mirror of
https://github.com/saymrwulf/prophet.git
synced 2026-05-24 22:17:39 +00:00
740 lines
276 KiB
Text
740 lines
276 KiB
Text
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"metadata": {
|
|
"block_hidden": true
|
|
},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"application/vnd.jupyter.widget-view+json": {
|
|
"model_id": "0700e1522a544128889a6f25fa181c2b",
|
|
"version_major": 2,
|
|
"version_minor": 0
|
|
},
|
|
"text/plain": [
|
|
"HBox(children=(FloatProgress(value=0.0, max=3.0), HTML(value='')))"
|
|
]
|
|
},
|
|
"metadata": {},
|
|
"output_type": "display_data"
|
|
},
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"%load_ext rpy2.ipython\n",
|
|
"%matplotlib inline\n",
|
|
"from fbprophet import Prophet\n",
|
|
"import pandas as pd\n",
|
|
"from matplotlib import pyplot as plt\n",
|
|
"import logging\n",
|
|
"logging.getLogger('fbprophet').setLevel(logging.ERROR)\n",
|
|
"import warnings\n",
|
|
"warnings.filterwarnings(\"ignore\")\n",
|
|
"df = pd.read_csv('../examples/example_wp_log_peyton_manning.csv')\n",
|
|
"m = Prophet()\n",
|
|
"m.fit(df)\n",
|
|
"future = m.make_future_dataframe(periods=366)\n",
|
|
"\n",
|
|
"from fbprophet.diagnostics import cross_validation\n",
|
|
"df_cv = cross_validation(\n",
|
|
" m, '365 days', initial='1825 days', period='365 days')\n",
|
|
"cutoff = df_cv['cutoff'].unique()[0]\n",
|
|
"df_cv = df_cv[df_cv['cutoff'].values == cutoff]"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"metadata": {
|
|
"block_hidden": true
|
|
},
|
|
"outputs": [
|
|
{
|
|
"name": "stderr",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"WARNING:rpy2.rinterface_lib.callbacks:R[write to console]: Loading required package: Rcpp\n",
|
|
"\n",
|
|
"WARNING:rpy2.rinterface_lib.callbacks:R[write to console]: Loading required package: rlang\n",
|
|
"\n",
|
|
"WARNING:rpy2.rinterface_lib.callbacks:R[write to console]: Disabling daily seasonality. Run prophet with daily.seasonality=TRUE to override this.\n",
|
|
"\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"%%R\n",
|
|
"library(prophet)\n",
|
|
"df <- read.csv('../examples/example_wp_log_peyton_manning.csv')\n",
|
|
"m <- prophet(df)\n",
|
|
"future <- make_future_dataframe(m, periods=366)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"Prophet includes functionality for time series cross validation to measure forecast error using historical data. This is done by selecting cutoff points in the history, and for each of them fitting the model using data only up to that cutoff point. We can then compare the forecasted values to the actual values. This figure illustrates a simulated historical forecast on the Peyton Manning dataset, where the model was fit to a initial history of 5 years, and a forecast was made on a one year horizon."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"metadata": {
|
|
"input_hidden": true
|
|
},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"image/png": "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\n",
|
|
"text/plain": [
|
|
"<Figure size 720x432 with 1 Axes>"
|
|
]
|
|
},
|
|
"metadata": {},
|
|
"output_type": "display_data"
|
|
}
|
|
],
|
|
"source": [
|
|
"fig = plt.figure(facecolor='w', figsize=(10, 6))\n",
|
|
"ax = fig.add_subplot(111)\n",
|
|
"ax.plot(m.history['ds'].values, m.history['y'], 'k.')\n",
|
|
"ax.plot(df_cv['ds'].values, df_cv['yhat'], ls='-', c='#0072B2')\n",
|
|
"ax.fill_between(df_cv['ds'].values, df_cv['yhat_lower'],\n",
|
|
" df_cv['yhat_upper'], color='#0072B2',\n",
|
|
" alpha=0.2)\n",
|
|
"ax.axvline(x=pd.to_datetime(cutoff), c='gray', lw=4, alpha=0.5)\n",
|
|
"ax.set_ylabel('y')\n",
|
|
"ax.set_xlabel('ds')\n",
|
|
"ax.text(x=pd.to_datetime('2010-01-01'),y=12, s='Initial', color='black',\n",
|
|
" fontsize=16, fontweight='bold', alpha=0.8)\n",
|
|
"ax.text(x=pd.to_datetime('2012-08-01'),y=12, s='Cutoff', color='black',\n",
|
|
" fontsize=16, fontweight='bold', alpha=0.8)\n",
|
|
"ax.axvline(x=pd.to_datetime(cutoff) + pd.Timedelta('365 days'), c='gray', lw=4,\n",
|
|
" alpha=0.5, ls='--')\n",
|
|
"ax.text(x=pd.to_datetime('2013-01-01'),y=6, s='Horizon', color='black',\n",
|
|
" fontsize=16, fontweight='bold', alpha=0.8);"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"[The Prophet paper](https://peerj.com/preprints/3190.pdf) gives further description of simulated historical forecasts.\n",
|
|
"\n",
|
|
"This cross validation procedure can be done automatically for a range of historical cutoffs using the `cross_validation` function. We specify the forecast horizon (`horizon`), and then optionally the size of the initial training period (`initial`) and the spacing between cutoff dates (`period`). By default, the initial training period is set to three times the horizon, and cutoffs are made every half a horizon.\n",
|
|
"\n",
|
|
"The output of `cross_validation` is a dataframe with the true values `y` and the out-of-sample forecast values `yhat`, at each simulated forecast date and for each cutoff date. In particular, a forecast is made for every observed point between `cutoff` and `cutoff + horizon`. This dataframe can then be used to compute error measures of `yhat` vs. `y`.\n",
|
|
"\n",
|
|
"Here we do cross-validation to assess prediction performance on a horizon of 365 days, starting with 730 days of training data in the first cutoff and then making predictions every 180 days. On this 8 year time series, this corresponds to 11 total forecasts."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"metadata": {
|
|
"output_hidden": true
|
|
},
|
|
"outputs": [
|
|
{
|
|
"name": "stderr",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"WARNING:rpy2.rinterface_lib.callbacks:R[write to console]: Making 11 forecasts with cutoffs between 2010-02-15 and 2015-01-20\n",
|
|
"\n"
|
|
]
|
|
},
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
" y ds yhat yhat_lower yhat_upper cutoff\n",
|
|
"1 8.242493 2010-02-16 8.954437 8.451457 9.466432 2010-02-15\n",
|
|
"2 8.008033 2010-02-17 8.720815 8.240268 9.199979 2010-02-15\n",
|
|
"3 8.045268 2010-02-18 8.604422 8.098728 9.113440 2010-02-15\n",
|
|
"4 7.928766 2010-02-19 8.526214 7.995282 8.998441 2010-02-15\n",
|
|
"5 7.745003 2010-02-20 8.268029 7.765918 8.794452 2010-02-15\n",
|
|
"6 7.866339 2010-02-21 8.599200 8.057087 9.092473 2010-02-15\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"%%R\n",
|
|
"df.cv <- cross_validation(m, initial = 730, period = 180, horizon = 365, units = 'days')\n",
|
|
"head(df.cv)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"metadata": {
|
|
"output_hidden": true
|
|
},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"application/vnd.jupyter.widget-view+json": {
|
|
"model_id": "d198a659eea54089876a9d87e61a09ff",
|
|
"version_major": 2,
|
|
"version_minor": 0
|
|
},
|
|
"text/plain": [
|
|
"HBox(children=(FloatProgress(value=0.0, max=11.0), HTML(value='')))"
|
|
]
|
|
},
|
|
"metadata": {},
|
|
"output_type": "display_data"
|
|
},
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"from fbprophet.diagnostics import cross_validation\n",
|
|
"df_cv = cross_validation(m, initial='730 days', period='180 days', horizon = '365 days')"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"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>ds</th>\n",
|
|
" <th>yhat</th>\n",
|
|
" <th>yhat_lower</th>\n",
|
|
" <th>yhat_upper</th>\n",
|
|
" <th>y</th>\n",
|
|
" <th>cutoff</th>\n",
|
|
" </tr>\n",
|
|
" </thead>\n",
|
|
" <tbody>\n",
|
|
" <tr>\n",
|
|
" <th>0</th>\n",
|
|
" <td>2010-02-16</td>\n",
|
|
" <td>8.956828</td>\n",
|
|
" <td>8.460272</td>\n",
|
|
" <td>9.476844</td>\n",
|
|
" <td>8.242493</td>\n",
|
|
" <td>2010-02-15</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>1</th>\n",
|
|
" <td>2010-02-17</td>\n",
|
|
" <td>8.723230</td>\n",
|
|
" <td>8.208639</td>\n",
|
|
" <td>9.222179</td>\n",
|
|
" <td>8.008033</td>\n",
|
|
" <td>2010-02-15</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2</th>\n",
|
|
" <td>2010-02-18</td>\n",
|
|
" <td>8.607021</td>\n",
|
|
" <td>8.106506</td>\n",
|
|
" <td>9.104792</td>\n",
|
|
" <td>8.045268</td>\n",
|
|
" <td>2010-02-15</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>3</th>\n",
|
|
" <td>2010-02-19</td>\n",
|
|
" <td>8.528870</td>\n",
|
|
" <td>8.061701</td>\n",
|
|
" <td>9.024450</td>\n",
|
|
" <td>7.928766</td>\n",
|
|
" <td>2010-02-15</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>4</th>\n",
|
|
" <td>2010-02-20</td>\n",
|
|
" <td>8.270872</td>\n",
|
|
" <td>7.773299</td>\n",
|
|
" <td>8.745526</td>\n",
|
|
" <td>7.745003</td>\n",
|
|
" <td>2010-02-15</td>\n",
|
|
" </tr>\n",
|
|
" </tbody>\n",
|
|
"</table>\n",
|
|
"</div>"
|
|
],
|
|
"text/plain": [
|
|
" ds yhat yhat_lower yhat_upper y cutoff\n",
|
|
"0 2010-02-16 8.956828 8.460272 9.476844 8.242493 2010-02-15\n",
|
|
"1 2010-02-17 8.723230 8.208639 9.222179 8.008033 2010-02-15\n",
|
|
"2 2010-02-18 8.607021 8.106506 9.104792 8.045268 2010-02-15\n",
|
|
"3 2010-02-19 8.528870 8.061701 9.024450 7.928766 2010-02-15\n",
|
|
"4 2010-02-20 8.270872 7.773299 8.745526 7.745003 2010-02-15"
|
|
]
|
|
},
|
|
"execution_count": 4,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"df_cv.head()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"In R, the argument `units` must be a type accepted by `as.difftime`, which is weeks or shorter. In Python, the string for `initial`, `period`, and `horizon` should be in the format used by Pandas Timedelta, which accepts units of days or shorter.\n",
|
|
"\n",
|
|
"Custom cutoffs can also be supplied as a list of dates to to the `cutoffs` keyword in the `cross_validation` function in Python and R. For example, three cutoffs six months apart, would need to be passed to the `cutoffs` argument in a date format like:"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 6,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"%%R\n",
|
|
"cutoffs <- as.Date(c('2013-02-15', '2013-08-15', '2014-02-15'))\n",
|
|
"df.cv2 <- cross_validation(m, cutoffs = cutoffs, horizon = 365, units = 'days')"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 7,
|
|
"metadata": {
|
|
"output_hidden": true
|
|
},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"application/vnd.jupyter.widget-view+json": {
|
|
"model_id": "2262c0413dfc4f63ac84b6e7005f9c1c",
|
|
"version_major": 2,
|
|
"version_minor": 0
|
|
},
|
|
"text/plain": [
|
|
"HBox(children=(FloatProgress(value=0.0, max=3.0), HTML(value='')))"
|
|
]
|
|
},
|
|
"metadata": {},
|
|
"output_type": "display_data"
|
|
},
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"cutoffs = pd.to_datetime(['2013-02-15', '2013-08-15', '2014-02-15'])\n",
|
|
"df_cv2 = cross_validation(m, cutoffs=cutoffs, horizon='365 days')"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"The `performance_metrics` utility can be used to compute some useful statistics of the prediction performance (`yhat`, `yhat_lower`, and `yhat_upper` compared to `y`), as a function of the distance from the cutoff (how far into the future the prediction was). The statistics computed are mean squared error (MSE), root mean squared error (RMSE), mean absolute error (MAE), mean absolute percent error (MAPE), median absolute percent error (MDAPE) and coverage of the `yhat_lower` and `yhat_upper` estimates. These are computed on a rolling window of the predictions in `df_cv` after sorting by horizon (`ds` minus `cutoff`). By default 10% of the predictions will be included in each window, but this can be changed with the `rolling_window` argument."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 8,
|
|
"metadata": {
|
|
"output_hidden": true
|
|
},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
" horizon mse rmse mae mape coverage\n",
|
|
"1 37 days 0.4961337 0.7043676 0.5067661 0.05873288 0.6740521\n",
|
|
"2 38 days 0.5019566 0.7084890 0.5117524 0.05931071 0.6740521\n",
|
|
"3 39 days 0.5241862 0.7240071 0.5178584 0.05991184 0.6726816\n",
|
|
"4 40 days 0.5314370 0.7289973 0.5207051 0.06021607 0.6763362\n",
|
|
"5 41 days 0.5388498 0.7340639 0.5216663 0.06029145 0.6838739\n",
|
|
"6 42 days 0.5425501 0.7365800 0.5220003 0.06030530 0.6879854\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"%%R\n",
|
|
"df.p <- performance_metrics(df.cv)\n",
|
|
"head(df.p)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 9,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"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>horizon</th>\n",
|
|
" <th>mse</th>\n",
|
|
" <th>rmse</th>\n",
|
|
" <th>mae</th>\n",
|
|
" <th>mape</th>\n",
|
|
" <th>mdape</th>\n",
|
|
" <th>coverage</th>\n",
|
|
" </tr>\n",
|
|
" </thead>\n",
|
|
" <tbody>\n",
|
|
" <tr>\n",
|
|
" <th>0</th>\n",
|
|
" <td>37 days</td>\n",
|
|
" <td>0.494800</td>\n",
|
|
" <td>0.703420</td>\n",
|
|
" <td>0.505277</td>\n",
|
|
" <td>0.058540</td>\n",
|
|
" <td>0.050149</td>\n",
|
|
" <td>0.676565</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>1</th>\n",
|
|
" <td>38 days</td>\n",
|
|
" <td>0.500706</td>\n",
|
|
" <td>0.707606</td>\n",
|
|
" <td>0.510301</td>\n",
|
|
" <td>0.059120</td>\n",
|
|
" <td>0.049955</td>\n",
|
|
" <td>0.675423</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2</th>\n",
|
|
" <td>39 days</td>\n",
|
|
" <td>0.522967</td>\n",
|
|
" <td>0.723165</td>\n",
|
|
" <td>0.516433</td>\n",
|
|
" <td>0.059724</td>\n",
|
|
" <td>0.050078</td>\n",
|
|
" <td>0.672682</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>3</th>\n",
|
|
" <td>40 days</td>\n",
|
|
" <td>0.530259</td>\n",
|
|
" <td>0.728189</td>\n",
|
|
" <td>0.519331</td>\n",
|
|
" <td>0.060033</td>\n",
|
|
" <td>0.049706</td>\n",
|
|
" <td>0.678849</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>4</th>\n",
|
|
" <td>41 days</td>\n",
|
|
" <td>0.537736</td>\n",
|
|
" <td>0.733305</td>\n",
|
|
" <td>0.520341</td>\n",
|
|
" <td>0.060114</td>\n",
|
|
" <td>0.049955</td>\n",
|
|
" <td>0.685244</td>\n",
|
|
" </tr>\n",
|
|
" </tbody>\n",
|
|
"</table>\n",
|
|
"</div>"
|
|
],
|
|
"text/plain": [
|
|
" horizon mse rmse mae mape mdape coverage\n",
|
|
"0 37 days 0.494800 0.703420 0.505277 0.058540 0.050149 0.676565\n",
|
|
"1 38 days 0.500706 0.707606 0.510301 0.059120 0.049955 0.675423\n",
|
|
"2 39 days 0.522967 0.723165 0.516433 0.059724 0.050078 0.672682\n",
|
|
"3 40 days 0.530259 0.728189 0.519331 0.060033 0.049706 0.678849\n",
|
|
"4 41 days 0.537736 0.733305 0.520341 0.060114 0.049955 0.685244"
|
|
]
|
|
},
|
|
"execution_count": 9,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"from fbprophet.diagnostics import performance_metrics\n",
|
|
"df_p = performance_metrics(df_cv)\n",
|
|
