoSPZitROIepdU1QRF+l5+GFmP926tTFLV2zCACzTM9h8kyv2IZPXdqA0GGxXL+K2Vdm2QU3q3flKsHfvhltQ6QTh6q1YI8EuRxoTJgA1q/PIYPvaYEdhlMrLzVLlp54Kx5xX9bFTTnGvD1DWRRBm8o2OzoDw/KAaw3Idsmq4ax+95x6m/qyD2DaqeuX6M2iHHRiG+UhNLS+MBNt0z0HNXenzRDOGGg+lUQ384Q/uYeVMh3h33ulWjo2hr6vL0eLr3p19KlVzbRLs3r316W3o21fdn2XCBGzfDnz4oXSxooL1wyRVxGWNgWIw2G3b2vMr+mp1NRNSy5r5AJIZa3Hm9LfeAg4/HLjjDmUxRtqThA8DLL/v0aP15qjN0IIQnEAIriYEv+F/rnldj2AvA3AwgBWg9BgA4wFYdrjNcIaLBFtl/5ORYAMKuzffumWo1HxMk2pcdUcd5IXQEeTbpyM4rAVSmw8ULpYmg82U+SiCyplhBtsFSamIe0pjtI8k3jjjDOZa06HsRkdnJimByCTYTrRdbbBt/fMgj4MrGfX1bv0/nxJsH/hK5M49FxgyxG5DrgOluYeKNrhu+jUSbIBthqat7oF6GMZOPg5eklQRLy83S7BbtQIGCoeLqs31Sy8Bn39upwdgfUPh5Eze0AdIYTO6YDkGhPPLTs7ee09dj47B5vlattTTKGPKFO0tOn26dMFR1R6ZuWpaTAbb1QbbJMF+5JHw7zgSbACdsQUDsSS8l3Ap0zYmXSXYNhVxYQ9EKdN6btFCUs0VGUoTunQB7r8/+3vZMnf6xDVXtf5q2uyzz4B16xQ3kpRg61TyCUlWvJoH7Q1uwWI9MImKOHP68uXsc84c5W1Oe97VxH0YbHnfUFUl+MJwKL8ZIAT/B+AMAJeAtdrpAPobMwlwHSW7wUNyEdISlM4Hi43djCTAO3Vtbfi6OFGqGGwAIzAXrSobkmewVTBNqrYJN19BAuUNl/A7CIBZW/thD3ccVqoMdgNrm+rW8zBr18AsvS++aC+7kCrif/0r8Mkn8elRIEAKSzEIm7cYJNg+dqNJSbDjbCTWrVOILRSwqZKXqgT7zTfZZ1TbuD/+EWjfPhHw/1gAACAASURBVNemXIb4fKbNvGrz0dCQa0cbALV1LTAPnodZrtD1qSTnQBuDDYTbTbe5fuONcBlHHaVOZ5KACfmNjs6A7HjSzSM2FXEVgy2HAPIFpeHQXCJWr865VI0arFlXhtV7usSrVwUdg+1irx6TwQYUjs5cYGPc4kqwNSriLVsyoZySwZbzqyDO7c89Z6dRxWB7rg9K5lHu46b6XRhslaaaowQ7kTBdLv1QkWbIEMYDFs0bt8s6qkkzdCgT3Ofd0ZkcUcQEed/w3//qDzabocMXKMX3AWyhFL8FcDiAIa6ZXWeHz0BIRwAvAXgdhLwMYIUlTzNkWFQESVpaqMSFS6MiXoEGjB+4Tb8oyky7K03iRHL00bnXTOlV12XVlKSYgs8+y37/8Y+BBx9s/BkEQF26ArMwOpm6osJ6+MDec1A1H3W0RZbeadPsZUeVYEdRET/99LCjJFNdnmh0dDZNkf/ww9nnCME+3Vc9yiTBFvuQjDgM9hNPuKWLqyKeFHwlqqqDDx88/zz7XLmSfc6bB8ycac7jymCLEmzZEzSXNpgYiTgn+Vu2uJUZVasCyDLYpk2zC4MtS7B18wkherqEcTkKs1GJPbltK9tgu/Y1WUVcxWC7mDzZ8PTT6uvPPptzqdHR2dZB8euV4TMG88BgB0hhGQZiEzq7leUCV7o8VcQBNpaVjs5sKuKA/4FiDAab06dkHlXlquAqwVaV7akibl3G40qwFX2ivByYMCGPDHY+zH4yyDvtKjp8GWwAuOaX0eraf8HtX3YRgt4A6gD0cs3sOjucAkq3gtLrAVwL4CEAJ/vR2QwdGvuxPAGKm6LjjsvNmJkFqwdtw1RMQIPqdV5+uWPl6rIBMCkTEE1F3FZPXHTtml14b7sN6JXt+43xCaNK95OCzQa7TVuQFhUIbmY2kV70JiXBdll8fZh5TzQ6OlMtUGefDSxZAnz5y9lrUSXYKrVKsVwZcTYSroynTYJdKBVx33I44xqVweb9iT//iBHA2LFmunwl2AoGe/BgoF1LBRMoYts24Je/jHa4sWaN+rrPoY8NspOzu+4yp9eN7x07wvWZHE3pnJzdfTfw9tsAgJbYizGYmevoTBUH24VOFydncUL3AMyG2MMUaRymo6yMIrXNM+KDC0wMtngYArAY1nIa8adOGqlxcgYIhwfy+8s3bBJsSUWco7qamfIvXarIo/ouwndu5/OcaL/vyaQr1zc51rsOrk7ORBTDBjvGXq+6Gpg+XdFFi60i3qhanaVDJqm62uCkLSn4vMMoa5cPA79/4O+EoCOAPwKYCmA5gL+6ZnZ1cvZ443dK3wWlUwA87ENlMwzQOOQJwWB7Fhy0FTtRhYUqzQWbbZELg21y6MFRLBVxEdKM178/0AUbS57BRnkFMHIU+n/vS+jSwqCNEKVsMY1p8ly1yrkc47wbkSHthK0YhMX6E2DRnhSw9ycdgy1vUilVqoE2ohAMdqnYYOtgk2BH2VFs357VHLA9fxQG2yDBLisDJvRea2Yi9uwBbr2VOerzhU5lPskNi6wirtrou0iwZUbExIyonJwRMIaDazkh608h9LT8XUdlsE3jUGM+5QICyqTUHmOoLXZhxMDdSG2N4Z/BV6pLKXDLLex7x47sk+8JOMOnKNPHyRkATMBUAAKDXahNtonBBnJUxHnyHLtdn7nQd27nBtTCIX6iKuI2Zt1VRVzOwz+j7sF4fxNho/Xee1mdq1czB2E2OjMIAnbeNXeuoez165PxKu4DgcHWDQkn2pOiQ/6ugoLB9grd98AD7mn3MRCC0zNfn6AUWynFC2C218MoTd7J2Uip9nLA7YiTEFJOCJlGCHlFce9cQsgGQsj0zN/5wr1zCCGLMn/nONJZ2tAOCCp9KmCwLQoOYv7mvBlJSvVegFUMts0Jjq4OIDdMVz4Wbok+QgTnWcWE46JPCBC0X+RO7yBHFUUXCfamTW5ludYVAQFS7ipWUSXYqnSu/frss91o43Dd0NgYVFuorahtzm2oo4JveKMw2F/6UjQG29QWOgm2YjMY9FmL6RiHOlikRraN3H335V5zsFU2XvdREY/LYFdURJJgh5ycSahGDbahYziyBTd3sTEkMp2ykzMVIkiwczaanmMoWPw0UlsHJe+LN4oNNv90XVNVB3aZvB2xDYOxsPBrpguDrThIGTUKqKxUSIbzIcEOAnaYcd119rI1WL1acZ6bpARbtsHmczMh0TWN7rhDTYuJhksvZd8fecSsISZB6yxMfO4ePfzXYk5XnPsyHRKMTtqSgg+DbXA+qvUiLpa5ZIkHYfscrsl8vsAvUIo9lMLrZMc8wxByDQjZDmAMCPk887cdwHoALzvWcRmAeYb7z1BKx2X+HmTVks4ArgNwKIBDAFxHCNF4IWlC0G6wMp+mWNGGgT2s9+doU1arXhRNg3D1amZXq6tv9mzmGMGBBu+T1X/+05w+ChQ0BEhhNkahFq0UGQoEj0W4uuNizMFIN3oXL/ar32SD7alOpH2kGBLfACmsWAFsQFd7YtvismlTo9qqkS7bxk6897Wv2ekSkZQE+5lnzPejMtjHHhstH4fFBtvYtKIXZx8GPYoXccXGNeizBnvQCnOks+McyJEd5DouuURft+26qg8vXw489JCZJiDXBjsOgy2mN6npKp8r9xmMasa+DHZVVW6+SZPCaeKqiF96qT+DjRTW7+mIVegTrU4XzTFbel/GmqNa8V6EdxvJ0VlS0AkS6uuV77myklmVFITB7taN+bT5whf88mXQvz/7zGHAXG2wo0iw//GPbN6oEux27XKvuaqIe/r1OOggZpFoPWjnz+WDPGtjDB7Mmiqvdtg+Ts58I3TIiDuvNm1sIgSvATiQEEyR/1wLMc8wlP4elLYD8EdQ2j7z1w6UdgGl1xjzAiCE9AVwAoAHbWklfA3A65TSzZTSLQBeB/B1zzJKD7p4wDonZ7Z4gpnJq7wcmNB2gXpRjKOaPXIkcNhhOfWZaNFCngw+/TQ6XbqyFZN+NWrQgArMxJjk6vOFy2KfQdBxCerRIll6z88ohpx4Yvaa/D6ScqQVQ4IdisNqg61fDx8eZiA9F/pGiH3K99mSssG2Id8q4jrEdXLGYXv+hG2w8dFHCPowO2krI2EKQabrO7r2cJFUH3lkLgOpAu+XLuY7gDnOs8uGWGuDnXtpJOagJXarx7Ft0yY7FevQIZeum2/2K9OGwYO9ma1GnxFJM6I6CbaJwXZltC+6iBkrj1QcKkmh1laiP9ajW2FVxAE9g62RYAPsvKCmJvMIokq0mF8FXydnKji2D6XAuHGsm+UwYDoJ9gkn5Kbzneu5ZtrHH9tNjXzgOl48192yMvY+i+JJ3NS2KvMLKXleaN+7F/jPf9R02PqebA7nArHMJMZH08UJAH4DYCOA2xV/TnB1cnYNCOkEQg4BIV9q/LPjLgBXAzDthk8jhMwkhDxPCOmXudYHgMiBfZa51rRx0UXq6zobbPG3jTFrOx/TMD43tqvv5n3AgNz6mqgNNmAIG1NIiG2jmBRFSV/QmXlrSZTeceNYJQceqE+T1OIbRYKdkQjk2P+Z4Gp/5KIW5qoi7ru5ce3zb7zhV26hYbPB9u07smp6XBtsTp+jDTYOPxyDOm9BB2y19zVXhl6Eq4q4Kv/69WZ6OGQnZzYJtovElBC1RJ7fc+zPLVCPcZhunsN0Y+nJJ8O/uaYT9zSvrDC6DXYjLZ5jeyxmoJzkITymi4q43N9V/R8KNfi+ffVrgJC3aI7OAP17UMTBblwzA8ZLLFmiyZ+UBDsm2rZlfhy1DLY8huV+7dJPZ8+OtZYnEqZL9EHhQu+CBaFL1dUsmETiwTOSOCyyPE91NTBjRoJnGT/7GXDEEVnDbvEZbOvmI4+otVVcsQ9IsAkhVxBC5hBCZhNCniKEOKmyUoq9lOIjsDBd78p/rvW7Ojk7H8B7AF4F8NvM5/XmLOREAOsppSaLhL8DGEApHQMmpX7MiZ5wPT8ihKQIIan6vLrvSwAtWzLJmoTGMSNPAK4bdEpR3XY+atEG8zEsfE9uE5NDJxFJM9g+k1tULxGKya8vPkN3rMMnODhamUnAY/PWt+0WdMe6/B8I6FTEZS/bcct1wTvvAAA64HMMGeJ4uODan2z+A2zltGmT/U4IVqMX5mCEPr2IQkmWiyXB5guwz25iwQLgK18JX1u4EOjXT50eiMZgm2ywW7cGIQmowur6ji40oq9ttgm+Ntgm+2/x3je+oWZmdU7ONLZ81ahBDaqRljfsvs/K5yXT2q7yPO8LzzHUGrsxqsOn+WewTellCbZtv2DaMAt5x2MaCNKFYbCPOIJ9mvYYXIKtoV9pt+vyPgvMYANZaXvodXJaxecbODD3nbtIsK+4whx20gShD5DNFp8sprZ7TNjG2/rz6NHAsPCeNQjYND9njpkEb8RhsH/6U6diEqedm1Jt3sw+xTH+roXPmzgx5zTHy8lZE2ewCSF9AFwKIKCUjgJQDuBMnzIoxYY4NLjOMJcBOBjAClB6DIDxALZa8nwRwEmEkOUAngZwLCEkFBiWUrqJUsp3TA8i6zhtFQBxx9U3cy0HlNLJlNKAUhpUNNUOoZNgi5tJy8ls0JqN6JwFX96YcOcTOqhUrFwYbEcVceWG7Le/Df+OK5EQQMBO5ItyGt9IhPukRsrLCuOY7aqrwr85k+QQrsa4TkVh9oT3HQSODLZrPS4Mtqks6UDselyP4/B68s6N4iDfDPb69Wp7rihexFUxov/yF/dNoYrBVqnIikyHPG916gRQigApzMBY7EGlW90ydANBZzPvIsE2Da4LL8x+d7HBFt+Zi7RdNfeL94QybBu1AClsR3ssghTKKmmV4299K6tGHgGN61EEZivotDTXW3pcRFERNxUnUmdaV4Wy2mM7hkJjcpY0VFJaFQwq4iNGMN9jWga7RCTYAFvf1q2TgnaoJNiy80Eg//O8WH6tJhICR1wVcQO0js7iIs7cw6XFNk3SpGmX9y/iM3D/FBGgfYp9T0W8AkBrQkgFgDYAHCWMycB1htkNSpn7VkJagtL5AIaaMlBKr6GU9qWUDgA7NXiLUvpdMQ0hRAzYfRKyztBeBfBVQkinjHOzr2au7duIqkZNKYa0XIEqbLcz2LY6ojLYcVTEufcPDt+DkrffBs47T3/CjRTmYoQ2ek7e4WGDjfJyVKOG0QuNzX4SuOKK8G8uKaqMyGxwxNy0BAHwGfphLXqYE7r2EVv8XduiKy4yhKAWrbEGvfEZ+trrLpT9Yr43Xt/8JjBEEQKQv+u4mkMqVTdKmS3y3LnRJNhbtrDfDQ25fTKzMQmQQh0qMRujotHt+36fey5sJuSTv29f4PDDs79lFXHVuBOdIJoYbJWkTEZ5eXgOP/U0Y7kFM825555I2UIHBBFUxAEg6LIMm9AVK3FA9uKvf+1IQIISbF2aIdIWzZHBBoToG8WywZbXTE0cbIBdbnR0VqIq4vwcV8mAcTrEtVfF3ESxwc4X8mSDDTDhfceOETQSCgEVHfX1wIoVAFhglw4dEmSw5f2LOE5bKbSdeSg/G7ZsBqZOzb3+0UfZ701VYJkBpXQVgNsArASwBsA2SulrhaSBUJcJlJAXAZwH4HIAxwLYAqAFKD3eqRJCjgZwFaX0RELIDQBSlNIphJDfgzHW9QA2A7iQMuYdhJAfAODeXm6mlFp1V/v160cff/xxW7LiYs6cnFAzj719JB79xyF489kXULZyuTrfAQfkqu6NGME2oIMGAWvW4PLbTsTe+nL8+dKnsmlat2bpOJYsAbYalA9atmSb2BEjsk7ZFi1iRk4DBjAvtyr07984yeSguhpz3qrFxTd+A7de8DwOGSqlk8sdM4YZ4WTyKsFdcdpsTGpq8J85g/DrR76Je++dilGjIjh+iItly7IqPpWVTC1KwKRJo7BxY0tMnlwDLFuG/7zfidF78VMYNcBw4BbHvgYIt+GGDax/iW2vqe/WW4eipqYTnn1WmIx5WWPGMGlDWZl6AbDQMqPiWFx++Xj87gd/w+Hf66xPv3Ilo9mGCRPY4jR3rlp194ADmDhBZ8/UrVu2noED8bubhuL1qSNwwzkv48jRFi/uGrXaxFFVZfZ2zcH1E8XfMkwxRuT08+Yxe7uhQ7N2dEKaW24ZhunTO+Lpp4V+snMnMH9+uJzKyrDBXXU1ex/Tp7Pdc0NDth1btGB9TKSVv+OpU8MbtwMOYFLc2trwnNumDdCpE9bM3I6zfn8BrjjtdZx0uKbPd+vGylGBUvUmxQbeRjt2sHZr2zarJik/A0eLFozJXraM/W7Vim3sevRg/XfgQObASqxDfJc9emTj+Iro35/VP3cuc+HboQMbv/Ic0Lcv62eZd7cGB+Ksq07FL376P3z99MzJpVBfQwPBCb++BBMPn4GLThJUGQcPZm6C1693c3TZqVNW60Hsf/L87xkb561pQ3HjkyfisasfwQFBFXvuWbO8yliwbTB+cuNJuP77U3DUmEy4y3Hjwh7yddClGzAA6NIl+3vmTPY+Ro1i9qoAY77GjWPtJ9rsS/3o1pdOxrQ53fH0pMnsWv/+QFdNhAap/Z5/bwL+NOUYPH/bX9EFa+zPExXt27O9RVkZMH68uv9368bWzy5dGk1JfvSjanTrtgc338za5O67B+PVV3vgld//BWX1e1k7cCex6XQ2TJzYh7Ztc4vE0bmz3nZ96dJcrZyKihyzhbPPPhQjRnyOq65agOOPPxJnnbUSP/xhZizPmsXmv9ats2tU69ZsXhTDBB54IHsm3g9cIc8FhnRvPLATN//1BPy/XzyMft0M4270aLfx0revWjtpzBg2p2n2cVdeORY7dlTg/vsz91Xrt+/+p7bWbH44aJA9NFW3blhbOQTf+c5h+MUv5uPrX1/Lnm/dOvbOKyrws5+Nxc6dAu1xMH8+WzN5f66vZ0beABsPcnjVkSOz+umKuXHdlnY48+Yf4efffhXHH7UkzBtIaVFVxdb2EsUxxxyzF4DYCSdTSifzHxnh7AsAzgDTuH4OwPOU0pAmtQmEoC+AewEcAebS830Al1EKN5U7SqnfH3AUBU6iQKV33jz/tWnThpY8hg/ncofGv992v48ClKYfeDDnXuPfn/+ce236dPb5wguUjh9Pr8QfaUvU0r2oyKYZOTJc/0kn6esAKB00iH1Om5bN87WvsWuPPabPN3my/h6l9MPTbqMApf/GV3PvP/JI+PeqVaG8StjuC+lWoRcFKL37bv/XlQjOOitLb//+ObdPPJHSCROyaRvpxSXmdxUXYjnpNKV794ava+o77zxK+/1/9r47TI7iTP+t2aS0klY557haxWkBBmEMNgabYAyYYGPAHNF3PkBOYJucbEww2BhMNmDAh4+z+ZHOAbDPRM8qCyEJZZRR1irv1u+P6pqu7qmqruowMyvt+zzzzEx3VfXX3RW+r740UNHW2rWxaNm+nVKCZnojrteXv/JK/bPhnz17WPmJE9Xjqq5OXf+KK7zfzz9Pz8NTFKD0x7gl/Nq1tWY0xv0cfbRZueC71bwHo/7mOOz4P/4hLXPBBZLu/u67he327Vt4nS1b2O+uXSnt0MF/vrnZT+vu3ex/RYW/3AknUHrmmZTW1/uPT5tG6a230haA1mETvQS/0b9/FXbtiva+ON56i/2fOtU7VlUlr9OvH6W/+533f9w4Srt1o/T229n///5v/bu++mp5uw89RGljI/v9xz+yeuvWFZb7+c8pfeed/P+lX/8xBSh98vy/KfvOkfgnPRp/9x9/5RVW9p57zJ7VjBny/hc89uqrlJ5+uvE7eA5nU4DSBRjN5oAVK6zf455zLqBV2Et/iDu849u2mdXfvFl+/Kmn/PfZrx87vnixV6a2lp0T56ZgP6qspBeOz9FBg1ooHTOGnX/8cXVfDtDxfziKApT+vyNujdbHTT9f+5r/XbZvz36L4+CKK9gc8N3v5smdNImxMhychVjQ53Psx9tveyd37JD3oVdfNaNRB5F+/unZs6DYsGGUfuMb7PfEiZSeeKJwcvBgVm/yZK+NiRMZYyC2++yzlC5aZPd8CZG+X9V9/g7nUoDShRipH3fLl5u1eddd8uMrV/rbC+CHP2RdgC/fdNw4u/ciw8yZelpffDH8fi6/nC5bxn4+8YTbLl9f5s6llFL6gx8EaI+Dww5jbb/3Hvu/YYNHy2mnyZ9J8PkI51dgIAUofQzforShofB6YlvHHJPADaQHAE2UquVBAF8D8Jjw/3wAv9bVKWyD/gWg3wJopfu5EKB/Ma0flge7W8GH7Rj8E0B0B4A2+OC+fL22yyCIjYMc9qIdPhSDMBXLRFzlr8Gjkuuuq/I7Swj9sBZ9saY0qR8AO1O0igqP3mJGPiek0ARPTBNy7LHm7cRAbS0wBh+F+8yb+unHNREXzxOSNy0taVT6IEplPhfy7Cg1JE1mWcDHjCyA2n33mdHBI18Hx191NUBpPj5D4oGq4tQXjv0dn8VQLMUWdC18mNxEnPfvqEEmTX2wA2X5OFAFOQNYoLMZmIJmGZth2mdraszKfelLzE0oCgiJZC5cs2EVxmOuN1cdfrid1Y6KFhlECxsVvyC+Y0rddyTM6xaxTSZhFjJoRuO24cZ1IiHoP68zEdeYrOZNr/dLAt6VgYm4CJ7KKf+6ZCbi/FhdnXdM58rwjW/Ij6e1NqRoIg6w97l/v6AkV7Xzs58BP/yhGS1hMHxWBaQH/KM57baGBlLoTMRF64Y00Pp9sFcCOIIQ0oEQQgB8Hp4bsil6UoonKMUB9/MkgJ6mlcNGSSOAnPu9EcAiAIvd3wnYP7QBgHrBFGHAQElzcwYFbFOmMCkBm5u72QjYcRlXCRzkSidg2/hgu8+YR+FVYtiwBAgLwQUXeL+DqZVUSGBBNxJ6TCd/3peiBjkLCNgciQc3igNC7IWLJAYDfzY241VWViZg83IHDhS+n//7P78pn2oThZvoB+ctMTgkcpiL8dgDhSBn2jfiQNHOIozCcgzF+zi8sJ+aRBE3oVVsg0M2z4vCPOBFydE8Awc5NKETForhWsLGYxA2QlCEuYeARvbBxhtv5ANoUgC45homJJm4rqjM41WbzbI0XWE+2Py2uHBu4VPZCU0YiwXI9T8NOP1043rWELM0AN77Ft/7G28wE2rNBsGYMayp3D7XfaRYQc4Mfb7F4es4wKefSoL1iwI2DyoobqzofLC/+EU7uuMixSBngEWwsGuuAe6806zRJOZr3fsWBGwgIT/sIO8t3kOEPNe+2BNhz6P1+2C/D+APAGaAKYYzAB7WVirEJkJwHiGocD/nAQgJse9BP0ooHQpKhwH4K4BTQGkPUNodwMkAiuosftBAqrVwv22E0GCblGI4lqALtvqFk6AGqNhBzhobgT/9yeyaweslCAc5fPSRmatq4gjRavhu12WUHeSwAGOxEx0NKqUE0V8vDYZYAQc5rEU/fUY508mfL0JRNdgigyO0sQk9sOKca8xoSBtRmJi4/vsi4vZFXeAymYD9P//D/IXDrq/SYAv/HeRwAFWYgwn2dKehwZYgH2xKvI+gBjtMwFb5mppqsIMC9r9dzL4PO0x5SWk+ZdtnZtO3LcoWREGPKggghy3ohmUY6r0flZ+zCJXvvkjHu+964aZlGuzgswxosPPgdS2zczjIITevHeiDD1nViwV+/2Jf5zEbNPRXVjK39Ny+8f52gr9F8GsccUT0+TDECkWGAgFMjC/BwWkWFSQ6AVu17lqux4nkwRYRcd0dPJi5vluGVtDDdu45/HCzcoF7HDKEGR4kKmDLoojL1k1D6CyP8hiesvVKEUApvYFSOoZS2kAp/Sb1slaZ4iIAZwFYBxYo7UwAF5pWNh19R4DSV/P/KH0NwJHGJLbBg25C1gm/snriwG5pQQa0MLdr2C63qk2xbb4i9HWDvtfWFtbTTbinnZanQzqwgzSlEBgqi0ZQ6sU6KSo6KoRkAfnH7T5HBzlQZDATk1MkLAQK80xtF0pAg523xNAtUEcfbdbYJZewb1X/DNNgi309UK7x2ECqM1v0DFgaNTZG26Aopon43LnAMcfAF5LfhnExoZUQpqUGmHAQVkc1X6gEbKE93tcipfGLKmAvWKCuLzmWF7BlGmy+ARHWb155RX48qgabZ37o3Fl5ydFYiI7Y6V+P3nzTjjFMScBOqq7PasymDd2mEIe4MS0GEKWUWX08+qhZ+1xIsxSws2jEunXAmvVFNBWVCdgcwqaqbNp2HGDmvnHMJcF0ngHYBvirr+rLJohgfK/8uApm8LDRYKvGf8R+HSqAma5TqrEeMncS4qbszAkHig2Z2b1Ah4qkAtrjQMcby9ynksRdd6XbfuvAAEpxKqXoSSl6UYrTADFthB6m3NwaEPITEDLE/fwYRc4ndtBAx1TJzn3ta2ZtcvMU5DAHE7AP7mIaZD51wuv48fJZ45Zb2GrAo19XVABHBvZXwoTiuGakQZx4onl7MBTa0oKYr/C3v9WXdTVRUnN/EcXQYEdJ2ZWABpv7/2nf1QknmDXG7fCi7KT37Ok3vXN9sAdgFSqxH7m5MVOaBa89fHis3JZFwZVXAv/4hz+dR9JjGwB++Uv7NmXmtSoNtltnEFaiBzbqx9mePYXRWsXr2iIYuVXRToG/v0zA3r8/nimfqQb7gQeA444rOKzjeyvQgsmY6X+299xTmCJQh2II2BF9sAGgAfNQjb3sHm3a0G0KcYibWGec4f2mVB7tuNA5lH1FMBEHhFRrs4poKqoTsEM2CBwH2EU74COMkbcZhBi/oFcvS0Kjo6aGBYXPr28yCwNuIh5Xg50WTK93TXQrL8dhfswyD6JIYz0hE/EwH2zAoz2QMMgeOhPxtAXs9immiW09kDEixsyJ6ag8F8yx+38AvOj+Ptf0Im0QIB3k7BihkkVXJ+RIzLgd5LAPNV5u16CdrWphf/ppZpIma7uykqXCEc8FJ7iQwU5bFXQTdAAAIABJREFUNJNbsK2WFuCll/QpFV5+2Wr26oP1GDCgRAJ2bzen8+23A5/9rL6sO5H2wXoMwCq1Zu2GG+LTtWSJPqWMJsCQcn2LyuSuWZN/3x2xC/X4MNl3FcUH2wkIXW65dtiD8ZiL3OwQAXvHDv35Ap/JiIx+MXf3OTO4c6dnvpoGFL7vUthqsIX/BAY+/8ccIzf7TcpEvLFRGxFnNQZgXXPPQhNxwMsPHJUW2bOT9cGAz7Dp5RzkMBOTcQCCFtQmHVZcAdtN6xRaL+IYqsZ+TMTsdDTYTU3e76AmMMz6gVJPBxlRgz0Rs1FRAeRm29WzgsrnXPYsDQRsQGJNoHovfC4rQjCn4DLDNZyUQq7Blvlg6/ppsQNSxRXog/1X4rvnOKzrzpmDwvuOsqlYJB9sIEB7HOiCnMUVsE2tWQ9BEILPEILvAuhJCKYLnxsBGA82s1FC6WZQeiUonQxKp4DSq0Dp5miktyEISt2O/Je/FJ7kE6duMAjme/ldZ1vNZ58+zJQ5zA+PI3g+TPNmM7m1tACnnAKMHasuU1FhHmHWRWJmO7a4/HJmbjN9enhZYeEqMPfnWLcOuPDC+HQNG1aQr9OHYmqw+/b1vW8HOTQ2JrAmhjWgE7A19+Igh8a5VfECnQWFmxiatKKB0/yVr3h5ldPQYNsI2LY+2IH2HOQwH+OwC+6OfbD8Bx/YXdcUYn3dOATQuH+Cn26uhefRlaPSIjMRT5CxcpDDbgS0is3N5vTGpeWqq1K/joMcZmAKWoz1FVDf/6uvev7yOvNaWf2CzZJ4GuwO2I1x44DG2SXQYMveR8jcOGoU0JE0laWAHYTjsPTZy5bBe5fB9/P66/7/aZqIn302+24Yb1Y+yjpVXQ185zvyc5JNN18a52B/L4aAbTsnCO1z2mPzm0HrrH/+0zuXtgb70EY1WKasSgC1wmc7mB+2EcqcmzsIodt5fvnlwnN8IgnzwXbPD8Fy1GGzWsA29W/WTS6yndRevbxgJHGuCyRr/nzOOfmfjgMsWhQp+GI8VFYC3/2u1qc5/ziFxd5BDgsxBtsR8HmPIvhGgeUGBoBkmPOOHeEc1wUbNqiD7RpDZT4sntc5Uyn+O8hhy9YMC24UFVu2FLZf7rvGEYL6xL6OqQY7WE4VRXzTJuD66/N/s2hEMyoxGxO9erY0RoFYv6WFRZ8WNVYCcvsnFpqI79sH/OIX8WixSdNliqOOyv+UbvimJWDrtEtBaxR+Ok4UcRdZNGIbumLJuvBYG3mo7v+pp4CRI13iNHOWyfPjtxVRgw24m9KzKtLLmBAMJCWLIs4hpomTTNsVFcCU6vmFvE+YiXhSAvb//q9xUd4dGxshv2dVX05LwH7kEfZ91ln+4+PG2V1Ph/79PcnToP8OHMi8tKRCaho8kGLuVSH/aCXPeNAgZvSUmIDNn7foFx7MEGTSnGkQu0MclOLvlOImAEdQipuEzz2UYrFpO20CdrFhy6Dyyd/QxznU5DHM90ti7iKlUyZ8jB6NSEjC/EeFp5/O/+RzuyqAa1kgEOEYAGZgir9MsQTsKNdJQkDcuRPZ21hqGOsookGTUBMBW4UgQ+P6YBNIUuJ98okloYrrRWFciuGPzyGbP1Q+xLK9C9P+kYRWnBDGNIVopAuiXUs2LmPTaAIx7zw8ZqgrtiB3QCFgA/F2DFtazIKc2eC22/I/R2IxarG9UMBOYqPXpOzAgcCDDwKvveY77GM0Y1qO5DcRPu5qXsmk7+gCM6rG4ccfAxs2+I/HELCzWWDjpxms5HF9DAJ2WiEYrFLng23QZ5x2czELk3Cg2aDfcIEqTn8X36NFOw0NbHnN5SDf2FJp8JMUsMXNDdXmGndvCyLKpoS4IBj0f0IEq8MgXVH8g8OuaTInGZqI+2iPAx3/EkODTUBZjIck+JaDGJRiRZz6bQJ2OUA38GXBDYBCJlCYHLS5XcN8v0wmQNlOatjiYspQ3XuvF6E2CQjCemJmO2lCWLiUgc6KJWArGDLtOpWQifPEiexRGL0rMTT8qafKy4hBuUSE9XPF/wbMQ3U1Dc/XbYPWoMG2ELClMC0r06zatslNxIPMYIBp7D+iA3pjnfcuS6HBBoClS6XFnJ4rket8nJ+uoM9iHBNxjgga7LCiGVBMwYzCzBbBiiprmbgCdibDXHTCUmfFGHf14zJoh93ILVJHVC9AVGYeUGuwKWXa76BQZGIiPnWq9HBe0xolyr4Jgvf46afy44CRhtGpmYs9aI/5y4T82sUyEQ+ZN0QyqqtZNPFcDnqtfbCBCO5MAIA//tH7/frrrK+ImxtuuwUazrvvjnY9GUQB23Dn3HGA+fOBXS2BVKchqU+V1xcRdEEU+9e11xo3o+KZHYeFlRFjFVpDbHPRIv+5uCbiy5ebxahoQ2SYjRJCfgtCugr/60DI42kRdVDDVoOtEniDu5ligAU3t+tcSPxpTIKrhNEkK88n3H/7N3n5t5nvSGj6h4su0p+Pik6d0LMnk93LWsAWFq6e+BSDsKKQuUlSw29IizESEhDbtw9EWtVh0iTPeiLILFGqCEPqYscOvYk4P3f44b5yNdiHCfUHPMEhqQAqrcUHO22kaSIeADn7LL/VT5ippozGKAjWV7TnnDca6zZVY81mgalMqp9E1GBrbz3IaCKHWZiE/XDnreZmoIMrAN13H/s+7DC5kKd6/gsXFgbBjOC3G3qdIOrqCg5VYT8mYRYaP7YQsONqsG34CFme5SD+9jfp4QkTgMpK6q1BwWvccou6TRPYWBYZCdgsWGDjAgMBW4wiHhUmvt6Q347jMDmTkkxhfbECT486dKj6HYdtEojnB7nWCLJ5zv0moMAzz7C1VYYoz0x8f9znOwSOw17T7N2j/CeS4DOCz0xc2047TV3vr3+VHw+8m2yW3fLs2RHpE9vMZLy5kiOW5C5Bm0934jAdJRNA6db8P0q3AKVM0NuKIZsgd2qiDesEbLHNgIANAP+ChGEJY5B1ExdfoEeNUmv3HnlEHhRINxnYMNNR8Oc/56P08kWtnKDywQYU5v7F0nJqFlElCQkKiHkGxESO4deVCdg6mm66SX1OvMnOnQtu2pnU7AY3Suh9lLuATYg8LGqpfbBV19+2jeXTDnPkJwRZNGIBxqIJHYqnwQ5CIUBkp7Dr5JYIJsjBTbZy8sEOwEEOe9EOH8JNTyaaiPfvz76DGrUgTUGMGlWogYoqYNtYjgwbBnz1qwWHs2hE46Ja8/0nIx/qCBps39+AubVuY7a2Vpqqql07YPy4lsI16LLLWG71ESPUbZogYQF7RNUK5pKwQDBlT1ODHYN3cRw2RS1pGcoO8PfUoYOfh7rmGpYHfcwYdb9RBZnVmZ9LBWyhrm7sRFmndu2yfkZ5q8PdAV9wS39pAIXPLpjqzsRqau1a4PLL/McUZfNR7aModChlPKtI069/HaEhC7TlvS4AIRhFCP5GCOa5/ycQgp+Y1jcdJRkQ4m3dEtINQBFDSx5EkEyQ2sADKhPxu+/2BvaMGT7zwoFYhR7YKDfrUnEA3DRLQye6dGGL6ssvFwZYyAi7sJKdcu09pi1gH3983uzccZibWjC+VNkgsHA5yOFjjMQWWPj3JYUo7yLB95fNsnhUK0y8YPh1ZQK2rTWG7Li7C8J9sAHAmXyABTfC8GTu24bRL5UpuSyycRom4jZtqua0P/+ZffOozCpkMnCQQwsqMAuT0vETN6kfuA8+Z06ayKaF3GJhDkjKrJVSYHMgIUjCKXgKAp2JAraYJUN2T0mYiJvUs7lnyeaGgxx27q4ssOJUIqzvNDcXptgU65q4alDKHgl/rhF8sAEgO5m5wlDAe8a33w58+cvx5yHVc5dp00KCnAFAhrD4GDlRg60CDyb3uc+Fl00BeQFsvxtckd9Q0EWuqsrTOqvmus4K6wlbATsYm0CFKHNEU5N1f+nXjyW4KRCwo1hSBcdH0LJNltUjCEFRVHA60H7//sxbI5KA/a1vAePHM0sdSdupgGcFaYOIRwBcC2A/AFCKOQDO0dYQYDpK7gbwLgi5BYTcCuAdAHdaEtoGwBso995rVp6PYnHwU+pPd/D88/4q0AQ6Uw1UzjiHTYBf/jLQrRvTDMnoBOwn37QFbAFlH+hMImADkkBnJaDFCAm+P6sdYJ0GO6pZc9ANI3Bv2Ums3cT8sG0Y/aAFSymRxvXFdCSmGuyofc/VYAPuuzR9tikL2BwdazMYNy4QREvWz6OgpYXN6UBqGuzhWIIu2CoXsMVnXUQBm29e5F2WbDZVJHTmNxFMmemw9/WjHxWmaRLr2piImwrYKk3clBZsRncsx5DCsnH7iqo+D+AnwlBr6SCHOYvbe02orjFlCtu9veIK9n/lSqP2fbj0Uu93iIltkIz6ehZ6ILfXdeUTlRQixPdqayIue0+6qOWmfFwU3kCVdk4DQtxgYbvq/SfSWHOCOcdNrSgUVqZ52qMI2L/9bYRK4SiY99oQhg6UImiSaxy+3TQP9lMATgewHsA6AKeD0qf1ldogBR+EX/qSWXndAiYTvl3w3K67EQgGoRI29uzxt2k7gYm7rmGL7iuveKaBQZqKJGCXrR92YKHkjH9qQWZkUC30NnUTwIQJjCc0ele2Gmwh0rFWg63Z/Bk3phk12JOsgG36zKM+57fe8geFSwJpC/imPtg6nHKKtv1+WIt+WF0oYOuQ9H2r7iOTYYza4s4eW6Rjwm0gq2fhgy19NfzgZz7D/oLNY1oBWya4fvvbdnOQxD86cRNxWZuUYgw+Qod2zebuR2F9VpayM3DN0GP8P3+uEWN35Dc6xXkubQFb9nxMBGxCmEvCvgzmzw+5BsA0w/x8lIBPxx/vMRWyTQEXstdVVcVcnAsE7CBUvtmqMrILG5uIG2qwY2xm2sJxgI/2DsFOCGb/LS1+t0OTlFVhc2SQD5X1t5aWQmtMzT05DsteG4xJaY04a40q93gQ4n2oYikdeviUEAwH8gY8ZwJYa1o5LOxhZ/e7G5hg/az7Wecea4MtxKAFJjAReCXnHOT8uV05VAt7U5P59Qou5jA7Hg6TSdRk0UgB3boxN7qyFbAD/aIbtmAolnrMzdCh6dMgW4AFaF9XghskNTXMSsqIaVWNp0WL5ASbLDrBewn8r6omLLhRUpsfUTXYEtqUOOYYdeCacoWpBjtm+3khsFgm4u+84/+vmpsrKuA4wMZtNfgEA9gxiZAXCWn4YHNahGwHDnKYgwnYhyq5iXjwN8A2wWxomTgRePVV/zFTAdvm+UnarEQzJo1sUq8rAwb4/4ddL8xcU1afm5MGy5humCrONzQA1djrn+eSmudV70cmMJ14olGTeWuUYq3xvJ9rBGwVHAeYsW8ci+Ohek9hvNLZZ4cL2CJk17HVYBfRRSmbhee+w0GpP2f3n/4U3pCJWwYHIfI+qNvkkbSfzbKpbtascPK0iLPW3H8/cI6BVbP4Th96KPr1Di78O4DfABhDCFYDuArAFaaVw1afZ93vRgA54cP/tyEqAhMUQUh+at2Ot2xgq1I8qQaqq20ILSdDMGWCrX9gEU3EgfILdKYLcgYI5v6nnaZM5ZMo4miwE35/3MQqtDuqYhUAbIFRlVfV4WUC9yP6YHNtSSOyaOnVBzjuuBAiQ0AIS51hApH+YkWVV0Hx/Ar8JHfsAKZPt28/CQ22gTbGQQ4LMRo7UGtGV1wB+9Zb/f8DzFvenC9DPMsb21RiMnTv7v1OMyq88Mwd5LAPNZiHBnMNtq1mGSi0DBOfkyyImgnEFF+yoIluP3DGNGHGDAUPfs89/v9hz33TJv15g7km3zv5c40SGApATTuC8Zgr33wS/3fq5E8HZQJTDXY2Cxx1VP6vygcbhDCXhNrmViNg72jphEWQBI6VQTbnmIwT8TzvD+J4c88X5IdPGmKbL77o/dbMpQVzHy//xhvydlWw1WDLBGzZuNUopcrGYrKIGyIHEyjFUkrxBQA9AYyhFNMoxXLT+vpVmtKT3e+hoHSY8GH/22APiQZbGwBMp1HWnOuP1f7crhxcUx3EYYf527RBsI6G4SeQrIwlELCXLQvnYUoCCePsIIdlGIZN+y3SwCRBQxkI2NkssHWrwb6CTuB48MHCYyKd69bJ64VosEGY7+5O1GLRkgqW6ua880II1SCqmaoqh3CxYCpo/vSn8gwDxbi+oYBNkcHMlonycioT3KSgEroIYemSKlrUAnZUDaxq7v3mN9X1TzpJfvyll1i+ec64Cxps34Zvc3Oh+TKl8nUj7nxiuhGh26QK0qASsMc2YdcuZhKaB998Dvo/x+073KVLBx7k7LnngBNOYBGjosDdSMzB8chO20Q8RjkCwKnfVbxN9O9/n303NFhX5QJYI7JmsSRMgtvJINNMi4oRWw12VIjtn3GGUZW+fYH+Vev9vOz69f4gZUmsgWKgXwMNdv5WNHx4v37sE7svJmSlZVymTSAHABCCroTgPwHcAuA2QnA/IZBobOQwzYNdmCRRdqwN4RAFbJPolXySs9RgEwiaT/F8MFq4RZs+iBNacCIO02DrTPKKMLDzi1oZabHz0ATQmbE9ZkoUU+i0wS4KXtOd6cQ8NA50pqNZplkwNR3lUGxwWQc3Mr1eGET6BUGmJDBd/KPm2TTVYMf0C8wLgc2CKeITT3i/kxSwZXU1c3z79kDDkKZk/P3FvvPLX8rLPPWUuv4vfiE/fsopLF/8tGkstdCTT+ZPDcUy1GGzJ2CbBDmLosEOIiwHOt/wbdcO6KrI1BCkQRFgzqlnPqG5HJh27bnngC9+Ud5mMdyi+CWmTWMB08IsXVTP2p3ntqErlnC9ikwgS3ND1rdrEQ5n3G7MmRMprpY9TjqJvc+ePdl/ybtVadzHjgXaV+z1WwfonolofSIizERcpsFu315Zn0BiqZEmQvqB0+FDvSuWyRoYNuauu85Pj8IHuwBhtMsCnb38MvD++3p6RCQ0Xxgp89og4lUAQwDMBbPc5h8jhPlgtwPzte4BQupASDf3MwRAf23dNsghTniqKKEixE6/cqU/p2uI+biDHMvtukM4v3WrtGxBm2ED+oEH5DQC0oW8pGm6ApjiBuQuudmODJL7nwIW8jy3ZXhxaHj0URb8xWZX+PvfT4VpbGhga2foZoiu38gEbJN+JjERz+OhhwBCMBYL0B4JaUvKQcAeFsEwyfS9xxSAY1+fQ5GOpTc2YCBWIndAELBFDj1YL05/j2Ca7YzaXpguKQrEvrN9u/fbtM1MRq9sy2SAO+5gqifeNIQN35YWMxPxior464Fis9e3Hk2c6P8OIkiDIn3WqMF70bGjO1cde6ze77EocUcSuoawkdjIN59Ugpvt+zIV4iyjRGXr92D/fmDuXDtyYiFCX62sBCbXrZAHkJP979YN2LDB/Nqy98SfuTi38fPS1F0JImKb2Q4LsBCjsV3lvhNFwA7rewoTcSUvqxjTjsPCI4hTLU45BTjiCP31Ddo2hmwDJdh2mwZbhnaUYjqleIJS/JZ/TCuHzW6XgUnrY+CX3v8E4FdRKT6kIWqwTQSYE05g39OmsSiXwWApYpsBZNHIgkO8L0ykYdEWTQVscUIL2+FXXYOjiEHOAKaoGDmyfARspT+Zi67YhhFYXDwB++tfZ+lLksq1GwPV1YzvNdZgyyDTnNpqsF1QEJCOHYDLLgMIQSWaMRkzPfqKtTCJ76amJj+GZmAyHsTl0dsNpt+zxVrjAJvmCJsfdD70HOJ7CWomhHNZNHp5aYMosoCd98F2yXNGbcdmdMcKDI5nIm7aR59+mrk9BGGj2ZowIf/TQQ7z0IA9ByrNgpxVVaVvIj5jpidYazS4eVAKvPaa/7z77CuqMpgyRTFXBbXxxdRgxwUhGIf5LGNCiyZdZJHTOkqrcnePccx8OP8u7rkHmD078rWMUFfH+rto9WIAp/syzMRkNLconkWHQE5vrinnsLX04ONM3CiS1S+mBvv444HvfU952mn/IXPfwWR5gSixJHT8jcpEfNQoeVlAzYe71v/GyTtk92ISJf3mm9XndP2jyPx3K8PThOASQtCXEHTjH9PKYT7Y94HSoQC+J/heDwWlE0Fpm4AdBTZRxA87jE08e/fKd7vCBjY3ebz5Vel5KUwnalHAtjURHzfO/1/cNCiSgFJugc7yUNy/gxxyWw7NsAfZLHtX2jVUZyKehICtiYHgIKcObpQWFBrsp3A+/gO/QhM6SCoZIIqfpvhsgsESRUQd22HMk8pEXCVgB9sTyjnIYXHzcGyDJN5BiTXY2ZFMBSJNJRbV+kHXxnnnyYNp2TDeb76Z/5lFI/ajGnP3jykUsGUa7CSC94XRWitoxEyYWB0IgeMwRjq0qTSDy7lIjG8mBFU4gImYjVzL5IJzeeie9euv+31mZfUtEHZvQwYcQLdugoB99dW+zZ5UUFnJhPiTT7aqlu22DE3ohIXb+sgLfP3r+gZ0D0OnwZa9r7S1mKo2m5qAu+9WVst2WABAErSXw2TxDT6nMKFT1mY3T7Yq8MFWwNolUXZdE/eqbhETO7UJ2DrsA/BzAO/CUzAbq+ZMV8p1IIStRIT8BIS8CEI0W5ltCIXOZIODr9IRTUDzuV1X9gwvHETYoNNpHnSM0V/+ygTq1au9Y1/+sve7iAL2ypVya6uSQiNgr9zVExs3FpkeCYo9HzsOM6/6+GNNobR8sHX9UfDdzQc3KtbDEek/88x8oB0KUpjSJG2I97xiBfveuRP4/e+B3UKu0rQEbBMNtq49ga58vANIlrckfbAjaPrHD92JKuyTC9gnn8xSz33/++EatLiaKZv6wlqQj1ewf6KZgK1z0TCFDa2q1FimLgqugL1nD/DhhyHttCYTcRcOcmhsnsRSSnEEBTLVs2rXrjDbCJCalpRkSNltoqsejdOdRfDMbRwsL2hiSRbWR2U+2Ndeqy+XdpAzC/Sq3opBWKEWsKPkwdbdH6XyNk02MwLo3ZsZnxpbTMoYnQQ2/5RoMxHX4bsARlCKIZRiqPsx1nSZjqDrQOkOEDINwBcAPAZAEpq3DaGQdGalT4epSkwz6Jnm08K02MIPT1knjmlxkQZ22QY6C96/G9wl7wNXbvQWATzQmfbee/dm3zImLioI8Y8thWlxSd6NOMZOOIFFy3nuufyhRIJhmUImAM+bB+zfB2zezD6PPZZs+ybnJWloAISaiAOK55ekBlvcVDRETTXFBMyRp0uqqmLp6O68E7jwQn1DJqbQOghzf2gV4R0Mwkr0wEYmYHNtpozxj0KTCjZCgolmn1Lg0kv953m/qKzUrytFNxGndo8vpLAzYD12oDM+xgh1xGtVG6ZWEzz/rswU1wTiZpnDpiGZ4rzY0L3u0Z3XoSN2egJ2FETxwZZpPNMWsG2xdy8bbzNm5FNiShHFfCxscCgE7AJ+3WCQSQOdqVBfX3jM5v4WL2baIxG2AnYbOD4GsCu0lAKmI4i/3ZMAPAxKXwFQ4tC1rRQ2ndnUX1rDgGbRiIU7+mHHDkP6OnZk32GTa0QBO/S2izTIJ09mlyoHP2wTXmsymANPOdALFHcurq9ncrP23h99lKXjOvxws0ZNbiBYprmZ+WAHTMNGYyE6dizyu1GY9/HFv6gCtoYRIaDA+ecDF18MzJ8frX1TDXZUE3HhXA9swuCKVekL2FzTr0HQBxvEy7uuDRoZBtNMEioIQc5CwdcTIB/orJFOBn72s8J0YUkJ2M8+66NVB1/zpkLgZz/r/8/NN6urMXIkszrPzwU8MnlNTTIC9siR5mWTlOHfew/ZZ78LIOLcYrqpIwp/UZ6RuFmWZVPTnDn2zRQTFRmKKZiB3MZB7IBtn9dZDsieoYY/K2oebBP86lfAI48AYLzsYozCVnQpLBfFRDxMgz19utl1Qlw1AdYXFy8Gtm0LJ1MKG5eSESOYylwC6bqxfDnwk5/4j7UJ2xxNAGYRgt8QN0UXSTxNF7AahPwGwNkAXgUhNRZ12yCDrgO7E0pSGmyKjHmAheeeY8ESJiuCSXCIk1NwoorjO1ekgd25MzB6dBkKrAqNQGfswOja1WVDbzFRVQVMmhTyrrp2BS6/PNld9yDjkh+PxDsPoAIt6uBGtjANkBPiP1dUAfusszQniZdnPGrOnKgabP6MDjvMWMAGAKdqTvoCdhcJkxjE+RcUXM9BDltRh6W7+8rrmKCpSX48ivWSCQSfVB7obDfa+U3Ak8yDfe65ngZUQauU0VTd1ze+oadJELAzGcZM5+eC++9nvqUnnKDvg6awevaW/VP3rA8/HPWf6YJ2GTelFM/rHXe9VmnAQ8ZWWGBQwCLFYxnAQQ6zNg3EAUSw/jN5GKaaabdc0dN0qSC4d2ndd9IwER8ssSjQpenS8eFuX5wxI4RGHT1xoHNJPeMM4Lbbom+AH9z4I4DbALyDxNN0eTgLwP8COAGUbgXQDcD37ehsA4DwgfLFL3qpckw12JrUW3mTR9NFpl8/lg8wbMK21GDH0rikhHLz0QIgZzjcid6pW9IqmIU0kM2yxSmUL01ygya4AHMBW7IZks0Cs2YBB6gBg3T88epzgsZPC9l9CscWYjR2oJNZW2kgSRPYqD7YHMFNC42JOAA41XOwFMOxBYG8yEkK2CbMq0QIz8/nW4uUUUAG2zEm3GsWjWhGJWZjYqGAnaSJOK+XhIn4HXfoy3EhwI2V4jgs1tX+/WDvcPr0ws26qH3H5n5sLxHSdmUlMNmpRG7SJV5k67C1/7DD5MdV19TF0rABpRg4kAXcLpc1XtmVCUEWjdh9oBoLMDbZNUyXB1tKi5+uxGHbprAeat130ghyJsOvf62uHqLBBmJs9phsyOnGjO5ed0W2gD7oIabmSiNNF0cPsMhpe0HIIABVAD6KQG8bwkzEDxzwgpolEJa4NzZgYPtPkxfMdAJ2K9BgA4wRWr06ncxCiYEQ4Oc/BwA4XZdg9WpPIXgowXFY3KxFi0IKRjH9NinnC3pCCs47DvP1W7DNIAq3jpHvdDO+AAAgAElEQVQ1ZaBl5YRj2pQmxUCSue2jarA5DUHz3DABu4ql8ynw90tSwDaJCit5bvl0SXFS9g0aZHw9KWw1W4Eo7QA8P/Ji+mCHvS8T/2GZtlDQYAOMmd67V6IQSkLAtohvYn0Jg7adwyswY3GtYMwTeBbHHw9cdZX3f88e9t2+vbxBnVtHFAjtEWLp+5oiwt6Fb1ykke7M2Lc6ZR9s2/EspCjrjs0YiqVyATtKELCk7s9Ag92jBzBkSIy+2Bbpu6ggBP/lfs8lBHOCH9N2THvYKwBedr//BmApgNe0NdogRzBNl+s3mTfZ2LfPM78y1WCHIFu3NPldXJ2JeDmYFhmgLAOdyTTY7jGnbgmA0jMMpZjrjc39TMaEKZMqMRGnIFINdp6+TUP9bfxWstkpu/5FF9nRpvHBrgRj+CObie/bBzQ0RKtbQBPiC0kmebAPHCg0fRYjVVuYiE+pYZJRwfNLUsA22DylJOMnjxBUYz9LlxRVwD79dODKK6PV5bAJchYo1B+r0Rvr2OZF8BmkLWA/GBKX1fR9BsceX6fddVs5VyVhIr50qUVhyyBnBhvj2SwbZvmNTtnm+r33ev95hDEuYK9a5d/Rjmgibopslm10lLuSbiQWo7ZqtzyAYRh0Ptg86KexBtvAB5sHR/vDH8xpjIrAxowy0FmxNNjQWGOG9NlYmz0Jm4gn2vbBCb5IngzgFMnHCGaSEKXjQekE93skgMPA8oK1wRZBDXZwZ7elxdNgxwnN379//qdTtwSLFsUIsCCDbiJuJQESJk1ivFI5CKw68zGOSV2Xg5Ay2xAoEsaMYZvZiQjYphtAwbbcRVzmL58PbhQUsKdNU7dLCPBdFjgobw5sKmBr/FU7YzsGYmV0AbuqKv4mWbE12DfcUHicM11BATuEoehWsQ3DsKTkAnbBc3Ov5yCHxs3D/OmSZOCR9UXU1LCcdybXU8EmyJlbPn8JuJkt4PjXt6RNxCXXRkMD8Mwz6rLiTb3yirpciAZ7+HA2nFMRsG0kRdv+aaLB1m10yt4VF7C5JnLAAKCPkO85ool4qNsxHysOe9SzZmmbU6MYvAwhyIAi23MVEx5tr6l7GO+9J72ejpY8ZGvAvHnAApaTGmecYU6jybVlCKxzWTRiKYZjM+r85VTz6fvve+dsfLBtYLgplM2y/bHNmyNcI+p8wWEiYLcSvr0YoBR8F/DblGKF+AHwbdN2ovUwSmcAMAzX2wYfgoMwmFaIUnMNtg6ids3VfEYOsCBDK9FS69CpE8tuVFYCq2azolPlHowdW/oNAaD4c3FlpUGgM8CsX0YRsCktDHIWaDKblQjYMkGYX79vX28zzdZnlLcrClHimOdCTFSkrXW2QVhwNEqBt99W17NNG+gGE0vVRNxkble8Agc57DjQnqVLAtR95q9/BV5+2X+stpbF+YiDGCbiAGOSP0Q9mtAhfR/sYH33HRZEaA/ic5+TH6eS4E/8XbpjWWmaLNZLwP0rcRhosAs2Ok3fjyp9YtIa7EB9oxSPJu0lgLCmsj1XYBYmYT81cLF74AHgvPPCy3FLpChuUbJxPm4c0KuXWVtx8Ze/AP/6l+9QPiVmcG6W9Zd33wWOOIIF8JIhLMiZKfgzCxGCYwU6M6HHoEx+3ks0xcBBDVnAnC+ZVjZbKQmZLny+B0KeBbDG9CJtEBCmwQY8ATtsETbciczWMbOyRAUznYk4wO7zm9/UkVUW4IxQ2VjJ6KwBKC0bn7JSwHGAmTNDhkXKJuLsuPxa2Swwe8tA7IfAIOkE7EzG5yoSStvXvub95uXEh0G8NF0OcliMUdiGzuzcvHnqdmVIUsBO2OxTeq3u3dXnxWBahnCQw3IMxacQ2g3SH+d+du4ML0Pky3NBsB++XgTR0ACcdJL/WKdOwJFHymlPywc70K6DHFpQgVmYxNS9APCDH6SjwQ6CM8FHSSxLxGdiEGk5D26lItCfzbL0UL69IdlckiZS0GBXVMCfMSHs/bz+OksB1KOHGQ0J+mADLGZrnz4x1syE+p/2VXAXsO7LsRftMH/viPAGv/1t4KijCtoIu0YYyipN1xe/yCLwC5gCJp0WbB7LHjBPhfjhh/IyMc2mC6obaLCBiH2xzUS8qCAEVxCCuQBGB/yvlwHJ+2DXCp8aMF/sr9gS3QZ4DA/f0RWCOABgnT0JE3EBPWp2YPDghDW1uiBnHCrGr4yQzbKgYWvKZbtIJmDX17PfJ54IxykzeosIx2EWkh/pwivGMRE/8kj//z17/IsP98GWBDnj9O1tqcZ8jPMOysZAVAFbzL8r2zV32yKghSlNZObCKSPPrKVt7dLSon/vQRPxMBCSF2J9mpIkNdgGkOXBBoB6fIh2Ffs8JtMmqGSnBCLLJ6DBBlwmuUsX9hzPPTcdATv4jvKbZCHt2gQifOUVJk2LFiQOsxz37WslYSJuAUrjmeOqkM+YcADhz3HcOOCWW+w3bxKIIg6wy/rSppUxnO7LAAC5prFmFUz8pU3PB8qVTZquAOqwFSOw2EzA5vwz79e2abpMYajBrqtj+4mR+mIR5ouy036VFs+C+Vq/BL/vdZZSGJiOMJj6YN8ESm8CcDeA+0Dp70DpHmuS2wA8/jhL7M4Fa5npVMIabBCSvObTZHLnGwXQBIaI5JCSHMohV2bo7nZ9PbBpE3DxxcWn94MPgN/8pkgX08Po3k2006qFlW9kcDz5pP9/3gdb/sLy9ImLv4xp5TQSYhcgUGa+F9Bgc2hTmpggIcGGJNGW4bWUsBWwodCUJKnBNoHCB7sSzZjcTfCxN8mpzaGK5iy7ngqCD7ZRlUCf7oe16IfVhWaeIbndEwFnVGXtmsYNCJ7r3BkYP953SDpXqTTYPGhU0qCWQc4MLXuMNjqjwsLaRXpvkoOOw9yGTYxGzC6SDoZ3Wo8u2OoXsAcMUFcwUXLEQZkKXMbuTzw2gmrjKKKAXcDLWvTZyHx4QhtOqbR9EIJSbKMUyynFuQEfbCuBxdREvAGEzAQwH8B8ENIIQhIKM3uIobran8D+0Uf9UcSjarCnTvVHh5WYFi9ZgsLcrmmipia8TF1deJkUMXEi4ytKvcOtXMv4iW7dAEIwcWKRA7NNnQpceqnvUKnm41GjmAIuf++PPQa88Ya/UBwBO8jojh7tfzFcOFFcY/hwoEtVk3/xr6oCLrnEywcL+P2t+eIvRrw2AW9DIWB3x2YMwTKPFltmqZx8sAHgM58pMBfMI2x3P+yZBmltaUFXbMNILDITsMeNQyrQvAOnx3LMwBQ0I2PnY27rj25Jl2n5LBoLmWTZhnJaArbKrYlDNUfIfLAlGDKETSdKAVvss3//e2h7RUGwbyiizfs2D5J+PxZBzkzhOKz8zJkx6EoAYWs8oS0s9kPTaO/cqlVmDSalwc6kbCKewLqQRSNWYjA2QnA70GmwucLKxkTcBoYabIBZU6xYAb/rkQkS8sFOtF4bQmFqA/IwgOmgdDAoHQzgu+6xNsSFyHgDdkHOxAniP/8TGKH23ckH++Bag8MPBzp2tCTWgA4Rgga7XNGhA+OPyybQmc4HGx69pd4QKAUqKoDJk4V3ddFFwLHHFhYyaUgGUVvwP/8DvPWW//w3vwmMn6AM8kIIkO2+3K+Zq6oCHn6YRTPlEM3Cg2PdNIUKb0Nc1AUfbCCw019sbURexZnQtTMZ4Oqr5YF9whgEWx9s95k6/dbIU8IEr3vjjeZt20AzFzg9V6AJnbAIo+xMOXX9y9TUPKaJOMD65kcYgx07hINpCNgqE/FMwPw+WNZGg60oUmCarNJg9+0b2l4kxPXBVsQ18G10Jj2vpBCvoSzTccpAKbJoxOymEdgLA97J0u0FgAHPJ7Rp43piigTeqzTQWRQT8aR9sPfsYfEY3lUnWCrgw00R10S8TYguCUxXyo6g9M38P0rfApCQdNaGAnDB1CYQSpCJCYz+Ka4rpk9rEGdxNGFGWoEPNuAxQmUxB4UI2EAZBmYrInigM+Xek40G+69/9Wutr7jC+33aaf50Mm6UYzpyFFTBpwAWqGY2JnoMki7IGRBfwBbnCMEHG2CMyFIMj2a1kiTjnATTzIVkmYlzkPkIboDYmoi77WVH7cQqDMJ6uO2pNNgpbV7oIl1ne64E4M7n55xj3qhOOI6Tg92yvIMcKDJ+raJsUEd9tqp6+SjiIRps3XUN799xmA/2Hu5MJ9b71a/Y9zvvFMZhSQyW440HnONQMPWZDOMnGhuRngY7LoR32bcvC3YWaVM6ofszmvpamAZ7P63CPBgYiNqYiItWUyblgHT4t7AHwQOSaWDkvgMUmoinrcH+8EOWzeLyy5VFpXy4CRLywZZGET8UGckiwXQ2WwpCrgMhQ9zPTwAsTY+sQxiiBtsGhGgZhG7dgGFY4t85i7OYidcaqwjK0Qo02ABjhDZu1FtjpQnf/GYoYJeSXqB07lmOwxhW5TpsI2B//vMsejHAmFxNbumQQx59PZZjP6o9BklGj6jB5tfkwoVtCrGABttHi7jTX0oT8aQ02OJ38FriNTp29AstYQK2gsFw+rNUmHlmKFjuvvvYNyHA//1fYQOcm4oKhQ82AIzpvAYd0ITcUVcBt99u3qauf5lqrBIyEQcCWsVimIjnNdgWgoaIm282pslxU33P4TFnZfUmTDBzpYoCW775178Gfv97ob66Acdhgc72NyccCCvuZpyifmTf11NPjUaHDYS5nM/ZRgJYFBNxm35fCg22gbtNZ+zAaHwULmAHTcRtECXImUGdLl2YBYi1gJ2mEKyLS9GGWDCdHS8C0BPAiwD+G0AP91gb0oDphBCcYEMGYYHJaFIa7Ouvl5cZMqTgUDmO4XIIdGbzXFqNyVsKCH1Xtj7YvHxCO8T5SLC6BVRmIs4Z/zga7ICJuG+nv1Qm4gCwdSv7jkNDMNq6iOC7GzVKXtcSU/quBUGL2pzv8cc9mqZJ0j41xAxTonleFRmKKZiB3LoByZmIW/j/xwlyBgC9sQEDsdI/jothIm7qg63CV79qpcEGQlJaiZkEEoY1T96xI3DWWUYN5Dc6VyRsyGjhgy3tGor+4jjAwoXA9u2GdOzaxYLR/u53hhUSQEsLhmA5ulVuT17A5ggb46UWsA1hFOgsJRNxZcBew3tznAgm4nF9sHXnVq+2o6UNxjCNIr4FlP4nKJ0CSrOg9CpQuiVl2g4p+IKc8YGvElylDWg0n+5vX27XuAK2CNWkff75wIsvJnONFDFhApuDy0JgNXgnnN5D0Q97xAigtlZz7yZMgZjjLOjLfOSRwHHHFdYxXDyHdPoU3bBJv4Am4YOt0WDzuaQOWzEcH0eLJJ6kQD53bvw2dBqY4Lt5/nn/f9kz1UXedturbbcfo7HQe5eqPpDW5kWINYuDHGau6m6XzTEJDbYtFNfMojE9AZv76gfT0519NjB0KPCFLxTWMWX+DWkaOJClfw