{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "8ed93914",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import localprojections as lp\n",
    "import statsmodels.api as sm\n",
    "from scipy.stats import norm"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c34782af",
   "metadata": {},
   "source": [
    "# What is a Local Projection?\n",
    "Local Projections (LP), introduced by Jordà (2005), are an econometric method used to estimate the dynamic response of a variable (e.g., GDP, inflation) to a shock over multiple time horizons. \n",
    "\n",
    "For each forecast horizon $( h = 0, 1, \\dots, H )$, LPs estimate a regression of the form:\n",
    "\n",
    "$$\n",
    "y_{t+h} = \\alpha_h + \\theta_h z_t + \\gamma_h^\\top X_t + \\varepsilon_{t+h}\n",
    "$$\n",
    "\n",
    "where:\n",
    "- $( y_{t+h})$: response variable at future horizon $( h ),$\n",
    "- $( z_t)$: shock variable at time $( t )$,\n",
    "- $( X_t)$: vector of control variables (lags, dummies, etc.),\n",
    "- $( \\theta_h )$: impulse response at horizon $( h )$.\n",
    "\n",
    "LPs are attractive due to their simplicity and flexibility, especially compared to VARs."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6f229e33",
   "metadata": {},
   "source": [
    "The goal of this notebook is to replicate Figure 5 from Jordà (2005), which shows impulse response \n",
    "functions (IRFs) of three macroeconomic variables:\n",
    "- Output Gap (GDP_gap),\n",
    "- Inflation (Infl),\n",
    "- Federal Funds Rate (FF),\n",
    "\n",
    "in response to shocks in each of these variables using the LP method. We use quarterly U.S. data and estimate horizon-specific IRFs with two lags of all variables."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "7c81e78d",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load the data\n",
    "data = pd.read_csv(\"lplin_data.csv\")\n",
    "Y = ['GDP_gap', 'Infl', 'FF']  # endogenous variables"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7536e956",
   "metadata": {},
   "source": [
    "## Econometric Reasoning Behind LPs\n",
    "**LPs as a sequence of conditional expectations**\n",
    "$$\n",
    "\\theta_h = \\frac{\\partial \\mathbb{E}[y_{t+h}|shock_t]}{\\partial shock_t}\n",
    "$$\n",
    "- Interpretation: $\\theta_h$ captures the marginal effect of a shock at time $t$ on the expected value of $y$ at horizon $t + h$;\n",
    "- Estimating impulse responses as derivatives of conditional expectations avoids assumptions about the full dynamic system;\n",
    "- Each horizon h is treated as a separate estimation problem, allowing the response to evolve flexibly over time."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "449705f3",
   "metadata": {},
   "source": [
    "| Feature             | VARs                   | Local Projections (LPs) |\n",
    "|---------------------|------------------------|--------------------------|\n",
    "| Estimation          | System of equations    | Separate regressions     |\n",
    "| Flexibility         | Less                   | More                     |\n",
    "| Misspecification    | Sensitive              | More robust              |\n",
    "| Long horizon noise  | Less noisy (if correct)| More noisy               |\n",
    "| Ease of extension   | More complex           | Easier                   |"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "b6b63d95",
   "metadata": {},
   "outputs": [],
   "source": [
    "def Local_Projections(\n",
    "    data,\n",
    "    Y,                # List of all system variables (e.g., ['GDP_gap','Infl','FF'])\n",
    "    response,         # List of response variables for which IRFs are estimated\n",
    "    horizon,          # Max forecast horizon (0..horizon)\n",
    "    lags,             # Number of lags included for each variable\n",
    "    newey_lags,       # Maxlags for Newey-West HAC SE\n",
    "    ci_width,         # E.g. 0.95 for a 95% CI\n",
    "    shock=None,       # If not None, only extract IRFs for these shock vars\n",
    "    store_internals=False  # If True, also store design matrix, fitted, residuals for bootstrap\n",
    "):\n",
    "    \"\"\"\n",
    "    Estimates IRFs by local projections for each horizon h=0..H, each response in 'response',\n",
    "    building a design matrix with 0..lags for each var in Y. Optionally stores 'internals'\n",
    "    for each (r, h) so that we can do a bootstrap later without re-running the entire code.\n",
    "\n",
    "    Returns\n",
    "    -------\n",
    "    results : dict\n",
    "        results[resp][shock] = dict of arrays: 'irf', 'lower', 'upper' (length horizon+1)\n",
    "    horizon_internals : dict (only if store_internals=True)\n",
    "        horizon_internals[resp][h] = {\n",
    "            'X_reg': DataFrame of regressors,\n",
    "            'fitted': array of fitted values,\n",
    "            'resid': array of residuals\n",
    "        }\n",
    "    \"\"\"\n",
    "    if shock is None:\n",
    "        shock = Y.copy()\n",
    "\n",
    "    # Prepare data structures for IRF results\n",
    "    z_val = norm.ppf(1 - (1 - ci_width)/2)\n",
    "    results = {\n",
    "        r: {s: {\"irf\": [], \"lower\": [], \"upper\": []} for s in shock}\n",
    "        for r in response\n",
    "    }\n",
    "\n",
    "    # Optionally store internals if store_internals == True\n",
    "    horizon_internals = {}\n",
    "    if store_internals:\n",
    "        horizon_internals = {\n",
    "            r: {h: {} for h in range(horizon+1)}\n",
    "            for r in response\n",
    "        }\n",
    "\n",
    "    # Loop over horizons and response variables\n",
    "    for h in range(horizon+1):\n",
    "        for r in response:\n",
    "            # Dependent variable: y_{t+h}\n",
    "            y_shift = data[r].shift(-h)\n",
    "\n",
    "            # Build the design matrix: for each var in Y, include lag0..lags\n",
    "            X_parts = []\n",
    "            col_names = []\n",
    "            for var in Y:\n",
    "                for lag_i in range(lags+1):\n",
    "                    X_parts.append(data[var].shift(lag_i))\n",
    "                    col_names.append(f\"{var}_lag{lag_i}\")\n",
    "            X = pd.concat(X_parts, axis=1)\n",
    "            X.columns = col_names\n",
    "\n",
    "            # Add constant\n",
    "            X = sm.add_constant(X)\n",
    "\n",
    "            # Align, drop missing\n",
    "            df_reg = pd.concat([y_shift, X], axis=1).dropna()\n",
    "            y_reg = df_reg.iloc[:,0]\n",
    "            X_reg = df_reg.iloc[:,1:]  # keep as DataFrame for column names\n",
    "\n",
    "            # OLS with NW\n",
    "            model = sm.OLS(y_reg, X_reg).fit(cov_type='HAC', cov_kwds={'maxlags': newey_lags})\n",
    "\n",
    "            # Save fitted & residual if needed\n",
    "            if store_internals:\n",
    "                horizon_internals[r][h]['X_reg'] = X_reg\n",
    "                horizon_internals[r][h]['fitted'] = model.fittedvalues.values\n",
    "                horizon_internals[r][h]['resid']  = model.resid.values\n",
    "\n",
    "            # Extract IRFs for each shock variable\n",
    "            for s in shock:\n",
    "                col_shock = f\"{s}_lag0\"\n",
    "                coef = model.params.get(col_shock, np.nan)\n",
    "                se   = model.bse.get(col_shock, np.nan)\n",
    "\n",
    "                results[r][s][\"irf\"].append(coef)\n",
    "                results[r][s][\"lower\"].append(coef - z_val * se)\n",
    "                results[r][s][\"upper\"].append(coef + z_val * se)\n",
    "\n",
    "    # Convert to arrays\n",
    "    for r in response:\n",
    "        for s in shock:\n",
    "            for key in [\"irf\",\"lower\",\"upper\"]:\n",
    "                results[r][s][key] = np.array(results[r][s][key])\n",
    "\n",
    "    # Return results. If store_internals, also return horizon_internals\n",
    "    if store_internals:\n",
    "        return results, horizon_internals\n",
    "    else:\n",
    "        return results, None\n",
    "\n",
    "def show_irfs(horizon, irf_results, shock_vars, response_vars, bootstrap_draws: dict = None):\n",
    "    if bootstrap_draws == None:\n",
    "        horizons_arr = np.arange(horizon+1)\n",
    "        n_shocks = len(shock_vars)\n",
    "        fig, axes = plt.subplots(1, n_shocks, figsize=(5*n_shocks, 4), sharey=True)\n",
    "        if n_shocks == 1:\n",
    "            axes = [axes]\n",
    "        for i, s in enumerate(shock_vars):\n",
    "            ax = axes[i]\n",
    "            irf_curve = irf_results[response_vars[0]][s][\"irf\"]\n",
    "            lower_curve = irf_results[response_vars[0]][s][\"lower\"]\n",
    "            upper_curve = irf_results[response_vars[0]][s][\"upper\"]\n",
    "            ax.plot(horizons_arr, irf_curve, marker='o', label=f\"IRF to {s} shock\")\n",
    "            ax.fill_between(horizons_arr, lower_curve, upper_curve, color='gray', alpha=0.3, label=\"95% CI\")\n",
    "            ax.axhline(0, color='black', linestyle='--', linewidth=1)\n",
    "            ax.set_xlabel(\"Horizon\")\n",
    "            ax.set_title(f\"Response of {response_vars[0]} to {s} shock\")\n",
    "            ax.legend()\n",
    "            ax.grid(True)\n",
    "        axes[0].set_ylabel(\"Impulse Response\")\n",
    "        plt.suptitle(f\"IRFs of {response_vars[0]} to Shocks in All Variables\")\n",
    "        plt.tight_layout(rect=[0, 0, 1, 0.95])\n",
    "        plt.show()\n",
    "    else:\n",
    "        horizons_arr = np.arange(horizon+1)\n",
    "        n_shocks = len(shock_vars)\n",
    "        fig, axes = plt.subplots(1, n_shocks, figsize=(5*n_shocks, 4), sharey=True)\n",
    "        if n_shocks == 1:\n",
    "            axes = [axes]\n",
    "        for i, s in enumerate(shock_vars):\n",
    "            ax = axes[i]\n",
    "            irf_curve = irf_results[response_vars[0]][s][\"irf\"]\n",
    "            lower_curve = irf_results[response_vars[0]][s][\"lower\"]\n",
    "            upper_curve = irf_results[response_vars[0]][s][\"upper\"]\n",
    "            # The bootstrap distribution, shape (B, horizon+1)\n",
    "            draws = bootstrap_draws[response_vars[0]][s]\n",
    "            # percentile intervals\n",
    "            alpha = 0.05\n",
    "            lower_q = 100*(alpha/2)\n",
    "            upper_q = 100*(1-alpha/2)\n",
    "            irf_lower_bs = np.percentile(draws, lower_q, axis=0)\n",
    "            irf_upper_bs = np.percentile(draws, upper_q, axis=0)\n",
    "\n",
    "            ax.plot(horizons_arr, irf_curve, marker='o', label=f\"IRF to {s} shock\")\n",
    "            ax.fill_between(horizons_arr, lower_curve, upper_curve, color='gray', alpha=0.3, label=\"95% CI\")\n",
    "            ax.axhline(0, color='black', linestyle='--', linewidth=1)\n",
    "            # bootstrap intervals in orange\n",
    "            ax.plot(horizons_arr, irf_curve, linestyle=':', color='red', label='Bootstrap percentile CI')\n",
    "            ax.fill_between(horizons_arr, irf_lower_bs, irf_upper_bs, color='red', alpha=0.2)\n",
    "            ax.axhline(0, color='black', linestyle='--', linewidth=1)\n",
    "            ax.set_xlabel(\"Horizon\")\n",
    "            ax.set_title(f\"Response of {response_vars[0]} to {s} shock\")\n",
    "            ax.legend()\n",
    "            ax.grid(True)\n",
    "        axes[0].set_ylabel(\"Impulse Response\")\n",
    "        plt.suptitle(f\"IRFs of {response_vars[0]} to Shocks in All Variables\")\n",
    "        plt.tight_layout(rect=[0, 0, 1, 0.95])\n",
    "        plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "35ce89c2",
   "metadata": {},
   "source": [
    "## What Do You Expect?\n",
    "\n",
    "Before we run the local projection for GDP_gap to a monetary policy shock (FF), quick thought:\n",
    "\n",
    "**Do you expect the GDP_gap to increase or decrease after a rate hike? Why?**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "b97b6adc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1500x400 with 3 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Convert columns to list (if needed)\n",
    "Y = list(data.columns)  # e.g. ['GDP_gap', 'Infl', 'FF']\n",
    "\n",
    "# Here we want to estimate the IRFs for the response variable 'Infl'\n",
    "# (i.e., how Inflation responds) to shocks from each variable in Y.\n",
    "response_vars = ['Infl']\n",
    "shock_vars = Y   # shocks from all variables in the system\n",
    "\n",
    "# Set replication parameters:\n",
    "horizon = 12      # forecast horizon: 0,1,...,12\n",
    "lags = 2          # number of lags to include for each variable\n",
    "newey_lags = 2    # HAC lags for Newey-West standard errors\n",
    "ci_width = 0.95   # 95% confidence interval\n",
    "\n",
    "# Estimate IRFs using our custom function (Step 1)\n",
    "irf_results, _ = Local_Projections(data=data, \n",
    "                                    Y=Y, \n",
    "                                    response=response_vars, \n",
    "                                    horizon=horizon, \n",
    "                                    lags=lags, \n",
    "                                    newey_lags=newey_lags, \n",
    "                                    ci_width=ci_width, \n",
    "                                    shock=shock_vars)\n",
    "\n",
    "show_irfs(horizon, irf_results, shock_vars, response_vars, )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "dd2ec781",
   "metadata": {},
   "outputs": [],
   "source": [
    "try_shock = data.drop(columns=['Infl'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "67bace4c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x400 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Convert columns to list (if needed)\n",
    "Y = list(try_shock.columns)  # e.g. ['GDP_gap', 'Infl', 'FF']\n",
    "\n",
    "# (i.e., how Inflation responds) to shocks from each variable in Y.\n",
    "response_vars = ['GDP_gap']\n",
    "shock_vars = Y   # shocks from all variables in the system\n",
    "\n",
    "# Set replication parameters:\n",
    "horizon = 12      # forecast horizon: 0,1,...,12\n",
    "lags = 1          # number of lags to include for each variable\n",
    "newey_lags = 2    # HAC lags for Newey-West standard errors\n",
    "ci_width = 0.95   # 95% confidence interval\n",
    "\n",
    "# Estimate IRFs using our custom function (Step 1)\n",
    "irf_results, _ = Local_Projections(data=try_shock, \n",
    "                                    Y=Y, \n",
    "                                    response=response_vars, \n",
    "                                    horizon=horizon, \n",
    "                                    lags=lags, \n",
    "                                    newey_lags=newey_lags, \n",
    "                                    ci_width=ci_width, \n",
    "                                    shock=shock_vars)\n",
    "\n",
    "show_irfs(horizon, irf_results, shock_vars, response_vars)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "aee07698",
   "metadata": {},
   "outputs": [],
   "source": [
    "def bootstrap_LP(data, Y, response, horizon, lags, newey_lags,ci_width=0.95, shock=None, B=500, seed=None):\n",
    "    \"\"\"\n",
    "    1) Call Local_Projections(..., store_internals=True) to get original IRFs + design/resid\n",
    "    2) For each horizon h and response var r, do the residual bootstrap\n",
    "    3) Return (original_coefs, boot_draws)\n",
    "    \"\"\"\n",
    "\n",
    "    if seed is not None:\n",
    "        np.random.seed(seed)\n",
    "\n",
    "    # Step 1: get original IRFs plus the internals\n",
    "    lp_results, horizon_internals = Local_Projections(\n",
    "        data=data, Y=Y, response=response,\n",
    "        horizon=horizon, lags=lags, newey_lags=newey_lags,\n",
    "        ci_width=ci_width, shock=shock,\n",
    "        store_internals=True\n",
    "    )\n",
    "\n",
    "    # 'lp_results' is the same dictionary of IRFs, lower, upper from NW\n",
    "    # 'horizon_internals' contains X_reg, fitted, resid for each horizon\n",
    "\n",
    "    # Let's build a structure for the boot_coefs: boot_coefs[r][s] = (B, horizon+1)\n",
    "    if shock is None:\n",
    "        shock = Y\n",
    "    boot_coefs = {\n",
    "        r: {s: np.zeros((B, horizon+1)) for s in shock}\n",
    "        for r in response\n",
    "    }\n",
    "\n",
    "    # Step 2: For each replication b, horizon h, response r:\n",
    "    for b_i in range(B):\n",
    "        for r in response:\n",
    "            for h_i in range(horizon+1):\n",
    "                # retrieve design & residual\n",
    "                X_reg = horizon_internals[r][h_i]['X_reg']\n",
    "                fitted_vals = horizon_internals[r][h_i]['fitted']\n",
    "                resid = horizon_internals[r][h_i]['resid']\n",
    "                n = len(resid)\n",
    "\n",
    "                # resample residuals\n",
    "                e_star = np.random.choice(resid, size=n, replace=True)\n",
    "                y_star = fitted_vals + e_star\n",
    "\n",
    "                # re-estimate OLS\n",
    "                model_b = sm.OLS(y_star, X_reg).fit(cov_type='HAC', cov_kwds={'maxlags': newey_lags})\n",
    "\n",
    "                # store shock coefficients\n",
    "                for s in shock:\n",
    "                    col_shock = f\"{s}_lag0\"\n",
    "                    boot_coefs[r][s][b_i, h_i] = model_b.params.get(col_shock, np.nan)\n",
    "\n",