"df_p.head()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"Cross validation performance metrics can be visualized with `plot_cross_validation_metric`, here shown for MAPE. Dots show the absolute percent error for each prediction in `df_cv`. The blue line shows the MAPE, where the mean is taken over a rolling window of the dots. We see for this forecast that errors around 5% are typical for predictions one month into the future, and that errors increase up to around 11% for predictions that are a year out."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 10,
|
|
"metadata": {
|
|
"output_hidden": true
|
|
},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"image/png": "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\n"
|
|
},
|
|
"metadata": {},
|
|
"output_type": "display_data"
|
|
}
|
|
],
|
|
"source": [
|
|
"%%R -w 10 -h 6 -u in\n",
|
|
"plot_cross_validation_metric(df.cv, metric = 'mape')"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 11,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAmQAAAF3CAYAAAALu1cUAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDMuMC4zLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvnQurowAAIABJREFUeJzsnXtsHNd59p+9kcslubukqQu5lMU4Em1Rji0zUiLnIikNDLUyqtS9pG6CIkjgqhcBCRq0aXozEiMfEiCAgQQK2qppk7Zu4hYNWhswokKxLQlwIyuKZKU2LZGSRUq7FEmtyL1wL9zr9wd7xmdnZ3ZnlzucIfX8AMMiuTtz5sy5POd93/MeR7lcLoMQQgghhFiG0+oCEEIIIYTc7VCQEUIIIYRYDAUZIYQQQojFUJARQgghhFgMBRkhhBBCiMVQkBFCCCGEWAwFGSGEEEKIxVCQEUIIIYRYDAUZIYQQQojFUJARQgghhFiM2+oCNEpfXx+GhoZMu34qlUJnZ6dp11+rsF6qYZ1ow3rRhvVSDetEG9aLNmu1XiYnJxGNRut+bs0JsqGhIZw/f9606586dQoHDhww7fprFdZLNawTbVgv2rBeqmGdaMN60Wat1svu3bsNfY4uS0IIIYQQi6EgI4QQQgixGAoyQgghhBCLoSAjhBBCCLEYCjJCCCGEEIuhICOEEEIIsRgKMkIIIYQQi6EgI4QQQgixGAoyQgghhBCLoSAjhBBCCLEYCjJCbE48HsfU1BTi8bjVRSGEEGISa+4sS0LuJuLxOE6fPo1SqQSn04n9+/cjEAhYXSxCCCEthhYyQmxMLBZDqVRCMBhEqVRCLBazukiEEEJMgIKMEBsTDAbhdDoRi8XgdDoRDAatLhIhhBAToMuSEBsTCASwf/9+xGIxBINBuisJIWSdQkFGiM0JBAIUYoQQss6hy5IQQgghxGIoyAghhBBCLIaCjBBCCCHEYijICCGEEEIshoKMEEIIIcRiKMgIIYQQQiyGgowQQgghxGIoyAghhBBCLIaCjBBCCCHEYijICCGEEEIshoKMEEIIIcRiKMgIIYQQQiyGgowQQgghxGIoyAghhBBCLIaCjBBCCCHEYijICCGEEEIshoKMEEIIIcRiKMgIIYQQQiyGgowQQgghxGJMFWQnTpzA/fffj23btuEb3/iG5mf+/d//HSMjI9i5cyc+9alPmVkcQgghhBBb4jbrwsViEUePHsXJkycxODiIPXv24PDhwxgZGVE+MzExga9//et47bXX0NPTg7m5ObOKQwghhBBiW0yzkJ07dw7btm3Dfffdh7a2Njz55JN44YUXKj7z93//9zh69Ch6enoAABs3bjSrOIQQQgghtsU0C1kkEsGWLVuUnwcHB/H6669XfGZ8fBwA8OEPfxjFYhFf+cpX8Mu//MtV1zp+/DiOHz8OAAiHwzh16pRZxcbi4qKp11+rsF6qYZ1ow3rRhvVSDetEG9aLNuu9XkwTZEYoFAqYmJjAqVOnEA6HsW/fPvzv//4vgsFgxeeOHDmCI0eOAAB2796NAwcOmFamU6dOmXr9tQrrpRrWiTasF21YL9WwTrRhvWiz3uvFNJdlKBTCzZs3lZ/D4TBCoVDFZwYHB3H48GF4PB685z3vwfDwMCYmJswqEiGEEEKILTFNkO3ZswcTExO4fv06crkcnn/+eRw+fLjiM7/2a7+mmB+j0SjGx8dx3333mVUkQgghhBBbYpogc7vdOHbsGA4ePIgdO3bgk5/8JHbu3Imnn34aL774IgDg4MGDuOeeezAyMoKPfexj+OY3v4l77rnHrCIRsqaIx+OYmppCPB63uiiEEEJMxtQYskOHDuHQoUMVv3vmmWeUfzscDjz77LN49tlnzSwGIWuOeDyO06dPo1Qqwel0Yv/+/QgEAlYXixBCiEkwUz8hNiQWi6FUKiEYDKJUKiEWi1ldJEIIISZCQUaIDQkGg3A6nYjFYnA6nVU7jwkhhKwvLE17QQjRJhAIYP/+/YjFYggGg3RXEkLIOoeCjBCbEggEKMQIIeQugS5LQgghhBCLoSAjhBBCCLEYCjJCCCGEEIuhICOEEEIIsRgKMkIIIYQQi6EgI4QQQgixGAoyQgghhBCLoSAjhBBCCLEYCjJCCCGEEIuhICOEEEIIsRgKMkIIIYQQi6EgI4QQQgixGAoyQgghhBCLoSAjhBBCCLEYCjJCCCGEEIuhICOEEEIIsRgKMkIIIYQQi6EgI4QQQgixGAoyQgghhBCLoSAjhBBCCLEYCjJCCCGEEIuhICOEEEIIsRgKMkIIIYQQi6EgI4QQQgixGAoyQgghhBCLoSAjhBBCCLEYCjJCCCGEEIuhICOEEEIIsRgKMkIIIYQQi6EgI4QQQgixGAoyQgghhBCLoSAjhBBCCLEYUwXZiRMncP/992Pbtm34xje+UfX373//+9iwYQN27dqFXbt24bvf/a6ZxSGEEEIIsSVusy5cLBZx9OhRnDx5EoODg9izZw8OHz6MkZGRis/99m//No4dO2ZWMQghhBBCbI9pFrJz585h27ZtuO+++9DW1oYnn3wSL7zwglm3I4QQQghZs5gmyCKRCLZs2aL8PDg4iEgkUvW5H/3oR3jooYfwm7/5m7h586ZZxSGEEEIIsS2muSyN8Ku/+qv4nd/5HbS3t+Pv/u7v8JnPfAavvPJK1eeOHz+O48ePAwDC4TBOnTplWpkWFxdNvf5ahfVSDetEG9aLNqyXalgn2rBetFnv9WKaIAuFQhUWr3A4jFAoVPGZe+65R/n3U089hS996Uua1zpy5AiOHDkCANi9ezcOHDjQ+gL/H6dOnTL1+msV1ks1rBNtWC/asF6qYZ1ow3rRZr3Xi2kuyz179mBiYgLXr19HLpfD888/j8OHD1d85tatW8q/X3zxRezYscOs4hBCCCGE2BbTLGRutxvHjh3DwYMHUSwW8bnPfQ47d+7E008/jd27d+Pw4cP49re/jRdffBFutxu9vb34/ve/b1ZxCCGEEEJsi6kxZIcOHcKhQ4cqfvfMM88o//7617+Or3/962YWgRBCCCHE9jBTPyGEEEKIxVCQEWJD4vE4pqamEI/HrS4KIYSQVcDStBeEkGri8ThOnz6NUqkEp9OJ/fv3IxAIWF0sQgghJkILGSE2IxaLoVQqIRgMolQqIRaLWV0kQgghJkNBRojNCAaDcDqdiMVicDqdCAaDVheJEEKIydBlSYjNCAQC2L9/P2KxGILBIN2VhBByF0BBRogNCQQCFGKEEHIXQZclIYQQQojFUJARQgghhFgMBRkhhBBCiMVQkBFCCCGEWAwFGSGEEEKIxVCQEUIIIYRYDAUZIYQQQojFUJARQgghhFgMBRkhhBBCiMVQkBFCCCGEWAwFGSGEEEKIxVCQEUIIIYRYDAUZIYQQQojFUJARQgghhFgMBRkhhBBCiMVQkBFCCCGEWAwFGSGEEEKIxVCQEUIIIYRYDAUZIYQQQojFUJARQgghhFgMBRkhhBBCiMVQkBFCCCGEWAwFGSGEEEKIxVCQEUIIIYRYDAUZIYQQQojFUJARQgghhFgMBRkhhBBCiMVQkBFCCCGEWAwFGSGEEEKIxZgqyE6cOIH7778f27Ztwze+8Q3dz/3oRz+Cw+HA+fPnzSwOIYQQQogtMU2QFYtFHD16FD/+8Y8xNjaGH/7whxgbG6v6XDKZxLe+9S188IMfNKsohBBCCCG2xjRBdu7cOWzbtg333Xcf2tra8OSTT+KFF16o+txf//Vf48/+7M/g9XrNKgohhBBCiK0xTZBFIhFs2bJF+XlwcBCRSKTiMxcuXMDNmzfx+OOPm1UMQgghhBDb47bqxqVSCV/84hfx/e9/v+5njx8/juPHjwMAwuEwTp06ZVq5FhcXTb3+WoX1Ug3rRBvWizasl2pYJ9qwXrRZ7/VimiALhUK4efOm8nM4HEYoFFJ+TiaTePPNN3HgwAEAwMzMDA4fPowXX3wRu3fvrrjWkSNHcOTIEQDA7t27le+YwalTp0y9/lqF9VIN60Qb1os2rJdqWCfasF60We/1YprLcs+ePZiYmMD169eRy+Xw/PPP4/Dhw8rfA4EAotEoJicnMTk5ib1792qKMUIIIYSQ9Y5pgsztduPYsWM4ePAgduzYgU9+8pPYuXMnnn76abz44otm3ZYQokM8HsfU1BTi8bjVRSGEEKLC1BiyQ4cO4dChQxW/e+aZZzQ/u579woRYTTwex+nTp1EqleB0OrF//34EAgGri0UIIeT/YKZ+Qu4CYrEYSqUSgsEgSqUSYrGY1UUihBAiQUFGyF1AMBiE0+lELBaD0+lEMBi0ukiEEEIkLEt7QQhZPQKBAPbv349YLIZgMEh3JSGE2AwKMkLuEgKBAIUYIYTYFLosCSGEEEIshoKMEEIIIcRiKMgIIYQQQiyGgowQQgghxGIoyAghhBBCLIaCjBBCCCHEYijICCGEEEIshoKMEEIIIcRiKMgIIYQQQiyGgowQQgghxGIoyAghhJB1Tjwex9TUFOLxuNVFIToYEmTlchnPPfccnnnmGQDAjRs3cO7cOVMLRgghhJCVE4/Hcfr0aVy8eBGnT5+mKLMphgTZH/3RH+GnP/0pfvjDHwIAuru7cfToUVMLRgghhJCVE4vFUCqVEAwGUSqVEIvFrC4S0cBt5EOvv/46Lly4gEceeQQA0NPTg1wuZ2rBCCHvEo/HEYvFEAwGEQgErC4OIWQNEQwG4XQ6EYvF4HQ6EQwGrS4S0cCQIPN4PCgWi3A4HACA27dvw+lk+Bkhq4FwN5RKJTidTuzfv5+ijBBimEAggP3793NRZ3MMqarPf/7zeOKJJzA7O4u//Mu/xEc+8hH8xV/8hdllI4SA7gZCyMoJBALYunUrxZiNMWQh+/SnP433v//9ePnllwEA//Vf/4UdO3aYWjBCyDJ0NxBCyPrHkCADgHQ6rbgtM5mMmWUihEiY7W5gfBohhFiPIZflM888g8985jOYn59HNBrFZz/7WXzta18zu2yEkP/DLHcDt8MTQtY66yXHmiEL2b/+67/i0qVL8Hq9AIAvf/nL2LVrF/7qr/7K1MIRQsxFjk+LxWKIxWK0khFC1gzradOTIQvZwMAAstms8vPS0hJCoZBphSKErA6MTyOErGXW06YnQxayQCCAnTt34rHHHoPD4cDJkyfxgQ98AJ///OcBAN/+9rdNLSQhxBy4Hd7+MMaPEH3W06LSkCB74okn8MQTTyg/HzhwwKzyEEJWmUAgwInepqwndwwhZrCeFpWGBNlnPvMZs8tBCCFEBWP8CKnPellUGhJkExMT+PM//3OMjY1VxJK98847phWMEELudtaTO4asH+hGNwdDguyzn/0svvrVr+KP//iP8eqrr+J73/seSqWS2WUjhJC7mvXkjiFrn3g8jkgkgrGxMbjdbrrRW4yhXZaZTAYf//jHUS6XsXXrVnzlK1/BSy+9ZHbZCCHkrodH3hA7IOIZL1y4gFu3bsHr9a7JXY12zllmyELW3t6OUqmE7du349ixYwiFQlhcXDS7bIQQQgixASKesa+vT0kS7/f715Qb3e6bZAxZyL71rW8hnU7j29/+Nn7+85/jueeewz//8z+bXTZCCCGw96qe3B2IeMZsNouBgQGMjo7aTtDUQ4hKr9eLRCKBSCRidZEqMGQhczgc+N3f/V1MTU0hn88DAH7v934Pv/jFL0wtHCGE2AErg5jtvqondwd2iGfMZrOYmppq+v7BYBCFQgHj4+NwOBwYGxtDKBSyTX8yJMg+/elP45vf/Cbe9773wek0ZFQjJsNdLoSsDlYLIqa+IHbByvQS8Xgc77zzDqLRKLxeLx577LGGyxIIBDAyMoJsNou+vj5ks1lb9SdDgmzDhg04fPiw2WUhBrF6giDkbsJqQcTUF4QAkUgEyWQSTqcT8/PziEQiTfXDUCiEq1evIpvN2q4/GRJkX/3qV/HUU0/h4x//ONrb25Xf//qv/3rN7504cQJf+MIXUCwW8dRTT+HLX/5yxd//9m//Ft/5znfgcrnQ1dWF48ePY2RkpInHuLuweoIg5G7CakFkB1cRIXbC4XA0/V079ydDgux73/seLl++jHw+r7gsHQ5HTUFWLBZx9OhRnDx5EoODg9izZw8OHz5cIbg+9alP4Q/+4A8AAC+++CK++MUv4sSJEyt5nrsCqycIQu4m7DCAr5dM5IQ0i9/vR3t7O7xeL/r6+hAKhZq+ll37kyFB9rOf/QxXrlxp6MLnzp3Dtm3bcN999wEAnnzySbzwwgsVgszv9yv/TqVSK1K9dxN2mCAIuZuw6wBOyHpHTkbr8XjQ1taGvXv3rsv+aEiQfehDH8LY2FhD7sRIJIItW7YoPw8ODuL111+v+tx3vvMdPPvss8jlcnjllVcMX/9uhxMEIYSQ9YyIl04kElhYWEBHRwd8Ph+KxaLVRTMFQ4Ls7Nmz2LVrF97znvegvb0d5XIZDoejJWkvjh49iqNHj+IHP/gBvva1r+Gf/umfqj5z/PhxHD9+HAAQDodx6tSpFd9Xj8XFRVOvv1ZhvVTDOtGG9aIN66Ua1ok2rJdlYrEYZmZm4Ha7kU6nkc/nUSwW8fbbb+P69etWF6/lGBJkzcR1hUIh3Lx5U/k5HA7X9Pk++eST+MM//EPNvx05cgRHjhwBAOzevRsHDhxouDxGOXXqlKnXbzWrlf5irdXLasA60Yb1og3rpRrWiTasl2XkjALBYBClUgkHDx5ct94hQ4Js69atDV94z549mJiYwPXr1xEKhfD888/jBz/4QcVnJiYmsH37dgDASy+9pPybGIPpLwghhKxX1PHSFy9eXNdznCFB1tSF3W4cO3YMBw8eRLFYxOc+9zns3LkTTz/9NHbv3o3Dhw/j2LFj+MlPfgKPx4Oenh5NdyXRh+kvCCGErGe04qXXa2J00wQZABw6dAiHDh2q+N0zzzyj/Ptb3/qWmbdf9zD9BSGEkLuJ9ewZMlWQEXNh+gtCCCF3E630DNnN0kZBtsZh+gtCiBHsNvkQUg+tNtsqz5AdLW0UZIQQss6x4+RDSC202izQOs+QHWOwnZbenRBCiOnIk0+pVEIsFrO6SGSViMfjmJqaQjwet7ooDVGrzQYCAWzdunVFAsqOMdi0kBFCyDrHjpMPMZ+1bBk1u83aMQabgmwdw5gRQghgz8mHmI8d3XJGWY02a7cYbAqydcpaXhkRQlqPmHyEC4vCbP2z1i2jdhNMZkNBtk5ZyysjQog2K7V6c6F2d0HL6NqCgmydstZXRoSQSlohprhQu/u426xMAq3Fi93DeCjI1ilcGZHVwu6D3Eqxy/O1QkxxoUbWCivpd3opM+xuHaYgW8fcrSsjsnroDXzrBTu5+ISYmpubQ6FQgMvlavgaXKiRtYDRfqcn2tSLl0gkgsXFRWSzWWzcuNG21mHmISOEVNBI3qJIJIJEIgGv17vm8lsZeU475e8KBAIYHR1FoVCA2+3GhQsXDOeWkp+1FTmcCDETI/1OiLaLFy/i9OnTFX1BtgQXCgWMjY1hcnISs7OzmJubs611mBayuxy7uGOIPWjEIhSPxzE2Nob5+XksLCygv7/floOcFkaf024uvmKxCJ/P15Db0k5WPmINa2mcj8fjSKVSKBQKNftdLRe+bAlOpVIYHx9XrjE0NIT777/flvVAQXYXw4GaqGkkTikWi8HtdmN4eBjRaBQjIyO2aj+1JiGjz2k3F18zApGB/Hc3a2mcl8sKAMPDwwiFQk0tluQ0L1evXkUsFoPX67WtGAMoyFbMWlp5qOFAvfYwu701MuGLz2azWfj9foRCoZaXp1nqTUKNPKedYjGbEYhmWfnW8th3N7Ha4/xK2oW6rJ2dnTWvsW3bNgDQFW2Nfs5qKMhWwFpaeWhhN3cMqc1qtLdGJny7WY9k6k1Cdi57PYwKRHlibPWzrvWx725iNcf5lbYLo2VV30dvMWj0c3aBgmwF2MXC1OyKRJ6UXC6XEjjJgdWerFZ7a8QiZCfrkYyRgd2uZW8FWhPj1q1bW3Z9u4x9pD6rufhYabswWlaj91lr7ZSCbAXYwcK00hWJ+CxXu/bHDu1tLbFW3BRmYPZExLa4tjBj8aFlCGhFuzBSVqP3WWvtlIJsBdjB7WFk4K1nQVtrq4i7FTu0t7XAWnNTmIHZExHb4t2NniFgpe3CqLfH6H3WWjulIFshVrs96g28Rixoa20VcTdjdXtbC6zWAsPOQe2rMRGxLd691Es50Uy7aNTbY/Q+a6mdUpCtccTAG4lENP9uZHJaa6sIQmqxGguMtRDUvpYmIrK2MKOPtXIhpV4s2XnxJENBtk64evUqSqUSrl69WjE5GO04HLzJemE1Fhh085O7mZX0MT1x1CqRp14sjY6O4sKFC7ZePAkoyNYBRjMW2311sFLWyiqImI/ZCwy6+cndTjN9TM+yLMbu0dFRFIvFFY3h6vlwenp6zSyeKMhUZLNZTE1NralJ3WjGYjXrScDYyYW0nuq1Vay3OrmbFjqEtAot4wHQ2l3+6vlwYGAAMzMza2LxREEmIQ7gzWazlk/qjdDM5GAnAdMK7OJCWm/12grWa53QzW8ea0HA26GMdihDI2gZD4yO3eJZ4/F43UwC6vmwu7t7TdQTBZlELBZDuVy2fFJvhkYnB7sImFZhFxfSeqvXVrDe6mStTYJrjbUg4O1QxlaUYbXbstYmNCNjt3jWmZkZnD59uuJZa6XgkO9rtzakBQWZRDAYhMPhsHxSNxPRAV0uly0ETKuwiwvJLsLQTqynOrHDRFyL9SAWawl4uzyfHRYZ9cpQr65Wuy3Lc496E1q9sVs8q9frRalUqnjWZt6FXdqRGgoyiUAggK1bt2LHjh22e1GtQGv3yUoDKO2EHVZBdhGGdmI91YkdJmI94vE4Tp48iWw2C5fLhYcffnhNnlKgJ+C1BAQAS9pVKxcZzYqDWmUwIrZWsy3L5Umn03C73di4caNy361bt+reOx6PI5VKoVAoKOFELpdLifVu9F3YeVFFQabC6/W29Mw3O6HugMViseXPareVhxXlsYMwtBvrpU7sbO2LRCIIh8MAgHQ6jaWlJfT29tpqwjGCnoBXj1+RSESxtKz2xNqqRcZKxEGtMhgRW6vZluXy5HI5FAoFQ/eV6wcAent7K9JYFAoFjIyMNGRcsPOiioLsLsLsDmi3lYfdykNag5Wi387Wvjt37iCdTgMACoUCisUistmsJRPOSt+RloBXj18ALJ1YW7HIWKk40CuDXFeFQgGpVKoqGH4127LL5UI6nUYul4PX6zUsoNT1AwDFYlFxX46PjyObzcLr9WJkZMTQnGbnRRUF2V2E2R3QbisPu5VHjd6kZTcro52wg8iWJ0G7vKt4PI533nkHAFAulwEA8/PzSKfTcLlcq14WM96RevwClhNi23FiNYpZ4kAOnh8bG8P4+HhV0nDxObPbbTwex4ULF+B2u1EoFDA6OorBwUFD31XXT1tbm/K7aDQKh8OB7u5uJTuC1jOqsfOiioLsLsOsDij7+e0yQNp5JVQrQaLVgsPO2Elk2+ldxWIxdHR0IBgMYnFxER6PRwlHKBaLVZ+Px+PKTrdWx5mZ9Y60xK+VE2srxLiZ4iAQCCAWi8HtdpveX2rVhWgPImZMqz3qoa6fixcvVonNZDIJh8OBvr4+wxZhu4ZQUJCRFaP28w8PD9simNjOKyG9SUv+/dzcHK5cuYL777/fUNntYq0xk2ZFthl1YydxGAwG4fV60dfXh87OTrS1taGtrU2zjkTw//T0NBwOB/r7+/HYY4+1TDSZsTCzU0C/XnlWIsrMKv9qLErr1YW6DHJAfq3nlvusOtZZ1FkoFFKEmQj4t9PCu1EoyMiKUU9MnZ2dthEEdl0J6Q2U4vdzc3OYnZ0FAMzMzNQd8MWgmM1mUSgUsG/fPsNugWaxasOEXZIg28UCq3XsDKAvVmKxGLLZLNra2gCgZXFmrVqYabUrOwX0a5XHbuEQgHa7MKOMRupi27ZtAAC/31/3XElhvR0bG1MC9/XGM1mYrYfFKAUZWTF2mZjWEnrCQvz+ypUrAFCxNbxe8Gs2m8XCwgKWlpZw5swZPP7448rfWj1QWemua1RkmzV52sECW+s96MUlCmva/Pw8HA4HvF5vS/psKxZmes9jt4B+u495q9k/jabfKBQK2LBhA7LZrO64Jj6fSCQQjUbR1taGQqFQMZ5pYdeFd6NQkJEVY4eJyS40YjXSG0QCgQDuv//+hs5fCwaDKBQKWFpaQnt7O9xut6lWhLVgIRC0YvLUe69WTwT13oNsbXC73Uo7eOyxx1oeQ9aKetZ7HrsF9LdqzGuVlVl9nWb7ZzPlqVUXohwOhwM3btxALBZDJpMBAM2FgPh8X18fZmdnkc1m0dnZCbfbreyyXElZ7Y6pguzEiRP4whe+gGKxiKeeegpf/vKXK/7+7LPP4rvf/S7cbjc2bNiAf/zHf1y3OcDWO1ZPTHag1XEljQz4gUAA+/btw5kzZ+B2u+H1egE0Z0UwMtDZ3UIgozWZj42NIZ1Ow+fz1RUkdgreV5erVryWbG1YWFjA9u3bFfdkrUScRu6rJ05XKlJqtSsxxqyWK64eKx3zWtWutK5jtH/K7xJo/pBvvboQC8WpqSnkcjnkcjn09vZiaGhIMzZWlDubzWJgYAD5fB5er7dKvMlJkL1eL/bu3WvIXV/r+e3Qp00TZMViEUePHsXJkycxODiIPXv24PDhwxgZGVE+88gjj+D8+fPw+Xz4m7/5G3zpS1/Cv/3bv5lVpJZitxdZC/nIivWUmd9uaK1Kxe+bqXOjA77cFh9//HHl38lksiL3jxHRZHSSWGtWUXkyP3nyJMLhMDKZDDo6OjA4OFgzqN2otWE1xwQ5ZjCTyWDnzp3Yvn27pnWir68P8/PziEaj8Pv9KxLPahfUyMhIhaBdqUip167sKo6boVVWZq3rbN26tWoRog6kV9fltm3bWjp+Acvvc2RkBIuLi0in0ygUCnA4HLoblbQWT1r3j0QiuHXrFpxOJ2ZmZpBIJNDb24tCoQAAFdZgvb6qZTm2ui2ZJsjOnTuHbdu24b777gMAPPnkk3jhhRcqBNnHPvYx5d/9aJFcAAAgAElEQVR79+7Fc889Z1ZxWspaGhTkgXt2dhabNm2C1+u1dZnXKlq7icxuJ1ptcevWrZq5f4zcu5FJQhY5erum7LZwEbF2TqcTDodDWY3Xek75veol2VztMUEdMzg+Po7t27dXlbtQKCAajWLDhg0tOUpJtA85KaeR3E+NUEvUrSVXeb2234wVy+h1jFi+1HUJwJTxKxQKobe3Fz6fTwnQB6oFokD9/rXuKU6iKBQKKBQKmJ+fx8DAAKLRKABgcHBQt32Ew2GcOXMGuVwOyWSywnJsdVsyTZBFIhFs2bJF+XlwcBCvv/667uf/4R/+Ab/yK79iVnFayloaFERZ29raUC6X0dbWVnU4K2kN6tXdarQTvXuI3zea+6dRV6ReOgK9v630+Vcq8ERAe6lUQrlcVsRFrecU77VWks3VHhO0YgZr3dPj8bQkVky0D5GUs5HcT82gft/1AsjtIv7FpC/CB7TavhErs5E+pGVVqmf50qrLUChUsVvRSJtWCz8jrmy5fFpW1nrE43FMTk4CWPbEdXV1AQCi0agSqqE3fsXjcZw5cwbRaBRutxvFYrElluNW4SiLtM4t5j/+4z9w4sQJfPe73wUA/Mu//Atef/11HDt2rOqzzz33HI4dO4bTp0+jvb296u/Hjx/H8ePHASw39Oeff96MIgMAFhcXlResRzabxdTUFMrlMhwOB7Zu3ao0BLshrBcAKgIkGy2zkXpZS2SzWSX+oNl3V69OVqOd6N1jJfdupG5isRhmZmaUe27evBlutxtdXV2af1vJoNeq+sxms0gkEsjn8/B4PPD7/Yauo/c84nrRaFSxvGmVTW4vrWh/om+7XC7NPt3q+hcYfV4j1OpDtdq2uu7q1UWrMPLestksJiYmkEql4Ha70dHRgVAo1FDdi3pp5h2qv9Pb24uFhQUUCgWUSiXce++9aG9vRzabhcPhQLlc1nwedf1v3ry54rPy3/P5PIrFIjweT936F+Vzu924c+cOOjo60N7ervkddX0vLi6iUChgZmYGALCwsICOjg60tbXB5/MBADo7O+HxeDSfKRZbTpmSyWRQKBTg9XoxMDBgeAxolj/5kz/B+fPn637ONAtZKBTCzZs3lZ/D4TBCoVDV537yk5/g//2//6crxgDgyJEjOHLkCABg9+7dOHDggCllBoBTp04Zur6dVmN6iNXV5s2bFbeVyObdaJmN1staQNQLAORyOTz66KMN10c8Hserr76KRx55pG5AuNntRH0P8fODDz5oesyg1gr+4sWLOHDgQMstZOJ4FLFi37FjR81NQK2uez1r4OnTp9HW1oaNGzfWXO2LPtSK9ieXSe8ZZStNKw8Zb2VMaq1xxej7jsfjeOmllwAsxw719PTUbRvNIN5bLpdDOp3WzY01NTWlbKRYWlpCT08PPvaxjzVUR+q20kgf0vpOMplU2kI+n0c+n4fb7YbD4cD73/9+3fcov+sLFy6gXC4rbVa4zb1eL9566y04HA5D9S9vNvH5fIrLcMeOHQgGg8ruX5GzDHi3n1y8eBGPPPKI8nx9fX0YGRmB0+nEyZMnUS6XkUwm8cQTT2i+GyvyNTaCaYJsz549mJiYwPXr1xEKhfD888/jBz/4QcVnLl68iN///d/HiRMnsHHjRrOKYgprYVeh2m3V0dGxqhOYXVmpe0l06pmZGZw+fbrmIGlGO1G/J/keRgfwVr3rWm6XVgf+N+JONcNdqvU8U1NTurm31McTCVrp3tRrX83GENbDLvmtZGKx5eOB2tvblbgiM9xPsVgMyWQSd+7cQalUUnJjae0U9Hq96OnpMRQzVQu5zblcLiXWS154Gel3sVgMPp8PwWAQ4XAYwHIY0dzcHM6cOQOfz6f5PkX7UrdzcW3hvna5XGhrazNU/+oQABHT6XK5Kk6Q8Pv96OjoqMhZpvd8586dQ7lcht/vRyKRwPT0tG4iWTtvRjJNkLndbhw7dgwHDx5EsVjE5z73OezcuRNPP/00du/ejcOHD+NP//RPsbi4iN/6rd8CANx777148cUXzSrSmqfRSdTqCaxVtFoorjRlgxzYXCsezwyBW+89GY37kK+x0vQBtURnKwVpI4NpI6Kn3ntSx8nI6LUlreOJhGtupe3PCM3GEBq97mrEyhl931oCyIwyuVwuJTeWy+VCuVzWfP56MV2Njq3is3Lc1dDQECYnJ3V3CKr7ndzm5DirQqGge9alOpmwus2qhZWcVb/e84nyqWPW5BMkyuWybkoX9fMNDAzA4XAgkUgo9azeeLMWMDUP2aFDh3Do0KGK3z3zzDPKv3/yk5+Yeft1RbOCSRxZUS9ocjUG2mYEympZOhpBDE61zk5rtNxG66beezIy2cvXqLdCthtGBV4jO9hqvSfZ7ScyxKsnQa22pJ5cstks3G638gxmr9LNEn2rISZljLzv1bJ6FItFbNq0SbGQORwO3eeXy61lXTJSRnlMkBeBly9fxszMDAqFAh544AFDmyq0RKLsitRaUKgD77UWblrCqtn6F8JanCDR19dXkV+s1nUHBwfxxBNP4Nq1a5ienkY4HMb09HRVf7az4QFgpv41Q6OCSd3wtOL3ZMweaJvtCGYJxZVYbsTg9uqrr+o+R6MWGqN1U+89GZmc5GvUWiGvdbZt26Ykf9Wj1nuSd2S1t7cruxnVW+rVLmMx0amPJ5KDhs0OeTBLpFjh8jGyWFlpfRpNhtzd3Q2Px9OQJc7lcjWcDzCbzVZZsZ1OJ8LhMFKpFDo7O5HJZDAzM4Pe3l7N3YTq51HXkfh3d3e34loXyAJQpDfx+/2aAke2ogm3oriGkbg0edxbyQkSg4ODKBaLWFhY0B3PVtPC2wwUZGuERgVTow3P7IFWXZ5IJGLoXqu9Iq+HegBqVjjJyINfNBpFJBKpWSf1rJ5i4NXLDya7GtLpNCYnJxVxppVja62hlXtPL1dWLZfjlStXUC6XldgkIar03qlaWO/duxeJRALA8ru6ePHi6lTA/6GegPVER6OWaz0BasYGklZYNIy4pOWs73pJgpsZI5uN5ctmswCgWLGnp6cxPDyMW7duweFwKOlO3vOe92DXrl0rtgKJI9ZEPwkGl9Oq3Lx5UwmeV1vi1FY0sdPS5XLB4/FoHgwufyedTsPtdlfEiDVygoTWe6037qr/7nK5mortMwsKsjVCo4NBM0Km2VVmo0ftFAoFwxmSrViR66Ee6IQ7SotGyi0Gv/HxcTgcDoyNjWmKrUasnkYGZTEIA8A999yD69ev480332x5os/VRghcI7n3tN6TLOjm5+fR29uL7u5u7Nu3D93d3brvVHZTZrNZFIvFikTYVqLXHlYieJpNOi2LuFgsVnMBoK7TRi0aRp5PZH33eDxYWFiouSAyKnLl8mvF8tX7ntfrRS6Xw9zcHGZnZwEAhUIBXV1dKBaLyGaz6OvrqxBj4pqpVKqhxbjW4l3MFx6PR4nNUlv35O9NTk5ifn4ePp8P6XQafr8fxWIRS0tLePnll7Fnzx7FrSm+k8vlUCgUMDc3h0KhAJfLpVtGNXrvtd64K/9dy0Jn9ZhHQbaGaEQw1WuYrQo4b+aonVQqhfHx8Yasd2aVvxHUA5dYxeph9H0FAsvHi4hBVm/iacTqWe+z6jiy8fFxpFIptLe3o6enpylTvngn9eplJTQi/kWepXquIvV7ikQiSCQS6OvrQz6fxz333IMHH3xQWeXr3VcEfYu8TY1MMEZptt3rtYeVuHDUwhcAEolETUGjFnFOp7PmTuWV1qnR5xPlbyQtpxHLmmiLsugwMmZ6vV48+uijuHLlCgBg48aNyjUCgQDa29vxgQ98QNdaJZ69VoyrbOlXL95jseWdq0NDQ5ibm9M8e1L+njj1AljO9l8qlbC0tAS3242FhQVcuHABV69eVVyvsdjy5oLh4WHFgnjhwgV0d3cban+13quWh0B8R/SbQEB75ygFGWkp6q32enl76g0IrQoyl5E7ytWrV5t2Q1oVmKkeuGpZyBolFArh6tWrNTcKNGL1bMR0LxIkiszv8rZ1dXuqN9GWSiXMzs6a4vZsRvw36kqLx+O4dOkS5ubmMDc3p7hfjEwWIui7ra0NuVyuZTsb5bI12+71XDUul6vpkABZ+JZKJUxPT8PlculaeIFqEedyuWruVF5pnRrpM6FQCAMDA4qwqhdvK6hnWRNjqFp06GXOV38PAO6//37MzMxUCZju7m6Mj4+jv79fU1gPDw+js7NTdzFuJGBfFk5aZ0+q+9nZs2eVReWDDz6ICxcuKAeKy1Zj9WkmIh1HI6Ko3nvVc6fKwtlu4TAABdm6QmurvdaqrZ6I0kuAqUWzrlEt653ReJSVrOpXgrrcIiaoFdY6Iy7ORtygzZju1cHKRtsTUPlOxATSaqtmM+K/USKRiBLEn0ql4Pf7K2Jc6rmeRSoUo8HbjbCSdl/LVVMv7YmRfFe3b9/G5cuX6x6lpLZeFovFmuPGSus0EAhgdHQU09PTGBgY0O1Xjz32WFNtU8+yVitWCoDumKmV41B+b9PT01VxV1riotbiSbZiT09Pawbsi3erDvbXqjvxHXUd9vf3Y2JiAq+99hpmZmYUC6e6bzYjiuqNb3JfuXr1KhYWFuDz+RCNRvHGG28ort56bWO1oSBbR4iOJm+11xoY64korYFfj0ZEgvp7WiLQSDyKlSsbvXK3wlpnREQ06rY26grWio0y2p6AavdFvYD3ZupJxNqFw2HDk3MzgezCctPW1oa2tjbD7azZvmCUlbZ7PVdNsVism1Vd772JawaDQWVyrxUsLU+CDz30EC5fvmw4hlSdGNUIIqi+VCphZmZG18rZjICvZVmTx9BcLodMJqO0W/WZkfJ9xffkHIfi3cjjI4CKPtBI2xNuYGG98vv9ulZKYbV/44036ma113IVbtiwAf39/boWzlrlrreAq/XOxM7WVCqFWCyGXC6HfD6PcrmM69evIx6PY3R01FDbWE0oyNYRYjUpb7XXGrTrdd5GB/5mrREyaldGo4HYq4kcK7Ua1rrViJfTeodG25P4vngnb7/9dsNWWTNoJJBdlNHv92NgYACLi4vo6OjABz7wgYaOG2u2LxhN7dCKuNBG+rf6ventjg4EAhgeHsbk5CQ2btyoGywtBJI4ukY+2UAP8ffVSJvTSF+rZVnTCm+QxYheO5EtiPK7Ec8hTrTRiumSF1Lyz2qEGxhYtpAlEgnNw7XFGCeOgNI7mUBGK+m0EJdOp1NzF7dWXax0s4lwESeTSQSDQdy5cwf5fB4OhwO9vb2Ki50xZMQ0xABhJOan1sRhheBRuzIaDcReKUYHYnWs1IMPPtiU1aKZ+632TqBG2pP4fCAQwPXr16v+ZiTmo159xGIxzTxgeuhNxloiQ+w4dTqdSvyL2+3G+Pi4KakW1J81+o712n2j1zDijgKM744Oh8PKWYJjY2PYtGmTYgUS9S5SiSSTSSwuLmJpaQnRaNRQvGGzgr4R8dlMX9N7H/IYamQTk9xetHIcys+hF9NltPyyG3hwcFD3/FVhkRYpNtxud8N9TsSMiWz+4+PjhnZxr0RIq8VrMplU8ggWCgXMzs6ip6cHAwMDSngFY8iIKbRKqLRa8Bi5X7OB2CulkYFYHSulDlI1Ut5m72fFKq6V7amWa8LoRNJIDiG9yVj9ewAVdSwOPW62zmtZ4LTEh7yrs5nUDuLajaaHUOee0hMWwsXodC4nJtWql+npaZTLZfh8PiwsLGBxcVFzZ6G8u7Kjo0M5GqdeWZt11zayuJTdhTMzMxWxRs0gu/BqbWLSai+14vVWGltrtE4CgQD27dunnFRhJExA6z2JRZBWAmq9hUsj4QlaVjlZvD700EPKwejRaBQejwfAcpiGXVIqCSjISMtp1sW22iJQ0Ijo0YqVarTczd7PLqu4ZtGrp2Ymkno5hOQdbolEoiJoVz0hAaiYMFe6ctazwGkdRh+PxzE2Nob5+XksLCygv7+/qXfcaHoIuYxzc3O4cuWKrtVF1HMmk0E+n9e0Xg8MDKBUKuH27dsAlvNXidgqeWfhxo0bkc/nkc1m0d3drWRVl+8njx1qy1ErxpV6IuDy5cvIZDKIxZY3K+htZGnk/rXKriXIm6GRscLomDU4OIjHH3/csJtc71m1ylZvIZbP55HJZBpqy7JVTi5Df38/rly5Ao/H03Qi2tWAgmyds9r5ump1slbmPjPq7tMb3NUDcSMDWa1YKSM0ez+7rOJaTTMTSa0cQlobRNRBu/KEFI/Hq04/qJUA1sjziNW9y+XC7du3FXGijosUloPh4WFEo1GMjIw09Y4bTQ8h6lxOPDozM1M1KcpWoxs3bsDv92tmnB8cHMRHPvIRnD9/Hn6/H7lcDk6ns2JnoWzx2L9/P4rFYkUf0rJ0qEW33uYDo2jlDhPPGQwGMTIygoWFBXg8HrhcrqYtlmpquZrHxsYQjUYxNzenK8hrWV3riaGVYsRNLtJnyBsbkslkRVnUZdPrw/F4HG+88QZmZ2frnl4Sj8eRSqWqEsyqyxwIBCpSiNj1VBIKsnXMaogjNXrWDnmSVB+n0apn0vqcuN/o6CjGx8c1v9foQCY6u1aslFY51NfVul+t92GV5XC1aGYiqSXiRBsEoATy6m0QaeT0g0YpFArKQdTz8/NwOp3o7e2tcLXKsZN+v9/Q/bUWGqlUSnG/GnEtCVfkm2++iXQ6revqFOWLRqNwOBzYvHmzkk9KzebNm5HP5xGNRlEqlbBp0yZlkhRlEwhxLPch9djRqqBrub4ikQimp6fR1taG+fl5TExMKPcRIrCnp0f5XSvSl9RaGIpnFvWfz+c1r6FndVULtImJCaRSKbz3ve/VratWjf2yWBfnXY6NjQGAEmOr3i2v1ba0XNvz8/PIZDLweDy6yXrlvpvP55HP5xWLrNaOSTHONBrPtppQkK0ztDq7njgyI1BczzStDuY1smNHC3kQqLVyEjE1YofQa6+9hu7ubt2cUrLFQv5ZC3mXZa3BrVY9y4NTOByuiNOw0wBhhEYD2LU+24joFNcQ+bPU6RBkC1Umk8HNmzdx7733ak6sWq67gYGBFR2pIsfLJBIJdHZ2AgDS6bSS2FO+diNitJYVCQCGh4cNHcosXJHJZBK3bt3C/Pw8AOChhx6q+Jw8iV26dAnRaFRXpKitdPfddx/Gx8eVhKj1NmSox45GXcdabUttxREWPmBZNKiPGSoWi9i7dy+uXbuGzs5ObN++vWoR20iMaz2r3+joKAqFgrLj1OVy4cqVK0qeMPmeQryIFBpCxEejUUxMTGBiYgKTk5MAgDfeeAO/8Ru/UbHoFUmex8bGlPpodmEsvy8h1vv6+hCNRgEAXV1dhnbLj46O4uWXX0a5XMbZs2cxMjKCUqmEzZs3IxaLoa2tDT09PZoLFbnvLi4uVgjbWuJdfNaquNxaUJCtEYxMelpWIS0rQi2httKVk1Z8jlYwr5EdO1qIybbeuY/ic2KHkMhErze465nftQZjMaBOT09jcXFR90xOI7FR8XgcZ86cUZKRNntskVnUaxOymHQ6ncoRUFrXEZOBkTNMa5WnnlsrEAhgaGgIN27cQHd3N/L5PIaGhjTvpeW6u3r1qmbyTaPIVi+Hw4FUKqVYyIQwaTaOpZ4VyUgaCfk6nZ2dSkJgIZxE9neB+PelS5dqxvQEg5VJXH0+n7I5QlhBRP8TVkK5rWhZSo26jvUWP+I5HQ4Hbty4AZ/Ph2w2C4/Hg7a2NmzatElp46Jcoj3F43Fs37694vrqPIn1kuqqBf+bb76JbDZbcbalCJwvl8uYn5/H5OQkFhYWEA6HK9r28PAwXn/9dSwsLGBhYQHlclk5HeGtt95CJpOBw+GA2+1GsVjE9PR01aHeiUQC0WgUbW1tKBQKTS+M5fcl+rVwAwNALpcztFs+kUggHo+jra0NiUQCQ0NDSt+ptQMUqBTwLpcLd+7cQSKRqIqhVI/dernc7AAFmUFWOxZLfW8jFi21VejChQvYt29f1YDRTIClVpmM1IcYkNTBvM12hEDA2LmPgUD1DiGtwVM8h1gpy+Z3Yc4G3s2BJGfdvnHjhjJwaE3cevUs15uwprS3t1cdW2Q19dqELCbdbjdyuRyy2WxVbIY8GSwsLGD79u0r2k1oxK3l8/ng8XiUw5F9Pp/m9cSkonVmYKOxJloB6CK7+uTkpNJ2ai0M6l1bfdRRLStSrT4q2mYymcTS0hIcDgfK5TLK5XLFexFCOhwOG4rpkWPxgHc3S8j9Tz0xDg0NVeR6q2c51XouvcWPWJhNTU1haWkJpVIJHo8HAwMD8Hg86OjoqDrKp1aqFJFPTCQaPXPmDHw+n+6YqRb8+XxesUaKMTAQCODxxx/HlStXlDxu8/PzuHbtWkWwfyKRgMvlUkQPsLyZY8uWLUgkEigUCiiXy8jn8/D5fBgYGFA+J8rf19eH2dlZpFIpeL3eqvfdKOL9yIluxf2MWhLFiQ3CclnLYpzNZit2VsupRd58882qGEo5ZrBYLKKjo6NmLjeroSAzgJW5oADju9DUViGxUlIHwmqtRBs5aLVebJreFmSxzXilKS2MnPsIGNshpD6QVza/yzueRN3kcjllQhVCT29y1bMWqre3e71e9PT0VBxbZDXCzSyv5tVtQhaTi4uLSr0tLi5WfFaeDObn5xGNRjUTURqhnltLWF78fj/6+/sNnU8YCASqzgwcHR1FIpEwHGui1SdEv+vu7sbMzAzm5+fR29tb16pS79rq72tZkeqNWbIQzefziMViynl/4r2IyWx6elrJ6q4X06N2uwurhtbkOjU1hWQyidu3byOVSuGll17Cli1bDLnr9Z5LL6ZQLOBisRju3LmjiE+gUhDJ96yVKiWZTCKTySAajSqLp97e3poLQ7Xg93g8VWJA3QaFBV7efTswMIBr164hnU7D6XRi06ZNFbtZP/ShD2FmZkaJIZNdkbLVdsOGDbh9+zaKxSLm5+cbPrBdCy0hXQshqv1+P/r6+nDr1i04nU5MTk5i+/btmps3wuEwxsfHkUgkquLSRGoRddyfHDMoLNaij9tNjAEUZIYQHaTe6tAsagUwywif/GuvvQav19tQYtV61hyZWgJR/bdEIlG1g22l6A30tZ4zHo9X5axSl3V4eBgAFPO7XNdyXhsxIXq9Xjz66KM1yyHXs5bo3bp1a1N5zMy01qrdM4C2aV8Wk16vt2LQkz8r2lYikUAgEMADDzxQEZvTyHNpiVzRvvx+f4WLZ+/evYaEjzomTV6kGM2dVKtPiDKrk30aRX1t9SJLy4pUbxEnnmFgYAA3btxQLBoiR5O4hshtJiZtOaZHttrpud21yuZyuXDr1i2k02mUy2WlzejFGhl5rlpjQigUgs/nw+LiInw+H7q7u7F9+/a6B2aL9iXGDVlYeTwehMNhJBIJTExMoL+/v2KzhiirKIta8Ne7tziQW959293dDY/Hg97eXjgcDnz0ox+tEuN68WBGrElmop5LZFG9fft2FIvFmh4PYY1Pp9NYWFioCu2o9f6FAHe5XBgZGcGGDRss8XQZgYLMAEbjlsxCq7Fp7dwRvvzu7m7NremN3AOo7DTiPEOgtkCU/6bO7N3KHWxaA70eRlfV4p1qnTOn1dmvX7/eUDlqreJX+iytRJ6Ie3t7dU37YgEgDucVk4M6HYj43JkzZ9DR0YHp6WklNqeZ55JFtvydgYGBChePLFz0xJ5W7KDaKqJepDRioZHL3OwkYHRBZvQ76mcYGhrSDAEQglscnRUKhfDwww8r/Vh24+dyOQBAJpNBd3e3pnteIESvLAZSqRR6e3vrPpvec9XbpawOXxgYGFCs3wAqxj31GChich944AFkMhk4nU7FWnjvvfcimUxi06ZNFbGUAJR/C6GvtwlFXdZAIIC3334bCwsLuH37Nrq6upQxye12Y2hoSBHmRsYOuW62bt2qaU2SP5NMJpU+3WzAv/r+cnsTOemEqPb5fPD7/TU9HuLZ3W63odAO2QInW8q1FoJ2goLMAMLsXS9uCTDPeiF3PL3AZnWMTr2Vj1ZSPzHRqd1VesG36sFFvRKrd2SIkXKt9LONrqq1BrlGBz4t0dyIZU8Po5aPlbQ/dZJROamq+nnlw3mFm04rHUixWKyZ/V5+rnqJSuUjf+TvvPXWW4jH41UJVmuJPdn6rY4d1HpfWlZOcR21ha1VY0Ez7abWd9SJSOUJUR0zpz46SzyrvDsxlUrhzp07Sgzali1bkEwmdXeqBoNBdHZ2KhaawcFB7N69W3MTjdbzqi3uRsS8HL4gB+6LUAUR2yf+LYSDiMlNpVKYnJxUYhHf//73KzFYXq8X77zzDuLxuPJdr9eLoaEhzM3NVcSZ6W1CEYjnTiaTmJubQ7FYxOLiIiYmJrB58+aGhblW3SSTSQQCAXR2dmLz5s0Vm20ymQzm5ubgcDjgcDjwxBNPVGwMaMaSr97JClS6hf1+f4WVWy1W5bQuHR0d6OnpqQrt0Ao/Ee+ilqXcythwLSjIDGIkbsmswHitQHCtwOZGYnT0yqrnrpItZED1gb/qnYniWrWODGmkXCv5rNpqJ084jVinGim33sC70vs1Yvlo1npmNMloI0f+1LPyiL/XSlQqxzSJeDWPx6O8146ODmzatKkqwWotESvuqxU7qPW+1M/hcrkMH2AuApJFsHMj6RO02k298UPvO+pEpGJCTKfTmJycrIqZ01oIiklvbm4Oi4uLKJfLcLvdSKfTuHbtGm7evFlzp6rH40FfXx9isRh+6Zd+qSo9g5E6lQWikfhX8SyyqA6HwwCWBZv4t0jfkE6nlZhcgdfrVTauiIleuADFuOLxeLC0tKRsDpHd3rVyq8nPd/PmTUWs3L59GxcvXsSmTZt04w/12oK6biYmJvDTn/4U5XIZpdJyrrilpSXMz89j27ZtiMfjWFpaQm9vLxYXF/Hzn/9cOXy8kVQw6t3XoizivQmLn6QaVTEAACAASURBVJ44FvcA3p1jAGDDhg04ePBg1b3l55TfqbAkalnK5WtbERuuBQWZQYysUuXVdr1YM6OTp9bn1JOCCGzOZrMYGBiouVVYXVb1wCB+r96JcvHixZrPq2VdEHVm5BDjeuVS14lYeQnLXTqd1q1vuRxmJQRUW3jefPNNJJNJdHZ2Gt5R2EwMVa3B16hFUo1wVakDZNVl1TvyR70Tql655b/Lwc/qZ5BdqcCycHz44YeV/E1i5546waoIOdA6F0/dNuptFFE/R71+JH4fiUQwNTWFRCKB2dlZ9Pb2Yn5+vipxphZa7aJZ8S3K1dbWhkwmg3Q6jbNnzypiSrj0tMYv9TMNDg5ifHwcLpcL+XwebvfydNLZ2YlyuayZ5kJ8V7jeLl++jGKxWPGMekJfr66NunTVO1WFBaqtrQ2x2HJsVzqdxtjYmBJgPjo6inPnziGdTiObzSKdTmNpaQl37tzBhQsXlPH46tWrSkoNYVkbGhpSctqpx2qtssrPJzZkxeNxAMCmTZuQzWYxPT1dYTmWQ1WEqJFzi8kLnUKhgPn5eZTLZfj9fty5cwfxeBylUglLS0tKSI7Iel8ulzExMYFr164hEAhU5HGMRCIVSWjVglodU/jggw+is7OzwnoMLKe90BNSkUgEi4uLFZ4a0QfVyG1A7EJV13E912mz42UroSBrgHrWDTHwG4k1Mzp5ypOQGJy0AsEbPepFbxBTN2zR+dWTrDAjZzIZ3L59W7HQaYkPI4cY1yuXQO5UmUxGEaIAcP78eQDamwfEgK4VpN0K1BaedDqNW7duoaOjAy6Xq+5OpmZiqPTK0IhFUu/6RhcfmzdvRjqdVixSYvOEcH+praa16jsQqAx+1opPlGOavF4v/H4/isVi3YOCa52LJ8qlFTtYDyP9yOl0KhM5AMW1Vy9xJqCfNLgZ8S332UKhgK6uLuV4oMHBQeRyOSSTSYTDYTidTmX8At5NYyBP7gDg8/kUa4rX61XSZzidy3mzhDtUnQxV1I3IGSVb3kRqCLXQ16trub3qxWep+5dI0NvR0aH87Pf78d///d9KQL1IkyHcjT6fD4FAAAsLCxULLTEey8JIxKnJsWP1xmr5+drb27F//37Mzs5ienq6wmMhLMcAcPLkSSwsLCCZTCq5FuXcYoHAu/GbbrdbcS2LFBoejwfJZBIdHR3weDzo7OxET08Pbt68qYyxhUJBOU5KWKPPnz+vLLTVSWjFOCun8lG7o9WWVrWQEvHHwtKYz+fR3d1d5akRqNtAIpEA8K6bfWpqqq7rtNnxspVQkOnQbByT0Vgzo5On3qHB6smtUVeY3qSr9Xt5kpXdcWKQ6OrqgsPhULYj6636jEwc9cSAfL3FxUVF8ADLKSsuXLigK/xaJViAd9+57PqULTxi1d3X16fkLqpFI/Wk1zaNCCmjiGfS2p0KVLdLv9+vPIeIq9Gymhq5r94zBAKVMU1abhSt7fKRSATRaBQej6em5VqvD9Vzc9TqR5FIBOl0GhMTE0in07hx4wZcLpcSo1MrcaaWpcGoVUi2Bsm5v4R1TIhbtTtJIISi+ogeIWTcbreSFV4IuqGhIeX7k5OTirBTWyLkw5/ffvttFItFZdEpEi1v3boVc3NzFQl967WNZDKJV155BaVSCV1dXRWHgqv7VyKRqIhp7OzsVJKUigPUy+WyYjUUVptQKIQbN25UJSAVbcfv92N6ehput7sqB6JaKMZiy7FisliT6+WBBx7AAw88oMT0ApWW41QqpaSLyGQyKBaL8Pv9VUm31fGbH/7wh1EqlTAwMIDFxUX8+Mc/hsPhQD6fR3t7O8rlMjZv3ox4PI7FxUW4XC643W5lh2IqlVIS2WoloRVtSy+Vj/pdiN3tAJQFlnADi3Q62WwW+/fvx9WrV6v6idwG1P1THiNkN7s4taFV42WroCDTYCVxTKOjo3V3jAiMpINo9NDgRtCbgNS/F5OsOg6ira0NTqcTfX198Pv9mrvxmhFBtcSl2oInDm8W5+XVSxbbig4o3vnMzAxOnz5d4aIVFp5sNguXy4W2tjZDSXC16kktBMQEq7Y2yAN6o8LcyHNq9QO9dhkMBuFwOHRjsowgT1jyz+Lf4mcRC2QkRKBcLisJPe/cuaOcuVfPtS/HVBYKBQwPD2umLtG7xtWrV5Xs6EKE+f1+PPLII8rko3ZFyu5QYWnIZDJwu90VAkAvHEAu861btxAIBOBwOCqSYgpXr9y2xCQo4qbkI4b0hMzw8HCFy1jsupQt0QA0XcapVAqJRAKZTEYR96VSCX6/HxMTEwCWz2aUd8bVEs0vv/wyIpEIXC4X5ufn8cYbb2DXrl1VAlaMFeoEvalUCsByDJNYVACVVhSfz6c7HotNLtlsVnG/eTwedHd3awb2CxdkMBisEJCBQOUZn3qW41QqhXK5DJfLhY6ODnR2dqKrq0s5F1KgHlvk+pyamkIoFFKeR3YtqgWu+F44HEY6nUaxWESxWFQS7crl1RpnRdsWrnKxGNGyoALLO3aXlpbQ0dGB7u5uQ3OfWuypY/aEm12cSiHuZRcoyDRoxFohPismhUQiUXPSl33+8s4eQN83Xi+eZyXUSgcgfi8mWdGh5Zg1kem5q6vLUF6fepNfvc+prwdAsUJMTk5W7BQLh8MViS7Fd7SsKI0gv3PZ3aTOZ9Vo0LZe2pFMJqMcnCuChEVG+XqZwmtRr761+oH4vcgYrm6XgUAAW7duxb333msoJkuvXGohKO4rl9VoiEAoFMKGDRtw69YtOBwOnD9/XrFu9Pf3V1hStOpAPv0in88rlpx6/VHUn8iOXigU4PP5lEWEKJtoO+qjpUZHR+H1etHV1YV0Oq15cLJWOIC4L7AsekSOL7kPq+tJlOHq1avo6uqC2+3G6Ogo+vv7KzbmyDFQYuwS7UO0FXFigxBgwnoqSCaTOHv2LKanp5HJZJDJZNDb24vOzk5FpC0tLSlWWCN5H8Wi0eVyKX1mYmICkUgE+/btQ3d3d8XGBSGYhKsyFns3RUIkElEy8U9OTlbs0pPr3Ol0VmwQEnUg3GrZbFZ5vlAoVCUSgOXYVzGGCHEt2hxQuatYK6B/YGBA8cg8+OCDivVSbie1xmD1/CK3i0AggE984hNV3ysWixgcHEQ+n0cymcTu3bur0mOohbN6s1hvb6+SmqlYLFbE34oxTbbkGp371OJTHbOnPs5rJeOnGVCQaaB+qXJAqjzxCrGiNSloTfqiUYr0FPfee68SH6Dn1mmlG0qUoZb7RTyfVtbxHTt2VMRBRCIRZZWUz+cRiUSqTPDiGbQsAFod1sgmBy33EABs375dmdTefPNNxTrQ3t4Oj8ezojMU5funUikUCoUKsdGKHY5yPY2NjSGRSKC7u1vZVdjZ2alYSwBU7eBqxApVq7zq4Ge5H9TKGC/wer1K7Fgz7VYtBNVuM9kiafQYrYcfflgJ4L5586ZyrJKR3aHq0y9yuZxmLJo8eYoJ2Ol8Nzt6OBxGPp9XMrB7PB709/dj7969umlrhBvc4/FUbXTQWziK+6bT6Qq3mjopplZaFhFvJMTfvn37KmJzREyU+hQD9bm5Ho9HGReuXbuGUqmkuP3EmCesMvl8HoVCQTnmSvRVYTEzgrAyxWIxJUdYLpdDOp3Gyy+/jM7OzoqNC7L1TrbOfPSjH8W1a9dw/fp1bN68uSqfHQDdDULy+y6VSkosHbB8oPXc3JwSWzYzM4NEIqFYbcvlMu7cuaO089nZWVy+fFk5u1Jr8SBc+OLdCFep1oaYWt6Qeptt1L8TIglYdjFu3ry57vuRxaqwdAl3p9p6Kd4PUGnJNTKGyM8jt1e1oFbfq9Hx0ywoyDRQv1S1OVUdt2I0bkxeMc/Pzyv5Xup9byVuqFoCTG+XiVihiY0EkUgE2Wy2SgTFYjF0dHQo8ULnzp1TkiRq7Rwzkg+qVueoJ3pEmcSkKawDhUJBSXC6ko4n3x8Aent7lTLI7rOZmZkKd4n6PdS7t7yDUbQRr9ermPo3btyorC7Hx8cbcgcL9OpbywUvBjP1d7SO5ZJptN3KQlB2cQHQbRtGj9GSPyesKMLqqBe/Jd6XnFRUpNdQT3rqlBxi8pRz8on8T9PT0wCgTN610tbouauA+kHuExMTynuUXU7i+bT6UrFYhNvtViyCIkA8GAxWjR3yZCbHhYn8g2JcWFpaQjKZBICKjRiyNbuvr09p0yJ2qFQqob+/v2ZCafk97d27F9euXYPT6VTygomYKHnjgnxO6e3bt6sO+961axfi8bhum5LHGbXrWtRBf38/fvazn8HtdiOVSiltenR0FIODg+ju7sYbb7yBRCIBt9uNUqmk/BcMLu80fe2115RydnV1ac4R4t/1TtaoNf402k9l4a62xukh2qo4eur27dvKZiet+VY8dzqdVr6vfu/y4kd971QqVWFtlucKrXsxqN/miEaqTgSplUfG6KQgr6AGBgYwNDSkuNnMaBDqQVedyRzQju2QA7ZLpZKy/VqOl5KfR8TH+Hw+JBIJ3Z1jtUSXkVizWiJCtliqrQPi+UUwp96Ox0ZdeAAqyl8oFHD58mVkMhnEYjHcvn0bjz32GIDG8t2IwX54eBgzMzNwOpcTTYqdVMLypD4YuZFBVc8KrN6JpBZdZu1KUu+8yufzyt/8fr/mfbVcxOr3IlAP+vIuLHUbAqrfl0gqmslkcOHCBcXaIayjV65cweLiYoW7SkzSgUBAcZ8XCgXlP5HvqV7aGj0rhvi9XlqZ6elpJaZo7969NftiJBKpEMOyRVDUqRyaIc5TlN+JGDOF61OMC5s3b4bP56tIA9HR0QFgefer3+9XBFFHR0dVMlq9dl0rGegHP/hBxX3ndDqRz+eVcW7fvn2KhW92drZKxKjbilabEv1HPaaIOggGg5idncXCwoJiHZSTdQcCAezatUsRhF6vF+9973tx9uxZxZIaDAbR0dGh5AbTWzyId6l3aHatRZaRMUNrXKyV6FnPiyFveurs7KyIwZNFofC+XLp0Cf/zP/9TscAR19da/MgLSrW1Wc9a2Gh2ArOhIKtDPZ+0ugM3Ev8UCASwfft20xqEPOhqZTJXx3YI5IBtMSmr46Xk55G3e9faOVZLdNWrQ9lVKH9fa6UvynTp0iWl7HrxFfL15cF9aGgIPp+vYkJQl1/egh0IBDA0NITp6WnFRao+nNzoWaiycJcPo3a5XMqAXSqVMDk5ife+9726xwPp5a8Sv9OyAsvb0Jt5R8K62ihyW9VK7Ki181crEa+wusi5mNR0d3dX5U06efKkMjGOjIxUCf9gMFix6hbWDuBd64R41yK+TohcUb/ChTIwMKCkG9i+fbtiMak1DtSyYshxZKKtCGEtW35k1G4ideya6CtyP85kMnjnnXfgdDqrYqvU7U2d202k0JHFQywWU8YKLWFXDzlf2czMDPL5PLZs2YJsNouOjo6KzPxnz55V6kAEiMuuMa3DvsW7lduYLORrWYkCgYBisZuenkYikagQbqKuRB2KRYJw34p79vX1obOzEzt37qw69kcrtEDrnEzZ45FMJqvipsRntN6jug7EYlJvLK+V1DcWiynzZ62YaGGBFCEGABRPjVg8yPkItXLVqa3N6rAj+V52EGICCrIaqFfgcvyU1grAqI+72Qah3speT8SpB111JnMxKImJTzRqsUoGgK6uLgDLKSX0zPeBwLs5nDKZDBKJhOZxO7Um9FrWKXnCFAfECqEk0nGo87TJZRITa72je4SQCIfDuHHjhhLjI+9+kssvJ8uNx+OYmJjA4uKi4o6Rz+Zr5CxUvXoSyRSz2Szm5uYwPz+PX/ziF3jiiSfQ3d1dJSgnJyd1s17LOcLU1hKxc07PvSHqS/5ZvKPFxUXEYjE8+OCDhs/BU4ttvcSOMqLMQuReu3atIvhezsUk7qFnpYxEIpienkZbWxvm5+cxNDRUMdlkMhm89tprSp4usepOJBJKPJSwTmzatAkbNmyo2DkmDtEWQq1QKODOnTsolUp46623sHnzZgwODmq2h0astnKQci1hLd6b2sUo3r8sZsT3xMYZ4N2UGOoM6Or61YsjlOvW7/fj0UcfbXhRKrv1o9Gokn5FHPQtCztxSLw8zsljo95h3+q6ffnllxGPxxWrzNDQkBKvlkwmK477EjsuRXiDGLvOnDmDBx54AJcvX1YEr0glksvllPFdJKF99NFHNceKRqxemUwGkUhE2dyxadOmCsuoHJ+pDsnRC2vRG6O0vBhAtbCtN38Fg5U5B10ul3LChBC2uVxOCedQu/Fla3OjpwxYCQWZDmoR8PDDDzfsomkkbsjIteQ4ASMZvrV88+pM5mq31djYWIUVQOxQevXVV+veCwAuXbqEUmn5bEOxYtQKHtZ7Ni3rhjxhikOMxTXkwUbEJMj3M+puE25asUPM7/drBn3rCWixogsEAkps0sMPP6x8tlacoZZlS7hs5HLGYjFlEAeWXSy5XA7T09PYtGmTIlDGx8exsLCAbDZbYbIHUCE6FxYW0NPTg71791a4X/x+v66YCofDmrmeIpEIwuEwlpaWkMvl8Morr+ATn/hE3XavjssbHh5GKBSqOOAYqF6lCxexELkulwvpdBqpVAper7cqF5PWRCH+Jo7IEfnBfD5fRb8RucBEEHI0GoXX61WswrLLS8QNyqEOqVQKc3NzyiT7vve9T8lxJXKNqcWj2nKpN5GoF13C6jM3N6eIw3qpPbRcwrL7UbiA5OSj6sOd9epXawGqXtToifxaiL4wPDysbNLYvHlz1bFZ6jrS82oAqLKgqOtWJPIFloP0L126pGS0B5bdr2+//TZ27twJn8+n1IeIhxM7LiORCDweDzo6OtDV1YVXX30VyWSyYpNDuVxW4u7kZwmHw5ienobT6TQUzymEoegjwWDljvl0Ol0RxqIOyQGq5wi5nmq1R1HX6sVTIpHAyMhIzfcrWxg7Ozvh8/mUuESRE02gdu+Pjo5WHI6uDjsSlja7uCllKMh0ECJAmJKXlpbQ1dWFoaEhTExMKK4wrS3zWlvYtQbTRgSbaNRtbW2GMnwL5E4jW/bENWV3WK0DynO5nO4uSvEs6gPJtVZHahO26CS1rBsA4HA4Kv4v7vn6668rlr7e3l4kEgndMyRruduEmxaAEsMBoML1ZHRF53K50NfXVxGMrBdnqLXSFSkB1PERYrAT+azEYmFgYADd3d1KPF+pVFJSCMzMzKCtrU1xlczOziKbzSKbzcLj8SjulNHRUbz88ssol8s4e/asbruWcz2JwQ2AkgtOWCqMtE3RBuXBsrOzU3GruN1uzMzMVMU+CiuoLHLFjjX17lf5/ei5WCYnJ+F0OrG0tKQEkYs2MzY2hlwupyxQenp6FFelsCoBUOKjRJsXgnFychJLS0vo7u5GLpeD0+lU3m2hUKiI0xL9QiwERbsGllNFTExMYPfu3RX1p7Xoks8DjcfjVUHxeik2tNyPwvUpXEAiHYE62adeTJUW6om8mR3KsiWkp6cHADSPzRJoHUhezy2nrtuzZ88q7dXj8cDlclUcyi48BHfu3EF/f7+S2d7r9SKVSimpPIRLUiRzFXFmS0tLijgulUpVdRgOh/Gf//mfFedQAqgI39CyWLndbnR0dCj3Gx0dVRJqnz17tuJUBHVITigUqkh2K8YIdeJd8R61PEpAfQ+B1qJUjOPxeFzZxSv6tt4iQ/6eMArUcs/bzVpGQVYDh8OhCJK2tjZMT08jGo0qAxOAqnggI0GF8ueMDkLyAORwOJQdhOqYhHoxbPKqV753Ld/7yZMncf369QqRIFvn1Na7fD4Ph8OhJHzUEmlyzM7evXs1A4nFc4RCIfT39yufFwNuJBLBwsKCsnVcvCs9S4jWRCDqTK7f/v5+bN++XfPYF733FAgEagYjGzXxyykBgMr4CPkasmtYWLPEzrrXXntNEWalUkmJcdm2bRs2bdqEdDqN6elpRTwBy8ex3L59W6l7rTi3WOzdXE9iUkin08q7F2IRQJUgqteuxUQuguZFdvqurq6q2EdxXVnkih2o4kgbOcN7vfp3u90IhUKYnZ2tcB3+f/beLEbO674T/dXy1b4v3dXV1fuiJtmmyBZp0pRE0qIYxZLHicYGxoM7cyfj+BoYBIPkIRjkKUHyNMAE8+SXMTIzDgLEwthwtpElmtZCcbiK7GZTzWYv7KWqu/ala9+X+1D8//vU11VNxojsXFwdgCDZS9VX5zvfOf/lt1BbjPz27HY7Ll26BJ/Px8B1OriUSiV7QlKAQxZAwL5dkl6vh16vx/j4OAtUii0XsRpcLBZZNR4Arl+/DpPJBL1e3xMuYTabD/UD7bU/ZbNZGI3Gjp8RMYW9CAfi/P5jmHci3vCw6uVhvzs3N4dIJIJCoYD+/v4D8yL/LHSQy792mKehOLdnz57l6rBWqwUAtiBqNptcfabgXpRsoCSjWq0in89Dq9VyUJXJZDhQo70tFAodYJiGQiEuBIjEsGdhvUjLjkzgl5aWWC5DJA+53e4DFmQAuLMSCARY8kW+Rxx2nlmth8vTHHYeiRXACxcuPLNT020tiexXkQH8PHjeX/X4IiDrMSgIIEwQbco6nQ6NRoNZfISroNErsJEfTr02oV6BlfwwJtDt7du3u+KFDss+ur13t9474T/osFUq2+rW8uocvV5fXx9qtRoHTlevXoXZbMbe3h57kalUKjx48IAZT3t7e8hmszh//jxvdt3A5LSByOdFpVLBZDKhUqnwNYsHZa+goFtlioYkSQyglZe7DzsserUzD/u+vHLj9XoRCAQ6/Brlc3HY+7vdbgwMDDAhQ9QlAsDtTqPRCIvFApPJBIvFglu3brG+GbX/5PNVKBSg1Wr5MBkYGODWTF9fH4rFIqLRKJRKJVKpFMs8iK8hv4d0kFPmfefOnQ4fPLVaDbPZ3IF9FH+Xnol4PI5bt24B6KyiHjb/9Jmy2SwH0vPz83C73dDr9SgUCnxgJRIJliwQ35sqTSsrKx0BDh2elLip1Wpks1nY7XbodDpMTU0xoUdk8tH1U7WP2qT0940bN+B0OnsmB1br4X6g3fYnar/S/iEPUA7DFIrjMOadfC3RsxeNRjE7O9sTTtCtciIKJpMsTLPZxCuvvHLgd8WqfSwWw+rqKktIEO4UeD72MFkT0WE+MzODF198kQ3JRbFsakmL1da33nqLNeWIZTgyMgK/349SqcRs0JMnT6JcLh9gxlosFk48FAoF+vv7uU1JiYM84KF1+uDBA65ih0IhBINBDA4OQqlUcjs6Go3i6tWrXTG61WqVYQUAWDIkk8l0PVPkbUExeSKpk26/G4vF8ODBAxiNxgMELgown6dwQdUw8X1o/dDz2mw2sbi4+MyW/q9yfBGQ9RhixePevXvI5XIcbIgq5fLRK7B5nl57LyNh8ZqojUJZ2tbWFiKRCOr1OmZmZrpmH3IsXC/MiJgZEUiVNiCqthCYshuQMp1umwWTCWw8HmfPt3K5jJdeegnz8/NIpVIolUqQJInxF2azGQaDAeVyGbVaDevr6wdYjsB+6yaZTMJgMMDlcnHWODU1BaCzPQEcxIYAnQwtOkDlwF8ADDZ/nlbMLzO6VW6el/bfbVBGTBgvYB/YPTg4yEG2KP0gGg1TW5wCCaDzAJUkCa+88grfm1wuxzYojUaDKwfUmqMA5rC1HYlEkEwmodVqUavV4HA42AePANDZbLZrO4qeCZvNhvX1dfb2297ePqC7JWb9YsuObInsdjvy+TwHPWJ1qNd7U9ArT8DkgbXL5YLb7caJEycOrEV5YuByuRAOh1kcFQDDCui5Oyzg6VUNpPVB+5Pb7YbX64XRaMTm5iZ/Vrp/4rp5njXYqy0sriOxDWqz2RCJRLqyaOXrrlvlJB6Po1qtwmAwIJ/PY2FhAaFQCBcuXGDbH9IjFKuVjUaDsV/NZhPHjx9/Lpa8HLe4vb3NiSLtk36/n9fRysoKXw+tUwqWKbmnPWthYQH9/f0ol8uYn59HPp8/UGXU6/UYHh7ugAUQi5cIDvIqMq0Ht9vNexclLLROqKJqsVg6/Genp6extrbG70HJOLCPuSUppOdpCz5LUDcWiyEUCjHL2uVy4dSpU8+UPhHv22HvQ98fHR1FIBCAVqv9Z1cl+1wDsvfffx+///u/j0ajge9+97v4oz/6o47vf/LJJ/iDP/gDPHz4EO+88w6+9a1vfZ6X80uNeDyORCLBYEvafMkEV77xH7YZikP+cwB6GgmLQ2QXRSIR3pDIKqivr6/jYQwGg3xIERaOpBToQKbXFYMxwiooFApcvnwZzWYTs7OzsFgsHb8n/ywieYACVvIioyqjx+NBOp2GRqOB3W7nIIHmdmVlBeFw+ICSebnctmMplUocHPp8Pn5ogc5WqMViwe3bt/n/olaNfAOTYydEVfpisYhSqQSTyfRcIojPO3qRDwD8o9Spe90LESsor0qJWAvCMlEgJ2+VyLNft9uNkZERfg0CIM/MzGB+fh6FQgFGo5EB+QRcl69tACxPQoG4VqtlRXlaS6LMRLfngYLXqakpNBqNA1WCbi24fD6PVCqFyclJtiYiGxsx6HlWdYiqidVqtSMBA9pEDlE+ZWFh4cB9prkVAc9TU1PI5/N8QNP7GgwGRKPRZ1Zy6B7T64vvZbN1SlLs7e0hFApxpUmhUODcuXO/lL7dYXtft3tACVwvgPhhlfx0Os0BPGGw7HY7ms22Ifqnn37KWEdJkmAymdjtYHd3F0ajkavA8/PzeOutt55pqSZvvWWzWayursLr9UKpbCvyE+iccKTydUitVhFjNTU1xWB6qorSsyhWmmw2G8xmM/8cBT3kPkCVXAK8i4loL9gH0GbSE/6UkodkMol3332XK1okhkwBZDQa7WiJP09bUExgurUUV1dXkc1mkUwm0Wq1kEgkOtYy0E4Y6HMBvbF/3d5HfI4aDT0WFycwPz8MjcaAZ3AMfmXjh0THwgAAIABJREFUcwvIGo0Gfu/3fg9Xr16Fz+fD6dOn8Y1vfKODHTE8PIwf/vCH+PM///PP6zJ+6UEbSCqV4o261Woxi8vhcLC1hjxwelbrqtvPETWbWjVyFhMNse+/vb3NQRZlTN0OLTJWbrVaMBqNaDabyGazTHcmo2XKaHQ6HQs2Egunr68PR48e7TjI5ZkHvS+RB44fP447d+6whYgogNnf3w+v14uJiQn+PRGUrlQqmQa+sbHBgrMicFyhUKBSqfC8BAIBbG9vA2ivP4VC0SFnQBuDOIe0gcm1oMSDcmNjg7NKSZJ4k+ymt9Wr5Sz/urxiJCdX/LIUbWJhibIj3X5fftj1Yi0BvSsfNAf5fB6VSgV+vx+XL1/GvXv3cPHiRcZara6uotVqdZhkl0olLC4ucrvEbDZzdUzeLu6lpSUXiHS5XIyvkV8n3cudnR3WyqtUKnjy5AmGh4fxta99jatwovsBHVwU2IjzQvew1Wp1sIOfFx9KLdNSqYRAIACFQoHFxUUAbfaw3+/HwMAAjh07hvn5eW4pExP1sHVxmGjq3NwcM//o/mu1WjidTt4reu1hz8Kq9vo9+XqjQPfx48ddg2xK7g6r5AcCAUQiEQBthmM+n4fD4QCADqwj0F7ToVAI6XSaYSdAO1mUY1YP+5zUestms0yciEQiHc9vNpvF4uIit4MJcH8YxoqYgbT+UqlUV304qv4D+6QSch+gSq7FYsG1a9eQy+VQLpfx8ssvY2Zm5gDsQ85wnpmZYaFyar2KQsGZTAZGoxEej4fn5x/bFuy1l1D18PHjxzyPxAIVAzBqodbrdbjd7gP4ZJpTqmYSNEajseHqVeCjj8r48EMP5uf/H9RqapjNFVSrzzYt/1WNzy0gu3v3LiYnJzE+Pg4A+Pa3v42/+7u/69j4R0dHAYCzi39OgzYQj8fDlHWlUgm1Wg1Jkhh/UCqVsLKygkAgAKfT+Uv3o0l7hqwk5ubmEAwGudcvLjSqdun1eiiVSuTzeWaTyA8ti8UCq9XKVGrRX40CilQqBZ1Oh9HRUcRiMcTjcVQqFcTjcRgMBni9Xjx58gQA8PDhQ+zs7KC/v7/rRgZ0kgcIZA2AAaNidi5WnOh7t2/f5qoHzTsdICRNQAGyVqvlFu729jYfWkB7w9JqtYx529nZ4Tmhtg1hquQbCrUqE4kEVCoVNBoNKpUKSqUSb5LRaJR/j17jMG9Q2khI60cErpN+FGW73TaZXoM2x1KphKtXr3LA+vbbb/eUr5C3GIDe7dFelQ/a9EqlEh9+er0ePp+vIzApl8tIpVIwm80dJtliq4/a3MTek2uTdWOSUUBIbZRGo3HA+07EiVFbjp4Rk8kEs9mMo0ePYmZmhoPZ6elpBogDvVnC8qofva54Xd0SNvlaqVar7AlIVYGBgQGWt8lmsx3tdaPR+Mw1Ibbk6TV9Ph9rldH6rdVqHGxGIpED7a5e10xzIcqTHKY71229UXv9sPfoxtijvz/++GOGEej1eoyNjeHEiRN8b2kPJ5KOKMItMnm72QyJlXa5f6S8zSeXcqCARNyLu1X7xH1DrOSfPXsWzWaTW4aErRIFXUXvUDGho9fP5XLY3d1FvV7Hu+++C5PJdEDrTkwqi8UiDAYDB22lUgnvv/8+J/t6vR4KhYLbsN38THu1BaPRKG7fvo2hoSEMDg4eKjdy6dKlDuLE+vo6VlZWWLC51WqxtA9pHhaLRZhMpgPrttFQYGWlDzdvTuE737EglwMUCi36+rI4dWoBL764id/7vRcxOzvTc93+qsfnFpAFg0EMDQ3x/30+H+7cufN5vd0/2aCSKEXo5XIZQ0NDyOVy7Dtms7V90yKRCK5fv47NzU0GtI6OjnaVDDhsZDIZXL9+HbFYDECbHbWwsIB4PH5A+sBqtWJ6eho3btx4GvlroNPp+I94aFG1Ra/XM/aHDhraSEulEh+kJChpNpvhcrkQi8Vw8uRJ+Hw+PHnyBCsrK7h+/ToLW/p8vkPbJqSoLJbubTbbgeycNif6E4/HGSNGVG2qZo2MjHCLiEDla2trANrYCKKMUwVNNOR+/PgxHj9+DLvdjjNnznB1cG1tDcvLywdEBIH9rJEqDdPT09jd3WX8Cx1m6XSaMXPyVgVtfCTrQfdODlwXs91ntaXEIOzu3btMm6dNmURLex2ScqzF0tISHjx40FPhXqx8iEHR3Nwc3nvvPTQaDZb8oEGHEImmWiwWGAwGBlhTVi/HWspxj2IbUH5Yi+KR1IqRB8jE/hUdJ5rNtrCpyWTC4OBgh6QABbNilU6+VqnK2q2iLVqPiUxocYgHdLVaRalU4uC/VqtxAnTv3j1+v0QiAZ/P90wZFnlL3uVysQQDtcSo+k2tPAos5Bpe4qAgj+AHDx8+xIMHD54rAeiF7RHdLuTzQlVRUXxWtImivaxcbvvsut1ufq9eOEzxb1H8VvzMBPOQJAl7e3sHMEZUzQkEAlwFunfvHr8XrY1eQrTy53p9fZ2Dl1QqhWw2C5vNhsHBQSwvL7PtFn1empdeuDuqWFUqFT7D7t+/fwBqQYbklMRSJYvmmxjO9AwUi0VotVqWZCHD9l5tQZJsKRaL+Oyzz7C2tsZnGUEe5AG+z+fDb/3Wb/F+euvWLb4Po6OjUCgU3Fol6EOtVkOppMajR0rs7gJ37wKffKLF4uJvoVpVQ6er4dKlBP7FvyiiXP4IpVKEq47F4ljX9frrGooW1XT/icdPfvITvP/++/iLv/gLAMBf/dVf4c6dO/j+979/4Gd/53d+B1//+td7Ysh+8IMf4Ac/+AGAdpvgnXfe+TwumcGMarWaPdgoIq9UKtjb24MkSXA6ndDpdNjd3YXf7+eMT6FQwGKxdFCRn2fEYjFsbGxwRqXT6bgKpFAooNFoMDw8zJvP+vo6M8AIgE2gZK1WC7/fj1arhVqtBqVSyVUqj8fT0cYRfTQ1Gg1cLhfMZjMikQhvsiMjI9DpdMjn8wiHwwiHwwDA1SnKSAlXRuDWcrmMzc1NFjc0m80YHBxkAgLhjNRqNW8AlCFWKhWsrq5yUGQ0GhlwDoCDLpfLBa1Wy6+Zy+VQr9d5HpVKJSYmJtBsNpFIJFCpVHhOTCYTPB4PUqkU1Go1kskkZ4HyOdPpdPz56P2oTTU0NNTx/rQOzGYzxsfHeS7k9wwA0+XpOmjOxXVHvy9W87LZLKuTZzIZbs9S5ZMYsd3Ux+UjnW4zokqlEur1OgwGA6anpw9ULmhQwkLXarfb2Si40WhgcHAQarWamWziz3o8no61Jf+c4vOwtbXF93lsbIwrhpFIhOeE2lO1Wo2DCvF16OcbjQaSySQUCgVarRZr1lWrVXg8HvT19WF7exuhUIjFdqnKJ/8M9DzQ10lTanh4uAO3RfglmhNKRIhoIb4uBYf0HkqlEplMhg3lAbAB9cDAACqVyoHrkd/TSCTC+CKPx8PYTwK3E37KYDBw8kmvJz6L9G+FQsEBGc03YftoPmjOeo1yuYxEItFRObdarRgYGOj4mc3NTQ4cqcNCLULxuoF2tZPIJpIk9ZyT5x3lchmRSASRSISfT1p/8hEMBuH3+5kdaTabodfrD6xzup5MJsPteQpsFAoFtra2eO8gXUFKXmguKLAX75P8M4prKp/P81y1Wi2YzWYYjcaO3xPPAKANxxgaGur4rHQ/yuUyCoUCJEnivYUqWNVqFRqNBlNTU7wW6H4RNICCM5VKxe8hf57F8wmgc3EbyaQVyaQZRqMHSqUFmYwKfr8CyaQRqZQZ6bQNxeL+XEhSE5OTGQwM7GJ0NISxsWVYLCpOxAqFAoC2lNXMzMw/CR74WeMP//APOWg/bHxuFbLBwUFuEQHtQKqbYN/zjO9973v43ve+BwA4deoULl68+E9xiQeG3+/H9vY2ZmZmkE6nMTU1BaPRyJUmqiCRLczu7i5+9KMfcUCmUqngcDjw1a9+tWs1oRdGgbSHqMLhcDig1+s7KmT0mn6/nzWESqUSYydI/oFo91TmpkNWjlvohr958cUXOzAzYtvno48+wksvvcTVEALjulwubG9vIxKJ8GFCVii04VClze12Y2Fhga9t9Kl/HNCufABtAdqLFy/ipZde4lYImc3G43FEo1HGWRDb86233mLcwcbGBh4/fsybzuTkJLxeL27fvs2ZntVqhcvlwuzsLONBDAYDpqam2HNO7vVGmZxCoeD3e/z4MY4cOcIWSoFAAB6PB9VqFXNzcx3t+dnZ2Q6F+8N8ALuBoYE2EJ3miIRsC4UCYz00Gg1Onz4NrVb7zBYSvXYwGEQymWRRSpfLhSNHjnQAnLu1Ceke9vf3cyuf5mthYQEXL15EJpPB8PAwgH3Gq1i1ENeZ+O9gMIhoNApJklCr1TA7O8v4xW64qF6OFYTxKhaLHVIDDocDDoej4/6Gw2HGJOp0OszMzDCW7XlxgfJ7Ri3qU6dOwefz4eOPP+a9S5wbAAyCXltb66ioabVaKJVKrsQR1q6/v58PcY/H06HB1a3yQGuYcJh6vZ69bMfHxzlB8ng8mJ+f71hvarUahUIBLpcLLpcLu7u7GBoaQrVaRSwW4wTm4sWLPT056V5QomkwGOBwOKDRaDr2893dXcRiMX5OyIOWSFUmk4nZppR4UPWIKq8Oh+O5khH5oHkzGAzcbegmgEpjeXkZyWSS52pwcBCSJDGTVlzbwWAQiUQCJpMJtVqNCWKFQgE2m42TxVarBUmSEI/H8eqrr/KzJuLuelnnEb6Kns1cLodSqYRqtcpkhCNHjvAzZjKZWCuSYAdKpRInT57swDZTwLa9vQ2XywWNRoMTJ05ApVJhdXWV7+ns7CxbuGk0GraXWl9f52CaKnZ9fX2YnJzsiZddWQH+9m8r+OEPG8hkDJAPrbYGhyMLqzWNI0ey8PnquHBhFC++aMDsrBIajR2ZjBKrqyUsL9s5oXY6nTh9+jSazSYmJiae297tVzU+t4Ds9OnTWF9fx9bWFgYHB/HOO+/gr//6rz+vt/snGTbbvq2EnMVCWYeoJE/6SKFQCADgdrvx2muvdW2ZiDZEohk3YYp8Ph/y+TwUCgUuXbrEPwfgAIZMp9PBbrczLV6k5wP7lHU5tkBedqeyfrFYxPb2dgcWQO5RF4lEoFQqcfHiRczPz/MG8ujRow5LEbE1SZo3RBH3eDwd10abZre20MjICG/uuVyONWzowaYgksrndL1msxnxeBz5fB57e3tYXl5GIBDA2bNnMTo6iuXlZa7IkAyE3ARZPmfU/jEajQx6HhkZwdbWFrciKPgE9rW+RHwZyXrk83nO0HqZgotDbOGIdHBqbdC9J3bh8ePHnwuMLa7NTCbDWKZuOlDyNiFR1AnUrFQqDwDN5b8nF9gV/98NdC4ywiwWC7foqO1FwXm3dgm9P+HUJElizSXC6Ij31+/3Q6/X4+jRowiHw9BoNIwnE3Ex8iFWxMT/EwZULpLaa06np6dRLBb5XtNhrdFocO7cOayuriIcDqPZbGJlZQUA+HmMRqNYWFjA8PAwYzS7Yf5EnapCodBBViIsjlKphN1u52CNCBAul4v3GZpPqrq89NJLLFAs+qmKgSCxHjOZDLRaLcxmM3cSVlZW+DkhXB6RDAwGAxN6zGYzV7nJdkilUrEjRblcxvb2NjKZDM/PP5YQI2+xj8oMx+VjcHAQXq+XBVcLhQIajQZKpRL76XYT4hUxfdSu1mq1kCQJANitAkAHML0bk1wMFkUgO0kcAWDyF5FHbt68ycm+y+XC0aNHEQgEYLFY0Gx2OmwQi1hM+ihYpWCMHFJECzd6Lt1uN6ampnDnzh0sLi6iXtfgyhU93nsvCZutiFOnzqFebwIw4Uc/MiCTAf7+74GbNwGVSouzZxPw+a5jeLiKVisDm02NM2dewGefXUO5XGL3jNdffx16fRw2mw2lEvDkSfvstFgsSKVSDH9Qq9UYHh5+JqP21zU+t4BMrVbj+9//Pt544w00Gg185zvfwbFjx/DHf/zHOHXqFL7xjW/g008/xdtvv429vT38wz/8A/7kT/4Ejx49+rwu6ZnDarViZGQER44cYXwAgdf39vYO+OQB7Rve19d3QDgS2AdNEnbogw8+4FJ9IpHgbHV+fh7nz5/vCV6VX6PczoOCHjHI6HXAd9Nt8fv9jIsSDzdRWJGELScnJ3Hp0iXMz88z9ZuyMFHI1Go9qM7cC/fQDV8hHloi0B1oGzjH4/EDbDqgrVNWKBSYvabRaBgUferUqQNinDabjbFj3cDJmUwG9+7dY79MylDFQcync+fOIRKJMCZLBLrSZl+pVDqCeqA7aJyGODdiC8nr9bKAqSRJKBaLOHXqVM9gTJ4YUKtHo9FArVZzZU9Ome+G6RFBzdR6kAPN5b9HtH6iwm9sbPD3t7e3UavVMDQ0xOuEwMVy1unc3FxHcA7gAChbfH+LxYJqtYqZmRm43e6uzwTNMf08Vd26aRTJ9cx6ebB2E0ntNjexWIwDx1qtBoPBwFgyage++OKLLBRL65BandT6AnDgMKXngaRFCFNGe5bRaEQikWBmM7lrkC5fs9lkFq1KpcLly5c5EOpVoRHvORlXUzCi0WhY2FSSJKyvr0OpVLIYKYAOXB4xTWOxGCKRCDO9qXp99epVNmm3WCzI5/NcNRfnQsSeHUa6kj9rolF4t/2Uktp0Oo3d3V3cvHmTnU0IRE/3Wi7ES+uAAvKtrS2oVCqkUinWTetGdnsWvg0AY3ypkjg7O4s7d+5gb28Pn376KZrNJt9Han8XCgVOdEX3F1F2hu4/zYPX64VCoeDEMJ1Ow2y2oF5Xd+zlFosVoZATf/M3F3D//ouoVrVd55/GzAzwX/4L8G/+DVCvl/E3f7PGga7RaEQwWEGlUmYHi729Pdy8eRMOhwP1eh21Wg3xeJw/Jz3TlPzF43EUCoWu3aBf9/hcdcjefPNNvPnmmx1f+7M/+zP+9+nTpznr/+c04vE47t27x0rQAwMDrNwtryJQdUQUjqTsWq1Wc9lYr9ej1WpxgEKWQoSj6mYOe9hGQP/vBl6lLFE+uolzAgfFT5PJJGNqCPhJ17q8vIyzZ8+yh5tOp8O5c+e4JCxueHL/RjEIkm908kCNSuXk3UkaZDqdjnFr3QCtn3zyCVd8gH35C3HugIPgcLn/Gb1+PB5HPB7nzdFoNDJGrVwuH3gdkkyQa8lR9iq3hwJ6Wz3R9fbSFaO1SpVVakHJhzwx+OSTT3D+/PkDlT2RMi+viIkbLIGaI5FIT8FceZBNQqmiGThd297eHhQKBdbX15nlJyYL3QK7Z1UxaL6Xl5cZ5/Xaa68dqGbRoKCatOtE3z2LxcItcZENRwlHNw/Ww0Dc4veo6kSBrV6vZ/IQDXqOUqkUrz1iS5dKpQN2VXIyg9lsRi6Xw8jICOvF0TwSFqxWq6HRaCCXyzE0w+v1IhaLcZtKr9cfWlmQfy5KmkQfTNK7MxqN3O6j/YXakCQKPDQ0hPv37zMutF6vd0ii9Pf3Q6PRsJ0dtQJXV1cxNjbGcyFCM0jXsFfXQL4PPUvChP79i1/8gi3jGo0GE2rECrpcp44q80RgovW0sLCAVqvFwZBcrJpg33L4N5EJiNQD7GPvKDijwIawifR3q9WC1+tFq9VCNpuF3+9nAd992Zl9IfRSCdjd9cHv/7/x4Yc1+P0SqlUJlYqEWm0GbncNZnMTtZqEXK6JdPolqFQNzM4+wokTi5iYKKHVkjA2dgapVAwaTQ16fROXLp2Fz2fF/pbtw9tvv42lpSUkk0nUajXo9XrGetK+TIH4zs4OJ5tUOdVqtejr62Ms3s2bN7k6SOv/l5EY+jzGF0r9wshkMvD7/djZ2eF+N91Yh8MBn8+HYrHYwUSSP8DE1qKFb7fbUavVGI9Qq9WQSCSYESSyI+XX8jxaRvJ2ymHSC3KaPmWwVIUiHMGVK1cYv3Ps2DGYTCa2+aCgxWq1wmg0dojidrs2uWBstyCIrlPc7EWmGmXAdCj2MjgXmW/UBiB7oMOETkX/yHK53DEvmUymg72p0Wj4XlFlQnydw7TkpqenOTgVD2mxLUFfkwfj5Jzg9Xo7Wp0E0lYqlT1Nwdtl/FJHhVesVooVDwreALAGXbeqZq+2nPh9+e/JRTUJA9lqtdDf39+1QtctsCN2q1jF6Lb2+vv7sbq6CpVKhd3dXfz85z/vwI71OnDF60wmk7hy5QrMZjNKpRL29vaY2Tk6OtrTg7Xb5z/suaDPNzIy0qHFRLI1VJUkSAAA2O12zMzMHPBxpCCWkhmDwcB6bxaL5YBt0+3btxkEXi6Xn7LW9m2JxDaVOLpV2+fm5rCxscGK67FYDLVajX0XgXYLjSrqtVqtQ0RVFOINBoOcWNGhKSY4VAkjwg+1vpvNJkafepmKiR3QxnrRmpVXNeneiPdK7ughT5hoP6HnirweSRT5sHUgBlB0T1dWVjjxpzaxGNTbbDZ4vV4OYMV9TQz+ms0mJ9T0h75uszkQCtmxtOTG+roLJpMGOl0CY2N1DA1VsLoaQzptxOamHoHAHFIpMzIZHTIZLZRKQKls4WlxCgqFBdPTRYyO7sBkakCpLGN83IHtbRXKZRW02ib6+oyw2TYwMrIESWqLvrrdbphMJhw9CqytidqPaSgUnfNrNpsxPDyMfD6PXC4Hh8OB8+fP46OPPkKz2fbqJbY9tfyJ0ED72tTUFAt7i2uBZHq6JcO/jvFFQCaMdLptnmyz2RAOh7m6IkkSYrEYa2BZLJaOzUh8oMi0WafTcRlYkiQ0Gg3Mzs5iaWkJjUaD/RK72QPRtRxWOTnsM8h/D0CHOCcFCwC4jSSKn5IMRq1W42Cl2WzbdFitVty4cYNlJTwez6HX9axKR6/PR+QGoN12SafTrFT+85//nNlGZPYMdOLrzGYz5ubmuhoO08ZFwNdGo8F4GZVKhfHx8Q5JApfLxS0dESNIWZo8WKAMX9TUoooFUdrpcxFrTRxyHaTZ2dmu+mLUQiTGmXhYyw8A2oTECm83bJQohwIcpMKLo5d3YSaTwd27d+H1evl74XAYOzs7qFar3OKge5NIJBCJRJjBJQ+Q5AdaL+C4fNBrqNVqVCoVVKvVA9dKAaioGSaKf4bDYfYlVCqVHYxqg8GA8+fP99Sz6oU9k39P/DzBYBA2mw0ajYbnin7e6/Xi5s2baDab/IyeOHGiZwtWrH52s3ETq+xUDf7kk0+QzWa5UuLxeDA7O9tRfe+WYFG1/dNPF/D4sQLLy3ZotQoolUasrZmh1b6An/wkAYOhCYNhBJOTHrjdOmxuPoTB0ITf34LBoIPNNohGw4rd3SwaDfD6IOYuza88qL1y5QozIwl/RnNBATQ9w7TO5VVN+ejm6NFNcsRmszGLvFxuC7E+D1hcnmwA+y1bah/KoSyZTIaTFvm5Ic5JPB7HysoKB5I+nw8PHjhw9eoRrK31o1DQPr2GNBQKJTKZUTSbnS1SpbKJ/v4s+vsLOH68DoVi+2lgV4fBUMPERBlHj6YxO+vGlStXOHh+8cUXkU6nO4LsJ0/CKJeNqNe1HfuyaL32rMIEPSuTk5MYHBxEX18fw0wikQjbT4VCIa74kosIYRzpfioUClitVpaDOUxi6Fc5vgjIhGGz2ZhpRQ+0UqmEJElMG6ZNshcgeXp6mgkAlOGQACW1IlwuF9bW1tisthv79LCWx7M+g/h7ZAFULu+Lc6rVagZOP3nypEP8lKojVBoeHx9HOp1GNpuFTqfjw4No9IdpXdHoJvIptyqSfz7CU7RarQOladJra7Va+PDDD/Haa6/xptWt5SBvU1Em/7Of/QyxWIwB0yaTidsAIpbk3LlzXStyOp2OGaXdggUAHaV/oB0kkFvChx9+iEqlgkKh0OFDWigUOLsl8U7ROYEkUqgNQRuMSqVCPB7Hp59+2lGGpyCdMBaHaU3R56S102g0eiYDom0Qbaa7u7tYXV3lAJxAvtvb2x1yFy+//DLW1tZY4JgqCmSvJQZOFAyK9/F5kpOJiQk8ePCAA0cKwMT11k0zjA62Bw8eYHd3F9VqlStjkiRBp9PB5XLxgSjqWdE979aW7zXo81AAkE6nGeawvLzM7yO/N0qlssNah+aInoNgMIjx8fGeSZ/4/iaTFUajDffv32fmrkKhQDKZxMLCAj9/tJfkcjloNDq4XEPY3i7jf/7PGv7X/9Lh3r2voVbrdax02ycu9fhZC5TKGVitPvh8aUxNJWG1OrG8nMPMDGC3d7qDvPHGGx0sZtpTrVYrzp49i0ePHiEYDLJQqVKpZJV+uRE2DapgkQbi6OhoV1Yg7Se9MKjPUujf2NiA0Whk2Ra73Y5qtXqgeieHnHQ7N+h6bDYbQqEQtreVuH17Cvfvj2NpSQ+Xq4JTp3YwMRHEkSNxqNVt9YNisQaT6RiKRS+2tp5AkhLQagM4enSCA7pbt26h0WigWq2ir6/vqZB4BrFYu+JFzy5VpSmI7YVrJkHcYrHIFXv5GhUrlGSrJOpGEkv/9u3bjDmkjkKz2RYSp2ujoojb7YZSqYTT6eTOy/8vMGT/XxtWaxvUPzw8jOXlZVQqFZTLZZw8eRK7u7tcTQL2cT+EgTObzYhGo7Db7ejr60Mmk+FNrVxuK/pbLBYEAgHs7Oww0LNXGRxoZ7WFQgETExMAuptk0+iFx6LDuK+vj/36rFYri/SJYo0UYM7MzCCXy3XQ4FOpFCwWC6anpxEIBNg0nA7SXqOXyOezKh0k66DRaJBOp1GpVLhCSfZJkiShWq12KFh3Y4jS5xLfmwytKVCiwI+wO8/r5ScPDsTDVXzvWq2GaDSKSqWCYDDIuB5JklAqlRCJRGAymbiqSlptzWYTgUAAjUaDJRlCoRD29vagVCpZoDiZTDLjTh7gEbtK1LnqNai1Tptrt6yV5rabzyTpx1ksFiSTSeTzeUiShHq9DqVSyfp4er2e1969e/eQyWRgMpm6BuqHteEPu0c+nw/f/OY3O+Rt8AzbAAAgAElEQVRTqKKSTqe5GuhwODjZIowWVWWBduBdr9dZf3BqaqprqzSXy3Uc2NPT0zxHzaYR4bADoRCQTAIaDTA0BBw/Dng8QKUCBAIZKJVqmExjyOeD8HrdHW1Q8d7U6y3k80Z89tljaLUqQXpHjWDQgmh0Dv/wD25EIga0WsCRI1q4XIDRCAwPl5HNllEq6RGNanHnDtDmR1hhMv0utNosLJYMHI4UdLryUxJBFm63BbncMeTzNeztabG15UOtJvHnd7tzOHNmAcPDcRw71q5QlMsqtFpl6HQxKJVVlEoqWCyDGB4+imJRhY2NKDyeSSQSFWg0dhSLSuzsLKJYLCOXsyKVsiAWG8RPfzqMn/60/T5qdQMeTxP1uhKFAlCvA0ajD319/xecziJ8vhqKRTVGRnJYX0/h44+ziMdHEIuNodm0QK2uwG7PY2SkjMHBAmKxdVgseRgMWly+fBkAeJ2IGGGDwdC1qk/PgohBpbUhdixisRhWV1c7yAIiKWtgYACzs7PIZrPQarUHAjuCnEiSFhpNPyKRDCoVK3Z2gJ0dYHcX8PuB7W1ga8uKra2vI5VqP+snTtTx3e9+hgsXVrG3F+bkTKPpf1oNTUKvX4XV6sd3vjOHbNaK5eUKQyxIpiSZTDLJTZIkxu5ls1kuXjQaDXi9XoYg0GeVj2AwiN3dXSby3Lx5EyaTiQMkoF2hJ104YoGSJV65XMby8jLcbjcqlQo8Hg+KxSLGxsYY2ylJUoebSzQahcPhQCqVQn9/f0/JnF/X+CIgkw0C61osFnzyyScwm83Y3NzEqGASDABPnjzhCkqxWGQ/yLt378Lj8TBrzel0cga+tLTEoorETulVphWBqH6/n6+t2wLqBtanoIRKwkR1J+YUWaYQPVvMYHK5HFZWVqBWq9kmo9ls8vuaTKaObPCwg1FUoabg53kWP7HMarUa4wbK5TLcbneHawL5EhL1WtzwaDMkfScS/p2bm8Pdu3eZpUODwN/r6+uYmprqaEU/7wNLjC4CNJMCel9fHxqNBgdibrebM0m9Xo+BgQHkcjmsra2xOwFtPpIkMX6RnAro2rLZLLa3txnYTNpCkUgEDocDNpsN0WiUgbDUNu01rNZOlXOLxdJ1DsRAn1qnANhomQJ2wq6IxArC4VEmu7e3h0ajgXw+j0gkgunpaZZS6NbuJkuxxcVFVt+XY+fENfnlL3+54zNSlScUCnEQTJUvSrIIB0ripUqlErlcDrlcjrNyep+PP76GdFqNaLSJXE6HZtOCVKqJ//bfyggEziIcdiGZ7E646BzDUCiG0Gq150qlasBmq2BgQAG7vY5Wy4py+bcRiTQRiUio1xWQpAY8ngrU6hKqVRVSKRNKpfa2PjSUxfHjOVQqNaTTfQiHW0ilmkgkdFAotDAaa/B6G/iN31BhfByoVst4+DCEeFyBcFiLlZUZlMtaKBTta9Fo2n8DVeh0VXz5y0uYnbXi2DEPLBY/dnf/FipVG9R++vSXmaVKOMG2gHUZFksC4fCVp6w5IJ+/AbNZekpuMMJojHNQq9PpMDQ0hExGgZ0dN9JpFzY3FVCpBmG3G6BSlWEwaFGraREINLG62sCnn5rxox9RoNgm6BgMVRgMWej1VdTrJjx+7MMHH+wTURSKFvT6MlwuBfT6IoaGWnj99S386389h1ZrP0BYX3+Czc0Sdnf7sLLSh709IJMBtFo3pqfzcDrTSCbTSKWsWF8H/H43njwZBFBGLqdBX18e164t4itfOYlEoohr1/oQDA6i0VDCam3io4+ScDiUqFRasNtzyGTM2NwEHjxQ4OHDiwiF9EgmzT2rkFotMDoKDA3VMDNTxpe+pMa/+ld6jI6qkckMY3W1hO3t/ed2enqa9ebEZ5mSV7H6euvWLZTLZej1ejgcDsZEO51Oxm0ZDAaW7KDuTy/fXko8CbKRSCTw85//nDGLo6OjiEajqNfrTOxotVrY2NiAUqmE2WyG3+/nFq1erwcA3utJasjr9bJILb0GSTV1Yyb/OscXAVmPQW0OnU6HlZUV7O3twW63c4VFrKA8ePAAiUSCqdflcpmDLgrASL2Z6P1ks9Qt0xZxLY1Gg1W3jUYjM/fo50qlEm7cuIFMJgNJkuBwOA5kbqTortVqsbe3x0GZ6PsoVnYoEyOwJOGe6DpFRe7DfN92d3dx//59lEolBj7TyGQy+NnPfsbq5W+++WZHKVu8boPBAKPRCKCN3env74fFYsH4+Dh2d3cRj8eRTqd5vp88eYLz589ze4esNqjsfevWLaRSqY45lyQJBoOBMzwR2P+8DBwxkCacjwis1el0aLVasFgsGBkZYTVvl8uFoaEh9q3L5/Ow2+28YVEwYzQaMTw83GF+XSwWGe9ITDRJkuD1enHmzBnGHqlUqg7A8WFBtLgWDtM8IhyeyLL0+XwYGxuDRqPpUJv3+XzMCDx37hy/DmEuSVblzp07TIIJBAK4fPkybLZOfaXl5WV2jrBYLAfo/4e1iSiQBNoMM6ra9ff3Mx7rwYMH3CIGwHIZCoUGn32Ww1/+ZQL5vBqt1iRWVoCVlcvIZPQH1kMbg5PG8HAEr722hSNHGvj2t+fgcgHVKrC4mMf8fAWplASNpgGTSYdMRgGDoY1X292t48mTPDIZPZJJNZxOKxwONUZHq3C7sxgYaGJ+PolYTI9iUQWNpowTJ5IYG8vh3/7bfgQCNw7gEKvVKvL5FmZmRlEq5Tv8H1dXV3Hs2Dpre5nNZiwtLfFz9/bbbzMonhKsS5cu4ehRA65diyEUAnuaFotFFroGwBVeYp5T8kP3QqVSoVAodDBw1Wo1vvzlL2N4eFiQ+HmIqanuDLl0Oo07d+5AqdTiwQM1ikUj3G4DgPtQqXIs+Gyz2SBJGpTLDqyvK7CxoUaxaEU2q4EkeZBIKPB//s8QfvGLUfzn/9zA3JwKdjsQDgPLy19HOr1fYW5DMy2oVr/CX1OpWti3sTQAON1jxzADGOjxvbb0Aw2TyQy3u4WhoRxeeimML33JiWAwCa22DperjDfeOIrBwSbU6j1IUicb2G6/DKD9TJPl0/b2NuOhyUFF3s4X94H19XWk022bonq9zl9PpVJsmUZt9ZdffhlOp5NfRySTib69ZNNH3Q8AnFTu7e3BbDbz+qFqJZ0FlCDRZ8jn87DZ2k42IlaaZH38fj+fD7Sn9sKt/TrHFwFZj0EHTiQSYcZGoVDgygH9bbPZMDExgYcPH/LPTU9Pw+l0shwEiTJSIEX0/l4MMRGISrR4OtjUajVKpRIWFxdRLpcRCAQYY0RVJeqlE+2X9HmoUqHVallludlsduBLCDehVquRyWS4LEyWL/IhVsDoYKT5uXXrFktQkKBqsVjkB3xrawtAW7phfX0dp06d4mug66a2Wy6Xg0qlwtzcHHK5HI4fPw69Xo9wONxhgZTP51EqlXDlyhW8/PLLmJycZOFbooATY5L0nAgbRAeEvC39vKQKMZCmQVYhBG4F2uzFpaUl6PV61Ot1nD17FmazuaPqSoKo1EKmiuXa2lqHcG0wGOT2rVLZtnDRarUdVTCfr00dJ6wKcLj2GY1umkf0OW02G7Msq9Uqrly5gpMnT0Kn0yEejzPxxWq1olqtYnx8HDs7O/wZyC6HMHTUciOSBVXZ1tfXYTAYOIumoFK0zqnX61hfX4fFYunQfup27yi4I3xiO4BQwOVy8yFDrhmxWByFghfR6AX87GdKPHrkRKOxfxjr9RV4PBVMTQUxM1OEzVaB0ViG06kCkEVfXxF6vZJbuisrK/B6J/h96vVrmJ4ucxuFQNyU7Pj9fiwsPODPcfLkSdhsto579+///RwajTpsNtPTe1OHzdb25wsE9u8lVemtVisqlRi2ttrJRiKRgN/vh8FgQKVSQSAQYI2qCxcuYHp6Gtvb2xgdHcXMzAwymQzb7Yh6VRMTE1hYWGDV/BdeeAE3btzgYJ0YzwMDA1hdXe0w3qbnUKlsOxIQhk2tVjMbnUzgif1KIrF0CFOLkT6ny9Vk9mkmY0CtJrFPbKVSAQAMDgJmcwZHjpTQarVJPWfOnMHS0hL29upYWhpDMnkSGxsqhELt1vLbb9cwMlLAyZManDljQl8fsLERwE9/uoJAwI1oVIv+fh9OnLBiaqr9O9UqEAhEcfXqddRqSjQaarz00jl4PC44nTmo1UFIUguAFbduPUY+r0IwWMCpUxcxPW3ExATgdCqQzQLpdAM2W7tytbCwxmujr8+Ex4/3meHUWmw2mwe0yroxs3tBNCi5oQqT0+lEoVCAXq9HJBLh+0Xrp1KpYGVlhYkSfr+/g/neaDRgtVpZ5+/o0aPY3Nzk84Gqa61WC06nE16vl+36aL05HI4Oc3MK6ul8JdFiq9WKmZkZfPzxx4xDdrvdOHr0KLxeL+Nw/7FdkM9zfBGQyUa5vG8uTirM9HWqnCwvL3f0/S9fvswHnt/vh9/vRzQaxeXLl+Hz+WCxWLC0tMQlXbl0hnyIbSMKJtoHRAw6nY5xKQA4C6UyrNls7rB5ouqUXq/nzEOlUqFUKmFtbQ1bW1vw+Xw4e/Ysstkss8kosxgeHoZarWawPw1qzd2/f5/p8tS+vXbtGlKpFAt3UtCjUqmwsrLCc1erNZ6yNVsdFSs6NEmVG2ir09frddy9e5f1oc6cOdPBhiWFa2r3vfvuu3A6nWxVRI4KWq2W5SwIeG4ymXq2pcWssRtIW2Se0UZDGEGDwcA4DFKnJ6HM4eFhJon4fL4DemOikbLIZpRr1hENnqRKTCYT8vn8gY04GAxyQCRqX4kVVfocFDyLmkd0bykY8Hq9KBaLSCSSSCYNuHNnCUajG5mMG/39w1hfz6Feb8FikTAzk8L4+P57rq+v49GjR5xkkKk2tbeAdkC8vLwMpVLJKufE0FSr1dDr9dBoNMjn89ja2uKKWrPZRKlUQj6f7wEJ0OD+/WO4d68Pfr8P6bQBKhUwMtLAiRNlWK0vIBb7Mu7ccSEeb8/fCy808M1vBqFUPoLdnoDVGoPNVofZ3JaEMZvNTFTYl3Z5hTf9+fl5RCIRXLt2rYNoQVXweDyORqOBDz74AL/927/NmDE5sUfOCpWbb9OgxIoCVHKZyGazjKuhCiyJrtpsNuj1erjdbq4Uz8zMYGBgAOl0mgNs2ptEk/ALFy7gW9/6Vgdej3THgPYhSgkTPdNAmzzjcDhARu8+nw937tzhYOLu3buwWCwslUP6h0RgoeoMrVnCnVarVczOzrKQM0l7EMOdkryBgQGcOXOG91SClej1Dbz66g4uX56B1arh+d1n/Cmh012AQmGF223DzEwF09OBpwmOD/Kt3WIpI52u8P9feaWAkREX2lWyGf76+LgR6XQajx8/xm/+prHjNcSkmSpGIkOTkpBEIsEszVarxXpvJPQtktYomBWdBQh+Qy1LgiYkEgnk83lei+FwmMlgVK2nCqmIe9TpdDCZTHz+RaNRhMNhLjRcunSpq86fx+NhSzuDwQCLxYJ79+51JJB0jcQqNZvN2NraQqvV4vOAAn2SWhGDsV7WTb+u8UVAJoxMJoPNzU1EIhEWq6TSOo3V1VXodLoDVkEjIyPIZrNYXFyERqNBKpXiA3V+fh65XA7hcJizT6og9FKQFh8+j8eDUCgESZLQ19eHYDCIXC7HBxeZ4NLmTpiqcrmMY8eO8QGsVCpZ0HNra4sDl3Q6jQ8++ICDFKvVylWt7e1tDA4Owm63d8wTBV0UfFBVo1Qqodlse9W1y8J2+P0mFIs+RKNW1GoDiMc1SKX0SKXegiTV4POFsL2tRa0GnD4NuN1WlhNotVqIxWLI5/MdlbZqtYr5+Xk0Gg0GljcaDdRqNdYmqlQqrL+UzWa5XJ/L5eDz+TAyMnJAw0kc3RibYgvPZDJhZWUFN27cYAYqgXKr1SokSeoQoRQP01qtho2NDUiS1MGkE9tu1DKl6pEc6E4b89GjRxnHGI/HOTsmyQqg3TYg6RZR+FapVMJqtWFzM4uf/OQhNjb0ePhQB61Wgt2ug8VyBn19IQwPJ9mCpK+vD+FwHO+/H8L8/DBu334L4XDv1gsNp7OAy5cDePPNPSwuLrLOFd1DCmibzSYHW1QppLVGxJJsNovjx49jZWUV2WyOg9AbN27AbDYjFotBrbYgEDDD72/go49q2NurIxLRYXPzGwAAm62Es2cLmJ1VodkEPvkkjf/9v52oVPohSXUcP57Ef/pPGvzLf6mH05lHMJjDrVtBDgLqdbC2G103CcyKMhGkHyYqyIvSFPV6nSt/e3t7WF9f5zapfA2Gw2FW66dARHwm6fXkgr5kop7P56HVajs8cGlvoGsQ8XS92r8U8MnZsGJ1T6/XY3Z2lm2edDodcrkc+vr64HQ62a3kjTfe4M9ITEhyn6hWq6hWq6yJR2zGSqXCgqfNZhPZbBaDg4M8x7RuxEocYU51Oh0zJ48ePYpms8mEnnS6LX1EVW2xutqr8iqHsPRiJFNVVmzLygf9LlmadatWiVqOIgCeEkiSJKLPvr6+jrGxMczPz3dI49DzRlIecucXl8uFqakprmz19/dzwpfJZOB2u9mybXx8HNeuXUOj0eDngz4PaehJksSYWjqv6OygORULA7dv3z4g2vrkyZOuJCpilWazWahUKvT19XEwRteiVLZ9OikIEx1gnrcL8nmPLwIyYVCgQwy3NghVzew+6jtTz5sWtJiBE96H/qaH2Gg0Qq/Xs+p1NpvF9evXOwKyV199teMBkz98pIyeSqWYJUPZK9BenPLsj0QgCQTt9/tRqVSgVCoZd0TVL8oyyV2ARPZKpRIMBgOzPImKTJnuPgBfgZ/8JINAYBR+vwsbG28im91vdWo0dbjdJTgcRRw9moYkxVEsSgiFRvCXf+nA//gf7Z+z24HpaR9GR78FszmBcHgDanUdRmMRPl8ISmUBgIRaTYt6XYLTqUajsceldMriaOMTN2UaBoMBExMTh1Ke5QxKeQuPdG0oY/f5fIhGowwSTyQSyGazrBtEWlwUWFJFQA4szWQyePDgAVKpFDwezwHBTFobpMTe39/PhzqtU6AdLKyursJkMqHZbGFnx4hMRgtJ0sHnexXFog5bW0b87u9q0LbXexUAoNcXoVIBhYKeAeZKZRNudwomUxn1uhGRiBmVSnv7cLkS+PrXfwGXKw6TSYFGowqLRf9UBLKGbFaHYvEYNjbm8M47R/D++2OYm1uBx7MGk6mActmIcnkayaQEtVqDZrOd3fb3a+H1rsPpzMNoHMXg4Azu3nXjT/+0jFDIC52ujmh0HNXqW9Bqq2i1lHA6yzAaGwiFdMjl9isMbncBLlcJdnsV3/52CqdOxTExkcNXv3oBVqsOfr8fr766AKvVhtXVLMbH7fD5nBgc1AGo8rNIrWH6QwlCPB7H4uIi9Ho9V0PX19exvLzMhzFVg6hNQgfqwMBAR1WI3AFE1jBVLj799FNe11RZon1GdA2Q27Gl02kmj6TTafh8Pm73iGb3pVLpUEKFWPk4TJZHDDip2k7uCvV6vSNApZ9Pp9Pc1iyXyzAYDEgmk4jH4wDABzTBN2jvqdVqSCaTMBqNPKditYUCfiJwiO9PiQzpzZG+m+gaQUOlUjH0RNRE67ZXyAf5cYqt9m5D9A6mamqvgFBeKRc1yPb29rhN12w2sbS0xMkU0Lafc7vd7ExB80QYK8JsVioVDgxVKhVMJhMHMEePHuU9KZ1u6/dRdVL8fCJ2bWdnhytW5XKZ9056vkgsutlsIpfLYWpq6lAlAvE9iLVN5xwFewRzGR0dhV6vRyAQgM1m4xZ2rzX86xhfBGRdBgVgVILVaDQwGAwolUqsSTY2Nga3243BwUFWURc3E1EnhjYmei3aCILBIG8sOzs7+PDDD3kj9nq9HYbW5CNJm5PIkhHH0tIS039HR0c54CsWi4yfIhVoyi51Oh2y2SxjzMi0XLRnefJkA+l0A6mUhFhMiUjEhlzOgGx2DI1GE7GYDevrk6hUdFAoWhgYyGBmJgy3OwCvN47jx3X4xjdOIZ/PsjG0VqvF7u4u+vs3cfz4VxAKDWJhAVhfB5aX67h+XYlQyAvgcGkNANBqazCZCjCbcwBaqNcNqFS0kKQm9PoGfvxjCxSKGgqFV9BqaREKqVGvK6FWt0G4JlMDxWK7UnLyJPD668CFC8DYGGC1gq08xApdoVDg9m4bLJ3njU2h0CKT0WB9fQ9udwYaDXDnzh2eY2ozb25ussUKsE8M2N3dRalU4sNzYGAQlYoV9+4Bjx7F8eTJIDSaJtJpA8xmD1IpNaLRFhIJBSoVCYAClYoRlYoVhYIGhcIkymXNgXmzWFr4zd+sYmwsBYViAzZbBI3GGqxWC4rFCmo1N7a27NjYsCOR8KBaNcLrBV5/vQSjcRkWywpstiRMJiPGx8efWoJVoVY3kUjkn1ZRMrh4UQOPJ4H/+l9v4cqVOVy7NotG40THtRgMFahUSrRaTSgUQLEoodH4yoFrdjozGBmJo1BQ4tSpIMxmIJ9XwOl0IBAACgUFjhwJweXKYmCghOHhIsbGshga8vEzYzSOdwTiFEBkMmm4XHVks1GsrSWZVk+HWT6fZ8Ay4ZiMRiNXaEne4IMPPkAikUC1WoXVaoXD4WDF+tu3b3Pl8/z583C73WwPRomeGAAB6DCoJg9chULB68Zma7sx5HI5VowPhUIdOFUxgBLV+sUK8OLiYod8Q6/ASzwAgX2ZEHotsWpEwRG5UZw/f549X3O5HK5evQpgX8uRgsNCoYC7d+8yHpKIRhQUEy5JoVBgfn4e4XCYWebBYBChUIhb2lTBp4pcPp9nz9lUKgW9Xs+sazL9FmElJFFBTHWRoPSsIerLpVKpA4GeCIMQmeHyRE0kt3RrxdPPFQoFbjHS/5PJJMNCyH7OarUy/Eaj0XBFkjB2lNzROiMjdLnZuQjX6CWVQ2x/ej3ChEqS1CGxQwLlZPNE3p+FQqGnJaD4+WkO7t69i2KxiL29Pdy9exeDg4OMvxU1JsUq46+7OgZ8EZB1jMHBQZjNZlgsFsbj2O12qNVqDAwM4O7du6xaPzExAZ/Ph93dXfz4xz9mNuXXvva1Ay2wbhY1Ij4IAFsE6XQ6RCIRBINBFvzU6/UMliU9J9ogSaCVrI/C4TBjo2gTICA/BZikqaTV6rCxUUIwOIF4vIW9PaBeNyOdNuDJEycKBQUkqY5CwYB83tShOSQfJlMBJ048wQsvPMbrr6vQaGSZVQoA5bIesZgP29vbyOfzLHVQKpWQyWSws7ODV199Fd/5zhSA/epgoVDG7m4chUId6bQF2ew06nUlqtXK0zaIBmazD+WyHUtLKcTjEpRKFZzOClwuBep1oNk0oF5Xo1wGcjktlMomxseT0Gha0Gj0KJdrsFgU6OszotEA7twB3n13/7Op1S3YbE04nVMwGKwwGmNwOrP8x2AooVxuIRabxI9/PIzPPjuNWMzBv69UtjAwUINW+5vQaLIwGAowGApwu8twOLJwOocRje4zZ9sHsxE7OxNYXp7A6uoUIhFx7t1P/3QOtboFk6kEjaYGhaIFi6WGoaE6tNoMTCZAo1mGxbKHVqsJj6eMF15wQK9vQqkEt31HR0exvl5lzTNJasFgeILx8RLbjLTZlmYsL5sxP6+Cy9UGWw8ODiKTySCRSECv13PLX6FQsFTK6GgY//E/XsXubgbxuBOlkglabQmjo0WYzQ0YjUaYzWb09fUhEEhhfl6DcLiJUkkPg8GMr31NQiZzEyqVkttLBPJ/4403uBJAlRfyR6zVVF0PEmD/ILPb7axPlEwmWS6FLFvo9QAw9o+CZvJnTKfTrJNH+mXlctsHtlgsYmVlhVt11WoV7777Lh9QhPkhSyyqwtAhTZ6QGo0GWq0WMzMz/BkAsKi1SJQgXF2vtlo3KRN5G/KwdhwxXomFbjKZ+P1Elh5V2ql9RExhcrqo1+vszEGVH9KmE3GD4t4nSRLPEc1puVzG6uoqV8ipA0AkAZVKhXw+z+9PVUnRE5QYtrSe0+k0E6To/ncTTO7FXE6n0xzkUHtU/B2xEzI9Pc0yRSRbIx/lchmFQgHhcLhnS9NgMOD06dNIpVLI5/MYHByEJEldmf00TzTH9My2Wi2eF6q2ESwGOKi71yu4IeZ+Ot32+DWbzR1tYQDMhqeiRb1eZ2uw7e1txioSVEg+1+L/qVVNLfhGo9HRHhUTCVEz7p/D+CIgE4bVasX4+DiGh4exuLjIeBwyFydRzUajwVnbo0ePmH5LhIA33njjwOvKb3o4HIbBYODyel9fHyRJwtraGjMiafOih4A2SmpfiZknBVsqlQrDw8PI5UrY3JSwuzuOWMyJaNSJcNiMYtGAalWFWk2DalUNuV0GAKjVdRw5UoDNlkaloobbHYbRmIPVWobRmIfJlIfBkIPb3cC/+3dvwWo14+rVqygU8k/lNQZQKh0UIE0mk5yNERCfcB2FQgELCwsIhUKYnJzkgwFI4+TJF7C5uYmZGT1arQDq9Trj3dqkimOwWs3Y3c0w7qwteqjhFtK+mKgS6XQWKpW6C6Bz/1oXF7P44Q8XsbOjQjqthkLhRC5nQCplx+PH7q7VJgDQ6+s4ejSKy5efQJKyTwWDG8hm3djcLCOdtiAY7EexaESj0b6///2/t4O2/v4CJif7kUq9jvV1B6pVDbTaOt54o4WTJwGHA5idBbxeoFLJIpHIoVpVQ6utY2LChOFhK7LZGgf/cpHSv//7z7hdrdfrYbW6kM+3mcE+nw+xWAzNZpNxFnQAjo2NoVgswul0dniXys3jyUmAvPjo0CSj5Lm5Oa48S1IZg4MhDqj0egO0WiMHMel0GrXaHpzOEOz2fWmERsMLt9vFWCjy5TQajZxpk/eqHNRNB0k4HMadO3e4bXz27Flcv34d29vbAMCAYjJtJ/wkSWMAbSwpYQWpBe3z+ZhNuLCwgFQqBUmS4HQ6cezYMdy7dw8ul+qingEAACAASURBVAvRaBTFYpGrZKJobqVSYXwLVWHE9p/b7WZG9Y0bN1jccnJykitYJDmRz+eZ0Xzq1KmOAEkEbj9LykSObRTxXiTxQntgOp3GgwcPOuAAwWDwqaBpu42/sbHBTO5cLodEIsHMV7pf9L5nz55l3aloNIpEIoFCocDyP8Qgb7Va/D2gfcC7XO11QkEXAH4f0XPWbDbDZDJxsEXCvwBw9erVDjIAwQLkVaBuGD5KzIn9SXu6KPYr4kopwKHrJbFlGjSPVOl67733GPZA3xdV7YnVHI/HOcCnz0XwE4vFwgx5OsNorvR6PU6dOgWPx8MVS5LmSacP2t+JgbQoYh4MBnneCoUCk0eo+kVK/nKBcmq57+7u8nsQs3J5ebkjidze3ub/0zNMbeJcLndA4oLwuaT4f5iTxa9yfBGQyQZlunq9vgP4SZscVZ92d9uWEwTUJIB9Pp8/oKgvZ+atr6/jxo0bDKqfnJzEmTNn2JJJoVCw1QxJGqhUqg7tGJ/Px8a5hPWiIKdYLCKVcuNP//Qt/lwORwGDg1kMDaVgMLTgdhtRKMTg8bRgs8UwMmJANPoYJlMVanUFr776CkKhEHK5HPx+P18HbfiEYQEasNms+I3fuNxRBVSpVLh+/Tp2dnbQarUYyEtZKG2Iok2L3W7nzUDMhIeHh7G6usp6YsSkAzoPFJ/P10EGSCQSBzAI8uCYWGFApxNCNrsIl+sTOJ0tvkcGgwHT09NYX3+CTEaFlZUy+vrO4s6dVQB1WCxRfOUrajgcxqfm6cscEE1ONlnTqR3MK1EoGBEKaZBOO5BO9yMQMCKddqFc1uDllzdx8uQO/sN/OILJyW6WMxYAoqdqu60qfj65RyIFLxRA0CYFALFYjFmxlCn39fUhFothZ2cHBoMBoVAIU1NTHVchgthJEJeqvdTyNhqNzIp8++23cf/+ffZWbTab+NKXvoRkMsn6QdSyWl1dZco7DaVSiRdffBFAG1NEFeFCoYBardYBeD937hw/J2RZFolE8NFHH/HaSqfT2NjY4OCL2vVerxdutxv37t3jgIDgAoSJefz4MX9GEhR2OBwIPNWbICmLS5cuwWw24/79+yiXy/B6vdzCoaoOHUL0fJBuVzAYhNFoZCJDW5+s7Q4SjUa5+gS0A9ZKpcLPE8nwLC8v86EqB24TS5zWzWGG8XKBT/JspfdrNpuoVCpYX1/Hw4cP0d/fzwKeFNAQ+02ETlBASpX8UCjExBMiRJFjyujoKG7cuMGVm7ZobAZKpZJFRkkAmRwYCI5B7xOJRGAwGGAymaBWqzE6OooHDx5w8Eb4ueXlZcZRNRoNeDwenDt3roOJTXuGiOErlUp47733mGTw/7L3ZcFtXufZDwgSG7EDJAgS3MRFEkVRMi1LtGVLjh2NU6eTZZI0uWnSSTvJzN9Oe9Xlqsn0Jp3pVWeaTiczvW22mSTuVK5Vx7JlRRG1kpIoiiJIcQdBgCCIhQRAYvkv4OfV+UDSdhLLdBu8Mx7bEpcP5zvnPe/yPM/b3d0tVVfK7fAuUKU68vk8fD4fGhsbsba2hmQyKT8fKKvWr66uynukSCr/X1W15zxfu90usx0BbVWL66XOluVeLhaLOxIwJv5MtrjmlWSjSuwzOzXc71QIACBntqWlZYcY7WN5mMcahKurqzKKr7OzU6aWZLNZtLW1iTp/R0eH/JusSv5M4ssqBcOrLMtPqKkZKUvXS0tLogS8ubmJUCiE119/XZwvLRKJ4Nq1a5IlMQqnfhjVvsnw2N7eFh2WoaEhoXWbTCbJhAFIhmUwGDA8PIyhoSEZrcOssFgsilzH8eMB/L//dw0tLSm4XCs4e/ap9zZ7ecByKpXCu+/eE+fa3OzE1aub77Vqyy0gzvOjBo3BYEBnZyfm5+eFVVgpIri4uIiVlRU0NzfjhRdekPlyFosFTU1NgrHzer3w+XwYHh6WcTrpdBput3vH7LP19XUNnZ2Zp9quoakMR4rqGgwG6PV6TWBc/vzly4XvUJ1HeuvWLcm2ACAej8Nqtb63H5rhdG7A4cjD719CTc2YKNo3NR3Cs88+C4dj51xLZmWNjY0yVsfhSGB5eQJmsxnPP6/Hs88+q2SEG6irK1d1dmuHvJ9wq/pOgHISAECwMgMDA3Kp0GkDkCCMjlbVwaPyOgDJZrlm/FlsdbDFRgYis1OHwyH4IVZQHQ6HAHyBx20EvV6Pe/fuyf42mUxSNbLb7dLeqKurg8PhwMTExK6Ad2JvJicnpSLFwIeEG6vVitXVVWxvb8NiscgMTl5klareDocDL7/8Mi5cuIB4PA6g3Jqy2WzY2NiQi56VA4ejPJbt8OHDIhlAdi7nAq6treHu3bsCaqbvKBaLQt7gmqXTaaTTaRFT7ejoAAAZ75NOp8V/FItFEePkhVrJEuc+IQBeHbbOi7FS4JNsOZ5vji9jpRSAtInZwiVzT5WDYTBMtuTt27cxNjYGj8cj0hb5fB6XLl3CV77yFXzpS18SiSH6JmLKtre3MTk5Cb1eLxUcMgbJMl5bW0NnZycWFhZgMpkwMjIilWPq39GYWLBtR7LXbu06SvVUtsm4pzlC7MyZMwAez7mlb+O7ZOtYPV/d3d0iDaJqdc3NzWFhYQGbm5tyXlkxLhQKQiJyOp0oFouyJiaTCQsLC/KclJxhW5IySer7Z/Uuk8nAYDDg0aNHyGQyOHLkiCRqDx8+lLF7nIbB37+9vY329nYJcDnT+fbt25qAaK+giNV34pqZjDU2NmJmZkYSJ51OJxJRle1Zda6yKhj+YYgDH4dVA7IK44vZrR8eCATE+TY1NWFhYUEuBZZk6TwKhQL++7//Gy6XC6lUCm1tbZifn5cMFoBgCThehoyQ6elpKcezVM+DTY0XOliOJCFgkvgSr9eOV16h0rxNI6tAgOrW1ha2t7fx3HPPAShfjLxI+fXUJOLvJ3A2m83i6aef1mxgjpyhA3v22WdlYC4Zh9QD48xCAJIZ+/1+tLa2ipYY157MVwBC096N/s0skervdIi1tbUYHh4G8BgrRZAoHR5HdUQiEVy5ckWD8yAIuq+vT1Nd0Ov1OHjwIIrFImKxGPR6Pfr7+zX4HHV9KmeM8hJbX1+Xdeal9n5ZJx2XClymzEolnoL/z3YcW30LCwvyLguFggQwxEOxIkMNvcnJSeh0Oty5c0eYpaurq2hpaZE9ybYbK00nTpxAV1eXVE4ZQFsslh3ZOCtYq6uruHv3rrT+SG7hhIutrS1MTk5KQlNfXy9ae1arVebPqmxlh8OBvr4+pNNpGAwGhMNhWUu/3y96R2S8+ny+98RB40ilUtJGzefzmjZVIBDAs88+i9u3b8NoNGJqakpYZD6fb0/2Fkdk2Ww25PN5HDhwAPl8XtTneSZ6enpEQ4r7GcB7VdogFhcXJfi9ceMGgDJIemNjA/X19cKYo+6UyWSSy55VOTImaWrFRqfTaUSm1TYfAAmUC4UCuru74fF4JLDnaDgSoUqlElwul8ZnTE1NyTQHBlMEYm9tbUliQP/AGYYnT55EIBDAzZs38e6774qcBoVvVagEK430uww8yBynEY6iWktLC6xWq/ipWCyGW7duiXyD2WwWGQeO/OK6sm3PlhyTHmq0qXNu+XttNpv4MspwqIkn8ZD19fWor68XoDpFvNXuQiqVkjXLZrNYWlqCXq/HwMAA5ufnRS+P60PfODQ0JBVltcXHfdPY2ChVQ+KW79+/LzOPU6mUCIVzDZeXl2Xd1ap85QQVdewdjTi/QCAgXaMyxMGMzs5Oee8ulwulUglNTU1IJpO7YuW0OnIQfBoTgyrL8hNm7H3zBQ0ODmqAv8QzcLApxe6YiZNWTSdODE0ul5MyKYMxGg8M8V8UDt3c3ITJZBJhWlYeKsUzt7e3BbTKbJCtDDVQUT+HepFvbW0hHA4jFArJxdPf3y9f39LSAr/fj8XFRZjNZsm+s9ksrl+/LqBbANKuItGAmQgv8+HhYcEycEC5Or5pYmICMzMzcqFYLBb09fUhGAxqgkcCdYm7ULN/Ctvyoq+pqREnAkCIGLxwVDwJxXRNJpOU1XU6nTyH+nsBCH7I5/PJCCi2WnYzlb5OYUe+e2o/VVYH3096gM+n/nu34I1OzefzYXZ2Fnq9HsvLy8L4pUZeTU0Nnn/+eXGuZNt1dHTsUEinTtTCwoIMSGe7nQDqiYkJNDY2YmNjQ5PtDw4OIhAISGWvq6sLw8PDUsFiBZZAb+65yclJGI1G9PX1YWtrSyrNAIT4kk6nd5wxAKL7x7b+sWPHYDAY4PP5dmAJeT7YArTb7XA6nZrKBt8NWdGUXGH7m/g1NSimb1H1j5aWlnDp0iUh2xDITVV0tmPUUS8tLS0y7UEdGE/sKf0D2YhmsxnZbBaLi4sivcHnVkVaAYjeFFCuNlOYlYED25QNDQ24fv26JEr379+H3+9HfX09+vv78dxzz0krGCgLWEejUbz77rsyjeDs2bO4cOGCBAW89GncA6za8edQt4+jzurq6mA2m6XSySCU+97r9WJjY0O6DQwQqTHJdWALl9XeVColzD76VxUXmclkEAqFkM/nsbKyIsmjy+VCY2MjDhw4AIvFguXlZakuhcNhDUY2EomIBIVKNmEwxaBexVlxP1+4cEH8p7pu9C181+l0WuSWzGYzOjo6EI/H4fP5RFuQhIpAICD+n50EKgio7MREIiGt4ng8junpabmH1ASe82aJi2toaMCpU6eQSqUwPT0tUiKES4TDYQXv+7iaRakR/uP1ejE0NCTrRf/D+dDNzc07SDuVpJWGhoYdTOP9tmpAphhZWzwovOh5idBx19XVobe3VyQvhoeH8eDBAyklA5CyLofr7hWM1dbWwu1249ixY6IBxmzcZDK9h2dKysXDi3d1dRWxWEwCBIvFgnQ6LQw1tkr0er20DQlgjkajcmCIv2H2E4lEROmfF9TQ0BB+9rOfwWq1Ynl5WdgrHAbLloPD4cD29jYikQjq6urQ1dUlkgFGo1FwQ/F4XGj6vBDItlLXj4DOYrEIl8slZAq73b4Dd8FLjBgpBjmqEwHKLeVKEVti9Xw+H7q6unD58mVZb72+PKON2S1HWvHdMSAnY2hpaWnPA74bo4oCp5XMXPV7d5Me4EXBy4aX8m5MOX4/WxLMyA0GAzKZjATRBJpzDdVKnqqQHovF5CJuamqSOZSUJAAeX3rvvvsuisWiTCZIJpNIJpOaAebqWJx8Pi9nJp/PCyCZciP5fB6zs7MaKQdWTYmnYltKnVSQTCYlUMzn81hYWIDBYMDs7CzMZrNGHJIK9szEe3p6BMxfWZnlRbu9vS2BTD6fF5yn6lu4Zty3xB0x6KeGGD8XAE1SpVaNe3p6NPpZBJpzpi0AaZuqYqCsGhsMBlHxr5RWqKmpkUCDCY2qhafX6zXtIaAcECQSCQkQ+NlnZ2eRyWREKX1zcxPvvvuujNZhq04lSNCIBzt9+rRgWUdGRiRwGhoaEuC+3+8XMgrxowwCOjs7sby8LJVxMllZGWZVS6fT4amnnsL6elnHkQEvEzySLnjufD4fbty4IW1XVrbsdjtyuRzu3LkDk8kkckNms1kIIiRPLC8vY3NzU8aN8Y5ZWVnBZz/7Wc07TyQSEuRTM1Ov10t3hvvQarVKxZ2+mskXscisfHq9XsHS0beo8JOf//zn4g9efPFFkXwJBoOamaZbW1syxk2VT2JAzvMbDoc17d66ujoZj6WeQfWsAZD79urVq9L2V33knTt3UCqVkEql0NLSosE6MsDbzY++X4t0P6wakCnGPvvi4qLITOzFKAEeVzrUcjFQvmAog6FuTnX8kE6ng81mE5C+3W7HgwcPpLVEvIDH40FfX5+MKGI52u12S8WCQFIGfMFgEFarFXq9Hq+//jpWVlakCsTKG5/JbDbD5/NJm0vFDIXDYYyOjsr8Q4/Hg0wmg7W1NWlbMvAEsMOhAo+ZeFw/ZvJk9ZDuD0AcHz8/AMHw0Knz73bDXfDwXb9+HcViWSuIeBUGzxcvXhTHqrI9gfIQ6UAgAI/HI9kbladnZ2cRDodFSZrrHAwGEYlEsLq6Cp/Pp6kEnT17VvaJKl/AgJ+Br5oVAjvxYpWSBQAEO7a1tYVEIgG9Xo833ngDTz/99A6gLb+fookkpzgcDmk7sOXNlorquNSq3cbGhpATVDxKc3Mz5ufnpdLAdhzbCWTXcTKB3W6X1uf4+LjgJ5nUMBjgRa4aA3NWAlKplLQ9WUnhPuJakojCS4raU2SPcvwLL6yamhrkcjl4vV65MCqD3enpaWG1McBhC+n27dvyrGTabWxsYH5+XogpZrMZmUwGb7zxhhAGKC1Cqj8DP+45BuPr6+s4efIkLl26hGg0KvpjhCyQfTg3Nwe73S5g6q2tLdTX10v7srJVw/ZuNpuFzWbD3NycTEhgBYdsQuI06XdUdXjCIpiMWq1WScxUliEr+vSTJpNJRK/dbjcGBgZk/iUTre3tbWkTqkYsG9+93W4Xn0R2PN+x0WjE3NycVPs5losB9srKiuxhJjtGoxEul0smcFAcm5+ZCSEhDaza07dxTJjdbhd8LrstrBhxf4XDYY3wa2Uy19zcLIQJMlwpi3Ts2DEcP34cqVQKoVAIAwMDsiZMnEhYO3bs2I6KPC0UCkkStLW1hZGREZmq0NTUhLa2NknS+Jlra2vhcrlkTBJn62YyGdhsNphMph13aUNDg+b+iUaj0kpkkFZfXw+HozwDUxXD5SSMVCqFtbU1bGxsIBqNwmQySQCs3tefNN2xSqsGZHsYHTSdFjFPLI/evHlTozNE/AwzBFUAlplZTU2NZG3MmMxmMwYHBzE8PIxHjx5JeZcjbmpra+HxeGSTM2Nju5EbnRkhwYwUVQyHw8KoI3C2sbFRWp1ms1kzsJosrImJCQm+qG8UDAbh9XoluwOgabfqdDphYiaTSUxPT6OjowO9vb3I5XKiVs5KDcfd+P1+RKNRofzvZWp7aDfcBQ+Z3+8X0PmjR4+kYhEOh2WdyKhiiV1tVVBNXf29xIqoyvtjY2Py8/jOM5mMgESXlpYEyM+LlXuKgW9lG7KSPn/mzBkNOYDsL7ack8mkBFec5+ZyudDb2wu73Y6lpSUNi4lYFrYiLBYLXC4XmpubRVsPwI4AUG2VUAAyEAgIMwqAYIAYyLIlzAvdYDDI5IHp6WnN1INkMim/s6mpCTdv3pTgXTXus42NDUlCWL1g+woA/H4/ampqcP78eQmQvV6vsP0SiYSM4wIeZ+Bscx06dEgufGog8f1FIhE5G+vr61hdXUUgEJDJHpWtdIKyiftRExe/34/nn38eN2/ehN1uF//Av19bW8P58+dFw8vr9QIoB3oMhlipYhJHLGJnZ6fog3G+X7FYxKlTp0Sxf7eLqaWlRUZbOZ3lIfJ8xxwDRcV3h8MhvoGBGfcdsUZk7FmtVqnQcl+xMs2qKwMLSjuMjY1hbGwMxWIRa2trUtXe3NzEjRs3pFXM+Y1cCxUKolbqGWSyYuZyuRAKhbC6uir+2WAwSKeExkqQ1WpFJBJBOBxGU1MTHA6HwCnoPxmkkdVM/B/HbN2+fRtnz55FQ0OD+DGyTxOJBCKRiIbQBexMBiwWi8ywpegwcZSs5rIKpZKWWKVVCWtqS4/vFCjPyGX1iz5e3dOqgC/1/6hfSIyo1WpFf3+/BLpM3niXkgTS3d2Nzc1NBINB/OpXv5IKtVopJ/SGkwNUX7m0tCQFD7K1GQBnMhkRPFYT5Uo1hE+CVQMyxbhBWMpXx9WQNbe0tIQbN268p7dlFP0aVneMRiOeeuopeL1evPPOO9ImsVqtyGQyciCIGaqvrxeQrclkEgfGwGVzcxN2ux1Hjx5FOByWLOTkyZOSNTPjZ/bPQHF8fFzTJuVzcoZgZXuTh50YAzqWfD4vzLdAICADeFlZamtrQ2dnJ6xWK958800JOKanpzEzM4NEIgGv1ysBaE3N40G0RqMR7e3tOHnyJFZWVhCNRjE5OSmVMQBSRaytrcWbb74pGfSRI0cExAk8rh5QfoFaTLlcDm+99ZZgS9h2oCJ3Z2enOLG5uTk0NTWho6NDAPDUhyOonVlvMpkUTF8+n8ejR48kwPD7y7MdVaxbKBTSBL63b9/eUaVgu4QX1Pnz5wVATGeittS47+hMfT4fstmsjPKJRqOaFg+Bt5RQ4VzPhoYG0fipJIBwckCxWITf79eM+KIz40guVmHUqQXFYlGkDmKxGHQ6HTwej+zNUqkkLDGCyo1Go3w+nhn+nHw+L4w1JhtsiXR2dqKzsxNNTU24cOECYrGYVIF7enpQLBZht9tx5coVRKNRGI1GGI1GycABaBhYBDbzjPT29uLKlSvY3t6WSjG1kHZrpavsVAq2Go1GTSU1EAggk8lIANHd3Y2VlRW57Nj+tVqtUgUgaJ9tKhoTQQZKDHbJcONooL20xYBy5ZfEB72+PHcX0I7roj85cuSIBPj19fWasTlqwMhgpxI4r2JtyUxfWVkRcVZqlFEzi/uLe54tdmJAGdSrI6ACgYBmNmxDQ4NUhefn5+H1emVwOec9FotFrK6uSvWJn4fV5cuXL6OpqUnwpoODg7h3756Qvqg/xyCT7EuPxyMt5JaWFgmqTCYTenp60NTUhLfeeguFQgGXL1+WClZlu00lCpB4o2ICVU0yKvbzvw8dOiSzUtXAppI0FAgE8OqrrwobOJ/P72CxU3dsamoKLpdLOiZ6vR6ZTAYdHR3w+/04c+aMwD4CgYAkmZlMRtqL/PmUNGEbfGtrC7/61a+kNf/mm2/i3LlzGqIB/b3api0UChIAqzI+w8PDWFlZEfb3J0HuglYNyBRzOp3S/uIlUKkEDEBAshQVPH36tDhpsrWA8uUYjUaRz+clsCNOx+FwoKWlBZFIRKJ/AMKg6e/vx9TUFLa2tnDx4kVpEdTV1cHtdstcOqrhE0xN8C9bBTR+Hw/W4OAgJicnhcm0uLiIX/7yl8J4slqtgjXjs5lMJjx69EgEOIGyk+Il29fXh9OnT2NkZATb29tYWVmRtlBzczNaWlrQ8Z4uzOXLl4U9t7i4iEQigbNnz0qwwEuG1Qo+A8V6i8Uibt26BbPZjPX1dWHr8GvoqIkDYvWSsg8UaFQzSrYB9Xq90LjZdigUCrDZbJiZmRGME5+PzCegnFVy7EpNTY1Qy7mf1PZkpSzG+Pg4YrEYwuGwBDO5XA6pVAr9/f3IZrMIBoO4f/8+AGiqJrlcTvYlhUdJWCiVSkin09JiYyDDNk46ncbNmzelSvBYjd+hwVUB5RFf09PTMnqF54KK9Zubm4L5ohwBf39dXZ0Ml15ZWYHT6ZSs/u7du1LdUGUX2LZne4gYHL1ej2g0qqmgsRIdCoWQyWSk7cNWGcUj2Tbk31EhvNLUKjmz9Dt37iAejwvOk1Vr6qXZbDYJTFSpDf7OlZUVPPPMM4jFYtK6Ji6Kch1LS0uyd9ni29zclGHJ+XxekgWOSWOLlYFsT08P1tbWMDU1JcldIpFAY2PjroKmZPwBECJBQ0ODSPxQBoSVMQag1PxjQsgA1ul0orm5WcgianVexbRls1mcOHFCw4odGxtDMplEKpWSPUafY7FYkEgk5Dzb7XbBmLKKB5Qrj4cOHZL/V9v+FKHmugCP9QyZdPNcELpCrFahUBDSUiKRkGkJHo8HX/jCF6SSXFNTZseTXNDY2IjJyUnNKCCn0ymBhSqimkgkkMvlMDs7i1wuB7fbjbNnz+6oWrMCNjU1JUzE9fV1gSaoUAqgTJqiP1f1xXbDnfLvDh06JB2H4eFh6YxQgFyFRFRCGuLxOCYmJgSGQ1KDqm135coVkVIxGo3in4ByVZIYUZUMs7y8jKWlJcG9bm1twe12S2JWV1eH5uZm5HI5uWPz+TwikQhCoRDm5+extbUFi8WChoYGzefdb6sGZIpRK6itrQ3j4+PSqqBmFC9flW1ENWGPxwOTyYSJiQlcuXJFQ8EHIBd6W1ubZoMw2wSAgwcPihgfDybLtFS0p3OrPAjMCLe3tzE2Nia0axqzdVbEKHx76dIlqe4QX+Hz+dDZ2Sn4K7vdjps3b6K3txdjY2Nyeakir8RCENcAQAIuADIKhErR/LN8Pi9A5PX18qiWP/zDPxTmmdPpxKlTpzSZKy8Pfi+BxhQRJIiVa0ZhShXrNzQ0JDMk1TYgWT8bGxvY2NgQGn0+nxdCg9qeppwAKyG8HBcWFkSnh2tFKQA67UpMGIHUbHGwJUfn7HA4cOfOHVkvXoAd7+ld9fb2CojWbrdjbW1NLnHiZ9bX16XCoGLnWD3Q6XRIp9PipDKZjOhzAeWg58GDB1haWpKgnhgYXsRk5DJR4D90oBwxlEql5L2zRcOWN59xY2NDNJzITlPB5eFwGHfv3hXAOPWtGIwxECBw2el0YnZ2Vp5DVflX5R14uQUCAQnyxsbGpHJUiXUcHx/H1NSUBCderxdutxuZTEY0merq6iS4oqYSEwCz2SyDnB89eiQ/n8/MbJ+B9/b2NtxuNw4cOCDiy2wR19XVYXZ2VsP4rampQUNDw45qgHoZk4nMOYgMgu12u5xV+i5Wk3iZut1uSbZY6Tx27JgkNsFgULBufr9fpGvC4bBMceCFrmKcWltbYTKZBKLBS5szKik9MTg4iLt372J8fFzYzpWftVIrUYVbqGQc7i2yJll5oU9nOzWTyWiEiCuryqoOGlBO1jo6OhAMBnH9+nXodGXRYBUTpfpV/ncoFMK1a9dw6tQp+VqVec3gn+8mFovJe8nlcujp6UEmk8HCwgLMZjNWVlYwOjoqiajKZEwmkxgdHUUmk9G0tZlk0AqFAu7evYuFhQVhzapry5mYJDyoZ4q+hfcan5NVLPoDj8cDs9ksRQ36EVbUGYiq2m5UQWCLmz5ycHAQoVAIm5ubUoUjwWO3ZGy/rBqQVZjaRgTK1OcrV65Iq8Hlcu1Kaa+pKStAkzm4mwvwtgAAIABJREFUvLyMXC4nlxLpuASfc4PwomM2pQJVVZAsD6nZbMaZM2f21LoaHx+XoAEoZxlsHSwvL4uTzWQyuHbtmgzLJeaBlQAGGnRqU1NTAtBnRYaik3w+6slkMhlNG8VsNqO/v1+ysrm5ObkIU6kU0um0rCdQzso4+5AlbgAyVmlkZASpVEqqKDz4bFvx0mpraxOcQzQaFdxQbW0t5ubmNJphu603DywzMwAa0U6gXGE4fvy40POpn8S9QCNzraamBu+8846IzBJfxNYmpRaoy6QCgzc3N4VJmM1m0dTUJOKNbGOkUilMTU0hmUwKCYMZZi6XQ3t7OyKRiFxa29vbwmRk9qwyOW/fvq1h0wGQdiRbGel0WoJHm80mMhV0dnS0XFdm8XSw3Ktc+4aGBhgMBtEMM5vNSCaTWFtbE+FgVRuwp6cHwWAQly9fFkXvvr4+CchLpfLcvHg8jkgkIkEpL+SamhrcuXNHQNHAY1YkZ6+ura1Jm1WFAaiyIzxDrA6vrq5KksK9w7Ou1+sRiUREp5DV63g8rrnE2ebnuszNzcFms8FgMKC9vR0jIyNCDjp69ChWVlYEw0idLRIkKnWZAC2Dl0zkXC6HxsZGtLa2wuv1SjJaKBQ0Y5tYwWOnoLJipo51UiefdHR0SALHvUlsEn0H2YpdXV2SSFEfb35+XpIhjva5fPmyBLLxeBytra17Vj5ICmKlnfAOVRiareeamho8/fTTMJvNmJ2dlZ/f2dkpCbfNZtNMNSB7lmQnAvn7+/uRTCblbiiVSrh48SI+//nPy56z2+0iM6SyzNfW1hCLxfDqq6/uYAxyXcgwHR8fF99RW1srlSoGbqVSCcFgELOzsyKFwb25uLiIxcVF3L9/H4FAQHzU4OCgEHZ4Bra2trC6uqphzXJtNzc3sbi4KEQfl8sl+Gb6eafTqZn4wASP8kPEzwaDQcRiMaysrGBtbU3eqbrGbJ8WCgVh8QPlSi73vc1mE3kOdjUaGhrE73wSrBqQ7WKV4yzcbrc4HmaH6ktkpWp0dFRK8eoIE/6cvr4+Te8eAK5evSqBG4MJzs+kpAGzNF5gwN6DbAFoAM5kHbE0yyG8165dk0tUrWKQhlxJQea/KytybBmQMcfLm4elra0NQPkyUan1xWJRJD6YAdMYCBSLZR2sdDqtAYWePn1ac0lwRI2q6m02m6UKlkgk8Otf/1qUxYnJUR029dYYSHBdAIhMAKujBoNBRGWNRiMmJiZgNBqRSCSkPVpp1Eza2NgQ8cvOzk5NxYTMU7fbjfb2dgnSgXILZnl5Wao9uVwOAwMDGh0dALIu+XweR48exaVLlwT/ZDQakUql4PV6xVmrOl7ZbHkI9smTJwFAZEr4d9xbVNp2Op0S6FHZu66uTgI+ajKZTCb09fXBYrHgwIEDWFpakkSAn49Ys0KhgOXlZdEfowQA/663t3cH+NjhcMBischZ47N2dnaKPtzAwIB8JgahxFuygsqWDQVia2pq8PDhQ7lgo9Hoe5MstqXdpeoBcg+bTCYBnzPgZHWQga7b7RYgN1CGFLS1tWF6elpYo/y53AfpdFqwcJlMBsPDw5KMeL1ewfDwHHo8HjQ3Nwvju1gsakbxcN+ow5az2SxGRkZkFuDCwoKItzLAy2Qy4jsaGxuFWMOKGdnTalJWU1NWwC8UCggGg+JjeZ54tufn50X3bHBwEDabTcZz0e+ePn0akUgEHR0dOHTokLAl1aQsnU4jGo1iY2NDvo++0ul0apTzW1tbRQIim80imUxqJoPQhy0uLiIQCGBzc1PTDVB9JX8+5XG4B8jg5Dvi+6VchEr+GRoaws2bN2GxWDA6OirnTq1cVzKvOS+SLbxSqSTv7O7duwKV4e/IZDIyD7irqwvRaFSIIvX19dIib2trE//xyiuv4MKFC9I+JLyAn0ENFOlr+TMZ+KrzOSs/g8Ph2JGILy4uCnOZ+Diz2Szsdt5brHJVBqqVSQihO4lEAg0NDZppM58EqwZku9husgqM2ul4VBYcy7XHjx/H3NwcwuGwVDrU1oYKaE0kEjKHjEwQXo4MNAYHByXIYAUjkUjgwoULUoqtBCXa7XYB/JIFNzs7KxpHZK6wZAtAFI4PHjwoKuUceaK2Fi5duoSzZ8/uoB0vLS2ho6NDqjlXr17VkBIodkkjaJ1r09HRgdraWgSDQXEYzIjD4TDeffddwQG5XC6YzWZ89rOfFSYlyRJsnel0OgkYgfLFo1b0GPhSrZ8OjniOTCaDlZUV0WwiBoygWbvdrgncTCYTPB4PVldXxbGp5I1CoSAtSALSt7a2sLi4KK0X6qMBZQycKow7Pj6O6elpAOVkob6+Xi5mtULKNgYviKWlJY2aOkfYlEol9Pf3Y2VlBfX19eKwKTw8MjKiYbaxneZyuRCPxzWB6aFDh+QCNxqN8Pl8mJmZkYuImLJgMCgtO2LfeB7q6+ulMkQNqcOHD8t0ixs3bsBsNiOVSuH69euCg+TZo7HFWSwWcfv2bTz33HPweDyaitrBgwcxNTUFAFKRZFszEomgpqZGsGbEoTHocTqdOHjwICYnJ4XlyUvCYrHgyJEjWFhYwNbWlmCeisWiVLTy+TwCgQDGx8exsLCAfD6PmZkZ5PN5mRXq8/ng9/sFa8RqN+fr9vT0IBQKSZBGPxOPxzE7OysVYYp6Usl8Y2NjRxVQrQiNjo6iVCpJkMSEkt/PahZ/FokDJISosiNMtIiNfe6552RGJt9vW1ubtFTPnDmjCebIxGUQo+LbGKD7fD5MTk7C7/fD6XQK5pWfq66uDr/+9a9lH/r9fvGVADRB3vDwMFZXVxGJROD3++UzMFin7yLZg9Xl1tZWLC4uSoVar9fL0HbKYkSjUaysrMiZLBaLcp4ITeDnUskjTqcTTU1NuHfvnlTaCeGgsaU6OjqKubk5xGIxbG1tiU9g4E5QPwBJure3twVPG4lEhOySSqWQyWQk2KyUz/nyl7+M9fV1xGIxDA8PCzTmzp07ACBsbrYteb84HA6NREilpVIpzTg2dorUcV28u3Q6nQSTXq9X7kuuSWWQR2OLtLu7WwL63arG+2nVgGwXY4ZDZ6rqAJERyQBHLdcCEFYlgyXqvgDAjRs34PP5xLmQAUjQKJ02cVBA+bKiXhadHi/F+vp60Vlh63R4eFiwVJwfabFYsLi4qAnsmEEDZUfz3HPPiRK0mtnyYuF6qFUlFStBp9fR0SGtKo63IACcNj09LYeeoH6j0YgHDx6IM+VIIQCynqxQ0ilRtoCOrLGxEeFwWC4UBrgkawCPgdpAGTw8OjqqudipKs/goKurS4agFwoFPPPMM1K1zGQyaGhogNFoFAkRtkQZeLFl53a7YTAYMDk5KZ+JLE+KlgKQ4IB7jTgjVv3cbrdcgrvtWxI09Hq9BDm07e1tuFwu1NbW4tq1a8JgogYUn4vYHJWcMjc3J1kxq1GHDh3C4uIibDabvM9YLAaLxYKBgQHU1NRI5YFDkSnkOTg4KKDdR48eyXBwPodaueP5YQWALdK33noLX/jCF+TzsfLJ93/r1i24XC7Y7XYNAYFJFSvXXHPO5eMs0XQ6LVptBJR3dnZKy5EYNRIrBgYGMDAwgNHRUanUZjIZYZ0Sn8gzTgIOcWLJZFLwS9Rzun//vlTk+M6TySScTqdUIXQ6HQKBgFxMTJjW1x/PgFUvenVqBUeFMfGk8cLj8/Hzr62tSWu+pqY8cJ0kB5IkVGA18LgVzYBtbW0NwWBQEhzivXghq21e+h5OhHA6nRLIZLNZGbfzwgsvyFqrSvH8/Uyu1N/Byi0r4EziLl++LGSlT3/607J3gHIFMRKJIJlMYn5+HqdPn5auyW5D21taWnDp0iXBdx06dAhtbW0ipv3SSy/BZrNhampK2uRMFJPJpOw/YmRJdADKIP3z58+LT6cArsVigc1mE3kJngkAovPGhL6mpkamVXBOZ0dHB/r7+3eVRuG/b9y4IdW4uro6rKysyEzK3t5euUMYgPIZdiOUkIhETbWenh5ks+U5mOxCsJWdzWaFKFNbW4uNjQ10dHTsCFS5/2nENb5f9eyTYNWAbBfbTYhTzdSohcLLQgUpcoQHQYos2QJlR9re3i4ZS1NTk2wOnU4nc/k6Ozs1G4/CrclkUliLpBWrGdz6+roMFS6VSohEIrh48aK0APx+v7Q+jx49iitXrkhrLh6P4+rVqyiVyiNBeCiAcruBTlLd+CzT83AQt0Iqt9frlVmG6vfQOTCDSqfT4vA4+FgFXNbW1sJiscBgMAh4czcKvt/vFwVxXiB8n6dOnRKiACs1xPhcvHgRJ0+exPXr16V9yCrM5OQkTCaTVNVGRkak4kYcBRmznF7AAIItPLatWIlsbGyUC5pzGHmBMKCnrEIymRT2I6UFQqEQFhYWMD4+rhkozlFCrOoZDAYJNmpqaqRSqRIH+HtJXMjn8/Lc3Js+nw+jo6PiEHlJE7+kzrej8yXYemFhQURcM5kMJiYmoNfrYTKVh6EDZWwg20VMTNbW1jAyMiIYOCY2qVRKcEzxeBzBYFBAvMSM8TOn02lsbm7i4sWLeOmllzQjkkjGiUajuHr1qlQNuBb87CaTSc4Pv6e2tlYqwurYG74H6ksxYFPVyKlppxJeWIkEIFViDrLm+mcyGbjdbgSDQdEG9Pl8ErCvrKwISYWmJpZWq1WSH54Bnl3udcoNWK1WFItl7TCOGQPKsye5vrzwideJRCKawI2tee65VCqlgYHodDoRsA0Gg3JWibOiQDHJVQw8GWytrq5K9ZfjiKxWqwSfsVhMzhUrQdSFVPXvOjo6NPtebXkXCgWMjIyID2NiSH/D9q7H4xFGvDq0fWlpCfX19Rp8FwkMPHesElKHi4LACwsLkpQSZkH9PjJB33nnHQmkOX2gra1N9Aa53ynzYTQaxYeqDO/19XUZpbaxsYG2tjb4/f4d+GTVhzMBZXBeW1urafnyd+ZyOfT29sJgMEh7Xv05DIZVqRTqFjKgZBJJeSH6UkImmpubNc+5G3OY1WC1uPJJtGpA9iFMZSKR/cjN4XA4JKNh/9poNEqAkE6nZVMUCgU5UBaLRTSS+vr6UF9fj7fffhvFYhEPHz4Upf3a2lr09/fLMGJWMyjySNp1KpWS8rFaYVMrSPw9/H/SodfW1nDlyhXZ7AaDQVomQHl8CzMzKqnT6THzA8oBiKrqTq0tHgxVPNHlciEajcrhAh7P66QsBfBYMPHkyZMCWr969aqMyAAeAzcBiMIzZ/4B5QM6OTkp+I0DBw5gcnJSgsNwOIxf/vKXSCaTEpgQVKxOJNDr9VIBoPMixm1mZgZ2u13wMwaDATabTfAm1LSy2WwolUoy5kWv10v2SFD98ePHd+g10SGRJQWUK5t3795FW1sb9Ho93nrrLcRiMWknUW4FKAcCPT098v/BYFAcU319vQDDyYyjblpzc7O01vmZ+T5jsZhgxnK5HJLJpCQF4+PjAlanNhHXtrGxEblcTqobrI6wssX2DzFFvOSoOZdKpQQbyedhBZVkCO4dXhiV6uCsJDHw59erWlaVWCuVwMOAjUw1nkHKIhCozM/CygdFaSt19ohTJduZ54VacQw+MpkM2tvbkUql0NDQgIcPH0qFlkkh8Jjso2I+r127Ji12tjZ5RlmpOnTokLx7vgOeb2KT2Mpkoki2OMHhJCL4/X60traK72O1jgxO7v27d+9KtbtUKk92mJ+fx7lz52RqAAlDPp9PmHuUvSCmSQ34HA6HJKckYrEDoOL+lpaWcOjQIdy7d098DytO9EcPHz4UZXxVdJb7jkxHwk5qamqEuU2cJjFguVwO165dQ319PWpra6XFya9jtfTRo0dSyQQg5yIUComCPhnVfNYDBw7g1KlTQpzifgeAEydOaIho3CM0+jlWL6empnZAAmgqRs5oNMp9xqTdbrcjGo1Kcjg6OirdgtnZWUkimRyqsjpAmdRFOIaqV/bGG2/ImWJ3xWAwoKurS/N8vK/VyiqZ6MlkUvB6U1NTnygNMqAakO1qlUJ5qsI6s3in0yk4ElXJWzWOVGE5n22R7e1tdHV1CfV5dHQUHR0dUv4lJR4oO+uWlhbRZqKD4e+fmJhAbW151Ifb7RbaOFBWnK9k4QGPy7eFQkFalFQwpyDjoUOHJFtLJpNYXFxENBrFyMgIfD4fzGYzYrGY5qLd3t5GKpXCzMyMMOJ4MMhWI0C8o6ND6Na8eBicsQXGzPCZZ55BfX09lpeX8eabb6JQKAiuwmazaUrPlbo+/LzESITDYczNzQGAZPSqDAQZqWzXGI1GHD58GJcuXdKwzBhEGY1GOJ1OwW/wsjxy5AgePXqE9fWyRhrJIbxACFQnnVxl1o2NjYk0BBXC6ewWFhY0s1GHh4exvLyMTCaDWCwmVSyr1YqnnnoKIyMj0Ov1SKVS0rb2+Xyoq6vDU089hWKxKO+Te0IdhkyQOS+gSmOAQywWs1Z1CgIvJJfLheXlZYRCIbnAePHW19fLEG8G+cQUccg229G8lImni0ajoiV28OBBLC8vCzOPwTNHOxEbydZdNBqVRIpB/G6VAXXiQWXAxmptKBQSPBOlWriXWltbcevWLVlLGt85MZ2sHgHl9jrJHqxcFwrlebd2u12ER1kJunv3LuLxuAZXquo9UczaYrFoWpu89NQEqq6uDn19feju7pa9zz1fW1uLhoYGmM1mnD17Fg8fPgQAwVYaDAa43W6kUqkdUw7IqKbkCPc1W5Cs/hNTRGZ3ZRuTiTCrKaxWMmlQgwOr1aoR/qU0RzabxczMDGZmZoRkwYCbezeRSODu3bt48OABTp06JX4vEolIZZj+1WKxyDnwer2YnZ2Fz+eTyi4TBgZnbIur8AUGKEyquYeBcsLA8+/1ejV/x7Y5A3K9Xi8tRXVf72YM3El4YeBYCcdRv76/v1+gJRSpZUt8aWlJsJVMskgyY+WQ+42/T6fTCT5YJYBxD8/NzUnFjEGYw+HQsPBVn5TJZPDo0SNZCzI8uX/ot95v9vB+WDUg28XUihijaoJAs9msME1KpZJcyOvrj+ddcj7gvXv3cObMGQwPD2Nzc1NEMDc2NjA7Oysq2MlkUpw0s1GdTiel9vX1dcn+eIHya9RRH3T+lLrQ6/UakC/weGArL3A6LtXhUriQwRRbp/l8XtorgUBAnoftolKphF/84hdYW1uT1ltDQ4NUCcm8KhaLiMViaGlpEWxWa2sr0uk0PB6PaJ0REEz6dCwW03wWj8eDZ599VsYAUdG+8nCpzB9VnoNVC7aY+Q4oephOp9HR0SHAcLKu/H4/xsfH5TMRV8MKJdskzc3NWFxclJZvOBwW4DgvhHw+Lz9XZV4xSKZ+F0ekED+o4n14cQMQBmZnZyfGxsakNep2uyV44RgttkUSiYSGrELKPQNUVk8KhYLg3XgRUOuMg8PZDuVeCYVCslcBCBtzZWVFZEjYsuJlRFkYTg5ge4SYpP7+fgBliRdWEZhAlEoleL1eOBwOac8Tp6Mag3vu4eeff14jlklLJBJ47bXXEA6HUVtbi7a2Npw7d26HHhQAwdFxvNZnP/tZuXguX74sIHvg8dxWnleyTbnvee55BrnXPB6PjDIi4J4/R6fTabBSZE4C0Og9MfhTCS0AZCYgg2ieMe791dVVadETKuFwOHDw4EHMz8+LCOmxY8cAlEdOqT5UNWocBoNBbG9vy94hJo9MWAbAxH7RF1AKhNUUAFL5sNlsOHz4MG7cuKGRcQEg5J2rV6+KFBEDEO4ZBjqsBEejUZRKJVy/fh0vvfQSHj16hGw2i3Q6rRkfRJLB0tIS7t69i1wuh0gkgtbW1h3McOLQiImlDMzg4KDAUmZnZ6WVx7Yek18KtLJCRdYtK+NkrlYyG/cyvsepqSkJHFU4jmqLi4uaxDgSiQgOkOeSYtqEEXD/kvhQW1uLRCIhlbRSqYTFxUUcOHBgV9YjfTjb6olEAidPntzzcxEOw26B2kVR8XqVs4f3OyirBmQVls1mpfLFy0x9ad3d3UKDZmWHWXdzczPu3bsnMxsp0Md2z+bmpmTyxCDR6XZ1dSGfz2NtbU2cJgMEjn7hxX3gwAGp+IyNjWF9fV2CMV4ODNKmp6dFakN18NPT04I1Y4ZaX1+P5uZmhEIhzMzMCCaJh0rFlI2Pj8NsNgtugBpZavafz+c1g2/p4FieP3z4sIhaTk9Pw+12Y2pqCtvb24J94cVOhheDAr1ej/7+fqRSKfz85z8X50D2VuVg78HBQdy/f18mATDLu3HjhrQ+nE6nDPsmzmR2dlZGpPA5GCirpXOj0ShEimQyiYmJCVH5LhaLIhVBB0tHzbJ7sVgU/Tdm3Ax26+vrUSqV9dA4kkXNhLe2tmC1WjWBeCQSkfFIxOKxpUIwuM/n25FM8FnUihjX3mAwSODEveNyuaSNyMyUz3HkyBHRxYrFYvKMDPY5f+/u3bsyWuzIkSOawIhtJp5BJizAY9FUssQqkw8187158ybi8biMlrp16xay2azMiI3FYpqJE8y6g8EgFhYW5B1WZtW8KBjAqNp8AGTYMasEACQg1uv1OHz4sFzumUwGZrNZ9ApZ7eEl5Ha78fLLL8uzra+XFeJVeQVW2W7evCnVWa/XK1pQ/Fm3b98WDCJQTtRSqZRUj3W68piwF154QfZ+Y2PjBw5nrqurk0o8Lz5WtogzmpycFNZvsVjEc889h2QyKbMMWeFSJ3iwxVdbWyt+x2AwaKopDNw2Nzfx8OFDqbJT71CtalKsl4l1qVTSrCP3PYMFoEw0uXXrlvj7SCSCuro6PP3001LJY6KlBpac18sAXVWz57ljxW1ychJnz55Fc3OzJEmcuBGNRqUzQK1MMqOZ3KVSKQlC2e6lnlmlriONTHkA8juJl9Pr9TtmPoZCIWl9c9+T8MX33Nvbi2AwCKvVKoxP4gSJy1WnzHC9KvFgNIejPPQ+FAoJvnm3YJHnQsVy63Q6TRdFnSqgJg17/byP06oBmWKJRAJzc3NIJpNSGtXpdKKPQiV2YrnU9sL29jbC4bBUOthiYFWHAGEqqxeLRbS2tkp14OHDh5KZst/O1sHU1BR8Pp+0eYLBIMxmM+bn52WeXWNjI44dO4ZsNotLly5he3sboVBI1Io5yzCfz0sQxCACKDPpWIkhMLeurg6BQEDGzgAQ9tfa2hpaWlqkbM1ZampABjzO+IktYbWDwSMPKUci5XI5bG1tSQbMqg5nSTY0NMDn80ngw+yVzoFSBKq2DwMIOmvichYXF8XBkVVoNptFAJT0+0KhsEPzh1UgVjbohFnZYsWxvr5esB6qFYtFwd08//zzMJvNIrdB7SuCwU+dOoV0Oo2NjQ34fD6k02nEYjF4PB40NTVpgpBgMIjbt29Lm4v4JQJv2b5gUMAL026348GDBxoWrjok2WQy4dChQ7h27ZrsSwKjHY7yhAuyJdluD4VCooK/uroqLTdWMtXKIFnLk5OTUvEAHrcsGJjduXNHsHfErxFTp46l4vcC5Yz+V7/6leCMjEajJBi8VG/fvi24rnv37uHs2bPo6enRQAfY3laDw76+PhESZYBO9tovfvELmW3IdjcDikAggEAggM7OTg2Gi7McOdqH0ha8sNRKH1t7DHhOnjyJubk5lEolxGIxqVrncjkcO3ZMzhLlJ3Q6nQDPGbioYqbEBbI7sFfbi4B3VYnd6SyPTtrY2EBXV5cwCZkM1NTUiMDr8PAwhoaGUF9fD6vVKqKzHLfFn0diC59dFRmlURQ5EomIVMLGxgYuXLgAm80ma0WcKTsUBoMBuVxOAzBnMsWRSalUSuRQAMiFPj8/jy9+8YsavN5//dd/SZUmmy2PPGNirJ5JrjVJXWpg4/f7ZcIEMYPspmQyGVitVrzwwgtYWFiQSuPW1pbgQdnOzWQyUg3W6XT44he/KEHZbkx5klfYwq6UeGpubpbzw/uP3QYKyRaLRXR0dKCvr0+zbxKJhIaowYohCRvs/uxmnKnKyiY1/SpbjpWCs6qQuupTOINTlfbYb6sGZIqx0gRAwNjU3aHT1+v1AsgulUqIx+Mym4+XJrFJbO8xYOCmoJREJBKRw87WCytfrMDwELrdbsRiMdEKYrtPdYTEZvDCZZuFvXu2DYiPovN1OsuDe4eGhhAOh3HlyhXJ3J5++mnBb/n9fszMzMisSGKs3G43amtrBbfA38F1YJWNAUIul4PP50NXVxeGh4dlZhwverZeXC6XZFYqsDccDgst3+FwSNUsn388nJZVRGKFWL2jU1Krg0D5wrRYLOjp6UFNTQ1u374tB1+v12uy683NTWk9Vxov7oWFBWE2ck+pptfrRaognU5jZWVFgNRk1NXV1eHUqVMYGxsT7CI1qPL5PFwul7QweFnfuXNH8GncTxzr0tTUhImJCayvr8PlcuHAgQOSmY+NjYlMBllxvDhYQVheXsaLL74oumOsDhI8y8ufFTayEYlT5EQAZvx8Zp1Ot2ebhA5Xr9eLppPJZML29jaeffZZ+ZyV4py0RCIhmmp1dXUiwkxpAL4vFVS8sbGB4eFhzM7Oor+/XxiKZCeTODE5OYl0Oi0Ad0o9+Hw+XLt2TQaEs+rFS4rg+Fgshng8vqPq5Pf7EY1GpZXGVg9xVfx8KlCe+FOLxQK32y2tZO51XjgE0LNySuiAyqTOZrNyPqhdRgyqWk3hRauKcRLb9/rrr8scy2g0inPnzuHs2bMIBoO4cuUKlpaWkM2Wx0ktLi4KG5wMZwrh8uJ1OBwy2N3lckl7r1Jnqlgswuv1IhKJyOfkZZ/P52WPUYqFCSQTQybDOp0Op06dwsOHDzWzRUmcUMlJnPepttDI3iXRgRIsPDMcLcTKHGfBut1u8TdcIw6MByAV+rq6Opw4cQKDg4NCfmFwwwoigyEKPDP4DIVCmiqrqnjPBLS9vR1zc3MazUhiyjjrdnZ2Fo2NjTCZTBJkVTIZK4N4Vro+RymkAAAgAElEQVTS6TQsFgu2t7dhs9mwvLwMq9WKyclJWK3WHVVYioXTJ5FoxsHklbjJvbTIVPuwX/dxWjUgU4wK8gyiCDQni8lkMiEUCsHj8UiAQTwYW0BU2SYGgUGAy+VCa2sr7t27J4N+2Vsn6J9GhiPxKCxFq6B/Xvg+n29HhM/Dy4CIlyb/jFpQbAM0NTUBKDv4hoYGaTEBwLVr18ThEy9DhlsgEEBXV5fQnFndIt6I8gmLi4twu92S+bF6RKOsBTNtAs4pC0KpAGZqbJ8BjwNY4nfoaNham5qaEswM15itOV4+fFfxeBw3btzQ4C96e3sxPDwsAdH29jYikcgOCjZBwCRU8Pvj8bgmA2Rmb7fbJfO9fPmy7BWXyyVVJK45A7WNjQ1pfefzeaHw8zI5evSoVBCYpfr9fgwODmJxcVGcJPfQ5cuXodPpMD4+LoxSrt3g4KBosvFyX19fR0dHh4hDqiX/SCSiUZhncBYMBpFIJHaok7MSx4CeWa3aJlEzdFYTVf06oCz0Gg6Hd5wBBg7j4+MCAWCViZifmpoaNDY2CoZJtVKphFAohL6+PnzpS1+Sdo/NZsOlS5cEj8hKLQARBZ6dnZXKOBOu+vp6mEwmIc6w3aoyPmmqSDGFcUnu2NzclBaSKmvBPcWA2+EoTy/gpU9mH7GoPH8LCwsYGBhAb28vZmdncfToUWlb5nI5EQReXV1FMBhEMBiUgKyxsREnTpzYQXQgfo3tIgbK7e3taGhogN/vlyCGATETAXYBWKkn8SiVSuH27duSKLjdbo3PTCQS0q5NJpMSiKmQDFa2jEajdDPoA5iAejweeafUxGK7eWVlBQsLC1LlZKtap9MJXnR6ehr19fWiV8dqNqvD7JwwoWPwyTM5MDAgembJZFKmd+h0Opw+fVpIXCaTSSrJLS0t8Hq94gvUKSUApKLFdSEWk3ceGZP0TTx/rNjT9xFiA0AqXIuLi+ju7pYq38rKCmZmZuT7KqV5AIgALZ/n4MGD8v4jkYiM0WIFmqx9+otisTzBhcPaKRiuJmN7SXao+4X7tXKW6H5aNSDbxZiFEE9AUC2BitPT0wLSVy/lpaUlEaIk8JKOZXl5WTSymIERlwY8nnMHlC+DhoYGaUGMj4/LQGRiwxwOB0wmk7Qi1AhfLZ1TjV0FvvKAsfJEJg4vMxWLlk6npfTP9eClks1mMTw8LEFUc3MzLBYLGhsb5bOrQ6NVfFttba0I/9lsNmm1AGUdJ4vFopHM6HhP94kCjDzMzGhbW1sxPT2NaDQqbEaVCs9KEVtwzz//PNrb26W9RzwT6fRtbW1CeSdmhArk6pBdtvsMBgOOHTuGqakpaVPx2RnQci8FAgH4/X7cuXMH+Xx5wgBbm6urqyiVSpLxJpNJYV9xzdVglvpohUIB169flxY0q5EHDx5EV1cXurq6hA3X2NiIYDAowTMTAj5jsViUgIWBLL9mfHwcPT09aG9v15T8KbJ548YNSRwaGhowMzMj+101BrBMPAYHB0UUlQEw3xWxg3a7XSjyBoMBs7Oz6Onp2ZHlkiXNC62np0emRnAyQkNDA7a3t9Hf3y8SIMQ3MhGjuHBfX58wEXm+GOzxTPBiNhqNWF5elkpFoVAQlfjt7W309vZKBbZytp9qvFCcTqfmUpydnRWiyNmzZzE4OCh+ZWRkRHBQVDDn2S6VyvpaFJSlzc/P48c//rEEOkwmWcUjVkev1+POnTsCK+AeLRaLcLvdmgkewWBQfCNQxkuyA0ApDQCCjWR1kfvI7/cjFovBaDRiZWUFv/71ryW4YlKmSuOorHgAMkuRe4itSJKqmFSpUiTUicvn8zKEmhWrRCIhe9DlciEQCCCbzcLj8YgwKQD85Cc/kcC/s7MTL7zwAkKhkGjHkZDD9WUbVBX9vnHjhkz0YMvR6/Via2sLHo9HcGiV8hXHjh0T4WV+blogEMAXv/jFXTFkDocDQ0NDEkg2NTWJ393c3JQ2Ie8FvV6Phw8fIpvNCmt9YWEBa2trWF5elgCc90s8HtdUdemz1MquxWKRCitHclFvMZvNCkuXUjsWiwX379/XEFVIjvgwVqmi8EkA89OeaED2xhtv4K/+6q9QKBTwZ3/2Z/i7v/s7zd/ncjl8/etfx61bt+DxePDjH/9YNvd+GFuWfLFso5CqTC0qKuGrdGSgjDk4duyYYLfIgCTOSG0jlUolUTy3WCyi4E7b2toSR0xnQCP+iIDSygifm+vOnTsoFsvjlgiU5uXF4IT/Vg/44OAgzp8/L1UNVqNYpQLKASQB+BSyZRWA1Qq2iEwmExoaGuSwA5D12dzclOCKsh5qJYutITqA3t5e2Gw2dHZ2aqQLWPbn2nDkDZ02gxb+nrm5OVk3UtmZSadSKczPzwtYnu0sNWim8R2zqvjyyy9LxYR4PuLNnE4nzGYzDhw4gHfeeUcydtLg+fPonOmwWEVVg2IV3K4GiJXPNT09jYWFBZw5c0ZTTSIZgJnxiy++CJPJhFgshps3b0q7jTIH1DTT6/UYHR1FQ0ODiDeqOCG2Xpubm+H3+4VNbDKZpDIGPGYZsnpLIPjo6KgEHBsbGyIUq44W48+jlhlbMWpLiUHJ2toaVldX4Xa78elPf1qYm5UEAV68lNjIZDKora0VUocqKnv27FlN5s7EZ3p6GlNTU+IP2BJlBYJkGL4fttY/yPr6+uS/VRAyg8JQKCTkF8qX1NTU4NChQzIHUJWMsFgsGqzrysqKPCdQTpiY6PD8sA3Ks8nPWIl74r9ZyWBScunSJbS3twtOjr7n5s2b+NSnPiXfq9frJcDk81IrjhcvgzN1NBorLOvr62hoaEA0GhW/4vf74fF4pLvB7oLqm5kcNDc34+bNmyJPtLKyIhc/14ZBIf9ucnJS1OSZ/CUSCRQKBRw8eFAS+FKpJKOrGMDzfPE5+P1qZU/VllQrP2qVp6WlBePj49JdqQxOiFmsNHVuMMW5k8mkSGjE43HZA4cOHZKKdSgUEjHotbU1CeBZMFATw0rbrbLrcrkQDodFX43nRQ0wVVA/Eyh1MLmqwfd+VrlfPglgftoTC8gKhQL+/M//HG+++SYCgQCeeeYZfO5zn9M4l3//93+Hy+XC1NQUfvSjH+Fv//Zv8eMf//hJPdIHGoGkjx49ElA3nS6zIapLA5CAQwXc9vT0oKenRwDIiURCwLFUMgfKDo5MTGI9uHmLxbIsBMUSeZgpQ6Cya95++23px6v9enXTLS0t4erVq+jv75e5m5VGQgODhvr6esFIkQlosVhENZ0ZXqFQEMB9LpfD6dOnYTabhUlE9iU/I6tlNptNyu91dXWi8F4qlUVTyVpSpSpisRjOnz8vAQgHGxNQXldXJzizjY0NmW/HS4QBDZ0GsVlsW6ltSVKs1UyWVR4GE8Bj7BkxTHQcNOKzwuGwtGRIWeeFRYA8q1B00sTe2Ww2aW+oY5ZYeSKYXBUNZiWWyvb/8z//g4GBAcG88HIAIEKO/PkMbLlWbH3ZbDZEo1GZGahKpczOzuLll1/GuXPn8Pbbb8slS6Fevt/19XWRbxgYGJB9C5SZfmtra8LCZADk8XjgdJZn+9XV1QkjkW1Sti3q6urw/PPPo6mpSSoMnDvY29srF5LK3JyYmBD2JTWhWNlqbW1FsVjcISpLB16Z+LAV6XK5RDKlv78foVBIKtxMaLxeL8LhMCYmJhAKhXbN0t9PD1EFp3MmJ5XRGVzQF1VWywcGBqTtyn1cU1MjmFCn0ymjn4gnZNWIFR7uO7bRM5mMrAM191TZDTUZVVu0U1NTUtVUx5YBEIyRulfVebzqaDR1XaiLpVZ9WFXntAsGPiaTCZ/61Kdkj/F9qmO8mNwQlkKxWzU4pk+ib2b1jYkPgxoAQqbi3zkcDg0BgMFQc3MzDhw4IPIdw8PD0v4jGJ9QmqGhoR0+Xd1He+Gk1HsiEong/v37SCQSog5Af+12uyXob2xslBFmZFTz85BxzmkVDLhUpmZlYeDy5csC+9HpdOjt7ZVh8cQ1skWvwofUwL4yYeIaqdjfSmb0JwnMT3tiAdn169fR3d0tGeDXvvY1vPbaa5rL6rXXXsN3v/tdAMCXv/xl/MVf/IUc9v0wXnbMnguFgjgzAiVraspDV4kRKRQK8Hg8MJvNeOmllzRlZLvdjgsXLogzYbZGx60eWjWT4OdXafKskvHv+PXRaBQXL15EbW0t/H4/Xn31VY0K8tTUFCKRCKLRKILBIM6dO6cRAa3UJ6Pjp2Ph72K7QNU+YibOauHKygquX7+Oz3/+83A6nRgdHRXMDz8v5w2yHdXY2AiDwYDe3l6hQy8uLqKrq2vHfDtWC1VsXDqdxuLiolwEPORs06VSKQmKidswGo3C+mPQSfwZQcjUi1Jn/PEzqP+vzgrk+6S+EwCNfAIz9u7uboyNjUkwwzYhA0aqtnPWpNlsRlNTk2ZoNd+L0WiEx+ORNgerIcePH8f8/LyQUUKhkAwwJ9aNVat4PI5IJCIBs/ruuf/IuLRardJmZXuGlyxBv6rjJxaKTpPYkEoVcOITm5qaZDCx0WjE1taWTLQYGhqSZ2Erk5U8Bs8jIyNwuVwSYKtzB61Wq/xOJjusojEQZavdZDJhbm4Ofr9fIypLLB/f8dLSklQUWE2luCkTIJvNhvn5ecFa1tXVaRKNvSj8lZdlKBTSEAAACMZPpysLSJMEoyZnqVQKFy5ckMvrS1/6Es6ePYvz58/LZdrY2Cg4JavViosXL8oF6fV6USqVh4Kz5en1egFAzjGlEpiYdHV1Ccuc/oKJjiqlAGDXFjNQnsDBEUBbW1uSCBBLpI5GqxTrZdubVb9sNov29nYhrtDnNjQ0iMgo7dixY4jH4+JneIHncjnxJWpwTNwaAefEa42MjAg0hVphBPmzWkwcsNPplCSYoq/9/f24du0aYrGYFAvY/ltaWtKMgJqent7BdFXb93u159TgJJ/Pi47jwsKCBFgMTinMur6+LhI2JHgZjUYhWJ0+fVr02DY3NwXWov5+VfCV5AtCYZgg7Sax0t7ejsOHD2v+TJ1KwM+u3mms1qnPoAaEH7ay9nHYEwvIlpaWJJMAyhfTtWvX9vya2tpaOBwOxGIxOez7YWxpUY8IKKtcc+NRQJJZ415ipEDZWRGjw8urrq5OxrtQPoF4H5PJJJuGLBwA0vJbWVmBx+PR4K1YKSNOrbJfz4zcarUinU7jypUr0lry+XwwmUzo7u7WbOhCoYCjR4/i0qVLUg0ixojyFcTOWa1WIUEAEEHL9vZ2nDlzBm+99ZZgqqihRYaUOr7I4/FIlqqCgCl5wMD4jTfekFYfM2j+t9frRVNTk1yEBHTz60ym8lxAj8cjwq5kwJI9qrbVaAxSVJo6AymLxYIzZ85IK4zK5Krjq8RMeDwenDp1CsPDw5LxqVl0IBCQUVzETp04cUIudQYbaiZKsc729nZ0dXUhEAjg8uXLCIfDUlnlfuG7s1gs8vtJ6QfKjolrXFNTIwE85SJIKlCB08QF0rnR1EqSOj+v8qzwYshms8Iy5EVONiqV4elIL1y4IAkcz5HP55NWlspM4/gkgvJJFADKoGcqzzPwaG5uxtbWluDHAAiGZWxsTHAtDIji8Tj8fj/+4A/+QGYx7tYiqqurw9DQkEb0dq8snWvyftIe586d28F6rLTp6WmpZGWz5XmIHR0daG1tFa2znp4e0Wqam5vbMTWBLUz6LwbWDML4dTzPXV1dAuwHylXYvr4+NDc3a6oZTGYqW8x2u12ex+/34+rVq1K1I/aRldXKfTY+Pi7BCsc0pdNpxONxkWVgMMdgRF23np4ezQi2oaEhqXKqlXDuRTIqidmzWq3id5nEuVwu2Gw2tLa24tq1a5pz09HRIXgpVqA5YkmdDMJEjKbeAfX19VIRUvfTB7XnKqtVw8PDmJubw9bWliQWQLldyeRCDXy591SlflVSQg2yd0s8nE6nSEqx2/DUU0/tKtIMlM9yJURnt4qX+rmJX1SDVf6MTxqW7H8FqP8HP/gBfvCDHwAoawq98847T+T3sLVCzabV1VWppHDW18TEhEZXSqXL7/bz4vG4lHPZcmFrqK6uTrAcer1egyUgfR14XHLO5/PSniSejZgrHs6xsTFEIhGsr6/LoGsqQ7PNsL29jY2NDRlozOfk5f3gwQMAkFI6QagqU8hisQgQlpg6oFx5ePDgAWZmZgBAxvIAECweRQF5QRgMBqnmqM/An6FaZ2cn4vG4tPnI7COmoKmpCVNTU1IZZJuF5XOycSgnwJYU3zGxZqqpWjlqy7i2thb19fUCbCd+I5vN4u233xanxfVl8MD1ra+vl0uNrUpm17xE+Pvn5+cFQ8OvJd6tpqZGhC7j8bjm86vVV/UzqAEZ9ezYmm5qapJAf21tTTMzr6WlRbJ8DshmqzQej+PBgwfI5/O/1RnlfmhsbITD4UA8HtewsR48eCBBFlC+BDj5oFgsChCYFxdbLHTUHNsUDoeFTLC1tQWv1ytC0Lzwo9GorDvZXEBZjZ/nhu/IYrHI3L5wOAwA8g4AaPbG6uoqbt68KRcR9//IyMiea8IZq5ubm1hbW9PsLdXYCq80yjawwkz9PXVPcpg7AAlWeRa5H0h04RBushVZoePXGQwGTE1NCYub1fi1tTXN+mez5fmbDx48EPIN24OVa6LufbIs91oz9dzTL7F6SYV4VsCLxeKuvob6XyaTSYhQ8XhcPqu6F/n7mBQQS0ZiAtfFbrdjeXlZU2XX6/VYXV2V9ww8xqoykVVZ3PPz81LFZQDIu0r1p3u9y738Ko1nR2WLF4tFjI+Pv+9Q7sq9t76+LrJLm5ubgrPb7fe7XC6poLLdv9e7TafTu/qWys+ufm5+pomJCc0a8Bl389n7ZU8sIGtpacHCwoL8/+LioiajUb8mEAggn88LqLbSvvWtb+Fb3/oWgPKQ1BdffPFJPTYAaEqii4uL+PnPfy5ZyIsvvrhr5ruX7dW/ZymZs+3UMi+AHWJ6lUB8luRZkmW1SsUYMPp3OByij0SA/Pb2Ntxut+i3ANjxnM8++6z83v/8z/+E3W6HXq/HsWPH5PmIZWDZWVUS/03t/bAOe309qx27tcEqcRZ74S/6+/tFOJEzFcl29Pv9OHnypOjORaNRkfNwOp34/Oc/r3mWvbKt3T6b+l7VFgvV03fbC1TcZmV2L/xE5efnPiFmTX1PiURCFNJZXVOfe68KTOW+5Gd75513PrIz+kF7QlUgr8zeWVVVK1bqeyI7cK9zVsnarDw3VDX/oAyb38/n/E0z8d+VFZZIJPD6668jnU7DarUKrOH91vbDnsUP+rrKv6/8LAaDAZ/5zGc+1O97P7X5yt/Jfc+qntquAnY/Wx9k7+fL1XPW3t4uieheX7ubv1RFWjOZDAKBgFRTd3vWj+odVX4t7yVO3dDr9b/Vvcf37HQ6dwjE/rb2m/iWvTBk6nn/pFXIdKXdaBAfgVHD6a233kJLSwueeeYZ/Md//AeOHDkiX/P9738f9+7dw7/927/hRz/6EX72s5/hJz/5yfv+3BMnTuDmzZtP4pEB7P7CP6wj+E3tNw1A9vpeYOdm2+vn73XpfJC98cYbO3r3H8Xn+F3tN70Q9vrzyou90mHvtm4jIyOavfJRvc+P8ns/zD75qO2jDMiehP02a/1+wdqHvRRJdvht1v53PWP7eUbf71kqz9CT+B3Ak9/3v2nQ837ndWlpCWNjY3jllVf25V3x+SqTmd/253yU6/5R+5aP61x82LjliVXIamtr8S//8i945ZVXUCgU8M1vfhNHjhzB3//93+PEiRP43Oc+hz/90z/FH//xH6O7uxtutxs/+tGPntTj/E62F2X4dzUV9/C7fu9uP2e3n//b/s7deve/68/8KOyDfvdef1/555Xv+LdZt4/yfX5U3/th9snvm/02a/1h99H7ff/v4vR/1zO2n2e00j6OZ/m49/1v8pk+zHmNRCKfWJ/6cf+cJ2mftGd8ohiyV199Fa+++qrmz/7hH/5B/ttkMuGnP/3pk3yEqlWtalWrWtWqVrVPvNXs9wNUrWpVq1rVqla1qv2+WzUgq1rVqla1qlWtalXbZ6sGZFWrWtWqVrWqVa1q+2zVgKxqVata1apWtapVbZ+tGpBVrWpVq1rVqla1qu2zVQOyqlWtalWrWtWqVrV9tmpAVrWqVa1qVata1aq2z1YNyKpWtapVrWpVq1rV9tmqAVnVqla1qlWtalWr2j5bNSCrWtWqVrWqVa1qVdtne2LDxZ+Ueb1edHR0PLGfH41G0dDQ8MR+/v9Wq67LTquuye5WXZfdrbouO626JrtbdV12t/+t6zI7O4vV1dUP/Lr/dQHZk7YPO5X9982q67LTqmuyu1XXZXerrstOq67J7lZdl93t//q6VFuWVata1apWtapVrWr7bNWArGpVq1rVqla1qlVtn03/3e9+97v7/RCfNHv66af3+xE+kVZdl51WXZPdrbouu1t1XXZadU12t+q67G7/l9eliiGrWtWqVrWqVa1qVdtnq7Ysq1a1qlWtalWrWtX22aoBmWJvvPEGDh48iO7ubvzjP/7jfj/OvllHRweOHj2K48eP48SJEwCAtbU1nDt3Dj09PTh37hzi8fg+P+WTt29+85tobGxEf3+//Nle61AqlfCXf/mX6O7uxsDAAG7fvr1fj/3Ebbd1+e53v4uWlhYcP34cx48fx+uvvy5/973vfQ/d3d04ePAgLly4sB+P/MRtYWEBn/rUp9DX14cjR47gn//5nwFU98te6/L7vF+y2SxOnjyJY8eO4ciRI/jOd74DAJiZmcGpU6fQ3d2Nr371q9ja2gIA5HI5fPWrX0V3dzdOnTqF2dnZfXz6J2d7rcuf/MmfoLOzU/bK6OgogP+jZ6hUtVKpVCrl8/nSgQMHStPT06VcLlcaGBgo3b9/f78fa1+svb29FI1GNX/213/916Xvfe97pVKpVPre975X+pu/+Zv9eLSP1S5dulS6detW6ciRI/Jne63D+fPnS5/5zGdKxWKxdPXq1dLJkyf35Zk/DtttXb7zne+U/umf/mnH196/f780MDBQymazpUePHpUOHDhQyufzH+fjfiwWCoVKt27dKpVKpVIymSz19PSU7t+//3u/X/Zal9/n/VIsFkupVKpUKpVKW1tbpZMnT5auXr1a+spXvlL64Q9/WCqVSqVvf/vbpX/9138tlUql0ve///3St7/97VKpVCr98Ic/LP3RH/3R/jz4E7a91uUb3/hG6ac//emOr/+/eIaqFbL37Pr16+ju7saBAwdgMBjwta99Da+99tp+P9Ynxl577TV84xvfAAB84xvfwC9+8Yt9fqInb2fOnIHb7db82V7r8Nprr+HrX/86dDodhoaGsL6+juXl5Y/9mT8O221d9rLXXnsNX/va12A0GtHZ2Ynu7m5cv379CT/hx29+vx+Dg4MAAJvNhsOHD2Npaen3fr/stS572e/DftHpdLBarQCA/9/e/cdUVf9xHH/euI5hU9nSq3fUH4FZKNxL6Y1m0eC6+od1S6AyrpJQbv3SrVqtrZaZlrp+rJltLS2lYrtrbFkKVs6ioGyw9Eq2kYwkJR0rmHBJsAt8vn8Y5wsh+tWvdID7emxs997zuZ/zvu+9792bc869n2g0SjQaxeFw8OWXX1JQUAAMr5WBGiooKGDv3r2YCXjp90h5GclEfA+pIfvbb7/9xlVXXWXdv/LKK8/5wTGRORwObr/9dubPn88777wDQGtrK263G4BZs2bR2tpqZ4i2GSkPqh/YvHkzHo+HkpIS69RcLOalubmZAwcOkJmZqXoZZHBeILbrpa+vj4yMDFwuF7fddhspKSkkJibidDqBoa97cE6cTifTpk2jra3NtthH0z/zMlArzz77LB6Ph8cff5zTp08DE7NW1JDJMDU1Nezfv5/du3fz1ltv8c033wzZ7nA4zvmfS6xQHv7r4YcfpqmpiXA4jNvt5sknn7Q7JFt0dXWRn5/PG2+8wdSpU4dsi+V6+WdeYr1e4uLiCIfDtLS0UFtbS0NDg90hjQn/zMuhQ4dYv349DQ0N1NXV0d7ezsaNG+0Oc9SoIftbUlISx44ds+63tLSQlJRkY0T2GXjdLpeLxYsXU1tby8yZM63DwSdOnMDlctkZom1GykOs18/MmTOJi4vjsssuY8WKFdZppljKSzQaJT8/n2AwSF5eHqB6gZHzEuv1ApCYmEhOTg779u3j5MmT9Pb2AkNf9+Cc9Pb20tHRwRVXXGFbzP+Ggbx89tlnuN1uHA4H8fHxFBcXT+haUUP2N5/PR2NjI0eOHOGvv/4iFAoRCATsDutf9+effxKJRKzbX3zxBWlpaQQCAUpLSwEoLS3lzjvvtDNM24yUh0AgwPvvv48xhu+//55p06ZZp6piweBrNz7++GPrG5iBQIBQKMTp06c5cuQIjY2N3HjjjXaFOWqMMTzwwAOkpqbyxBNPWI/Her2MlJdYrpfff/+dkydPAtDd3c2ePXtITU0lJyeH8vJyYHitDNRQeXk5fr9/Qh5pPVterrvuOqtWjDHs2LFjSK1MuPeQjV8oGHMqKirMNddcY5KTk826devsDscWTU1NxuPxGI/HY+bOnWvl4Y8//jB+v9/Mnj3bLFq0yLS1tdkc6ehbsmSJmTVrlnE6nSYpKcls3bp1xDz09/ebRx55xCQnJ5u0tDRTV1dnc/Sj52x5Wbp0qUlLSzPp6enmjjvuMMePH7fGr1u3ziQnJ5s5c+aYyspKGyMfPdXV1QYw6enpxuv1Gq/XayoqKmK+XkbKSyzXy8GDB01GRoZJT0838+bNM2vWrDHGnPns9fl8JiUlxRQUFJienh5jjDHd3d2moKDApKSkGJ/PZ5qamuwMf9SMlJecnByTlpZm5s2bZ4LBoPVNzIn4HtIv9YuIiIjYTKcsRURERGymhkxERETEZmrIRERERGymhuWkhScAAATISURBVExERETEZmrIRERERGymhkxEbDOwdt2A7du389hjj13QHJ9++ikbNmy4lGENYYzB7/fT2dk5bNsLL7zAq6++esn2tWvXLp5//vlLNp+IjB9qyERk3Ort7SUQCPDMM8+M2j4qKyvxer3DlkIaDbm5uezcuZNTp06N+r5EZGxRQyYiY1JzczN+vx+Px8OiRYs4evQoAMuXL+ehhx4iMzOTp59+eshRtYyMDOsvISGBr7/+mvb2du666y48Hg833XQT9fX1wJmjWyUlJWRnZ5OcnMymTZvOGkdZWdmQlSleeukl5syZwy233MLPP/9sPb5lyxZ8Ph9er5f8/HxOnTpFJBLh6quvJhqNAtDZ2Wnd37RpE3PnzsXj8bBkyRLgzHqX2dnZ7Nq169InVETGNDVkImKb7u7uIU3U4NN1K1eu5P7776e+vp5gMMiqVausbS0tLXz33Xe8/vrrQ+YLh8OEw2HWrl3LggULWLhwIatXr+b666+nvr6el19+maKiImt8Q0MDn3/+ObW1taxZs8ZqnAb79ttvmT9/PgA//PADoVCIcDhMZWUldXV11ri8vDzq6uo4ePAgqampvPvuu0yZMoXs7GwqKioACIVC5OXlMWnSJDZs2MCBAweor6/n7bfftuZZsGAB1dXV/2dmRWS8UUMmIrZJSEiwmqhwOMyLL75obdu3bx+FhYUALFu2jJqaGmvb3XffTVxc3FnnbGxs5KmnnuKjjz5i0qRJ1NTUsGzZMgD8fj9tbW3W9WC5ubnEx8czffp0XC4Xra2tw+Zrb29nypQpAFRXV7N48WImT57M1KlTh6x3e+jQIbKyskhPT6esrIyffvoJgAcffJBt27YBsG3bNoqLiwHweDwEg0E+/PBDnE6nNY/L5eL48eMXmEkRGe/UkInIuHP55Zef9fGuri7uuecetmzZ8j8tNBwfH2/djouLo7e3d9gYp9NJf3//eedavnw5mzdv5scff2T16tX09PQAcPPNN9Pc3ExVVRV9fX3W4sgVFRU8+uij7N+/H5/PZ+27p6eHhISE8+5PRCYWNWQiMiYtXLiQUCgEnLmOKysr67zPKSkpobi4eMjYrKwsysrKAKiqqmL69OkXdIH+tddeyy+//ALArbfeyo4dO+ju7iYSibBz505rXCQSwe12E41Grf0NKCoqorCw0Do61t/fz7Fjx8jJyWHjxo10dHTQ1dUFwOHDh62mTURih/P8Q0RE/n1vvvkmxcXFvPLKK8yYMcM67TeSX3/9lfLycg4fPsx7770HwNatW62L9z0eD5MnT6a0tPSC4sjNzaWqqorZs2dzww03cO+99+L1enG5XPh8Pmvc2rVryczMZMaMGWRmZhKJRKxtwWCQ5557jvvuuw+Avr4+li5dSkdHB8YYVq1aRWJiIgBfffUV69evv6AYRWT8cxhjjN1BiIiMVSdOnKCoqIg9e/Zc9Bzl5eV88sknfPDBB+cc19raSmFhIXv37r3ofYnI+KQjZCIi5+B2u1mxYgWdnZ0X9VtkK1euZPfu3VRWVp537NGjR3nttdcuJkwRGed0hExERETEZrqoX0RERMRmashEREREbKaGTERERMRmashEREREbKaGTERERMRmashEREREbPYflQj3tzSWKMMAAAAASUVORK5CYII=\n",
|
|
"text/plain": [
|
|
"<Figure size 720x432 with 1 Axes>"
|
|
]
|
|
},
|
|
"metadata": {},
|
|
"output_type": "display_data"
|
|
}
|
|
],
|
|
"source": [
|
|
"from fbprophet.plot import plot_cross_validation_metric\n",
|
|
"fig = plot_cross_validation_metric(df_cv, metric='mape')"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"The size of the rolling window in the figure can be changed with the optional argument `rolling_window`, which specifies the proportion of forecasts to use in each rolling window. The default is 0.1, corresponding to 10% of rows from `df_cv` included in each window; increasing this will lead to a smoother average curve in the figure. The `initial` period should be long enough to capture all of the components of the model, in particular seasonalities and extra regressors: at least a year for yearly seasonality, at least a week for weekly seasonality, etc.\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"### Parallelizing cross validation\n",
|
|
"\n",
|
|
"Cross-validation can also be run in parallel mode in Python, by setting specifying the `parallel` keyword. Four modes are supported\n",
|
|
"\n",
|
|
"* `parallel=None` (Default, no parallelization)\n",
|
|
"* `parallel=\"processes\"`\n",
|
|
"* `parallel=\"threads\"`\n",
|
|
"* `parallel=\"dask\"`\n",
|
|
"\n",
|
|
"For problems that aren't too big, we recommend using `parallel=\"processes\"`. It will achieve the highest performance when the parallel cross validation can be done on a single machine. For large problems, a [Dask](https://dask.org) cluster can be used to do the cross validation on many machines. You will need to [install Dask](https://docs.dask.org/en/latest/install.html) separately, as it will not be installed with `fbprophet`.\n",
|
|
"\n",
|
|
"\n",
|
|
"```python\n",
|
|
"from dask.distributed import Client\n",
|
|
"\n",
|
|
"client = Client() # connect to the cluster\n",
|
|
"df_cv = cross_validation(m, initial='730 days', period='180 days', horizon='365 days',\n",
|
|
" parallel=\"dask\")\n",
|
|
"```"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"### Hyperparameter tuning\n",
|
|
"\n",
|
|
"Cross-validation can be used for tuning hyperparameters of the model, such as `changepoint_prior_scale` and `seasonality_prior_scale`. A Python example is given below, with a 4x4 grid of those two parameters, with parallelization over cutoffs. Here parameters are evaluated on RMSE averaged over a 30-day horizon, but different performance metrics may be appropriate for different problems."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 12,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
" changepoint_prior_scale seasonality_prior_scale rmse\n",
|
|
"0 0.001 0.01 0.757489\n",
|
|
"1 0.001 0.10 0.745049\n",
|
|
"2 0.001 1.00 0.753315\n",
|
|
"3 0.001 10.00 0.763111\n",
|
|
"4 0.010 0.01 0.536260\n",
|
|
"5 0.010 0.10 0.538103\n",
|
|
"6 0.010 1.00 0.544326\n",
|
|
"7 0.010 10.00 0.520970\n",
|
|
"8 0.100 0.01 0.524669\n",
|
|
"9 0.100 0.10 0.521302\n",
|
|
"10 0.100 1.00 0.520692\n",
|
|
"11 0.100 10.00 0.515338\n",
|
|
"12 0.500 0.01 0.532103\n",
|
|
"13 0.500 0.10 0.528939\n",
|
|
"14 0.500 1.00 0.525256\n",
|
|
"15 0.500 10.00 0.524619\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"import itertools\n",
|
|
"import numpy as np\n",
|
|
"import pandas as pd\n",
|
|
"\n",
|
|
"param_grid = { \n",
|
|
" 'changepoint_prior_scale': [0.001, 0.01, 0.1, 0.5],\n",
|
|
" 'seasonality_prior_scale': [0.01, 0.1, 1.0, 10.0],\n",
|
|
"}\n",
|
|
"\n",
|
|
"# Generate all combinations of parameters\n",
|
|
"all_params = [dict(zip(param_grid.keys(), v)) for v in itertools.product(*param_grid.values())]\n",
|
|
"rmses = [] # Store the RMSEs for each params here\n",
|
|
"\n",
|
|
"# Use cross validation to evaluate all parameters\n",
|
|
"for params in all_params:\n",
|
|
" m = Prophet(**params).fit(df) # Fit model with given params\n",
|
|
" df_cv = cross_validation(m, cutoffs=cutoffs, horizon='30 days', parallel=\"processes\")\n",
|
|
" df_p = performance_metrics(df_cv, rolling_window=1)\n",
|
|
" rmses.append(df_p['rmse'].values[0])\n",
|
|
"\n",
|
|
"# Find the best parameters\n",
|
|
"tuning_results = pd.DataFrame(all_params)\n",
|
|
"tuning_results['rmse'] = rmses\n",
|
|
"print(tuning_results)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 13,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"{'changepoint_prior_scale': 0.1, 'seasonality_prior_scale': 10.0}\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"best_params = all_params[np.argmin(rmses)]\n",
|
|
"print(best_params)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"Alternatively, parallelization could be done across parameter combinations by parallelizing the loop above.\n",
|
|
"\n",
|
|
"The Prophet model has a number of input parameters that one might consider tuning. Here are some general recommendations for hyperparameter tuning that may be a good starting place.\n",
|
|
"\n",
|
|
"**Parameters that can be tuned**\n",
|
|
"- `changepoint_prior_scale`: This is probably the most impactful parameter. It determines the flexibility of the trend, and in particular how much the trend changes at the trend changepoints. As described in this documentation, if it is too small, the trend will be underfit and variance that should have been modeled with trend changes will instead end up being handled with the noise term. If it is too large, the trend will overfit and in the most extreme case you can end up with the trend capturing yearly seasonality. The default of 0.05 works for many time series, but this could be tuned; a range of [0.001, 0.5] would likely be about right. Parameters like this (regularization penalties; this is effectively a lasso penalty) are often tuned on a log scale.\n",
|
|
"\n",
|
|
"- `seasonality_prior_scale`: This parameter controls the flexibility of the seasonality. Similarly, a large value allows the seasonality to fit large fluctuations, a small value shrinks the magnitude of the seasonality. The default is 10., which applies basically no regularization. That is because we very rarely see overfitting here (there's inherent regularization with the fact that it is being modeled with a truncated Fourier series, so it's essentially low-pass filtered). A reasonable range for tuning it would probably be [0.01, 10]; when set to 0.01 you should find that the magnitude of seasonality is forced to be very small. This likely also makes sense on a log scale, since it is effectively an L2 penalty like in ridge regression.\n",
|
|
"\n",
|
|
"- `holidays_prior_scale`: This controls flexibility to fit holiday effects. Similar to seasonality_prior_scale, it defaults to 10.0 which applies basically no regularization, since we usually have multiple observations of holidays and can do a good job of estimating their effects. This could also be tuned on a range of [0.01, 10] as with seasonality_prior_scale.\n",
|
|
"\n",
|
|
"- `seasonality_mode`: Options are [`'additive'`, `'multiplicative'`]. Default is `'additive'`, but many business time series will have multiplicative seasonality. This is best identified just from looking at the time series and seeing if the magnitude of seasonal fluctuations grows with the magnitude of the time series (see the documentation here on multiplicative seasonality), but when that isn't possible, it could be tuned.\n",
|
|
"\n",
|
|
"**Maybe tune?**\n",
|
|
"- `changepoint_range`: This is the proportion of the history in which the trend is allowed to change. This defaults to 0.8, 80% of the history, meaning the model will not fit any trend changes in the last 20% of the time series. This is fairly conservative, to avoid overfitting to trend changes at the very end of the time series where there isn't enough runway left to fit it well. With a human in the loop, this is something that can be identified pretty easily visually: one can pretty clearly see if the forecast is doing a bad job in the last 20%. In a fully-automated setting, it may be beneficial to be less conservative. It likely will not be possible to tune this parameter effectively with cross validation over cutoffs as described above. The ability of the model to generalize from a trend change in the last 10% of the time series will be hard to learn from looking at earlier cutoffs that may not have trend changes in the last 10%. So, this parameter is probably better not tuned, except perhaps over a large number of time series. In that setting, [0.8, 0.95] may be a reasonable range.\n",
|
|
"\n",
|
|
"**Parameters that would likely not be tuned**\n",
|
|
"- `growth`: Options are 'linear' and 'logistic'. This likely will not be tuned; if there is a known saturating point and growth towards that point it will be included and the logistic trend will be used, otherwise it will be linear.\n",
|
|
"\n",
|
|
"- `changepoints`: This is for manually specifying the locations of changepoints. None by default, which automatically places them.\n",
|
|
"\n",
|
|
"- `n_changepoints`: This is the number of automatically placed changepoints. The default of 25 should be plenty to capture the trend changes in a typical time series (at least the type that Prophet would work well on anyway). Rather than increasing or decreasing the number of changepoints, it will likely be more effective to focus on increasing or decreasing the flexibility at those trend changes, which is done with `changepoint_prior_scale`.\n",
|
|
"\n",
|
|
"- `yearly_seasonality`: By default ('auto') this will turn yearly seasonality on if there is a year of data, and off otherwise. Options are ['auto', True, False]. If there is more than a year of data, rather than trying to turn this off during HPO, it will likely be more effective to leave it on and turn down seasonal effects by tuning `seasonality_prior_scale`.\n",
|
|
"\n",
|
|
"- `weekly_seasonality`: Same as for `yearly_seasonality`.\n",
|
|
"\n",
|
|
"- `daily_seasonality`: Same as for `yearly_seasonality`.\n",
|
|
"\n",
|
|
"- `holidays`: This is to pass in a dataframe of specified holidays. The holiday effects would be tuned with `holidays_prior_scale`.\n",
|
|
"\n",
|
|
"- `mcmc_samples`: Whether or not MCMC is used will likely be determined by factors like the length of the time series and the importance of parameter uncertainty (these considerations are described in the documentation).\n",
|
|
"\n",
|
|
"- `interval_width`: Prophet `predict` returns uncertainty intervals for each component, like `yhat_lower` and `yhat_upper` for the forecast `yhat`. These are computed as quantiles of the posterior predictive distribution, and `interval_width` specifies which quantiles to use. The default of 0.8 provides an 80% prediction interval. You could change that to 0.95 if you wanted a 95% interval. This will affect only the uncertainty interval, and will not change the forecast `yhat` at all and so does not need to be tuned.\n",
|
|
"\n",
|
|
"- `uncertainty_samples`: The uncertainty intervals are computed as quantiles from the posterior predictive interval, and the posterior predictive interval is estimated with Monte Carlo sampling. This parameter is the number of samples to use (defaults to 1000). The running time for predict will be linear in this number. Making it smaller will increase the variance (Monte Carlo error) of the uncertainty interval, and making it larger will reduce that variance. So, if the uncertainty estimates seem jagged this could be increased to further smooth them out, but it likely will not need to be changed. As with `interval_width`, this parameter only affects the uncertainty intervals and changing it will not affect in any way the forecast `yhat`; it does not need to be tuned.\n",
|
|
"\n",
|
|
"- `stan_backend`: If both pystan and cmdstanpy backends set up, the backend can be specified. The predictions will be the same, this will not be tuned."
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"celltoolbar": "Edit Metadata",
|
|
"kernelspec": {
|
|
"display_name": "Python 3",
|
|
"language": "python",
|
|
"name": "python3"
|
|
},
|
|
"language_info": {
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 3
|
|
},
|
|
"file_extension": ".py",
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"nbconvert_exporter": "python",
|
|
"pygments_lexer": "ipython3",
|
|
"version": "3.7.8"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 1
|
|
}
|