Amazing-Python-Scripts

1
{
2
  "nbformat": 4,
3
  "nbformat_minor": 0,
4
  "metadata": {
5
    "colab": {
6
      "provenance": []
7
    },
8
    "kernelspec": {
9
      "name": "python3",
10
      "display_name": "Python 3"
11
    },
12
    "language_info": {
13
      "name": "python"
14
    }
15
  },
16
  "cells": [
17
    {
18
      "cell_type": "code",
19
      "source": [
20
        "!pip install catboost"
21
      ],
22
      "metadata": {
23
        "colab": {
24
          "base_uri": "https://localhost:8080/"
25
        },
26
        "id": "fjtCd9-2YJtA",
27
        "outputId": "5f63d4c3-48c2-4cb4-9fd7-d026c7c7ddb3"
28
      },
29
      "execution_count": 44,
30
      "outputs": [
31
        {
32
          "output_type": "stream",
33
          "name": "stdout",
34
          "text": [
35
            "Requirement already satisfied: catboost in /usr/local/lib/python3.10/dist-packages (1.2)\n",
36
            "Requirement already satisfied: graphviz in /usr/local/lib/python3.10/dist-packages (from catboost) (0.20.1)\n",
37
            "Requirement already satisfied: matplotlib in /usr/local/lib/python3.10/dist-packages (from catboost) (3.7.1)\n",
38
            "Requirement already satisfied: numpy>=1.16.0 in /usr/local/lib/python3.10/dist-packages (from catboost) (1.23.5)\n",
39
            "Requirement already satisfied: pandas>=0.24 in /usr/local/lib/python3.10/dist-packages (from catboost) (1.5.3)\n",
40
            "Requirement already satisfied: scipy in /usr/local/lib/python3.10/dist-packages (from catboost) (1.10.1)\n",
41
            "Requirement already satisfied: plotly in /usr/local/lib/python3.10/dist-packages (from catboost) (5.13.1)\n",
42
            "Requirement already satisfied: six in /usr/local/lib/python3.10/dist-packages (from catboost) (1.16.0)\n",
43
            "Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.10/dist-packages (from pandas>=0.24->catboost) (2.8.2)\n",
44
            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas>=0.24->catboost) (2022.7.1)\n",
45
            "Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->catboost) (1.1.0)\n",
46
            "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.10/dist-packages (from matplotlib->catboost) (0.11.0)\n",
47
            "Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib->catboost) (4.42.0)\n",
48
            "Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->catboost) (1.4.4)\n",
49
            "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib->catboost) (23.1)\n",
50
            "Requirement already satisfied: pillow>=6.2.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib->catboost) (9.4.0)\n",
51
            "Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->catboost) (3.1.1)\n",
52
            "Requirement already satisfied: tenacity>=6.2.0 in /usr/local/lib/python3.10/dist-packages (from plotly->catboost) (8.2.2)\n"
53
          ]
54
        }
55
      ]
56
    },
57
    {
58
      "cell_type": "code",
59
      "source": [
60
        "import pandas as pd\n",
61
        "import numpy as np\n",
62
        "from catboost import CatBoostRegressor\n",
63
        "from sklearn.model_selection import train_test_split\n",
64
        "from sklearn.metrics import mean_squared_error\n",
65
        "import matplotlib.pyplot as plt\n",
66
        "import seaborn as sns"
67
      ],
68
      "metadata": {
69
        "id": "lCEz3mIoXx6Y"
70
      },
71
      "execution_count": 45,
72
      "outputs": []
73
    },
74
    {
75
      "cell_type": "code",
76
      "source": [
77
        "data_url = \"http://lib.stat.cmu.edu/datasets/boston\"\n",
78
        "raw_df = pd.read_csv(data_url, sep=\"\\s+\", skiprows=22, header=None)\n",
79
        "df = np.hstack([raw_df.values[::2, :], raw_df.values[1::2, :2]])\n",
80
        "target = raw_df.values[1::2, 2]"
81
      ],
82
      "metadata": {
83
        "id": "PRd11JRTX1Qn"
84
      },
85
      "execution_count": 46,
86
      "outputs": []
87
    },
88
    {
89
      "cell_type": "code",
90
      "source": [
91
        "df.shape"
92
      ],
93
      "metadata": {
94
        "colab": {
95
          "base_uri": "https://localhost:8080/"
96
        },
97
        "id": "-EvoYWuIaCwk",
98
        "outputId": "5bef08c0-ae53-4598-9672-6b97cce059f7"
99
      },
100
      "execution_count": 47,
101
      "outputs": [
102
        {
103
          "output_type": "execute_result",
104
          "data": {
105
            "text/plain": [
106
              "(506, 13)"
107
            ]
108
          },
109
          "metadata": {},
110
          "execution_count": 47
111
        }
112
      ]
113
    },
114
    {
115
      "cell_type": "code",
116
      "source": [
117
        "df.dtype"
118
      ],
119
      "metadata": {
120
        "colab": {
121
          "base_uri": "https://localhost:8080/"
122
        },
123
        "id": "RenipdVGaaf7",
124
        "outputId": "fa6ed386-1042-4399-857b-825ee627c4ad"
125
      },
126
      "execution_count": 48,
127
      "outputs": [
128
        {
129
          "output_type": "execute_result",
130
          "data": {
131
            "text/plain": [
132
              "dtype('float64')"
133
            ]
134
          },
135
          "metadata": {},
136
          "execution_count": 48
137
        }
138
      ]
139
    },
140
    {
141
      "cell_type": "code",
142
      "source": [
143
        "X_train, X_test, y_train, y_test = train_test_split(df, target, test_size=0.2, random_state=42)\n"
144
      ],
145
      "metadata": {
146
        "id": "e-GxZmfEYm1j"
147
      },
148
      "execution_count": 49,
149
      "outputs": []
150
    },
151
    {
152
      "cell_type": "code",
153
      "source": [
154
        "model = CatBoostRegressor(iterations=1000, depth=8, learning_rate=0.05, loss_function='RMSE',\n",
155
        "                           random_seed=42, l2_leaf_reg=1)"
156
      ],
157
      "metadata": {
158
        "id": "G0x4Y6z6Xgun"
159
      },
160
      "execution_count": 50,
161
      "outputs": []
162
    },
163
    {
164
      "cell_type": "code",
165
      "source": [
166
        "model.fit(X_train, y_train, verbose=100, eval_set=(X_test, y_test), early_stopping_rounds=50)"
167
      ],
168
      "metadata": {
169
        "colab": {
170
          "base_uri": "https://localhost:8080/"
171
        },
172
        "id": "-jD7L2X8XkEf",
173
        "outputId": "da585195-5991-40a8-bb26-2304c756c1c8"
174
      },
175
      "execution_count": 51,
176
      "outputs": [
177
        {
178
          "output_type": "stream",
179
          "name": "stdout",
180
          "text": [
181
            "0:\tlearn: 9.0020476\ttest: 8.4095123\tbest: 8.4095123 (0)\ttotal: 13.6ms\tremaining: 13.6s\n",
182
            "100:\tlearn: 1.7496020\ttest: 3.2646698\tbest: 3.2646698 (100)\ttotal: 601ms\tremaining: 5.35s\n",
183
            "200:\tlearn: 0.9726505\ttest: 3.0362205\tbest: 3.0362205 (200)\ttotal: 1.44s\tremaining: 5.74s\n",
184
            "300:\tlearn: 0.5818381\ttest: 2.9857265\tbest: 2.9857265 (300)\ttotal: 2.07s\tremaining: 4.82s\n",
185
            "Stopped by overfitting detector  (50 iterations wait)\n",
186
            "\n",
187
            "bestTest = 2.980601834\n",
188
            "bestIteration = 314\n",
189
            "\n",
190
            "Shrink model to first 315 iterations.\n"
191
          ]
192
        },
193
        {
194
          "output_type": "execute_result",
195
          "data": {
196
            "text/plain": [
197
              "<catboost.core.CatBoostRegressor at 0x7bb8f2b08a30>"
198
            ]