    "    return lp_results, boot_coefs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "ac8574eb",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA90AAAGMCAYAAADHg8H9AAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlHJYcgAAAAlwSFlzAAAPYQAAD2EBqD+naQABAABJREFUeJzsnQV4HFXbhp/VbNytSd1daWkLLVZKgeLuBYq7fbg7H06BAh/+41IoTpEibaHurnF33935r+dsJtlsNtpsGnnv65pmOzM7O3PGznNeM2iapkEQBEEQBEEQBEEQhDbH2PabFARBEARBEARBEASBiOgWBEEQBEEQBEEQBB8holsQBEEQBEEQBEEQfISIbkEQBEEQBEEQBEHwESK6BUEQBEEQBEEQBMFHiOgWBEEQBEEQBEEQBB8holsQBEEQBEEQBEEQfISIbkEQBEEQBEEQBEHwESK6BUEQBEEQBEEQBMFHiOgWBEHoImzfvh1HH300QkNDYTAYsGDBggO9S4KP+P3339U5/uyzz9r1d++//371u9nZ2T7Z/kUXXYQ+ffrgQMHf5j54tjP/dhT2Z594bEFBQc1al7/B8y0IgiDsPyK6BUHo1rz99tuqc7lixYp6wkKfLBaL6oxfd911yM/Pr7cNLnNf330qLy9vt2O58MILsX79ejzyyCN47733MGHChEbXLywsVOtyPQp1Pz8/9O7dG2eeeSa+/fZbrx19feK6sbGxOOyww/Doo48iKyurwbbVJ5vNhkGDBuGaa65BRkYGOjPfffedzwTJwoULMX36dMTExCAgIAD9+vXDGWecgR9++MEnv9dd4DnjddijRw84nc422+4JJ5ygzlNRUVGD65x77rmwWq3Iyclps98VBEEQOg/mA70DgiAIHZVXXnlFWYVKSkrwyy+/4MUXX8SqVavw119/1Vt3zJgxuPnmm+vNZ0e7PSgrK8PSpUtx1113KVHbFDt27MDMmTOxd+9enHzyybjgggvUsSYlJSlxcvzxx+Pdd9/F+eefX+d7HHg46KCD4HA4lNBesmQJ7rvvPjzzzDP45JNPcMQRR9T7rQcffBB9+/ZVAxBsO7Yrf2PDhg1KrHRGuP/z5s1rc+H93//+F7feeqsS3XfccYdqH56rRYsW4aOPPsIxxxyDrszrr7/epoLYnf/7v/9TA2R79uzBr7/+iqOOOqpNtktBzYGSL7/8Ut1HnpSWluKrr75S5y4yMnK/f2/atGnqfm+vZ4sgCIKw/4joFgRBaIDTTjsNUVFR6vPll1+Os846Cx9//DH+/fdfTJw4sc66CQkJOO+88w7QnqLG0hwWFtbkuna7XQltWpsXL16MqVOn1llOEf3TTz8pYe3JoYceqtrFnbVr1yq39lNPPRWbNm1CfHx8neWzZs2qsbpfeumlSnhQpFOInH322a063q4Iz8tDDz2EGTNmqPb3JDMzE10depX4Ag6c8Xp77LHH8NZbbykB3laim5bu4OBgfPDBB15FN3+Xv09xvj9w0IpC22g0Kq8RQRAEofMg7uWCIAjNhIKT7Ny5s8XfpevpDTfcoCxtdM2m6zDFFS3nTbF69WolXENCQpQ1+sgjj8SyZctqltPaSrdwQispXWgbi4v99NNPlZX5nnvuqSe4dSii+ZvNYfTo0XjuueeU6/1LL73U5Pq6NXz37t1oLrTs0crOQRAKHAqdlJSUenGntNxfddVVGDx4MPz9/ZXAP/3005V105vr+x9//KEGVLge25eiKS8vr8m4WFq5ibv7vA4FFr0eevbsqc4194UWbE3TGt0u46Tp8t/QOeE14wmtwgwRSExMVEKM1wYt497O+fjx41WbsA05QMT282TLli3KlT06Olqty32n90RjsM0HDBiAESNG1IQNML8AB2Hi4uLUfnH/OGhVUFDQophunje2LdvvtddeQ//+/VWb0tti+fLlaC60QvMa4rXA/fjiiy/aLPSD7XTKKacobxhvAyMU4/o1m5ubi1tuuQUjR45U9zKvOd5nHLjyFs5B74a7775bDerR64HXh7eY7j///FMdW69evVT78Nq78cYb1TF7Y9euXcrTJTAwULnb0xulqeuT8Jq5+OKLVWgJf2f48OF48803661HryAu4z6Hh4erQTe2gyAIQndFLN2CIAjNRBdu7ER6UlVVVS+5FDucuvv0FVdcoZJe0fV72LBhKraTrtabN2/GuHHjGvzNjRs3KrHPzvltt92mLIHz589XsdS0Uk+aNEl1+GnhZiebluNjjz220WRJdIUlbWmZp/X7kksuURZaisDG0ActWuJqSzFG93W6ux988MHq2I877rh661GI0eWdwopCj+eM7uxsL1rhPd3ZeT7YdhTuW7duVetSROrCxhsU6ampqfj5559V7Lw7FC4UV7/99ptqD4Yd/Pjjj2owhILl2WefbfAYKaop4Hh+rr32WkRERDTZLo8//riyfFLIUdA++eSTyqL6zz//1BlgmDNnjhKqtPRSGD///PP4+++/1YCO7h2xbt06da3xGrvsssuU+OW54v40dE65nIMo3Fe2BwV9ZWWlEnQVFRXqOCi8eezffPONGphh/oCWQsHGgSu2Pc8Lj5PXPcVjc6zjtGwffvjhal94bdx+++3quChU2wK2+TvvvKOuUffwDopsnn/elzy3vJ+Z4JC/y5ALngvezwwn4PVJAewOPR9o3eb5ZXs25FLOQRW6sV955ZXqvqI3DoVvcnKyWuYOPVjo6s77iO3IXAH0bqGnBcV3Q3Bf+R22P4+RAzPff/+9us45GMBBRT1EgANkfCZcf/31anCD1xavyXPOOWc/W1oQBKGTogmCIHRj3nrrLZp3tOXLl9fMu++++9S8rVu3allZWdqePXu0N998U/P399eio6O1kpKSOtvo3bu3Wt9z4nZ0QkNDtauvvrrF+3fSSSdpVqtV27lzZ8281NRULTg4WJs2bVrNvN27d6vffOqpp5rc5tixY7WwsLB684uLi9Xx6lNBQUHNst9++01t/9NPP21wu6NHj9bCw8Prte2iRYvU9pKSkrSPPvpIi4yMVG2ZnJzcrDZYuXKl2s4NN9xQZ/5FF11Ur51LS0vrfX/p0qVqvXfffbfevo0fP16rrKysmf/kk0+q+V999VWj+8Rz6e0VumDBAjX/4YcfrjP/tNNO0wwGg7Zjx45Gt3vvvfeq7wcGBmqzZs3SHnnkEXX8nujnY+jQoVpFRUXN/Oeff17NX79+vfo/jy0mJkYbMWKEVlZWVrPeN998o9bj7+nweuJ1tXfv3jq/5XQ6690bPJ+bN2/WevTooR100EFabm5uzTqrV69u8lppiAsvvFDdT57XNa8Z99/g+eH8hQsXNrnNjIwMzWw2a6+//nrNvClTpmgnnnhivXX529wHz3bm38aw2+1afHy8Nnny5DrzX331VfX9H3/8Uf2/vLxcczgcddbhMfr5+WkPPvhgvd/t169fvWva2z55u+4fe+wxdc25n08eG7977bXX1jm/xx13nHrO8LzqeN5bl1xyiTrG7OzsOr9z1llnqeebvg9s1+HDhzfaXoIgCN0NcS8XBEFoALrW0ppDix9dKulCS8uOt+RftDjT0uc+ucd30ppISw8tpM2FFilajk866SSVwVqHMdO0GNFSTgtTS+F3vFnC6UbM49WnllqluE1vGZwZO8vt0eWVVkauR3dfusw2Bz1rN93G3aEV1RNaE929D+hRwPPG9vfmyk+LrrullJZCs9msEqW1Bn7PZDIpS587dDenjuH10xgPPPCAsuqOHTtWWUh5TugWTm8IekV4Qgu2u/VTD4GgBZgwKz9dntl27nHA9BIYMmRITZZ65gSgqz2vc7oou+PN4s/wBFpneW8wyZu794duyeb+0/raFjCjvvtveB5nY9BFm94AdHfXoeWZ56KpUILmwnPOa5vJDN1DGXgu6YpNt39Cl2zui35/8/rk/cBnjbfrkxUJ3K/phnBfh+EN9LqZMmWKuubozeCJuzVet1zTQ4Hn0hvczueff47Zs2erz9y+PtGrgV4W+v7zXqOFvSXu/4IgCF0dEd2CIAgNwE4mxTM7znSrpHhpqANMt1qKS/fJXSjTjZNChcKTSdjoztyUYKAQomhhh9yToUOHqnheZhtvKYwvLS4urjefwkwfMKBQaCncJrftCeOfuU26XNOFVo8nbS5096ZQoTuuOxTTnjCG9d57762Jp+Z5oeCnW7O3eOKBAwfW+T8FEAc1PGPAW7KvdBH2bAeeL315U1AQMkaXgpCDLhz8oHCi4PGMQ/YUyLow1cWk/nveriGKbn25fi0yLrs5cF94jBTWDH1wh+fppptuwhtvvKHan+ea10BT8dyN0dRxNsb777+v7jkKXMa7c+KgBkWmp+v1/qAnStNjlyk8eR4pxinKCe9ZhhjwunO/Pul+7a19PK/5hti3b58KwaCbP69hbpODIsRzu7yX3J9NhKX8SEPXPZ9FvIcYV+8+MMeJAz9Ej2f/z3/+o/aBbc7jvPrqq1UogyAIQndGRLcgCEIjpXkonimCKBopuNmxbk1JIyanorBhnCVF2VNPPaUSDTVl+fQFFFvsQHsm0mLHWx8waGl2ZFqVt23b5lUIs/PNbTKumuJTt/T5Alq/GX/M9mZ8LUUrzx3jXH1VispXUMwy2R7jkWnxZPy0e6w20cWcJ81JirU/0GrM/eG+eePpp59WQvLOO++sSYLH651CtDW09jiZ0I0WV3qFUADq0yGHHKKWN7T/rYEeCby3PvzwQ/V//uX+uWctZ017Dkjw2cLBAA5a8Ppk23i7Pptj5abFnNcJvRYoeBkzzm0ylp+0xXWvb4N5IDw9evRJTwDIe5z5EehhwHbm4CX/Mm5cEAShuyKJ1ARBEJoBLTfsNNKqQzFH61VLoQWV1mROtArRZZgCsaEs4bQi0ZWdHVhvWaYpXmnRbSmswc0OMQUHk7O1BUwSR3HVEgt2c2Fmdnb6me3c3TLtLUs394MClaJPh9ZhDjI0JMqYYMvdWp+WlqaS0TVGQ0nWuK900aWbvbu1m+dLX94amP2Zibq4by1B/z1eQ5411DlPX65bPumN0Rw4aEQ3fF7LPE5voQjM0M2J2beZ3I6i7NVXX8XDDz+M9oLXOMMHmPDOU7hTiL/wwgvKSuxpSW8tFNisCsABB1q8eb0ygZ379cnr7X//+1+d7/H61MsTtpT169erAS9eH+4hLRTC3uC9xAFA3bpN+H3SUNUDPot4ninwm1NqjVnRGRLAiR4FTHrHZx1rz0u5M0EQuiNi6RYEQWhBh5oZsZ944okWfY8dVU8XT2aqpsWbGYkbgiKBpbtY59fd7ZNZhNmhp/XI07W3OdAKzAzqzIzsXnqstZZSljti5mK6/NKVtK3RhfzLL79cZz69Bry1mee+cz1vNccJ3WVppddh9nJmcW6qXBpFBfEU8xTr/C3P0ml0KaZQb2y7DCVgTLA3dI8Ib27iTYl1XmsUu+7XGrfHGHE9AzxFFa2vLP9EEdrUtcBjYdsxQzUHOb7++us6OQPYhu5QfHOQqLHr3Veim/HfFH/cV/eJGeWJbpluC3SrNkMc1qxZU682t7frky7u3sq3NRd9MMF9u/zMDPUN4X59cl3+n4MTeuy5t9+gdwOt1t4GZuh+rkM3fneYc4DPG/6O+70mCILQnRBLtyAIQjNhp5QlcNhZZ3Ivlt1pDrR6Uqyzo8+a1rSa0xpKt1d3i6w3aBWkxYoCm1ZFWhdZYojihXHirT0OJjKjmOV2aYWiMKGQZOefAorCy1tJLsao0nKsJ4FirCbXZ/IsbpMlmdoauu2yw89a4PxNvWSYbp1ztzrTik+rJveHHX2KWLZ1Q+XJaIWj0OBABC2/FPZsE5b9amqfCN2m2Y56Ii3GOtOSyQRoHCjh+aaLOwdOODDBOtONiW4mv+Lx8dqiFwNFPd2F2e5MqMdY5Jaeaw4S0UODMb4MldBLhtGqyTJzOrT68tjpgcEEc4wn5jHQbZkC0hOKaLpIc7/YfkwiR2v6r7/+qhJzsSwWrakU4Lql2T2Zma+hKz69IdyThrnDRH48VgpzumW3BWwznkOeb+Ipunl9siwXzwfXo5Wav+8ZY90S6NLO64plxXj/ciCO4riheHdamvn84mAJE0ByAIbnmKEAHHxprDwd8zLwO3PnzlX3F0uiMYEa7zF+Jhwo5HOAng3MDcHBHYp6Pk+85XwQBEHoFhzo9OmCIAgdtWSYe/kcHZbRYnmc6dOn1ykzxJI7DcGSTrfeeqsqqcWSTCwHxc8vv/xys/Zx1apV2syZM7WgoCAtICBAO/zww7UlS5bUWaclJcN08vPzVZkilhDjtlkyqGfPnqq8lWcpJr1MkT5ZLBZVPo1lpljWKjMzs1lt21pYpo1luiIiItS+spQaS7px+48//njNenl5edqcOXO0qKgotR7bbcuWLfVKQen7tnjxYu2yyy5Tpc64/rnnnqvl5OQ0uT8sEcWyS2wDlmVyf50WFRVpN954oyqnxXYaOHCgOi/upbe8UVVVpcpa8di4vywjxfPN88Pvu5cGa6iEm34d8Pjc+fjjj9V2uE22IY/TW8m2DRs2aCeffLIqKWez2bTBgwdr99xzT6P3BktF8X5g+y1btkzbtWuXdvHFF2v9+/dX2+Dv8Zpl6bjWlgzzdl17lrTyhOeH67iX2/Pk/vvvV+usXbt2v0qGuTNv3jz1nYkTJ9ZbxpJhN998syq9xbJ5U6dOVSXt2H7uz5TGSvR526dNmzZpRx11lDoHvPbnzp2rjsnzWuCx8fnDNjn66KPV9RUbG6va0bOUmbf2Zfk13od8TvDajouL04488kjttddeq1ln/vz56rnAMm+83ngd8PnnXoJQEAShu2HgPwda+AuCIAhCS6H1lZZfWls9LYpNwSRTtDbS24Au2IIgCIIgCL5CYroFQRCEDg+TtHlCd3O6ODMWWRAEQRAEoaMiMd2CIAjCASM9Pb3R5SyZxPhsxq+vXLlSxUszrp1xqJwYe9yaDO6CIAiCIAjthYhuQRAE4YDBMmqNwWRPdAVn0ikmlGPGdZb1Yomn+++/XyUsEwRBEARB6MhITLcgCIJwwGDW48ZgWTVmSRYEQRAEQeisiOgWBEEQBEEQBEEQBB8hidQEQRAEQRAEQRAEwUeI6BYEQRAEQRAEQRAEHyGiWxAEQRAEQRAEQRB8hIhuQRAEQRAEQRAEQfARIroFQRAEQRAEQRAEwUeI6BYEQRAEQRAEQRAEHyGiWxAEQRAEQRAEQRB8hIhuQRAEQRAEQRAEQfARIroFQRAEQRAEQRAEwUeI6BYEQRAEQRAEQRAEHyGiWxAEQRAEQRAEQRB8hIhuQRAEQRAEQRAEQfARIroFQRAEQRAEQRAEwUeI6BYEQRAEQRAEQRAEHyGiWxAEQRAEQRAEQRB8hIhuQRAEQRAEQRAEQfARIroFQRAEQRAEQRAEwUeI6BYEQRAEQRAEQRAEHyGiWxAEQRAEQRAEQRB8hIhuQRAEQRAEQRAEQfARIroFQRAEQRAEQRAEwUeI6BYEQRAEQRAEQRAEHyGiWxAEQRAEQRAEQRB8hIhuQRAEQRAEQRAEQfARIroFQRAEQRAEQRAEwUeI6BYEQRAEQRAEQRAEHyGiWxAEQRAEQRAEQRB8hIhuQRAEQRAEQRAEQfARIroFQRAEQRAEQRAEwUeI6BYEQRAEQRAEQRAEHyGiWxAEQRAEQRAEQRB8hIhuQRAEQRAEQRAEQfARIroFQRAEQRAEQRAEwUeI6BYEQRAEQRAEQRAEHyGiWxAEQRAEQRAEQRB8hIhuQRAEQRAEQRAEQfARIroFQRAEQRAEQRAEwUeI6BYEQRAEQRAEQRAEHyGiWxAEQRAEQRAEQRB8hIhuQRAEQRAEQRAEQfARIroFQRAEQRAEQRAEwUeI6BaEA0RxcTEuvfRSxMXFwWAw4IYbbjjQuyQIHY49e/ao++O///1vu/7u22+/rX53xYoV7fq7giB0LORdLbQF999/v7p+srOz2/V3DzvsMIwYMaJdf1PwjojubozeqdQns9mMhIQEXHTRRUhJSTnQu9flefTRR9U5uPLKK/Hee+/h/PPPb3R9p9OJd999FzNmzEBUVBQsFgtiYmJw9NFH47XXXkNFRUWd9T3PbUREBMaPH4/rr78emzZtalDc6JPJZEKvXr1w8sknY82aNejM8Hj5wuMx+oLdu3fjmmuuwaBBgxAQEKCmYcOG4eqrr8a6deu8vnj1ieuynWfPno233nqr3nkkvCfdvxMSEoLRo0fj6aef9rq+IAhdB3lXH1jkXd3539We95D7dPvtt9es16dPnwbXKy8vb9N9Erof5gO9A8KB58EHH0Tfvn3VA2XZsmXq4fTXX39hw4YNsNlsB3r3uiy//vorDj74YNx3331NrltWVqZeqD/++COmTJmCW265BbGxscjNzcXixYtx1VVX4Z9//sH//ve/Ot/jS/+CCy6ApmkoKCjA2rVr8c477+Dll1/GE088gZtuuqneb5199tk49thj4XA4sHnzZrzyyiv4/vvv1bUxZswYdNYX+QMPPKBGfPlSbUu++eYbnHnmmaqzdO655yoxbDQasWXLFnzxxReq/SjKe/fuXed7nB8UFKQ6YOw489xefPHFeO6559Q2e/bsWWd9Pz8/vPHGG+pzfn4+Pv/8c3UdLF++HB999FGbHpMgCB0PeVcfGORd3TXe1e73kDueVmC23c0331zvu1artc33R+hmaEK35a233tJ4CSxfvrzO/P/85z9q/scff3zA9q070LdvX+24445r1rqXX365OifPPfec1+Xbtm3T5s2bV2ce17/66qvrrZudna1NnjxZLf/2229r5u/evVvNe+qpp+qs//XXX6v5l112mdZZ+fTTT9Ux/Pbbb2263R07dmiBgYHa0KFDtdTU1HrLq6qqtOeff17bt29fzbz77rtP7UtWVla99d9//33NaDRqkyZNqjP/wgsvVL/jjsPh0CZMmKC2lZKSonVVGrouD9TzURDaG3lXH1jkXd3539XNfZ737t272ee6pTT27vcl06dP14YPH96uvyl4R9zLhXoceuih6u/OnTvrzKfl7rTTTlOuTxxVnzBhAr7++us661RVValRyoEDB6p1IiMjccghh+Dnn3+uWYcucbTw7dq1CzNnzkRgYCB69OihRiBd759aSkpK1IgjrX609A0ePFjFdnquR9cfuvcuWLBAjVpy3eHDh+OHH36os15RUZGKx+IIKtehyxdHmFetWlVnPY5EH3PMMQgNDVXuv9OnT8fff//drPbLzMzEJZdcoka32Qa0fHLEWuf3339X+0vr57ffflvjutSQO1VSUpKycHJ/6G7mDbY3R9CbA88JLaO0zD7yyCNNrn/EEUeov9zfljBv3jz069cP/v7+mDhxIv788081es1Jp7KyEvfee69ypWNb81rg9ffbb781GNf77LPPKqsxt8vzQitPY9AadPrpp6vPhx9+eE178zzo0JrA64XXBK9FuoXTmtwUTz75pLpG6RYeHx9fbznb+LrrrqtntW4IWsoZO8jrz/2e8Qat6XpbtsQVb+/evTjhhBNUW/P6v/HGG5VVxrNNeL7YbnRbZLvwGLguLTnutOR+9gZjpvk9umHynNIKQYu/N+ia2b9/f7U/Bx10kLLye7NK8RrifoSFheHEE09UViBP6F3A+5T7yu3xd+k+ymuyIfLy8tS1nJiYiK1btzZ5bILgS+RdLe9qd+RdfWB58cUX1b7xOgwPD1f33QcffFBvPe4v7y2+n9iWc+bMQWlpaZ117HY7HnrooZr3He+DO++802s4Gb0b2L7BwcEq9IzvRm+/685PP/2k9pPeEvwtoX0Q93KhHvoLhQ8NnY0bN2Lq1KkqjozxL3zgfvLJJzjppJOUmyvdqQhjcR577DElHPjwLiwsVJ1qvij5wtShOxRfTHTZonDhC5euW7z5+UInfFlTHPChzhcjXX4oDm699VbVYeYD3R262dGdly80PnxeeOEFnHrqqdi3b596eZErrrgCn332mXrpM+Y2JydHfY+d8nHjxtV02mfNmqVeLtwnihuKKr7Q+DLicTUEBQlfVDt27FC/wY78p59+qh6wfNDyRTx06FAVF0YBw8677sYUHR3tdZt8oLK9zjvvPLQVFFJ8SLNteY74oG4IvUOnt2FzoJsbj58vZR4nryleK7ymeMw6/G12Uvjgnzt3rupo0e2OHbx///23nosc4+S4Dl+0dLF8/vnn1XlZv3696jh5Y9q0aUr48nrgS4vtT/S/vGbZ+TzqqKOU6KKY4v5T0LHzxni8hqAb+IABAzBp0iS0FYwXpLjkS9H9nmmLc8OOMdsrLS1NXYtMDMSXs2fHifC6ZUeAbcLt83ywU5GcnKyWudOc+7mhTi/jHHnt87nCTgivFd7HnnA/ee4vv/xy1RHj75xyyilKEOjnaNGiRereZQeS55X3I/eZzy4+g3R3xdTUVHUf85687LLLMGTIEPVM4bOBx+zNjZDJb3g+dDdRdoYE4UAi72p5V7sj7+qG39U6dN33TGTGAV/PASnPdfRcLQ3x+uuvq33nYBevHR4z87lwUOicc86ps+4ZZ5yhrjfef7zf2K4cVGIYgQ7vSw4AcXu87rgdrs/r/8svv6wzUMFBaor9O+64Q71DV69ere5Tz99177dwuwyLe/PNN1VOAKGdaMACLnQDdHebRYsWKXeXpKQk7bPPPtOio6M1Pz8/9X+dI488Uhs5cqRWXl5eM8/pdGpTpkzRBg4cWDNv9OjRTbrm0FWWv3vttdfW2Ra/Z7Vaa1xvFixYoNZ7+OGH63z/tNNO0wwGg3Lt1eF6/K77vLVr16r5L774Ys280NBQr25c7vvB45k5c6b6rFNaWqpczGbMmNHosdGljL9JN2GdyspK5SIWFBSkFRYWttiN6cYbb1TbXLNmTZ35FRUVqq30ia5ozXFZ07n++uvVOmwnd5e1Bx54QG0vPT1d+/3337WxY8eq+Z9//nmT+6rvV2RkpHbQQQcp92qdt99+W22Hrk46drtdre9OXl6eFhsbq1188cU18/R98/f315KTk2vm//PPP2o+26g1LmuZmZnqujn66KOVu7bOSy+9pNZ/8803G9xmQUGBWuekk06qt4zH4H5ueP0018WM3+Xyk08+uZ57ub49XuePPvqoug9GjRqlNZenn35abZv3lk5ZWZk2ZMiQeu3jvs86jz32mPrNvXv3tvh+9saXX37ZpMuffu55TeXm5tbM/+qrr9T8hQsX1swbM2aMFhMTo+Xk5NTM4/VNl/0LLrigZh4/c56339Xve3d3xLS0NOWe169fP23Pnj0N7qsg+AJ5V9dH3tXyrm7uu9r9HvI2ucNz7W0dvrcb48QTT2zShVt/97u3F+G7nudBh9cP17v00kvrrHfLLbeo+b/++qv6f35+vhYcHKzC0fged8f9nnB3L+e1YbFYtLlz59ZpR6F9EPdyQY0acuSWbmEc/eLIOF3R9FFOWnY4oszROY5ccgSQE0eeOcq5ffv2mgyqHGXjSDvnNQVHVz1dzujCRGsV+e6779QIHEcP3eGoH99THFX2PA5369OoUaPUqDAtYTrcP44Y0tLlDWb+5L5zhJDHpx8rLYRHHnkk/vjjD5WZtCG4z7QecjRYh6OvPAaWHaGFrKVwhJnQzc/zt3je9MkzUVdT6NvjOXWHFgNuj8dBSwBHzzkCS6tic6C1hG3H0XC6xbm7TrtbZAjPr25VZLvyWqMFhW5Znm6EhCPwtODo0JJBKzPbojXwWuM1RzdGWkl0uO+8duhS2NLzQthu7ueG7nv7e154Derbo3WdloDJkyfXGfVuCo5+s/1oldKhWyWP1xO6BLr/Nu8DJgbivceR9Jbez97g/aiPvNO60BgclXe/fnTXWv3+pvWe9y8tVXSrdX8O0HKnXyO8zujaymzxvM484b67Q8s+LU3cP97/Lb3PBKGtkHd1LfKulnd1c9/V7vBdzBAK98kT7qfnOkxy1xi8Xvmu8Bby5Am9ONzhu4znQb9+9DbyTJ6ne1rox8r94jVBjxbPRIqe7zHy4YcfqvcovcXmz59fpx2F9kHcywX1EGKpI7rd0NWELyvGkOjQ/YovznvuuUdNDbmJ8gFLdzPGUHJ7jNeiWxrdZflSdYc3O11A3eF33F3mGHvKmB26n7mjuxpxuacblid8cTAOU4fucRdeeKHqtNAljZk/+TDV90XvgHCdhmA7eb6QdLhPjNnyfJg1tM/NQT9+dgTcoQuh/sJ46qmnmh3HpqNvz7N96W7LuCoeA18kevxUc9GPkcLQHb7UvWUjpQsVS18xDtFdeHlmGCVsW0943dB9sjXo+8r4Q3fYueA10dj5aui8EL7Q+DLMyMhosathQ+eFL9WFCxeqz3oMsrv7X3Pg8bCz6/lC9jxXhK6ejOFjp979HtLvgZbez96gmKVbKV0G6YLKjiM7a+xIe15znve3fg/q+9bQudTvP7q7skPO9mXnprl1S/n84rVLtz52bgXhQCHvanlXuyPv6ua9q92h+Pc22Orpbs6BoZbwn//8Rw0McPtsT4ZN8T3Gc+9JY+8yDiDwWHhOPc8L3z88z/qx6uEEzXmXMc6ffRFeLwy5Eg4MIrqFOg8hdniZTIUPC8bLcIRVHy1m6QuOlntDfzgwJocPgq+++krFpDJWhZ3pV199VcWo+JKG4lLcE7nQAsBRRVoHuX98AXJkmPFljA3Tj5XzGyq54c2y6UsYb0qYhISJXnQ4wq2/GN5///0Wb5fbY5t5vjD5smzpC6e1cL9pmeR1x/g/xjVxnxi75JkcqKPBBChMnuYtOYwe492aWqP69jxfuGyX9jovjEvU45fZmeA1SKsarWQ8X41ZkFoCxT/jNlnihgMKetk0duw4z/1ea8797QtoNWJ8ImMSeV0KwoFC3tXyrnZH3tUdBw7W8D6k1xY9ypg/gUnfOHDNQWV3mvsu82atbi3sq3CiFZ0eDk0NPAi+QXwLhDroD1G6dL300ktqnj6yTNcrPuC9Te4jsHTtZDZGurIwmydHzpkAwx2+MN1dyci2bdvUX32ElS5Y3A9PlyqOsurLWwMfPEzgQhdTjv4x6YieGVR3eeNoY0PH2liyDu4TR+A9Rcn+7DM7GDwv//d//4e2glZMus/RPdlz9Hx/0Y+RVhd36IrmKUIpuHh9sSNFKws7imxjJiHxhjdXSF43TdXzbOjlpe+rZyZqurF5q63tyXHHHaeOk4lk2gom7iENdZr3Bx4PO0ieL3fPc8VkN2xXil+KblrEeF5ozfJGc+7nxmCSJt6D7AzwOqfba0trjzd0LvX7j9YLDhywA8z7u6lMujrXXnutsgo+/vjjahKEjoC8q+Vdvb90p3d1e8D3C923mcyP5439A16vDbVRQ/BYeF16tiE955jkTz9W/R5ozruMnnIcEOBADb1a+I4V2h8R3UI96OLJEfXnnntOPSw4osl5dJll3KQnWVlZNZ8Zl+I50syRdW9lDvSOAqEI4P/5kmQ8FqE7GS1u7usRjsbzwcwXXEvgtjzdYnlsFBL6/tGNjQ8ylrvw5jbsfqze4D6np6fj448/rvMCozsP24LutC2Frki0/jEuzrMtWmPto/WScWxsj7vuugttDUdQ2TliNk/3UhTsiHi6Kesjvu77zzi+pUuXet02O196TCKh2OX6TV0LfBkSz9Ii7DTQPY3ZUt33gVlZea3wpdkYt912m8poyvPDF+L+WmGZoZsWJ3aw9PugLWFHie3nXj6I9zjPVVPnhZ9p7W2Ipu5nb/B68Gwj3Wrl7ZnRVAed36ULpPt5ZoeEljLem4Rue7TW0LJOkd+cc0ZXXVoPmR2W2XIFoSMg72p5V+8P3eld7Ws87yfuK7Puc1+bylfiif6u4n3tzjPPPKP+6sdKF3YOxHDwzVPYe7vO6J1HbzK9/J54KLQ/4l4ueIXuQ4z9YDkCJn1gLBld2UaOHKkSV3DEkyKDD1wmj1i7dq36Hh8yfOnzhchRdHZq9bIfnqNudMFhPBZdcfmSYnIIJofSy3Ew0RFrNfJlw1FXumux80x3OCbTaGnJHo7CMwaWCWi4Lb5YGYPDxBe06OkdcooevhgYH0UrAOPf+PJgyQ6Oqutxtd5gjBU7PHTDWrlypRrV5fEzhosP0NaOVPO7HM2l1Y0WQLYNH5xMHMNtc5+8xbJyZJluYXwAM46V54llUdhJ4QOcI55tDV82tJZwX1kihG6CPH+8ljzjiY8//ng1cs4yNnyR8Bjp3sjryFtHip1CXocsF8LOF9uFnQaK38agGGOnge6JfEEz7o37xjakkKL7F9uCCcY4kk63MNa6bCoem6PGFMrsGLH9mYCG1xbbm8fCZbymvMVe87rgNciRel5ffBnyXPL7niW52gomUGFnkPvLsiYUquxg6UlY9HNDN0meKwpN7huve7rLeXbEWnI/e4MCmW3N88/f4z3KDiB/T+94tAS6mvLe5aAFSxfpJcPY2XC34D366KPqWcKONe9ZugZSpLDdWZZIT/DmuW1eOyyBw/u4LcsCCUJrkXe1vKtbS3d6V/saCmDGXDOGmyXRmAOE71q2VUuvJV7zvN9YOpSDD3xPcdCC70sOGPNeI7zGObDFcBC2AUNNGB/Oa4elL91rzuvQ44v5BXhuOJDB9517wjvBx7RTlnShA+JeEscTlhLo37+/mlgqguzcuVOV2omLi1MlBxISErTjjz9elS7RYcmQiRMnamFhYapkBEsRPfLII6oUh2f5I26P5R8CAgJU2QmWU/AsYVBUVKRKTPTo0UP9JkuEPPXUU3XKITRWcoPlH/h7hOUubr31VlUqhWUWuA/8/PLLL9f73urVq7VTTjlFlXFgSRZu54wzztB++eWXJts1IyNDmzNnjhYVFaVKXLB8C9va2741pwyJDs8Dt3PEEUdoERERmtlsVr/BEjGvvvpqvZIR7uUuWB6J54QlRVh+ZOPGjfW2r5f6YPu2BS+88II6RrYfr4m///5bGz9+vHbMMcfUrMPzyNJX+nrcv2+++UadM87ztm8se9WzZ0+1/qGHHlpTRqUpXn/9dVXyyWQy1StJwrIjvFZ5jfFavPLKK1U5lObC8jf8zoABAzSbzVZz7V9xxRX1ysfoZUP0iesnJiaqe4llT9xL/XjeM23Brl271HXHfWTJoZtvvlmVEeG+LFu2rGa9TZs2aUcddZQqn8PrjCVG9NI+7tdzS+5nT1atWqWdffbZWq9evdT5ZLkvtsOKFSuadV16K+XCskpTp05VxxcSEqLNnj1bHYsnLHvG55ledonXBp8helkcb89HHg/3l/eee9k1QfAl8q6Wd7U78q5u+bu6sXtof861zvz587Vp06bVXIe8H3kNs7RoU+VC9X1j2+mwhBtLwrH8HY+V7XjHHXd47R98/fXXqiSg/s7jOfzwww+9lgxz77PEx8drQ4cObbSsp9C2GPiPr4W9ILjDkWWOKHsbHRW6LoxRomWEiak83ZmbgqPvTCJDayOtr0LbQivEjTfeqCxhLR31lvtZELomcm93T+RdLQi+QWK6BUFocxhf5DmexwzQjFGjS6Nw4KDLtee5opslXeXFzUwQBKH7IO9qQWg/JKZbEIRmwxcxY5AbgrFYHCFnuSdaThlryDiuVatWqYQnrCfJeULbwnPCc9MYjGv29/dX1gsm/GHsHGPmGEfIjL1tmXFXEARBOHDIu1oQOh4iugVBaDYUbCxf0hAsZUH3Mial6dmzp8o0ypc/E/VccMEFquQSk7cIbcuSJUtqkqs0BMuY0F2UGcyZgIgim1lxmQiHCX9Y6kQQBEHo/Mi7WhA6HhLTLQhCs2GW14YyWBNaUpm9U2hfeE54bhqDGX6ZrVwQBEHo2si7WhA6HiK6BUEQBEEQBEEQBMFHiHt5M7I4pqamqjp77jULBUEQBKErwTF41kju0aOHqoO8P8i7UxAEQegOaM18d4robgJ2GhjvIgiCIAjdgaSkJCQmJu7XNuTdKQiCIHQnkpp4d4robgKO0usNGRISst/bq6qqwk8//YSjjz4aFosF3Rlpi1qkLeoi7VGLtEUt0ha+bYvCwkIllPX3Xkd6dxI5/7VIW9QibVGLtEUt0hZ1kfbwXVs0990porsJdLc4dhraSnQHBASobclFL22hI21RF2mPWqQtapG2aJ+2aAt38LZ+dxI5/7VIW9QibVGLtEUt0hZ1kfbwfVs09e7cv6AtQRAEQRAEQRAEQRAaRES3IAiCIAiCIAiCIPiITiW6//jjD8yePVtlh6MJf8GCBY2u//vvv6v1PKf09PR222dBEARBEARBEASh+9KpYrpLSkowevRoXHzxxTjllFOa/b2tW7fWiSmLiYnx0R4KgiAIgiAIQscra2S32+FwONBd4nbNZjPKy8u7zTE3hrRH69vCZDKp9fc330mnEt2zZs1SU0uhyA4LC2vWuhUVFWpyz0innyBO+4u+jbbYVmdH2qIWaYu6SHvUIm1Ri7SFb9tif7bl63en+/7J+Ze2cEfaoum24P8zMjJQVlaG7jTIEBcXh3379rVJcsjOjrTH/rWFv78/YmNjvSZea+6zx6DxlzshbKQvv/wSJ510UqPu5Ycffjh69+6tOgMjRozA/fffj6lTpzb4HS5/4IEH6s3/4IMPVKY7QRAEQeiKlJaW4pxzzkFBQUGLM47Lu1MQOi4UC0FBQYiIiFAWO0EQmg89RHJzc1FcXKwGr1r77uzSoptu5RTeEyZMUKL7jTfewHvvvYd//vkH48aNa/ZoPWuvZWdnt1nJsJ9//hkzZsyQlP3SFjVIW9RF2qMWaYtapC182xZ830VFRbVKdPv63Unk/NcibVGLtEXjbcH7kha9Xr16dasBMMqboqIiVTu5u1t2ibTH/rUFhbV+H/n5+bXq3dmlh7sGDx6sJp0pU6Zg586dePbZZ5X49gYb0rMxCR9ebfkwb+vtdWZ4wbdFrERXQK6Lukh71CJtUYu0hW/aYn+2017vTl9ts7MibVGLtIX3tmDMqt7PMho7Vf7k/cLpdKq/PPbudNwNIe2xf22h6xT+9XzONPe506VFtzcmTpyIv/7660DvBrr7CBOT4tECQjZu3Air1ariJWw2m/qsvzD0iUkMBEEQBEEQBEEQOhvdTnSvWbMG8fHxB3o3uiUcbaXrRVZWlnLFYNZAwlEmukTpWQT1iAfO1zMGUnhTkLuLcn2+iHJBEARBEARBEDoqnUp0M4B9x44dNf/fvXu3EtFMDEEf+zvuuAMpKSl499131fLnnnsOffv2xfDhw5WgY0z3r7/+ip9++ukAHkX3g9ky8/LylGWb55BiOjAwUE1MTEAh7U000/1DL2/B80frOOe5i3IKb36XQpzboXujN0t5d3elEQRBEARB2B8cTg3/7s5FZlE5YoJtmNg3AiajhAYeKPr06YMbbrhBTQcyh5bQBUX3ihUrVDZynZtuukn9vfDCC/H2228jLS1NBbnrVFZW4uabb1ZCnMkjRo0ahUWLFtXZhuAbKI6ZpCAnJ0cJaybyoCBm6TYlsJlePytLreu3aRMMQUHQ/P3h9PODxslmU0KZArohKMb1icKegt693p67KOdv65ZyT0He3eKcBEEQBEEQWsIPG9LwwMJNSCtweSmS+FAb7ps9DMeM8I0H6UUXXYT8/HwsWLCg5v/vvPOO+sy+W2JiIk4//XQ8+OCDqn+n4y1HECsXNRReethhh2HMmDHKWLc/6FWTPLnrrrvw8MMPN7lc6Np0KtHNm6KxZOsU3u7cdtttahLaDw508AFJF3KKbp4vDniwVAUfgoaSEphzcmBOS4NWVAQkJsKUlweznoLfYIBmsUCzWuEMClJTHTHORD3VApliuiG3cv6uu6WcWQfp0q4nT9C/r4tyPqxDQ0OV9Z37KyU1BEEQBEEQXIL7yvdXwbMHnl5Qrua/ct44nwlvT4455hi89dZbKixx5cqVyvDG/uUTTzxRZ73//e9/SmgzQ3VTRpy2htWT3LNYsw/ckuVC10TMe0Kbpd6nl8GGDRuwfft2JXL5oKPrv81qhSk/H9atW+G/ejWsW7aw6B3s0dHq+46ICNjj4lxTdDScgYHcKEw5ObDu2AG/9evhv2oV/FesgP/y5fDbuBGWfftgysiAsaAABsaGewzG8AGsW7gporkv4eHhiIyMVBP3iw85WropxCnIGa6wadMmrF+/XmW558ABj6OTVtUTBEEQBEGoB/s1pZX2Zk1F5VW47+uN9QS32k713/u/3qTWa2pbbdGfYr8uLi5OlSSky/NRRx2lyqR5Qs9K1ifnupzY7/MGreeLFy/G888/7zIOGQzYs2ePWsb5TMDM32Q+qNtvv10Zc5oiJiam5nc5eYrqppbrsL3uv//+mjJVPXr0wHXXXVdnHfZTL774YtXP5XqvvfZaneXs0x5xxBHKqNSvXz9cfvnlyjPUnTfffFOF4urHec011zR4bPfdd59aZ926dU22g1AXMecJrYYPHiZGY6w2//L/zEBOUatceyorlQXblJYGU24ui8LDERwMLSys4Y0ajbUWbXdY8qKqCobKSpiyspSlvGZ9q1WtT7HuDA6u46LOZbSee6Kn/efkXuaGVnG6wlNwp6en18SK8+HNhyIfWu05WioIgiAIgtCWlFU5MOzeH9tkW5TR6YXlGHl/0/mSNj04EwHWtpMeNPQsWbIEvXv3bvU2KLa3bduGESNGKDd1Eh0drUJTjz32WCXKmStqy5YtmDt3ruoTUgi3B59//rkqc/zRRx8pUcx+6dq1a+us8/TTT+Ohhx7CnXfeic8++wxXXnklpk+frkomMxfSzJkzMXnyZPzzzz9qMIHx3xTVunfwK6+8osJ1H3/8ccyaNUv15//++2+vAwAU/N988w3+/PNPDBgwoF3aoCsholtoMRxV0xOj8YamRZliVK9T5+5CbiwsVO7ijvBwFrJr/Y+aTNA4ucXs1IjxykqXGC8uhjk1FZTYTrqgU4zbbHAEBkLzJsa9/oxJWcY5ET2renJysnrgUKDzWCnCdVd0yZwuCIIgCILgeyj6aAShoYdGErqOv/TSS/XWO/fcc+v0z95//32vycAYWkhjCvtztDrrvPzyy8qazm3TUDNkyBCkpqbiP//5D+69995GcwEx1tydvXv3KoNUc5fr0IOU+0RrPvvYtGTT8u4OBwauuuoq9Zn7RpH+22+/KdH9wQcfqD4sBw1oFOP3X3jhBZx44onKHZ+eAIwlZ/6r66+/vmabBx10UJ3fYFufd955WL16tYqLT0hIaPDYhYYR0S00C1qA6YLNxGgU3Izd5mgfXbbVg8fpVLHZpsxMmDMzYWT5r4AA2GNilGD2GRTi/v5q8irGKypgLiqCISVFuaBrjNVmvDgt4xTiFOQU4TYbnNyGx77qydYI3dB53Ho7uMeC062HIpz/95bAQxAEQRAEoSPgbzEpq3NzYLbyi95a3uR6b885SGUzb+p39xcmIqN1lkYfCkx6LJ566qn11qMF+OCDD1YCnf3UlpYL3rx5s7IQu/fpGCNO12waYihgG4KWYPYLddhXbslyHSaJY3I3uoUzlp0Ce/bs2XXyDjFJtA73lSI9MzOz5hhGjx6t+qd6TiMeAz8zrpzrcyDhyCOPbLQtbrzxRmV0WrZsGaKiohpdV2gYEd1Co3AU0T0xGuHNW5MAgi7kFNu6C7nTCUdIiMuyfSBpSIzb7S4xXl6uxLixui64St5Gq3hICJyhoXAGBECjIHeziPOhrWdAJ3ops4yMDJU5n+KcI4m6KzpHTcUVXRAEQRCEjgTFVnPdvA8dGK2ylDNpmreIbErSuFCbWq89yoexD6q7NjMWmaKSSdMuueSSOutRfFKssr/a3hVqWK6YfcHWLtehpZ3imJWXGLdOi/ZTTz2lYs11g5D+1/3cuicNbgz2WZvDjBkz8OGHH+LHH39UHgRC6xDRLTSYGI2lvmjRpbCkeKRFV3fVMdCVu9qF3FRUBKfVuv8u5O2B2ays3Vq1+3hNgbGqKmWdZwy6soozVpwinBnUw8Jc8eIU4nxAVY966m71nNhmuis63YH40OOoIMU32013WRdXdEEQBEEQOgsU0iwLxizl7P24C29dYnP5gajXTTHNWGbGJJ9zzjnNFpGesI/rXnKWDB06VMVUs3+nW7sZ60wLtad7uC/hMdG6zenqq69Wbu5MjjZu3Lgmv8tjYOw2vQL0tuExsN3ofs5jYa3vX375pdFyyieccIL6fbYx+7FnnXVWmx5jd0Gylws1UDQyTpvJIpjFmy4nvLkYZ8KRQhMzgufmquzjzELut22bcuOuio2Fg7EoHV1wNwazmAcHwxEdDXt8POxRUXCynFhBAazbt8O2erUre/rKlbDs2KHEuZGW/+oslnwg86HNBxjbS69HTlf8HTt2qPZkwg8mseBABuuKS1Z0QRAEQRA6OiwHxrJgtGi7w/+3Z7mwhlyw2d+aN29eq7dB4aknGmM/mJZiWpWTkpJw7bXXqn7xV199pTJ3U+C3l+WcgplWfPYfd+3apeLSKZ6bmziOVml6Z7KsGrdBt3bGbp9//vkqnpswKRxd8RnrzepDq1atwosvvlhvWyeffDLee+89zJkzRyVsE1qOWLq7OapshFtiNH7mw0svp0VUkrLcXJdVOy9PxUZ3CBdyX7unBwaqJGwKjnRWVKjJunevimFvzCXd0xVdT/hBN3QOZrBtafnWE7KJG7ogCIIgCB0VCusZw+JUjHdmUTligm0qhvtAWLjdYXwzs3E/+eSTKnM3+1Qt5ZZbblHCdNiwYcoowhKyFOLfffcdbr31VuXCzpJjdGG/++67fXIc3mAfkVnFKfRpiR85ciQWLlzoNemaN9jPpEs4hfakSZOUYGf8O2PhdXjc9NLkPLYDY7ZPO+00r9vjfA5IULSzn3vKKae02bF2B0R0d1N40zBWm1ZX/mWCMN6MNYnR6AZRXAxTdrZLbBcXKxdye2dwIfcFBkNtwrXQ0Hou6caUFGi6Szpd0cPD67ik6+XJ3F3ROcDB0gy0kusDHHTpZ/1GScYmCIIgCEJHggJ7cv/mCb62QC9r1dD/dVg/m5MO+1ns5zLxbXMYNGgQli5dWm8+S2/9+++/zd7fww47rFEvxqaWe8Js694yruvo9cTdWbNmTZ3/U6j/+uuvNe3hLcadtbs5ecNzf8844ww1CS1HRHc3hAKbccdMjkZxVycxGrOQ5+bClJEBc1YWjBUVSkTShZxxzoKHSzrFMt3S9YzpFRUwFRbCnJ3typbOEmXM4h4W5ipbFhCgsqTTsq1bt/kg5MgqoSs64+mZZbM1o7WCIAiCIAiCIHQsRHR3M5hMgfUA6U5OtxW97IByIdcTo+Xn17qQRzRe/kHwcEkPCFCl0mpc0qszpTfmkm4ICKhxQ2dMOEs90AJO4U2rt3tpCEEQBEEQBEEQOhfSm+9GUGhTcNOtmbEpdC8RF3Ifu6TT0s2a4E24pFfSqm2zwa+4GH7h4SgtL1cxRTxnCQkJKgO6uJwLgiAIgiAIQudDRHc3gPEYtJ7SpZyfKbiVC3RKinKDVi7kQUHt6kLu0IA1RUasdRpgNxoxJtgJk6Ebu6QzEzoTr61bB4SGwhwfD/+wMBQUF6sajbR40/KtW8QFQRAEQRAEQegciOju4jDbYXJyssqYzbrRgUzqlZoK6+7dyu3ZERra7i7kf+Qa8eI+C7KqdJVtQrRFw7W9qjAtwonu7JLO2G9rYSFsOTmwBgXBGhuLspAQpKWmKpfzHj16qKyVUu9bEARBEARBEDoHIrq7MCxRRXdyJkxjrLDN6YRl61ZYkpNVZm1HXFy77xMF970767uuZ1VBzX8Q3VB4u2OxqJrnDk1Trv9+O3fCYrUiIDIShUFB2FFYiLzYWCW+eU4FQRAEQRAEQejYiOjuohQXFyvBzXJgTJjml58P665dMBUUwB4ZqWpJtzd0KaeF24WnLzn/r+GlJAumhld0D1fzxjAY4GS28+Bg5X7OTPKR6ekICQpCXlYWtmVkILpPH8TFxUmNb0EQBEEQBEHowEgNqC4Iaz1v375d1eOLCA6G/7598NuwAYayMlTFxR0QwU2W5BkxZNtqPP79i5i+a2XNfD97Jd7/6C5c+/dHyC+1Y3WhXJbuMBGbIzoa9uhomOx2xKSmImzjRmT//ju2L12KnKysFtV9FARBEARBEASh/RBLdxeCwistLU3FcDPTdaTZDOuWLSpTtoN1ovVSVu1EZXkl0tbuwA/xI7GiyITtpUbcs2slzlr3E5wGAxb3G6/WG5+8CYfsXYuBOUl4ccpZuGs7MDHUieNzNqF/XDAie8XCYOzupm9X/LczLExN5pISRBUWomzFCqRu3YrCoUMRO2IEAph5XhAEQRAEoQmqqqpU7p/2gLloLFIZR+jGiOjuItjtdiQlJSnR7e/nh5CiIuVOTuu2nVnJ2yHxllMDdpYZsLLAiNV5Trz2yFwMqijBA5e+il2RiWqdHwZNVoL7p4EH13xvW3Rv3DnzapgdduVWXaEBf+abcMe7r2FY5m7ccdrtKDr4YEwIcWJciBMhctVCCwxUk19VFay5uaj46y8kbdiAsBEjEDlsGMyRkQd6FwVBEARB6MCCm9VRysrK2uX3/P39MXjwYBHeQrdF/Hi7AOXl5di5c6fKUB5isSAsJQV+GzeCDsd2JkvzoeDOrACWrUlG+sMvYP1Dr2DuRj+8mmzBPyV+2BDXH1lBETgBGbizbyU+GV2OPf2G45EjLsHyniNqtpEdGI4PxszCu+OPV1nM5w2pwNzYUjgCg1BpMuOnuBH4JsuM+3da8b//W4qK6+/Amo9/UW7old0455rCYoEhNha2AQOUd0POn38i+dNPUbh4MbT0dI7GHOg9FARBEAShg0ELNwW32WxW5Uh9OfE3+FsttaoXFRXhhhtuQO/evZVonzJlCpYvX15nnYsuukj1f9ynY445pk5S4fPPPx8hISEYNGgQFi1aVOf7Tz31FK699tpm7Q/DNu+66y4MGTJEHRfz6hx11FH44osvasL8DjvsMLXPguCJ2Aw7OXwg7dmzR/2N0jT4b9sGU14e7BERKha4rSkrKkXGik1YGpiI7/x7IanciGEZRny35g+UWGwIPuZqDA8zKau0dsfNKI4IwEnKNdyljlkWzJW9nA8nd5dxrWb58GANw4ONwFP3YWdZBW6t8MeKQjtWFBgxbdcqDE7Zjl+SRuPJrVbYjBpGB9px6drvEDJ2GGIGJHZPV3SjEdboaGXhLs7LQ/ny5QjbsgXhAwbAr39/ICYGaOfwAkEQBEEQOjYUxO2RkJUemS3l0ksvxYYNG/Dee++pqi3vv/++ErmbNm1CQkJCzXoU2W+99VbN/1kiV+f111/HypUrsXTpUnz//fc455xzkJGRocT57t271fIVK1Y0uS9MTHzIIYeo8q0PP/wwDjroINV2ixcvxm233YYjjjhCJS4WhIYQ0d1J4YgaE6ZRcFeVlSGG5aX27QOcTlTRndxobDSL+LoiI3KrgAgLMCrY2WC2cLvdgc1lZqwoNGFloREXfzQPp2z8DRsPPh1J0y+EERoMfXph0bHnwDZqCL4YUwWLWTc/B9bbHsuBsSyYq0537fwYK3BNz/rlwvz9/XCwvxMHh7nm58ecjV+Xj0B6+ECEmzXk2Q0o3JmEGZ++jpIFNhx+ywcYHU7R78BB/hWICGzcjaklbdEZMBqNCIqMRFVICNILC1G8dSui9u1DSI8eMCYmAvR8YNx3I9eHIAiCIAjCgYSW8c8//xxfffUVpk2bpubdf//9WLhwIV555RUlfN1FNq3O7jidrn7j5s2bccIJJ2D48OHo168fbr31VmRnZyM6OhpXXnklnnjiCWUFb4o777xT9bm3bdumBgB0aD0/++yzleVbEBpDRHcnhA8SPWGapbwccVlZsKSnwxESoupvN1Un2yV4a5UlXbppYabgpXdMUrkBq/KcOOTV/2LQzg0447LXkBsQqtb9q88YHJS2BQlRgXhoQCXGBDsRzKtoxCnN3n/+DsuCrSkyYq3ThNFGh9pOc8RuWGwEwo6fjn4A5mgV2FVmQLKzAqsHjkO6yR+ZTit+zgF+zjHhvY8eRFhZHr4/4zJEjhmK0cFO+Jua3xadGcZMhUZGoqy0FHsrKxGekYGo3FwE7N4NREUBPXsC0dGAlBsTBEEQBKGDQcs43dE9xSzdzP/66686837//XfExMQgPDxcWZwpyPmZjBo1Cv/3f/+nRPyPP/6I+Ph4REVFqXnc9sknn9ysfvdHH32Ec889t47g1gkKCtrv4xW6PiK6O2HiCyZMS09LQ2hJCUJSU2EoKUEVBZS58dNJkely7a5LRVExVixciUJTOd4dOROZlS4ROjMrAyEVJTgyeS2yJ03F+FAnxo+YAsecqRij1mi9MKXAHhPihNlsxAi7E62JOjcYgP4BGvpP6gtMuhMBDg3PlFQqN/S1uQ5MSNkEf3slviiPwM7tVpgNGk7O24xjU9Zi5/AJeBgD6m2T1ne2Ea3xnV148ywGBATA4eeH/JISFAGIrKpCZGamGqQBR3Z79XK5njdjlFcQBEEQBKE9CA4OxuTJk/HQQw9hKCu0xMbiww8/VG7iAwYMqONafsopp6Bv374qvxEt0rNmzcLff/+tll988cXKRX3YsGFKbH/yySfIy8vDvffeq8T63XffrQR1//798eabb9ZxW9ehZZzfYSy3ILQWEd2dCI7S7d27F7lpaYgqKEBAWho0i8WVnZwKtAk3alp1idnhgNlpR7nFNXo4In0nXlj4X2QEReC/g2bCYtQwMsiJlWfOQX6UP64c2gdGk+4L3nF9r/1MBpXdnBN6AjtffhUZq7dgSN84FBdpyKg0YMjKv3H4iq+QlpQNHHNNzfFEF+eqpG+u/2t4KcmirPGd2dXcvUwHXaeYTCQ9NxdFgYGIjoxEqNMJw/r1HDZ2uZ1z9JZZz9sh070gCIIgCEJjMJaboplCmH2ZcePGKVduxmjrnHXWWTWfR44cqSzbFNAU1Iy7puffvHnz6mx3zpw5uO6667B69WosWLAAa9euxZNPPqnm0aXdEz1JmiDsDxLY2UlgxsTt27ejcPduxKWkICApSbmTO+g+04TgJqsKjcqN+opln2Pli+firLU/1SxbmTgMa+IHYcGww3BNbAkWjq3AM0OqcMhhwxE/oh+Mps55mQRFhKD/kRNxaz8HPhpVgfdHViBuzEAsHToJvwyYWCO44wqzsXzeBfjivZvhZ69U82ntZ6x3V4IxT6GhoUp870tORnJxMcpo5WZIAvMBLF3qmvbuBYqLD/TuCoIgCILQjaF4ZqKy4uJi5eX577//Ko9PxmY3BJfRor1jxw6vy3/77Tds3LgR11xzjRLmxx57LAIDA3HGGWeo/3uD8d9MkrZly5Y2Ozah+9G1VEUXhKNrWVlZ2L5lC5w7diA+ORnW4mJl3daaSNpQWVaBPb/8i8e2GXDXdpeVu8JsQWhFCabuXVuzXoXZipMueAaPHX4xwoOssHVBQyfHJRJtGoYfczA23fAf/DJgUs2y4Zk74YSBKeFUW+js+XMVsvekoyvBbJ2MPaLbuUrEt3s3skpKXN4StHaXlACrVgGMl2JZjqQkEeCCIAiCIBwwKIoZi00Xb8Zln3jiiQ2uy3xHOTk5an1vJXavvvpqzJ8/X1nOGTNOEU/4t6GSZkxSS4s648BZntcTDgq0Jju70L0Q9/IODBM38OZO3b4dQSkpCM3PhyMoCI4IukF7p9QB/FNgxOIcIx584hoclp+O/53xICr7jlPLvx46HRtj+2NFwlCv32cG766O5zFSgE+6+l1ElebVzDM77Ljow+cRXl6Eay95EtGjB2J6uBO9/buGixHLXISEhqoXUEpKiio5x5FcZj43MNFaaSmQmcm3l6vUGK85PfO5JAwRBEEQhC5Be4jF1v4GBTaNT4MHD1aWa2YeZ1w13cN1sfvAAw/g1FNPVdnLGdPN8l2M+Z45c6by7HOH8eG0bI8dO1b9f+rUqWqb3N5LL72k/t8QjzzyiLKET5o0SX2eMGGCcl3/888/8dhjj6n64VIyTGgMEd0dFI647WP89qZNiMjMhH95Oaoohiz1VXFJSQUyf/8XpTv24sapl6BSc7lN/9FnLI7YvRJH24pwxpAKPLjTiqzAUOQEensoaKpsF0tmdXV4jMxS7ipZ5mqrrKBwNbnQ0LOyAHsT+6MifR++ixgMR4oJb6YAc7f9gillqbAdcQji+sY3x7O/w8Jd97fZ4Ge1oqS0FCV79yIiPFyJbyuFtl7X21OAM+6blnEK8Say5QuCIAiC0PGgpZeZwJkvqD2EN3+Lv9kSWBP7jjvuUNbriIgIJa4peCl2Cbe3bt06vPPOO6qONjOLH3300UpcM6TOXXQzmRqTqK1Zs6Zm3mmnnaaE9KGHHqqE/QcffNDgvvD3ly1bhscff1xlR2eOJWZIZxz5U089pcL3BKExRHR3QEpZ5mn7dpRt2IDovDyY/PxQRSujm8IrrNLwd4EZi3ON2J1WhiVvvwiT5sRjw2dDi4lWVtnYq85DRdjFONToSg7GUliu7OW01rqrRZf1lnWyu0LisKbgMTbVFnNGBCNs2t3ILKvCLcVOLM4DVhQacdyybzEmbRvudkZi8eTeqp2nh1VhQABgUO3c+aDbVHBQkBroYSgDrd4crdXd0I2eAjwjw+V2rgtw3QIuAlwQBEEQOgUUrhSaDblUtzUUyLpYbi6Ms+bUmJCnNdwbep1unREjRqjcSJ79n5dffllNzYHCmlZtTg3RUFy4IIjo7mBwVC9p3To4N21CdHk5nJGRcDC7NID8KmD7qh0Y+OVH2OEfiSeOvdH1pYBwfD/mKARFh+LRYRp6xldW63O/OttmCSyWwnLVpq6dTws3BXdnL5HVEprbFiH+Fszyd2BWtANFVRqyjpmFlcvC8Mugg5FWbsT7aUak/bkSD/z6OtYeegxMp87G4ACtU1rAVW3vsDDlcp6RkaEEuM3fH2GhoSqeii83gy7AmcmzrEwEuCAIgiB0Uvjeb6kQFgShdYjo7kgJ0zIykL58OSy7diHUYoEjPh4F2YVYlurAD1XhWFtkxJhUE77YsQb9rAEYfOJVmBpjxLRwJ/ocdFmzfodikqWwmJk7t8oV30x36+5g4d7ftgi2GBB83KHAcYfiDQewLL8Si/NMOHbbEiTmpeOnlFw8uMkPsVYN08MdmF20HQlDeneq7O+6yzknjn7TNYsx34wBp9U7tFqA022rjgAXC7ggCIIgCIIgeEVEdzvicGr4Z3cuVmYbELk7F5MHxMBkNChxk7pjB3L/+QeBmZnIC4nGN1Wh6Pfiuzj5rwX4+dBzsXqKqw5hyYCB+PnkOQifOg7z+9AVuuVuQRSVY1nLWmh1WwSagCMjnWoqu+Ui/Pb3WOwM7A2b0VUPfMWmdDz5xq1ICYvF83e+hEOijRgRpMGbBzprqK8pMmKt0wC70YgxHWQQhK5gFNqcGO/FsAeWruOoOIW3LsCtVqtLWHNyF+AsQ8Z5zEXAGHAR4IIgCIIgCEI3pFOJ7j/++EMlK1i5ciXS0tLw5Zdf4qSTTmr0O4ytuOmmm1RNvp49e+Luu+/GRRddhPbmhw1peGDhJqQVlFPO4N3tKxAfasOdswZhRHkKkr/5GVUrNuCB8SdjVXaw+s7pwb1wKjSMLkrFlXR5Dnci3k8DRh7X7vsvNIx/oD/6Hn0w5gI431GB5YVGFKTtRbHVHzvCE/BJjj8+yQEiLRpu2fYDEvvEose4wTCZTfgj11jt4q6rbJNK8saY847k7k9LN2O8Ocxjr6pCUXGxSlpCi3dQcLCKCQ8MCoLFbK4vwNPTXbW/RYALgiAIgiAI3ZBOJbpLSkowevRoXHzxxTjllFOaXH/37t047rjjcMUVV6jaer/88gsuvfRSVbuPpQTaU3Bf+f6q6hRdtVCAX/vRWsQaKvDR/FfQNy8Nn9n6wTBkKkYGaeh51CSsPnY+BsZHYmArLNpC+8Ma54eGO4ETxiP16P8hL7UYM+HAX/lGlJRW4MQv30BAVQXOufhZVPbvp5KzecIYcyZ5Y8x5RxLexOAWA8bruaqyEvl5ecjNyVECPCQkBMHBwco6rrKUehPgtIDTBV0X4MyCridqEwRBEARBEIQuRqcS3bNmzVJTc3n11VfRt29fPP300+r/Q4cOxV9//YVnn3223UQ3Xcpp4dYFd0h5MS5auRAj03dg7il3q4zkGZoN3w05BIdmbMWMXn64ZEwFIlVeCyuAyHbZT6HtsdqsGNMvAmNQhSonsDGpEGvGHILQpL1YEjUAKHRZt+f+8wUG5CTh/bHHYn38wGppq+GlJIuKOe8Irube4G7RtZwTcxIw/pvJ17Kzs2Gz2ZQAr8mAbjQ2LsCjo2st4CLABUEQBEEQhC5EpxLdLWXp0qU46qij6syj2L7hhhsa/A6Fg3tdP8awEpZT4tRSGMPtcil34TAYcfXST+DnqMLg7L3YGt1HzQ8+/zQERmgYRXFibE2kdifD4YCD4stsdv3tjOm+WwBP68jeIcB/roTdoeHyTDvmJ1uUAD1r3U/on5uMJb1HVYtuYkBmpSvWe0xniL83GGCx2dTEMh28h9IyM2HMyoKfvz9CQ0JU/DfFuIHnmhn5OelZ0FNTXS7onBcVhSomYqu+77o7ehtIW0hb+Lot9mdbbf3ubGz/5PxLW7gjbdF4W/AzB8b5bvYso9WV4THrf7vTcTeEtMf+tQXX4/q8nzzrzTf32dOlRXd6ejpiaT1zg/9nZ6CsrEyVQPKEtfceeOCBevN/+uknZbFrKUyaxjhdnRK/ADw/9WxkBEUiJSSmZv4Oqw2hNk8H9C4MY3+r2dzdylWYgTL/2kGGu4++CrO2/o1fB0ysmTcway+qTGasdcbBbO482c9rYHI1dyorXVNTIxPstKekuCYAP//8sw93snMhbVGLtIVv2oLJEltLW787G0POfy3SFrVIW3hvC+ZkiYuLQ3FxMSqbeg93QYqKig70LnQopD1a1xa8d6gdmV+MyYVb8+7s0qK7Ndxxxx0q8ZoOBToTsB199NHKXbalMEs5k6a58/LkM+qtNyoxFn0DKmGvrIS9ogKa3Q6DpqkTZDYYYDYaYXY6YXQ6YeCyqir1F/w/R2k4asO/+v8bGrkxGqEpa7rRZV32/I7BUO3c7OV7XF//XvU29HmayQSNQtpsdn2mkOZIED9Xr0frPa3a+lTpdCKzrAwJRiNCSkpgLS6GsaICTparohtyFxbjzFKuBmMMBiztPUpNNWgaHv/hRRWC8HrxDeh94sEI7gJ3Kh9SFeXlsDscKuFaQGCguqfYIVcZ0N2ocjjwc0YGZjCGnDOCgoD4eFcpsrAw1/XXTeAIKjtQM2bM6Pb1VKUtfNsWunW6I7w7vSHnvxZpi1qkLRpvi/LyciQlJalwL3qbdRdolaSoYp4Z5WHXzZH22L+24H1EY+20adPq3UfNfXd2ga58w3BkL4Oli9zg/9kB8GblJkwGxckTPXlUS2FZMGYpTy8ory9kq+Ni40JtOHnGRFVOig9M3U2PE5PHcWSltNpFjxcKLxCOXHKyUIwbDDBSdDscLvHcyF9QrLsJdiWSzWY4qwWzEsm8AKvFshI37vOq/9b5TFFNIU2XcYdDiSv9M90xuL9cTncM7jP/+lutCLFYkLlpE/z69EEuBXdJCYIrKxGQlwe/vDy1f87AQDV1NZHFsmDMUs6kaa6roJbgylIU2gKVpfud8JGYv94PF/Ww44RoBzqj0VvHZDbDzy0DemlxMYoayoBejaVHD1h4bXM0cts21/XGuO/ERFcCtuDgLh+asL/PoK6ItIVv2mJ/ttPW787GkPNfi7RFLdIW3tuCfTH2w5hbReVX6SbobsP6sXd3Okt77NmzR+XjWr16NcaMGaOqUB1++OHIy8tDGI0uB6gtuB7X9/acae5zp0uL7smTJ+O7776rM48jgJzfXrAO932zh6ns5Z4WZF0qcDnXg1tiKo6+uF8cdGugCOdfjrboYryssrImlkC/GMx+fuovxW1bjWbVE9VVVTWiWv9t/p4+cVCDI0HshOkXqNo3DhRYLOri5X5v2rQJgwYNUseUk5OjbqpcJt+qrERweTms2dkwc+DEZIIjOBgaR5e6gMhicjSWBWOWctdVUXtMRX4BmHP6/bjWmooAYzgyyw14YZ8Ffgu+xoihPdDrkDEweCv43UloKAN6Xm6uuvZZ/9vmXk6MQpsPWk681gsKgNWrAV4LzIDeo4dLgDcwkCYIgiAIQueDJX7feeedmv9HRETgoIMOwpNPPolRo9w8BNtY6DWH+++/HwsWLMCaNWvabD+64/nNz89X7ahDDymWhY5i/64NoX567rnnVDWr7du3K50yZMgQVdXqvPPOU31Sb/vTlnQq0c14lB07dtQpCcaLnTdhr169lHtbSkoK3n33XbWcpcJeeukl3HbbbarM2K+//opPPvkE3377bbvu9zEj4vHKeePc6nS7oIWbgpvLG4MClQLW052BolcX45woXNlGuoVcjzng991Fr2cCAELxrItqd3GtJxsg+nf5lxcrJ11U62Ja/9ySUTSuS6HFiQMJFN7MgJ1VUgJjaChCqqpgy8+HOS8Phvx8aFYrnBTgnnHDnQyWA2NZMFed7tr5MVbgGtZlj4jEiVolvs0y4Zd16bjsl3dh+dmB/1T9FzMn90W/gM6fA8BbBvTMzEyXF0VEhPJMCasuQaauKY4m6g9iJmDLzASSk13u53FxtSXI3KzlgiAIgiB0To455hi89dZbNbma7r77bhx//PHYx+onnQAamDqbB8aB3GeTyaQ8ldsSaiUm0l67di0eeughZXxln3LDhg145plnMHbs2GYPtuwPHde/wAsrVqxQDcOJMH6Mn++99171f46MuN+EHLWiwKZ1m/W9WTrsjTfeaNca3ToU1n/95wi8f/EEXDDQof7y/00J7sbQLcp0t2CCuN69e2P48OFq9I9/OYLDNoiJiVE3D28ixh3QoswpNze35jNHdpgIgEKb26ULfo8ePdT3aYnm9jiNHDlSbZ/l1/r06aNqnnM0ivvA7NQUT/vjtsLj4e/ytwYPHozw2FgUBwcjNTYWOUOGoGzoUDhDQmAsLIQlLQ1GWj3pNt+JhfdHoyvw9OBKdV3w74ejKmrqc5sNwIkxDjw2MQBLps/GD4On4OOQIbh0oxXP7DEjv6LrZKCktwQHljj4QjdzwhJkHFzbuXOnEuMcTKrJNEnLNh/MPXu6xPiuXSxZAPz1F7B9O1AdoiAIgiAIghdKSlyTm4FFJT3lPLdqBHXWdX+v0vuM88rLm163ldC4QxHGicLo9ttvVzHq7B/orF+/HkcccYTqQ0ZGRuKyyy5TRigd9hsefPBBJCYmqu1xOz/88EPNcvZ1CTUF+yKHHXaY+j9dmydOnKj6t+znTp06FXv37sXbb7+tEkdSxHF9TpxH+PmVV17BCSecoL73yCOPKEPWJZdcon6H+8j+7fPPP1/nOGllPemkk9R2o6OjVT+cxsPGkt/xN7lftMwOHDhQ9aGocdg+7nz11VeYMGGCasMBAwao33BPBuZtn8nChQuVZwG3y77+ySefXPMdGkluueUWJCQkqO9MmjRJtZfnvv34449KMwQFBakBFGo13VOAXgzcN70N+X16HfBzYx4ELP986KGHqrakZfy6665T/cOGoIWbCdB++eUXXH311er8U8Occ845+Oeff1TbtQedyhzEm8Dd8uqJfsF7fofuIh0BupBP6huBnM2a+qu7lLc1erw3bwIdPc29e7w4HwIUye5Wat1SfaCTLFD404MhPDxcDQbUWL/pxt6nD4KdTtiKi5XruTk7W33HGRQEJ7PkdjL3c7qasywYs5SPsDvdct3XEhgSiMCrz0NKGTAtxYE/8kz4KdWOq5+4DbumTEPPM2bB4te5RlIbQx+4UQmYHA51vaampqq48AB/f4SEhiLIvQQZwzE48SXC+O8NG1xCnFbvhARXArZqIS8IgiAIQnWSUkKvseho1+enngLuvhu49FLg9ddr142JYZpmupkCfVzlbjFvHnDjjcA55wD/93+163I5+2Z8Fw8f3ma7SyH9/vvvK+FIcU0otig0ab1cvny5GqCny/C1115bI2z5l4a3+fPnK2H95ptvKoG5ceNGJbj+/fdfJa4XLVqkjD7sG1OUUgTPnTsXH374oRK/XI99jjPPPFNZSSnc+R1Cg4EOBeXjjz+uxB771BT9FPyffvqp2u8lS5aogQEars44oza5MkUh+zW6+JwzZ45aXxfB3mAfmcvp5cv9vuqqq3DWWWfh77//Vsv//PNPXHDBBWpfeOz0IKSYJ/fdd1+D+0yjJUX2XXfdpbbN43cP2b3mmmtUiOhHH32kjGVffvmlEtUcANFFLPftv//9L9577z3Vr6MbN4U6Xbz5d/PmzcoYqHsysN/Pvl5j0AjD33n44YfVeeTgC/eFk74dT/h7LCGtG20PVC6ITiW6hdbDh4S3ePHOsN8cPOBEa35BQYES3/ybz9jviAgEVlTAnJOjxLclIwNOk8nlft4Fs3Qm+AMPDqjCmkI79n7xCwZn7UHgbyU4b9hszOlrxLRwJq5Dl4IDMHQv58SXIMMomHWSD0mOcirLeGCgGr020K2cidY4cZSeGSXT0wEOQLFDQcs4X9ReEj4JgiAIgtCx+Oabb5SVVBfYFKqcpw/Of/DBB6pfQGGoG5sYWjp79mwlGDl4T+H3n//8R4lR8sQTT+C3335TAnPevHnKskwocHXXZnqDsq9JV/b+/furebTY6nCf9HJsntCCSsHsjntJRVq8ly5dqkJe3UU3++gUkuzvUPzTOn/rrbcql+iGvEhpUOPx0tJMaD3mfuoDCfxdegdceOGFSuDSW5XbY+itu+j23Ge2FSf3/abXMKFXMQUu/1JwE4poDkJw/qOPPlqzb6+++mpN+11zzTXqmPT2Yx+ORpWWuJOzPOW5556LG264Qf2fAv+FF17A9OnTlbXeW4Z+xnDr3gsHEhHdQqeBIovuLXwoUnTR+k3X+Ew+qOLjEZiQAL+SEpgyM2Fi/HdenhLeDj6sO1k8TVOMCdEw6vzD8WukGQvLQrHH6Y/7dgKjg524xbIXPfu3PmyhI6N7cZAqu12NovIlwmuDL1sKcL6sVBZlTvrIPd2OOHrK8BMOOrH8GJdRnEv8tyAIgtAd0V2w6SWoc+utAAWN57uR1nDinrT06quBuXNdCU/d2bOn/rqthJmrKaYI+30vv/wyZs2apUQlwyppLaUYdPfupBs4rcsUWwyxpPWU89zh/+ke3hC0utLlm1Z0lmCjpZQCmaK/KejK7QnFPQU1hSrzF9Fy7BlHzONgH0aH1nta9+kuzmP1BvtEdAHXYWgp3brZLhTdPEZavd2t5fR05UAF+1D673nuM927aeX3Bq3Z3AbDT92hgNY9EAi3rQtuwrajJ8L+wONZt26dsl67e/PyfDMc0X1gxH15R0B6m0Kng9Zvjlxy4ugY49Fp/S4sKlL1wQMGDIA/Y9MLCmBOT3cJcL38GB8uXhLJdUaMJiP6zZ6OuQ4gON2Oj9JMCF27GlM/vR9/T5wB/+vnIsqvi5m93WBpMYtbCbKi4mI1Ks2RYr58g0NClAu6chviy5gT48vofs6YbyZlpDsYy4/xJcHPXc1NQBAEQRAawr1SiA6T1HpLVOttXb5fvRk1vK3bSvg+pzu5DnMzcYD99ddfVy7GvoRWW8YL04L78ccfqyRuzBN18MEHN7nP7tAFm5ZgurhTSNPj9KmnnlLxxL6Gop3WarrK8zMtzLrV3N0q7LnPDZVW1rdJL8SVK1fWS86seyUQT7dtQ3UJ4f09nssvv1ydF0+YVNsbHBzYsmULDjQiuoVODS2adDuna5CeJI4jocUVFfCj1ZNJ5Gj9zstzxX9zhM1odJUf4wOlC4isABNwcYIdx0fZkbF8I4zQsNXpj/9usOHsODvOjHPA1jXGGZpdgozim9eBlTXAg4IQwgzoFOAcuae45sT4bybiW7fO1cGg8Gb8N+PA27DDIAiCIAhC26DXVqa1mNCyyZxOdD3XhSMtu1yHrsd6YmDOowuyDv9PSzDhYD2h9dYTPYEzKyRRMNOdnaKb3/G2vjf4W1OmTFHx1u6xyd6suDwuXfAuW7ZM9WGYLKwhGHbHRNP6sWzdulUZo3SL77hx49Q8Dlywn8z2aE7CY7qhM8bc001ebxMeO63WTGjWWqwtaEMdHg9jyd0HYpqCrvN33nmnyvHlGddNF3h6HXgOOvgCEd1Cl4APELrTcHIvO5ZfVKSWBSYmwpqYqKzfpqwsmHNzXeXH/PxUAjb+7ezE+AExV56Bv6eMxc/23ih3GvBWqgX/7CzALUWr0eeYqco63pWpU4KMSVgrKlT979ycHDVAw5cNR5j5QlNu6hTanJh5NTfX5YLOBy9LjzHGiAK8k5emEwRBEITOCl2WWSqMsG/H+GVaOxmzTRjfy9hkxiwzGRgTazGJGpN20bWcMC6a69DVmS7dtGDTfVp3UeZ67BfQos2EZ7QAM6b7tddeUwnXKNopXOmuzqRkhNmv9dLF/A77Fiq0zQsU/4w5ZyZvxnMzsRiTvulZ03Uo/pjlnBZ1JlLjPjMOujGRTIMDj5dxzezXcH0OCuginBWeGJdO4U5XefaD6B7ORHCNeQrwt4888kjVZoztprhnIjXGxtNyzHZnW9B6TyHLdqdIp1g/7rjjmnVu+/Tpo9qEbUu3dPdkdA3B3+fx8TiZMI9imSKcHgi8NrzB+G8mhuPxMJ6dAyAcvKH1mx4H//vf/9qlZFirRDdHZ3jB8i8zAvJi/f7775VZn4H/gnAg0WuIeyZeK6yshH9AAPyHDIGpvBym/HxX/Hd+Poy5uSr2mwK8s1u/E0YPxOMa8FtuJeYnW3DJt+/iiA2/4psNW6FdNRcjgztGbIuv4VnkC5CTXgOcLwVeD3yhKvdzJuPz94eJLlac6PbE+G/GfjMmjfHftH4z/jssrMuEJgiCIAhCZ4BCWI+jprBlzDKzgOuJsRg3TOF2/fXXq9hm/v/UU09VydP0EqN0RWY/8Oabb1bW2WHDhuHrr7+uybJNsUrRyiRfFKm03tKdnKKMicnoRcl9YLkpujYT/sYXX3yhYs5pWaYuYgy4N/gdWlmZ9Zxi7+yzz1ZWb2ondygKuU/Tpk1TfRaux4GExuDxUojSmpuSkqL2nSJSh0Kbied4bE8++aQS6WxDCtbGYPuynSlSmdWcYp37pcPjpWhnm/J3mXOJYpgCv7nMnTtXZWpnPDkHUpjcjkK8MSjqFy9erJLk8VjZv+PAANu2IdgPpCh/9tlnVQZ7uvpTJ/A64LUxYsQItAcGrYXO9TxQJjBgAgLWPGOgfr9+/dQJoXvDZ599hq4EXTE48sKbVZUv2k/oxsCRomOPPfaAFZ7vKLRXW/AS18uOUXTREs4YlMBqd2NjURFMOTmwpKfDUFzsSr7Gc92OAovONRvMZoxgLHobbrfCoSHl/a9x0E+f49wzH8a6+EE4PNyBy3raEe/XccW3r9qD8CVcUVmprOAcPaYA572tZ9KsGVGmyxPjvznxWmDSNb38GMV4Ow3OyDOjFmkL37ZFW77v2vrdSeT81yJtUYu0ReNtwYRZtMjSquots3NXhe/6lrhTH2go2CneWXO7udCtnlZcfq+rtYcvaU1bNHYfNfd912JLN9POc2TjpptuqlN6ikXpGzLrC0JHKjtWk3itsFDFknCU0NanD+w9erjEd2oqzFlZ0Fh6LCSkU7ue+5kM6Hfhidhx8tHomROM9dkafsszocfvP2NGVRpizzsR/sGuzJUODVhXZERuFRBhAUYFO1UN8a4GH7D+NpualACvdl0zmkxqnl6CjALcQOs2p6oqV/z3mjUui3hUFMAyGRTg3agT053gYJ2eEdXbX/1aooWEg3jdvRMjCIIgCALaTnQzDoBJBDyhizmFjCB0ZDjyy6RrdINxLzvGicsCoqNhj4lxJV5j5vOcHFV6TCVe68TJtcJD/HFriB0nxzrw5vZK3Lz4XUSUFeIhaxzCZh+FYLOGefssyKqqVdnRFg3X9qrCtAiXe1ZXRAnw6nAEvYQG3aQopDgYQwHOEU3GiJsjI2Gg2GbyFibkS05mmk5X7DdjwBn/LeXH2gUKX8aXNSaKm/rL883Pnn/dP+viWv/s/n/9+tEnXjO8TvSkfroY5+T+2X0SBEEQBKF70OIeIhNVpaWl1Qv+Z6xCAl0vBaGTlh2j8KYQZ4fbxtjvYcNgLipyZT3PyoIhLU2VHHPSw6OTWrUGBGh4ZKQZ6y6+CsZFv+HtEUfDsZedfw3+leWAtbZERFYVcO9OCx5E1xbeOnrIAaGgY0gCrwddUFFIUZwzNsgaEABLaCisFRUw7doFcKJFnM9ACnMpP9YieM/pE9ve8zOTy9BtkoMihAlg9NIjjU1EX89bqRLOa2ziuedfXhuey4i7QOc+cv/0eZ5wW7pFXP/Ma0pP/OcpzL0JdUEQBKFrQlfx1rikNxRHLnQB0c0MdgzYZ3A9Ox7sYDAVPoPS9Yx+gtAZy47RW4OJHHTrdx4TrBmNCOjTB7bERJhzcmBOTYUlIwNOljlg3EYnjB8zGA3oc/gEVE2fgMsynHg12ajyh737yX0osAXivhlXIiWUGT8pLDS8lGTB1PCKLulq3hAUPHqtSV1EUfQxH4Bu5dRFES3h/lYr/LKyYE1JgSUgAObYWBj0+O9O7CHRWnRLsjcBrbelXqaDkzcrs6dgdhedDQlhb8LYl+jCuSl0C7v7xONnaIP+f89BgoZEui7U9eNj+3X3OFZBEARB6HKi+9FHH1XZ+5h6np0jZn7jX2bNY4p7QeissBPLPAWcmKVSr/vNxAhFlZXwCw9X7ud+BQVKfJvz8tT3KL6ZfK2zYTECgwI1aDBgWOYujE3dgkqzBXY3K76tqgKZsKlY77EhXd/a7Q1d9LgLG8ojh92uhCQHagocjhqhZykvh19aGgLWrIElPBym+HhYe/WCNS4Opuram13ZGq3/bchVW8eboHR31/YmmnULMgc6OpPlVx8kaO4+N0ek623B51R71BcVBKFz08K8yYIgtPH902LRzRH2119/XaXUZ3w3O5ysz6an3ReErgAFAGsGRkREKOumXnqssKQETsZ+DxqEwPJyl+t5djaM1XHfTnZ+O5FbMZOmkU2x/TDzknkYmrkbGcFRNcvnf/koYopz8fnJcxF6yBD09afV8cDtb0fBUG3pVrW+vcQal1utKGbyNXpH7N0L07//whASAlOvXsprwhobC79qV3Vea+1hlfUm6ryJaHdrtC6gOXmzRru7bLsL5oaEdKuprISxrAwGxtOz7VNTYWQtdn3igAinLnJxNkek8xxwUFA60oIgNIY+YMyQKYZICYLQcnj/kP3xLGt11h9aunVrN8U3XXLDWVJHELoQ7PwyoRYnuqAzxjc3N1dd75m8gXr0QHBcHGwFBbCkpcHsHvfdCSxxzFKuszOyp5p0bFXlOCh5IwKqKvCrMxJvbPRDT5sTJzpSMdVShLihfZSrulALhSUHJhXs3NALggKpshLOggLY169Hwfr1qAoOhoMJ2CIiYImIQGB1uTJacFXMuNXaIkuuLqK9iWd9Hv+6W6PdrajuLt06ekyzNxHt7trd1hgqK5W4ViK7tBSmggL1GdVWXsbN27Ztg5Fik6KfAx8WixLfTmakDwysI8briHJBEIRuBp/XzMfE+tSE/Zn2Hug9ELjn2pDqEtIerW0Lveww7x/eR/vjZddi0c16cCNHjsQll1yiOmrTp0/HkiVL1E3M4ut6sXpB6GrwxmQ2a05MGkjrNy1NdO/MCwmBf0gIgktL4ZeeDnNmpuroO5hQqwN39lkWjFnKmTTNZb+tpdxiw+Qr38IRyesQ2y8eSYUaksqNiFj0HSav/BofTjoBq8+8GNMjHBgaqEH0dyNWcQrx6GjXVFWFINaDT0pCVWoqyoODkRsWhkpmyK+2fOvZ0+k2rFvTmeyPHaWGLNHeRLTesdLjot0FtO4y35RLt8/gPukCu7zcJbCZR6FaYBsosCmqKaYpnMPD4ahui6rYWFf9dh6j3a7a1MCkdiUlquqAykZAUW4y1YhyeqhoHBALCFDt7C7I+bczDJIJgiC0BiaMJbrw7g7wHUBPRVX+sxsMMjSFtMf+tQUFt34ftZvo/uyzz3DeeeepzwsXLsSuXbuwZcsWvPfee7jrrrtUUjVB6OrQEqmXHispKanJfp5N8dK3L4LKyhCYmwtTbq4SDxTfWgd062JyNJYFY5ZyV6Sy+8NHQ4F/MMYeMxHTIqpQ4gCW5RuR6OdAmdmKXxJGY1GGGZ9kmDG4Ihd3r/gYmDoJPSYM61ZJ11oMB2PoFRQeDnN5OUKKihBWWKjEYFVUFCpCQ1EeEFAzqKNboLdu3arEsnvCLfe4aF1Eu8/rMFBgU0jrArukxCWw+bmyUonnGoFNQcwkds0RwUajSzBTPHtbzlh7u901cUS7uBhmivTqNtT4GxTduqWcVnJ//7pWct1S3pHaUxAEoQXwfcFcNUwYy0Ha7gCP848//sC0adMk2aS0x361hd632l9aLLoZ16or/e+++w5nnHEGBg0ahIsvvhjPP//8fu+QIHS2FxmzXHPifaG7n1OE59tsCIiIQHBhIfxyc2HMz4cjKAhOCooONMrIcmAsC/aiqtNdOz/GClzTs7ZcWKAJODLSCdw0B3tLzsb0Egu0IgeW5BsxYdMyHPrXt1izcztOMz+NQ8IdmB7uxJggB8yiwBuECfgcnJiturQU1uRkNQUGB8MeG6vEeVVAgBLfzC/QKZKHUWBT4FJQU2QXF8NUWKjmUXgrwcvKF35+LoHty1AMDlJw8vPzvpyinFZyux3GkhIYCwpclnPenyw7xpex2ays5XRdp6VcTbScV4t0Cn5BEITOQHcqP8jjZFgVw7a6u8gk0h4Hvi1aLLoZ17pp0yY1YvbDDz/glVdeUfPp795dbmRB8AbdgJnXgBPjRPTka9nBwSqJVlBJCYJyc1Xst9Pf31VyrIPcMxTWLAvGLOVMrsZYb7qeN6SXbYE2HBoIHBpThQonsBc9sSTnCPwSNRh5dgMWZpnxbYYDP795PVL6DUL6uRdgZI9AWMVY6B2K0MBAl4hzOJRQ9du2TblEG1n/22ZTteKNvF5ocaWFl8KQf6v/X2e+vp6voXt3UwLbZGofgb0/oryh5dWCnJOpqAiG3FyXVZ7QMh8QoO5jDo7UnD+P5HqCIAiCIAgt7h3MmTNHWbcpumnlO+qoo9T8f/75B0OGDPHFPgpCp4OjZ5zogs4M/7r7eWpoqCo5FpKfD1tWlhJGKu67IUtcO0KB3ZqyYH4sPTZ+IDB+IM5yAoOLKvFHnhFlazahf04SIkrycWHytfDLNGFyqBPHOVIwvFcorDbvx+zQgDVFRqx1GlT5sjGNiP8uCUVqaKiaVJxyYaES3X4bN8JM62u1pbhGYFd/VpPHfCUoKQIpdHWByf9zchPuapnbdtyFu/t80CKsC+yiIpcQrXYRNzCZG63CtADTRZvXdWd3ydZdz70t4+BIeTlMmZkqgaJqWw6mUYCHhblEeEBA528DQRAEQRDaX3Tff//9GDFiBJKSknD66aerTLuEVu7bb799//dIELoQjKsNCQlRk177m9bvvNxcaFlZCMrLQ2B+vutGTEhAZ4e1vyeGOtVkT+yPP+MfwJ6UPITaTMipMmBRrglXvvcCErL24NXzbkP4wWNwcJgTAdXGzz9yjdVu7rrKNqlEb4w7193cuxN0i3ZUP2Ppbl5H/NHiyonu3NV/az5XT8ptmonJuMxz3eoI/hoR7w4Fu6eY58RtMjabP68LbMZB0xrf3cQlB0do2dZrZFdVKRFuSU4G9u1zxYIHBMAeGalCSjipvA4dKLREEARBEIT2oVV+cKeddlq9eRdeeGFb7I8gdJva37R+Z2dlITM9HcbsbLUOLWYIC+uQSddaitlsQs9Jw8EiZFO1CmwsNmBphh3xpbkIrCrHJ/79kLHLCotBw1mFWzEkLwn/jTkYhba68TWMM2eiN8add0fh3SC6IK5OgafTJlWbdWFOkV0t5tU8Wr6ZBE6EY32qM6SrcoFupc+su3ertuMACoW3w12EdwAPF0EQBEEQOqjo/uWXX9TE0gOetV3ffPPNtto3Qegetb9791bW7+SNG5HFkmQ5ObAxw3VkZJeJD2U5sZHBGkYGm1Dx2jz8uT0FRwSE4Y88J1IqjBj55w84Y/0iVI3biftnXOHxbWWPxUtJFhV33q1czQ8UutW6sXhnoVH0zOcME9CztzNZGysaqOVMoBcSAmdEBBx6PLgkZRMEQRCELkmLe/QPPPAAHnzwQUyYMKEmrlsQhNbBsAzW/mM95o0bNyJm+nTk79iB0p07EZycDBOt3uy0d6H7zGA0oOfgRFwOOy5LBHaVGZCzsRe2pvXCD4On1KwXXZyHa5d8hHfGHY+dUT2RWQmV6K01ceeCcEChu351pnr3BHSmvDxYMjJq4sHtjOVnPDgt4RThHSnpnCAIgiAI7Se6X331Vbz99ts4//zzW/+rgiB4hQNZtH5n9e+P3A0bYNi5U8V8m2JiVHxoV4NjCf0DNOyZfTxmDj+lJtaYnLPme1yw+lsMy9yF0857Ss3LrjyAOysIbQXd9Jn5nJOelK2sDOaMDBhSUlSyO0nKJgiCIAjdWHRXVlZiypRaa5QgCG0LkxMm9u6NKIrvgQNRsG4dDHv3IsBshiE2VsWOdjVYokzhZtH/q88YJbi/GnZYzbw39mro+8uP6DHrEASEVCewEoSukJQtKAjgpCdlKytzJWVLSnJlUA8MhD0iQsWMiyu6IAiCIHRx0X3ppZfigw8+wD333OObPRIEQcGSYz0HDUJkYiJytm9H0Zo1MOzZA7/QUBijorqU1Ys1wZmlnEnTXDHcwMrEYbg8cVj1GpqaO2nDMhy18HXsWfQtnrtrHk6OdaK3v0QdC100KVtIiPqvyhhfXg7rrl3KG4Su6lUU3rR+Mzu9IAiCIAhdS3SXl5fjtddew6JFizBq1CiVkdmdZ555pi33TxC6PSrp2ujRKOnXDzkbNqBk7VoYtm+HJS4OJsZ7dwGYHI1lwZil3JV/2z2G3SWq7+pbhdgCM3ZH98KXgw/FgiwLFmQBB4U4cEXBevQdPwhGU9cZiBAEHWY5V9nP9aRs5eUwlpYq0W0sKDjQuycIgiAIQluL7nXr1mHMmDHq84YNG+osk6RqguA7AoODETh5MooHDkTu6tUo3bQJlZmZsCQkwNwF4r1ZDoxlwVx1umvnx1iBa3pWlws7ajy0I8ahb54TU3MdWJJvRPnWXTjy3buxi2L8nqdxdKwBgZJ/SujKSdkY790FygoKgiAIQnehxaL7t99+882eCILQLIKiohB41FEoHjIEeatWoWzbNlSaTLDGx8PcyeM8KaxZFmxNkRFrnSaMNjowJthZp0wYs5+PjTRhbGQVUssN2J2ajEK/QKyN7ofnU/zxWpqGWVEOnOGfi7gYl3uuIAiCIAiCIBwo9qsIcDKTvABITExsq/0RBKEZ0KskuGdPBPXogaIdO5C/ciXK9u5FZVAQ/GJiVCmyzgoF9pgQJ8xmI0bYnWjsSHrYNPQ4cTJSjhqD7NRK9C53Ym+5Eb/vKcGjr1yBzf1GYNf1N2NsjJ+qFS4IgiAIgiAI7U2LAyCdTqeq0x0aGorevXuriXWGH3roIbVMEIT2w2AyIWTwYPQ89VTEH300gv39UbVzJ4pzcuBwqGJE3QL/QH/MGBiKt0dU4r+DKnFR9mpY7VUwFBXh5r0huHCDFV9kmFBaJc8oQRAEQRAEoYNbuu+66y7873//w+OPP46pU6eqeX/99Rfuv/9+lWTtkUce8cV+CoLQCAY/P4SMG4egfv1QtG4dCtevR3FSkioxFBgUBGMXynTeGEwrMSHUCZx6MFZPeAl/JZUi0AwklRsxb4+G2ffdgn1DR8Fy3umIj5SSY4IgCIIgCEIHFN3vvPMO3njjDZxwwgk185jFPCEhAVdddZWIbkE4gBjDwhB66KEIHjgQhatWoXDHDhQVFUELDVVZ0LuL+CaRvWNxYm9ghqMCP+WYkPbHSgzM3oewlYU4ZOLFKi78lFgHJoQ467meOzRgXZERuVWuGuKjPOLKBUEQBEEQBMFnojs3NxdDhgypN5/zuEwQhAOMwQBjfDzC6G4+aBCK1q5FQUoKCktLYQwMVOK7O1UaCDABJ8U44Dx5FP6IvxdrU4pRYbZiWQGwrMCEl356Hv6D+qLHsdPgH2jDH7nG6gzqtW3EGuIsaaYyqAuCIAiCIAhCC2ix2Wv06NF46aWX6s3nPC7zNfPmzUOfPn1gs9kwadIk/Pvvvw2u+/bbbytx4T7xe4LQLbBYYBo4EGHHHIPE6dPRMyQEAYWFKMjNRWlpKTTNVf+6u8Aa3r2mjsLsM6bg/ZEVODXWjrFZu3D86p8x/ZM3cNUKO+7YZlG1wt1LlhH+n/MpyAVBEARBEATBp5buJ598EscddxwWLVqEyZMnq3lLly5FUlISvvvuO/iSjz/+GDfddBNeffVVJbife+45zJw5E1u3bkVMTIzX74SEhKjlOt3JwicIiqAgmEaPRlhCAoK2bEH4zp3ILS1FQUUF/Gw22Pz90d3uikQbLdd2lEeE49eiuUhLycHugCjsLuBSDeet/h67w3vg796jXYHiqoU0vJRkUSXNxNVcEARBEARB8Jnonj59OrZt26Yszlu2bFHzTjnlFBXP3aNHD/iSZ555BnPnzsWcOXPU/ym+v/32W7z55pu4/fbbvX6HIjsuLq7Zv1FRUaEmncLCQvW3qqpKTfuLvo222FZnR9qindsiLAyYMAGBCQmwbtuG4LQ05FRVIa+yElY/P+UF0lG0pJ533df51y1B/uh95kz01IC56VV4PdmCsLIi3PXr/+Bvr8DJ5/0XqxP0cBoDMiuhaoizpFlXa4vOgLRFLXob2J3ONntu7M92fP3udN8/eWdIW7gjbVGLtEUt0hZ1kfbwXVs0dzsGrZP4mFZWVqpY1M8++wwnnXRSzfwLL7wQ+fn5+Oqrr7y6l1966aUqyRvLmY0bNw6PPvoohg8f3uDvMAv7Aw88UG/+Bx98oH5fEISuycpsA97dbkJUSR6uXvoJhmXuxplnP1Zt6QYO27kC2YFhGHdoX4yP6hSPTUFoEQw7Oeecc1BQUKC8xFqCvDsFQRCE7khpM9+drRLdeXl5qmzY5s2b1f+HDRumrM8RERHwFampqUo8L1mypMatndx2221YvHgx/vnnn3rfodv79u3bVXZ1NsR///tf/PHHH9i4cSMSExObPVrfs2dPZGdnt7gT0tBoyM8//4wZM2bAYrGgOyNt0QHagskPd+1CVXIyCisrka1paoCL+2C1WmE2t9gZps2seJvNZgy122Fqp99cU2jEzVuttTP4aKwW3EanA4tfuww9CzJw5xl3Iv7wg3BEhAM2U9dsi46KtEX9thifkIDYNsqnwvddVFRUq0S3r9+dRN4ZtUhb1CJtUYu0RS3SFnWR9vBdWzT33dniHjVF6+zZsxEaGooJEyaoeS+88AIefPBBLFy4ENOmTUNHgeLcXaBPmTIFQ4cOxfz58/HQQw95/Y6fn5+aPOFJacuLtK2315mRtjiAbREbC0RFwZKYiIAdOxCRkYECf38U2O2qA11WXAyT2Qw/qxUWq7Xd3c8prNpLXI0Jdqos5a4kaoYawU2CKsuwMmEI/OyV+DxxPCr2WPBqkhmXlG3HIbFGxAzwPojXWduioyNtUYvZaGyzZ8b+bKe93p2+2mZnRdqiFmmLWqQtapG2qIu0R9u3RXO30WLRffXVV+PMM8/EK6+8ApPJ1e1xOBwqppvL1q9fD1/AEQT+XkZGRp35/H9zY7bZKGPHjsWOHTt8so+C0CnhfdyzpxLf1r17Eb17N6LKy1EeGooyk0nV+abrTFlBgcqRQPFNEd7Van4zORrLgjFLOZOmuZKnuSi0BeKG2bfgjoRSzDEY8XWWE6kVRkz84h1M3LsWL59wFfyOOwrTwp2wdK1mEQRBEARBEPaTFncPKVhvvvnmGsFN+JlZxX0pZunqOn78ePzyyy818xinzf+7W7Mbg4MDHBSIj4/32X4KQqfF3x8YMoQuIjAMGgR/gwERRUXoHRaG/v36qVJ90dHRMBmNKCkpUbkU+LfKblcStSvAOtwP9q9CtMegZYwVav7MHiacFe/A+yMr8VS/UtgCbag0mvF/PSbgoV1WnLHWDx+vy0NuctaBOgRBEARBEAShg9FiSzeTkTGWe/DgwXXmc56v63RT2DNxGt3aJ06cqEqGsdOvZzO/4IILVNz3Y489pv5Pl/eDDz4YAwYMUALhqaeewt69e1VyNUEQGslyzqlXLyZTAJKSYE1PhzU4GKGxsao8X1lZmZoYx1JeXo4SuqGbTGpwjFNnLs1H4c2yYOuKjMitAiIswKhgZ50yYUYDcFCkEXjwVmzIKcJR5eH4NktDdpUBPb77EmNWf4+PZp4HnH4yJoXW/a4gCIIgCILQvWix6L7uuutw/fXXK6s2BS1ZtmyZKiH2+OOPY926dTXrMoFZW0K39qysLNx7771IT0/HmDFj8MMPPyCWcakA9u3bV8fllQnfWGKM64aHhytLOROxMfGbIAhNEBwMcHCNrufp6cCePUByMkwBAQgKC0NQUJAK+yivqEB5WZlyQy8pLa0pFaQLcHevmM4CRfLYZpYFi4gMxhzYcX68HUsLjBjwTR6M0LAwfAiWbrcixqrhlKBCzAoqRWhsuM/3XRAEQRAEQejkovvss8+uyRrubRktXEyIzr90525rrrnmGjV54/fff6/z/2effVZNgiDsByz3068fkJDAJArA3r1AWhpVNQwREfC32dTEgS1mhKQFnOK7qLBQxYLzOcAs6EyyZLZYOkwt8LbGbAQODXcCD9yMFXsz0MvQAxtzNGRWGlD1428Y9vtb+GHayai64ByMDXa652kTmoFDc9VIX+s0wG40qsR34kEgCIIgCEKXFN27d+/2zZ4IgtCxYWZiupz36AFkZrrEN0U4vUsiI9VyPRMkSybEREcr13N3N3SKcHqjdAU39MaI6h2LK+HAxYkOLM41YsAPO2FxOrDMGoP/22pFT5sTJ0ZWYlZAEQLDgg/07nZ4/sg14sV9FmRV6deLSWWaZ+I7hgMIgiAIgiB0KdHdu3dv3+yJIAidA9bupvBmWEd2NuM6XOKbni0U30zIVp1gMTAwUE2RkZGuEmTl5SguLlYx4HRHp1dMZ3ZDbwo/I3B0lBO452r8s+V4VKEH/Es0JJUbsfGP9bhmwWP46+CZqLz0IgwNpIdQx7Tucj8ai3H3teB2ZZSvC0u7cf6DEOEtCIIgCEIXE93vvPOOiuM87rjjatzMX3vtNRUn/eGHH4ooF4TuAkUyhXdMDJCbqxKuqcRrFOLh4UBQUM2qtGjbbDY1hYeFqYznjANnIkRVkqysDA67vcYN3dAFa0jGDumNqwBc5KjAohwTEn9bCZu9ErsrTHhksx8GBDhxYrQDRwWXwd/f2mGsu/X3A+22HxT7/G0Xniqf/9fwUpJFJb4TV3NBEARBELqM6H700UdVjW6ydOlSvPTSSyqL+DfffIMbb7wRX3zxhS/2UxCEjgrNs7Rwc+rTB0hJUQnXkJPjyoIeEuJaxw2L2QxLcDCCg4NVNnTd9byouBhlpaWoKCsDIiJgt9thomW9CxFgAk6IcUC75UL8vW4qdjqiYdU07Cg14stVqbjovZvw19jDce+0y+vpzPa27vrCyuzUgHInUOoASqo0WHbugqO0DHsHDkepZkKp04DILRvQa9MarIkdiKzEQ1xf1DR8+d4t6uN1J9yKpLA4Jbz9M1KxYtFeJPaLg61XPMLMrkR4XdHqLwiCIAhC56TFvdmkpCRVgossWLAAp512Gi677DJMnToVhx12mC/2URCETlxuTLmfMxM657tVF9BhjHdAQICa6EVDN/Si0lLsKylR1vBKlcstoMu5nxuMBiSMGYgrAJxjr8AP2SaE//MHgitKYcnK5AquFTUNkaUFMEBDdiCzn2t4fp8Fw425MFdVQbPZ4LTZXNt0OmAuKlZi3RESWvNbxrIyGKqq4GRcvs3PNdPphLm0RH10BAXX6HtDRQUMdjvsZjOe3xdSvQ9ASEUxAirLkR4SVWNl/mbZPiTYdyIjNhG7eg5CqcOAqooKnPLJK7CUl+GJM29DkcGiBPbZv3+M85d+gQ/GHINHD79EbdbkdGDnU/9Rn6+97gPkV4cmXLN6K87/83Okjjoa0EW3wYDB2XsQUFWBcrO15tiO3rYMZ/7+JhYMm44bZt+qMseHW4D5H94Lo9mEL06/HKboaERYNPQsykJcSS5s8VEIiQxTye86i9VfEARBEIRuJLpZJignJwe9evXCTz/9pGpnE7qNMmGSIAhCTbkxim9mOq8uN6YyoVN8N2K9pnu5ke7lJSXo2asXCvLyVCZ0uqh3RfFNQszAGXEOaFedjA9HDsYHBdViF0BgZRkWvzZXCc0J1/6fErw5VUDy02/ixM2L8cCRc/HWhBPVuon56fhr/qUosdgw/KbParbx+Pev4ax1P+HJaRfg5clnqHmRJflY+dIc9bnPf76pWfe+Re9gzsqFeHHymciZdr6aF1BVhnXPn6U+97/1KziMPAcGHLV+MY5c/iXmTzwFbxw+XC03OQ14apWrksS2nEoU+LtEPoV3UGUZgipK1f8pjv0tRuyJTIBmNGGktQLlIQ74mwDLkAH4A8ejsOeQOu105Ul3ws9eiZyA2gGFQlsgtsb1Q0p0T7VNJwzIr3Bg3M416v+X512PrCrX9XbZP0txyu9v4cthh+Gm2Tcj1AxEWjQ8+PmTajDiz9nnwRoZpubFlRcg2lGGoOgwWG0ud3+JLRcEQRAEoV1E94wZM3DppZdi7Nix2LZtG4499lg1f+PGjehD11JBEAQdWi4bKDdG93E0EbtN9/Ow4GCVfI2DfYz/NhiNCAwIUBbyrgat36UjRmL9rlpL7jHblsJWVYFSi8uaraMZoASm+h40aO1QjK3KaFKDAIU2V7z+9qhe+Lf/WFgT4nBslF25znP65eSLYLDZcOMADdaASgQYNYQmHokVJ03G8LBg/BhSDquhOupg/vNqzx9y/YLrhwaMAGaOQIIGvLFWU8KWR7m433iPPdLw20FH47JLpuM4AzBTq0BBFZBb7sQf190BZ04eZg/wR7bDjpwqAyJtRmQERyEtNFq1V74dKKp0YvL6v5VAv37SRcgucV2Tl/+zGHf8/ja+GH447j3hJpRV6+mHfnoFJVZ/vD9mFpKrXdwltlwQBEEQhDYV3fPmzcPdd9+t3Mw///xzlZWYrFy5sqaGtyAIQkvLjTUExTVLkNHLhqJbF9+0eAd0QfHNOGF3Ph95pJo80W65HvtCrsWFAC5ERfXcMOyZ4bJw/45y13oagPFzsRtzcRqA0wz6fD/sPORj9XmRyTVPMfY87HCei/gSE7DDNYuCf+AtX6LKaK4Tn//pqBmYcvp0HB7ixOGw127j3OPVn37q32q1yth+1FrwmwMFLF23XRZmHoi7ouX/gWt6VtUIXTPTC1g5GYFp49z2oXrfBs5C2aWzcIwGTLGXKyGeW2bH7+dfDUNeHqb1DkC2w4GcSgMitUpUmCzIDAxHsdP1A2aHHeev/k59fmv87Jo9GZq5GxGlhVidMAATorpWDgJBEARBEPafFvcOwsLCVPI0Tx544IE22B1BELo0zSw35g2K69DQUGX9Zt3vriq+mZiLccK6dbc+GmKsrvWag9LI1UK5ztY4T7mJe2B2zRtrQe1+GAyoMln2az9aC1226brtiqWunc/fpuBujUu30QCEWThp6E/T/ImufCTXKSFf/SPDTkHq1SfjkEo7Ls+rwvxki4pBf+ywi+BfVaEs5joXrvxGue+/sesk3HLSHIwPcWJCsAP9/Z0wmrrGdSkIgiAIQutp1ZD8n3/+ifnz52PXrl349NNPkZCQgPfeew99+/bFIYdUJ70RBEFobbkxxn43AMU1B/+U+KblOztbiW+WG6P4Zux3Z6al1t2uvh+Ewpqu266a5SaMNjrapWY53f2DbBYMCXQdb4XFD/Mn0V+gLnn+IUgPisCffcZiRaFJTYuy0/Hph7dj47AJWH/x1ZgQ6kRMww4dgiAIgiB0YVo8BE+X8pkzZ8Lf3x+rVq1SmYZJQUGBKicmCILQ4nJjY8YAU6YAAwcC5eUuEd4EtHCz5jcH+5jY0ernp55DLD2mKZ/qzouy7vavQrSHcZnWXc5vr4RdHWU/CAX2mBAnxkdp6m97xk7r3gf6YIMnTxx2IWZf/zYuPG6YGog4ONSBw/etRkRpAZCVgyf3WnHGOhvOX2/Fig9+wp7fVqC0xM2lXxAEQRCELk2LLd0PP/wwXn31VVxwwQX46KOPauazZBiXCYIg7He5MYru7dtdNb9pDW8k5luJ7/DwOm7n/GuxWNTgYGe1fB8o625D+9Gda1M3x+p/bW87+gUZ0C/IgdPiHKjqczj+Gp+IbaUmDAt0YkuJARnFDhz39Tvwt1dgVtmLMPXtrVzRD7YUYWCYBWarxIMLgiAIQlekxW/4rVu3Ytq0afXmM9YyPz+/rfZLEITuXG6MFm+K7p49XaXGmO08KsprnW8dupdHRESopGu0eFN88y9LkNkovtH50K27ZrMRI+xOmA7gfowN6d7lsFoaW26xWpA4YRgSARyJShTZgU1pJVh50OEISdqDzVF9gGIDNhQbEf/7Ahy6+jt8cfS5yJ51nBLivWyae866Ojg0VA/GGGD2q8AxTg0mBqoLgiAIgtA1RHdcXBx27NhRrzzYX3/9hX4sDSQIgtBWjBjhSry2bZvL+s0yYxTljUDxzaoKIdUDgbkU3/n5nVp8Cx2D/bH6B5uBST0DgZsvVf//sKISKwuNWFlgxLj07aqG+UqE4qt9Ll/+IZW5uOevd1AxejQijpyiEr8R1gt3CX/Xj767PRfxq3/FfbOH4ZgR8T48ekEQBEEQ2k10z507F9dffz3efPNN5baZmpqKpUuX4pZbbsE999zT6h0RBEGoBy3b8fEusb1nD7B7NxNIuJKwNVHj22I2IzoqCmHV4jtHF982G2w2m4hv4YBa/eP9NBwf7VCT88m7sXTzHvT074FxVQ6sLzZi8Pa1mLr8F2zYtwfHRx6BAQFOxFo1ZG1PQiHrg7vVbU8vKMeV76/CK+eNE+EtCIIgCF1BdN9+++1wOp048sgjVcIiuprTgkTRfe211/pmLwVB6N4wpnvwYFd8944drkznNpsrCVsTMduM7Y6Ojq4JgcnNzVXim8KbAlzEt3CgYVmx+BH9XHXUUYVyB7DXloDFJSdhrS1GrbOj1IgdJRr+/fgehJYX45Tz/4uNsf3VMj3K/IGFmzBjWJy4mguCIAhCZxfdtG7fdddduPXWW5WbeXFxMYYNG4agoCCUlZWpxEWCIAg+geXExo1zWb8Z880634z1Dgxs8qtWqxUxMTGq3FheXh5y8/KU+OYzi5nPRaYIHQWbCRg8ohcw4jz0BnBIVTm+yDDhp22FcBiMcBiN2B7Zq853KLzTCsrx7+5cTO4fecD2XRAEQRCE+rQ6VSo7sBTbhGXDnnnmGTz55JNIT09v7SYFQRCaV+M7MdFl5aa7ue5yTiu42dysZ1dsbGyN+OZUWFDgsnw3kiVdEA4UjB3v668hMzgSk696G3FFOag0ew+vyCySUmSCIAiC0GnrdFNY33HHHZgwYQKmTJmCBQsWqPlvvfWWqpP77LPP4sYbb/TlvgqCINRCrxoO/B18MBAd7XI5z8sDmlmjmwKbiSH5/IqJjVVhM3Q/r6ys9PmuC0JrhLfCYEB6SFSD68UE18Z6C4IgCILQySzd9957L+bPn4+jjjoKS5Yswemnn445c+Zg2bJlysrN/7NeriAIQrtCi3doqKumN+O9meWcVm/GfDcDWrjj4+KU5Tu/2vKth8rQKi4IHQFmSY+2aNXlyuoHQ3BOXKgNE/tGHIjdEwRBEAShLUT3p59+infffRcnnHACNmzYgFGjRsFut2Pt2rUqzlsQBOGAQbfy3r1d8d07dwJ797oyn9MC3szBQH+bDf7x8Up8M9kard4U3wGBgSoTuiAc6Kzp1/aqwr07LW6p01zon1g2TJKo+Q6Hw4H87Gzk7d6NgOhoRPXsKQNzgiAIQrNodk8yOTkZ48ePV59HjBihXDPpTi6CWxCEDgMTqo0cCcTFuRKtJScDYWEuS3gzoYU7ISEB4eHhSnzT8l1uMCAoMFCed8IBrxP+IKqq63TXzqeFW+p0+1Zs52VmImfTJlRs2wZrURFy/PyQ368fwocNQ6SIb0EQBKGtRDdfOu4vFbPZrDKWC4IgdCgojOlezkznzG5Oy7fuct6CRGkBAQFKgIeEhCAzMxMFBQVqnnSuhQMtvKeGV2BNkRFrnSZMSojGMUcfLBZuX4nt9HTkbt6Miq1b4VdaitCQEGi9e8O/tBRVW7cie+dO5PXti/DhwxHZq5c8HwRBEIT9E92apuGiiy6qye5bXl6OK664AoEepXq++OKL5m5SEATBd1gsQP/+LhdzCm8KcHaI6YJO1/NmQMs2Rbd/QABysrORk5OjkkryuWds5jYEwReu5mNCnDCbjRgf4yeCu41h6FxeWhpyN21C5fbtSmyHhIdDi46GVh2uooWEwBwcjJDiYlRt346c3buR16ePS3z37i3iWxAEQWid6L7wwgvr/P+8885r7lcFQRAOHCEhwOjRLpfzbdtcVu+ICCA4uNmbYEw3M53TuycrK0tZvf1sNpWETeSOIHQdsZ2bnIy8jRtRtWMH/MrLEcxEjbGx0LwNshkM0IKDYQ4KQnBJifoOxXd+nz4Io/ju00fEtyAIgtAy0c3SYIIgCJ0Sdpjj411ie8+e2tresbEui3gzoeimy3luXh6ys7JUfW9avRluIwhCJ7ZsJyUhZ906OPbsgbWiAsFRUdASElzhKk1B8R0UVCu+d+50Wb579UL4yJGI7NtXxLcgCEI3R3qKgiB0HxgeM3iwK76b5cVY25ulxWjNamaSNJZGjI6Kclm9MzNVlnPOY5ZzsXoLQuehqqoKeXv2IG/DBlTt3g0/ux3+dCEPDobWyqSJGgfh+vZFUEkJ7Hv2IGfvXuT17o3wESMQ2a+fiG9BEIRuiohuQRC6H0yyNm6cy/rNLOeM92ast0eOiqZKjCUmJiI4JESJ74L8fGX1trTAci4IQvtTVVmpyn5RbFMYW51OBHEgLihIFWNrCIcGrCsyIrcKiLC4aqczvt4ruvguLVW/kUvx3bOny/Ldv7+Ib0EQhG6GiG5BELonTIiUmOiyctPdXHc5Z+e7me7iTKYWHhaGwIAAFevNEmPlFRVSXkwQOiCVFRXIY7bx9evh2LcPVoMBgQwxCQho8rt/5BqrS7XV3tfRFk3VTmdG+QYJCFDi21xWBvu+fcjdtw/5iYkIo/geMADWFlRUEARBEDovIroFQeje+PsDw4a54rtp9abLOZOssb53M4UzrVY9evRAcHBwTXkxxn7r1R4EQThwVJaXI3fbNhRs2ABHcrJKjGijlwvv/WZAwX3vzvoeLKyVzvmsnd6o8Cb+/rXiOzUVuUlJyO/ZE2F0Ox84UMS3IAhCF0dEtyAIAqHFOzQUSEmpdTmnEGfMdwvLi+Xm5CA7O1uVF2Pst5QXE4T2p6K0FHkU27Rsp6bCYrXCj8nRmnlP6y7ltHC78ByE4/81vJRkUbXTG3Q19xTfvXvDXF7uEt/79qGA4nvkSIQPGKCqIgiCIAhdj1aJ7vfeew+vvvoqdu/ejaVLl6J379547rnn0LdvX5x44oltv5eCIAjtAd3Ke/d2xXfrtb3tdlf2c8ZgMl6bFin+bcAFnVa02NhYJbYzqzOc0xJu8/eXRGuC0A5UlJQgd8sWFFJsp6fDYrPB2rs3DM3Mt6BpQFFZBYq278OOjBJkhR9cs2z+Fw9jSNYePHTEXCwaOEkJ78xKV6z32JAmrN3u2Gwu8V1RAXt6usvynZCAsFGjXOK7mVZ4QRAEoYuK7ldeeQX33nsvbrjhBjzyyCNwOBxqflhYmBLeIroFQej0MKHayJFAjx5AcTFQWgoUFbn+lpQAlZVA9bOvjiDnX05ms0qq1stmQx6znGdnS3kxQdgPHE4N/+zOxcpsAyJ352LygBiYjHWHscqLipC3ZQuK1q+HPSMDlsBAWPv2hcHLPUdhnWcHUsoNMK5ajcAtW7FkwHgsjhuGlAoDEtPS8MNbd2CYLRj3XV8ruvNtweidn46w8qI622NytVbh5wdzr14u8Z2RgdzvvlPiO3TkSEQMGiTiWxAEoYvQ4t7fiy++iNdffx0nnXQSHn/88Zr5EyZMwC233AJfM2/ePDz11FNIT0/H6NGj1f5MnDixwfU//fRT3HPPPdizZw8GDhyIJ554Ascee6zP91MQhE4O47lp8eak43QCFRVAebnrLyeKcF2Qc8rPrxHkJoMBUX5+CAwPR05BAXILC2Hy85PyYoLQAn7YkIYHFm5CWkE57yq8u30F4kNtuG/2MBwzIh7lBQXI27xZWbadWVkwM8yjf39oMCC73IHkUqMS0gWZ+Zjx6WuwFhfj7LMfRZnTdRc+8fs/OG79z1hVZsXWkBFq3t6weGQERyItIh5+9kpUmF3Zxp895Fys6TEYn404smb/wsoKEWHaz5hsXXxXVirxnff99yhYu9YlvocMEfEtCILQ3UQ3XcrHjh1bbz4TBpWw8+lDPv74Y9x0003KtX3SpEnKsj5z5kxs3boVMcw47MGSJUtw9tln47HHHsPxxx+PDz74QA0WrFq1CiNGuF6sgiAIzYZWbXZ+vXWAdUHuLsrLypQg9y8uRoLJhGCnE3lZWShNSVGx32Z/f2hWKzSzGVojLuuC0J0F95Xvr6pXyiu9oFzNf2iMHwZuWY6iPSlYN3Qi0m3DkFJsxKyP38Npy77G55PPxLwpZ6rvBFYE4q4NS9Vnc1kpDH4BiLVqSBk2Cn8FmZA4oi8eGlCJBD8NPfyAsqnzEawBIWuZtZx7YEB6SBQ+HHNMzX6YHXb830d3o/L7MORcfwUi4yL274CtVph79oSpqsolvn/8EQXr1tWK72ZkWhcEQRA6Hi3u4TFue82aNSqO250ffvgBQ4cOhS955plnMHfuXMyZM0f9n+L722+/xZtvvonbb7+93vrPP/88jjnmGNx6663q/w899BB+/vlnvPTSS+q7giAI7SXIDRUVCK2ogK2wEFlJSchJToahpAQhBgNMFOjFxTAwfrx6W7oQd1KMM5u6IHRDl3JauHXBPTRzFybt24AdkT3xV18O/mt4clk21j1/p1p+/Q3TUeLnitsea7DBZq9E3/xUJPg5kWDTkOBnxc9nXg5rbCReHulEbHAFrMxxOHoygMlIVN+sG5fN5GgsC+bKXu4S3rVoGJW+HQNyklBamIXjtvnjNIMJJ8U44OH53mIYf25JTIRZF98//YTCdesQUi2+jVLnWxAEoWuLblqar776apSXl0PTNPz777/48MMPlTX5jTfe8F3Jj8pKrFy5EnfccUfNPGYEPuqoo1QyN29wPvfXHVrGFyxY0ODvMNswJ53CwkL1l8fIEkA6CQkJmDZtGvLz8/H999/X2w4t7PpgRF5eXs18u92ujqWqqgpbtmzB6tWr63wvOjpaHRPX+fzzz+ttlzHzAQEB+O2