4VsFODZRTxgurq55HP6buoc4wLSJBwmi4OvtlhHOisfXsWjDZB64LQd9HSAgIg23mxmQAWxQc7pI7vsZWxgJ1FI1ZjANaht7rd4Jpqmtv04otZjCJTyNZiDbJZ+F2PTNDmg90qYRpF/C8gpKvwvw6E/G9aRB1q8O2IUUHQvukm80ZCTMQBFOZ2TTvPISFsxx+aXb8yQLt2LMtKWQisBotm+/ZMOVYW9BYZmQxboJSbIbZRkoPmXW+/Dfztb4Xn4S+ma04aIVmETsC2NRGXtSvAQa5kJuKJjnlTDXb79kDXroXa/mC9bdu83ypTbELgiO/SVsCO+Qx1PtgA62e791XapUtKQoNtC5VWETksWiS8iiQF7GuvBZqamIQrom9fYOlSeV54UybUcIwS4mqrdBu3aa7BcXnq2lrlqREjWHayRATsiy4C/vQn9jvuvKOon98QKNGaGZqKE/CCK3ZehLkYjz0IEe7T8MEW43iUwgfbEAWBznTt8nsPZENR4pFHjDYX8o/c0q0hUqCzYgjI5Whe2sphOrv3AKVb8/+Y9tpi+6UNxrAZSPv2eb8NfHe5yWh+YCdlIn4QoKwCnYnQmLyVit5SPyPHAWbP9nf/PKIK2CpIblZbhVI4yOkZJJHJCfpg22qwQwjLW61sTnkzLQj3uSW2ZOsEbNnGos3cpgpeBsDJzMAa9McaBCI9a3zfQ4+bQuODDXhMppXQUEYabE5/XqsomidzRH2GhGiDh0lN3Pk7/a//klcaPdqaJscB5s9nFsfS55CyBjsWFGm6AGGjc7EghEd9V4895vk6qzTY3/hGtLZd9OrFLArKelOaC9hdP8YBVGEOJujLR9Fg2/S3tOaDBDAZM0HQEr75qUNSAqWlBnvyJOqn3QS6tnn8jy99SV3GfT7lrOg6GGE62lpAyKD8P0IGI/7+aBtksJko9u711wvWDQQf8+V2JSQ9jUUrhOMAmzczt6tiQxvkTIFS0ltqOA7r+vPnS04mLWBHgIOcnkEShcCoJuI8tc/gwb7zwQU0b7Uy05KRT8r3NayZ0aNDCrjYuJF9R81fbHM/fF4lBNkMk/4akfVfR2R4Oiu0eClp4zhGYRE61eyzExp0bUZYD6L6YANe38zTLwrEL71kcYGEsNSN28rDfk+dCvziF+z31q3eToCFkOI4TDE/ezaSMREPCr26QHpxd0JDgpQ6DjB7SSfsQ4KaTpU2MGDNp/TBFgsEEDnQWbHg0ux0WQzAIBCW+ABMTYhbgw92//7efK9AJzRhLBbEE7CThiENtZ0oxuCj5DTY06ax88HYIxqQNvGtKDCd3X8M4J8g5GkQ8gyAfwC4Nj2y2mAEUcAG9IOQ746KwSHiTKDlMKEliLzZTon8sG35yFIHOiulNZHW3M9WSAjz+YtgWi3N0ylrM6qJeEUFM2N75RWW5ifQrrh45gOdzbIc68V6wabzCBduZHQ98wzLWw4kI2Dn8yoBkyrmIoNmNmeKtIrmzKpNAvGaPC2TDYI0B9LGZUCRHbzJTmjQPW+L9cBq+lc8+x7YhMGDFeO4Xz+LCyQMHgnrgw88gbZLFy9FnEVf8s1VhlYnWhx/vP8/32CT5GKnNN0xnM0C+/ZnzFJKmUJlqRLHdcaF4wAff+zFXCw2lKQFNhUGtv8UPbDRTsAOS+mq0mC/+SZbR2RtlkrAXrMG+POfQ4txXrZonKhrZVGgBdZpsHfvLoxB0tIS7kYWhPjcvv9983qHOAghXQkhfyCEfEQIWUAI+Uwxr28a5Ox1AFMA/B7A8wCyoLTNBzsN2HAugwapzzU0AL/8Jfs9bVp+Ac6iEaswCBv217UJ2AIaGtiGfcl3uA0ZrvHjmWxWcnpLgOHDGb8r3VyI64MdgoJiDz8s5OFhGIhVegZJZCKDAr6Ofl7moouYn/GXv+wXRCRMaBdsxygsRM5Wgx0XsucZPHbDDfbtyhjtp5/2GEyVibiNIMPzpwLolNmFsVig12AnaeY7cmT+Z4EPdkMD8MQTrM+5tGSHbMLs2T6So6PIJuIAE3r+9S/JiVLu4IXNIRbvu39/5u6tFLA5ZFHoZVC5DYwfLykcM8hZCPJR0qMEUVSB98Gg/28CN8LpnTEjdlPWMM2DDQAkQ7zYGTokIWB/7nNsHZG1mbQP9rHHmmvaDR5YFo1Yh75Yg37FMRFXWXToeIhvfYtFpd0ixIR207GtQX/juGu+56YzBVfB5Pn885/27ZY/7gPwOqV0DICJABYU8+I2nEEzgA0AtgOoByGfTYekQw8UJJrJRo8ewNFHCw0Ji+3TTwNjxrD/7drlg4jktWtNY0piIl6ucRRqasok0JnhA6qpYfN2yektAXjwoEQ02KYCtnDe94ouuaSAuSUISSMi09KYCNhhOXwlJuJwaWmcZflcdu2yKx+EiYAdRTBNYwIJsV7Ia0rEYiLDo3pnaZiIX3gh63OctkEb9HnhAfkaIUNa60GIgL10qZ//DKtTcli8V1+gsyOPVBd88kmzBm0sNFLeBB82DOjaab99yiEduJtA1LmCB2aTlC91oDMlghrQTAYOcpiPcebTcJjgWg4+2C+/DOOUBwZ915cz3KavB61ATNGune9vQZAz2Tv4xz/Y9+7d3jEh37mxBWIwzshnLBWxsncZVNBt2sS+0whuVwIQQroA+CyAxwCAUrqPirHEigDTcJgXg5mF/y+Am9zvG82qkgpCyExCyMuSc9MJIR8SQuYQQv5GmG83P9dMCJnlfl4yovNggO2iyKOhigvsF74AdOrkFx7ctDT54BA7x5SvtFsilCpwmO96uvRBAZQy0Fmp4ThMcRz0kkjcBzviGOEMkriu5iEK2EEBP8gA9RWCa/EFPESgC27WZdGIVZ9ksH69xQ0EtPKJQJaH1Lbzmr6vILMTda5zg9atRx+sXic8d1FjZNLnCAEOOyy8nJgWSEezywQ5A9YBCBEaxGdciskiRMAGJFrFUgrYYdpAS9ocB1iwANj5wG+B730vBmEo7BNcahwwIF67EUlxxuxMVoPNzfCD41fyzKXD47nngNtuAyZOLDjVvTswZEgZCthi5hgg72bUjErmu2+CsHRihgK2b4PWRsD+/e/154cMYZsniZjaMEzCLGTQXGhdFIbnn2cRUm3XhDDezJSGlpY87cZ9Mdi2gQm9D506FR474wx52dtvt2u7fDEUwEYAT7gy6KOEkI7FJIBQk05ByFwAUwG8B0ongZAxAG4HpaeHVyXTATgAOlNKTw6cOxbA+5TSXYSQKwB8jlJ6tntuJ6VU0ivUGDhwIH366adtqpQFHrmlPV74exZ//tl9bIGprzevzLf/hw1jk8YnnzChe8AANpnNmcN2qjZvBnbuBABccOeFGNBnB277wdvAOsag5RdqU2zfDixebFa3sRGzPh6Aqx86G/feOwuTJm31tu6CzsS2dCSIV17pi7vuGo1nnnkf/fvLJKN0MH36RDQ3E9x33yx2YONGYPVqxuhNmKDcUSwVvbfcMhYLF9bimWc+KNo1g/j733vixhvH4aGHGjF69A7vRHMzMGtWeAO8n23cCKxc6T8mYudOYOFCtkCNHo3rrhuHNWva47HHFCvj8uXApk3457zhuO7J0/DAAzNQX+/6dPI+3qsXsGEDG+v9+zPHwC5dWO6bffv8PlsTJyLPZQ0cCKxa5YXEDaKpCffcOgD/nD8CL97wUP7w7CX9cdWD5+COO+bgiCM2hz8bkdYoyGaB7dtxy40jsWh1Pzz9g0fZ8c6dPf9WgJm3b9ok2SXRtLt6tTdnyVBRAUyaxHy2OZOezQIrVgCffiqvM2AAmzc52rdnGod+/YC1a/Hh8j74919+HbdcPxPTjnVzSon9bPJkxrgGn1mPHt41Bw1iDGZYTq2OHVl6KQB/WHwSHvjNGPy///dPdOoU0PysWgVs2ICW/gNx6sWn4/OfX4+rr14sb3Phwvzcj8GDvdRVQXonTpQz1du2sTlogWtdl81i2bKOuOiiqbjxxvk45hh9QCJ88glUuzs7Rh2OU0+dhksvXYJzz13l0VRf7wlbKawNr73WB3feOQbPPfcu+vTZ67/OwIFsjKnQ1OS9x44dPUsxBd55pzt+/OPxuP/+mRg/YLkXTA3w7ik47lUYOdJbd3n93bvZswq8z5ufPw0fr++Lp56ynKd372bjKCTIGQA8/Mv+eOFPw/DKrb9EdYcMW68Axm/s2OEPwiiisTE/pxZc+8MPPT6I31NgHfzmNw/DqFE7cN11dhafN95Yj0WLavHss++r6QIS50NOP/1ITJv2KaZPX1R4ks9NXbqwsda1KzauOICzbrkM3/nOYpx++mp5o1u2sL5UV8f4v1mzCjeH+H3w51pTw1xNFMiPix89jD7HGwTNEp+Xbs3g1xXXWx2GDDGK4Ppvd5+Pnl124Kc35QrH7Lp1bL3o04ets5w+Pl/Pmydfe8R3L95T377A2rVYtq47LrrrQlx//Xwce+xGtn5v28b47vXr/Tz8nDmMDxf7b0sLMHMmLrrrfPQeksEddwTGvew5is9j9Gi2lvC4JCZ9dc0aYO1arNxQhwvuvAg/+cYr+PyXtsrXUg3PWU449thj9wEQH97DlNKH+R9CiAPgPQBHUUrfJ4TcB2A7pfS6ohFJKQ3/AP9yv2dRoMb9PT+sHoABAP4G4DgAL4eUnQzgbeH/TiPahE+HDh1oa8Q1uJ1WYw+LAz5hgl3lM89k9X7/e0p//nP2e/p0dm7tWvb/wQcpPeIIHmecfgNP037VGyhtbs4fs8bq1eZ1AfomjqEApW++6R3z1Y1KR4KYOZOR8Pzzxb3uscdSevTRgYN9+jBi1qxR1psxgxV57rl06Qvi3HMpHTGiuNcMYulSdu8PPRQ4sXWr15d0H44HH2T/CZFf6B//YOenTaOUUvqVr4QM0QsvpBSgn6AfBSi9/37hHL/2lVey74YGSl96if0+6SRWZsUKr1xDg7/evfd69WV4+216GR6kvbHWd6/b0YkS0kJvuklDdxAmz1D3bLt2pefgWTqywyrv+Fe/yr5HjGDft97q/TZt9wc/0Jepq2Plamr89S6+WF3nrru835s2UXr99ez3jTdSWl1Nd6EdrcB++uPLP/Wez6ZNXp2dOwuf2UMPUXrJJd7/X/+a0g8+CL/HI4/M/77n+i0UoHTLFsn7ueoqVu7uu+lxx1E6darmXR51lJ8O1TtualK3sXOn73nOnct+vvCC5roc06dr3+mwYWwZ89E0b14hnQni8cdZk8uXCwf5de65R1/5vffMnpkLvlTeey9li4tsHlqyxGwM/PnP8voi/e7n7F5v0NGjjR9JJLxwTY4ClH4Ah9Levc0rNjdT2tJSeHzePEb/2LHsP7+fwDo4ciRbh2zx0596w1yKFPoapZT26kXpZZcpTvK56cQT2fdpp9EWgPbGWnr++ZpGn3uOlT/7bPbfXXuk/WP2bPZ/1CgtnflxgUFmN9a5M6ObUn2/HTOGlbnvPrN+/uSTRuW+hcdoT6ynLff+opC2225j5a65xk/f7val8HUAACAASURBVN3s/9Ch6nWGQzx+552UAnQe6inAWG5KKaUnn8zO83lOZBB69y7sv9u2UQrQC/AE7d1bGAYHDrByMpoefdT7/eabbN6x6at33EEpQD/CKApQ+izOofSGG+TX+uQTszZLDABNlGplyj4Algv/jwbwiq5O0h9TW6dPQEhXAH8E8BcQ8icAKwzq/QLADwCYRDb4NwCvCf/bEUJyhJD3CCGnGdLZ+sE6gjlMIpNS6tvZdJDDmn09sXZ9DDO8fv2AZcuA114LL9tKMG4c22gtOxMyBTi9pYgkXmrvgiFDgG7dJO/KxFz3nHO83xFuxKRKP6xBb6zzv5tXXmE+tDoTcV3jfAyr7jGTkfpg12Inxoymxe0nbqhen7k6p5+nFkrTB9t2HuXo0sVfl1K0xx6Mw3w0zhfMMEVNkew+GhoKI/KaRojnMDARx/79yGY1eeEB//3ofCA1eaNjDfiQutJ4CuVsIi7ej+6ZuejXj32048/0+Vq8B2pXPBKcIcxCw9pMPJOREzd6NHDeecyMN1g+AZQ6+4YWfJxmMvk4HlZ06p5RFB9sE2zbZsYDcssYUxNxw/k7i0ZsRC+s2lpbeJLf8/r1zKKCa5W5L7Xt4AiY4Rf4YAdpnjXLs9yRpFRzkMP69UzJDgD40Y/U2ROCbdvSLuMZVFrqUjN3CYFSug7AKkIIN5P5PABdtJLEYRpF/KugdCsovRHAdWBO41qhlxByMoANlNLQKYIQch6YGfnPhcODKaUOgK8D+AUhZLii7qWuIJ47YBpA4WBCgBn0gQ+Uxx/3+TRZB1hQYcgQ4MQTYzZSPqiqYlaSxRawpWsJNzvUmOlVV5eG3nKAMtCZiYDNc9vyhoDoAlkQbvCRfKAzkb4vf5lFgValolEd4+BjWFVG4YMNAM6UltL3kyD9URZyUwYxqg+2WI4Qf3rDee28bhIW5EzsT7W1wAUXmNEumv4bCtiOw4TrefMUZUVaRJPIM88Mp8eElph1HSfvWeGhnAXsCLTl56q4zKvNtZOa0zQY3HkLuuPT5AKdVVayAK3c1JwjIaa/bAOdAQXzo4Mc893faVjf5BmValzx6yYsYOcDna3sqS70xBPMAb9vX32gwTCofNJVcT8mTy4sI5TL08774ssFYaoK6gBgaSRtx4OsfCswA08A3wHwO0LIHACTABTVwdx+tFH6d1D6EihV7ZdzHAXgVELIcrDUXscRlkPbB0LIF8DybJ9KKc2v/pTS1e73UgBvgZmQS8ihD1NKHUqpU5lWmpGU4YsiHnVRDDKG4ncu5xug1gEWDiHwiK+m2SSSQsH89+KLbGe4e3dtvVLRWw5wHCZUCGmLzQKziExG2EI1dSpwzDHA/febEXXJJcCSJcCoUXB6rMCCBXmX2sLr22qww8po6mYnU6xZA/O0IGlAJmAnYbGjuxaHaLUQ1r5k09JBDp9uqfTcB8OCnFHq0XrnnWw3LIy5veACLwoypwWKWxbyp+fTJanmc5WA/cIL5kEV4zDmBgI2ENjwDdaplWio0kLYRn0EYS+bZa7w23eFMOkc8+d7v8VAh7prb9oE3HWX9z99+Rpk/z77nL5REOh/4vCyQV0dS/NYCt5HSa8kijjA5pyWFoOQInx863LH8zIlyBwDwHt/caOIUwqMHZv/OwFzUIn9aFyliZkg1rVZ+4MI4y1M1rLdu/Na7YmYjYoKYd4zWfsBZh2WhIAdlnbsIACldJYrH06glJ5GKQ3mq0gVqW1nUUqvpZQOoJQOAXAOgDcopeeJZQghkwH8Bky43iAcryOE1Li/e4AJ60VV7bdK6MxIBIawE5owpsPK8lpkygSOw2KzfPxxiQmpqzOyDuD0LlbENzqYkc2y9doX8NqEgTA1wwWYOdlbb+V3o0PXUEJYwJmFC+E88e9yBkkmYMvoUV1MI2DLTMQBwMmytoytVq691rCgBKqcUcE0Y2losFXahOOOK3ye06ezb/F4cKNSELABgTGX5cEWtTMyyyIT2oV2Ve8SgM/kcuhQNl0o53NRUx20I49ommyyH2R6De4x4KNffFZ//GPiUe219IcN8ogabEqBmSvqzCoMGeL9PuUU77fuWXbrxgIJcsgiByeNvXvhIId5aMBu2i68fFQkqHnNp00rN/DI56ez2MFZMCKN+bSf/ER9LiC8Fx283yahwRYixLfHHjRgHv61snd4my0t8RhQd84tmJdVa44Ifj+f+1zeVL099mDcOOH9mliv8XJparDLnUlvRSj6aCOE3EwIOdX9+3MAnQC8EEjHNRZAjhAyG8CbAH5KKT14Beyrp3u/o2qwVUwiR8DszaldxFI8RbuaHS67rBhXSQSh2qAyQylM3opgeWgE6btK0s9VAdMqyncjo5E/1K5d1Q0aMv4yE/FJE6k00LUSwei+NjjmGPlxmYl70hpsm/ZMXqTb3njMRWVFi1zAlrUjU7Gp+ibXrmcy4fM4R58+7LuuDoSEBPGdPt27RkICthVC6nbpwoJjK8fxV77iFzjTwgsvsO8rr9SXiyCk5OeCpd3kBXQbbRKrBiXE89kp5gRGRffuXkqpA+PSu06CTL/jsMDdG0OC3ycJ7bTEo19PncrGpztW+2JduO8+4D0bXdR3QwE7tbWd03jCCWbldYQ89pjP79tBDo2f9A6nParZA0eYibiOAH7uA39Ef+NUq7zAZz8LfO1rkQVsvjlA+vRRWy+1CdiJoSgCNqX0Leqm6KKUXk8pfcn9/QVKaW9K6ST3c6p7/B1K6XhK6UT3+7Fi0FkyiBOjra2vjlmV+H1wOLULsX49sAYas6Kk8NOf6rUxQDzfmAQxdizLstBaBOz6eqZkbS30JomBA4GePSPcO0//A6S6mPTty6z2lAK2zES8Qwe1TWAME/GOnQjq64vUT8R0WOKUFNRgUwrce6+XNsoExVj8JdxOO+zF+OZZaLzzb0wLI/PTVc3FYe9NFXRHd68XXcRia1x1FQDGqM2dG3CXENv52c/YYLnoIvNrRCkXEQXxFErB5J15JntXYeboEVzRevdm81XjEoUGW7cZc/PN6nKqdqZOBc0UwWXuq1/1Yrpc8lBI4RhIUPOqDXS2ejWTvouJ664DHn4YOOusAq2iNM5IFFhqsGWbtInAlM/TSZwdOgBHH53/m0UjNu9qH57VS2cifttt4TQFxn2+uo0GOwDHYctlaOYyXv/SS9UBAnUIlr/qqtLGuThE0PaEWzt0jJzCRBxgAjYQIfpnFHTtCrzxpr7MG2+wvI4lRmUlS6PbWjTClZXMerksTd5SBiEhDMi55/r/f+c7TEMgbmgVW3AA9CbiQLiZewQBG4QgmzXcLU8UkijiIp2nnmqnSjI1EU8CgbYc5JBrmQy6ZWv4RqhojhhmIq7ySdf5YGcywLe+lWf6HIfJ/cpUyoMGsdzrI0fKrx2GFDXYAKN/1SpgA9xgReXM/EWM9eI4QG6poYm4+MzESOWm/d8V1FLfpyAEA/AJemIDcusHhpePioR8sAGFSwJHv35srBQTNTUsdofk3TqO67u/XVPfZEIPbm4WG7YvK+yehPYK3HdU0JmI6/zXOeL4YCvWC58Vnkjbf/wH89cO1pfx9iaQbeCp+Iw2DXZiKONV7NABpUg3yBlQIGBPrF2KTKZIArYJamr05rFFhOMAM2aEB5NNEnHmtNZGb5JwHObyu2uX5GRQM0pIod+R5Y3YDk/OIO3YIRyU+SAnIfVqfLA5Lb60ICmjgJYk/ADT6HjBZ6/QODvIYQu6YdmKjJxhUmmgIwrYoVY/Im1RXVtM30URBGwAXjTqg1DAzmaBxWtrsRUS00xTdwJTDXYRIwQTSDImJI0E+0OXLsCoUcXflI4yhPK++zNjNlguPtimCNvAFNobj7mowr7w96nTYJs8F9so4sFrSzBhAhuqjY0o5AdMrVOjIJM5JIKclRplvIq1wRoWO2gdKvexAAtTLgP+9a+UCWtdcBwW