199
          },
200
          "metadata": {},
201
          "execution_count": 51
202
        }
203
      ]
204
    },
205
    {
206
      "cell_type": "code",
207
      "source": [
208
        "y_pred = model.predict(X_test)"
209
      ],
210
      "metadata": {
211
        "id": "IB6QbK9xXnZa"
212
      },
213
      "execution_count": 52,
214
      "outputs": []
215
    },
216
    {
217
      "cell_type": "code",
218
      "source": [
219
        "y_pred"
220
      ],
221
      "metadata": {
222
        "colab": {
223
          "base_uri": "https://localhost:8080/"
224
        },
225
        "id": "N7JUDoILYt7y",
226
        "outputId": "adfc6754-2010-403e-ea8d-6f6a69eb0cb4"
227
      },
228
      "execution_count": 53,
229
      "outputs": [
230
        {
231
          "output_type": "execute_result",
232
          "data": {
233
            "text/plain": [
234
              "array([24.61951657, 29.79612399, 16.10995832, 23.90291017, 16.16479168,\n",
235
              "       21.96620609, 19.41533747, 14.85955243, 21.19257177, 20.46921239,\n",
236
              "       21.25112561, 19.42673204,  7.80799285, 21.73588536, 19.43968294,\n",
237
              "       23.57411435, 19.75321019,  9.37650806, 43.76299704, 14.28887094,\n",
238
              "       24.95484852, 25.1917329 , 13.33651447, 21.58680042, 14.40969043,\n",
239
              "       16.09083103, 22.30573291, 13.90180886, 20.20803133, 20.63283845,\n",
240
              "       20.95367068, 23.56590007, 21.37815241, 22.03890376, 15.11999286,\n",
241
              "       16.49008812, 35.52581167, 18.52302   , 22.9998298 , 23.24337579,\n",
242
              "       18.09930231, 29.42451049, 42.64947385, 19.48418839, 22.93099906,\n",
243
              "       13.81754368, 14.22441547, 24.09969962, 19.20374409, 26.05365903,\n",
244
              "       22.53293348, 36.45414434, 18.23660788, 24.90167829, 45.03091217,\n",
245
              "       22.50490127, 14.2964888 , 32.60026588, 22.04437289, 18.49242439,\n",
246
              "       23.55633875, 35.51997742, 29.5665242 , 18.17335086, 23.85466921,\n",
247
              "       18.37995176, 13.73776741, 23.64060698, 28.58094162, 14.67940568,\n",
248
              "       20.55768573, 24.54235025, 10.55305368, 20.77955652, 22.48437537,\n",
249
              "        7.04140151, 20.37419805, 43.59246225, 11.52873761, 10.56385587,\n",
250
              "       21.70285593, 13.76140818, 20.07970065, 10.45062855, 20.04264377,\n",
251
              "       27.82619285, 16.36425016, 23.43126727, 24.48350906, 18.47783108,\n",
252
              "       22.5117491 ,  9.62743311, 19.41891295, 18.22799834, 29.42397234,\n",
253
              "       19.59499851, 30.82681357, 11.09794744, 11.96605782, 15.49374648,\n",
254
              "       20.45985914, 24.01940107])"
255
            ]
256
          },
257
          "metadata": {},
258
          "execution_count": 53
259
        }
260
      ]
261
    },
262
    {
263
      "cell_type": "code",
264
      "source": [
265
        "plt.figure(figsize=(10, 6))\n",
266
        "sns.regplot(x=y_test, y=y_pred, scatter_kws={'s': 20})\n",
267
        "plt.title(\"Regression Plot: True Values vs Predicted Values\")"
268
      ],
269
      "metadata": {
270
        "colab": {
271
          "base_uri": "https://localhost:8080/",
272
          "height": 562
273
        },
274
        "id": "ekdHHCKOZXuu",
275
        "outputId": "ee2a9b75-a932-401b-92a9-858bea4eae7d"
276
      },
277
      "execution_count": 54,
278
      "outputs": [
279
        {
280
          "output_type": "execute_result",
281
          "data": {
282
            "text/plain": [
283
              "Text(0.5, 1.0, 'Regression Plot: True Values vs Predicted Values')"
284
            ]
285
          },
286
          "metadata": {},
287
          "execution_count": 54
288
        },
289
        {
290
          "output_type": "display_data",
291
          "data": {
292
            "text/plain": [
293
              "<Figure size 1000x600 with 1 Axes>"
294
            ],
295
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAzYAAAIQCAYAAABTzfveAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/bCgiHAAAACXBIWXMAAA9hAAAPYQGoP6dpAAChI0lEQVR4nOzdeXzU9Z0/8Nf3mDOZmSQkEEggidyHR0VBLvFABa9S71sRtu2qra7d+qvd7bbW7rrabt3ubrW2Alot9cBqrQrWE+RWFBVFQEw4Agk55575Xp/fH0PGTA5IQpKZSV7Px6OPR/l+vzPfz4yTMC8+n/f7IwkhBIiIiIiIiLKYnO4BEBERERERHS8GGyIiIiIiynoMNkRERERElPUYbIiIiIiIKOsx2BARERERUdZjsCEiIiIioqzHYENERERERFmPwYaIiIiIiLIegw0REREREWU9Bhsiyhg/+9nPIElSuodxVOXl5bjlllvSPYxB5ayzzsJZZ52V7mEMWpIk4Wc/+1nyz0888QQkSUJVVVXaxtRW2zH2F/4+IMosDDZEGaDli0LL/1RVRUlJCW655RZUV1ene3iDQuv3X5ZljBgxAueffz7efffdXnn+gwcP4mc/+xm2bdvWo8e/++67KWM82v/S5S9/+QskScLjjz/e6TVvvPEGJEnC//zP//TjyLJXS9hv+Z/b7cakSZPwr//6rwgEAukeXresWLEC//3f/52We//617+GJEl48803O73mD3/4AyRJwssvv9yPIyOi3qSmewBE9LWf//znqKioQCwWw6ZNm/DEE09g3bp12L59O5xOZ7qH1+f+9V//FT/60Y/Sdv/zzjsPN910E4QQqKysxCOPPIJzzjkHr776KhYsWHBcz33w4EHcd999KC8vxymnnNLtx0+cOBFPPfVUyrF7770Xubm5+Jd/+ZfjGltvueiii+Dz+bBixQosWbKkw2tWrFgBRVFwzTXX9PPostujjz6K3NxchEIh/P3vf8e///u/4+2338b69ev7PczeeOONuOaaa+BwOLr1uBUrVmD79u246667+mZgR3HNNdfghz/8IVasWIF58+Z1eM2KFSswZMiQ4/5ZJ6L0YbAhyiALFizAaaedBgBYsmQJCgsL8eCDD+Lll1/GVVdd1W/jEEIgFovB5XL12z0BQFVVqGr6fi2NGzcON9xwQ/LP3/rWt3DSSSfhv//7v9P+ZWfYsGEpYwOA//zP/0RhYWG7461ZlgVN0/olGDscDlxxxRVYvnw5Dh48iBEjRqScj8ViePHFF3Heeedh6NChfT6egeSKK65AYWEhAOC73/0uLr/8cvzlL3/Bpk2bMGPGjA4fE4lE4Ha7e30siqJAUZRef96+NGLECJx99tn4y1/+gkcffbRdKKuursbatWvx7W9/GzabLU2jJKLjxaVoRBlszpw5AIA9e/akHP/iiy9wxRVXoKCgAE6nE6eddlqHyyc++eQTzJ07Fy6XC6WlpfjFL36B5cuXt1sfX15ejosvvhivv/46TjvtNLhcLjz22GMAgObmZtx1110YOXIkHA4HxowZgwcffBCWZaXc65lnnsHUqVPh8Xjg9Xpx4okn4je/+U3yvK7ruO+++zB27Fg4nU4MGTIEs2fPxhtvvJG8pqMaG8MwcP/992P06NFwOBwoLy/Hj3/8Y8Tj8ZTrWl7DunXrMG3aNDidTpxwwgn44x//2I13PNWJJ56IwsJCVFZWHvW6r776CldeeSUKCgrgdrtxxhln4NVXX02ef/fdd3H66acDABYtWpRcVvTEE08ASHwB/eKLL1BfX9/jsbaQJAl33HEH/vSnP2Hy5MlwOBxYvXp1cilb26V1VVVVKWNp0dXPWFs33HADLMvCM8880+7cq6++Cr/fj+uvvx4AsHz5cpxzzjkYOnQoHA4HJk2ahEcfffSY9+isxqOz17h582bMnz8fPp8Pbrcbc+fOxfr161OuCQaDuOuuu1BeXg6Hw4GhQ4fivPPOw4cfftjpOFauXAlJkrBmzZp25x577DFIkoTt27cDAGpqarBo0SKUlpbC4XBg+PDh+OY3v9njOpVzzjkHAJKfzbPOOgtTpkzB1q1bceaZZ8LtduPHP/4xACAej+OnP/0pxowZA4fDgZEjR+Kee+5p9zMUj8fxT//0TygqKoLH48Gll16KAwcOtLt3Z+//qlWrMHfu3OTvgNNPPx0rVqxIju/VV1/F3r17k5//8vLylHv35hg7csMNN8Dv96f8bLZ45plnYFlW8rP5q1/9CjNnzsSQIUPgcrkwdepUrFy58pj36KxO8Gjv2Zw5c5CTkwOPx4OLLroIn332Wco1vf3ZIRrIOGNDlMFa/uLKz89PHvvss88wa9YslJSU4Ec/+hFycnLw3HPPYeHChXjhhRfwrW99C0DiXyDPPvtsSJKEe++9Fzk5OXj88cc7XT6yc+dOXHvttfjOd76Df/iHf8D48eMRiUQwd+5cVFdX4zvf+Q5GjRqFDRs24N5778WhQ4eS6+XfeOMNXHvttTj33HPx4IMPAgB27NiB9evX48477wSQ+Av/gQcewJIlSzBt2jQEAgF88MEH+PDDD3Heeed1+h4sWbIETz75JK644gr84Ac/wObNm/HAAw9gx44dePHFF1Ou/fLLL3HFFVdg8eLFuPnmm7Fs2TLccsstmDp1KiZPntzt97+pqQlNTU0YM2ZMp9fU1tZi5syZiEQi+P73v48hQ4bgySefxKWXXoqVK1fiW9/6FiZOnIif//zn+Ld/+zd8+9vfTgbWmTNnAgC2bNmCs88+Gz/96U97pQD67bffxnPPPYc77rgDhYWFKC8vR3Nzc5cf39XPWEfOPPNMlJaWYsWKFbj77rtTzq1YsQJutxsLFy4EkFheNXnyZFx66aVQVRV/+9vfcNttt8GyLNx+++09eentvP3221iwYAGmTp2Kn/70p5BlORmo3nvvPUybNg1AYhZk5cqVuOOOOzBp0iQ0NDRg3bp12LFjB0499dQOn/uiiy5Cbm4unnvuOcydOzfl3LPPPovJkydjypQpAIDLL78cn332Gb73ve+hvLwchw8fxhtvvIF9+/alfMHvqpZ/7BgyZEjyWENDAxYsWIBrrrkGN9xwA4YNGwbLsnDppZdi3bp1+Pa3v42JEyfi008/xcMPP4xdu3bhpZdeSj5+yZIlePrpp3Hddddh5syZePvtt3HRRRd1aTxPPPEEbr31VkyePBn33nsv8vLy8NFHH2H16tW47rrr8C//8i/w+/04cOAAHn74YQBAbm4uAPTbGC+77DL84z/+I1asWIHLLrss5dyKFStQVlaGWbNmAQB+85vf4NJLL8X1118PTdPwzDPP4Morr8Qrr7zS5fsdy1NPPYWbb74ZF1xwAR588EFEIhE8+uijmD17Nj766KPk56K3PztEA5ogorRbvny5ACDefPNNUVdXJ/bv3y9WrlwpioqKhMPhEPv3709ee+6554oTTzxRxGKx5DHLssTMmTPF2LFjk8e+973vCUmSxEcffZQ81tDQIAoKCgQAUVlZmTxeVlYmAIjVq1enjOv+++8XOTk5YteuXSnHf/SjHwlFUcS+ffuEEELceeedwuv1CsMwOn2NJ598srjooouO+j789Kc/Fa1/LW3btk0AEEuWLEm57p//+Z8FAPH222+3ew1r165NHjt8+LBwOBziBz/4wVHvK4QQAMTixYtFXV2dOHz4sNi8ebM499xzBQDxX//1Xyn3ufnmm5N/vuuuuwQA8d577yWPBYNBUVFRIcrLy4VpmkIIId5//30BQCxfvrzdvd955x0BQPz0pz895jhbmzx5spg7d2671yHLsvjss886vMc777yTcryysrLduLr6GevMD3/4QwFA7Ny5M3nM7/cLp9Mprr322uSxSCTS7rEXXHCBOOGEE1KOzZ07N+V1tvy8tP4Md/QaLcsSY8eOFRdccIGwLCvlvhUVFeK8885LHvP5fOL2228/5mtr69prrxVDhw5N+ewfOnRIyLIsfv7znwshhGhqahIAxC9/+ctuP3/Lz8TOnTtFXV2dqKysFI899phwOBxi2LBhIhwOCyES7xEA8bvf/S7l8U899ZSQZTnl8ymEEL/73e8EALF+/XohxNc/a7fddlvKddddd127z2bb97+5uVl4PB4xffp0EY1GUx7f+n2/6KKLRFlZWbvX2Bdj7MyVV14pnE6n8Pv9yWNffPGFACDuvffe5LG2n01N08SUKVPEOeeck3K87e+Dtr/DWrR9z4LBoMjLyxP/8A//kHJdTU2N8Pl8yePH89khGoy4FI0og8ybNw9FRUUYOXIkrrjiCuTk5ODll19GaWkpAKCxsRFvv/02rrrqKgSDQdTX16O+vh4NDQ244IILsHv37mQXtdWrV2PGjBkpheoFBQXJpRZtVVRU4IILLkg59vzzz2POnDnIz89P3qu+vh7z5s2DaZpYu3YtACAvLw/hcDhlWVlbeXl5+Oyzz7B79+4uvx+vvfYaALT7l/8f/OAHANBuScmkSZOSsyEAUFRUhPHjx+Orr77q0v2WLl2KoqIiDB06FNOnT8f69etx9913H7XY+bXXXsO0adMwe/bs5LHc3Fx8+9vfRlVVFT7//PNj3vess86CEKLX2tXOnTsXkyZN6tFju/MZ60xLzU/LMiQAeOGFFxCLxVI+f61ruPx+P+rr6zF37lx89dVX8Pv9PRp/a9u2bcPu3btx3XXXoaGhIflawuEwzj33XKxduza5pDIvLw+bN2/GwYMHu3WPq6++GocPH05Z/rZy5UpYloWrr746+TrtdjveffddNDU19ei1jB8/HkVFRaioqMB3vvMdjBkzBq+++mpKDY3D4cCiRYtSHvf8889j4sSJmDBhQsrPcMtStnfeeQfA1z9r3//+91Me35VC/zfeeAPBYBA/+tGP2tVydaWxQX+MscUNN9yAWCyGv/zlL8ljLZ/Tzj6bTU1N8Pv9mDNnzlGXJnbHG2+8gebmZlx77bUpr1lRFEyfPj35mnvjs0M0mHApGlEG+e1vf4tx48bB7/dj2bJlWLt2bcrSsS+//BJCCPzkJz/BT37ykw6f4/DhwygpKcHevXs7LCrubFlVRUVFu2O7d+/GJ598gqKiok7vBQC33XYbnnvuOSxYsAAlJSU4//zzcdVVV2H+/PnJa3/+85/jm9/8JsaNG4cpU6Zg/vz5uPHGG3HSSSd1+n7s3bsXsiy3G3NxcTHy8vKwd+/elOOjRo1q9xz5+fld/kLwzW9+E3fccQckSYLH48HkyZORk5Nz1Mfs3bsX06dPb3d84sSJyfMty5H6S0f/LbuqO5+xzpx00kmYMmUK/vznPyfD2ooVK1BYWJgSntevX4+f/vSn2LhxIyKRSMpz+P1++Hy+Hr8OAMkQffPNN3d6jd/vR35+Ph566CHcfPPNGDlyJKZOnYoLL7wQN910E0444YSj3qOldufZZ5/FueeeCyCxDO2UU07BuHHjACQCx4MPPogf/OAHGDZsGM444wxcfPHFuOmmm1BcXNyl1/LCCy/A6/XCZrOhtLQUo0ePbndNSUkJ7HZ7u/dgx44dx/wZbvlZa/u848ePP+bYWpbF9fRz3h9jbLFgwQIUFBRgxYoVyf1n/vznP+Pkk09OWa76yiuv4Be/+AW2bduWUufTWx3oWj6bLeGtLa/XC6B3PjtEgwmDDVEGmTZtWrIr2sKFCzF79mxcd9112LlzJ3Jzc5P/uvzP//zP7WZXWhytHuRoOuqAZlkWzjvvPNxzzz0dPqbli9vQoUOxbds2vP7661i1ahVWrVqF5cuX46abbsKTTz4JIFF7sWfPHvz1r3/F3//+dzz++ON4+OGH8bvf/a7T1sAtuvplorNOTUKILj2+tLS001aw2aSj/5advYemaab8ubc+YzfccAN+9KMf4YMPPkBpaSneeecdfOc730l2vduzZw/OPfdcTJgwAb/+9a8xcuRI2O12vPbaa3j44YfbNac4ntfyy1/+stMW2y11HldddRXmzJmDF198EX//+9/xy1/+Eg8++CD+8pe/HLUjnsPhwMKFC/Hiiy/ikUceQW1tLdavX4//+I//SLnurrvuwiWXXIKXXnoJr7/+On7yk5/ggQcewNtvv41vfOMbnT5/izPPPDPZFa0znf0Mn3jiifj1r3/d4WNGjhx5zHv3tf4co81mw1VXXYU//OEPqK2txb59+7B792489NBDyWvee+89XHrppTjzzDPxyCOPYPjw4bDZbFi+fHnKLGRHuvvZfOqppzoMKK27Qx7vZ4doMGGwIcpQiqLggQcewNlnn43/+7//w49+9KPkvx7bbLZjfgEvKyvDl19+2e54R8c6M3r0aIRCoS592bfb7bjkkktwySWXwLIs3HbbbXjsscfwk5/8JPlFuKCgAIsWLcKiRYsQCoVw5pln4mc/+1mnwaasrAyWZWH37t3JGRAgUbDf3NyMsrKyLr+WvlJWVoadO3e2O/7FF18kzwO99y+9PdXSgKJtE4G2s17d+YwdzbXXXot77703WZRtmmbKUp+//e1viMfjePnll1Nm2lqW4BxNV19Ly7/se73eLr2W4cOH47bbbsNtt92Gw4cP49RTT8W///u/H7PV99VXX40nn3wSb731Fnbs2AEhRHIZWtvx/OAHP8APfvAD7N69G6eccgr+67/+C08//fQxx9ZTo0ePxscff4xzzz33qJ/Blp+1PXv2pMyAdPTZ7ugeALB9+/ajht7O7t8fY2zt+uuvx+9+9zs8++yzqKyshCRJuPbaa5PnX3jhBTidTrz++uspM+bLly8/5nO3/mzm5eUlj3f22Rw6dGiXPpvp+OwQZSPW2BBlsLPOOgvTpk3Df//3fyMWi2Ho0KE466yz8Nhjj+HQoUPtrq+rq0v+/wsuuAAbN25M2em+sbERf/rTn7p8/6uuugobN27E66+/3u5cc3MzDMMAkOjG1Josy8klZi3LONpek5ubizFjxrRr59rahRdeCADtditv+Zfd3upOdDwuvPBCbNmyBRs3bkweC4fD+P3vf4/y8vJkrUvLkraOupP1ZrvnzpSVlUFRlGRdVItHHnkk5c/d+YwdzahRozBnzhw8++yzePrpp1FRUZHsAgd8PbvWejbN7/d36ctjy5fC1q/FNE38/ve/T7lu6tSpGD16NH71q18hFAp1+lpM02xX0zN06FCMGDHiqJ/PFvPmzUNBQQGeffZZPPvss5g2bVrKcsBIJIJYLNbuNXg8ni49//G46qqrUF1djT/84Q/tzkWjUYTDYQBIhrf/+Z//Sbmm7c9eR84//3x4PB488MAD7V5n6/++OTk5HdZO9ccYW5s1axbKy8vx9NNP49lnn8XcuXOTdYxA4rMpSVLKLEtVVVVKd7bOdPTZDIfDyZnrFhdccAG8Xi/+4z/+A7qut3uels9mOj87RNmIMzZEGe6HP/whrrzySjzxxBP47ne/i9/+9reYPXs2TjzxRPzDP/wDTjjhBNTW1mLjxo04cOAAPv74YwDAPffcg6effhrnnXcevve97yXbPY8aNQqNjY1dmkH44Q9/iJdffhkXX3xxsm1yOBzGp59+ipUrV6KqqgqFhYVYsmQJGhsbcc4556C0tBR79+7F//7v/+KUU05JzrRMmjQJZ511FqZOnYqCggJ88MEHyfa6nTn55JNx88034/e//z2am5sxd+5cbNmyBU8++SQWLlyIs88+u3fe5OPwox/9CH/+85+xYMECfP/730dBQQGefPJJVFZW4oUXXoAsJ/79aPTo0cjLy8Pvfvc7eDwe5OTkYPr06aioqOj1ds8d8fl8uPLKK/G///u/kCQJo0ePxiuvvJKsX2itq5+xY7nhhhvw7W9/GwcPHsS//Mu/pJw7//zzk7N83/nOdxAKhfCHP/wBQ4cO7TBQtTZ58mScccYZuPfee9HY2IiCggI888wzyaDdQpZlPP7441iwYAEmT56MRYsWoaSkBNXV1XjnnXfg9Xrxt7/9DcFgEKWlpbjiiitw8sknIzc3F2+++Sbef/99/Nd//dcxX6fNZsNll12GZ555BuFwGL/61a9Szu/atQvnnnsurrrqKkyaNAmqquLFF19EbW0trrnmmi69lz1144034rnnnsN3v/tdvPPOO5g1axZM08QXX3yB5557Lrl31SmnnIJrr70WjzzyCPx+P2bOnIm33nqrSzO8Xq8XDz/8MJYsWYLTTz8d1113HfLz8/Hxxx8jEokkv9RPnToVzz77LO6++26cfvrpyM3NxSWXXNIvY2xNkiRcd911yeWCP//5z1POX3TRRfj1r3+N+fPn47rrrsPhw4fx29/+FmPGjMEnn3xy1Oc+//zzMWrUKCxevBg//OEPoSgKli1bhqKiIuzbty/lPXv00Udx44034tRTT8U111yTvObVV1/FrFmz8H//939p/ewQZaU0dmQjoiNaWoG+//777c6ZpilGjx4tRo8enWwpu2fPHnHTTTeJ4uJiYbPZRElJibj44ovFypUrUx770UcfiTlz5giHwyFKS0vFAw88IP7nf/5HABA1NTXJ68rKyjptxRwMBsW9994rxowZI+x2uygsLBQzZ84Uv/rVr4SmaUIIIVauXCnOP/98MXToUGG328WoUaPEd77zHXHo0KHk8/ziF78Q06ZNE3l5ecLlcokJEyaIf//3f08+hxAdt0rVdV3cd999oqKiQthsNjFy5Ehx7733prQiPtpraNsquDMAutTut217VyES/z2uuOIKkZeXJ5xOp5g2bZp45ZVX2j32r3/9q5g0aZJQVTWlxXJvt3vu7HXU1dWJyy+/XLjdbpGfny++853viO3bt3fYhrqrn7GjaWxsFA6HQwAQn3/+ebvzL7/8sjjppJOE0+kU5eXl4sEHHxTLli1r18q5o/+Ge/bsEfPmzUu2Pf7xj38s3njjjQ5bWn/00UfisssuE0OGDBEOh0OUlZWJq666Srz11ltCCCHi8bj44Q9/KE4++WTh8XhETk6OOPnkk8UjjzzS5dfacm9JklLaswshRH19vbj99tvFhAkTRE5OjvD5fGL69OniueeeO+bztvxM1NXVHfW6uXPnismTJ3d4TtM08eCDD4rJkycLh8Mh8vPzxdSpU8V9992X0vY4Go2K73//+2LIkCEiJydHXHLJJWL//v3HbPfc4uWXXxYzZ84ULpdLeL1eMW3aNPHnP/85eT4UConrrrtO5OXlCQAprZ97e4zH8tlnnwkAwuFwiKampnbnly5dKsaOHSscDoeYMGGCWL58eYe/nzr6fbB161Yxffr05O/CX//610dtUX7BBRcIn88nnE6nGD16tLjlllvEBx98IIQ4vs8O0WAkCdHFqloiGhDuuusuPPbYYwiFQp0W2xMRERFlG9bYEA1g0Wg05c8NDQ146qmnMHv2bIYaIiIiGlBYY0M0gM2YMQNnnXUWJk6ciNraWixduhSBQKDT/UmIiIiIshWDDdEAduGFF2LlypX4/e9/D0mScOqpp2Lp0qU488wz0z00IiIiol7FGhsiIiIiIsp6rLEhIiIiIqKsx2BDRERERERZL+NqbCzLwsGDB+HxeLq0gSAREREREQ1MQggEg0GMGDEiuel1ZzIu2Bw8eBAjR45M9zCIiIiIiChD7N+/H6WlpUe9JuOCjcfjAZAYvNfrTfNoiIiIiIgoXQKBAEaOHJnMCEeTccGmZfmZ1+tlsCEiIiIioi6VqLB5ABERERERZT0GGyIiIiIiynoMNkRERERElPUYbIiIiIiIKOsx2BARERERUdZjsCEiIiIioqzHYENERERERFmPwYaIiIiIiLIegw0REREREWU9BhsiIiIiIsp6DDZERERERJT1GGyIiIiIiCjrMdgQEREREVHWY7AhIiIiIqKsx2BDRERERERZj8GGiIiIiIiyHoMNERERERFlPQYbIiIiIiLKegw2RERERESUFIzpMC2R7mF0G4MNEREREREhpps42BxFXTAOS2RfsFHTPQAiIiIiIkof0xJoDGsIxvR0D+W4MNgQEREREQ1CQggEogaaIlpWztC0xWBDRERERDTIRDUT9aE4dNNK91B6DYMNEREREdEgoZsWGsMawnEj3UPpdQw2REREREQDnBACzREdzVEdYgAsO+sIgw0RERER0QAWihtoDGkwrIGz7KwjDDZERERERANQ3DDRGNYQ1cx0D6VfMNgQEREREQ0gpiXQFNEQiGZ3++buYrAhIiIiIhogAjEdTWENpjUw62iOhsGGiIiIiCjLxfRE+2bNGNh1NEfDYENERERElKWMI+2bQwOwfXN3MdgQEREREWUZIQT8UR3NER3WAG3f3F0MNkREREREWSQcN9AY1qCbg3fZWUcYbIiIiIiIsoBmJJadRTQuO+sIgw0RERERUQazWto3xwwILjvrFIMNEREREVGGCsZ0NIV1GBaXnR0Lgw0RERERUYaJ6SYawhriupnuoWQNBhsiIiIiogxhWgIN4ThCMdbRdBeDDRERERFRmgkhEIgaaIpobN/cQww2RERERERpFNVM1IfibN98nBhsiIiIiIjSQDcT7ZvDcS476w0MNkRERERE/UgIgaaIDn9UZ/vmXsRgQ0RERERpUd0cRY0/imKfCyV5rnQPp1+E4gYaQxrbN/cBBhsiIiIi6lfBmI6HVu/Eml11iBsmHKqCueOKcM/88fA4bekeXp+IGyYaQhpibN/cZ+R0D4CIiIiIBpeHVu/Equ2HIEtAvtsOWQJWbT+Eh1bvTPfQep1pCdSH4qhuijLU9DHO2BARERFRv6lujmLNrjrkOtTk7IxNkSEArNlVh+rm6IBZluaP6miOaDAt1tH0B87YEBEREVG/qfFHETdMOG1KynGXTUHcMFHjj6ZpZL0npps40BRBQyjOUNOPOGNDRERERP2m2OeCQ1UQ003YlK//jT2qJ2ptin3ZO1tjHGnfHGL75rTgjA0RERER9ZuSPBfmjitCKG4gENOhmxYCMR3huIG544qychmaEALNEQ37m6IMNWnEGRsiIiIi6lf3zB8PIFFT0xTR4FAVLJgyPHk8m4TjBhrDGnST7ZvTjcGGiIiIiPqVx2nD/QunZPU+NpphoSEcR1Rjp7