335SLvTsjR45UFnx6IyxbtqzOMmZVPu6449Tnjz76SJ07z3aJiIhQ3gF79+6ts2zQoEEYP348UlNTsXjx4noeDqeccor6/MUXX9RpOzJ9+nRVSonnbtu2bXWWsQ1JRkYGfv3113qZoM866yz1mQMr+nnQOfjgg9UA0IYNG7B+/fo6y+Li4nD44YejtLQUX331Vb02PPXUU1Viq0WLFqnayu7Qi2PIkCHYuXOnurbdCQ8PV4M4+vXgyaxZs1Rugz/++AMpzIDtBgekxowZo+ZzuTuM8+V3dW8OJy2mbvBYeEzLly/Hjh076ixjG7AtmCmbA0rumEwmnHHGGerzwoULUczYZDemTJmiBs/WrVuHjRs31lnGc8Zzx+/wu56cfvrpKjb5p59+Qk5OTp1l48aNw+DBg5UHCr1K3ImMjMTRRx+t7gOGfngye/ZslYDsl19+Udcat63HQA8fPhyjRo1S1yevU3f4HX6XfPLJJzW5JnRmzJiBqKgodV/w/nBnwIABOOigg9T9xPvKHV4nvF7I119/Xc+bh88AXscciNy8eXOdZY09I3j/8X5MS0vDpz/8gMqSElUzWIluhwNj+vdH39BQ7Nq+Hev37EFyYCB25eaC+iAyKAiHjByJSgDfrVoFzWRSkxL9PNaJExFgs2Hp+vXIdHv2kCG9e2Nw795IysjAqq1b6ywLDgjAERMmqM8L//wTTo9nxPSxYxEWHIyVW7YgOTOzzrJ+PXpg5IAByMjNxbING+oss1mtmHmwKyb2x2XLUM54eDcOHjECsRERWL9jB3axXJsbiTExGD9kCPKLirB49Wolh1JNJmx3OGA2GDD70EPVer+uWIEiuva7MW7wYPSMjcXWvXuxxeOZFhMejskjR6K0vBw/e9znZNbkybBaLPhr7VoVFuDO8H79MCAxEXvT0rCGWe7dCAsKwvRx49Tnrzzuc3L4uHEICQrCvxs3Is3jvhnYsyeG9e2r5nO5OzyfPK/k+yVLUGm317TFvogInBQd3SbPCM/nYUvwxbtz+dYkbF+yq2bZ5LTtuHfl13ht0GT8UJqv5vGp9qMtCGY/fxxpyYchEsjetASZvWx4/JyLYAkPwqn5i2rvi8I4132xdmmL7ov7UYUHv1uCQnvtfRFs1nDEtNFYM+ppvPnrGmzbtQaP7gLes2k4KbgEowf33f/7Yu9e133hdMKxeTMcP/yAnv364ZATTkBRURHeefttmE0mGIxG9d7k3+707jzhhBNUf4rvBPf3BZF3Z9d7dzbWvyYMN+3fv7/qX/O88zrX26I79a95ffI6zc3NxY8//qjm8dphe7DNzj333G71jCA85zz37m3B+yIxMbH93p1aK3j//fe1AQMGaAaDQU0JCQnaG2+8ofmSlJQUXsXakiVL6sy/9dZbtYkTJ3r9jsVi0T744IM68+bNm6fFxMQ0+Dv33Xef+p2mJm5jwYIF2gMPPOB1OZdxstls9ZbNnDlTLZs6dWq9ZcHBwWoZ29Pbdl988UW1PCwsrN6ygw46SC074YQT6i2zWq01++Rtu3fccYda1qNHj3rLBg8erJZdfPHF9ZYZjcaa7fKz53J+h8u4Dc9l/C0u42831obcd89lPEYu4zF7LmPbcBnbytt22bZczrb2XMZzwmU8R57LeC4ba0NeC1zGa8Nz2fDhw9Wyc889t94yk8lUs13eT57Lr7zySrWsX79+9Zb16tVLLbvxxhsbbUOz2Vxv2WmnnaaWjRkzpt6yyMhItezJJ5/0ul3eV1weEBBQb9nhhx+ulvGv5zKuz2X8vrft8ve4nL/vuYz7yWXcb89lPL7Gzg3bh8vYXp7L2K5cxnb2XMbzoW+X58lzOc8nl/H8ei6TZ4Q8IzrrM6KgoKDF7+j2eHdO6jdB+37QZO3w2AGd4r44KjxK+/yLL+W+6CL3hT7Ju9M1ybtz/58R8u5Et3p3GvgPWglHOjia5y2euq3hKBBHvzhSNHkyXcFc3HbbbWp06J9//qn3HY62vPPOOzWjYuTll1/GAw88oKyrzR2t79mzp3JHb0tL9wUXXKBGe7q7pZvXD7ctlu5ZaiSNlguxdLtG67ltXs/dYbSev83nBNvbYrGo/enVq5e6DnluMjMz1XOW3j28T3nu+Iz46Ycfaqzj6q/TiRkHHYRAAMv+/RfZPDdsC7q3O50Y0qMHhiQmYl9eHlayHJrB4LKUG40IDgrqNJbuHmLprmmLvrR0X3hhm1m6r7jiChQUFKh3RkvwxbuTlu6XF9dauv16DIElPB6VOUmoTK89zrPCizEqyIjJffqoZ8uijRthtNlcJcI4GY3t5gFSaAeCfvoTR+xYjVV9x+Hji+7HnLAMpO9c36b3xeiBA7G8shKpixfDoGnqnc6J/i7HjB+v0rMvXrcOxcwvQarfK6P79kXP6GhsT03F9rQ05SyvJoMBMWFhOGTYMHV9/bRmjZpnrJ74rDhp0iS134vXr0d2UZHL0Z7hMUYjxg0ciCGDBmFnQQH+3bPHVVqRNcetVoRHRPjc0s1+Hd87YunuXu/O5li69bboTv3rxizdvBbE0m1Xx3fttde2maW7Oe/OFovusrIydUHxwiS8gL788ksMGzZMPRB8BRuKv/nZZ5+pZGg6F154oboxvZ18dlrpXs7yZjr33Xefci9fu3Zts36XF2NoaGirOiHe4Mvhu+++UxnU2bnuzkhb1CJtUZfu2B7s7PDhzpcvn7N83vDYOX/79u2q+gIf9C3CboehshKGqqravxUVMJaVwVhaqv4PzuN61Z1yjUKc8eTVE0WL+lvtvr5f6K8bz7/uyz3mUVDoy9gdXB8YiBFlZa62aIt96qSwLTaYzZjUsyfiqoX+/tKW77u22BZjug954leVNM1bR4WiLy7Uht9uPARVBfmoyM9HeW4uSjMz4cjOhrO4GEZe906n6nSbAgJgDAiARkHow+eK5tSw6/u/cH/oQUjyC4PJoOH8iFKc08MBq83apud/hN2OljwVVDtqmhrcVQMIXj7rAt59AJgCnPOUC3u1CFeC3GhUnezQoCAEGo2wcYBPH0BgO7OvGBHBurKuUoycOL8N6Y7vi4aQtqhF2qIu0h6+a4vmvu9aHNPNkSCOvFDRU+xyVIkPXHYWmejsyiuvhC/gb3A0iKN4uujmC4H/v+aaa7x+hxZxLncX3RytcLeUC4IgdAQoImNjY9UDm8Kb1m3O0wc4W4Uunhta7i7G3UV5aalLmFOUl5e7rOiNjc+yI86OOj9zPXbK3dfn/z0/V//VGpjvdV3+DQyEqbAQ5moLfs1v8/eYgI5ivNp6r/5Wi3N9fp3tCx0a1uFmWTBmKedZc78C9bPI5TabH2y2WATHxqp5vBY4UM9SYuV5eSjLyUFZdjYqcnPp/6eEuFnTXELczw8GVhHw83NVEGiDgRyD0YD+xx2K56qA5/c68EeeCT0/+QB+e1Yi6YqrkThm4H7/Rqv3Tf1jUM+WFg7h1aB5iHPm+KGXFjuvLIcYGhKCAH9/UFobaGmn5ZvPEN5/fJ4xMWRkJM2sronzuvEAmiAI3YMWi266vDz77LPqM63OdDWgizTN9vfee6/PRDeh1ZqWbdYEp9hnyTC6rOjZzOmyTbcUJnUj119/vXK/ePrpp5XrB90+VqxYgddee81n+ygIgrA/0BW3X79+ypWK7lK6+xwt3rQqKStTW0ErNidvyyhiKcJ1Qc5JF9LeBLOnaG7gr/pOK9d1UGQnJ6N87FiYaFGj8KaVnu71/FxVBWN12TY1YGC3u/7P7+nr6IMC1QMDnqLcU6wroSAcMFiH+5XzxrnV6XYR51an2xPeI3TN9IuJQWh1+BtFIsVheXGxyxpOIZ6XB2duLs0UMOXlwUKLuMkEMwW4PjFLeCuvgUgL8OCAKvydWowZW/5ETHEu7t1agahwMy5JtCOgk15abF93rxvdUlRlt6OkuBiFBQUuAR4QoKw/AZGR6nwo4U0RzjZPS2tXa7ggCEKnE9304w+uLl/DuBFavdkRpN+7Z6xCW3PmmWcqv3mKe8Zb0IefMR20DpF9+/apfdFhPANrc99999248847lXsmXculRrcgCB29U8sYPj5rk5OTVVwWLUn6Mj0qSMVcGo1qYifY2+f92AkVj6nqiLMT3AHQquMNnYGBMDRHCLmJ8RphXi3S1V/d/Z5TRYUaYDByGd1juX61WK+x3FeLdRUHz3JutNKJKPc5FNYzhsVh6Y5M/PTnPzj60EmYPCBGWcKbC+8FikDlOVItxBnXp4R4aamyiBdnZqKssBDO/HwY6U3BHAsOByy0CjPEolqEOynEW+CSOLWHH7Keexo//LgCi/tNADKBv/ONuD2mAGPivZQY7KRYzGZYgoLUYJm9qgpFxcXK3ZKeioytDA4JQVBgoFpHwXuKg2JlZWINFwShy9Ni0c3ECRSuJ598sgrOv/HGG9V8ukK2RcxzU9CVvCF38t9//91r0gpOgiAInQ12Vpnkg8lMmDeDIptCgVZvToxL0ksQctLnMeEKP9O65ynSGxLn+y3SOyK6xZoDB81Zn+3kLsr1BHUe1nQKdFNxMcxMFGM0whESwvSrvj+ebgwF9qS+EcjZrKm/LRHcDUH3ciaS4qSE+ODBLrd0CvGyMpTm5aEkKwulFOJFRTBSQBYWwmK3w+rnB2d0dLPDFQLDgjHtzMPxZEElnt5jQWFxBca/cAuSBo1A6JUXIjBkP8JIOhhsEVq6OfG+q6qsVOKbXjtsN7Z3SHCwckW38L7hFB7u+rJuDaeHjzdreGioS4SLNVwQhK4uumllPuecc5TYPvLII2vio2n1ZmY6QRAEoe3Q3clpKWos4YceZ0mx7S7M3T/rAp1/9fn8v0qkVD25u697WtL1ZXosp/7ZfR9a8tf9s+fggJ60SV+Hn/XETqrzbrUql1W2SZsNFvD3ql3u1e82ti4TWOXnw5SRAXNODox5eXAEBrqs311t8KIbweuKkzIixMaypo8axKIQZ4LDYsaIp6WhdPNmhKWkwBkf3yJvh4mhTrw1ogL/frscPQsygG3A2VtsuHygEYeG161c0RUwuLUp76fKigrk5+UhLzdXzaM3Dyd6IKhs25x063ZT1nCuExXlEu36uoIgCF1FdJ922mk45JBDkJaWhtGjR9fMpwCn9VsQBEFof3QrNid2ZpuCQtabMNf/z8ndks7/e7q165/dJ32+Hn/enPm6uK7JjNzAZ+4Dk3bS+s+SPBRCzOvB/WKHXe/ctzjLe2swm+GIilKTvagIppwcmNPSYMnIUO7HtH77MkO20D7wurPZbGpingXEx6Oif3/si4hA3ooVCElOhjEuzpURvZkwlvuwEybir4SH8VGaEcmGANyzAzgs3IEbogsQFtp1rN7u8G5WsfZ009c0NZjBslmcOC8kNFRZwZmEreYe5jOgIWt4fj7A0k7VSRSxfDlrdrliw3n/SeiHIAgesI9Dz5tOIboJk6dxcoeJzQRBEITOIyYoVDmpJEdNoGcr9iaK2wuKf8LapNxvDgjQ+siJJTsowPmXL1V98IHH5l671xc4g4PVZO/RQyXkMqWlqb90R1fLaJWTrOldBl5T/UaNQkpwMHKXLUNQaiqs0dEuL4cWkDh+CK51AiEpdnyUboJhxSr0+fYZrDrrYvQ99tAufcm4D2aoDOgVFcjKzFQT5zEBG717aAGv58niaQ1n2Add0VlvODPTNdjFmHBdgHOSATBB6LZomqZyklFsc+Bez5HTwqrZ+02zeiJ6cfbmwALugiAIQteio8V712So9vNTFsj4+HglynURTks4X6wU4pyv1xPmRJd0XwwYMMmWPTYW9uhoFf9rzs6Gme7naWnQ/P1d1m+xvnUJOKjTs39/+AcHI33ZMlTt2IHAigo4mfyrBfgZgct62nFYhAPBX36HsLIi7NiwD/MHWnBz7yrEdIOwZd6L/jabmji4Rws4k+XynnUX4Kzs4PU5pN/LdDXnciZCLC4GNm50/Z/x30y4y+UU4JJ/QRC6BZWVlWognt40/Mv/62FpB4JmiW4+8ARBEAShI6Mnb2I8Lqta0OKtx+JSfHOUW68prFv62zwunBiNcIaHozI8HFWJiTDl5sKSlqZEOFGJ1/y7Ttbq7gqvoejYWPgdfjhSQkJQsG4dQlJToVHgtXBwZVCgBvv9N+PHz3/Gi32OQVGBCRdtMOLqmGLM6mGC0dSxBr18Be9DimtOvH8pwFNTU1X2eIry0LAwlQGdYrzBgTOG1zDpGie6olOA79oF7NjhEuAU30yCp5co68ouBYLQzXA6neodn5+fryq/8P3PQVJ6zegJvzko32FF91tvveX7PREEQRCENoQvWlrIOEVFRbncWKtFuO5q5uu4cIpre0KCsoDXSbyWny+J17oI7MhZJ09GckgI8pcvR2hKior9bqlLs9lqxuCzZ+GlMgOe3O3ExhIjes1/GaXluSi/5kpE9XGF9Tk0YE2REWudBtiNRowJdsLUBXWj3lHmxHwOFOApycnqPq2pAR4YCFNj7UxXdN3FnIkYS0sBnh8mZePAF+czXFKPA5d7URA6HZqmqfc63+m0alNUcx4H58LDw2sH1SsrYSoogF9ysuv+74ju5YIgCILQJdxYq61oERERSEhIqBcXTjHuk7hw98RrxcUw0fU8Pd2VeI01v2n9bkYCPKFjws5d3zFjVJx33pIlCEpKgpkJ1hjP30J6+2t4YWglft2cgyN2Lv//9s4DPKoqfePvlMxMeiMVCL13FBBQFBsiitiw97Y2LLv+7V3W7uoK9l117e4qll27UkSKIiBSpBMCIb23qff/vGdyJ5MhgSSkzny/57mZzJ07d+6ce++c856vwepy4Oz1TkywmpBi1fDC7jDkO3WVbUJSmIYbM5yYkhB82c919PwThAKc9ymtWcpbhdZqs1ndw0abrfEJMw68/WPBmRFdL03Ge4+im5Mlukhv41wQgiAcGgwd093HKbh193FWRPD12R6Pqi7CPCsM9zJykp33/oABnV909+nT54CxcDvowiMIgiAInZyOigundZuLkwnhJPFacMV5DxgAW3Q08pYtQ9jOnbAlJEBrQYgeLdcnDE3E5if/hmU/bsKalAFYs4evaAh31ACWuvCEfCdw3/YwPITgFt6B9dWJkwKcrqJxcdi5cyestVZwLpwIsdpsCGtMPNPSpYd5sCwZ97N+fZ04pwWcMfoU4FITXBA6jft4RUWFch+n2FaTbUZjPfdximkjJ7fpXcb8EGVlMLAsamSkyrniYuWDDqDZovvmm2+u95wDkTVr1uCrr77Cbbfd1prHJgiCIAidMi6cs+sU33Rdb7Erup54LTnZm3gtPx/mvDxlAddsNriZgVmsbV0KTsQkp6XBdvzx2Pvzz6hYvx5RVVXQKOBaMJGS0CMJM85NgiHfiacyzehWUYIv3rgR746ajnmTZsNpoms196thXlYYJsfbg9LVvDEoqI21ApweLB6nE6VlZSqWk/elOSxMie9IXYRbreq+3W/CjKKaC0W2Hge+dat3aSgOXBCEdqXaz32ck+EU34Hu44aaGuU+bsrL805k2+3evpTlBjtBBYNm9+Y33XRTg+vnz5+PVatWtcYxCYIgCEKnjgtnp5+Xl6dm27kNLW8tdkE3GOCJi4MjLq5+4rXCQvUaxbckXutasOa05aijkBUdjdJVqxCdlQUDS1i14BqhPky3adBgwGkbFyKpsgTHbf8Zz086x7fNVSsXICc6Ed8njMbU7laEhWBosgoHMZmg5ybnvUrDUGVFBcpq6/JyQo2im/erbgm3Wiz1EykGxoFXVgJZWcDOnQC9UDiAZ7I8vs6JMYkDF4Q2weVyqQluTqKxr2VeB96/9dzHnU5vqU6GbBUUwFhVBY/ZrLzGNCZT7ES02hT69OnTceedd0rSNUEQBCEk4sITExPVQCA/P189cpBPcd6UuucHTbyWmupzjfMlXouI8CZek7JjXQKKur7jxmFvbCxKli1DxO7dCEtPV5aX5lLkLVGP18adjuyYZOyKT4fL5B3C0d38zkWvwwgNY3u/g8dzrehh1XBa5i8Yk7MV1aNGIXL4QHS3aTAbQute1cNBCKM3XU6nivvkhJmePJFCXC9JplvDfd4rFNQU1lwY/8lYUFYhYDI27pehA3ocOP8XzxRBOCQ0TavnPs78DXpVA06WKS8VxmnToq3HabPuNievGbbVQq+i9qDVfh3+85//qMQ0giAIghAKcGBO4c2+j7PxFN/FxcVqwKDHlLa4HrjJBHdiolpU4rXCQlXvm+7nWm3iNRngd5E478GDYYuJQd7SpXBnZsKWnAyNIq4ZJOiekQYDvhh8ZL3XbC473h81DanlBaiKioHbY0BmjQFpq1di6rpv8PdSDc9gBMIMGvqaHXjwf39HdfceyJkxExnRZqRZNRibeZkyg/q6cqOaDOCxjewCGdQNfuEjugh3u1wqLpyDe7qr8nzxdT0unJZwm17Xl/cyLd16cryaGq8b+u+/eyfCeE45DqZXCgU536M/6gvv2U4qCAShI6mpqannPs7Qrv3cxysr1WS0EtqlpTC6XGoymnHaXWEyutk99pgxY+oNIjgjkZOTowYbL7zwQmsfnyAIgiB0atgnsnwR48AZ981BQ0FBgXrUreKHUgfcl3gtLc07s8/EMEwE04LM2EIHxXl37w7btGnYu3w5KjduRGRNDTTGCTdRgFHUMks5k6Z55WMdxRGxuOuk65FsAf47wo4iF7Cr2ghb7nAss7iwb8BQ2IwaajwGaNn7cMSaxSjbEIGRQ89Vn8/Xbvn1Y4ws3IWdk4+FaeQw9A73qP01dHhLiox4vl4GdXTJDOoGv6zorAFOONB31saFcwKN5y5MjwuvrQ/uiwvne3SvBcaB09q2e7f3f38otHXBzYXvoTBnbLi/INcXCnWZUBNCxH28vLy8nvs470fea/rkmMHhUNnH6TrO0CtDdbXyFvLExsLdxSp+NPuunjVrVr3nHEgkJSXhmGOOweDBg1vz2ARBEAShy8ABOt3fuCQnJ6uBBCek+XjISdeIxQI3k7vRUspSR7R6i/DuMsTExcEydSr2xMaibNUqRO3dCwNdk5twTdCKTFHLLOVeG62/GvaWvbmhpxNmI5RYTrZ4gFMmqeUaxnxrduQ6DMjJtuKHUy9EebUb/SM1ZFZDifERf/yKibvX4aOUUfhPuHcgO6hsH579/Cnk9uqPX867En3CNeTagScz909IFCwZ1Hl/mhqIC9dLCfrHhUdGRSmx7osLZ6x3IHRJd7u9QpyL0+l1Uc/P967n6/rMhi7K9YX3tp5h3V+QB1rOBaELoWmampz2dx8n9CxhH6kMuyzZWVQEI/Ob5OfDwLrbjNOOioLW0H3WRWj23Xr//fe3zZEIgiAIQpBA6zbrgHNSmhYzxpDSdY4T1YeUdI0wdo3xoxTdeokUoUtAS2nv8eORHRODUsZ5Z2bC3KNHk2q0U8xS1HqtzHXrKbIpuA8kduk+TjfytD7xQB+v8eQ1OODSgH12A6qqZ2LhtmEwDx2krNxZNQb0ytmFIXs2w+10YX5WndB+9vMnkVZWgKemXIRfeg6vXRucGdQbjAt3uVRceFVennJJ572sT6rxvtdd2LlOebjoIvpAUHzrwlwX50ykqD+vO6D6wpzCWxfmFOm6Rw3d3vkbIUnehE4ktCsqKtQkNB85mcXfQ3qJqclolvkqL69zH6+d5GIJTU42B8O13KJen+43CxYswKZNm9TzoUOH4rTTTju0QYQgCIIgBBkceLP0GDOfc2ZfF98chFB864N5IXTgWKnnsGGwxcYi/8cfYd69G1ZavJtQiorCmqJ2bbkRv3lMGGV0Y/QhxFMzsVpPmwZMGa2WPwH4ExxweoC87n2wMPFW5LrNOCrOjT8qDch3GjEuayO6l+dD8/M971eQhelbfsJXAydhXe9UjIntutbug8aFM/la7XjXPy6cYoIinEJdlSszm5Wo4GKhS3qtEOf6/XI98LluvW6OOGd9cWZX5/+0nOv7WrbMG2OenFyXZZ2iXOLJhXaCWpFCm+7jnHiuqqpSQlvPmeBzH6+u9iYNzc1Vj0anE24mFGX5viDTlc3+Nhs2bMCpp56K3NxcDBo0SK17/PHH1Wz+559/juHD9VlPQRAEQRD8k64xKQzdVBnzzYEIBySHnHRN6Jpx3j17wnrSSdj300+o3rQJEfHxTSpxQ4E9OoYWViOGuzxoi/RBLDnWPS0OSJuEPgCOgBPfFxrx8A4LrjrzXgwsyMSmJL7iZeamJbhp2XsYkbMNd6TehRO7eZRQHxrpgbG5Wdq6EP5x4Xp8t24Npxjn/c3JNkKrt76trTZTui7EKUCaZLg6mDhnibPsbIAeMEz0tnmzV6jz2LiOCadoAacIlzKEQivD655WbH+hTfHNPAgRfkIbDgdM+fneMl+Fhd44bYtFlflyH0L1j6AT3VdeeaUS1r/++qsaPBA27KWXXoqrr74ayzi7JgiCIAjCfnDgHRcXp1zqaAXQE67pSdc4MBHxHTrEJiTAesIJKs67fPVqlWDNwJI3ndCVUs+gvjGlr1r8WZ/aD9/3G4f/DT4KxS4jPsgx4n+ZDnzz+g3YMWQMci69HKMSTCFRPzzQGq5DKzgFCIVJSXGxek50q7huAaRACaMQr3Vbb1ESRopsWrY5iUPRTQHORG95ed7X+RpFOC3hfKQID2KxI7QdtF5TZHMymXqQWcjpycXrWNXTNplUMjRDZSWM/H2rqIA5Px9GemgYDHCznjYngkKg32u26F67di1WrVrlE9yE/8+dOxfjxo1r7eMTBEEQhKBOukb3c4puJl3jIwcrjA89lIznQheL8540Cfvi4nz1vE3dux/c1bidOVAG9W8HHIFvB0xAtzDgvp4O/FRiQtzyVUgvzUP1lg24cGckIndrOCLWg5mV2zGwXxLCI0PL0sr7mYvP2ldrFffUCnGKFU7EUbC0yEW9MbidHvdNKPaZzI3JGHNyvK8ztIFu6LSE63XJO9n1J3QemGWcQpuhUlx47fJ6ZELBOE4YOZ0wlJXBmJ2tYrOV2HY4vNcec5J0oTJfHSq6Bw4cqFzLhw0bVm8949T69+/fmscmCIIgCEEPLdw9evRQGc9pKWAfy0cOug856ZrQJeA57jFiBCzR0ShYuhRhmZmwUHh3IhfgpmRQn1NbNuzYRA+cPcZgcZ97saXYiXizhmKXQbmoP/Dy40iuKMLcKx9G6uhBmBTnRlyI6juDX8Z0TrbpUHi7asV4Yy7q/N2wBrioN8lDgttQZOs5BBgLThGemwtkZdVlTmdMLRddhIeYQBJQ73qksNavRT7aq6pgdjrB+hkxrHHPGtrl5TBQYDPXAD0sjEZ4rFa1aHINNV90P/roo5gzZw4eeOABHHHEEWrdihUr8NBDD6nYbr2kAmHNUkEQBEEQmp50jbHfetI1vU+l5VuSrgU3tBSl9OkDW0wMcpYsQdXmzYigNYgWyE5CczKoh1nD0GvyKPQCcKxmx8YKA9ZmlcNgNMBjMOLDyP6o2RUGI8y4NPtnHFm1F3FHj0dCejeEOqo++EFc1IsbcFE38TfCYlFeM2F0663dl77Qytjouuho77paEW7Yvh1GxoSzJjkFenIyDPHxMMTEeLfl/kPAJTiUhTZjspXQLihAZX4+3OXlsLhciHI40M1uh5Fu43a7un48ZrM3Ljs83OsuLp5ahy66TznlFPU4e/Zs383GE0OYYE1/ztf4wyAIgiAIQtPh4JnZzhMSEpTo5gBaT7pG8e1vEROCj9jERFimTUM24/7XrEEELUcsmdNJBI6eQX1duRFFTm+s98iDZFDnayOiNYwYGgXny89j9Z5CnGcy4ccSD7ZVGTFl6Rc4ZueveCLfhW+POwtHxbtxZKxb1QanSG8Mt4baTO4GuIzGQ8rkHhQu6rRYWyzKW8ZYOzZvCj4B7n3iE+bqKS2aOTkwrl8Pg6b5hJU7MVElvlJWcNZXNhqV+Nf35bPGW61q0d3ihc4LJ3Eqi4tRwQnf3FzUsGxdcTEsdjuY4tFcq+9YM1ujBTsy0ls3u5P8NnV2mn31L1y4sG2ORBAEQRCEBpOuMSMsk67pNU5FeAc34RER6DVliorzZj3v8MxMmHr27DTumRS2Y2JaVhaMIrp7RjdcAjcu6e5WdcIrdh6G3zW7ig3fWmVUy+8rNuOZr57DhiOOhevsMzA0SlP1xnWWFBlrLe76SpOKOacL/IFqlgezi7q59neBnqZNvVKUNK8V6DSaaf7/6xuFh8Oje1zQsllVhbCdO5UI91gscLHEU0IC7KypHBEBj82mBJxuidcTxfF3iyEzjFHXhTgfJX9FB2G3K+s1rdhV+fkoz8yEk6EMNTXgtE4cz43NBi0qSk22uMXbqn1F99FHH31onygIgiAIQpOhZYFZYLmkpqaqZGu0ZAkhEOc9ZgysrOe9ZAnMO3bAmpERdFmm06waMPtEtTzpBH4qceLHYiNO+GEFehbtw8+Z2fjzH1YkhGmYHOfGaUWbsKd7Xzywe/92oMs7Y87pAh9KwvtQUFMWulW7KRZLCi9at4mmwWy3w0Z39H37vKtsNrijouChBdRkgsdggIsx6h4P7LSkUozzcxifbrWqJSIqCuEU4xERsPgJcnFfbyX0DPZk7144y8pQnZ2NqoICVBUWwllTA94t5ogIdR4MDGsJC/PWoe/oYw8iWuTnwWD6devWqXgzfRZLZ+bMma11bIIgCIIgNJB0jVVD9uzZo4S4EOT1vPv1g5Vx3osXo3rrVoSnpdWJniCDCdVmJLnVUnP9mVi4rD82WVIQadJQ5DRg+a5yPDfvLpRbI/D0tf9AuTUqYA8UaRrmZYUpF/hgdjXvFNDVmCK7tkY5xR0TaZnKymAuKPBuolvTKaBrs1erBFsUdB6PV5BrGko8Hmh0n2dsOi2sVits0dFqsbDGc3g4LOHhCOOkEz0+aB1v6FH/P0CfhJzArqryLmVlcBUUoKY2GV/uV1/BXl0NO8OAWR8+Ph7W8HDxNuiMovurr77CxRdfrNzcApE4bkEQBEFoe/SkanTTFIKf2KQkWKZPx77aOG/GWIL1vIMYW1Q4+px4BPowj5DHjjXlRuz7dTcKI+OQHd2tnuA+f+2XqAqz4bv+E1BhjUCeAyrmvKUu8MIhiHDGex8o6z5FIQWxx6Pizi0eDywU67XrGJ/ucTjgrqxEVW4uKlwu5cZuZJw4Xejpkl7rlq67rYfZbDAxXpzCUV90K/kvv3iTETIZHI+Lv5lcgsFV2k9ge8rL4SwqgjM/H67SUniqqmCvqYHd6YTTZIKdeQCSk1HIEnQxMQgXT4LOL7pvvPFGnH322bjvvvtUllVBEARBEAShbQmPjETG1KnIjolB6cqVap1WUeEVE0E+eLYYgQmxHuDYQfhk+Kt4ZUOV7zWTx41bf3wb3apKcdHsh/Bjn7Fq/T47MKYDj1loBF6rtRZp/1Rv/v8baxf/SnI06nGxu1wodbmgUaQ7HDC73TA5HLAycRtLqJlMSohTpCtYAYKGQt3KTnFOazkFOLNsR0V5RbguyCnGO+P9xBj76mo4S0tV3LWzuBju/Hzv8/JyOOx25T3gMpngCgtTsfaMxzZFRqp4f2azJ1HR0U2O9xc6WHQzjuzWW28Vwe2HqqfocjXJyu90OtXMHF30Q90rQNqijlBtC73Micy2CoIgHBz+XvYcPx7mmBjs2LIF1aWlMGdnq1JRprg4GFnOKcjdRLvZjMiPYi5lL1aXA++MPhmTM9diecZI3/p9C75FwZ7VyDtxOnpPHI4IURpdGj1ZnH/pRBVzXDv+rnI6UV5T46ugZKC4jolBJhNPsrY5Xanpvu52w1hZCXNpKYxZWUqA0rXawHuIbta6GGfZY90qri/tNFZxOZ1wlJX5BLaruBiO3Fz1nBZs5Q1Qm8SO7v0s6cb7n9Z+WyOl3EJnZBlEovuss87CokWL0K9fv7Y5oi6Gw+HAvn37VC27psAfAybCycrKCnmhIW1RRyi3RUREBNLS0qQGsSAIQhNgH5HUvz+wZQvSzzxTDcYrd+6EKycHnrw8b/3kuDglzE1+paWCBZYnY5Zyb51wA6os4fjbUReoxYumhNSs9QtxWPYfuD99NG62HYYj4jyYGmPHEZEOhEdKWEYwYKidiOLiX9GBYyp7rQGjuqoK1bQS18Z469nZoYttg8H7WF2t4tDNHo9aeOdQxPIeMthsMEZEqBrlRorbyEgYKXRrF95zzYUTBTS40EKtC2xHcTHshYXQCgqgVVUpy7Yq08aJNF1cx8Z6LflBPrkWjDRbdM+bN0+5l//4448YMWJEvVqBZM6cOQgVmERu586dauYtPT29SZkW+R6We2HJhFC/YaQtQrst2PFx0oo1iHkfDRgwIGS+uyAIQmsQk5yMsO7doY0ZoxIlVWVno3r3btTs3g3X7t2wU2BER8PMgbrVGhSTukyOxrJgzFLutXX6fyevoLqvnxPO667CosUrsHb4EXBoBiwpNsG4agPO/eRR/HT4cdhz+VXKZT1cLOBBB6/zsNqa4BEUqgcYh6jSZrWi3G02q6Ru/us0h0NZxg2sVe50ei3ltKRTaPOeohiOjoYxPh6mqCiYo6LUI0W68kAxmdTYxl9g1xQVKYGtlZXBUFICY00NDHa72q9KJEeBHxcHQ2pqiwS9ECSi+7333sM333yjkrfQ4u3/A87/Q0l0UzDwxuzZs6ey1jUFbs/3sf1CXWBIW9QRqm3BTMycuMvMzPR9f0EQBKF5cPwVHh+vFgwbBjetexTgWVmo3rULjpwc1NANNzxcuaFSgNM62FVhOTCWBfPW6a5bn2wBbuhZWy4soRcwuBee1YBtVXYsKjZh2OLfEO5yYI/DhAe2W2Azajgi1oPz9/2KXocNgjUiuMqxCQe/b5TbejNrmitRTks6S20xqWFODty7d8PB9dzEbFau36xX7qIlnC7rlZUIq6hQAjvM7UY4BTYt1nytWzdVB1vFugtBS7N/ce+++248+OCDuOOOO0JKHBwIaQdBaDly/wiCILQutJRF9e+vFiabsufkoHrPHtgzM1VGaFrdymvrLbMuclesiUxhzbJga8uN+M1jwiijG6OjPfuVCePXGhCpYUCkC9qtF2D5pskosEchzezBPrsRO3bk4cRXHkKZNRK33fNPTE4Jw4Q4D6zSNQmN1DTX48sbzIDu8cDgdMLgcKhHsFRXYaGyWHusVmhRUfUEtn8COSG4abbopjXqnHPOkYGyIAiCIAhCZ4fllTIy1ILDD4enqAg1e/fCvmsXqvPzUU23dLrVhofDbLXCUmsF7woSnAJ7dIwHZrMRw12eg1osDUYD0ob1wVkAztQc2FxlQNbKHGTHJWNbXHd8XRGJryugLOD3bPwcPbrHI33SKFhsknNEaCJGIzSKa78Yc0Fokei+5JJL8MEHH+Cuu+6SFhQEQRAEQegqsIxQaioiuIwciXiWHsrNhX3nTtTk56OqtBRVRiMqw8JUPCozPrMmcjAaWmgBHxypYfCxQ2A/Zj6ceZU4x+nCoiITSiodmPXlW4hyVOOciqcQPWwAjklwY1xswxZwt+atC17kBBLCvMneAi3ugiCENuaWZNt74okn8PXXX2PkyJH7JVJ75pln0BYUFRWpGuGff/65+vE/88wz8dxzz6nEU41xzDHHYPHixfXWXXPNNXjppZfQmXB7NPy8swh55TVIjrZhfJ8EmIzyay00n0svvRQlJSX45JNP2uwzeF+NHj0azz77bJt9hiAIgtDGcPyWlIQwLoMGIaqkRGVNtjMBW14eaqqqUFZdrQS4x2j0lWsKoys6ggtawPulRuFauPCnHi5sy63A6oknIGbHNqxMHQQUGfBdkQnXrlqAKcXbUTZtGvqMGaDqhy8pMtbGlte1CrOrM9mbii0XBKHToCbIqi3YUGBAws5iTBqU2m6aq9mi+/fff8eYMWPU/+vXr6/3WlvGA11wwQWqNNe3336rYpEuu+wyXH311Xj33XcP+L6rrroKDz30kO95UxOetRdfrd+HBz/fiH2lNb51abE23H/qUJw0PK1dhBmfv/nmm+p/upT16NFDZahnu/kntmro/E6ePBlLly5tc3HGDJOvvfYa/vnPf2LDhg0qiUWvXr1w/PHHq8mY/oxbA/DAAw+onAOEA4S4uDgMHToUZ5xxBq699tp6JSX8J2W4vm/fvrjhhhtw3XXXHfLxCoIgCEJXE+CGpCTYBgyAraQEsYWF6LZ3L2ry8uCorkYZayHb7aiurlZvoQDnomJbgwgVA54aBdx4MTwaML/SoazfXGb99i0GFezGrWlj8LVhOAaEe7ChlKWpnICpzgWdyd2YXZ3J3kR4C0LnoG6CzKtt/rV1dZtrrkMS3QsXLkR7s2nTJnz11Vf45ZdfcPjhh6t1zz//PE4++WQ89dRTqlxXY1Bks/5xU7Hb7WrRKSsrU48U+lz84XNfuYHa+n8HQ68PyMcv1mXj+nfX7JdEIae0Bte+vRrzzx+Dk4Y3/dibCj9bP279+bRp05Sg5Xf69ddf1aQGeeyxx+q99x//+AdOOukk33N2uAf67v6f09BrB9tGf52TLp9++inuvPNOPP300+qcZ2dnq4mDhx9+GK+//rpv22HDhqkM+9xnYWGhEtZz587FW2+9hR9++AHR0dG+fV955ZVKpLPOOl+//vrrERsbi/POOw/tSVPboin7OdR9NPVzWuszuB/uj9eePnjT77XAey4UkbaoQ9qibdviUPbVnL7zUI9Pzn87tEVsrHfJyIClrAyW4mJE5eTAUVgIR2WlckEvB1BZXQ23x6M8EJUVnDWN2zkhmzvgsVWhC3qUhsFRLlzdw4mcq69B7o/LsXrIeFS6DVhbYcKpm5di7jcv4I2xp+CZKRfVvREans8KwxHx9nZzNW/TtuhiSFvUJ9Tb48ciIx5QZQYb1lzPnzsK04altGjfTf0d7hL1IpYvX64slrrgJrRw8kd+5cqVOP300xt97zvvvIO3335bCe9TTz0V99577wGt3Y8++qjPUuoPRVzg+2gV5n5ZX5kJ5igcapxNEyIV+cV44LMNDWYt1Nc98PkGjEy2NMntwRZmbHJHx4vD5XLVGxRR7Ojf79hjj8XRRx+tQggCY/dpEQ5sB30//tBaTLHL5e9//7ta99tvvyEjIwM//fQT7rvvPuUpER8fj3PPPRf33HNPo+VLPvroI5VHgOeSEy06uhWb7a4fAwd9bAf9GBl+cPHFF+OII47AUUcdpQQ6P4uwDfiZ3JbLLbfcoj7j448/xowZMw7ajpzwefnll1FTU6OuwYSEBHz//feqhj1ZvXq1+rx169apNmZd+7/+9a8YNWqUbx/8/tzPl19+qdolJSVFXX+nnXZao5/LyYfHH39c1bZmyS2GefC4IyMjfeeWkwzz589X1yWt/Lyu9VAQejmw+gAnsvj6pEmT1P769evn+4wVK1bgkUceUd+BA6nDDjtMTbiwzbl/vk9vc14n9Cjh95g9ezaaC/dFy8mSJUvUvv2hZ4vgRdqiDmmLtmkLTj62lOb0nYeKnP8ObAv20xTjnZBN7VECbfwwtdykAUtz3PholwlH7VqDGHsljH4jOqPHjec/ewIbUvrh1cRTMK6nBVZTkLVFF0Haoj6h2B4eDXg2S78B62ulWpMX7vl4LZy7WIO97frOJrc8B+5NgYKltcnJyUFycnK9dRRLFDl8rTHOP/985YJMqyiFz+23347Nmzcf8BhpSb311lt9zyksWIf7xBNPRExMTL1tKbaysrKUsKMbdpXDhTGPt14HmFfuwJHPrmzStusfOAERlqadToovtp/+fQKfUwzTq4BtF/idKfIC1zUEBd+uXbuU1VkfiCUlJanzRWHGhHz/+te/sHbtWtx8883Kunz//fc3KjIHDRqkxPnB4KQAJxACj5ETNrTQf/HFFyonAeF3pqD035bClSL+YN+RIpcW93nz5ikXe04KMJ9Bnz59fO+lBZceA/xs7pOvM/M/r0F/azsHqxTj9CpYsGABrrjiCvWeIUOG7Pe5DLGgdZ4iedasWSgvL1fu/dwfr0OeSz7nNUur/rZt25TVfty4cUoYE05CcD3blcdKAc625Xnn+3lOuG8eOz1K2E6LFi1SA2du799uDO/gBAsntk455RS0BN5HvK6mTJniC2fg5AEHkyeccMJ+eSNCDWmLOqQt2rYtGppAbSrN6Ttbipz/TtQWrFHM66W4GMjOVmWRnEYjajgWcjq9xgi7vV2s4O5aITHE5WpyveXWoEAllzPh9ulz8O8Rx2NfTJLvtYEFuzFj80+YsnM1Rk04Ex/tM6JvhIbZu1agHyoRNXY4ElPjlSt7MLRFZ0Taoj6h2h5uDVi2ejeuWLQSG1L64qtBkxvYyoASB5A09AhM6JPQZn1nk0U3RVFrw8E+xcPBXMtbCmO+dWhlTEtLw3HHHYft27fXs+oFijb/uF8ddhaBHRuTyrEDYYeiLx1Fcz6fx6wft/78f//7nxoY0dJIazFfo6AM3CfdvP3jtyi2KNACoQWXnSxFrL/7P5PYcSBGUU4h2r17d5/llaK7oe+wdetWJbr9X6NQZ4w3ofV1z549vu+it0cgFLEcpPi/prcDz+V7772nJmd43RysLXn8FMdcCI+d++ZAQ38vvTH8efXVV9Wx0hLuL1AZP08hzZuWlnFay7n/F154Yb/Pzc3NVeeIiQQ5KUL8Lef8Pmx7vp/niZ4AtNozLIRJBNmWTEZIqzot3ITCmefks88+U8dCizVF/4svvljv/vGHn8PX7777brU/eka0FLYX99fQPdbQulBF2qIOaYu2aYtD2U9z+s5DRc5/J2gLfiYnSWkQ6dMHyM9H2O7diMjPRwLDj1JTUWMyKS8m9ou0BNEVvS1jwbm39hQT3WqbXTMY8UvP4fVeK4yIw8PHXokIRzWiwowocxuwrcqAkd99hiOy1uP2fTfi68NOxNAoD8YayzGhcAeShvWFLbIuj05XaovOjLRF6LVHWUEplrtjsKLCgl9Kjbho2W+4ffkH+K7fuEZEt5fCKleLfk+b+p4mi249ZrY1+fOf/6ySeB0IJreiC3deXl699RQezGjenHjtCRMmqEda+RoT3YdCeJgJGx+adsBtaP0sLyvHpkInLn/z14Pu843Lxqls5k357ENh6tSpSkRVVlbib3/7m7JmUtgFwtf8xSQnMpoDJ1EmTpyoRJYex0zxx06Zwpnu502BYo9Jz+i1QCtxU+DnBc6yU9hSvNPFmQMAupgz4drBoLU6MOHa+PHjlXXZXyDTlZ1WYl6/FPYceOzevbve+9gegc9pbW4ICmxOHFEEMw6fVqSzzjpLCW0dehf4D2Z4jpgAUW9/nlv9XiCJiYlqUkOf4OJnU3wfiP/85z/qO1G804ouCIIghCgWC9C9OzsboLAQ2LsXxpwcRFRVISI2Fok9e8LpdisBXllVhYrycvU/+0SjyaRKknVELPihwrJgzFLOpGmBLqv5UfH4x7jTkGwBFoy0o9ABbKg0omLQEGzSnFjXYzBKXAYsKzEhassm/GXBXGxM7oOrrn8Ow6I8GBrpwShPCZK7RavM6k216K0tN+I3jwEuoxGjpWyZECK4NeCPSgNWlppwyryHMX7rr3jk/Mfwc+1k2NIB4zAkbye+HlB/vB0IK0i1JR3q2E93Yy4HgyKE1lAm+GJsKaG4oYD1Fw8HQxcyzRWKTUXFEh/ExZvH7LKYcNSAOJUxjwH8DcV183cyNdaGowYktUsqe1qk9QzgTKhGcccYXt2Sq8NJDn279mLAgAFK5DZ07QSGHRwIikq6fwda7ing6d7M66I1vRXoQs9EbixtR6s0rUC8linwWwrFNC3qy5YtU7GSdP/m8TO3gf7dAmfceF02J+kZ2+JgsIIB4715rdAq3tUGS4IgCEIrw/6TYzoudLdk+F9WllrCIiIQFh+vPOo8yckqrMjfCt4VM6JT0LIsGLOUeyND/ftB78juhp5OtV2ylYsH+NM5AM7Bsx5gW5UdGyqMiN1VhdzoRKxNG4itVUa1sLbM0hdvR7jbiSeveBDRAzIwlDXFIz0Ib6Bp9i9bZpKyZUJQU1ZejYIlq1CZuQ93T7wIZS7vtT8mzBu+ObVoKwaNH4wJsW4MiEzFham31U6QNa65mmLkPBQ6zh+6GdAtmPG4jEn9+eeflXWNVk7Goequy3v37sXgwYPV64Qu5HTVpVBnbDFdZxnLyrhRJp7qaCikmaKeBMoV/Tlf74h63RSeTKBGK63eEbYEdpycyQ48l0yMp1u5CQUkY5JZqqwhGJNM0c0Y5Jbyxx9/qMRhgdZ7hk1wEoFu7s0R3LQMM+7dn8DnvE7nzJmjkr/R+kzRXVBQsN++mLQs8HlD8dw6FLiMI2es/Jo1a1Q7Mxa8KXC/9BKhSNfhxADbl67ohPcHXdwPBD1F6LLOc8KSbYIgCILgg3H8AweyrihAb6ioKK8IpxXc4VA5QuhlxQlp9sGcNE5OSVGeWFXV1crQUu6XpLazQkH7UD8nkgK8S2nh5vrGBK/VCAyL0jA71Y1pZ09G9esvY8Atl+L+fg6cleLCeEMJkiuKEVdVhs9M6Xh1Txhu2WzBh698DceNt2PFBz/gmwIj9tYYsLjIqIR/oKDQy5ZRkAtCV8fj9mBrXhXe2GvCtRstuOoXN459/TnM+OHfCCstRaRJwzHxblSedw5+e/FVTL9yOq7o4cLwaE3db5yA8qJ1mObqMinsmLiKQpuutRRHFE96Vmw9qQiFg55BjkLku+++UzWi6TLNmFW+R89c3RlgTbgXLxy7X53u1HasGdcYdC++7bbbVGzwX/7ylxbto3fv3krccdKDSb6Y+I4u2TwnFGr8n94HrK3NBDyNiV5OrtCNnI9M1kO3amb5zszMVAnMAmfEKSqZsE0vGUb3bmbiZs1wfqfWgMfPSSBaeekez+NgPDjDIfwt9CxDxm0Yr83PbsiK/O9//xtjx45Vx8fJIU4c0cugIdieFMR0K6eVn8/z8/MPKNL94TExMzqPnZnXOdnBeHpOOugZ09nGdF/n+fnTn/6k7iUKbF4T3bp18+1r4MCBaj3rnXOg1Br12AVBEIQggnHfPXsCNJBw0pn5V3JzVQy4yoIeHe2LS++qVnAK68nxdqwrN6LICSSEeV3Pm+vanRQVhqnwYCqFeoYNu/71L+Rsz8YliWZsrHArq/i4rA0YuG87FuRV4sWd3rrgNmcNXv58LtamD8Kr406Hy2SuV7ZsXlaYOj5xNRc62gV8XTPvkVIXsKrUCG3RUpzx6T9Q3G8c3jj5Zu+L0d3w/fApMKUm4a/97ejX3Q6z2l9S4xNkcNZ6hKBDNFeXEd0UbEz4dCCB5z8bSpHNclWdHZ7kE4am4uedRcgrr1HxBHRv6AgLtz8UUZzkYKZvxjjT/by5UKzTxZoWVHaaLHHF88QM4hSgTCzGWOTLL7/8gJMhtOxS1HJ75hbgMXGShZZxTsIwK7g/GzZsUK7i7JhpyebnU0jyezSU6Kcl0C19x44d6jtygMCM7MxPoHtaEApnJmWjoOb1yNjzhiYwaLHm92N787iZ0E23OgfCQQlLa1HgUsjTSsAs6tOnT2/ysbMNb7rpJpXMjVYEen/wnOhu6RTTdF2ntwPj1DlRwDCOhmqX0+LPUA8Kb7Y3j0UQBEEQ6kGhnJLiTbxWWlrnes4cJxxfxMWpcmScfNfLeNISzr7ePxacVnA3sy+bzb5Y8FZPAd6Sr2cAxsS0rhu3xWZBxrDeyFB5p71eg8Upl2Dh75OgJfbFkHAPNlcaMDx3O6ZtXYEx2Zvx4oSzfO+/dclb6F2yD/8aOwMvxQ/CuFgP0swupJjdsFjDOpW4EoKb/cMf0GD4A0t75W7aiZoVq/HOgKPxg607PDBgsicBV1aV4vC9mzAl3o0JsR6Mj3UjadycFk2Qrdpbjg1RCThh0jhMGpTabprLoHVmv51OAIUNhVtpaWmDJcMoJOkWpZc6Ohi0vnKf3FdHZjvvDARbW7B0C2Pead1uKpxQoGv4zJkzg6otmkND9xEHWpwIoGt+qGcplraoQ9qibdviQP1dR+5LR85/kLUFPROZJDczU5UcU8I8IYGp8BsdM+hWcJbL5CMnjj0GA3YnJGCY0wlzJxDg7clXBUa88VsZZvzxI4yahlcn1JX3/eRft2D0vq245vS78PVAb7WSsXs34T9v/x82pg/AHdc+hVSLhlSrhsN3rUNCmAZr/95IjI+E2di24qo94DTFerMZw0OsRFZnaw9eE968B2gw78G93StgtFmxstSIlSUmPPfOfZiyaw0emXo5Xht/BvqGezAp0o6T8jcidfQgmJtYHvlAVBcWYktKCqZPmwZLE/Vba/R3XcbSLQidCbq8sfwZXd1p4aV1muEMTHImCIIgCMJBiIigmyLAfC50N9ddz5kLhpZvxoH70ZgVvKyyErvdbiXEzUYjwm025a0XCqRYgJyYbvjH+NP3e+3Zyeejf2EWfk/tjyGRblR7DOhdngcjNFSaLFhfYcT62m3P+uBtjN63BdfMugvfDpqIJAswrjQT5y/7GCUZfbH7xJOVQE+zaugWpjVoGawvrvaPLadrryR1Cy3o9cBJGC+Geq/FVlfg1Y8fVlnFD7/xHdhr79nvBk9CRIQFo4am48ORNSoJoXpvn2Ho6oTGr5IgNBMmPmPMeEMwFvqMM85QVoa5c+eqmXe6WX/00Uf71eYWBEEQBOEAcLDNqjIsAVtcrJKtITvbW34sOtob+91AHLceCx5OcZ6drcK4yktLlRs6reIMjWIMeDBzoLJli/qNw6J+h6ukbvOGeGO6taHj8fvJ/0B1mR33xzqwz25Ajt2AiqRUZDoqkR2fqtx5cx2AYWcmJq36AStzcnHdgFm+/X7w7u3oXlGIl86Yg6LBQ5WlvJejFD/8nodu0akoiAzMAC2x5aEKwwzo9ZBQVYqjd/wKt9GEz4YerV4rtUWhZ0kuoh3VmJr3B2LGDMURcR6MOGwqwoxTUZdBKHgQ0S0IDUBBzVn0hmASN3bmtGwfKnp0R3NKegmCIAhC0EHXcLqXc2EJTFq9GfdNAU7xHB/vfWwEuncmxsWp5LnMfk6XT3qlWW022KzWoCxt2ZyyZYQ1v6MTYxGdCPSG37jjvjlq6+c0oNhZo8R4ja07ftAuQHZ4PMbGuJU4z3UY0LdoL5IqS7DGFYENBV4ZccqmjXjzsyfwc4+hmH3BE77dXrjmCziMZnzffzzyEKdEWGvHvgudj/LCMvxmt+LjMq+3ysTMdfjb/57BpqTePtHN+/3mU/+CPbEpuHxMHI5LdCHYEdEtCA3ABGWCIAiCIHQAtF5zYeZzup4z4RofOVFN8d1IclcKa1ZL4UIvNArv4uJiFWtJl3NOmHe27OeHSmNZmWnhpuBujks3vcYTLVw0YEQPtbAmy5Fw+tyF9z76GP7Yl4/T01IwTnMix2FAismFPTHJyIzzlvHVuemnd5VAP/Xiv6EwMg53bw3DqfkbcOr6H1A8eDiqjjwSGeEaUiya+myha1Lp9lq1V5cZccKbz+HE3xbizZNvxuoRXu/P5b1GYm3aAPzUazQMmgeawZs0YGXGCPWYEOZAKCCiWxAEQRAEQeh80LLdvbvX/byoyBv3zcznLD9Gt/MDJC1iYk4u8QkJyuW8qKhIWcEpzG3h4QgLorhvPSvz2nIjfvOYMMroxug2yBrO/cWld1NLT7XGm1V9TeKROHLgsd5JkVqMHjf+O/go9Cvcgx0J3dW6Ko8BiVs24sgV3+DjciduTzlWrbcYNLz9n/uhRUbipzMuRlxqInqFa+hh89ZYbi6cHPC2hQEuo7FN2iKUsXuAzfl2xHyyANE7tmP2mQ/AbfBOZvWKSMKJAA4rzYIn2YXvCk0oiojBrIv/1sCeNDU5xDCJUCB4fnEEQRAEQRCE4INVPbp18y5lZV7Xc1q/KcIPkn2Y4prlSel+ztrfdD1n0rWqykpVRpTu58GgxygqR8d4YDYbMdzladcM1fVjy714jCY8ePw1tc+8Cdge7u+AQxuMRbazsSe5H3qHe7C3xgCzvQbjt61WW1599HUorfKGEVzxywJcvvq/WDzhRKyddqayimfYPOjjKkd0fP1Ee41nUDd1WAb1YMHlcCFvw3ZsqQA+TRqukvBpLjPWLv4fohzVGJSXidKM3hgb40Hi6dOw7pJpmNgtFhPhUhMeTQ1/CHZEdAuCIAiCIAhdA1q3ueiu5zt3Ag6H1wJOUd5I3Dezn7OcT3R0tMp6XlpWpgR4aUmJSrhGq3iolexsz9jyORlODInSgPED1dIbwEw44GJt5nIXFt9wJ5z7cjGpZzh2V3uQWWPAgIIsdC/JRV6FCx/meiWL1eXApqcvQ0lENK67+SUkxkcoq/jgylwU2jU8XJ4GT8BpDPUM6s21/HvcHuyoAlZXhimX8UFLfsCDX70AQ8YIrDnvUbVNN5sJX55wLhITo/DgxGgkJeou4rFtFv7Q1RHRLQiCIAiCIHQtaOGm8E5KAr7+2iu4KcKZMO0A4pvu5b7SYwkJvrhvWr8puhn3HSolx1qTloorswHoHhMGHHOYen47vAm16Kle3usc/LjjSMSHd8NZMS5kVhtgytqnyp6Z3G6scEUDBV71+MjXn+KytV+iYuJsPD3lYrXO4nLi5M1LkRmXhjXpA9WxhVoG9aZY/tnWWTUGrCk3YvA7/8SE1Ysw9+Sb8X3/Cer13J6jUBweDS0hAbdkODAmRkNPmwbD6BnNCn9YV25EkZMx3F7viFA6D0R+VQRBEARBEISuiZ4YbexYoKTE63a+b59XfCcmAlZV6LdBaOHu1q2bcj+n6Fau5xUV8LjdSnyHWSxB4XreXrSmuOLpi0mMVQvjx4+uFeMYlII/Jr6Nwn1FuDfeid01RiXG4zQH7KYw7Ejo4dtHz5IcPPvfp1FuCceImz9UwvOS3y24fOO36Fuag/zDJ8A6sA+62zQkmL2f2doW5o4Umgeqnf7oJjfM2UuQlJ2JO4++CgW1onxupRNx1eU4Mut3VB52uHIZHzM0EcXH/wPpJiNO88963wxMBoR85noR3W0AS0253d7kEoGwNJTdbldZNVvLjYmZOFmrUhAEQRAEISThmColxWv5ZqK1zEyvyznNeBTfB4j95jgqLi5OxX0z2RqznauSYyUlKu6brufBWHKsLWgPcWWLtKF7/3R0VwLQ+1nfX3c9hmybA5NW99kWjxPLM0agxmzxKeo9diP6r1qKKbvW4DZzOv7tGazWDyrZi/mfPIac7r3xv4tuUkK8u1VDT08FEqJtMJqMh2hhRrvGllPw8/OJ0eNBt8oS2FwO7I5PU+7/Jk3D7A/nw6x5cP/wWQiLTcKIKA/Kp0/HT6dMwVFD+2Kqxb90roReHCoiuttAcG/evFnFCzVWl5mCuzV/wDkbO2jQoCYLb87m3nvvvViwYAHy8vIwZswYPPfccxg3bpxvm0svvRRvvvlmvfdNmzYNX331lfqfEwdXXnklPv30U6SmpuKFF17A8cd7SwOQJ598Ert378bzzz9/0ONhx8btP/roI+zatUt1fMOHD8d1112H008/XbXTMcccg9GjR+PZZ59tRssIgiAIghBy4js5uU5865Zvj+eg4tu/5FhiYqIan+g1vynMg7HkWLBASzKTt/mnkNuU3Bfn1cYg61yR7kTl5ElYmpYCT/++SLN6kGs3IL0wG/1zd8KhAe/l1MmjNz58DsOzfsejp9+MbWMnKyHe11OOodlbEZmRhrjuSftZrw9kYW5pbLnm0VDtASrcBpS5DXDlFcK2bRtKrJH4o/9IlHO9Czj93y8hsWAfHp92DfKjM9R7T9u4WNXJ/mLgJFx3+l1qXYU1Ah+OPAGxCdG4p78H/XraazPFezPNC62PiO5WhhZuCm7GAzUUE0TRzaW1RLfL5VKfx89tquimWF6/fj3eeustpKen4+2331aCeePGjejO0hy1nHTSSXj99dd9zznbq/PKK6/g119/xfLly/Hll1/i/PPPR25urvpOO3fuxKuvvopVq1Yd9Fg4mzxjxgz1+Mgjjyjhz3ZbvHgx/u///g/HHnusEuGCIAiCIAhNhmMsCm/GdxcWAllZQHY2B07edQfJeh5Ycoxx37SCcwynXM/Fw7BTUT+DuqHR8lTnp7thOn0qgKm4EcCNcMDpAQp698Hi9LtR6ATOSHZhr92gMqv3LM1RFuLN5jisKPEK+qN37MCf/v0QNiX1xrQrnkea1WsVP3P1V0iAE++kTgQikxs4Dj7X8NzuMAws3gV3aRn2du+LEpNViebobVsxeNUS7ElIx2cTZqDcZUC5G3jtxTnoXbAHp1/0FDak9ld7On39H0pIL+k9Bi+d442HJzds34hBBbuBwiKgVnSX2ryZ3mPtFfWO5q6TbsS9fR04LjG03b7bCxHdbQSFI2OFAuGPNYUyX2stSzf311Qo0GlRpoV6ypQpat0DDzyAzz//HC+++KISvv4im1bshti0aRNmzpyJYcOGoW/fvrjttttQUFCApKQkXHvttXj88cdVltCD8dBDDynr9pYtW9QEgM7AgQNx3nnnqQ5PEARBEAShReiJ1WjlzsjwWr518c114eFNLjlG0a1bvvk/y40pI0q7fRnhUDKoN1aeKswIpCVFAUlj0IvpAfT4cY6xX3gGv2YXYLYtAUfAqYR4yj4HMrv1wPZuGXBpBpWELKsGmPvDZ+hXtBevndsHiExR7z9sz0Y88s0L+LnnMNx/wrXquCjsez98P1IrijDj0uewIaWf2vb0LTm4+sf/4sdeo7Fi8My6o/d4YPG4EFtTAbNBQ7QJcHfrho0Zg1HRvQdOTHQj2sz1Gracdg72ehyY0DcNy2o19pI+Y9H/L5/AZTI36CEgtA8iukMMCnRaxQPFLGdtly5dWm/dokWLkJycrDobWpwpyOluRUaNGqUs5RTxX3/9NdLS0lQyknfeeUftm27hB4Px7R9//LGykvsLbh26dwmCIAiCIBwyemK1hASgV6868U0rONdFRBzw7czDw3JjvpJjpaW+kmO0enMcJSXHOpa2KE9lNpuQmJECjn7HojZfU8YYaDPHYIgGfOCowV67UYnxzLETkbNnD3Yk1HmNDsnbiSH5u5AfGV9vv9mxKXCHWdA3zInwGLcS0smDM7DIfibK03vgtt5OxJg1RJmAwttvx1qbCfcmxMJmsXvD08cMBE59BEMBDIXfl+3uzTjeSwPe/s1r+W9IbOuWf3oICO2DiO4Qg53FxIkT8fDDD2PIkCFISUnBe++9p9zE+/f3uqzoruVnnHEG+vTpg+3bt+Ouu+7C9OnT1XaMZ7r88suxbt06DB06VIntDz/8ULle3XfffUqs33PPPXj//ffRr18//POf/6zntq5Dyzg7rMGDvUksBEEQBEEQ2hQqFopsXXzT7Xzv3jrxHRl50F1QYHPR4745/qmo8JoVmfHcEhYmsd8dnEHdW5fahFFG90HrUrcU7jPFysWDsXTu/NO5WFNmRO7mOk/XH/uMwcVnP4jsmKR67818eC4SYjz4s3pWK5r79wAmnqf+HaELfBKT0q6Wf6FtENEdgtBCTdFMIcxOYezYscqVmzHaOueee67v/xEjRmDkyJFKQFNQH3fccWpWd/78+fX2e9lll2HOnDlYs2YNPvnkE/z222944okn1Dq6tDfkai8IgiAIgtAhxMd7F7qdU3zv2QMUFXnXNcHbjmMhCm/mnqHo5kK38yrm2nG5YGKoYVhYq4YUCgeHQnJ0jAdmsxHDXf6p1do/tjwzPl0tHWFhbgvLv9ByRHSHIBTPTFTGjoEztHQNP+ecc1RsdmPwNVq0t23bpkR3IAsXLsSGDRvw2muvqfjuk08+GZGRkZg9ezbmzZvX4D4Z/80YqT/++KNVv58gCIIgCEKTYcJWLhTfFN4U4BTftHw3QXzTgMHxDBeG8LHCC13QOc6qrKpSVWNoaNDz/ZjDwiQOPEjpbBbm9rT8CwdGgk9CGIpiCm66RTEu+7TTTmt02z179qCwsFBtHwhLoF1//fV4+eWXVcfDDoel0w5Ws5yxT3Rhf/fdd5HNuKoAOGPcnCRxgiAIgiAILSY2Fhg2DJg0CRg0iAMcb+x3eXmTd8FxUEREhLKAZ2RkqNC9Pn37qvETXdI5LiorLVUx4RTmMs4JPpSFuZ8TSQFJymhh5vr2tjDrlv/DumnqUQR3xyCW7jaisR9RznTyB9fhcLRaybDmQoHN42Btb1quaZlmXDXdw3Wx++CDD+LMM89U2csZ083yXew4WKs7EMaH07LNet9k8uTJap/cH63cfN4YrBfOOPEJEyZg7ty5OPzww5W71o8//ohHH30Uv/zyi5QMEwRBEASh/WD1laFDgZ49vfHemZl1budNqMwSmP08LCoK0VFRysOP4z8aK+iCzlJktIpz3EVDBOPBrRaLJGQLAnQL87pyI4qc3izhdCkXwRu6iOhuZTjDyZnMxmYvKXb5A0vB3VrxPfy85iTs4OzqnXfeqazXCQkJSlxT8Oo1J7kvJkl78803VaIzZhY/8cQTlbj2r9VNWO+bSdTWrl3rW3fWWWep2O+jjjpKCXtashuDmdGXLVumYr+ZHT0zM1OtYxz5k08+qVy1BEEQBEEQ2p3oaIDJXnv0qBPftHxzbELx3cxxHMd9HEdx4fjGk5ysxoQU4XRF12PC6SHIeHAKcI7NJB68a0KBPSZG4qYFLyK6Wxn+OFJoNuZSzTJZjO1hFvHWmsmkSNYFc1NgnDWXA4l4WsObwvDhw7F169Z66/i9XnjhBbU0BXY8tGpzaQyKeEEQBEEQhHaHcd10N29IfHNpoSjmeEnPhE6DA8eOFOA03FCA85HPJR5cELo+IrrbAArgxkQwRTddi1jLWtyHBEEQBEEQuggsJzZwIMAyqPv2Abt2tYr49jeiMN8OFyavZTiickWvqlIinFZx/k/Ltz7WpBgXBKHzI3eqIAiCIAiCIDRHfPfvD6SnA0wEq1u+uZ5GF4vF+3iIglgX1vSOTPZzRdct4fyf1nEVD87a4PxcQRA6JSK6BUEQBEEQBKG5RER4xbdu+c7LA6qqgMpKlm9htlvvdrSAU4D7C3IuzcjHQ+s2vSS5MMEsPSd9pcmqqlBZUYEqfq7FogS5lQncKMSb8RmCILQdIroFQRAEQRAEoaWEhwN9+3oX5vRxOAC73bvwf5YeoyCuqPCu43Ou93jqRLm/GNfF+QHc1f3jwZkUl8l7K6qrsau0VFnGHdXVKkO6p9YSTjd0xoPzUWLCBaH9EdEtCIIgCIIgCK0BLcsU4VwaghbwQFFeXV0nyvlct5RrWt0+/cW4/r8fFNOMBUdpKXr27AlDbQ4hnzW8shIO/l9VpRKz0QKuErOZzZJjSAgZDDU1MNEbpQMQ0S0IgiAIgiAI7YEumCmQA6HIpujWRbn+SBHOhWKBAr2szCvK/fepu68TlwvmWkEdERGhMqPrJWv1OuF0SeejvbJSuaorazhjyM1mVa5MrOFCUODxwFhdDUNVFYwuFzxWK5zx8d7X2nmySUS3IAiCIAiCIHQ0dCe3Wr0La4QHQnf0QCs5H2kh10U5KSjwbqtbyg0GGMxm2GqXGAr+2FhQttudTm9W9OpqZQXXk7MR/wzpUitc6DK43TBWViqxzXtACw+HKyUFnoQEuKOjUcN7g6X/2hkR3YIgCIIgCILQ2aFlzmbzLg1BkfHNN8DEiV7Brbuy+7uw64K9ogJhLhfCNA1RmoZEavqICNhtNjhYL9ztRqXdDjuzpXs88NAlncnZJEGb0AkxOBxKaBt4bRuN6lp29OoFD5MORkdD40SWDiepOgAR3YIgCIIgCILQ1dFLlLFmeEDMtw9a+XQxzke//401NQivrER4dTVinU5oTiec1dVwVFUpt/Rqlimz25WFvKb288zh4TDZbDBZrTCIEBfaC01T8dlG1q13OKCFhUGLioIzIwPumBgltANL9jHEgl4cTv/QjHZERLcghAC7du1Cnz59sGbNGowePRqLFi3C1KlTUVxcrEqPCIIgCIIQItZy3YX9QLhcMDidsDgcsPiJc1dVFeylpbAXFcFeVoaq0lK4iorgpIXR41EWcJUpnQnfIiLgYUK5xiYABKEF8dnKou12w2OzwR0bC3dSEjwU2gybqI3TpsB2cdKodmF2f2Ku9dToCER0hyCXXnop3nzzTd9zlpoYN24cnnjiCYwcObLNhF5TeOCBB/DJJ59g7dq1rXYcoXh+S0pKVDvqMJPpvn370K1bt1b9LM58P/vss3jnnXewdetWlbBl0KBBuPLKK3HhhReqH7aGjkcQBEEQhE4MrYRcArKwm2sXlQaO8bJMzFZejpqyMvVYUVyMqvJyuEpLYSouhrmgAAaXC0abDVpkJIyRkTBZLJIxXWgavHaYBK02X4EWEQFnaio8iYkqPpvPlcB2uVSZPAps/5wEFNk0LkVFRaka91arVU0M7dmzp93zFHQZ0T137lz873//U2KMJQ44iD8YPAn3338/Xn31VbX95MmT8eKLL2LAgAEIdU466SS8/vrr6v+cnBzcc889OOWUU7B79250BXhTddRMVVc8Zv7ApKamtrrgnjZtGn777Tc8/PDD6v6KiYnBihUr8NRTT2HMmDFNnmwRBEEQBKGLwQRtVivCufhN6nO8w4RsdE13FhfDWVgI+7598DDBW04OnC4X3CYT3OHh0Gw2GGszpptNJjVeMRiNkj09hDHUxmcz3EEzmbzx2b17q/hsCm2HweC1YDsccDNXgV/SPxoS/QW2LrL96Sj38i4zzcQB/tlnn41rr722ye+h5fbvf/87XnrpJaxcuVLVL6RI4A9Bm6KXdtCzRhK97iLdbxraljE2OrwYuC7wOBvbtgXwIqQI40JhdMcddyArKwv5+fm+bX7//Xcce+yxCA8PR2JiIq6++mpU+CUfYImJhx56CD169FD7436++uor3+u0chOKL84mHXPMMeo5XZvHjx+P6Oho9OrVC0cddRQyMzPxxhtv4MEHH1Qijttz4TrC/zlhMnPmTHUeOQnDmawrrrhCfQ6PkRbW5557rt73pJV11qxZar9JSUlKFP7pT39S11Nj8DM5K0bLLCdoeOPyumH7+PPpp59i7Nix6vW+ffuqz9DdVxo7ZvL5558rzwK+j5bn008/3fceZhD9y1/+gu7du6v3TJgwQbVX4LF9/fXXGDJkiPph4QQKrdi6pwC9GHhsehvy/fQ64P8H8iBYunSpOhdsS1rG58yZo+p6NgYt3EuWLMH333+P66+/Xp1/tsP555+v7jeZ3BIEQRCE0IPih2O8hORkpAwahB6TJqHfmWei3yWXIOO889DjlFPQfdQodO/WDWmahriKClhKS+GuqFDjjrLSUpSWlqKsrEyNO6sp4GstmH4jayGY4rOrq2EqLIQ5OxvGsjIVllDdvz/Khg9H/uDByEtMRJ7BgKLKSqXjKKQ5hua4k+Ph4cOHK29djj3T0tJUmTx6X3amhH9dxtJNQUN0EdYUKzdFAS24p512mlr3r3/9CykpKUpMnXvuuW13sFFR3se8PCApyfv/k08C99wDwxVXAE89VbdtcrK3xMPOnUDv3t518+cDt9wCnH8+8M47ddvydc4Srl8PDBvmXcf2uOqqQzpc/qC9/fbb6N+/vxLXhD96FJoTJ07EL7/8gry8POUyfMMNN/jOAQXu008/jZdfflkJ63/+859KYG7YsEFd9D///LMS19999x2GDRumPBQoSimCr7rqKuWSXFRUhI0bNypBeM4552D9+vVKuPM9JJbJQGqhoHzsscfUeaW7CEU/Bf+///1vddzLli1TEwO82WbPnu17H0UhBa4uPi+77DK1vS6CG6Kqqkq9zmuGx33dddepa+ann35Sr//444+4+OKL1aQOher27dvVZxN6VzR2zPTWoMi+++671b4p/r/44gvf9jfeeCM2bdqE999/H+np6ViwYIES1ZwA0UUsj42W5Lfeeku5Z9GNm0Kd7clHvp8dle7JwFm/7OzsA14DPH5+ziOPPKLOIydfeK656PsJhJ93/PHHq3MfiD7jKAiCIAiCQOhibk1PV4sax9K4xJrjZWXQ8vJUbLiLrukeD5xmMxxhYbDXGiQ4fnQxjrfWdZjjRo6BKKr0xUgreUd/SaFF8dluqxU1kZGoSU9Hjc0Gp82mEvNxLMlxeHxUlBLRHM9zsXTBEIUuI7qby86dO5XbNEWBDgUcLYfLly9vVHTzxuaiQ/FC9EB8f/ic4p7ij4uOfgmodfp6TVPr9Rk6/X38cTA0ti1jZfz22+C2/v83Ee73v//9r7KS6gKbQvWzzz7zHTdFOGeSKLBpcR06dKgSmJzAePTRR9XkBYXf//3f//kELtcvXLgQf/vb3zBv3jyfgOdsUzInFwAlsjl7efLJJ6vZKVqfDz/8cF9cBT+L4lTf3teOAM477zxccskl9b6Lv8Cl1ZzC+4MPPsBZZ53l+668MV977TV1s3I2jEL49ttvVxM5Dd2w/DyeW35fXi+EwpMTB3Sd5kQC38t9XHTRRer13r17q3X0GLj33nt9+wo8Zl53nFzwP+4RI0ao46Qlne3NiQEKbnLrrbeqSQgKYU4C6Mf2wgsvoF+/fmobWpnp3s3X9B8knruG2lC/VgOf//Wvf1UWalq3CffNiQImW5s/f77aZyCM4T766KPrXfsNoa7j2uu9Ibier/N76TOS+r3WUS5AnQlpizqkLdq2LQ5lX83pOw/1+OT8S1v4I23RhduCfX58vHfJyFBlzczl5TCXlsJWWOgt7WS3e+ssW61wWyxwGgze+F2Ho25xueChq7H/OIPju7g41DidsEqdcbgDHjsCg93uXaqqvOeQkyrR0XDGxMAdFQVzTIwS2RTY9LrUXcQ5jg88f/R60GO3O/o+aep+glZ0U3ATikN/+Fx/rSEoHHWruj/ffPONEjT+UBzSPZuW4nruynv2eB+ZubF24AFaQS+7zJe+vry83Lt+yxbvIxNV6NteeCFAIcsfI30d0V2D/bc944z62zTx4qB1llZqwnj3f/zjH0oI08KckZGBdevWKZHJC1ofPFEcUiCtXr1a/U/rKV2K9dcJBTSt1bpLEFGuQrXbsM0o7qZPn67czbnQ8q3HG3PQ5v+Z/lD4B65nvD4trkyIQKHJ88Bj8x/w8Xvw5vb/Hjw2Wtj5XQPhfnicdFfX30MRzEkbJoUbPHiwctOm1ZtiVYfHzffy+tKvlcBj5vsuuOCCBr8fj4f74P79YZvQLZ7v4f65b05W6PvgcdETwf87+39fEnguaC3Xr0NOPPB70UPh3Xff9b1HF8q0srMtAuHrbO+Gvos/DR2PP6oMSXW1clX3d88n33777QH3HUpIW9QhbdE2baH/LrSE5vSdh4qc/zqkLeqQtgjSttCNI3q9cX84Tg5I9BbItoO8HmpsCiij1a6YzbSu0QVz/9c4Tm3n+tmtdZ80te/sUNFNq+Djjz9+wG3oKhsoQtqSO++8U1kXdSgUGN964oknKuHjDwUQrZN6wL6PgO0ChQqFDmNd1KzNAbbdj+ZsewA4i8Tv4p/kiiKcFmlaiWk15awShaf/d+ax69ZofT0HU/7b+L9Pt6T7b0/oFq1bcD/++GNlwWWM8hFHHOFLeBDY1oSxG/7r6YJ93333KYs738s25f90a9e30zMX+r9PPy5u39Dn6OeSr/lbwnm++BrXU7zSYu4fj61DC7P+vsBj1mfuAj+Xbct98rvTnT8wBoXHzPfwvfr50+E54Pub8p31c6EPgvU2oOilezzd2wPhxATPayADBw7Ejh07GmxDfxo6nsD7iO0yZcoUX9tTqPPH8IQTTgh5N3VpizqkLdq2LQ42gdZafWdLkfNfh7RFHdIWIdIWtGrqwqyoyLtQ7HA9vyvHORxD6La9zesAABWOSURBVB5zHg++zcnB1MREeGot4/aaGlTVZrhmOSmOamk/NdeOU8xBbBF31wruIS4X2iTK2elUcdkeWrEZDsD4e4tFZaxHYiJMsbGISEqCNT4etogINd7nNdoR7d3a90lT+84OFd1//vOfVaKrA0EX5JagW05zc3OV67QOnx8oo7Ke6a4pMaq0SuoxJU2NK9BdbPX3dQR6gq3Az+dzCiA+0kLLhFwUYxRqhG75fI0u2kzmResv19EFWYfu3XS/5na6gKIgDPysww47TMUC0zWaVm8K6EmTJqm2Z7s21DaB7czP5nu4Dx2KQH1b/bsyMRutxRR2hKKcIpTu6I19Di2utOjzu5DNmzcrjwBazfk6E6ht2bJFCc8DEXjMTPJAF3wmgAu8Lvgav3tBQYGaBGlsf/6PDa1jG3J/jW3jf0z6//w+nOA62Pfxhx4Ld911l2rfwLhu/qCxg+O109j15n9sfL2he0xiw+uQtqhD2qJt2uJQ9tOcvvNQkfNfh7RFHdIWQd4W/D4cVzJLOnMc0aWXXqMUPMx3VFwMlJZ6kxhzu9oxHzOrh/lZu/VwNjvd0u12Ne6lpZLrKMj1MasS4RTjjBMPIiFOwX3IopttXFMDT0UF3JWVcDud8JhMKgzAEB8PEw1OSUmwdesGW1ycz2Bk6GTt2Fr3SVP30aGimy6yXNoCZrSm8GYSLV1kcyaCWZWbkwE9WKEI1d3si4uLVQw2XZBPPfVUtY4u0Iw7ZjwyLbpMrEUrKGOYdZf92267TW3D+F+2MeOe6T5Nd2/d4kuhS4s2E57xpmNM9yuvvKISrvH80K2ZscFMSqbHRjMen/vhe2iJbWggR5hYjMnIaCXn+aYFnVZiPWu6DsUfRS6T6jFemsfMBGEHmvTgDcTvy7hu/vBye1rTdRFOCztLrNEKzPhx7ovik671TEbWGPzs4447TrUZ47sp7plIjW3JRHYUsmwLuv5TyLLdeQ1TkM+YMaNJ55ZtyDbhRAHj6v2T0TUG49P5/fg9mTCPYpnu7pwJ5LXREDfffLNKDMfvQ++II488Up2vVatWKQ8WhixIyTBBEARBEFodCh26KXOhCGdOidqkbGAlHr208N69Xus3PfYYG2yxKO895cFX6wXYqBBn+JvLtb8Qp0UcoYPGmPmKCngosKuqlIeAZrXCGB0NY//+iExJUQLbmpAAa2RkgzHYQheK6Wb9aAo2PtIaqJc+olDRXWfphs64Mrr88mRTFFAAUZxRiDHBFa2zjCEOdSiEdQ8ACiW2HbOA62W96H5M4XbTTTep8lZ8fuaZZ+KZZ57x7YNJt5gUjR4LjCmmdZzJ2PQs2/xRomhlWTGKVFpv6b7+xx9/KCt6YWGhEvDMDH7NNdeo9/Az6HJO6zktyxTyjXlD8D0U7UxMxvPNpGXc15dffllvO4pCHhPdlznZwO04kXAg+H0pRCmC9+7dq46dIlKHmd2ZjI7fjQKTIp1tSMF6INi+bGeKVGY1p9slj0uHCdMYJ8425efSPZ1imAK/qTAzPDO1M76eEym0rFOIHwiK+sWLF6us6vyu7GA4McC2bQxOhlCUM3EeM9gzc7qerI7XBss3CIIgCIIgtDk00NCQx4WJZim+Fy5kIh+VoE091x8ZG66X9aUFlhmymbCLQp7enQaDL2+Nckv3E+IU5dUUnroQ93dNR9eH34vCmgKbCzjpwCzxUVEwJCYictQoJbAtdBNPSFDtJgK7aRg0PVC3k0PhRaEWCAWFLhR50v1FGr8aLYu0rFLA0RLHrM/NcaGldZyWQorLhmK6aZWloG8ou3ND0O2X+wyMFw5F2qMteC3w3LNMXFNhBnFO2PB97UUoXxcN3UeccaYHAJP7BZ2LXDORtqhD2qJt2+JA/V1H7ktHzn8d0hZ1SFvUIW1xkLZgslZaxFmqjAv/p4s6Fz6nGKfbOkNBORbj+2ot5Fw0ljHzE+KsH04BrieMJSxbRgEeZjbD1ImEOGO615vNGO4X002d5HI46gR2TQ2FIYwRETAyXxXLuyUnw5qYqBYLhXcQCGxnK98nTe3vuoylm0LoYDW6A+cPeGHQEslFEARBEARBEIQQhdmz9QzagVBw64Kcj7SKM2kbLeNcV14OA8uP0ahuMCC61j3dExcH5lR3eDzKPb2mulpZxFVtcQrZWiGuS1V/0drY/7S0+/71O8RDea+H681mVLNqDb8XczhRgDOumQK7Rw9Y0tNh0QV2fLyqky20Hl1GdAuCIAiCIAiCILQ6ukU7Orr+ehr0KMj9rePMmk7reEUFjDU1sDkcsOk1o41GeOLjvUKcOZTo0edwQPN4lHFQNxDyOfR1fPR4lJVZvV67Xn02t6vdho9KSPP12mMz1K4PXPTP04W3i5b7/v1hq6xERFwcLCkpavEJ7FYu7Sjsj4huIag5mHdEYy7pB8uqLwiCIAiCIAQ5tBAzXpxLYGJaCl5/6zgfq6pgLCtT4tZGV3WupxDmfih8da9cWty5Tl+vfxb/r12vtuRjQ89r3894a/Ueo3H//5lRnO8xGuF0u7F1+3ZkzJ6tRLZ6v9CuSIsLgiAIgiAIgiA0BwpbliPzK0nmg5ZvXYxz0QW2v7D2E9gN/a/cxmvLqtZ7vQWYOAGwfTsMcXEiuDsIafVWoIvkohOEToncP4IgCIIgBBWMh2bseEPx40JIElppklsZPeMdEyYIgtAy9Psn1DOtCoIgCIIgCMGJWLoPAZPJhLi4OFWjmrBG8cFS6bM0FEsNsExSqJWGCkTaIrTbghZuCm7eP7yPeD8JgiAIgiAIQrAhovsQSU1NVY+68G6K0KiurkZ4eHhQ1Lo7FKQt6gjltqDg1u8jQRAEQRAEQQg2RHQfIhRIaWlpSE5OVsXWDwa3WbJkCaZMmRLy7rTSFnWEalvwu4qFWxAEQRAEQQhmRHS3EhQOTREP3MblcsFms4WUuGoIaYs6pC0EQRAEQRAEITgJjeBRQRAEQRAEQRAEQegARHQLgiAIgiAIgiAIQhsholsQBEEQBEEQBEEQ2giJ6W5CVmlSVlbWagmzWCaJ+wv12F1pizqkLeoj7VGHtEUd0hZt2xZ6P6f3e52p7yRy/uuQtqhD2qIOaYs6pC3qI+3Rdm3R1L5TRPdBKC8vV489e/bs6EMRBEEQhHbp92JjYw95H0T6TkEQBCEUOFjfadBaY0o7iPF4PMjOzkZ0dHSr1E/mbAgHIVlZWYiJiUEoI21Rh7RFfaQ96pC2qEPaom3bgsMBDhrS09NhNBo7Vd9J5PzXIW1Rh7RFHdIWdUhb1Efao+3aoql9p1i6DwIbr0ePHq2+X57kUL/odaQt6pC2qI+0Rx3SFnVIW7RdWxyqhbut+04i578OaYs6pC3qkLaoQ9qiPtIebdMWTek7JZGaIAiCIAiCIAiCILQRIroFQRAEQRAEQRAEoY0Q0d3OWK1W3H///eox1JG2qEPaoj7SHnVIW9QhbRHabRGK37kxpC3qkLaoQ9qiDmmL+kh7dHxbSCI1QRAEQRAEQRAEQWgjxNItCIIgCIIgCIIgCG2EiG5BEARBEARBEARBaCNEdAuCIAiCIAiCIAhCGyGiWxAEQRAEQRAEQRDaCBHd7cz8+fPRu3dv2Gw2TJgwAT///DNCjUcffRTjxo1DdHQ0kpOTMWvWLGzevLmjD6tT8Nhjj8FgMODmm29GKLJ3715ceOGFSExMRHh4OEaMGIFVq1Yh1HC73bj33nvRp08f1Q79+vXDww8/jFDJe7lkyRKceuqpSE9PV/fDJ598Uu91tsN9992HtLQ01T7HH388tm7dilBrC6fTidtvv13dJ5GRkWqbiy++GNnZ2Qg2pO+UvvNAhHrfSaT/9BLK/af0nZ27/xTR3Y588MEHuPXWW1Wa+tWrV2PUqFGYNm0a8vLyEEosXrwY119/PVasWIFvv/1WXfgnnngiKisrEcr88ssvePnllzFy5EiEIsXFxZg8eTLCwsLw5ZdfYuPGjXj66acRHx+PUOPxxx/Hiy++iHnz5mHTpk3q+RNPPIHnn38eoQB/C/j7SKHVEGyLv//973jppZewcuVK1WHyt7Smpgah1BZVVVWqL+EAk48ff/yxEmEzZ85EMCF9pxfpOxsm1PtOIv1nHaHcf0rf2cn7T5YME9qH8ePHa9dff73vudvt1tLT07VHH31UC2Xy8vI4/agtXrxYC1XKy8u1AQMGaN9++6129NFHazfddJMWatx+++3akUce2dGH0SmYMWOGdvnll9dbd8YZZ2gXXHCBFmrwt2HBggW+5x6PR0tNTdWefPJJ37qSkhLNarVq7733nhZKbdEQP//8s9ouMzNTCxak72wY6Tul79SR/rMO6T+9SN/Z+fpPsXS3Ew6HA7/++qty5dAxGo3q+fLlyxHKlJaWqseEhASEKrRezJgxo971EWp89tlnOPzww3H22Wcr18kxY8bg1VdfRSgyadIkfP/999iyZYt6/ttvv2Hp0qWYPn06Qp2dO3ciJyen3r0SGxurXI5D/bdU/z2lG11cXByCAek7G0f6Tuk7daT/rEP6z4aRvrPj+09zm+xV2I+CggIVZ5KSklJvPZ//8ccfCFU8Ho+KwaJb1PDhwxGKvP/++8q1hS5yocyOHTuUSxjdSO+66y7VHnPmzIHFYsEll1yCUOKOO+5AWVkZBg8eDJPJpH475s6diwsuuAChDgcNpKHfUv21UIUugoxRO++88xATE4NgQPrOhpG+U/pOf6T/rEP6z4aRvrPj+08R3UKHz1KvX79ezUKGIllZWbjppptUfB4TBIUyHERypv6vf/2res6Zel4bjD0KtUHDhx9+iHfeeQfvvvsuhg0bhrVr16oBNhN9hFpbCE2D8b2zZ89WiXI4+BaCG+k7pe/0R/rPOqT/FDpr/ynu5e1Et27d1Ixbbm5uvfV8npqailDkhhtuwH//+18sXLgQPXr0QChCt0kmAxo7dizMZrNamCyHiS74P2doQwVm0xw6dGi9dUOGDMHu3bsRatx2221qtv7cc89VmTUvuugi3HLLLSp7caij/17Kb+n+A4bMzEwlQoLFyk2k79wf6Tul7wxE+s86pP9sGOk7O77/FNHdTtDF57DDDlNxJv4zk3w+ceJEhBKcSeKgYcGCBfjhhx9UWYdQ5bjjjsPvv/+uZmL1hbPVdIPi/xxshgp0kwwsf8OYrF69eiHUYFZNxq36w2uBvxmhDn8vOEDw/y2lKyEzsYbab6n/gIFlX7777jtVLiiYkL6zDuk765C+sz7Sf9Yh/WfDSN/Z8f2nuJe3I4y1oWsLO4bx48fj2WefVensL7vsMoSaWxzdfj799FNVb1SPJWFCB9YNDCX4/QPj8VjCgTd+qMXpcSaaCVDoHscfQdbhfeWVV9QSarCuJGPQMjIylHvcmjVr8Mwzz+Dyyy9HKFBRUYFt27bVSwDDgTQTRrFN6Cr4yCOPYMCAAWogwZIfdB1k3eJQagtat8466ywV10rLJ617+u8pX6dgDQak7/QifWcd0nfWR/rPOkK5/5S+s5P3n22SE11olOeff17LyMjQLBaLKoOyYsUKLdTgZdfQ8vrrr3f0oXUKQrnsyeeff64NHz5clbAYPHiw9sorr2ihSFlZmboG+Fths9m0vn37anfffbdmt9u1UGDhwoUN/kZccsklvtIn9957r5aSkqKuleOOO07bvHmzFmptsXPnzkZ/T/m+YEL6Tuk7D0Yo951E+k8vodx/St/ZuftPA/+0vpQXBEEQBEEQBEEQBEFiugVBEARBEARBEAShjRDRLQiCIAiCIAiCIAhthIhuQRAEQRAEQRAEQWgjRHQLgiAIgiAIgiAIQhsholsQBEEQBEEQBEEQ2ggR3YIgCIIgCIIgCILQRojoFgRBEARBEARBEIQ2QkS3IAiCIAiCIAiCILQRIroFQehU7Nq1CwaDAWvXru3oQxEEQRCELoH0nYLQuRHRLQhCs7n00ksxa9as/dYvWrRIdfolJSUt3nfPnj2xb98+DB8+/BCPUhAEQRA6D9J3CkLoYu7oAxAEQdBxOBywWCxITU3t6EMRBEEQhC6B9J2C0PkRS7cgCG3GRx99hGHDhsFqtaJ37954+umn673OdQ8//DAuvvhixMTE4Oqrr97PRY6WAT4PXGgZIMXFxer98fHxiIiIwPTp07F161bfZ7zxxhuIi4vD119/jSFDhiAqKgonnXSSsggIgiAIQmdD+k5BCD5EdAuC0Cb8+uuvmD17Ns4991z8/vvveOCBB3Dvvfeqjtyfp556CqNGjcKaNWvU64E899xzqpPXl5tuugnJyckYPHiwb2CxatUqfPbZZ1i+fDk0TcPJJ58Mp9Pp20dVVZX6nLfeegtLlizB7t278Ze//KUdWkEQBEEQmo70nYIQpGiCIAjN5JJLLtFMJpMWGRlZb7HZbBp/VoqLi7Xzzz9fO+GEE+q977bbbtOGDh3qe96rVy9t1qxZ9bbZuXOn2seaNWv2+9yPPvpIfcbSpUvV8y1btqhtf/rpJ982BQUFWnh4uPbhhx+q56+//rraZtu2bb5t5s+fr6WkpLRiiwiCIAjCgZG+UxBCF7F0C4LQIqZOnarc2PyX1157zff6pk2bMHny5Hrv4XO6r7ndbt+6ww8/vEmfx9n8iy66CPPmzfPtl59hNpsxYcIE33aJiYkYNGiQek2HrnP9+vXzPU9LS0NeXl4Lv7kgCIIgtAzpOwUhNJFEaoIgtIjIyEj079+/3ro9e/a0aD8HIycnBzNnzsSVV16JK664otmfERYWVu8549roSicIgiAI7Yn0nYIQmoilWxCENoGJV3766ad66/h84MCBMJlMTd5PTU0NTjvtNBWH9swzz+z3GS6XCytXrvStKywsxObNmzF06NBW+BaCIAiC0H5I3ykIwYlYugVBaBP+/Oc/Y9y4cSrD6jnnnKMStdC97YUXXmjWfq655hpkZWXh+++/R35+vm99QkICBgwYoAYVV111FV5++WVER0fjjjvuQPfu3dV6QRAEQehKSN8pCMGJWLoFQWgTxo4diw8//BDvv/8+hg8fjvvuuw8PPfSQypjaHBYvXqwyr3L2nfFk+rJs2TL1+uuvv47DDjsMp5xyCiZOnKhc37744ov93OIEQRAEobMjfacgBCcGZlPr6IMQBEEQBEEQBEEQhGBELN2CIAiCIAiCIAiC0EaI6BYEQRAEQRAEQRCENkJEtyAIgiAIgiAIgiC0ESK6BUEQBEEQBEEQBKGNENEtCIIgCIIgCIIgCG2EiG5BEARBEARBEARBaCNEdAuCIAiCIAiCIAhCGyGiWxAEQRAEQRAEQRDaCBHdgiAIgiAIgiAIgtBGiOgWBEEQBEEQBEEQhDZCRLcgCIIgCIIgCIIgoG34f08IZNEIk3cPAAAAAElFTkSuQmCC",
      "text/plain": [
       "<Figure size 1000x400 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# number of bootstrap replications\n",
    "B = 500\n",
    "\n",
    "# 1) get NW-based IRFs + do store_internals\n",
    "lp_results, boot_draws = bootstrap_LP(data, Y, response_vars, horizon, lags, newey_lags, ci_width=ci_width, shock=shock_vars, B=B, seed=123)\n",
    "\n",
    "show_irfs(horizon, irf_results, shock_vars, response_vars, boot_draws)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "f9f39d1f",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\Users\\valte\\Dropbox (Personal)\\Valter Nóbrega\\Projects\\Immigration, Inequality and Welfare - A Skill-Distribution Perspective\\Code\\Python Code\\.venv\\Lib\\site-packages\\localprojections\\lp.py:794: FutureWarning: The behavior of DataFrame concatenation with empty or all-NA entries is deprecated. In a future version, this will no longer exclude empty or all-NA columns when determining the result dtypes. To retain the old behavior, exclude the relevant entries before the concat operation.\n",
      "  irf_full = pd.concat([irf_full, irf], axis=0)  # top to bottom concat\n",
      "c:\\Users\\valte\\Dropbox (Personal)\\Valter Nóbrega\\Projects\\Immigration, Inequality and Welfare - A Skill-Distribution Perspective\\Code\\Python Code\\.venv\\Lib\\site-packages\\localprojections\\lp.py:1520: SettingWithCopyWarning:\n",
      "\n",
      "\n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "\n",
      "c:\\Users\\valte\\Dropbox (Personal)\\Valter Nóbrega\\Projects\\Immigration, Inequality and Welfare - A Skill-Distribution Perspective\\Code\\Python Code\\.venv\\Lib\\site-packages\\localprojections\\lp.py:1520: SettingWithCopyWarning:\n",
      "\n",
      "\n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "\n",
      "c:\\Users\\valte\\Dropbox (Personal)\\Valter Nóbrega\\Projects\\Immigration, Inequality and Welfare - A Skill-Distribution Perspective\\Code\\Python Code\\.venv\\Lib\\site-packages\\localprojections\\lp.py:1520: SettingWithCopyWarning:\n",
      "\n",
      "\n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "\n"
     ]
    },
    {
     "data": {
      "application/vnd.plotly.v1+json": {
       "config": {
        "plotlyServerURL": "https://plot.ly"
       },
       "data": [
        {
         "line": {
          "color": "grey",
          "dash": "solid",
          "width": 1
         },
         "mode": "lines",
         "type": "scatter",
         "x": [
          0,
          1,
          2,
          3,
          4,
          5,
          6,
          7,
          8
         ],
         "xaxis": "x",
         "y": {
          "bdata": "AAAAAAAAAAAA",
          "dtype": "i1"
         },
         "yaxis": "y"
        },
        {
         "line": {
          "color": "black",
          "dash": "solid",
          "width": 3
         },
         "mode": "lines",
         "type": "scatter",
         "x": [
          0,
          1,
          2,
          3,
          4,
          5,
          6,
          7,
          8
         ],
         "xaxis": "x",
         "y": {
          "bdata": "BgAAAAAA8D+mZzyUXgb1P51Y0uIU6/4/ij/H87aHAkB090mlN8L/PxhnarZvfPw/CIvirBFQwb+cOd8eNG4FwD5CMhzjBxFA",
          "dtype": "f8"
         },
         "yaxis": "y"
        },
        {
         "line": {
          "color": "black",
          "dash": "dash",
          "width": 1
         },
         "mode": "lines",
         "type": "scatter",
         "x": [
          0,
          1,
          2,
          3,
          4,
          5,
          6,
          7,
          8
         ],
         "xaxis": "x",
         "y": {
          "bdata": "8///////7z+28DlwVi/wP/DisVlIJu8/PCYPwdHT4z+6m5c0Q7zhP0Glibtqi/Y/fFXfM8yS7b8kfrG8ac4KwL9YjBY1Jw5A",
          "dtype": "f8"
         },
         "yaxis": "y"
        },
        {
         "line": {
          "color": "black",
          "dash": "dash",
          "width": 1
         },
         "mode": "lines",
         "type": "scatter",
         "x": [
          0,
          1,
          2,
          3,
          4,
          5,
          6,
          7,
          8
         ],
         "xaxis": "x",
         "y": {
          "bdata": "EgAAAAAA8D+W3j64Zt35P+HfZcyCIQdAwlqluzwNEECGECTYJlMLQHiUpVi6NgFA+A9uXcPq5D8U9QyB/g0AwB1YHq0r/BJA",
          "dtype": "f8"
         },
         "yaxis": "y"
        },
        {
         "line": {
          "color": "grey",
          "dash": "solid",
          "width": 1
         },
         "mode": "lines",
         "type": "scatter",
         "x": [
          0,
          1,
          2,
          3,
          4,
          5,
          6,
          7,
          8
         ],
         "xaxis": "x2",
         "y": {
          "bdata": "AAAAAAAAAAAA",
          "dtype": "i1"
         },
         "yaxis": "y2"
        },
        {
         "line": {
          "color": "black",
          "dash": "solid",
          "width": 3
         },
         "mode": "lines",
         "type": "scatter",
         "x": [
          0,
          1,
          2,
          3,
          4,
          5,
          6,
          7,
          8
         ],
         "xaxis": "x2",
         "y": {
          "bdata": "ag7f9Dj/ob/00VJZAWKVv7XLKpeg1qE/mLZTMm3EYD+/J36bgQuxP9RbgosIGJI/UojwhaDSur+r8MOuYSbLv9hfonzBVco/",
          "dtype": "f8"
         },
         "yaxis": "y2"
        },
        {
         "line": {
          "color": "black",
          "dash": "dash",
          "width": 1
         },
         "mode": "lines",
         "type": "scatter",
         "x": [
          0,
          1,
          2,
          3,
          4,
          5,
          6,
          7,
          8
         ],
         "xaxis": "x2",
         "y": {
          "bdata": "9sVOGithwr/cFSMVZanJvzTPtVV/+b+/eBpNxtcExb+vng9L3B69vzrFrrjZFcS/X/6bM1Riyb9LBCTSNJ/Uv38nZshMDMY/",
          "dtype": "f8"
         },
         "yaxis": "y2"
        },
        {
         "line": {
          "color": "black",
          "dash": "dash",
          "width": 1
         },
         "mode": "lines",
         "type": "scatter",
         "x": [
          0,
          1,
          2,
          3,
          4,
          5,
          6,
          7,
          8
         ],
         "xaxis": "x2",
         "y": {
          "bdata": "g32+Px3Dsj9eYc6+5FDEP3RNcPYP6Mg/LLjfL/uKxT8W9wXB75rPPy5cj9vbm8g/MJ9IJcUEh79/sX9ysxy6vzGY3jA2n84/",
          "dtype": "f8"
         },
         "yaxis": "y2"
        },
        {
         "line": {
          "color": "grey",
          "dash": "solid",
          "width": 1
         },
         "mode": "lines",
         "type": "scatter",
         "x": [
          0,
          1,
          2,
          3,
          4,
          5,
          6,
          7,
          8
         ],
         "xaxis": "x3",
         "y": {
          "bdata": "AAAAAAAAAAAA",
          "dtype": "i1"
         },
         "yaxis": "y3"
        },
        {
         "line": {
          "color": "black",
          "dash": "solid",
          "width": 3
         },
         "mode": "lines",
         "type": "scatter",
         "x": [
          0,
          1,
          2,
          3,
          4,
          5,
          6,
          7,
          8
         ],
         "xaxis": "x3",
         "y": {
          "bdata": "d7VTYfterT/rsWXBtkvnv5ZT+hXsd/W//34ASr1d2r9H2nkNoQrMv67oMd1TdPE/OtZQErfaCUD6vL+5SeQNQFbzTzBa1Pu/",
          "dtype": "f8"
         },
         "yaxis": "y3"
        },
        {
         "line": {
          "color": "black",
          "dash": "dash",
          "width": 1
         },
         "mode": "lines",
         "type": "scatter",
         "x": [
          0,
          1,
          2,
          3,
          4,
          5,
          6,
          7,
          8
         ],
         "xaxis": "x3",
         "y": {
          "bdata": "sdFa+SjP7r8cg0IWUtMDwFMNb4MlXAbAP+NtbSXk+r/7DW9chn7sv84TdCIgpd0/ajQSwxnTAkBQkf+qEJ7+P07rAns5CATA",
          "dtype": "f8"
         },
         "yaxis": "y3"
        },
        {
         "line": {
          "color": "black",
          "dash": "dash",
          "width": 1
         },
         "mode": "lines",
         "type": "scatter",
         "x": [
          0,
          1,
          2,
          3,
          4,
          5,
          6,
          7,
          8
         ],
         "xaxis": "x3",
         "y": {
          "bdata": "MKTCMoQ98T9OVB9r7VrwP6A3l64th7w/fkfbkI1q6z+uQWSra/LcP2jMxrFff/s/BbzHMCpxEECm2P+OxTwWQCEgNNWCMO+/",
          "dtype": "f8"
         },
         "yaxis": "y3"
        }
       ],
       "layout": {
        "annotations": [
         {
          "font": {
           "size": 6
          },
          "showarrow": false,
          "text": "invest -> invest",
          "x": 0.225,
          "xanchor": "center",
          "xref": "paper",
          "y": 1,
          "yanchor": "bottom",
          "yref": "paper"
         },
         {
          "font": {
           "size": 6
          },
          "showarrow": false,
          "text": "value -> invest",
          "x": 0.775,
          "xanchor": "center",
          "xref": "paper",
          "y": 1,
          "yanchor": "bottom",
          "yref": "paper"
         },
         {
          "font": {
           "size": 6
          },
          "showarrow": false,
          "text": "capital -> invest",
          "x": 0.225,
          "xanchor": "center",
          "xref": "paper",
          "y": 0.375,
          "yanchor": "bottom",
          "yref": "paper"
         }
        ],
        "font": {
         "color": "black",
         "size": 9
        },
        "hovermode": "x unified",
        "plot_bgcolor": "white",
        "showlegend": false,
        "template": {
         "data": {
          "bar": [
           {
            "error_x": {
             "color": "#2a3f5f"
            },
            "error_y": {
             "color": "#2a3f5f"
            },
            "marker": {
             "line": {
              "color": "#E5ECF6",
              "width": 0.5
             },
             "pattern": {
              "fillmode": "overlay",
              "size": 10,
              "solidity": 0.2
             }
            },
            "type": "bar"
           }
          ],
          "barpolar": [
           {
            "marker": {
             "line": {
              "color": "#E5ECF6",
              "width": 0.5
             },
             "pattern": {
              "fillmode": "overlay",
              "size": 10,
              "solidity": 0.2
             }
            },
            "type": "barpolar"
           }
          ],
          "carpet": [
           {
            "aaxis": {
             "endlinecolor": "#2a3f5f",
             "gridcolor": "white",
             "linecolor": "white",
             "minorgridcolor": "white",
             "startlinecolor": "#2a3f5f"
            },
            "baxis": {
             "endlinecolor": "#2a3f5f",
             "gridcolor": "white",
             "linecolor": "white",
             "minorgridcolor": "white",
             "startlinecolor": "#2a3f5f"
            },
            "type": "carpet"
           }
          ],
          "choropleth": [
           {
            "colorbar": {
             "outlinewidth": 0,
             "ticks": ""
            },
            "type": "choropleth"
           }
          ],
          "contour": [
           {
            "colorbar": {
             "outlinewidth": 0,
             "ticks": ""
            },
            "colorscale": [
             [
              0,
              "#0d0887"
             ],
             [
              0.1111111111111111,
              "#46039f"
             ],
             [
              0.2222222222222222,
              "#7201a8"
             ],
             [
              0.3333333333333333,
              "#9c179e"
             ],
             [
              0.4444444444444444,
              "#bd3786"
             ],
             [
              0.5555555555555556,
              "#d8576b"
             ],
             [
              0.6666666666666666,
              "#ed7953"
             ],
             [
              0.7777777777777778,
              "#fb9f3a"
             ],
             [
              0.8888888888888888,
              "#fdca26"
             ],
             [
              1,
              "#f0f921"
             ]
            ],
            "type": "contour"
           }