+XnRolJTYgZO78KFpaak+Mhm2cbC7NmSkyaMcIo+2ICCQRJNpHWNGQp+wXal5n2EJBtf4LjjjIr5aOH+vyY+a6WERsAGgNzsqvDdLPHd2gjYYb7dCgwaxBIOWAsNETXYVkHODDB5Mmsrv+FbzkxeDA02AMyAgW90FCsV8XwgZ2/acJDDhx9KMiYkhYT7Q2Km14aIOtVpY6zYNGoaaLG1QOgPNdiHCZhjr8GOKGArg5yZ+GAHUFMDNDQo3q9MwE5Sg90mYKeOg2S0HUSIw3Ryv5TPf559azTYgBtNc1Uv0GyZaLHLBGWdK1OC1kZvktAKjUETqGBuVSD1xUT6brZtY9+i45VJcCsbH+wbbyw4N3Ei/GlBdNA9lx/9yB/Z2BTvv8++4zB5aQjlhn2gAfNQjb3Iza4M17DYBDlTMU0WXTPUXUKF//5v9i1Gn1ZdICoM3ndtLYurlxewUxYEYm0QxNBgA8I9PvqodzJpDXbY+0wYPKWUdKMzCSTcH7JZ4JNPgHXrEm02cfTq5fru6+Zsk05cDA32hRcC06Yl05blPJ9FY7j7k25D2+S5hFmF8Ivv3VuY01pDmDLQmUhrwibipIIUfRPuUESbgF1uiBNFfNo0Zit7/PHsmGyACnAc5v64alW0S0ZBnqR33gH+8IfiXdgCY8Ywt7diCaxxZYZi01tO6NePBVSW3ntw0QwGeAJSF7A5g+Sj77nn2PennyarzeUm4pmMlBlo316zW255nVj0ihr8coSCrmrsxwTMQeO7++Q2myqTPhsNtuhvSzIFzerA88KLrnuhcFPGpJof1/AGHKd4AnYsRDS/7tEDGNKryTOD55HgZYgqCHArkSIL2NYppWwhue+4blVA64hdErpxZjKPFkPAfuIJ4Iwz5OdS9MEG2AbPtm3AkiUhbSZoIp6vHjQRX7iwcAM6RMDesgVYtn+A+tqqHcH+/UOIduHen6d9J20a7CKgjFexQxROTG2yKkJyUMB2gx4BxRHMCuaXz3xGPRmXGBUVLBBKMQXWOHNasektJ7mIa+6kjFJQaJA95JR9sAEJgyQu1DIBu7eb0/Oss+QXD9FgE1DmZCg5l0igs2A6KVukaSIeZSBZ5Bt3kENjI9By3jf1bcoC6oRZHhAC3HSTR5aNChusnyndJVoBHAdYg/5Yiz7lzeRF1GADgDN8q3wTIaKpfgF27mTfnTrFzkpkg35Yo97oTAIKF4WoyLsktII13nGAxYuBrVtjNFjqIGe2iCBgAyEbJrogZ0n4YEcIcgYImz176r2DYT7YALM+evdd9TVlNIpQabDLee5tZWglo+0Qgmg2ZoOwQRE0EScEEyawOeNQ1HyGwXFYtqQDB0pNiRlaG71JIpsFFizweMs8TLRymzZZX892/eEMErcMDxWwe/Rgha+7zt+QoQ82AJZyKJBzk9NilBZEBxsNtqxYFCaP5z0Nu24SebCvuIJpdi+4oOCUgxy2oSuWYDg7cOut8vbESMQ2GuxOncLpUyDWhmlEicWIRAsNNuAGOoshxKaOOAL2iK1YiuHYjLpojGxYHb4AFDHIGcC8GRwnxXAuCQuGtbXM8qtsN6VPOgno2BGAN65nzIjRKBfwQtbE2HueJu5LX/xieDuWAvY4zEdNVbP/fcpimKj6URwBm/MQEYKcAcyqrLoayO2q95/QmYgDwOmnM/M4E8g2e9s02KmjTcAuA1AKkJpq4Pnn/RrouAgxEU/MZPQghOMwa/uPPio1JWZwHGYaumBBca5XTnOw47DuXZA+Ok2zVwvkgxtxBilMwAaYiactUxl8KVOnAocf7juXiGlkUhpsG3Trxr6LYT4xaBAwf740dUs+0BnXQsr8+gFg7Nii+mADwIABzCXB6t1GHMhWr8HwGpMmARk0s2fLc4OXI2II2NnhTA3ZiGx0DbaubNLR5ywgzZiQFFLQvCotn8oBL7+c3zEO3Tgzedd9+7LvI44wunxqebABtrMRBksBuxr7MXHwNv8z+vGP/XVyOX891W8VCsyswRiPN95gv3/7W3Vdzf1UV7NlxCdgBzXYMgE7DgjafLCLgDYBu1yQqQDOPjvZNkOCnAHeIlNOZr/lgJKaz0fAoRzoTHnvJotRETQ9BfSJ17RZMA1MxCmInzl6/XUWXMytw9OCxOonVgK2PKI5OyWcGzIk/JpAePTusOd5zDGFxygFXnoJuPRSfV0A9fgQ7bDbE7B1mzjB+zQRsAX6OSNnI3sVOzqyEQwF0o4dgbFYwJ5tysxfrDk3joA9gpmx5OBE12CXsYBNqWSjMwmkcD/ZLLB2LbBmTeJNJ4oePdj0qNwMEDvz4sUsb2UQ9fXA3LnAzTenQWI4QpQ9sdpzkR2yibnv6Jr/9FPv9w03aNsLuybZ/Kn5blLIhOM4QOPuerRAIfTHHdeyemEm722IjTYB+2CBbADrBGzBJ3PzZmD58vRIa40YNYpZa5Yds6pAa6M3SfTty2J9FDAgJloPS047CmPevTtjkPLvRrawmTQctsjyAFliW127Aocdlv+rTQtiCkMTcaUPsUzAXrgQeOEFdWNckN2/35BIBd56q5AOgAWl+c1vQqtX4QAmYZZZvmZTAZv3hwLhyZ7R4XnhU0uXFAUW2mgHOeTggFYUx0Q8Ei8ZQ8Cu67Qfw/FxdA12JqPvcyUUsIu9KR33FhNNW2iAuEHZjDaQR4xg1jMyNDSkb9VlYiJus9ZZXMcZtAE7dgAff6ypJ/rQnXMOcNpp3v9zz9XHBQpe89JLJY7xCoRsKjgOsK251nM9qqy0f2Y6BDcHMhl1X2gTsBNDm4B9qCAoYLu+G8VeZFoLMhnGMBTLhCzunFZsessNPHiXDykI2EC0d+VjkKJqsMMwYAAweDDQrbsRLdpb19GVyRhrIaSmhrL3Ul2tF8Q4M1AGQQayaEQjskzbYNPHwgTsTMbebDFIW1bhLqGC6+eJa66xvpYxLNyeHOSwHn2wenV65MRGHHNlQvKbCGlrsIsZ5AxgQdH79289vMSkSexVtoY1M5sFli5lypA8WqvZYQom4gDgDGMPx6r/iRtSzz5rn9kmH1jF8DoK+OJPAIVzTFwTcbeeb9O7TYOdOtoE7IMFskEhHhMZ089+Frj/fgDA+PEJmIxaoDWNXR44LK7SrFgoFr3luK5z/7/t24WDKQnYUeA4AoMkGwRJaLAJAT3uC6ECTT4tyLLwS6quk0qaLt3kkIaAHfEeHOSwE7VYhFFmJuKq/xy8jTDhyYQ2Wx/76mr2HH74Q7PyrobHSlFqKWADrUPoiQoHOazAEGzcLpjBiw+S745cfDFwxx3+yuVqIu5u1JSli4ICHTsyy+nW4AbWmtKKSSH2x3//9/DyEczI6wc3oV27GAK2IU0+IXXvXrvrKFBfD9SQveo0hXHHdbC9uro2DXYR0CZgH8xQCdjnnptfEGtqmF9m2hN3OQplYchmgT175C5N5Yhsls338+eXmpLig/v/+dITl5mADbiBzkTmQRXkTAbDRTZsfYzNrNn4YMuKqe7ZRMC23T1auNCuvAF8gc6S1GAH7j8KT9WvH3OZSEVo2L6dBeK0xa5dxkUnYjYqcKDVCGnWcDXYANC4qNZ3PA8eOO+RRwotC8pRwN6wAdzkwHGARYvMFXulhpE1TxlAan5fjoJQBF9mKSLE2qjMtGDSJIrcfy1RR3sN1osgYPtguuGr6mDu8aoqYFL7RWoBO67fevD+KirKJgjswYw2AbsMkJopl0rADqC1LDLFRrHM55N67sU09y+3tZ0zID6h0YTIIvhgAyxPOeC+mxqF5qpIyKcFidpPCIkXHM7ETy8IznDYmucG84GbXk+DMfgIHdDEmCEbDba1D3Y0pKZFrK2N5n985JHGRdsv/wjjRuw9eAVsAJPBdgFzizrLC+j6QJj1SCkE7J49gS5dAHhrkG+jMwUkxTM5Dtsf+OST+G2FIQ69dXXA8OGHkCIkTMCWgVI4I7djxureaD7pVGUZ6f8IQj8BNd/wVQnIDzyQp8HpuMBzPQquK0mN6+EjvN9tGuzU0SZgtwHZLNtxXrKk1JSUF4YPZ3xDaxFYi0lvuaFXL5ZdKZeD5+NVRj7YnEHK5QA891w0OhJaZPNpQaL2k0wG+I//AK6+2qCw5L5UzJOJBjvM3LgIzEElmv9/e28eXslR3f1/S9JIoxnNJs2+z3hWaaRZumzjDPAaHMAYYwgQMCTEGAcTAjFLgMAvbzD4lzyBhJfNj4HXgA2/sBjHGDAGTABb4AUv8uz7jGfxjGffd81Wvz+qW2rd23tXd1f1PZ/n0SPp3l5OL1V1TtVZsBjLqxNV+RE1i/ipU8oM7A0bMiqXlAQnMDwK06aBv3Jo5hO+heUCYwwjcBxzsHHgCnbUiaOw7cLetYwxrZqFSfJWTZwFNZARI4CZMxOfS3mZrrgNLcmKrRDgHWdwCi3YdCHitacwsAFEN7D9ntU//APwhS8AkAa2b+iRohhsdHb2f0Yx2JlDBnaZibhSRInOvDEtcZhp8qqmL9HZm94kP2hsDN8pxyn7PgVp2rT+D+MMZhGUgagrO6nK8zEmDd0vfSnBzvCPwQ7CUTicTOlh3Hsv8JrXxJMrBhw9WIYluCgChtDK6/Qzeu6/X/7+v/9XiXJjWR7hEkXDWLA3gQvOZTWdF1/MWKYC4ehBz8aW/g+iGsRhK9iq6+XGZMwY10SnASxcKLsWE1aGLQvYsQM4cCDCxocPy5JdSbnvx8n2S+Kd5EXSFeyOMwCAnvMLI+8DoDgDG5DJ1QBYZ58EAO+JW0VlusQl0f8vrWBnDhnYZSZiQ+nokF6rpgyKeWJZwMqVwLlzRUsSDc6lvFFzb5QJzqVOcfSD/wx8/OPA+98fvlPOBvaOHQNLcUaS45vf7BuEVcqS2GslzerY2LF97qSJYrBvukm6A/ix0Fas3vMe4H/+J5pMQffe8e2vwMLzOI2hWL+zxfN7ANWx5n73zR2j7LoHSXUqz3AJxSSS7fHHI21mfEKnIOwbxtGDXfubsHev/XnUeEjGgieZXO9a3lnEHUxKdNbcrKBsYU5UtYuwkJo0/fTSpcn39aJS1u98J3j7hAb2vGlnZPhO7wLfbTz/97uXrhKXjkwDkpypMLDtSbH5ex9FM0575/ZIcj/ceF0fxWBnDhnYZSbi6NrYKPXSUio0KeFcGtdr1mR3DpU2nmXJPt8UeVXSl0hs8zDgP/9zYKzz7NneO+UUgw34GA5Rkpy9//0yMaFCv9ZUXisRzy/Aqmd6brih/zP38wk7rqMMzJxZUaumgp/8JJJsoedz8Ckd1peoamOAge2Qsz/y+PGyYpt2RsPYsZE26+yU3ovaya+QqmzpcVzEf/Ur+fe4cdXfF7yCDci+5YUXZKWCLFF1iXnloEkrrzPXVwo97b3vDf4+oYFdb4fv9Jzt9N3G83+/h/M//9MfCuVVXixtDLZLBif0qAe82r3fuR9JX6I3vlF6EN1yS/9nfga2rgqegZCBrQE6vM+Oy2jaZIVhmOZ9Ypr7vGnyqiRw5c4vFXxOMdhARaKzJAeL6CIehfb2EK+VKAnHIlAVy1dXB5w8Kf92ajBHOWfU2XZndVwVPgb2HGxCC04EG9hRk5xl0Clqu4oYoQbu4MHSyNZS/rTYz3oxloMx0X+NUdtUczMwffqAYw2gsODyfgZUTMgIlToT58ChQ9K7SGdGjJA2Ut87o4PiWImq9y5JOUYhgEuXwNGDFWfn4QI8xoxKBdep6zlsWPW2gLzpX/qSXGWZMWPAV7GSnAU9K5du0hd69Nc3ecud9P62tcmKGpdd1v+ZXwy2ju+VoZCBrQmZZxEPwbJkUpw0YTtBmNpmZ8yQHqlZzxqrev6myauStjapez73nMeXGgg8fHiFggT0D+xTpig7T5RLHTQIWLQooRGTxvXQbWC3VBinKgzsKDQ0AJMm9f8f1Dl94xueidXqcQlLsAw964d67FRBysRTSV5dy9K0XFIMN/EyV7ZowSnMm362v5+O+n4PHhxsRGtgYJuUOAzIR15V73FfnhHTyCkGGxcvgqMHp0UzNsBjMq/SwD4jY7Yxfnzwsf2qZqgwsF04oUcbNlbcL0epUdmuaQU7c8jANh2fGqq+n/lQyyufQTCm8WqQB6bJqxrHE6MKP+Mm58Gk6tksXChrC999d/jOipVnzuUqU2yvlTTnr6uTQY8AMH9+9OOqNLBPnwa2bwc+/WkZq/3BD/pvO2cO8LOfeX5l4Xks39jsv9hSeT0x75uKcAStEp0BwMiRkTbjXLoYb9uWjRhFZhF34PNPx1/BHjy4/x7+7d9Wf6+Bgd3aKj1cTRmDurqk/WSC6zXnsqTY3r3I5BlrY1slzCLurGAD6K8pXbmNm/vuA26/HZg1q3rbKERNzhPxxlaFjjh0d0eXKQKMwbvPmT27euKbSAwZ2Kbz1a/KkjlO5mQ3MTI6trfLsduUQTFPLAtYvRo4ezab46se1LKWV2c4B7Zu9QjT9WsLOcZgA/0K0j644lHf8Q5/FzWvkys0sCN5rUR1dY5CXZ2MaVu5Erjqquj7qTSwBw2SE5MjR8ps41HuvQccPTjbW+cbfdB3XCcpld81+CRSS0PWq3KJX8WIO2if6Ky7G/ja1+Lv5zaw209jzx5g927EM7CHDpV5DD73uervXQ+mqCRngFkrrU1N5oQkaN8uiswifukScOmSDN+pO+VtYFca7nPmAJ/9bCz5lCc5c30/FxsxFCf738XKGdKUDTpUf7nrLi28/coCGdimM3YscOed/i4sEWloABYv1rjjLhDOZT+6enXRkkSDcxnCtGpV0ZLkT+z4P2fEcWcLDSHN+NOnIMFKfpAA4ijVkY0wxoDf/W7g/0lxstt2dXmfJ2g/zehbKfG7fx//OPD5zwMf+ID8nzFgy5bq7e66S/5WGD8+ZoysBqed0RDx3VmwQCbf9Az30IH/9b9kDdu4uOIe+0oK9SD6BJIzzjc2ausiDsh+bvt2GducBaonD/IISVAh7+LFzgAmMwAAIABJREFU8jilDwFL4SJeB4ElTWu9x1iFDzhWDHbYirz9fV/okdNvV07+Zv1gNBxnTYbuZpmJ2Rgdl9G0FQHKRh7u86qVBaA2J0s8E4kF4Qy4V1+dhThVOAqS5+x6GIqV5/nzZXhxpHt1zTX9g2/aFWw/nOtauLAqoUyhJUV8lLJZ2ILhLRf921lTE/BP/zRw8tPr+p1kbz4db9LHreUqYozKFl1dJezDXAb2onlnUVdnP6Ow+3LddfJ32HaOIl+woqxsDFqxQrrxZgznwNGj0vspC1TZdcOGyTyBPT3o94wJKluoC3nFYNvvPz/zOFZgEc6jIpGX6iy+USfZwl4Al1wcPVi+3M7zlnc7JgNbKXQ3NSAzV66YB7Us4NQpmWyQ6GfqVGD0aHOUPUferN1DdWTUKJkoM7aBndOUfUuLrSBpYGA7XiuRVrCD/o9DFANbt5qdPi98HQSWdPTGa2eV1zZzZr/RVaFUqghHyKNcUixi5gXJo7JFrrgmW4YMb0B7uz2uhN2XBx8E9u8PP74mK9ixJzr9WLhQhtBkjEk5aPomzq6/XoYIfvGLRYvUjyoXccerJw72CjZgh++gGevQPnCbtJ3JhAnJ9ovoIg7I3B5nz9rJxSvHy6zbNdXGVgoZ2GUmwQo2YMYgkyeMaboa5AMlOsvOwFYxucB5QgM7AnHl41yGeQUuGKiOwQ47D2PV5yxy4A9QynjnOaxcGT3XzYDr37pVWlc+BnZasiyXlIcdx7nMgv7CC+qPXdgkodubob4+umtyU5P0+w9DEwN75EiZL8mUMaijQ3pNmDCJzjlk7P4eBtx2GyWlcnCtYFuQDzKrcTY2MVewAftdzNvAphVspdDdrEV8Gum8edLrKItBUZNxPzGcA2vW9Fd1UEkWyp5lAWvXZiMvoPdz5FzWND14MMLGCV7MtNfOObAHE7EbMWfDI74oceTj3MdrJeggUScjwLzrYIfhdfwo+7361ZHkik3AfecLz6G3V7a1SLivbcYMaYk4BrZXXHoKTCuXVElgXXtF5N6PuWvPNjSAc7kwvWuXouNX9GdF9tNZTvKq9vprbJSL5SaEgWm9EFLkC+dawZ6FLRiOY5nkOhmQ5CwqYSvnb3xj35+zsRnDhtnPNyMD2/cwZGArhe5mLXLDDZ4f19dL1y4TZnHzhnPZd69cWbQk0TBNXpUkiv/LUTHoU5Dizq5nMEsVyQjLewUbqF6xjnLNb3lLMpnCCFrBXihrdEV+17yuv75e1of+zW88d0n6uFtbpQ2vpSIegY4OuXBrqvyeeKxgAwqv0VVzvehQHssCdu6M5tmuA6aEJCxahP7YfVPIY3wVou/9r4OAheerx1jVSc7iyBaEK4loHUS/x6Ti+xZ6+WRgK4XuZi0ybpzvV47LqG9t1xol68RhqscfrWe5MyZW/F8BWuiiRUAdLiafXVf4ssydK3NsBd6r2bPDz29FvJaoLuIPPwz84z/6b+uVcTsr5SBA4545Q2DkyBjtzLnGxsaBn7/85dIidqEsHMHQPmDQINlWTJXfE7eB3dCAri65qK3sGp13VQMXI9OSbXIOHD/uneg/LSqHmaFDZYLKLO5rZsOhk8gxS1wGNiBdrVdiIc4hXYWdASRtVzFvrGXJxZHzFykG22TIwNaAomea3ViWdCtev75oSfRi0iQ5L2GKsmeavCoZPlyWt4xlYOcYgz1kCNCOdclXsEM2iTMGh3qtDB8OPPqo/Ns5sJchO2UK0N5e/XklUVew58wJTt7z7LPAr38N3HOP9/4qCbjvrKE+Xn4G5/pzMoCyLpeUNU5lC91XFSNTsYLd3CxLkikzlj7wAdnxv/3tig6YnL6KCYaMQSZNSmddVixx9+S142c/O7CfTsqf/Vnw93/8Y5WBfQ5NWIMF6c+dlpgPinNZ6n7t5oqJWIrBNgq6m5qgwYQzALMGmTzJMtFZFoOkafKqpm/l7nWvC96wgBhsQA7+PeDx7mVGiQwCvVauv77f48XlflpF1JnvqAZ2GHPmANdeC9x8M/C+98XfPw5BD6muDpzLmvO9vRGOFZQpPQOyWkVM9SrGsPYtCzhxAti8OcF5dKQiBhvo76eVdKtz5gB79wKTJ6s4WiqGD5ceMlnpEqqbUHs7MHiwGV5qymP3s+T224MT9E2dGp4/49gx4LHHgre5/35g27a+f51EZ0rjsKdPzyYGu4I+PXxlxeo7GdhGQXeTGMCcOTIppSluXXnCuSydcOpU0ZJEg3PpiWCKvCrhXCof+779C6mh+9HWJn+PHp2PYDYcPdiPcXjppQQ7Kx5kY3utuM/v1Kitr48mV9IyXUUSpBzZBvb58zIJYigJVrDT3A5l5ZJUMnJk5E2zmvAtLOlmxQo2IK/x0CFgB6blLEz2ZBWikMUkb0ODOSEJprnfB7J0KdDZGbzN8OHVYTVeuF6MmdiKkTiiNpP4z38O/Ou/xt8v5gt72WUyCqrKwM4aMrCVQneTGEBdnVklqfKEc6lrr1ih/thZKHqmyauSPgVk1aDgMiZ/93fAt78NfOhD+Qhm45TiiNXOMnARB/rv1XPPRTynexB2Sku5V7Bf8YqB23/hCzJbVeW+fsS9gKxfxqD7Xl8fL1t3jEkEFUbEyJHArFma9ecxntf8+UBzs2byp6EiBhtIkfQwBNWZtpPAObB7tywrZQJOSILiinnKJwQWLpRdrnbtIskLl5FLHEO/p5gyRo8Grvlz+/gKk5xV0FdqdWVD9RcK8D0MxWArhQzssvOe98TexbKkUXb+vDoxTC/TBeRTNkYlppfpSUPk+L/6euCWWyIPLKp0gS6sQj0uxHs2H/kIcPnlwN/8jRohbGbPBoYNq3ivo5bpcvzK3SvYd901cPu6umD38srj6tZJhLiIT58u85OpNrBV4WRH1gbn2mfMCN20oUG25dL0YR4r2J2d8mNtavYqxLQxk3Pg5Elg06aiJQmmuVlm2S9Fu7h0SV1/WOFtxNGD1ejEWdgTvCoG8JwmESwLWLW2Hr1wrdynvE+URTxf6G6WnY99LPYufQkWotZ2rREmTpQ/pgxqpsmrkpYWWdc9i2tXoQs04ywWYE08+aZMkcm9xo5NL4ALx2slVAn2SnLmtYJtj+J9dbDd26uKwc6TEAO7b7UhyrPMOckZIGV78UXNyiU99BDw5JORNrUsmSNA9apiIXjEYDc1SSM7i5q9RWNaSaksc9BkUSkky0RnuaHyAio6CQvP4zwasRohLuhxSPIgE2RplKFHLN8kbWRgK4XupgZk2kEmaDCU6MyfLNzns3z+tezur3uJIo4ebRQkzn28VtzCOcqLW8FwlwXyUzyirmA7xFVgsr6BQcqRK452zRr0r5T4EZSJPWSXpGSxipjaI+mNbwQmTIi0Kecyj8TGjQnPpRMeK9iA3Vc1LYX4wQ8LECo7Wlqkm38WY2YWc1Tz5skqDyasuDux+y++qO6YqbvSG26Iv4/KEgEeK9iA2smrREnOEtxYz9ARSnJmFHQ3NSGzdpPgwE6CBRMGmbzhHNiwIThvlk5wLhVTlfLqYBBGgXMZ+7d7d9GSeMPRk4mClKQvsawKr5Wgg7gHYSc5nHt5VAippTq4V7eDBnBd40hCVrABef8uXABWoSvaMXOKwQY0TXQWgywmfAvrwwIM7KO9Q7D1yncWIFS2mLTS6pQtNGESXcvV9vHjZabcKLzxjfJ32pJyn/pU/98VK9jTsANtOKg2/MK+ObFjsGO+BDL0SORrYFMMtlLIwC47CRokJTrzh3PZTy5frva4WfWbWclrAllkWlWpKDllRHRoZ7GUNffL+spXyto2H/nIwM+feab/76gu4kkN7IKTnAExElUVMImQdbmkrJk7Fxg6VDNDIinu99918qyMJR3mqjgH9u3Td6KzEickwbNsoUZ0ddmx+7q167/8y2jbPfSQ7A/f/vZ0L+o//3P/3w8+OOCrTBKdJY3BTpDozFp8aaDsg9RkFfe9hBKuYDPG6hljyxljD+d97vLdTWIgCTsuywJWroxY27WGMC1pS1aJznRQ3MLIKv5P1bV3YZU2ClJfWZA4ccQAMGqUrPH1mtf0fyYEsGABMHJU//ZxXMR1I6RMFyDD48eM0dPABjRMdBaD+vqSJTrzoKNDViHSdTIwDaaFnHEOnD4tPdVUorrJNzXJbla7+3rHHcCRI/mdz31jPfI6cPRgDRbgDAYX1ygSGNgAwC1gDRb0hx5FKVUWIkYgJo7P4XwYQNQipEop5d0kXCTs1WPVdq0hxo2TyrQp7orjxgGTJ2s4COfAkCFAe7u+1940czI6O9W/S0mavJOoK5KC73cC5/PKFzruCnZciozBtq+nL9FZmIHd3Cx/v+MdkU+vQjHnHHjpJXPKJVXi5AjQfVUxKY2NsvSSrn1VGpySUp5lABOSZQkykyYEnD5bl8kUALJPjFHrPjUhL4KF53ERDdHDd1Rw880D/790KVmiM0vgAgb1y94UkuMjLSUzsBljkwG8AcC3izh/ue4mUU0KAxtQN8joGl6ZBNPc501evUqLtvF/p08D69drpSBx7vJaueEG4PWvB/7936s3jNyIPVats0hylna/MIIejuuclgWsQztOo9l/++Zm4OBB4M47U502Lqo9b/LuzzmXjhLrC1mHyAenL1CZ80kHnJJSpoxBc+bIsoUmjPGcy8XibduKlqRAQjohJ9GZKjfxSP3ydddJtxv3TklWsC+X19Yne8oV7FDKF4P9FQCfBFBIr9oQvok5tLa2oru7u2gxYrNz5yxcvDge3d1PqD94by/wxS8O/CzCPRICGDZsKX7xiwOYOzd9UciVK0cBWIhly5aht/d46uMVSVvbVGzaNBMPP/w4WlrS1445fnwJgPPo7l6dXjgPVMt74EAHTp1qRne3/hrI8OETsX//HDzwwJ8wZkz6eIfDhxeit7cO3d1qgtqHDZuAI0fm4kc/ehoTJ55Nfbx9++bjzJlh6O5+Nva+gwePwfnzHfjud3swd+5J4JOfBLZvlz9Afz9y6ZJ3H3LrrdIK2rsX6O7GgRkzcGr3CHSPGgV8/vNym/Hj/fufkyflOVpa+rdxzhnUZy1dKgN1W1sj9W2xaWmp7kMdXOdramrDRXTi3g99Gx1p5LDPtW3tNgAz8Ic//AH19ems7TNn6sHYy/HAAzvQ0rI91bEAYP36YQAsrFq1CkOGHE59vDAuXmwGcCW+//0NeP3r96Y+3qZNEwHMwZNPPonW1srU+Rnj8063tIzH8ePz8IMfPIMpU86kPs3Bgwtw8mQTuruLt2wnTZqLp55qw2OPPaVkUubcuauwZ88hdHdnU7B65sxFeOwxpqyfv3DhFdi5cze6u19Qcrx+WgBwfO97a/GqVx1IfbSNGycAmIunnnoKbW3n0h0sSt/tsGSJfx/rdwxn+6efDtxXCGDU507h4XkfQMdN81OPERs2yL5v9Xvfi5b2V3lv1NAgx8+XXpL/X7ok3deDrtGNLaMQwIihV+AX7X+P9ndcJjOi7k3e/23ZMhTA5VizZg1GjTpYLc+6dfoXge+ngTHmVkLvFkLc7fzDGLsewH4hxPOMsatzlw4AhBCl+RkyZIgwkQ9/WIgRIzI6+ObNztxZ/09EXvMaIRYvViPGI4/IUz/1lJrjFYlzLY89puZ4V1whxLXXqjmWF468jz6q5nhveYsQCxaoOVbWPP20vPaf/lTN8a65RoilS9UcSwghnn9eyvfjH6s53jvfKcTs2cn23bpVyvLNb/ps4PQfP/+59/eLFsnvly0TQgjxlpG/EwuwSoh77xWivl5+9/Wv+wvwxz/Kbdw3OEqf9b73hQieku98p7oP9ZBr1y750dfwoXTns499xx3yz/Pn0x3Oob1diOuvV3OsZ56Rsv3yl2qOF8bFi0IMGybE3/+9muPddZeUf+9eNceLhc87vWKF/PiHP1RzmhtukE1SB77+dXltO3aoOd7EiUL87d+qOZYXH/uYEIMHC3HunJrjDR0qj6ma3l4hGhuF+MQn1Bzvm9+Uz2n3bgUHi6NvfvSj/n2s3zGc786eDd4XENfhYTkWzZyZ+rKefVYe9mFc53/OBx8U4vOf7///Zz8T4vTpUDm9rvda/Ep0YqX8fOfOVLI7fcyDD9ofVJ53375Ux88TAKdEgD0I4N8B7AKwHcBeAKcBfD9oH9U/5CJedlJMF1sWsHo1cDb9wlqpUJ04TGTsHmyavCrp6pJeT7q6+y1YIL2+VD6bpE1elgVRIEvlCxI1yZmzjfsCPv7x8Ky0Wb+QEY8/cSIwHnvUZqyFOjdsbcMlIlBXJxe5VLsZFxKy9MQTnj697e0yIb8OfYFqsohrzvLaOJd6z7p16o6ZhbyNjXKMq8WxvY8IN9bC8zJ859LgHASC7LDcY92lS9U3d3A0WTh6sBYdMvRIUQx2LWQRF0J8WggxWQgxHcCNAB4VQvx1njKU524S3qTo1Tm3a7uuUihPCRg9Gpg2TV+jrRJHXlNi4FTS3KxpplUbJ7mRDs8mVqIzvwO4cfSJNDHY//mfwP33B2//spfJ3+3t4cdOQkStkzHAGrYZz49/Q56njYxlSe9CFeWSvOZCssZJdHY+Z49u5SxdKmezKhg0SFY+0LWvSkNnp/SaNcUQNC3R2bJlamP3lbTrnh7gd7/L/oRBY0pLCwBppF5CPVacy2iMqISxgXI5a8SV20SAL7yAS6jHSixMXaYrtN2UyMDWAbqbZSelgQ3oofzrhrMapIqsFVXT5FWJypW7LBQ7nZIbca7Aa8VrBdvr77D9onLTTcCWLcArXpFs/zBiPBj+sVdi/f7ROHkyG1HSYJLR4AXnMqXI2rVFS5IdjrF0MX2qDK0YPBjKKyZkiVO2UHVSwCzgHDh2DHhBdXh3WiwLuOaa7M/jp4y0tsofuBKdnV2Q+nSRniVj8iVy75TwJeDDZUx0D3j2Sch0UEIyQAjRLYS4Pu/zZm5gBxX5Zow1McZ+zBjbwhh7hjE23fXdp+3PNzLGXpe1nEWS6WxsCkto6lS5+mnKoJgnnMsBLc9yj2kwTV6VcA4cOiTzg6hA9eSCZalTkNK6hVpWBK8Vvw7rhhvk7wkTBn4etw523AtoaBiozKhmypTIm3IudZQVK1Kc77vfVVvTyCaruvB5oTrURUcsS+b6MyfPUHR0qpgQhhOSYMK7ZvrEWWqCxgv7u4nYgwnYjZ5znepOi4AXua4OePObgW98Q/4vRLXxGnGcmzj4MMZhrzSws1xh/tGPpMJPKCOPFeygIt+3ADgihJgF4MsAvgAAjLF2SJ/5DgDXAvg6Y6x0+ePdZLYimOLAfbVdFXTcRbgUZokzqC1bVqwcUallbwTdFRCd5Esly2c+A+zbJ4OR3bhn3ePGYOvA61/v/fmhQ1UfKTECb7qp/0FA3e0YMsSsckmVqFxV1NXIK3M/zTlw+HB/UQLdccoWnkuZTNshq26tvV2G5uowfhSC341lbMB3HD14vjf9CnYsmRyvKq8Y7IgvBKtj4OiRBnaWY+ONN2Z37BolUwM7QpHvNwH4nv33AwCuYYwx+/P7hBC9QohtALYAuCJLWUtLygZpWdIl7/RpRfKUBJWrKXkoe0uWyN9lVNzC6OyUoUu6KiCqkxulYcoUYMyYEFn8Xti6OmDsWO/Pvf72O65uBjYAXH559We2+6GbCRPk/IKu/YJlmZ3ozJFfFbq9avPmyYkQVe+PTteneszMI6zq3DlgzZpsz5MWJ3a/Fsd2AJFWsAGZ6Gz9+VnZhO/MmuV9Xud3ihhsMGlgb8A8nDxNUb0mkfXTCivyPQnATgAQQlwAcAxAm/tzm132Z0RcUo5CnMt4sJUrFclTEkaNAmbO1MMoikJrqzp5TVPOm5rUxf9lce06KUipE515EddFXEdiPHjl908hnAMHDgA7d4ZvG0RRcyHOqmJv+pL2WtLQACxebM64EgfVFROyRqU3QR5J2XTJ45EbK1YEd2QeK9gCdViesrS557OsTJrgjHMqDGy4krStUjN+6jTxVmYy03bcRb6zOod9nlsZYz2MsZ4LFy5keSozUWBgA/oqjEWiMnFYHh2e6kRnJqEy/i+LZ2VZahQkFSs7nPt4rTgx1lFlgR2nlnWSM83gHNi4ETh+XM3xVL5vOoUjJMGyZBZx3VcV02BZwPLl5Ut01tSktqRU1syYISfSTZCXczWx+4V1wUk6uYULgcmTg4+5dWvfvxakEqtMZ3PHYPvFV7sN7KSDO2P9si9PFylbkiHWGLJcTlgK4AbG2HYA9wF4NWPs+xXbvARgCgAwxhoAjABwyP25zWT7syqEEHcLIbgQgjc0NKi9gjKQUjubNAkYN86MQSZvOJfxZB6hmFqiUl7TZkA5lwnePMrPaoEqBUkFlqXYayVNmS5diLmCLQRSr5RkQVeXXCU1dcK0FiZ8OZeTWxs2FC2JekxKdMaY2pCErOt2A2bIWhTjsQ+T63dn03f4GdjOeJfSRXwC9mIiXkLP8yV8MCUmMwM7YpHvhwDcZP/9NnsbYX9+o51lfAaA2QCezUrWotE1i7izu+q4t7KgStnLS9moBeXUDyf+L4PkzErQaWXRV5a4fUncOtgmaN0RUBVrmsXt0L0ufBgmrSomRae+QDWqSkrlFV/ulC3UPSRh3jzZtmtxbPfF4wWxGtdk064qDexKF/H/+I9UBjYg3cR7lpGBbRK5B8Qxxu5gjDm+ht8B0MYY2wLgYwA+BQBCiLUA7gewDsAjAD4ohCiZw9RAdMwi7sA5sH49cOqUAnlKhJM4zBRFyDR5VeLE/+k6GeIkN1IhX9omP3EiMH58wHsS9yaYnkU8JmPHymRxuiq7Jic6U1XZQudrnzMHaGlR00/r1pRMK7XGuQxJWL26aEmCKU3s/r/8i7pjebz8vGm10vCdPv7t37zP7fxeuRJV2dUSGNibNmUgO5EZuRjY7iLfQojPCCEesv8+K4T4SyHELCHEFUKIra59/k0IcZkQYq4Q4td5yFlKFBnYaWu7lkR3HsCIEcDs2eYoQirlNY3GRhmypeuz0klB8k10lvTC3UZ1UGCpzp1ETItM5/wMKsolFfmonFXFs2fTH0vHV62+Xk1foOMkQkeHWSWldPZGqYRzWTbU6Nj9YcMyPTxvXAUgXXlVz2d5000D/680sL2I2flYeB5CMCWhRzr2e2XE0JSuRGQUtCTTZp3zhHN93Y69KPvqTxCOAqJrplXL0kdBcrxWlJQ0cRvYO3aEb6/j6O+89P/935E25xzYvBk4ejRDmRJieqiIZQEXLgCrVhUtSXZwLie0y5a3VaeKCVGYNg1oa9N3YtZNmWP3E+HlIt4ksyMqeZ4IUIScMc899iVVnOzrsCBnBUgPNwcysMuOgl594kR1tV3LBufArl3A/v3Jj5Gnwcq5rGyRRl5TURX/lxU6KUiWld5rpS8IO+4Kto44so0bF2lzZ1JS+UqJAnSvCx+G6RMEUeBcrtCvW1e0JOpRVVIqj3k4VSEJeVAL7cKXMWOqP/N4QcZ8/CZMm5bDPfJawfZLhBbxWOPqDmDKlHTvou+YcuRI8oMSvpCBXXYUjUKU6Mwb0wY1R/FPK6+Oi4xhqPDEyNIGVJHcSFXyn8B7FfcmRDWwHXR+uSLW8VbVzrLAtHJJlUydCoweba78UShzojPLAk6ckB4eScl7UnrNGuDMmfzOmYQ5c4ChQ/Ud3wJJ2+f/x3+Eb/O2twG33ZaPLutlYFeOfTENbNTVZTfZM3JkBgclyMDWAJ2ziDs4tV1PnFByuNKweLG8xaYoQqbJq5L2dmDw4PTXnpX95yQ30sEomzBBlugbcK9iXrgQrLoOdpDPq84r2A7OtbS2Bm42ejQwfbq+7SxtorMiH5WKVUXdX7VZs4Dhw/V9f9Jg2uQB59I2ShOSkMf7Vl8vE5ma4M4eide/Pt3+PhfBObBlS8aLtpVZxAElLhuO7DqGHhHVkIGtCTpnEQf0ru1aJMOGAXPn6mu0VTJ8uBp5TcSJ/9P12lUlN1KFZ6IzIF0W8aAV7Fe/Grj5ZuBb34p3/DxwZ/VatUoGqIegs2upqnCJohRxywLWrtV/VTEpdXXpjaW8SlnFZf58WVJK17ZRiaocNHmVFStN7H7aGxZgYAPJw3ciDX+VdbABJSvYKkKPiPwgA7vsKHQRB8wZFPNEZ0XaC9PkVYnuic44l5NYSRUklUq147WSuixIVBfxQYOAe+6RmYV0Q7jiyTs7ZS2uECwL2LpVZuxOc8osMC20pRJnVXHlynTH0dEAdeBczuWcO1e0JGpxKiaY8u5NniybuwljJudy0snY2P0sOz0nWZiqMLmgJGcZxGCDMfWTPe9/P3DbbekORvhCBnbZUaRBjBuHVAkWdK7AkxbOgd27gT17ku2ft7tiWnlNxrJkZuxNm5Ltn/Wz0im5kWUp8lpxG9i33pryYAUTMQYb0NuINa1cUiWmuRkngXOgt1eu1JeNtBUT8lydNynRmc65HwLxephxHrDXwOyzf2srMGNGxs/Ty8DeuNF7m6jHqqtLHXpUdZu++U3gq19NdjAiFDKwy47CUYgSnXmjsyLtRdpBWPf4xSBUKOZZKnY6vUtVs+Xt7fL3+PHxDuQ2SnVcnY5DjIevQtnN6l1TWRe+CCZNkpO+psofhTJPInAOnDpVbXPoCudy0vP06WT75zVmzp4tw9ZK8c4wJmdhosSxRDGwXdtkPmHiuKC5ZfjoRwduE7dzt7f3Dd0itIMMbA0wIckZ0F/b9dgxZYcsBYsWSRtCV6OtEhXymsq8ecCQIfpeu4rkRqrepbFjZcbmPlk++1ngsceApUujHaDOYxbfVNwu4hEZNQq47DJ93zXLSl4uqWiPJMbKP+E7c6ZM7lvGazRt8kBN2cLsqasrWbtYvFg2BBW4+m7OgW3bgEOH1By6Cieuwz1euHORxKFiNZzzdKFHRH6QgV123BrQv/wL8JOfJD5U2uQQZWXoUJm4xZRBraUiTjS0AAAgAElEQVQlvbym2ky6x/+lTW6kerJuwGx5QwNw9dXRd66zFYreXrVCFUECAxtIp+zmEY5w4oTMSmsinMtcc6dOxd/XBC8cZxJBRw+ItMydK8dNXfvhSnT3fHLDucxNcP58PufLDNVJzlz/p/EU65tcDIrBdgxstwyVBnYCF3HA4DCAGoQMbE3IJYv4HXcAb3lL4kNRojN/HEMkieJWhLKXRl7TcRKdJYn/y+N+OQqSDsmNHK+VRGVBGmyFIqlfpY7ENLA5B3bsAA4ezEieFJi2ilgJ5+lXFXU1QB2cRGdJ5qh07tvTlpTKO0P6xImydKEJbSVN7L5W70zaGOxKXH33kiXyt1Ijdf/+/gnoLAzsiiRtJryLtQ4Z2GVH4Sike23XIuEc2LtXJg8zAcsyS16VWJa0+TZsSLZ/1oqdTsmN0syWi7oGOctfJgM7Jmlj6rN811TVhS+KWlA0OZcrkatXFy2JeiwrXcWEvEkTt5un4aqiXWgx8RRHiFGjwvd3/T9ypAzHUtJ3PPus/D1mDNDWJv/2MrAbGoLlC8OeIHBCj8ro2VI2yMAuO4pbUqniexRimrJn+upVGnS/9rTuayqbfCp3tDmzATDgqqvUCVQUCTVkZ6VEx3fNCZfQUbYomLSqmBTTxpU4OCWlIpSU1wLLkpOyJ08WLUkwl10GjBhh6DuTdCbiL/6i+rPKgbDC+0hZorPLL+//u7FR/nYMbPf1VHo/JVzBBpLLrpWHQg1ABnbZUWxgOwkWjhyJt1/RSXGyZuFC6QGUtMPO+76kkdf0TnrOHBmHrmsMk07JjdraUpQ0aW2TL1qEmtHak7ADGzFCZvZ97rnkp8wSZxUxbriELv25KeWTkjJ9uiwrpGtflQadKiZEgfN0ZQuprFgAact0Rdm2YhvOgRdfBA4ciH6aUL78ZeA97+kPxXS7Z1x55cBtoyY9q4jBBvpDj5TKTiiHDGwNMCWLOGDeoJgXQ4bI2rKmGKyOvLX4HNPE/+XxrHTLkExlQVwk6E91vn+cp6sLXzScy1JPJ04ULUk2pDWWip4ACcK0klImeROkid3XhqFD0+0fYQUbiN83ByY5GzcOuPdeGXsDAIMG9X9XWd7SWe0Ow2MFmxKdmQEZ2JqQS5IzBZg0yOSNaYnDHMUtibw6K25RSBP/l8e1p1GQVMtHZUGQqlFzDuzaBezbF3/fPOL9AXP786Sriqb00YC8xjVrpDt1HHS/xjQVE/JOcgZI+2jyZDPaimXJ2P01a4qWJAVf+1q6/QNisAEZHsNYxs9z9Oj+vyvdhNzGdxSyTtJGKIcM7LKjeBQaNUq6sJowyOSNZUmXnZ07i5YkGqbJqxLOgbNngXXripbEGye5UVwFKQulmmbLXSRcwQb0vH+614UPI+2ErwkThZYlJwJXrSpaEvVwLrPAm1JSKmnZtLwnO4ydOHPfqNZWtceuWMEePlyGi+V2jypn8/0MbL9s467OasSIdLKb0O+VATKwy04GLUlnl8ciSTOoFdHhGTsIK0D3a9fJU0RJoq5t24Cnn1YiTyGk0JCTrpTkoZSnLZdUNOPGmbOqmBTd+6o06FQxIQpOSMLx4/H3zXOMd2L3dexzciNkBRvIOVY96gp2BAMbMDDOvgYhA7vsZGRgb9+uZ23XIunqkpl5Ten0TJNXJbNmyRnspPFXWZNUQcqCUaPk/Uo1qTZ9enWSFxNJ0J8OGwbMnavHs/TCsuQqYpxwCV2SnAHln/CdMkVWACrjNers3eGFI++yZcXKEUaZY/cjExKDDch79NJLsmRpVBLrAJUGdmXZLgc/A9sjhnzXrpxkJxJBBrYGmJTkDDBvUMyLwYOBzk59jbZKTJNXJWni//JQPpIqSFnFJuokSyGkfOmTKrt5xfunqQtfNJzLJG3HjhUtSTYYmRU6IklLShXVt+jkWRSGE7t/9mzRkkQgj4fpY2ADyXRZzyRnXtx2m/xdOYPpl+RsxoyKE3mvYFPolv6QgV12PDqVtCRxGdVpxSNL0iQOKwInW7Up8qqEc2Dlyv6Slbqhk4JkWTVeFiRlB8Y5sGcPsHu3QpkUYboLchJF07T+zrKkG/Xp0/H203281a1iQhhjxgBTp5rhel3m2P1IRHARX7Qoh0RnTgf7058O/NzPRfx3v/P+vEKXd0KPyMDWFzKwNcGULOJAf21XatjVWJbMtrx9e9GSRIPzZPLqrrhFQff4P871UZDIa8UmhYEN6GkEOnXhTTFyKqmFlRzOgUuXpCt/VEyZRHAqJug60VlJ0pCEvMdM0yfOUhPBRbylBZg/P+N75Jy3soyEl4t4WxswYcLAz3xWsIcNk0kqa/b5GgAZ2GUno169rC5raUk6qBVlsNbyIKy70ZjUHTGLd0lJorMaZtEiqWfpeP/q6uJnR9bJeBszBpg2zQyjJym691Vp4Fwa16aUlOIc2LIFOHKkaEmCcWL3dexzCsGnsWeuy/p1MpWx1oCcRfPb38fFXdfQI4IMbCIhnMvyTklqu5aZBQtkaE0S9/kicOQto+IWxsyZwMiR8Z9VXoNTEgUpq3dp+HCZqKsW3xMAqW/s0KFAe7sekyVeOInO4pZL0kVRK/uE78SJsg5zGa8xySRvkfkdaiXRWSGoHMAirGAD8h7t3Rs9fKcvWihqDLZfmKbXC+x1/T4r2IDeoUcEGdhEQso8o56GpiaZnduU++LIa9QgrAjd4/90U5B0vleZoyCJhM75DnSvCx8G58ALL+i/qpgU3fuqNEyfLisVmHJtaXLQ5I1lyTYdNXZfx74pMRFisIEcvPj8xgwvwzvoAXhsHzc8plTP1wDIwNYAE1/6pLVdawGdFWkvTJNXJU78X29v0ZJ4w3k8BSlrWeKWBSkdKQxszoH9++U9jEKe7dH0UJFaicNevx44eTL6Prp4GASh20RiGG1tMtFz3HetiGfBuawOtXJl/ufWDp+V5IULMw7fiWNgB7mI+yRp0zX0iCADm0iIU9u1zApNUjiXJWNeeCH6PkUqQnHlLZMhzrl0i129umhJvLGseApSlq6TNe218rOfAe97n6wrlJAk9y+vfiFpuSRdiJuvwMQ+jHMp9/Ll0bY36Ro5l32wDhUTomDKhIAxOWGyOGHEFewhQ4COjgyfp5+LeNQV7AADO2noEZEPZGBrggkzzZXEGWRqpUwXEH9QK1oRMn31Kg1xjZ68Y/90ejZxy4KUqg52Rwdw992pyh4uXCjz2ujwLCuJm+hMt/68tVXmVDBhVTEpZZ7gciom6DrRWQnnwLZtwKFDRUsSjHGx+1kqQx/6kO9XmZZXTesiHpDkDDCvNGwtQQY2kRjOZXIFSrAwkI4OGdtsiiKURF6TFNMgpk2TyrmuCohOClIuJU1KTHOzTCqo6/2zLL3rwodhyqpiUsaPl/1BGa8xiQdC0V5fgP5jvGnu90qptDhnzvTdlHPgwIFo4Tuxk5xFMbDvuUf+9nIRDzmOE3r00kvRxAkSiVALGdhEYkwZZPJm0CC5WmXKoDZokIzlMUVeleiugCSRL8vBs6yJlvIizmpD3isSppVLqoRzYPt24ODBoiXJDp37qjRMnQqMHm3OtcVNdFbk6qJlARs2xIvdL5Qf/AC4/vr0x4lx0zP1FAtzEb/vPuAv/kL+7SVzS4v87ZMoJmk5TyJ7yMAmEuMkWCADuxrO5X0JmpB0U/SMouMeGlXeMsG5NCp0jf/jPLqClLUiR2VB0mFZ0q10x45o29dqOEISamHCl3Ng40bg+PFo2xc9rkRF94nOSkaOBGbNMsPri3M5rq9YUcz5I+G+Oe96F/CLX6Q/pluZ+eQnAzft6gIaGjJ6//wevPP5pUv9xraXAjZ3rvx94oTnYeKEHpEbeb6Qga0Bpr70Q4eSy6gfnMv+cPPmoiWJhmnyqsSJ/1u1KnzbIlwTLUsfBcl0I6xodDYCZ8yQ5ZJ0lC0KcVYVTR1znfcnaqIzk+AcWLsWOHOmaEmiYcqEgBErnFk3yC98IfDrwYMzDN8JcxEXQlrIgLeB7WzncxzdQ4+KgjE2hTH2GGNsHWNsLWPsw3nLQAa2Jpgy01wJJVjwJo4ircO9M01elehuNMZVkLLsS8hrJR1dXTIkQ8d3Lc4qom5JzgCZBX32bD3vrSri9AWm9dNxSkoVHYMNSHlffFHGv+rMhAnApEnlfGcG8MEPDvw/5sVkpstWuojPni1jrt2r1m5j24+AF97xmDT6+annAoB/FEK0A3gZgA8yxtrzFIAMbCIVnAP79sVLsFALzJ8vZxZNUfZMk1clkycDY8boe+06KUhDhlBZkDQ0NQGdnXo8Sy8sy6xySZU4imZUijbS4jJ2LDBlSjnbnxErrS7i1F4v2vCJmzvDyDJdV14pfzc1yd8x4904Bw4fDg/fSZ3kbNMm4OabvQ3soDrYAXAuc0+8+GIykcqIEGKPEGKZ/fcJAOsBTMpTBjKwiVREXf3TccUjSxoazEocFlfeMj1HE+L/4hoOWUJeK+mIc//ybme614UPg3Ng50456VtWdO+rkjJpEjBunDnX5oQkRO2Xi856vmlT9Nh9I3nXu4A77wRuv13+n2AFG4j5/kV5qGEu4mEr2AF1sB2cyZ7nngsXpxZhjE0HsBjAM3metyHPk2VNa2sruru7ixYjNrt3z8G5c6PR3f1UNif44hfl7wzuTW9vHerqXoEHH9yBkSO3+263enUbgE709PTg+HFT0lmmY/z4Wfj1ryfg979/vC/ExotTpy7HwYOn0d29Nj/hPIgq76FDnThxYhC6u5flJ1zGjB49Hb/5zTQ88sjjGDzYf+b72LEluHjxArq7IwRsK6S1dRo2bpyOX/7yCQwdetF3O/lsGtHdnZ01Pnz4ROzfPwf//d9/wtix3plNAeDgwQU4ebIpU1lMZNiwCTh6dC5++MOnMWmS/1Lxiy/OxKVLk9Dd/Xhusp0/3wTgKvzoR5tw6pR/JrsVK0YCWIQVK1YAOJqXeKHU148AsBj33rsKL3vZYd/ttmyZDGAWHn/88cD2pCOtrVOxZctMPPzwE2hpueC73ZEjXThzph7d3eYEbM+Y0Yk//rEJ3d3BVs6FCy/Hrl170d29JSfJvJky5Qo88shpvPzlYan3r8b27dvR3b09D7GqaGxshRBduOee5Vi06Jjvdps3TwIwG0888QSGD/d/t5TT0SH11EmT0umpCxZIn/0vfhFobOyvORjhmOfOMTQ0vAIPPrgLo0dv9d1uxQrZx6z4uw+Azbo+/NgXLvTr4G5ZXvUq6c40bBjw5JP+enprq/xu0CDfczmy//SnOzF69DZfUdatGw5gCVatWoXBg/37R0NoYIy5O4q7hRB3V27EGGsB8BMAHxFC5DvFJIQozc+QIUOEidx6qxDjxmV4Ajkvltnhu7qEuPba4G1+/nMpwvPPZyaGdnzve/Ka164N3q69XYi3vjUfmYKIKu911wnBeT4y5YXzfj71VPB2V14pxOtel49Mbn71Kylfd3fwdm94Q/bP5umnpSw//WnwdtdfL8SSJdnKYiLPPy/v349/HLzdJz4hxODB+cjkcOmSEKNHC3HLLcHbPfqovIbHHstFrMgcPy4EY0J87nPB2/2f/yPlP3YsH7lU8pvfSNl///vg7V7zGiH+7M/ykUkVt98uRF2dECdPBm83fLgQH/lILiIF8ld/JcSkSeHbAUJ85jPZy+PHvn1Shi9+MXi7r35VbnfoUD5y9fHpT8sT/+u/pj/WV74ijzV1qhzQv/a1yLtalhDXXBO8TXe3PPyjuFqI+vrwgz7ySL8O7tbD3/te+f+3viU7Xj89/Vvfkp9PmBB4miVLZJsP4k9/kof69a/DxdYdAKdEiE0IYBCA3wD4WNi2WfyQiziRGnIZ9UbnjMFemCavSnSP/4sqXx5tsKsrelkQopoFC+Tiio73j7F48Zq6hYoMGyar2ujQTrJCp75ANTpVTIiCZcn8M3v2FC1JMNrH7qvsSNzHuuoq4B/+IfKuUZKFpY7BdnC7hTvbzJsXff8KSA8fCGOMAfgOgPVCiC8VIQMZ2Jqgm6ISh7gJFmqFuXNlKTNtB7UKospbxg584kRg/Hh9n9XYscDUqXrIR2VB0tHYKGuXRrl/RYwLTl14U8olVaJTvoIsaGsDpk8vZ/vTfaKzkjiT0kXreGVvF31EycjtA+fA0aPAVn8P8YFEeaiVWcQrP3cSm/3ud8Af/pDsHJBt58gRYJu/h3itsRTAuwG8mjG2wv65Lk8ByMAmUlPLK59B1NcDixfrq0hXEkfeshE10Zl7sjlvoiY3ykM+mi1Ph6Psxkx0mwtxyiXpCOfA7t3yJwwd+t0klDXR2cSJ8seUa1u8WL5DJug+nAObN0sD0o/C+vM3v1n+fsMb0h8rKCN3CLEneOImOXMfuFLOa66RM+l++4ecK06SNlP7vTgIIZ4QQjAhRJcQYpH986s8ZSADuxbYtEmmVs2Izk6ZhdqUQTFPOAeWL5d5Lkwgqrxl7KA5BzZsAE5qmoPPsoAtW/RQkDgHDh0ir5WkcC4z+m4JyNFUlLJr+oSp6fJHgXO5UnXY+DxF1Zi00trSIktcmqD7OO1iWYTcpLmP75dfLju8RYvSHyvFCnZHh6zypfR5ulewHQve/XnYREDEh6Fz6FGtQgZ2LTB7tiz2mxGDB4fXdu2LWymhYRYE59LVcsMG/210WgV05F2/vmhJ8kf3+L84ClLWJCppQvShsxE4aZJcSInSn+vIokVSdy3zuxn1/TFxvHUmOk+c8N+mSE+iSpycBTq3CcA89/vEpDCw44TvAEhXpsvRydvaou0fci5H9qA+Qfd3tGyQga0BZXjpyWXUG9MGNZ0V/6zR/VnpJF9np6waooMsJtLeLicmw+5fEUZEnLrwuhg5boYOlffX1AmCKDg1mMvY/ixLPp/lhlQX4xzYu9c/JEGXxYUyx+4PIIWLOBAevjMgyVkaA/sTnwB+/GPgHe+Itn+Ec1mWvqFHtQgZ2IQSOKcEC17MmSPdyEwZ1GbPlpl4TZFXJRMmyNW7MMW8KEWprQ2YMUOPVaumpuheK0Q1DQ1ypVXXdsY5sG4dcOpU0ZIkw1E0y/oOjhoFXHZZOdufThOJUTBpUtok9/vEpFjBBuQ9OnEiOHwnkTyVNDQAb3979AE7wnacA8eOAS+8EEM+IjPIwNaEomc302LSIJMndXXRyt7o8vzr6uTqSBkVtyjoroCEvUt5PpsoJU10ea91hHPp7n/xovf3RbYzzuUqiMmJzvbtkyWUgjD5/SxrorNx42RJKZ37YTcmhSRwLjNklzF2vw+nUSfsQGNN8KRZwY5KjP0pdEsvyMAmlEAJFvzhXMb1nj/v/b1uBmuYvGWGc2DjRpmASkd0UpDIayUdnMuEeps2FS1JNaatIlZSC4om5zLJ4IEDRUuinrDJA51isIcMCQ9J0IWaWAjxWzGOSNTwHQD5GtgRjqNz6FEtkpmBzRgbzBh7ljG2kjG2ljH2OY9tvuyqT7aJMXbU9d1F13cPZSUnoYbGRqCry4xBJm84B3p7pculCTjyrl1btCT5o3v8XxQFKa/B03QjrGh0epaVTJwoQyb8nq0ucaV+LFwoyw6W+d3U+f1Ji2XJiadjx4qWJBpBOWh0mkAvc+x+HyldxBsaYpQrTVMHOyoxGvGgQeGJzoj8yHIFuxfAq4UQCwEsAnAtY+xl7g2EEB916pMBuBPAg66vz7hql92QoZyFo1MHnIYoLqO1iGmGSJkVtzDCnlXR73aYgpSnfOS1ko558+Tq13PPFS2JNya7IDc3y/fTVPmjsHix/F3Ga9SpYkIUOJeeBEHVUHUYM8Ni94se35SQ1qBFf7lSr/AdZUnOohJz/6AkbaV4vgaRmYEtJE5F2UH2T9DjfSeAH2UlT9HcdRfw7ncXLUW2BCVY0H3FI0suuwwYMSJYEdLpvkSRt6yMHQtMnarvsxo1Cpg1S48Z6tglTYgB1NdLI8nvWRatDOleFz6MoAnfou+tCkaMkEk0y2gslXFSWhei5BnRSR+JTcoVbEC+f5HCdzRzEQf0Dj2qNTKNwWaM1TPGVgDYD+C3QohnfLabBmAGgEddHw9mjPUwxp5mjL05SznzYPdu4L77ZI3hslILcW9JCEt0ppsixFi0xGxlxfREZ3niJOqisiDJcFZKLlwoWpJqONc7XCIMywIOHpRxymXFZC+DIEaPliWlgiafdDICu7qka7EJz4JzYMeOcsbuA1BiYCvVZXN0EQdID9eJTA1sIcRF2/17MoArGGMLfDa9EcADQgi3Q8Y0IQQH8C4AX2GMXea1I2PsVtsQ77mgo5Ziw7lUolat8v5ep8EiKe3tsnwPNexqOJfP/ty5oiWJhmnyqsSygM2bgaNHw7ctgjAFKc++xLKoLEgaOAdOn5YrxV4UOS6YtopYSRRF0/Rxl3OZKX3v3qIlUY9OE4lhNDcDHR3e8uo2gW7SansiUmYRB/rDd0LfPw1XsKPIbnq/Zwq5ZBEXQhwF8BiAa302uREV7uFCiJfs31sBdANY7HPsu4UQXAjBGxoalMmsmtJ3apAJFhYt0jemsEgsSxqra9YULUk0OJfyrl5d/Z1uCoNqguL/dLj2oL4kb/mCjBgd7pXu6DwujBsHTJ4c/Gx1VtS6uuSYZIqRlgSd35+0cC4n7nSomBCFoERngD5tpcyx+wCUxGDX14eXK9U1BruhQerhZewTTCPLLOJjGGMj7b+bAbwGQNU8PWNsHoBRAP7k+mwUY6zJ/ns0gKUADMnB7M3kyTK+s7Sdmo3j8kguowNxFCFTJh/KrLiFEbZyV7SipFMm2LCyIEXfK92ZMwdoadF3gsJkF+SmJqCz01z5o7B4sWxjZWx/JiY6O3wY2L69aEmCcWL3Szu2KzCwgf5ypZWOsbH7ZVUu4jFc6pzQLa8kbUR+ZLmCPQHAY4yxVQCeg4zBfpgxdgdjzJ0V/EYA9wkx4LWdD6CHMbYScuX780IIow3soLhWHRQpVXAOnDghXWyJfmbMkAmq/AY13RSh6dOlvGVU3MJoa5PPS1cFZPhwYO5cPd4lx2ulzEZMltTVBa+UFN3OOJfJcnStCx+GX6Kzsoy5LS3SJbSM7c+Z6NS1H67EpElpkyfOQlEQgw3I9y8ofAdAPivYvb3yd0wD20v2svR7ppBlFvFVQojFQoguIcQCIcQd9uefEUI85Nrus0KIT1Xs+5QQolMIsdD+/Z2s5MwTzmVt4dOni5YkOyjBgjeM+Q9qOnZ6QfLWArpfu07xiZToLB1+KyU64Bg5pqwiVsI5cOQIsG1b0ZJkh0njShyCSkrpluQMkN4SXiEJOj4HzoFdu6pj93WUNTYKV7CBkHE2DwM7AaSH60EuMdiEhHOphK5YUf2dboNFUubNkwk//AaZslxnEjiXMdhnzxYtSTQ4lzHYpsirEssCtm6tjv/TRQHRSUGKXNKE8IRz2cbWaeij5RcuoUs7CMP0RG1R4Fz2A7t3Fy2JenSaSAwjLCRBJ90nzDtAJ1ljo2gFOyh8J5E8SUlwHXPmAEOHmuFNUWbIwM4Rk1yIktLQIOPCTBkU88SygPPnvROH6YiT+d4UeVUS1FZ1UD506ktotjwdOhuxY8YA06aZYTR4sWCBrNduqvxRKHP741zGNB88WLQk0Qiqva4TYbH7RqPIwPYrr9q3WJRXkrME1xGWpK0M/Z4JkIGdIxMnAhMmlLRTc0EJFrwJUoR07PD85NVdeVCBTonEvAhSkPJ+lyKXNCE8mTVLxtXr8Cy90L0ufBCNjcDChebKH4VFi6QxoOv7kwadJhKjwLkMld26tWhJghk2TPbbptzXWNTXy98KYpYsC1i5Ui6MeKJxA3MSDusYelQrkIGdMya5PCXFSbCwcWPRkujF1KnA6NHmGKxTpnjLWwuMGiUNH10VkJYWYP78avmKeJccrxVd75Xu+K2U6ALnwJYtMpbZRJwJgrLmCBgyRGbz1/X9SYPfRKeOMdiAWd4EuucZSYxTrldBgw8N32luTn2OUBIO6l6y66prlhUysHOGc2D9ehmz6FC2l74W4t6SYFrisCB5dVRuVON17Tq1VZ2MMsuq9lrR6V7pDudypeTcuaIlqcb0RGeWBRw7JmsqO5Tt3fSqwVyGazStpFRHh4zFdvfLuuaf4RzYs6eEsfuOga3AhTJ0wmTIkPCDqGqIf/M3sTYnPbx4yMDOGc5le/NKdFYW5s6VCRaoYVfjZJI/c6ZoSaJhmrwqsSxgxw7gwIGBn+uiKPkpSEXI51cWRJd7pTuWJY3rtWv7P9PFQPJS1HSRLQomrSomhXPZT+3aVbQk6tFpIjGMxkagq8sMeUtrgCk0sC+7TE7y+N4jjVewZ8+WoQCmTE6VETKwc8avUyuTIuqVYMEkhSxLLEv2+ytXFi1JNDg3S16V6B7/p5PhoJMsJuJ3/3QYF1pbgZkz9U34F0Z7OzB4cLk9ccrc/jgHdu4E9u0rWpJomBKS4BW7Xwo9TWEMtlf4zoAkZ1FWsB1mzEgmREIXCN1Dj2oBMrBzZvx4YNKk8r/0Otd2LRIvRUjXeDKg3IpbGLonOnMUJLfhU5SC5JQ00XUyQndmzgRGjtT3XTMptKWSQYNkWynzu9nVJe0KU59REH4TnTqPmSdOAJs3Fy1JMEOHysknUyfOfFEYgw1II3XVKp/wnVtvjX6goUOTCZAixsAv9Mjo52sQZGAXgMnKSlQ4l27F69cP/LzWG/akScC4ceY8/4kTq+UtxSx3BIYPl+EOOhiwXvglNyqijdXXy0Rnzz2X/7nLgO75GSwL2LYNOHSoaEmSYcqqYlKam2VJMh36AtV4VUzQqR+upHJCQNcYbMA7dt94HANbEZxLA3XNmoovnngSuPlmpefyJKWB3ds7MPSIyA8ysAuAc5lh+/hx+X+pOjeb0sb3pER3RboS0+RVjde166Qo6aQgkddKOixL1pzv7ZX/6/BMHXQPlwjDsmRi0U2bipZFnLIAABQhSURBVJYkO3TqC1RiWkmpoJAE3bAsYP/+ksXuZ2BgAymeZ9oGmcLArtTDy9Y36A4Z2AXgNNjly4uVI0ucBAsmDDJ542SSP3WqaEmiYZq8KrEsqXzs3Vu0JN5wPlBBKnIADS1pQgTCuay3unp1/2e6TOZUhkuYpqhVKsmmyR8FzoHDh2ViRqBc12hSLKlTttAEeUsZAubEYCtixgxZtjP1RHvazjzB/k6SNlMmp8oGGdgFUAuru5RgwR/Lkq6K7kzyuijSXnBulrwq0X3lTicFSSdZTETn+zdypJw0NSUOtpJ582RIha7tWAU6vz9p4VxWSzClpJRX2UIdWbiwhLH7ilewGRuoy+Y+cZXihLXugVg0ZGAXwJgxwNSpA196UxSVODgJFs6fL1oSvTDNbacWJoT8qIz/0+1ZdXVJfcJtOBTVl8yaNdBrRbd7pTvTpgFtbfq2M5MnTP1WFcs07nZ2yoRupj6jILzimnV+dpxLj6+NG/XuB53Y/VJNPCk2sAH5PNeskR5ahZHwhedcJmlzQo9SHIqICRnYBVELs0ruBAs6DzJ5M3Gi/DHl+U+YYJa8KmlpAebP18OA9aK5Gejo0OPZOF4rut4r3XFWGyqTI+kC58CLL8qQBBPh3IxVxaQ0NUkju4wT914lpXTGy/NJ12dRuth9xS7igHf4TmRUxWAnxLJSyE6kggzsguAc2LIFOHq0aEmyo5ZXPsMwbYLFNHlVovu1uxWkopUkv7IgRDQsS66UnDkj/9dJKXcbDUW/Z0mwLOD0aWDDhqIlyQ5ngsbE5xPE0KHVE50644Qk6DxuOFiWrA6wY0dJ3puMVrCBgp5nyjT0uoe5lRkysAvCeemXLStJp+aBk2ChjDPqaXEyyZ84UbQk0XDLW9b31Q/LAvbs0Tf+j/N+BQkoto1RWZB0cC6zsK9aVbQk1TjhEiasynnhVpLL2odxLiftt24t3zWatNJaXy8TA5pgYHsZjya16yoyMLCnTq0O38n9HiU84fTpQGurOW2nTJCBXRC1sLpLCRb8sSzZ2S1frn88GSCfoyNvraG7Yq5TcqNa6NeyRKdnWYlTF15H2aIwZ44M+SjzSo7O709aOAf27QNeesmMMdOy5Hipe9nCrq6Sxe5nYGC7ddnYOsD06fL3xz6W7OQplQ7Sw4uDDOyCaG2V6f/L/tJ7JVggzDNEKuXVXblRSWX8n27X7iQ30sE11MtrhYjO5MnA2LH6TuaYnOjMpFXFpHR0yFjsMl6jaZMHnMtQj/Xr5f+6jRsOTux+aSaeMojBBuTzXLu2P3wnMiNGyM78Pe9JduKULuJAdegRkQ9kYBeIe1ZJ1843LU5yiDVripZEL8aNA6ZMMUdZGDvWLHlVMmSIVFx1VUC8khsVRWWiLiIeTkkY5/7pNi5wLlcQda0LH0blqqJu9zctjY1yRbKMeoVpJaVMmhBwJs50nNSLTQYr2IB8nhcvyhwjuaLAwK4MPSpTv6AzZGAXCOfAtm0yfrKsmLZSmyemue2YJq9KdI//c8tX9OBJXivpcFZKTp8uWpJqTDIavOBcltpZt65oSbLDmeC6dKloSdTiVEwwZfLOCUkwoa24Y/eNJ0MDGyjgeSoysAFz2k5ZIAO7QNyJzsqKO8ECMRDOgc2b5cBWtFEUBUfeY8eKliR/LEuWJ9q5s2hJvNFJQUpV0oQA59I4WrGiaEmq0T1cIoxaUDQ5l8koN28uWhL16DSRGIZTttAE3cf0ibMBZGRgT5rUH74DmJPkDJDeh2PGlOT5GgQZ2AWyZIn8/dJLxcqRJY7L6JEjRUuiH87q/uHDxcoRFWcQ1jHDcdY4167rZIgjnw4TAM57ffCgnvdKd5xnqeMERUuLLEFkqqI2a5ZM1lZG49PBeX/27StWjizgXPYr588XLUk0OO8Pj9O5L1ywQIYX5O7+nAV12Zg1ji6be3iMArc5J/TohRcUyENEhgzsAhk5Ug74ZccZ8AG9B5m8cQwRU3DkrUXX366uzCbGldDRIRUkoPg25nitEMmYOBEYP14aEUU/Sy+cWEQTcVYVy0x7OzB4cNFSZINblzAByzKjrTQ2yhj3c+fk/zr2O5HJUPhC3j8FLuKAeW2nDJCBXTDOS290hxZC2RWapIwe3V/BwQTa2vrlLfP76kVzs5zl1xVHQdIBZ6afSI7O909n2aJQ9vGooUG68pcRp6SUKZjUVsreLlRQ6PMkA9s4yMAumFp46WvhGpNi2gRLLT9L3a9dJ/l0ksVEdL5/OssWhVrwqDJtXIlKU5PeE52VOGULTcD0dp0H7kmI3NqWosyqtdDv6QYZ2AVTC52ak2CBqMa052+avCpxBtcdO4qVww+dng2thqRDp2dZidtTwkRFTed7q4oyX6NJkwfukATd5S3zO6OKiROBCRNyPqkiF3En9KiWYIxdyxjbyBjbwhj7VN7nJwO7YBYv1r/jTQu5jPpjmiFSy89R96z/OimetfyeqEBnpXzIkKIlSMfMmTL/SZkpc/sz7dpMkbfMsfsqKex5phwMnERntQJjrB7AXQBeD6AdwDsZY+15ykAGdsEMHy7rJZYdUwaZvDGtw3My39cinZ1FSxCMTgoSea2kY/x4WRZGV8aNk791rQsfRC0omvPmmT8R4odpuoQp79qgQfrk8dCZ3N8/hZ2saW0nJVcA2CKE2CqEOAfgPgBvylMAMrA14JWvBEaNKlqKbLn2Wrlq4ChmhGTUKOCKK4DJk4uWJBqjRsm4slqkqUk+p5tuKloSbxoagKuu0mN1jjHgta/V20jUHZ2VIUe23EvWKOKKK2R70dFDQAX19cDVV8u6vWVjwQI5DplSqUAnz6IwdO5zYnHnncAf/pDJoa++Wj7LtrZMDl+NIhdxALjySvlbl4n4jJkEwF24dJf9WW4wYeIUtA9TpkwR//Vf/1W0GLE5c6YOvb31GDnSkOKOCRHCjEEmby5eZKirE8bcm4cemgAhGN70pt1Fi0JUcOxYAxgDhg+/ULQouHiRgTGRVVnS0rNq1Qhs3tyCt771paJFqeLAgUZ8/euz8IlPbMSQIQbUIargxIkGbNrUAss6WrQomXH2bB3q6oDGxktFi6Kcw4cHoaXlAhob9ddfhQAeeGAyli49iIkTzxYtTiCbN7fgl7+cgA9/eLMx+kgRHD06KD99/eJFYPt2YNq01LVChQCee64Vl19+2Pjn+6pXveocgNWuj+4WQtzt/MMYexuAa4UQf2v//24AVwohPpSXjKUysIcOHSpOnTpVtBgEQRAEQRAEQRCEYhhjp4UQQwO+vwrAZ4UQr7P//zQACCH+PScRyUWcIAiCIAiCIAiCKAXPAZjNGJvBGGsEcCOAh/IUIJ2/AUEQBEEQBEEQBEFogBDiAmPsQwB+A6AewD1CiLV5ykAu4gRBEARBEARBEIT2hLmI6wC5iBMEQRAEQRAEQRCEAsjAJgiCIAiCIAiCIAgFkIFNEARBEARBEARBEAogA5sgCIIgCIIgCIIgFEAGNkEQBEEQBEEQBEEogAxsgiAIgiAIgiAIglAAGdgEQRAEQRAEQRAEoQAysAmCIAiCIAiCIAhCAWRgEwRBEARBEARBEIQCyMAmCIIgCIIgCIIgCAWQgU0QBEEQBEEQBEEQCiADmyAIgiAIgiAIgiAUQAY2QRAEQRAEQRAEQSiADGyCIAiCIAiCIAiCUAAZ2ARBEARBEARBEAShACaEKFoGZTDGLgE4U7QcATQAuFC0EARRMNQOiFqH2gBBUDsgCGoDyWgWQmi9SFwqA1t3GGM9QghetBwEUSTUDohah9oAQVA7IAhqA+VFa+ufIAiCIAiCIAiCIEyBDGyCIAiCIAiCIAiCUAAZ2Plyd9ECEIQGUDsgah1qAwRB7YAgqA2UFIrBJgiCIAiCIAiCIAgF0Ao2QRAEQRAEQRAEQSiADOycYIxdyxjbyBjbwhj7VNHyEIQqGGP3MMb2M8bWuD5rZYz9ljG22f49yv6cMca+ZreDVYyxJa59brK338wYu6mIayGIJDDGpjDGHmOMrWOMrWWMfdj+nNoBUTMwxgYzxp5ljK2028Hn7M9nMMaesd/3HzPGGu3Pm+z/t9jfT3cd69P25xsZY68r5ooIIhmMsXrG2HLG2MP2/9QGagwysHOAMVYP4C4ArwfQDuCdjLH2YqUiCGV8F8C1FZ99CsDvhRCzAfze/h+QbWC2/XMrgG8A0hABcDuAKwFcAeB2xxghCAO4AOAfhRDtAF4G4IN2H0/tgKglegG8WgixEMAiANcyxl4G4AsAviyEmAXgCIBb7O1vAXDE/vzL9naw286NADogx5av23oUQZjChwGsd/1PbaDGIAM7H64AsEUIsVUIcQ7AfQDeVLBMBKEEIcQfARyu+PhNAL5n//09AG92ff7/CcnTAEYyxiYAeB2A3wohDgshjgD4LaqNdoLQEiHEHiHEMvvvE5CK1SRQOyBqCPt9Pmn/O8j+EQBeDeAB+/PKduC0jwcAXMMYY/bn9wkheoUQ2wBsgdSjCEJ7GGOTAbwBwLft/xmoDdQcZGDnwyQAO13/77I/I4iyMk4Iscf+ey+Acfbffm2B2ghRCmwXv8UAngG1A6LGsF1jVwDYDzlB9AKAo0KIC/Ym7ne67323vz8GoA3UDgiz+QqATwK4ZP/fBmoDNQcZ2ARBZIqQpQqoXAFRehhjLQB+AuAjQojj7u+oHRC1gBDiohBiEYDJkCtu8woWiSBygzF2PYD9Qojni5aFKBYysPPhJQBTXP9Ptj8jiLKyz3Z5hf17v/25X1ugNkIYDWNsEKRx/QMhxIP2x9QOiJpECHEUwGMAroIMgWiwv3K/033vu/39CACHQO2AMJelAG5gjG2HDAd9NYCvgtpAzUEGdj48B2C2nUWwETJxwUMFy0QQWfIQACcD8k0Afu76/G/sLMovA3DMdqH9DYDXMsZG2UmdXmt/RhDaY8fMfQfAeiHEl1xfUTsgagbG2BjG2Ej772YAr4HMR/AYgLfZm1W2A6d9vA3Ao7anx0MAbrQzLM+ATAb4bD5XQRDJEUJ8WggxWQgxHVLXf1QI8VegNlBzNIRvQqRFCHGBMfYhSEWpHsA9Qoi1BYtFEEpgjP0IwNUARjPGdkFmQf48gPsZY7cA2AHg7fbmvwJwHWTCjtMAbgYAIcRhxtj/CzkZBQB3CCEqE6cRhK4sBfBuAKvt+FMA+H9A7YCoLSYA+J6d7bgOwP1CiIcZY+sA3McY+1cAyyEno2D//i/G2BbIRJk3AoAQYi1j7H4A6yAz9H9QCHEx52shCJX8E6gN1BRMTpQQBEEQBEEQBEEQBJEGchEnCIIgCIIgCIIgCAWQgU0QBEEQBEEQBEEQCiADmyAIgiAIgiAIgiAUQAY2QRAEQRAEQRAEQSiADGyCIAiCIAiCIAiCUAAZ2ARBEARRAWNsJGPs7xPu+yunHnDANncwxv48mXTFwRj7LmPsbeFbEgRBEERtQgY2QRAEQVQzEoCngc0YawjaUQhxnRDiaMg2nxFC/C6FfARBEARBaAgZ2ARBEARRzecBXMYYW8EY+0/G2NWMsccZYw8BWAcAjLGfMcaeZ4ytZYzd6uzIGNvOGBvNGJvOGFvPGPuWvc3/MMaa7W36VoLt7T/HGFvGGFvNGJtnfz6GMfZbe99vM8Z2MMZGu4VkjNXbx1pj7/tR+/P3McaeY4ytZIz9hDE2xHXebzDGnmaMbbWv6x5bzu+6jnuSMfZl+9y/Z4yNqbxBjDGLMfYH+x78hjE2wf78NsbYOsbYKsbYfUqfCkEQBEFoDhnYBEEQBFHNpwC8IIRYJIT4hP3ZEgAfFkLMsf9/rxDCAsAB3MYYa/M4zmwAdwkhOgAcBfBWn/MdFEIsAfANAB+3P7sdwKP2vg8AmOqx3yIAk4QQC4QQnQDutT9/UAhxuRBiIYD1AG5x7TMKwFUAPgrgIQBfBtABoJMxtsjeZiiAHvvcf7Bl6YMxNgjAnQDeZt+DewD8m/31pwAsFkJ0Afg7n+slCIIgiFJCBjZBEARBRONZIcQ21/+3McZWAngawBRIY7qSbUKIFfbfzwOY7nPsBz22eTmA+wBACPEIgCMe+20FMJMxdidj7FoAx+3PF9gr7qsB/BWkAe3wCyGEALAawD4hxGohxCUAa13nvgTgx/bf37dlcTMXwAIAv2WMrQDwvwFMtr9bBeAHjLG/BnDB53oJgiAIopSQgU0QBEEQ0Tjl/MEYuxrAnwO4yl4lXg5gsMc+va6/LwLwi9/ujbBNFUKIIwAWAuiGXC3+tv3VdwF8yF7V/lyFbM65LlXIdyng3KLifwZgrb3Cv0gI0SmEeK393RsA3AW54v9cWMw6QRAEQZQJMrAJgiAIopoTAIYFfD8CwBEhxGk7ZvplGcjwJIC3AwBj7LWQrt0DsGOy64QQP4FcRV5ifzUMwB7blfuvEpy7DoCTLfxdAJ6o+H4jgDGMsatsOQYxxjoYY3UApgghHgPwT5D3qSXB+QmCIAjCSGhWmSAIgiAqEEIcYow9yRhbA+DXAH5ZsckjAP6OMbYe0th8OgMxPgfgR4yxdwP4E4C9kIa/m0kA7rUNWwD4tP37XwA8A+CA/TtossCLUwCuYIz9bwD7AbzD/aUQ4pydpO1rjLERkPrEVwBsAvB9+zMG4GthGdUJgiAIokwwGYZFEARBEIROMMaaAFwUQlywV4q/IYRYFLafonOfFELQyjNBEARBxIRWsAmCIAhCT6YCuN9enT4H4H0Fy0MQBEEQRAi0gk0QBEEQBEEQBEEQCqAkZwRBEARBEARBEAShADKwCYIgCIIgCIIgCEIBZGATBEEQBEEQBEEQhALIwCYIgiAIgiAIgiAIBZCBTRAEQRAEQRAEQRAKIAObIAiCIAiCIAiCIBTw/wNHK51eOyW2YQAAAABJRU5ErkJggg==\n"},"metadata":{}}]},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"plot_acc_agg_ttf_data('std')","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"plot_acc_agg_ttf_data('max')","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"plot_acc_agg_ttf_data('min')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plot_acc_agg_ttf_data('sum')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plot_acc_agg_ttf_data('mad')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plot_acc_agg_ttf_data('kurt')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plot_acc_agg_ttf_data('skew')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plot_acc_agg_ttf_data('std_first_50000')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plot_acc_agg_ttf_data('std_last_50000')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plot_acc_agg_ttf_data('std_first_25000')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plot_acc_agg_ttf_data('std_last_25000')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plot_acc_agg_ttf_data('std_first_10000')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plot_acc_agg_ttf_data('std_last_10000')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# <a id='5'>Conclusions</a>  \n\nWe analyzed the distribution of the aggregated features and also the time to failure and the aggregated features on the same graph.  \n"},{"metadata":{},"cell_type":"markdown","source":"# <a id='6'>References</a>  \n\n[1] LANL Earthquake Prediction, https://www.kaggle.com/c/LANL-Earthquake-Prediction  \n[2] Shaking Earth, https://www.kaggle.com/allunia/shaking-earth  \n[3] Earthquake FE - more features and samles, https://www.kaggle.com/artgor/earthquakes-fe-more-features-and-samples  \n[4] Laboratory observations of slow earthquakes and the spectrum of tectonic fault slip modes, https://www.nature.com/articles/ncomms11104   \n[5] Machine Learning Predicts Laboratory Earthquakes, https://agupubs.onlinelibrary.wiley.com/doi/full/10.1002/2017GL074677  \n"}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.4","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}