          ],
          "contourcarpet": [
           {
            "colorbar": {
             "outlinewidth": 0,
             "ticks": ""
            },
            "type": "contourcarpet"
           }
          ],
          "heatmap": [
           {
            "colorbar": {
             "outlinewidth": 0,
             "ticks": ""
            },
            "colorscale": [
             [
              0,
              "#0d0887"
             ],
             [
              0.1111111111111111,
              "#46039f"
             ],
             [
              0.2222222222222222,
              "#7201a8"
             ],
             [
              0.3333333333333333,
              "#9c179e"
             ],
             [
              0.4444444444444444,
              "#bd3786"
             ],
             [
              0.5555555555555556,
              "#d8576b"
             ],
             [
              0.6666666666666666,
              "#ed7953"
             ],
             [
              0.7777777777777778,
              "#fb9f3a"
             ],
             [
              0.8888888888888888,
              "#fdca26"
             ],
             [
              1,
              "#f0f921"
             ]
            ],
            "type": "heatmap"
           }
          ],
          "histogram": [
           {
            "marker": {
             "pattern": {
              "fillmode": "overlay",
              "size": 10,
              "solidity": 0.2
             }
            },
            "type": "histogram"
           }
          ],
          "histogram2d": [
           {
            "colorbar": {
             "outlinewidth": 0,
             "ticks": ""
            },
            "colorscale": [
             [
              0,
              "#0d0887"
             ],
             [
              0.1111111111111111,
              "#46039f"
             ],
             [
              0.2222222222222222,
              "#7201a8"
             ],
             [
              0.3333333333333333,
              "#9c179e"
             ],
             [
              0.4444444444444444,
              "#bd3786"
             ],
             [
              0.5555555555555556,
              "#d8576b"
             ],
             [
              0.6666666666666666,
              "#ed7953"
             ],
             [
              0.7777777777777778,
              "#fb9f3a"
             ],
             [
              0.8888888888888888,
              "#fdca26"
             ],
             [
              1,
              "#f0f921"
             ]
            ],
            "type": "histogram2d"
           }
          ],
          "histogram2dcontour": [
           {
            "colorbar": {
             "outlinewidth": 0,
             "ticks": ""
            },
            "colorscale": [
             [
              0,
              "#0d0887"
             ],
             [
              0.1111111111111111,
              "#46039f"
             ],
             [
              0.2222222222222222,
              "#7201a8"
             ],
             [
              0.3333333333333333,
              "#9c179e"
             ],
             [
              0.4444444444444444,
              "#bd3786"
             ],
             [
              0.5555555555555556,
              "#d8576b"
             ],
             [
              0.6666666666666666,
              "#ed7953"
             ],
             [
              0.7777777777777778,
              "#fb9f3a"
             ],
             [
              0.8888888888888888,
              "#fdca26"
             ],
             [
              1,
              "#f0f921"
             ]
            ],
            "type": "histogram2dcontour"
           }
          ],
          "mesh3d": [
           {
            "colorbar": {
             "outlinewidth": 0,
             "ticks": ""
            },
            "type": "mesh3d"
           }
          ],
          "parcoords": [
           {
            "line": {
             "colorbar": {
              "outlinewidth": 0,
              "ticks": ""
             }
            },
            "type": "parcoords"
           }
          ],
          "pie": [
           {
            "automargin": true,
            "type": "pie"
           }
          ],
          "scatter": [
           {
            "fillpattern": {
             "fillmode": "overlay",
             "size": 10,
             "solidity": 0.2
            },
            "type": "scatter"
           }
          ],
          "scatter3d": [
           {
            "line": {
             "colorbar": {
              "outlinewidth": 0,
              "ticks": ""
             }
            },
            "marker": {
             "colorbar": {
              "outlinewidth": 0,
              "ticks": ""
             }
            },
            "type": "scatter3d"
           }
          ],
          "scattercarpet": [
           {
            "marker": {
             "colorbar": {
              "outlinewidth": 0,
              "ticks": ""
             }
            },
            "type": "scattercarpet"
           }
          ],
          "scattergeo": [
           {
            "marker": {
             "colorbar": {
              "outlinewidth": 0,
              "ticks": ""
             }
            },
            "type": "scattergeo"
           }
          ],
          "scattergl": [
           {
            "marker": {
             "colorbar": {
              "outlinewidth": 0,
              "ticks": ""
             }
            },
            "type": "scattergl"
           }
          ],
          "scattermap": [
           {
            "marker": {
             "colorbar": {
              "outlinewidth": 0,
              "ticks": ""
             }
            },
            "type": "scattermap"
           }
          ],
          "scattermapbox": [
           {
            "marker": {
             "colorbar": {
              "outlinewidth": 0,
              "ticks": ""
             }
            },
            "type": "scattermapbox"
           }
          ],
          "scatterpolar": [
           {
            "marker": {
             "colorbar": {
              "outlinewidth": 0,
              "ticks": ""
             }
            },
            "type": "scatterpolar"
           }
          ],
          "scatterpolargl": [
           {
            "marker": {
             "colorbar": {
              "outlinewidth": 0,
              "ticks": ""
             }
            },
            "type": "scatterpolargl"
           }
          ],
          "scatterternary": [
           {
            "marker": {
             "colorbar": {
              "outlinewidth": 0,
              "ticks": ""
             }
            },
            "type": "scatterternary"
           }
          ],
          "surface": [
           {
            "colorbar": {
             "outlinewidth": 0,
             "ticks": ""
            },
            "colorscale": [
             [
              0,
              "#0d0887"
             ],
             [
              0.1111111111111111,
              "#46039f"
             ],
             [
              0.2222222222222222,
              "#7201a8"
             ],
             [
              0.3333333333333333,
              "#9c179e"
             ],
             [
              0.4444444444444444,
              "#bd3786"
             ],
             [
              0.5555555555555556,
              "#d8576b"
             ],
             [
              0.6666666666666666,
              "#ed7953"
             ],
             [
              0.7777777777777778,
              "#fb9f3a"
             ],
             [
              0.8888888888888888,
              "#fdca26"
             ],
             [
              1,
              "#f0f921"
             ]
            ],
            "type": "surface"
           }
          ],
          "table": [
           {
            "cells": {
             "fill": {
              "color": "#EBF0F8"
             },
             "line": {
              "color": "white"
             }
            },
            "header": {
             "fill": {
              "color": "#C8D4E3"
             },
             "line": {
              "color": "white"
             }
            },
            "type": "table"
           }
          ]
         },
         "layout": {
          "annotationdefaults": {
           "arrowcolor": "#2a3f5f",
           "arrowhead": 0,
           "arrowwidth": 1
          },
          "autotypenumbers": "strict",
          "coloraxis": {
           "colorbar": {
            "outlinewidth": 0,
            "ticks": ""
           }
          },
          "colorscale": {
           "diverging": [
            [
             0,
             "#8e0152"
            ],
            [
             0.1,
             "#c51b7d"
            ],
            [
             0.2,
             "#de77ae"
            ],
            [
             0.3,
             "#f1b6da"
            ],
            [
             0.4,
             "#fde0ef"
            ],
            [
             0.5,
             "#f7f7f7"
            ],
            [
             0.6,
             "#e6f5d0"
            ],
            [
             0.7,
             "#b8e186"
            ],
            [
             0.8,
             "#7fbc41"
            ],
            [
             0.9,
             "#4d9221"
            ],
            [
             1,
             "#276419"
            ]
           ],
           "sequential": [
            [
             0,
             "#0d0887"
            ],
            [
             0.1111111111111111,
             "#46039f"
            ],
            [
             0.2222222222222222,
             "#7201a8"
            ],
            [
             0.3333333333333333,
             "#9c179e"
            ],
            [
             0.4444444444444444,
             "#bd3786"
            ],
            [
             0.5555555555555556,
             "#d8576b"
            ],
            [
             0.6666666666666666,
             "#ed7953"
            ],
            [
             0.7777777777777778,
             "#fb9f3a"
            ],
            [
             0.8888888888888888,
             "#fdca26"
            ],
            [
             1,
             "#f0f921"
            ]
           ],
           "sequentialminus": [
            [
             0,
             "#0d0887"
            ],
            [
             0.1111111111111111,
             "#46039f"
            ],
            [
             0.2222222222222222,
             "#7201a8"
            ],
            [
             0.3333333333333333,
             "#9c179e"
            ],
            [
             0.4444444444444444,
             "#bd3786"
            ],
            [
             0.5555555555555556,
             "#d8576b"
            ],
            [
             0.6666666666666666,
             "#ed7953"
            ],
            [
             0.7777777777777778,
             "#fb9f3a"
            ],
            [
             0.8888888888888888,
             "#fdca26"
            ],
            [
             1,
             "#f0f921"
            ]
           ]
          },
          "colorway": [
           "#636efa",
           "#EF553B",
           "#00cc96",
           "#ab63fa",
           "#FFA15A",
           "#19d3f3",
           "#FF6692",
           "#B6E880",
           "#FF97FF",
           "#FECB52"
          ],
          "font": {
           "color": "#2a3f5f"
          },
          "geo": {
           "bgcolor": "white",
           "lakecolor": "white",
           "landcolor": "#E5ECF6",
           "showlakes": true,
           "showland": true,
           "subunitcolor": "white"
          },
          "hoverlabel": {
           "align": "left"
          },
          "hovermode": "closest",
          "mapbox": {
           "style": "light"
          },
          "paper_bgcolor": "white",
          "plot_bgcolor": "#E5ECF6",
          "polar": {
           "angularaxis": {
            "gridcolor": "white",
            "linecolor": "white",
            "ticks": ""
           },
           "bgcolor": "#E5ECF6",
           "radialaxis": {
            "gridcolor": "white",
            "linecolor": "white",
            "ticks": ""
           }
          },
          "scene": {
           "xaxis": {
            "backgroundcolor": "#E5ECF6",
            "gridcolor": "white",
            "gridwidth": 2,
            "linecolor": "white",
            "showbackground": true,
            "ticks": "",
            "zerolinecolor": "white"
           },
           "yaxis": {
            "backgroundcolor": "#E5ECF6",
            "gridcolor": "white",
            "gridwidth": 2,
            "linecolor": "white",
            "showbackground": true,
            "ticks": "",
            "zerolinecolor": "white"
           },
           "zaxis": {
            "backgroundcolor": "#E5ECF6",
            "gridcolor": "white",
            "gridwidth": 2,
            "linecolor": "white",
            "showbackground": true,
            "ticks": "",
            "zerolinecolor": "white"
           }
          },
          "shapedefaults": {
           "line": {
            "color": "#2a3f5f"
           }
          },
          "ternary": {
           "aaxis": {
            "gridcolor": "white",
            "linecolor": "white",
            "ticks": ""
           },
           "baxis": {
            "gridcolor": "white",
            "linecolor": "white",
            "ticks": ""
           },
           "bgcolor": "#E5ECF6",
           "caxis": {
            "gridcolor": "white",
            "linecolor": "white",
            "ticks": ""
           }
          },
          "title": {
           "x": 0.05
          },
          "xaxis": {
           "automargin": true,
           "gridcolor": "white",
           "linecolor": "white",
           "ticks": "",
           "title": {
            "standoff": 15
           },
           "zerolinecolor": "white",
           "zerolinewidth": 2
          },
          "yaxis": {
           "automargin": true,
           "gridcolor": "white",
           "linecolor": "white",
           "ticks": "",
           "title": {
            "standoff": 15
           },
           "zerolinecolor": "white",
           "zerolinewidth": 2
          }
         }
        },
        "title": {
         "text": "Single Entity Time Series LP: IRFs of Investment"
        },
        "xaxis": {
         "anchor": "y",
         "domain": [
          0,
          0.45
         ]
        },
        "xaxis2": {
         "anchor": "y2",
         "domain": [
          0.55,
          1
         ]
        },
        "xaxis3": {
         "anchor": "y3",
         "domain": [
          0,
          0.45
         ]
        },
        "xaxis4": {
         "anchor": "y4",
         "domain": [
          0.55,
          1
         ]
        },
        "yaxis": {
         "anchor": "x",
         "domain": [
          0.625,
          1
         ]
        },
        "yaxis2": {
         "anchor": "x2",
         "domain": [
          0.625,
          1
         ]
        },
        "yaxis3": {
         "anchor": "x3",
         "domain": [
          0,
          0.375
         ]
        },
        "yaxis4": {
         "anchor": "x4",
         "domain": [
          0,
          0.375
         ]
        }
       }
      }
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from statsmodels.datasets import grunfeld\n",
    "df = grunfeld.load_pandas().data # import the Grunfeld investment data set\n",
    "df = df[df['firm'] == 'General Motors'] # keep only one entity (as an example of a single entity time series setting)\n",
    "df = df.set_index(['year']) # set time variable as index\n",
    "\n",
    "endog = ['invest', 'value', 'capital'] # cholesky ordering: invest --> value --> capital\n",
    "response = endog.copy() # estimate the responses of all variables to shocks from all variables\n",
    "irf_horizon = 8 # estimate IRFs up to 8 periods ahead\n",
    "opt_lags = 2 # include 2 lags in the local projections model\n",
    "opt_cov = 'robust' # HAC standard errors\n",
    "opt_ci = 0.95 # 95% confidence intervals\n",
    "\n",
    "# Use TimeSeriesLP for the single entity case\n",
    "irf = lp.TimeSeriesLP(data=df, # input dataframe\n",
    "                      Y=endog, # variables in the model\n",
    "                      response=response, # variables whose IRFs should be estimated\n",
    "                      horizon=irf_horizon, # estimation horizon of IRFs\n",
    "                      lags=opt_lags, # lags in the model\n",
    "                      newey_lags=2, # maximum lags when estimating Newey-West standard errors\n",
    "                      ci_width=opt_ci # width of confidence band\n",
    "                      )\n",
    "irfplot = lp.IRFPlot(irf=irf, # take output from the estimated model\n",
    "                     response=['invest'], # plot only response of invest ...\n",
    "                     shock=endog, # ... to shocks from all variables\n",
    "                     n_columns=2, # max 2 columns in the figure\n",
    "                     n_rows=2, # max 2 rows in the figure\n",
    "                     maintitle='Single Entity Time Series LP: IRFs of Investment', # self-defined title of the IRF plot\n",
    "                     show_fig=True, # display figure (from plotly)\n",
    "                     save_pic=False # don't save any figures on local drive\n",
    "                     )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "cc764808",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".venv",
   "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": "3.12.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}