NMwaVoRERERJQWJXkuTC0ryKpQY1kCDaE4qpujAzLUCCGwcU8Drv39JjSGtXQPp1s4Y0NERERE1AWBmI6m8MBt3/zRviYsXVeJzw8FAQC/W7MHP75wYppH1XUMNkRERERERxHTTTSENcQH6AabOw4FsGxdJbbua045/seNVbj9rDHwuW3pGVg3MdgQEREREXXAMC00RjSEYgOz09lXdSEsX1+F9Xsa2p2bO64IP7xgfNaEGoDBhoiIiIgohRACgaiBpogGSwy8ZWfVTVE8ubEKb+04jLav7qRSHy47tRQTi3ORn2NPy/h6isGGiIiIiOiIqGaiPhQfkO2b64JxPLVpL1Ztr2lXJzRuWC6unz4KW6ua8NiaPTAtC06birnjinDP/PHwODN/5obBhoiIiIgGPcO00BDWEM6SDTZrg3HUB2Mo9DgxzOM46rXNEQ1/3rIfL22rhm6mBpqyIW4smlWOOWMK8T9vfYn3vqyH267A67YjblhYtf0QAOD+hVP67LX0FgYbIiIiIhq0hBBojuhojuoQWbDsLBw38Ph7ldhS1QjNMGFXFUwrL8CSORXIcaR+tQ/FDTz/wX6s3FqNaJvGB8N9Ttw8owznThwGRZZQG4xjS1Uj3HYFOXYVNkWGXVUgkNhItbo5mvFtuRlsiIiIiGhQimgGGkJaVi07e/y9SqzdXQe3XYHPZUfcMLF2dx0A4M55YwEkuri99FE1nnl/PwJtGh8MybHjxhllWDClGDbl6y0t64MxaIYJnyu1rsZlU9AU0VDjZ7AhIiIiIsooummhIaQhomXHsrMWbWdVAEC1qxAAtlQ1oro5ivcrG/H05n3tNtf0OlVcO20UFp4yAg6b0u65Cz1O2FUFccOEav86IkR1Ew5VQbEvs0MNwGBDRERERINEti07a6uzWRWHIuNwMI47n9nWLtC47QqunFqKK6aWtluq1towjwPTyguwdncdBACPpCJmWAjHDSyYMjzjZ2sABhsiIiIiGgTCcQON4exadtZW21kVIQRCcRN1oTgMSyCsfV1HY1dlLDxlBK49fVSX96JZMqcCQGL2pymiwWlTsWDKcNwzf3yfvJ7exmBDRERERANWti4760jLrMqaXYcR1U2EYia0NkFNkSVcdOJw3HDGKBTmHr1bWls5DhV3zhuL2mAcMgRKC3KyYqamBYMNEREREQ042b7srDMzRhfgvS/r2y05kwCcN2kYbppRhhHHGUaGeRwYWeBOaS6QDRhsiIiIiGhAGQjLztraVRvEsnWV2FLV1O7cnLGFuGVmOSoKc9IwsszBYENEREREA8JAWnbWYm9DGMvXV2Ht7vp2504vz8etsyowvtjTq/esDcZRF4xxKRoRERERUX8aiMvODvmjeHLDXry5oxZWm5c0ZYQXi2dX4OSReb16z9abf5qWBadNxdxxRbhn/nh4nF1rQJBODDZERERElLWycZPNo6kPxfH0pn147dNDMNokmjFDc7F4djmmlRdAkqRev3frzT+9bjvihoVV2w8BAO5fOKXX79fbGGyIiIiIKOsMtGVn/qiOZ7bsw4vbDkIzUkPayHwXFs0qx5njiiD3QaAB2m/+aVNk2FUFAsCaXXWobo5m/LI0BhsiIiIiyhoDbdlZOG5g5dYDeH7rAURa7UMDAMO8Dtw8oxznTRoGRe6bQNOis80/XTYFTRENNX4GGyIiIiKiXjGQlp3FdRMvbTuIP2/Zh0AsddYp323DjWeU4cITh8Ou9k/L5babf7aI6iYcqoJiX2aHGoDBhoiIiIgy3EBadqabFl77tAZPb96LhlDqXjQep4prTh+Jhd8ogcum9Ou4Wjb/XLu7DgKAR1IRMyyE4wYWTBme8bM1AIMNEREREWWogbTszLQE3tpRiyc37sUhfyzlnNMm48qppbhy6kjkOtP39XzJnAoAwJaqRjRFNDhtKhZMGY575o9P25i6g8GGiIiIiDLOQFl2JoTAe1/WY/n6KuxtiKScsykSvnnKCFw7bRTy3fZOnqH/5DhU3DlvLGqDccgQ3MeGiIiIiKinBsqyMyEEPtjbhGXrqrCzNphyTpaAC08cjhvPKEORx5GmEXZumMeBkQVu2JT+qe/pLQw2RERERJR2A2nZ2fZqP5auq8THB/wpxyUAZ08YikUzy1GSnz0zIdmCwYaIiIiI0mqgLDv78nAIS9dVYnNlY7tzs0YPwaJZ5TihKDcNIxscGGyIiIiIKC0GyrKzfY0RPLG+Cu/uqmt3buqoPNw6uwITh3vTMLLBhcGGiIiIiPrVQFl2VhOI4Y8b9uLvn9fAavMyJg334NbZFTh1VH56BjcIMdgQERERUb8ZCMvOGsMant60F698cghGm0RzQlEObp1VjhknDIEkSWka4eDEYENEREREfU43LTSGNYTj2bvsLBDV8ewH+/GXD6sRN1KDWWm+C4tmlmPu+CLIDDRpwWBDRERERH1mICw7i2gGXviwGs+9vx9hzUw5N9TjwE0zynDB5GIoMgNNOjHYEBEREVGfyPZlZ5ph4eWPD2LF5n1ojuop5/LdNlw/fRQuPmkE7Gp27fcyUDHYEBEREVGvyvZuZ4ZpYfVntXhq417UheIp53IdKq4+vRSXfaMULruSphFSRxhsiIiIiKhXZPuyM0sIvPPFYTyxYS+qm6Mp55yqjMunluKq00rhcdrSNEI6GgYbIiIiIjpu2bzsTAiBDXsasHx9Fb6qD6ecsykSLjl5BK6bNgoFOfY0jZC6gsGGiIiIiHos27udfbi3CY+vq8QXNcGU47IEzJ9cjBtnlGGY15mm0VF3MNgQERERUbdl+7Kzzw8GsHR9JT7a19zu3Nnji3DLzHKMLHD3/8CoxxhsiIiIiKhbsnnZ2Z66EJatq8LGrxranZtxwhDcOqsco4fmpmFkmcFpU+Bz2WBTsq/TG4MNEREREXVJNi87298YwRMbqvDOzrp2504Z6cPi2RWYPMKXhpGlnyRJyHEo8DptcNqyt9Mbgw0RERERHVU2Lzs7HIjhj5v2YvX2Glhthj6h2IPFsytw6qg8SNLg21xTkSV4nDZ4nSrULJyhaYvBhoiIiIg6la3LzpoiGlZs3oeXPz4I3UxNNBWFObh1Vjlmjh4yKAONTZHhc9vgcagD6vUfVzT7z//8T0iShLvuuit5LBaL4fbbb8eQIUOQm5uLyy+/HLW1tcc7TiIiIiLqR7ppoTYQQ40/llWhJhQzsHRdJa5/fDNe+LA6JdSMyHPiXy6cgN/fOBWzxhQOqC/1XeGyKyj2OTGywA2v0zbgXn+PZ2zef/99PPbYYzjppJNSjv/TP/0TXn31VTz//PPw+Xy44447cNlll2H9+vXHPVgiIiIi6ltCCPijOpoi2bXsLKqbePHDajzz/n6E2tQAFebacdOMMsyfXDwgllx1hyRJyHWo8LlssKsD+7X3KNiEQiFcf/31+MMf/oBf/OIXyeN+vx9Lly7FihUrcM455wAAli9fjokTJ2LTpk0444wzemfURERERNTrsnHZmWZYeOWTg/jT5n1oiugp53wuG66bNhKXnjwCjiwuiu8JRZbgddrgddmgyANrZqYzPQo2t99+Oy666CLMmzcvJdhs3boVuq5j3rx5yWMTJkzAqFGjsHHjxg6DTTweRzweT/45EAj0ZEhERERE1EPZ2O3MtAT+/lkNnty4F4eD8ZRzOXYFV55WiiumlsJtH1wl5XZVhs9lQ+4Aq5/pim7/l37mmWfw4Ycf4v333293rqamBna7HXl5eSnHhw0bhpqamg6f74EHHsB9993X3WEQERER0XHKxmVnlhBYs7MOyzdU4UBTNOWcQ5XxrW+U4OrTR8LnsqVphOnhtieWm7nsg2tmqrVuBZv9+/fjzjvvxBtvvAGn09krA7j33ntx9913J/8cCAQwcuTIXnluIiIiIupYti07E0Jgc2Ujlq6rxJ66cMo5VZZw0UnDccP0URiS60jTCPvfYKqf6YpuBZutW7fi8OHDOPXUU5PHTNPE2rVr8X//9394/fXXoWkampubU2ZtamtrUVxc3OFzOhwOOByD5wNIRERElE7ZuOxs2/5mPP5eJT4/lFqyIEvAeZOG4eYZ5Sj29c4/umeDwVg/0xXdCjbnnnsuPv3005RjixYtwoQJE/D//t//w8iRI2Gz2fDWW2/h8ssvBwDs3LkT+/btw4wZM3pv1ERERETULdm47OyLmgCWrqvC1r1N7c6dOa4Qi2aWo2xIThpGlh4Ddf+Z3tKtYOPxeDBlypSUYzk5ORgyZEjy+OLFi3H33XejoKAAXq8X3/ve9zBjxgx2RCMiIiJKk2xbdlZZH8ay9ZVY/2VDu3PTKgpw66xyjBvmScPI0sNlV+Bz2QZdI4Tu6vV35+GHH4Ysy7j88ssRj8dxwQUX4JFHHunt2xARERHRMRimhYYsWnZW3RzFkxuq8NaOw2g7p3RiiQ+LZ5fjpNK8dAyt30mShBxHItA41MHbEKA7JJFhc5GBQAA+nw9+vx9erzfdwyEiIiLKOkIINEd0NEezY9lZXTCOpzftxWvba2BaqeMdNywXi2dX4LSy/EGx/EqRJXicNnid6qDbTLQj3ckGnM8iIiIiGkDCcQON4exYdtYc0fDnLfvx0rZq6GZqoCkrcGPR7HLMGVM4KAKNTZHhdSXqZ2Q2BOgRBhsiIiKiAUAzEt3OIlrmLzsLxQ2s/OAAnt96AFHdTDk33OfEzTPKcO7EYYOi45fDpiDPZUOOg1/LjxffQSIiIqIsZlkCTRENgZiR8cvOYrqJlz6qxp/f349gLDWADcmx44YzRuHCE4fDNgiWYOUc2X/GaWP9TG9hsCEiIiLKUsGYjqawDsPK7GVnumnh1U8O4enN+9AY1lLOeZ0qrp02Ct88ZcSA/5IvSxJynYlAMxjCW39jsCEiIiLKMnHDRENIQ6zNMq5MY1oCb+6oxZMb9qImEEs557YruGJqKa6cWjrgl2GpsgyvS4XHyQ01+9LA/hQRERERDSCmJdAY1hCM6ekeylFZQuC93fV4Yn0V9jZGUs7ZVRkLTxmBa08fBZ/blqYR9g+7KsPnsiGXG2r2CwYbIiIioizgj+poCmuwMriORgiB96uasHRdJXYfDqWcU2QJF55YjBuml6HI40jTCPuH255YbuayD+yldZmGwYaIiIgog0U1Ew3hODQjs+toPjnQjKXrqvBptT/luARg3qRhuHlGGUbkudIzuH7ADTXTj8GGiIiIKAMZZqJ9cyie2e2bd9UGsWxdJbZUNbU7N3tMIRbNKkdFYU4aRtY/uKFm5mCwISIiIsogQgg0R3Q0R/WMbt+8tyGM5RuqsHZXfbtzp5Xl49bZ5ZhQfPSd4rMZN9TMPAw2RERERBkiHDfQGNagm5m77OyQP4o/btyLNz6vhdUmd00e4cXi2RU4ZWReWsbWH5y2xHKzgd7JLRvxvwgRERFRmmmGhYZwHFEtc9s3N4TieHrTPrz66SEYbRLNmKJc3Dq7HNMrCgZs969chwovN9TMaAw2RERERGliWQJNEQ2BmJGxy878UR3PbNmHl7YdRLxNA4OR+S4smlWBM8cVQh6AgYYbamYXBhsiIiKiNAjEEu2bzbbruTJEOG7ghQ8P4LkPDiDSZiZpqMeBm2eW4/xJwwbkhpPcUDM7MdgQERER9aOYbqIhrCGuZ+ays7hu4q8fH8SKzfsQiKV2ZMt323DDGWW46MThsKsDbwaDG2pmNwYbIiIion5gWgIN4ThCscxs36ybFlZtr8FTm/aiIaSlnPM4VVxz+kgs/EYJXAOwxoQbag4MDDZEREREfUgIgUDUQFNEg5WBdTSmJfDWF4fx5IYqHPLHUs45bTKumFqKq6aORK5zYH1t5IaaA8/A+oQSERERZZCoZqI+FM/I9s1CCKz7sgHL1ldib0Mk5ZxNkfDNU0bg2mmjkO+2p2mEfYMbag5cDDZEREREvUw3LTSGNYTjmbfsTAiBD/Y2Ydm6KuysDaackyVgwZThuPGMURjqdaZphH2DG2oOfAw2RERERL1ECIHmiI7mqJ6R7Zu3V/uxdF0lPj7gTzkuAThnwlDcPLMMpfnu9AyujzhsCvK4oeagwP/CRERERL0gHDfQGNYyctnZ7toglq2vwubKxnbnZo4egkWzyjG6KDcNI+s7OY5EQwBuqDl4MNgQERERHQfNSCw7i2iZt+xsX2MET6yvwru76tqd+8aoPCyeVYFJI7xpGFnf4IaagxuDDREREVEPCCHQFNHhz8BlZzWBGJ7auBevf1aDtvt/ThzuweJZFTi1LD89g+sD3FCTAAYbIiIiom4Lxw00hDQYVmYtO2sMa/jT5n145ZOD0M3URHNCYQ5unV2OGScMGTCbT9oUGT53oiHAQHlN1HMMNkRERERdlKnLzgJRHc9+sB8vfliNmJEatkryXFg0qxxnjS+CPEC+/Lvsif1n3HZ+laWv8dNAREREaVfdHEWNP4pinwslea50D6edTF12FtVMvPDhATz7wX6E42bKuaJcB26aUYYLJg8bMPu15DpUeNkQgDrBYENERERpE4zpeGj1TqzZVYe4YcKhKpg7rgj3zB8Pj9OW7uEByMxlZ5ph4eWPD2LF5n1ojuop5/JcNlx/xihcctII2NXsDzRsCEBdxWBDREREafPQ6p1Ytf0Qch0q8t12xHQTq7YfAgDcv3BKWseWicvODNPC6s9q8dTGvagLxVPO5TgUXHP6SFz2jVK47Nk/o8GGANRdDDZERESUFtXNUazZVYdch5qcnbEpMgSANbvqUN0cTcuyNMsSaI5m1rIzSwi880UdnthQhermaMo5pyrjslNLcPXpIzNmlut4sCEA9RSDDREREaVFjT+KuGEi321POe6yKWiKaKjx93+wCcUNNGbQsjMhBDbsacDy9VX4qj6ccs6mSLjkpBG4bvooFOTYO3mG7OG0KchzsyEA9Rw/OURERJQWxT4XHKqCmG6m1E5E9UStTbGv/0JN3DDRENIQ081jX9xPPtzXhKXrKrHjUDDluCwBF0wuxk0zyjDM60zT6HoPGwJQb2GwISIiorQoyXNh7rgirNp+CAKJmZqobiIcN7BgyvB+ma0xLYGmiIZAmwL8dNpxKICl6yrx4b7mdufOHl+Em2eWY1SBu/8H1ovYEID6AoMNERERpc0988cDSNTUNEU0OFQFC6YMTx7vS4GYjqawBtPKjDqaPXUhLF9fhQ17GtqdO+OEAtw6qwJjhuamYWS9R5El+Fw2NgSgPsFgQ0RERGnjcdpw/8Ip/bqPTUw3UR+KQzMyo47mQFMET2zYi3e+OIy2EevkUh8Wz67AlBJfWsbWW9gQgPoDgw0RERH1iUzbdNMwLTRGNIRimdG++XAghj9u2ovV22vQdtJofLEHi2eVY2pZflYHAadNgc9lQ46DXzmp7/FTRkRERL2qO5tu9scGnUII+KM6miM6rAxo39wU0bBi8z68/PFB6GbqeMqHuHHrrArMGjMkqwMNGwJQOjDYEBERUa/qzqabfb1BZ0Qz0BDSoJvpX3YWihl49oP9eOHDA4jpqeMZ7nNi0axynD1+aNbWnrAhAKUbgw0RERH1mu5sutmXG3TqpoWGkIaIlv5lZ1HdxIsfVuOZ9/cjFE8dT2GuHTeeUYYFU4qhZmkYUGUZXpfKhgCUdgw2RERE1Gu6s+lmX2zQaVkCzVEd/qgOkeZlZ5ph4ZVPDuFPm/eiKZLaTtrrVHH99FG49OQRcGTpci27KsPnsiGXDQEoQzDYEBERUa/pzqabvb1BZyhuoDGkwbDSu+zMtAT+/nktntxQhcPBeMq5HLuCK08rxeWnlmZtQb3LnmgI4LZn5/hp4OInkoiIiHpNdzbd7K0NOuOGiYaQhphu9s2L6iJLCKzdVYfl66uwvymacs6hylh4yghcM20UfK7eaYrQnyRJOtIQQIVDzc4ZJhr4GGyIiIioV3Vn083j2aDTsgSaIhoCMSOty86EENhc2Yhl66rwZV0o5ZwqS7joxOG4/oxRKMx1pGmEPafIErxOG7wu1s9Q5pNEuhegthEIBODz+eD3++H1etM9HCIiIuqh7uxj0909b4IxHU1hPe3Lzj7e34zH11Xis4OBlOOyBJw3aRhumlGG4d1cUpcJ7KoMr4sbalL6dScbcMaGiIiI+kRJXtc35uzqtZphoT4UT/uysy9qAli2rgof7G1qd+7McYVYNLMcZUNy0jCy4+O2J9o1u+xcbkbZh8GGiIiIMl6mLDurrA9j+foqrPuyvt25aeX5uHV2BcYN86RhZD3Xsv+M12mDXc3OltNEAIMNERERZbhMWHZW3RzFkxuq8NaOw2gbq04s8WLx7AqcVJqXjqH1GPefoYGGwYaIiIgyUiZ0O6sLxvH0pr14bXsNTCs10owdmovFsytwenl+VtWhcP8ZGqgYbIiIiCijmJZAY1hDMKYf++I+4o/oWLFlH17aVg3dTA00owrcuHVWOeaMLcyqYMD6GRroGGyIiIgoY/ijOpojWrvZkf4SihtY+cEBPL/1AKJtZoqKvU7cPLMM8yYOy5qlWy37z/hcrJ+hgY/BhoiIiNIuppuoD8WhGempo4npJl7adhDPbNmHQMxIOTckx44bzhiFC08cDpuSHeGA+8/QYMRgQ0RERGljmBYawxpCcePYF/cB3bTw2qeH8PSmfWgIaynnvE4V10wbhYWnjIDTlh3Lt7j/DA1mDDZERETU74QQR5ad6bDS0L7ZtATe2lGLJzbsRU0glnLOZVNw5dRSXHFaKXId2fFVyWVXkOeys36GBrXs+GklIiKiASMcN9AY1qCb/b/sTAiB93bXY/n6KuxtjKScsykSFp5SguumjYLPbev3sXWXJEnIcSjwuWxwqAw0RAw2RERE1C80I7HsLKL1/7IzIQTer2rCsvWV2FUbSjmnyBIuPLEYN0wvQ5HH0e9j6y5FluBx2uB1qlCzpOaHqD8w2BAREVGfsiyBpoiGQMyASMOys08ONGPpuip8Wu1POS4BOHfiUNw8sxwlea5+H1d32ZRE/YzXyfoZoo4w2BAREVGfCcZ0NIV1GFb/LzvbVRvEsnWV2FLV1O7c7DGFWDSrHBWFOf0+ru5y2hLLzXKypN6HKF34E0JERES9LqabaAxriLXZC6Y/7G0IY/mGKqzdVd/u3NSyfCyeXY4Jxd5+H1d35TpUeF22rOnIRpRuDDZERETUa0xLoDGsIRjT+/3eNf4YntxYhTc+r0Xb/T0nj/Bi8ewKnDIyr9/H1R2yJMHjTASabNkzhyhTMNgQERFRr/BHdTSFtX5v39wQiuPpzfvw6ieHYLRJNGOKcnHr7HJMryjI6LoUVZbhc9ngcaqQuaEmUY8w2BAREdFxiWomGsJxaEb/1tH4ozqefX8/XvyoGvE29y7Nd2HRzHLMHV8EOYMDjaOlfsauZHTwIsoGDDZERETUI4aZaN8civdv++aIZuCFrdV47oP9CGupNTxDPQ7cPLMc508aBiWDZz5yHCp8rJ8h6lUMNkRERNQtQgg0R3Q0R/V+bd8c1028/PFBrNiyH/5oag1PvtuG66eX4eKThsOuZmZtiixJyHUmAg3rZ4h6H4MNERERdVlEM9AQ0qCb/bfszDAtrNpegz9u2ouGkJZyLteh4prTR+Jbp5bAlaGzH6osw+tS4XHaMnoWiSjbMdgQEdGAVN0cRY0/imKfKys2X8x0ummhIaQhovXfsjPTEnj7i8N4YkMVDvljKeecNhmXn1qKq08biVxnZn6dsauJhgC5Dm6oSdQfMvM3ARERUQ8FYzoeWr0Ta3bVIW6YcKgK5o4rwj3zx8PjtKV7eFknHcvOhBBY/2UDlq2vRFVDJOWcTZFw6ckjcN30Uch32/tlPN3ltieWm7nsmTmDRDRQMdgQEdGA8tDqnVi1/RByHSry3XbEdBOrth8CANy/cEqaR5dd+nvZmRACW/c2Yen6KuysCaackyVg/pRi3HRGGYZ6nf0ynu6QJAm5RxoCZGqND9FAx2BDREQDRnVzFGt21SHXoSZnZ2yKDAFgza46VDdHuSytC/Qj3c7C/djt7LODfixdV4lt+/0pxyUA50wYiptnlqE0391v4+kqRZbgddrgdbF+hijdGGyIiGjAqPFHETfMdkuUXDYFTRENNX4Gm6NJx7KzLw+HsGx9JTZ91dju3MzRQ7BoVjlGF+X2y1i6w6bI8Llt8LB+hihjMNgQEdGAUexzwaEqiOlmSjvdqJ6otSn2MdR0pr+Xne1vjOCJDVV4Z2ddu3PfGJWHxbMqMGmEt1/G0h0ue2JDTbedX6GIMg1/KomIaMAoyXNh7rgirNp+CAKJmZqobiIcN7BgynDO1nSgv5ed1QRieGrjXrz+WQ2sNpNCE4o9WDy7AlPL8vtlLF0lSRJyHIlA41DZEIAoUzHYEBHRgHLP/PEAEjU1TRENDlXBginDk8cpob+XnTWGNazYvA9/++QgdDP1fhWFObh1Vjlmjh6SUcu6FFmCx2mD16lC5YaaRBmPwYaIiAYUj9OG+xdO4T42R9Gfy86CMR3Pvr8ff/mwGjEj9X4leS7cMrMcZ08ogpxBgcamyPC6EoEmk4IWER0dgw0REQ1IJXkMNG315yabUc3EXz46gGfe349w3Ew5V5TrwE0zynDB5GEZNRPitCWWm+U4+PWIKBvxJ5eIiGiA689lZ5ph4W+fHMSKzfvQFNFTzuW5bLhu+ihcevKIjNrrJdehwuuywWlj/QxRNmOwISIiGsDCcQON4b5fdmZaAqu31+CPG/eiLhRPOZfjUHD1aSNx+amlcNkzIzzIkgSPMxFobBk0a0REPcdgQ0RENABpRqLbWV8vO7OEwDtf1OHJjVU40BRNOedUZVx2agmuOm0kvC5bn46jqxRZgs9lg8fJDTWJBhoGGyIiogHEsgSaozr8fbzsTAiBjV81YNn6KnxVF045Z1MkXHzSCFw/fRQKcuydPEP/4oaaRAMfgw0REdEAEYzpaArrMKy+XXb24b4mLF1XiR2HginHZQk4f1IxbppZhmKvs0/H0FUOm4I8NgQgGhT4U05ERJTl4oaJhpCGmG4e++LjsONQAEvXVeLDfc3tzp09vgg3zyzHqAJ3n46hq3IcKnxsCEA0qDDYEBERZSnTEmiKaAhE9WNffBy+qgth+foqrN/T0O7cGScU4NZZFRgzNLdPx9AVkiQh90igyaSua0TUPxhsiIiIslAgpqMprMG0+q6Opropiic2VOHtLw6j7V1OLvVh8ewKTCnx9dn9u0qRJXicNvhcbAhANJgx2BAREWWRmG6iPhSHZvRdHc3hQAxPbdqHVdsPoW1uGj/Mg1tnl+O0svy0F+HbFBlelw1eJxsCEPWm6uYoavxRFPuya6NjBhsiIqIsYJgWGiMaQrG+a9/cHNGwYss+/HXbQehmaqIpH+LGolkVmD1mSNpDBBsCEPWNYEzHQ6t3Ys2uOsQNEw5VwdxxRbhn/nh4nJnRsv1o+BuBiIgogwkhEIgaaIposPqofXMoZuC5rfvxwtZqRNs0IBjuc+KWmeU4Z8LQtC/zYkMAor710OqdWLX9EHIdKvLddsR0E6u2HwIA3L9wSppHd2wMNkRERBkqqiWWnelm3yw7i+omXvywGs9+sB/BNjNBQ3LtuOmMMiyYUgxVSV8hvixJyHUmAo0tjeMgGuiqm6NYs6sOuQ41OTtjU2QIAGt21aG6OZrxy9IYbIiIiDKMblpoDGsIx/tm2ZlmWHj100N4etNeNEVSO6p5nSqunz4Kl548Ao40zoyosgyvK/EFK90zRUSDQY0/irhhIt+duqmuy6agKaKhxs9gQ0RERF0khEBzREdzVIfog2VnpiXwxue1eHJjFWoD8ZRzOXYFV55WistPLU1r7YpdleFz2ZDrYEMAov5U7HPBoSqI6WbK7GhUT9TaFPsyO9QADDZEREQZIRw30BjW+mTZmSUE1u6qxxMbqrCvMZJyzqHK+NY3SnD16SPhc6WvONhlV5DnssNlZ/0MUTqU5Lkwd1wRVm0/BIHETE1UNxGOG1gwZXjGz9YADDZERERppRkWGsJxRDXz2Bd3kxACmysbsWxdFb6sC6WcU2UJF504HNefMQqFuY5ev3dXSJKEHIcCn8sGh8pAQ5Ru98wfDyBRU9MU0eBQFSyYMjx5PNN1K9g8+uijePTRR1FVVQUAmDx5Mv7t3/4NCxYsAADEYjH84Ac/wDPPPIN4PI4LLrgAjzzyCIYNG9brAyciIspmliXQFNEQiBl9suzs4/3NWLquEtsPBlKOyxJw3qRhuGlGGYanaWlJy4aaXqea1sYERJTK47Th/oVTsnYfG0l047fp3/72NyiKgrFjx0IIgSeffBK//OUv8dFHH2Hy5Mn4x3/8R7z66qt44okn4PP5cMcdd0CWZaxfv77LAwoEAvD5fPD7/fB6vT16UURERJksGNPRFNZhWL2/7GxnTRBL11Xig71N7c6dObYQt8wqR/mQnF6/b1e0bKjpcaiQ2RCAiLqgO9mgW8GmIwUFBfjlL3+JK664AkVFRVixYgWuuOIKAMAXX3yBiRMnYuPGjTjjjDN6ffBERETZJG6YaAhpiOm9v+yssj6M5eursO7L+nbnppXn49bZFRg3zNPr9+0Kl12B18kNNYmo+7qTDXr8G8Y0TTz//PMIh8OYMWMGtm7dCl3XMW/evOQ1EyZMwKhRo7oVbIiIiAYa0xJoDGsIxvRjX9xN1c1RPLmhCm/tOIy2/1J5YokXt86uwMmleb1+32Nh/QwR9bduB5tPP/0UM2bMQCwWQ25uLl588UVMmjQJ27Ztg91uR15eXsr1w4YNQ01NTafPF4/HEY9/3XIyEAh0ei0REVG28Ud1NEc0mFbv1tHUBeN4evNevPZpTbvnVmUJp5Xl48cXTkCus387nSmyBK/TBg/rZ4ion3U72IwfPx7btm2D3+/HypUrcfPNN2PNmjU9HsADDzyA++67r8ePJyIiykQx3UR9KA7N6F4dTW0wjvpgDIUeJ4Z52ncr80d0rNiyD3/9+GC751ZlCQU5dqgysLM2iKXrqnDnvLHH9Tq6yqbI8LkT9TPcf4aI0qHbwcZut2PMmDEAgKlTp+L999/Hb37zG1x99dXQNA3Nzc0psza1tbUoLi7u9Pnuvfde3H333ck/BwIBjBw5srvDIiKiAaY7XXkyqYOPYVpojGgIxYxuPS4cN/D4e5XYUtUIzTBhVxVMKy/AkjkVyHGoCMUNrPzgAFZ+eACRNq2hFQnwuGwoyrF/HSokA1uqGlEbjHcYkHqL05ZYbsb6GSJKt+P+LWRZFuLxOKZOnQqbzYa33noLl19+OQBg586d2LdvH2bMmNHp4x0OBxyO9PTPJyKizBOM6Xho9U6s2VWHuJHY8XruuCLcM388PG2WVXXn2r4mhEAgaqAposHqQV+ex9+rxNrddXDbFfhcdsQNE2t318GwLJTku/HMln0ItAlLBTl2nDuhCG/tqEWe254yU+JUFfijGuqDsT4JNrkOFV6XDU4b62eIKDN0K9jce++9WLBgAUaNGoVgMIgVK1bg3Xffxeuvvw6fz4fFixfj7rvvRkFBAbxeL773ve9hxowZbBxARERd9tDqnVi1/RByHSry3XbEdBOrth8CANy/cEqPr+1LPV121qI2GMeWqka47Qpy7Im/mhWbglDcwKrtNWhbnuNxqrjm9JH41jdK4I8ZWPdlA+KGCdX+9V/rsSOzPoUeZ49fV1uSJMHjVOFz2WBj/QwRZZhuBZvDhw/jpptuwqFDh+Dz+XDSSSfh9ddfx3nnnQcAePjhhyHLMi6//PKUDTqJiIi6oro5ijW76pDrUJMzLjZFhkBiJ+zq5mhyqVl3ru0rhmmhMawhFO/esrO26oMxaIYJn8sOIQSCMQP1YQ1Gm0Tjsim4cmoprjitFLlHln45bYkla2t310EgMVMTM0xENRNnji3qldmaloYAXpcNCvefIaIM1a1gs3Tp0qOedzqd+O1vf4vf/va3xzUoIiIanGr8UcQNE/lue8pxl01BU0RDjf/rsNKda3vb8S47a6vQ44RNkdEcSYQkzUx9TpsiYeEpJbh22kjktXm9ALBkTgUAYEtVI/xRDXZVwZlji5LHe6plQ02vkw0BiCjzsdKPiIgyRrHPBYeqIKabKUudonqifqbY5+rRtb0pqiWWnelmz5adtSWEwL6GMKK6BX+0/T435UPcePDyk1B0lJmXHIeKO+eNPWZHta5y2BTksSEAEWUZ/sYiIqKMUZLnwtxxRVi1/RAEErMvUd1EOG5gwZThKTMw3bm2N+hHlp2Fj3PZWWufHvBj6fpKfHLA3+6cyyZj1uhC3DlvbJcDxjCP47gCjduuIs/NhgBElJ0YbIiIKKPcM388gESdTFNEg0NVsGDK8OTxnl7bU0IINEd0NEd1iF5YdgYAu2qDWLa+ClsqG9udO60sH+dNGoqTRub3aZvmFpIkIdeRaAhgV9kQgIiylyR667d0LwkEAvD5fPD7/fB6vekeDhERpUkm7GMTjhtoDGu9tuxsX0MEyzdUYc2uunbnppbl49ZZ5Zg4vH/+7pMlKVk/o7LDGRFlqO5kA87YEBFRRirJ63pI6c61XaEZFhrCcUTbbITZUzX+GB5b+1Wic1mbf06cPMKLxbMrcMrIvF6517GosgyfywaPU4XMDmdENIAw2BARER1hWgJNEQ3BmNEry84aQnE8saEKr22vaRdoKgpz8A9zKjC9oqBfOo7ZFBl5bhtyHexwRkQDE4MNERERgEBMR1NYg9l2N8yePFdUxzPv78eLH1Uj3mbTTlWW4FBlnDjCizNOGHLc9zoWp02Bjx3OiGgQ4G85IiIa1GJ6on2zZhx/HU1EM/DC1mo898F+hNssY1NlCUNy7PA6VYR1E+/vbUJtMN5nDQJyHSq8LnY4I6LBg8GGiIgGJeNI++ZQL7RvjusmXv74IFZs2d9uLxoJQEGOHfluG+QjS8CcqgJ/VEN9MNarwUaWJOQ6Ex3ObGwIQESDDIMNERENKkII+KM6miM6rOOsozFMC6s/q8EfN+5FfUhLOZfrUHHRScPx7s7DUGUpGWoAIGaYsKsKCj3O47p/C1WW4XWp8DptbAhARIMWgw0REQ0aEc1AQ+j42zeblsA7Ow/jiQ1VONgcSznntMm4/NRSXH3aSOQ6VcQ0M9ENDYmZmphhIqqZOHNs0XHP1tjVRIczNgQgImKwISKiQUA/suwsfGTZWW0wjvpgDIUeZ7fChRAC679swPINVaisD6ecsykSLjl5BK6bNgoFOfbk8SVzKgAAW6oa4Y9qsKsKzhxblDzeE257YrmZy876GSKiFgw2REQ0YAkh0BzR0RzVIYRAOG7g8fcqsaWqEdqR5WDTyguwZE7FUbuGCSHw4b5mLF1XiS9qginnZAmYP6UYN55RhmHe9kvLchwq7pw3tsdhqoUkSch1JAKNXWX9DBFRWww2REQ0IIXiBprCqcvOHn+vEmt318FtV+Bz2RE3EsvEAODOeWM7fJ7PDvqxdF0Vtu1vbnfunAlDccvMMpTmu485nmEeR48CjSJL8Dpt8LpsUFg/Q0TUKQYbIiIaUDTDQkM4jmibdsu1wTi2VDXCbVeQY0/89afaVQgklom1bb2853AIS9dXYtNXje3uMeOEIbh1VjlGD83ts9dhU2T43DZ4WD9DRNQlDDZERDQgWJZAU0RDIGZAdNDtrD4Yg2aY8LnsKcfbtl7e3xjBExuq8M7OunbPccrIPCyZXYFJI7x99jq4oSYRUc/wtyYREWW9YExHY1iDaXXevrnQ44RdVRA3TKj2r//6a2m9DEnCr17fidWf1aDt00wc7sHiWRU4tSy/T8YvSRJy7Ao31CQiOg4MNkRElLViuomGsIa4bh7z2mEeB6aVF7RrvRyOGxiS48Ddz26DbqYmmorCHNw6qxwzRw/pk+VgsiTB41Th5YaaRETHjcGGiIiyjmkJNIY1BGN6tx7XuvVyUyQOzRSI6Rb80dTWzSV5LtwysxxnTyhK2Vizt6hyYv8Zj1PlhppERL2EwYaIiLKGEAKBqIGmiAargzqaY8lxqPj2mSfAaVfw8raDiLaZ6SnMteOmGeWYP3kY1D6YQbGrMvLcduTYFTYEICLqZQw2RESUFaKaifpQPKV9c3dohoVXPjmIP23eh6ZI6kyPz2XD9dNH4dKTR/TJHjHcUJOIqO8x2BARUUbTTQuNYQ3huNGjx5uWwOuf1eCPG/ficDCeci7HruCq00bi8qklcNt7969EbqhJRNS/GGyIiCgjCSHQHNHRHNU7bN98LJYQWLOzDss3VOFAUzTlnEOVcdmpJbj6tJHwumy9NWQA3FCTiChdGGyIiCjjhOIGGkMaDKv7y86EENj0VSOWra/EnrrUpgCqLOHik4bj+umjMCTX0ckz9Aw31CQiSi8GGyIiyhhxw0RDSEOsC+2bO/LRviYsXVeJzw8FU47LEnD+pGLcNKMMxT5nbww1iRtqEhFlBv4WJiKitLMsgcaIhkC0e+2bW+w4FMCydZXYuq+53bm544qwaGY5Rg1xH+coU+U6VG6oSUSUQRhsiIgorQIxHU1hDabV/Tqar+pCWL6+Cuv3NLQ7N72iALfOKsfYYZ7eGCYAbqhJRJTJGGyIiCgtYrqJhrCGeA+WnVU3RfHkxiq8teMw2sahk0p9WDK7AlNKfL0zUHBDTSKibMBgQ0RE/cq0BBrDGoKx7i87qwvG8dSmvVi1vabdDM+4YblYPLsCp5Xl91rxvqOlfoYbahIRZTwGGyKiLFbdHEWNP4pinwslea50D+eY/FEdzZHuLztrjmj485b9eGlbNXQz9bFlQ9y4dVYFZo8Z0mvhI+fI/jOsnyEiyh4MNkREWSgY0/HQ6p1Ys6sOccOEQ1Uwd1wR7pk/Hh5n7+7L0htiuon6UBya0b32zaG4gec/2I+VW6sRbbNkbbjPiZtnluPcCUN7Zb8YqaV+xskNNYmIshGDDRFRFnpo9U6s2n4IuQ4V+W47YrqJVdsPAQDuXzglzaP7mmFaaIxoCMWMbj0uppt48aNqPPP+fgTbPHZIjh03zijDginFvVLAr8oyvC4VHic31CQiymYMNkREWaa6OYo1u+qQ61CTszM2RYYAsGZXHaqbo2lfliaEQCBqoCmiwRJdX3ammxZe/eQQnt68D41hLeWc16nimmmj8K1TRsDRC0vEuKEmEdHAwmBDRJRlavxRxA0T+W57ynGXTUFTREONP73BJqollp3pZteXnZmWwBuf1+KPG/eiJhBLOee2K7hyaimumFraK5tgOm0K8tw2uO38K5CIaCDhb3UioixT7HPBoSqI6WbKUqyonqi1KfalJ9TopoXGsIZwvOvLziwhsHZXPZ7YUIV9jZGUc3ZVxrdOGYFrTh8Fn/v464a4oSYR0cDGYENElGVK8lyYO64Iq7YfgkBipiaqmwjHDSyYMrzfZ2uEEGiK6PBHdYguLjsTQmBzZSOWra/Cl4dDKecUWcJFJw7HDWeMQmGu47jGJksScp2JDmfcUJOIaGBjsCEiykL3zB8PIFFT0xTR4FAVLJgyPHm8v4TiBhpDGgyr68vOPj7QjKXvVWL7wUDKcQnAeZOG4aYZZRhxnOGspSGA12njhppERIMEgw0RURbyOG24f+GUtO1jEzdMNIQ0xNq0YD6anTVBLFtfifermtqdmzO2ELfMLEdFYc5xjYsbahIRDV4MNkREWawkr38DjWkJNIY1BGN6lx9T1RDG8vVVeG93fbtzp5fn49ZZFRhf7DmucfV0Q81s2+CUiIg6x2BDRETH1JP2zQebo3hy4168+Xkt2j5iyggvFs+uwMkj83o8JkmSkHsk0HR3Q81s2+CUiIiOjcGGiIgAdD57EdEMNIS0Lrdvrg/F8fSmfXj100MwrdRIM2ZoLm6dVY7pFQU9XiqmyBK8Thu8rp5vqJktG5wSEVHXMdgQEQ1ync1e/NO8sdBMgYjWtfbN/oiOP7+/Dy9tOwjNSA1BowrcWDSrHHPGFkLuYaCxKTK8Lhu8zuPbUDMbNjglIqLuY7AhIhrk2s5eRDUDr356EIGojjvnjT3m48NxA89vPYCVWw8goqU2E5AlwONUcXKpD6eV5fco1LQ0BMjthc05gczf4JSIiHqGwYaIaBBrO3thWgJOmwrdEthS1YjaYBzDPB3vJRPXTby07SD+vGUfArHUWR0JgNelosBth2ZaWPdlPWRJ6lJQauG2q8hz9/6Gmpm6wSkRER0fBhsioixQ3RzFpweaAUg4sdTXazMKLbMXPpcNmmElN9h0qgr8UQ31wVi7YKObFl77tAZPb96LhpCWci7HoSQ2xXQo8DhSl3kdKygBiYYAOQ4FeS57txsCdFWmbXBKRES9g8GGiCiDBWM6fvHKDrz66UFENROABJddwcUnFeNfLpp03B28TAswTQF/RIPP9fXSrJhhwq4qKPQ4W10r8NaOWjy5cS8O+WMpz+OyKbhiaglOLPHhwdVfwGVL/evlaEEJAGRJStbPqErfBJrWMmWDUyIi6j0MNkREGeyh1Tvx123V0EwLypH6lIhm4KVtB2FTlB538ApENfzi1R14b3c9gnEDmmEhGDNQ5HFCtyxENRNnji3CMI8DQgi892U9lq+vwt6GSMrz2BQJC08pwbXTRiLPbUdtMA67qiBumFDtX/8V01FQAgBVluFz2eBxqpB72OGsJ9K9wSkREfU+BhsiogxV3RzFWztqYVgCqiwnWxtLloBhCrz1RS2+2zy621/II5qBn/71c7y76zDcdgXDvU4cDsYR1U3UBKIoyHHgzLFFWDy7HO9XNWLpukrsqg2lPIciS1gwpRg3nlGGolYzMMM8DkwrL8Da3XUQSMzUxAwzJSgBgF2Vkw0BjqfD2fHq7w1OiYio7zDYEBFlqBp/FFE90WWs9WSGLCWWhcV0q1sdvDTDQmNYQ2VDGJsqG+C2K8g5MqtSmu9Cc0yHaVr48YUTIYTAT/76GT4+4E95DgnAuROH4uYZ5SjJ7/i+S+ZUAEjU1PijGuyqgjPHFmHJnAq47In6GZe9dxsCEBERMdgQEWWoYp8LLpuCYMyAJQDlSLixRKLI3mmTUzp4dbasyrIEmiIaAjEDQgjUB2PQDDOlpgYAcu0qGkJxPLpmDz4/GGg3nlljhuDWWRWoKMw56rhzHCrunDcWtcE46oMxFHqcGF2YA5/bBofKQENERH2DwYaIqBPprr8oyXPh3InD8PwH+6GZFoRIJBtTCNhVGedOGIaSPFenG2zeM388BICmsAbTEsnnLfQ429XBaIaFmmAMMd2Cv02omToqD7fOrsDE4d5ujX+414mxQ3Phc9lS2ioTERH1BQYbIqI2jhYUjrcLGdC9wHTP/PHQDCulK5rbruLik4qTHbweWr0Tr3xyEA5VRq5DhWkJvPbpQYTjBu44Z0y752xdB6NbApG4iVDcaHfdpOFeLJ5djm+Myu/W61NkCV6nDV6XLVkXRERE1NcYbIiI2nho9U6s2n4IuQ4V+W47YrqJVdsPAUCPu5ABPQtMHqcND15xEr4/b2yH+9jsqg3ixY8OIKZbCAJoCGnIcahw2mRs/KoBV54+ssP2ypefWoJPDvhR2RBud+6EohwsnlWBM04o6FZhv02R4XPb4ElzQwAiIhqcGGyIiFqpbo5iza465DrUZNho2WByza46VDd3vVi/reMJTJ117/r133ciopmQkZgpsUQiQJmWCrsqtds3JhDVsWxDFVZ9egi6KVKeqzTfhUUzyzF3fBHkbgQTp02Bz2VDjoN/pRARUfrwbyEiolZq/FHEDRP57tTCepdNQVNE61YXstZ6MzC1LGUDJHxS7YeERDMBSFKie5qVaOnsstmT+8ZENAPPbNmPZ97fD8NKDTR5LhuuOn0krpxa2q2lYzkOFT6XDU7b4GgIkO6aKyIiOjoGGyKiVop9LjhUBTHdTCl4j+qJpWOtu5B1R28EprZL2YQl4I8ZcNmVRP2NBUgSIISAJYBxxR7ku2xYufUAVmzeh+ao3uHzRjQdf/v4IGr9MSyZU3HUmRdJkpB7JNDY1cHREKCva66IiKh3MNgQEbVSkufC3HFFWLX9EAQSwSOqmwjHDSyYMrzH/1LfG4GpZSlbjl2Bx6EiGNOhGRYUSUau04ZI3Eh2P3OqMkYX5eDGpVtQF4qnPI8sJWaLdMMCABgWoBsm1u6uAwDcOW9su3srsgSP0wbfIGwI0Fc1V0RE1LsGxz+3ERF1wz3zx2PBlOEQAmiKaBACWDBleLILWU+0BKZQ3EAgpkM3LQRiOsJxA3PHFXUYmKqbo9i6txHVzVFUN0fx7s7DcNkUOGwKZEmCz2WHyyYjqltw2GQU+5zIc6mwqzJkWcKTG/e1CzV5LhtK890wTQsCgIXEvjhNER1x3cSmygbUBr9+jCrLGJLjwMh8Nwpy7IMu1LRdQmhTZHiciXqiliWERESUGThjQ0TUhsdpw/0Lp/R6TUVLMFqzqw5NEQ0OVekwMHW09Gns0ByENQN5LjvQqkSmyONETSAKwzARjRuI6la7GhqbIuHcicPw4d4m2BQJQggYqZcAAGKGBTOioT4Yw8h8F3wuG3IHeYezvqq5IiKi3sdgQ0TUic46kfVUVwNT66VPPldiidn7e5tgGBbitq831QQA3bKQc2Q2YW9DJOV5ZAmYP7kYN84owzCvE795czfW7q6D3GauXpYAVZFhmBYMU2BIjgOl+e5ee93ZrK9qroiIqPcx2BAR9bOjBaaWpU85dgVOmwLLEnDbVVgAmg0dwZgBAcCpKgjEdDRHdBiWQGM4tTHAjNFDMG9CESaV5CXbPS+ZUwEAWPdlXfI6CUfaRFsCQgAOmwKHjauUW/RVzRUREfU+Bhsion7Q1WVtB5sjiGoGPE4brFZLypyqAqfdxKThXnxRE0RdMN5uHxoAmFaeD7ddxc7aIB55NwC7qmBaeUGy29md88Zi3qRh+OnL2xHVTBimgGUJKLIMt0NBntvGWYg2urqEkIiI0ovBhoioD3WnVXAgpsMSiWVhcSN1yVnMMKFIEkwB1Ie0dvc5ZWQeFs8ux5ufH8ba3XVw2xX4XHbEO+h2dsrIPMybOAxv7aiF065ClSUYlkBcN3H2+KGchWijr2quiIiodzHYEBH1oa60Co7pJhrCGuK6iaJcB6aVF2Dt7rrkkrOwZqAprEE3BepCDSnPP6HYgyWzK3BqWT5qg3FsqWqE264g50goUu0qBIAtVY1oimgYN8yDXIeKn1w8CQ5VwZpddYgdqRfhLMTR9XbNFRER9S4GGyKiPtK2VTCQ2D9GILGsaV9jBE6bjFDMSHlcSy3Mxq8acDAURezIfjOtVRTm4NZZ5Zg5ekiya1l9MAbNMOFzte/gFYwlanBaxsFZCCIiGmgYbIgordL1xbqz+/bmeDprFexUZTRGNHxyoAmThvtSztUG49jXEIIkAf6ojnibUDMiz4lFM8tx1vih7faUKfQ4YVeV5DI2WZagyBLicQNOm9ph7QxnIYiIaKBgsCGitOhO7Ul/3Pe2s0bjkXf39Op4OmoVbFkCobiR2Pgy15m8Nhw38Lt392Dt7nqE4gbatgUozLXjphllmD+5GKrScdeyYZ7EMrb3dtdBkSW47SpCcYMdvIiIaFBgsCGitOhK7cnx6GzmpbP7bq5sQGNY69XxtG4VbAkBmyIjqpuIaibOHFuUbMOsGRbu/cun+OxgoF2gsSsyFs+pwDdPHgG72nkbZlmS4HXZcN83J+O//r6LHbyIiGjQYbAhon53rNqT6uae7+Z+tJmgQMzo8L66JfBVXRjFXkevj+efzx+HmG5i3Zf1CMc12FUFZ44twpI5FTAtgb9/VoPlG6radTqTJSDHocJtV3DmuKJOQ40qy/C5bPA4E0vPALB2hoiIBiUGGyLqd53VnrhsCpoiGmr8PQ8SR5sJWviNER3eV5UlWEJAllPDw/GOJxDT0RzV8Y9njcZlU0tRH4yh0ONEUa4da3bWYfmGKhxoiqY8RgKQ57ahwG2HAOCPaqgPxpKzOy2aIhoimoGKwlz43O2XyrF2hoiIBhsGGyLqdx3VngBA9Ejb4e5uENkyOwFIR50JWviNkuR9BQDDtKAqMgxLQJYkWFZqoX5PxxPVTDSE49BaFf4P8zgwNNeOzZWN+NcXK7GnLtzucTl2BcM8jmQNTUgzYFcVFHq+rsUxLYFl6yqxfk9Dv9YmERERZToGGyLqd61rTwQSMyNR3ex2kXvbZWcQQCBmYGR+6uNbZl4AgZmjC/DStoMwTAEhBCRJgqpIKC90ozmiIxDTezwezbDQGE7MpLS1bX8zHn+vEp8fCqQclyXg/EnFMC0LH+xtQsy04JQkxIzUWpxchwqf24ZfvLIDb+yo7bPaJCIiomzFYENEadFSzH48Re5tl52FYjrihomD/hgqCnOS17WeeRFCQkuFfsv+LxDASSV5yHGoPRqPaQk0RTQEYwaESC3/33EogGXrKrF1X3O7x80dV4RFM8sxaogb4biBx9+rxJaqRvijX9fi3DVvLEry3bCrcp/WJhEREWU7BhsiSovj3SCyoy/5+TkONEd1RDQDjRENHoeaMvMCJDa9LPY54VAV6GZiqVhYM7DpqwY8/48zsfAbJfiiJoAJxV5MLcs/6hiEEAhEDTRFNFhtAk1lfRjL1ldi/ZcN7R43rTwft86uwLhhnuSxHIeKO+eNRW0wjvpgDOWFuZhQ7ElZqteXtUlERETZjsGGiNKqp0XunX3JH+5z4UBTBIZptZt52VUbTD5GliTUhXSEYgYsIWAJgWse2wgBQDetY9auhOMGGsNaMhy1qG6K4smNVXhrx+F2rZtPLPFhyewKnFjqQ0dkScK4obk4vSy/w71qers2iYiIaCBhsCGirNTZl3zNtFDkceLhq08BIFJmglo/JhAzEIjqkCUJEgAhgANNUeQ4FJTmuzutXYnpJhrDGmK6mTKeumAcT2/ai9e218C0UiONTZFw2qh83HvhBOR2EJIUWTrSstkG5UjL5o70Vm0SERHRQMRgQ5RBuPdI1x3rS35Hy8haHvPKJwcRjBloiRAWAElKzJhohoAQiaVyrWtXhnocaAprCMVTGwM0RzT8ect+vLStGrqZGmhUWcKQHDsUGfiiNoil66pw57yxyfM2RYbXZYPXqX5d73MMvVGbRERENBAx2BBlgKNtKskWvp3ryZf8e+aPx+FgDG9+fhgCAookIceuIKKZUCTAFAK6acGuynDZFDSG49j4ZQMcNgmFHmdyP5lQ3MDKDw7g+a0HEG0ze6NIErwuFYU59q8Di2RgS1UjaoNxjMx3Ic9tR66j+7+Cj7c2iYiIaKBisCHKAEfbVJItfL/W9st8T77ke5w2/Nslk/FptR+WJeA7UqNTWReGKRL72bQsbQtGdYTiJh5avQOmELCrCk4dlYcijwN/+bAagVjq7M2QHDvOnTgUb35egzy3PWUWxqkqCMR0CMtCab77uN8LbsBJRESUisGGKM3YwvfYjjWj1d0v+SV5Lpw7YRhWbT+EmG7CZVNgV2WENQNOmwwhBBrDcdSF44AAbKoNOYqMxoiG1z6tadcUwOtUce20UfjmKSPgjxl4b3c94oYJ1Z74FSvLEnTDhNuuoqwwtxffGSIiImrBYEOUZmzhe2x9MaPVdhlbntuGYp8DobiJhnAciixBPbKkzDAFagNRGG2aArhsCq48rRRXTi1FzpFlZU6bgmnlBVi7uw44sswtqic22zxagT+XlhERER0fBhuiNGML36Prqxmt1svYqpsicNlV5NiV5D4y9aE4/uvvu9AQ0ds1BQCAcycU4Y6zx8LnTq2BkiQJd503FjkOFeu+rIc/qh+19of1VURERL2DwYYozdjC9+h6c0ar7ayIZQnk2BUM9TiTG2wOzbVjb30Yf9y4D6G42e453HYFuQ4VS84cnRJqJEmCx6nC57LBpsj4j8tO7NIsDOuriIiIegeDDVEGYAvfzvXGjFbbWRG7ImPm6ELcPLMMTpuSvO6TA81Yuq4Kn1b72z1HrkOF2y5DNwVmnDAk2R1NkiR4jwSatptqHqv2h/VVREREvYfBhigDDNQWvr3xeroyo3Ws+7SeFfE6bYhoBv7+eQ1iuok7543Frtoglq2rxJaqpnaPHe5zQjctCCGgyDJmnFCAJXMqIEsSvC4bfK6jb6p5NKyvIiIi6j0MNkQZpL9b+PZVkOrtupHOZrRuO2s0fvLS9qPep2VWxG1X4FAVCCGQY1chAKzfU4+aQAybKxvb3fO0snzcOrscE4q9ybqbQo8TJT4XfC4bPE4VchcDTWfvM+uriIiIeg+DDdEg1NcF671dN9LZjNZPXtqecp9QTMfLH1cjHDfw66tPAQDsawgjohnwOm0QR+podNNCIGogFDdQH0oNNVNGeLF4dgVOHpmXPDbM48DI/ESgyXWoKfvTHE1X2lSzvoqIiKh3MNgQDUJ9WbDel3UjrWe0Wt/HbVdRE4ghFDNgCoGXPz4ISwh8/9yxwJENN+OGCSgyGiI6/FG93XOPKcrFrbPLMb2iICW4uOwKfC4b3Pbu/7rsyvvM+ioiIqLewWBDNMj0dcF6f9WNtL5PTSCGQFSHLElQIKBbwJs7DkMI4M55Y3FKaR7e3nkYmmG121xzZL4Li2aV48xxRZBbBRq3XUWe25bSXADo+vK9rr7PA7W+ioiIqL8x2BANMn0dPPqrbqTlPqGYjlDMgARAlgBTSFBlwO1QsKmyAbZ3Zby7qw5xw0p5vMum4NtnVuD0iiFoCsdRF9IwzOPoNNB0d/led9/n/q6vIiIiGmjkY1/ytQceeACnn346PB4Phg4dioULF2Lnzp0p18RiMdx+++0YMmQIcnNzcfnll6O2trZXB01EPdc6eLTWW8GjpW4kFDcQiOmJepaYjnDcwNxxRd3+8l7dHMXWvY2obo52eJ9ATIdhWZAgYFoClhBw2RUYhsDhQBwrtx5AtNVr9ThV3DKzHH9aMg1V9RH88PmP8bOXP8MPntuGx9+rRI5DaRdqgK+XlckSkO+2Q5aAVdsP4aHVO9tdC/T9+0xERESpuhVs1qxZg9tvvx2bNm3CG2+8AV3Xcf755yMcDiev+ad/+if87W9/w/PPP481a9bg4MGDuOyyy3p94ETUM70dPDpyz/zxWDBlOIQAmiIahEC360aCMR0/eWk7rv39Jtz2pw9x7e834ScvbUcw9nV9zG1njcaMEwohAdAtQAgBmyojrJlojGgpy848ThX/MKcCz3z7DNw0owxPbtiLtbvroMjAkFwH7IqMv39e02FQabuszKbI8DhtyHGoyWVlbfXH+0xERERf69ZStNWrV6f8+YknnsDQoUOxdetWnHnmmfD7/Vi6dClWrFiBc845BwCwfPlyTJw4EZs2bcIZZ5zReyMnoh7r64L13qgbOVrh/b0XTkBjWINmWPh/CybAFBbe290A3bQQ01OXnDltMq6cWoorp45ErjPxK682GMcHe5vgdarwuhJLxRyq0mmdUU+X77ExABERUf85rhobvz+xO3dBQQEAYOvWrdB1HfPmzUteM2HCBIwaNQobN27sMNjE43HE4/HknwOBwPEMiYi6oL8K1o9VN9LZ/TsrvLeEwFs7anHhScMxzOOAEALvfVmPnbWhdjU0sgRcctII3DSzLCWQ5DpUHA7GYFgWPM6uBZWe1g2xMQAREVH/6XGwsSwLd911F2bNmoUpUxJtS2tqamC325GXl5dy7bBhw1BTU9Ph8zzwwAO47777ejoMIjoO6SpYP1YhftsZEksk6mdUWUY4rqEuEMW+hjCWravCztpgynPLEnD2+KH49pknoMjjSB7PdarIc9lhV2XoluhWUDne/WaO9j4z9BAREfWOHgeb22+/Hdu3b8e6deuOawD33nsv7r777uSfA4EARo4ceVzPSUS9q7e/fB9rf5eWGZKoZgB2FZaVqJaJGSYACY+u+Qo7DqUGGgnA2ROGYtHMcpTkJ8YoSRJyHEoy0LToSVDp7WVlfb1JKhER0WDTo2Bzxx134JVXXsHatWtRWlqaPF5cXAxN09Dc3Jwya1NbW4vi4uIOn8vhcMDhcHR4jojS61hfvrsTeFquBaSUZWaaaUGRJThsSrK+ZbjXiekVBXhzRy10S8CpKgjGdDRFdBiWQENYS3nuWaOHYNGscpxQlAsgEWhyHYm2za1nZFrrblDp7WVlfblJKhER0WDUrWAjhMD3vvc9vPjii3j33XdRUVGRcn7q1Kmw2Wx46623cPnllwMAdu7ciX379mHGjBm9N2oi6hedffnWTRM2RenSbEPbcAQBBGIGSvKcqG6OIhQzYAkBCYAiS/h0fzOMEV7cNKMMmmFhw5561AXj0M22W2sCJ5f68O0zT8DE4V4AXQs0LXoaVHpj+V5fb5JKREQ0GHUr2Nx+++1YsWIF/vrXv8Lj8STrZnw+H1wuF3w+HxYvXoy7774bBQUF8Hq9+N73vocZM2awIxpRljnal+9XPqmBTZHgc9mOOdvQNhyFYjrihomqhggAQJYkKBJgWAKGIfDChwdwb/FEBOMG4oaF+nCiXXRrNkWCQ5VRPiQHBbkOfHbQj/LCXEws9kA9RqBpKx11Rn29SSoREdFg1K1g8+ijjwIAzjrrrJTjy5cvxy233AIAePjhhyHLMi6//HLE43FccMEFeOSRR3plsETUfzr78q3KEqKaiVyP/ZizDR2Fo/wcB5oiOsKaCVkCFAk4UkIDl03Gxwf8+M/VX+DtHYdhWKmJxq7KKMyxI8euIBg38Mbntdj0VQMEBJw2NWtqVHraZY2IiIg61+2laMfidDrx29/+Fr/97W97PCgiSr/OvnyH4wYAgRxH6q+PjmYbOgtH+W4bwpoJCYmZGlmS4HaokAAcDsbx989qU66XJaAw1wGfU4UkSQCAiG4iqpvwulTkux1ZVaNyvF3WiIiIqL3urdkgokGj5ct3KG4gENOhmxYCMR1x04LLrsBsM5vS0WxD63AEJP5xxLQEdEtAkRIBZ5jPiRyHinDcQCBmpDznUI8D3z7zBAz1OGBTJEiSBFmWAAmIxE0osgSfyw6bIsPjtCHHoSZnjTLdPfPHY8GU4RACaIoklttx804iIqKeO64NOoloYOuoc9jFJ46AZlh464vaY842tISj1z49CNMSsCkyYoYJzbBQku9CXTCOxoiONhkJ+W4brp8+ChefNAJ2VUatP4a1u+ugyBLcdhWBqA5LCHidtpQ2ztlUo8LNO4mIiHoXgw0RdaqzL9/BmA67KnepVfJtZ41GMKZjc2UjIpoGmyJjVIEbB5qiiOpWyrWqLOGaaSNx7emj4LIrAIBch4p/u2QS/vvN3cn7JQKOAq8z9VdYNtaopGuTVCIiooFGEl0pnOlHgUAAPp8Pfr8fXq833cMhoqM42mxDKG6gKaxBNxPh5VAghr9vr8Hrn9WiJhBLudauyLjwxGIsmlWeLPxPtG1O3Viz9f1+9+4erNp+CDkOtd2sUabX2BAREVHXdCcbcMaGiFJ0Z2lUR7MNbQONEAIb9jTg9+9VYn9jJOVamyLhkpNG4Lrpo1CQk2gw0FGg6Whc3d1gk4iIiAY2BhsiAtB+I82jbbrZkbaBBgA+3NeEP6z9CjtrQ+2uP2/SUNw6qwLDvE4AgNuuIj/HBoeqdHlcLcvkPj3QDEDCiaW+jG/1TERERH2DwYaIALTfSLOr7ZNDcQPNEQ2a8XWg+fxgAEvXV+Kjfc3trnfZZNgUGW6bimFeJ5w2BQU5djhtSrtrjzWue+aPx+/e3dPjMEZEREQDB4MNUYbqz25ZHW2kKUSiGP+tHbX47lmj240hHDfQ1CbQ7KkLYdm6Kmz8qqHdPXLsCoYcCTAhzcD7VY0whcCIo7y2jsbVejPQsGZg7ZHzrUNPWDNw/fRR7DRGREQ0iDDYEGWY410S1hOtN9I0LYGaQAyhmAFLCAghcP/fPsMvrzwZHqetw0BzoCmCJzbsxTtfHEbbbiSqLGGox4HcIxt6SpKEHLuKQExHIKp3eVxtn7M+GE+Gmpb3RZYk1Ic0vLztINbuqoPbrnIGh4iIaJBgsCHKMD1dEnY8Wm+kGYgZCER1yJIECQAkCZurGvHvr+7AHeeMSQk0hwMx/HHTXqzeXtNuL5rxxR5cfmoplq37CpIEQAJUWYYsAcF419oytx6XTZGToSsQ1WFZApAAwxJw21UosoSaQAxRzQCkxH43soQ+f++IiIgoMzDYEGWQYy29qm7um40nWzbSfOWTgwjGjESgASAAeJwq3DYFa3bV4ZvfKMEwjwNNEQ0rNu/Dyx8fhG6mJpqKwhzcOqscM0cPgSRJ+OygH+8lN9eUENY63szzaONatf0QBAB/REcglpjlyXWqiGhmMoQVeRwIxQxIkgRZkuCyKbCrff/eERERUWZgsCHKIJ0tvXLZFDRFNNT4++7L+T3zx+NwMIY3Pz8MAQEZQI5DRUGOHUIA/qiGfQ0hvPLxQbzw4QHE2myuOSLPiVtmluPs8UOhyBIkSYLHqeJnl0zCr9/Y3eO2zC3XvbWjFsFYIsR4XTYUe52oCcTQHNEQiOpw2RQYlgVJkpDrVJPtovvjvSMiIqL0Y7AhyiBtl161iOpdW7p1PDxOG35y8SR8vL8ZhiXgcdpgkxNzNwFNh2YI/PxvOxDWzJTHFebacdOMMsyfXAz1yJjb7kXT0pa5J80QPE4b7l84BbPGFOLHL36KfLcNbnviV1ex1wnLEgjGdITjBmRJgtMmo/hIC2mgf947IiIiSj8GG6IM0nbplcumIKp3felWT5mWQCCqw7QEplcMwdrdicYFUGQ0RDQEo0a7pgA+lw3XThuJb548Ao4jrZqP1rq5o808u+PEUh9yHSrMVsU8iizB57bBbVfwb5dMxt8/q8Ha3Yluaf313hEREVFmYLAhyjAtS696unSrO3TTgj+qIxgzIEQiMCyZUwFLCKzdXYeamNGuKUCOXcFVp43E5VNLkjMnNkVGQY4dOY6++5VyrNA3f0oxZo0Zkuwo19fvHREREWUWSbR8m8kQgUAAPp8Pfr8fXq833cMhSpu+3MdGMyw0RzWE4yZa/wqwhMDaXXVYtr4KB5qiKY9xqDK+9Y0SXH36SPhcicYGiiwhz22H16lCkiT0ta62wu7PPYCIiIio73QnGzDYEA0iccNEcyRRj9KaEAKbKxuxdF0l9tSFU86psoSLTxqO66ePwpBcB4DEXjReZ6IdtSz3faBpi8GFiIhocOhONuBSNKJBIKYnAk1EM9qd+3h/Mx5fV4nPDgZSjssScN6kYbh5RjmKfV8X47d0Smvd3KC/HW+9DhEREQ08DDZEA1gobsAf1RHXzXbnvqgJYOm6Kmzd29Tu3NxxRbhlZhnKhuQkj9lVGUNyHHDZ2zcGICIiIko3BhuiASbR/thAIKZDN6125yvrw1i2vhLrv2xod25aRQFunVWOccM8yWOKLCE/xw5vqxoWIiIiokzDYEM0QBimhUDMQCCqw+qgdK66OYonN1ThrR2H27VuPrHEh8Wzy3FSaV7ymCRJ8LlsyHPZ0lJHQ0RERNQdDDZEWa6zDmct6oJxPL1pL17bXpOyBwwAjB2aiyVzKnBaWX5KV7Nch4r8NNfREBEREXUHgw1RlorpJvzR9h3OWjRHNPx5y368tK0aupkaaMoK3Fg0qxxzxhamBBqHTcGQTjbYJCIiIspkDDZEWSaiGWiO6Ih10BAASDQMWPnBATy/9QCiba4Z7nPi5hllOHfiMCitlpepsoz8HFvKXjBERERE2YTBhigLCCEQ1kw0RzRoRvuGAEBiBuelj6rxzPv7EYilzuIMybHjhjNG4cITh6csL5MkCXkuG/Lctn7ZYLMnuGcNERERdQWDDVEGO1aHMwDQTQuvfXoIT23ah8awlnLO61RxzbRRWHjKiHbLy3KdKgrcdqgZWkcTjOl4aPVOrNlVh7hhwqEqmDuuCPfMH8+ZJSIiImqHwYYoA5mWgD+qIxjT2xX8t77mzR21eHLDXtQEYinnXDYFV55WiiumliLXoaI2GMeeuhAKPU6MKnBnRR3NQ6t3YtX2Q4lGBm47YrqJVdsPAQDuXzglzaMjIiKiTMNgQ5RBNMOCP6ojFDc67HAGJJalvbe7HsvXV2FvYyTlnF2V8c2TR+C6aaPgc9sQjhv4zZu7saWqEZppwWVTcPb4obhn/viMDjbVzVGs2VWHXIeanJ2xKTIEgDW76lDdHOWyNCIiIkrBYEPUA63rPgAcdw1ITDcROBJoOiOEwPtVTVi2vhK7akMp5xRZwoVTinHDGWWwABxojiBmOvHM5n1YuzsRELxOO+KGlRWzHjX+KOKGiXy3PeW4y6agKaKhxs9gQ0RERKkYbIi6oXXdR1Q3ENVMABLcdgVOW/drQKKaieaoduR5OvfJgWYsXVeFT6v9KcclAOdOHIqbZ5Yjz2XD4+9VJmZnDBOKJCGkmShw25B3JCDYVSUrZj2KfS44VAUx3UxpdhDVE7U2LYGSiIiIqAWDDVE3tK770A2ByJFAoiqJcNPV2ZBQ3IA/qiPeScvmFrtqg1i2vgpbKhvbnZs9phCLZpWjojAHAPCbN3dj7e46uO0KfC47QvFES+iQJiM/5+vHZcOsR0meC3PHFWHV9kMQSIw5qpsIxw0smDI8Y8dNRERE6cNgQ9RFres+HKqCiBaDKidmEyJxE8O8zqPOhgghEIwb8Ec673DWYm9DGMs3VGHtrvp2504ry8ets8sxodibPFYbjGNLVWMy1MhSoialMawjFDOgmRbsR2Y+smXW45754wEk3s+miAaHqmDBlOHJ40REREStMdgQdVHrug/NsGAJAfXIJpeGJWAcKc5vOxvS0rLZH9VhWEcPNDX+GJ7cWIU3Pq9F22Zok0d4sXh2BU4ZmdfucfXBGHTTwpAce3LjTbsqIdehIhDT4Y9oyHPbs2rWw+O04f6FU7iPDREREXUJgw1RF7Wu+3CoCmRJSoYPWZKgKnLKbIhpCQSiOgJHadncoiEUx9Ob9+HVTw7BaHPtmKJc3Dq7HNMrCjrcRNNhUzC5xAe3XUXcsGBXv+525nGqMCwLsixl7axHSR4DDRERER0bgw1RF7Wt+3DbFQRiOgDA67IhdmQ25ILJxXCqMvY3RmB10rK5hT+q49n39+PFj6oRN1Jnc0rzXbh1VjnOHFcEuYNAo8oy8nNsyUYFHdWkRHUT3/pGKb571uhuz3pwpoSIiIiyCYMNUTe0rvuwqYmGAYAEuyLDsgTOGjcU104bCX9UP+rzRDQDK7cewPMfHEC4TUe0oR4Hbp5ZjvMnDUsuK2tNkiTkuWzIc9tSZnCOVpPicdq6HE5ad36LG4kZqO52eyMiIiLqb5LobBfANAkEAvD5fPD7/fB6vcd+AFEatJ7NiOsmvjwchMdlxzCP46iPi+smXv74IFZs2d8u/OS7bbh+ehkuPmk47Krc4eNzHSoKcuxQlY7Ptx1bT2ZafvLS9mTnN6ctsfQudKQuJ5P3viEiIqKBpzvZgDM2RD1QkudCnsuG5iPhZMxQz1GvN0wLq7bX4I+b9qIhpKWcy3WouOb0kfjWqSVw2ZQOH29XZRTmOuDs5HzbsfV06Vjrzm8tszM2Rc6KvW+IiIhocGOwIeqG7rRsBgDTEnj7i8N4YkMVDvljKeecNhlXTC3FVVNHItfZ8Y+iLEnIz7HD5+qfJWCtO7+11l9737Cuh4iIiHqKwYaoCyxLIBDTEYgax2zZDCQC0PovG7BsfSWqGiIp52yKhEtPHoHrpo9qFyBa8zhtKGjVvrk/tO78Zmu13K2v975hXQ8REREdLwYboqMwTAv+qI5gzDhmhzMgEWi27m3CsvVV+KImmHJOloAFU4bjxjNGYajX2elzOGwKhuTYu7TsrLe17fzW0l2tr/e+eWj1zmRdT77bjphuYtX2QwDAuh4iIiLqEgYbog7EDRP+qI5w3ERX+2tsr/bjd2u+wueHAinHJQDnTBiKm2eWoTTf3enj27ZvTpejdVfrC6zrISIiot7AYEPUSkQz4I/qiLZpwXw0Xx4O4fdrv8IHe5vanZteUYAlcyowuii308fLkgRfB+2b08XjtOH+hVP6rd4l3XU9RERENDAw2NCgVt0cxaHmCDxOO9x2pUsNAVrsa4zgifVVeHdXXbtzDlWGXZFQ7HUeNdTkOlUUuI/evjldjqe7Wnekq66HiIiIBhYGGxqUgjEd/7nqC7y7sw4xw4RdkTGtPDG7kuM4+o9FTSCGpzbuxeuf1cBqs0rNqcoozLXDbVcR0gxsqWpEbTDebn8bl11BQY4dDrX/62gyTbrqeoiIiGhgYbChQUczLNz38ud464tauO0KfE4b4oaJtbsTMy93zhvb4eMawxr+tHkfXvnkIHQzNdEoElCY64DXqSaXkznVxFKqLV81YNoJQzDM44BNkVGQYz9meBps+ruuh4iIiAYefruiQSOmJxoCfFUfxvo99XDbFeTYEz8Cql2FADqcYQlEdTz7wX68+GE1YkbqUrWSPBcuO7UEz3+wH4osJUNNTLdQG4xCNwWe2FCFZ97fjzljCvGvF08cdKGmK7U6/V3XQ0RERAPP4PqGRYOOEAKhuIFAzEBcTzQEqA/GoBkmfK7UYnWnqsAf1VAfTGykWd0YxpaqZrz66UGE46nNBIpyHbhpRhkumDwMqiJjX0MEa3fXwbQEwnETwbiRvNa0BBQJeHvnYThsyqBpX9yTvWn6q66HiIiIBh4GGxqQTEsg2MmGmoUeJ+yqgrhhQrV//SMQM0yoiowXP6zGB3ubEIwZaNvoOc9lw/VnjMIlJ42AXf260H3JnAoAwBuf1yCiJ+4nAVBkIKIlntfjVAdV+2LuTUNERET9icGGBhTNSGyoGYobne4/M8zjwLTyAqzdXQeBxExNzDARiRtQZBnv7KpD24eqsoSbZpTh8lNL4bK3L/jPcai4ZvoobPyqHjbFQihuQJUlyLIM0xIIxQzku20IxY1B0b6Ye9MQERFRf2OwoQEhqiXqZyKaceyL8fUMy5aqRjRH4rCEhLgpEI1qKddJAHIciVqc8yYXdxhqWtQHY7AEMCTXjqhuJWd7ZAkwLIFw3Dhq++KBVF/CvWmIiIiovzHYUNYSQiCsmWiOaNCMru8/AyRmWL5/7his+qwWKzbvxcHmWLtr8lw2FLhtgCQla2/atm1uYVdlTC7xwW1XYYnE/jSBqA5YSM4cxU0L500qbveFvqNalNPK8vGtb5TghKG5WRkAuDcNERER9TcGG8o6liUQjBnwR/V29TNd9eG+JixdV4kdh4LtzrntCgrcdkACBCTEDRN2VUGhx9nuWkWWkJ9jh/fIcquW/Vhy7AosK9G4wBICbruKi08c0WH74ta1KF6nDYf8Uby0rRqrttegyOM4ZsF9XzmeGSTuTUNERET9jcGGsoZhWgjEDASiOqxO6meOZcehAJauq8SH+5rbnTtrXBEsIbDpqwYc8keTxxVZwryJw9rN1nhdNuS77VBkKXms9X4sDpsMt92BE0t9+MF54zCu2Nvunm1rUaqbo4jpFmRJgmFaMIXo94L7nnQz6wj3piEiIqL+xGBDGS9uJOpnwnGz04YAx7KnLoTl66uwYU9Du3NnnFCARTPLMXaYB7/6+xeJwhoAQgCShMSfpa/v67QpGJJrh0NtX2/T3f1YWteiaIaFUMyALEnJuhynKkOVpX4tuO+tbmbcm4aIiIj6E4MNZayIllhuFtXMY1/ciQNNETyxYS/e+eJwu9bNJ5f6sHh2BaaU+AAAtcE4PtrnR1GuA3ZVgWFaUBUZccPER/v8qA9rmFjs6dKsRVf3Y2ldiyJLEiwhoMoSLAHIkgRVkWFT0G8F933RzYx70xAREVF/YLChjCKEQDBuwB/RoZs9q58BgMOBGJ7atA+rth+C1SbRjC/2YPGsckwty8fhkIbPDvpR6HGmbNypyhJscmJGRlIVBGM6JIher3NpXYviUGVIR2ZqgMRSN7siIxDT+63gnt3MiIiIKFsx2FBGaNlQ0x/VYbZNIt3QFNGwYvM+vPzxQehm6vOUD3Hj1lkVmDVmCCKaif9560tsqWqEdqQ5wJQR3uQMTcvGnbIswTBMuOwqRuS5j+s1dub/t3fvwVXW977HP89az3rWLcnKBciFkIs1oBXBigIRld3KrmVbK9r2WLdtabHTMy32SD0dZ9zjpY7u0bH/tM7x1J6jldpua9W9saft9sK2NqAgCJYKXiDUhGsSgpCslWTd13P+iFmyICEkWSuLBe/XDDPm+a08z0/5mclnnt/3+zu2FsV0GIomUvJZpqb4LQUj8UktuKebGQAAKFQEG+RVPPnxgZqRxLgbAkhSXyShZ7fu0/Nb9ysSz3zTUx3w6NuLGvTZWdPShf6Pr2/TutZu+SynAl5L0URSW/YcVcDrUm84LltSkWUqHE9qIJbMabA4thblw+6Q1vz1oLa0H1Xvx29qJrPgnm5mAACgUBFskBeReFLBcFx90VM7UHMk4XhSa94+oN9t2adQJPNeU4osfWNhvZbOrpJ5zNuHrlBUm9uPyGcNHrwpSaZlyv74fpedW6F39vVOerAYqkW5omlaXgvu6WYGAAAKEcEGkyobDQEkKZZI6Y/vdOjfNu3R0YF4xliJx9TNC+r0pbk1crtO7Fx2bC3NsbyuwVqaFYsaVRXw5rWTVz4L7ulmBgAAChHBBjln24MHVfaG44olxt8QQBqsxXnlvS79akO7DoWiGWM+y6mvzqvVV+bVyu8eeWlPKfbIMp3pWhrDMAZrW2IJeVxm+hf5s/2Xef4bAACAQkKwQc6kUrZCkcFAk0hNLNCkbFvrdnXryTfate9oOGPMbTp0/Wem68ZLZyjgHb1rWWWxW/MbyrWutVuGYchvOdUXo44EAACgkBFskHWJZErBSELBcHxCDQGkwbc9m9qO6Jevt2t3d1/GmOkwdM2can19QZ0qitxjuu+qf2xSkcfU+tbD6glPfpE+AAAAsotgg6yJJpLqDcfVH03KnmCgkaS/7evR46+36d2DwYzrDkP6x09Xanlzg6oCnjHd0+1yqsJvyeNy6l+vv5A6EgAAgDMEwQYTFo4NBpqB2MQ6nA3Z2RnSE6+3acueoyeMXdk0Rd9e1KD6Cv+Y7mk6HCrzu044YJM6EgAAgDMDwQbjYtu2+mNJ9QzEJtwQYEjb4X6t3tCu9a2HTxib31iuFYsaNLOyeEz3NAxDJR5TZT5Ljo/PsAEAAMCZh2CDMclmQ4AhB3vC+tXGPfqv97p0/Aa2C6eX6JbLGzWntnTM9/VaTlX43bJMx+gfBgAAQEEj2OCUxJMpBcNxhSKJCTcEGNIdiuo3m/boP7d3KpnKvGfTtCLdcnmjLm0ok2GM7U2L6XCovMhS0UlaPgMAAODMwm9+OKlIPKlgOK6+aHbqZySpdyCupzfv1e//dvCEbWx15T59e1GDrmyaMuZAw7YzAACAsxfBBsPqjybUE44rGk+e9HNdoagOhyKaUuxRZfHJWy73RRN6fst+Pf/2fg3EMu9bVeLR8svqteT8SjnHEUrYdgYAAHB2I9ggLZWyFYoOnj8TT568fqY/mtDj69u0uf2IYomkLNOp+Q3l+s4VjfIftwUsEk/qhW0H9czmvQpGMt/8VPgtfX1hnf7pwmq5nGMPJU6HoXK/dUK3MwAAAJxdCDZIH6gZisRPqHUZyePr27SutVs+y6mA11I0kdS61m5J0m1LmiQN1uX85/YO/ebNvfqoP5bx/SUeU1+bX6dlF9XI43KOa94lXpfK2XYGAAAAEWzOauM9ULMrFNXm9iPyWU75rcElZFqmbEmb24+oozei7ft7tHrDHnUGIxnf63U59dVLavWVebXjLu4/9pBNAAAAQCLYnJUGYoPtmsOxk9fPjORwKKJYIqmA18q47nY61N0X1f98dps6g9GMMZfT0LKLpuum+TNU6sv8vmOdrGbHYRgq81sKeNl2BgAAgEwEm7OEbdsKRk6tfmY0U4o9skynoonk4Jsa29ZALKlDfVHFk7b6op8EJqfD0D/NrtLXF9Zr6kmaC4xWs1PkMVXhd4+rsQAAAADOfASbM9x46mdGU1ns1vyGcq1r7VYkkVJ/JKHIcW2bDUlXnT9Nyy9r0PRS76j3HKlmx+Ew9OANF7LtDAAAACdFsDlDjbd+5lT9w6yp2vjhRzoUip4wtujcCq1Y1KjGKf5TutewNTtuUw7D0NY9R/VRf+yUwhEAAADOXgSbM8xE62dGs+ejfj25oV3rdh0+YWxefZlWLGrQ+dUlY7rn8TU7Doch02HI4TZ0dCCmzt4wwQYAAAAnRbA5A9j24PkzvQMTr58ZSWdvRL/a2K6173Xp+B1tF9SU6JbLG3XRjNJx3XuoZieWSMrrs+QwButowvGE3KZTVQFCzenuQE9Ynb1hVQW8hFAAAJAXBJsClkzZCobjCmaxfuZ4H/VF9ZtNe/WndzqUOO4Zn5rq14pFjVp4TrkMY/xF/TUBj65smqpXP+iSM5qQ1+VUOJ5UfzShpbOr+UX5NBaKxPXwSzvVsqtb0URSbtOpxTOn6o4vzOLQVAAAMKkINgUolkipNxxXXzSRk/oZSQqG43rmrX1a89cDih7XGKC2zKsVixp05cyp6bcr42EYhko8psp8lu764vmyTIdadnXr6EBMbtOppbOrdccXZk30XwU59PBLO/Xijg4VuQf/HiPxpF7c0SFJun/Z7DzPDgAAnE0INgUkHBtsCDAQS+TsGQOxhP596wE9u2Wf+o+r05lW7Nby5np9/oKqCbdd9lmmyv2WLNMhSSr2uHT/stlsaSogB3rCatnVrSK3mX4743I6ZEtq2dWtAz3URgEAgMlDsDnNDdXPBMNxxRK5qZ+RpGg8qf/3t4N6evM+9YbjGWNlPpduXlCvL86pTgeR8XI5HaoosuSzhl9600sJNIWiszesaCKpsuMOXPW6nDR9AAAAk45gc5pKpmzt7AqprbtP5UVuVZ7kcMuJSCRTeundTj21cY8O98Uyxorcpr526Qxd/5np8loTO0fGYRgq81kq8ZrD1uPwpqbwVAW8cptOReJJuZyfBN5wPEnTBwAAMOkINqeZWCKlAz0D+unaVm1uP6JYIinLdGp+Q7m+c0Wj/O7s/JUlU7Ze23lIqze062BPJGPM43LoyxfX6sZLZqjIM/rzukJRHQ5FNKXYM2wAK/a4VO63ht2+RvF54Zpe6tXimVP14o4O2RJNHwAAQF4RbE4Tx9bP/Oy/WrWutVs+y6mA11I0kdS61m5J0m1Lmib0HNu29cbuj/Tkhna1He7PGHM5DX1pbo3+eUHdCduLhtMfTejx9W0jBjCPy6lyvyWPa+S3PRSfF7ah5g40fQAAAPlGsMkj27bVFx08UHOofqYrFNXm9iPyWU75P65DMS1TtqTN7UfUFYqOa1uabdvauueonnijXTs7QxljDkP6wuwqfXNhvaaVeE75no+vbxs2gBmG9MD1F6polLdLFJ8XPpo+AACA0wXBJg+SKVuhSFzBcEKJVGZDgMOhiGKJpALezDcmHtOp3nBMh0ORMQebHQd69cs32rRtX+8JY587b5q+dVm9ast8Y7rnsAHMPVg/s3XPUfWG46MGG4rPzxw0fQAAAPk25hZX69at07XXXquamhoZhqEXXnghY9y2bd1zzz2qrq6W1+vVkiVL1Nramq35FrR4MqXDfVHtOzKgI/2xE0KNJE0p9sgynYomMlstRz7e6jWl+NTfqOw+1Kd/WbNd/+OZbSeEmuZzKvR/vzlPd11z/phDjfRJAHObg9vMHA5DltOhIrepWDKlzt7wqPc4tvj8WBSfAwAAYKzGHGz6+/s1d+5cPfroo8OOP/zww3rkkUf02GOPadOmTfL7/br66qsViUSG/fzZIBJPqisY0b4jAwqG40qd5FDNymK35jeUayCWVF8soUTKVl8soXAsqfkN5af0tmbvkQHd/8f39N1fb9WbHx7JGLtoRqn+102f0b9eP1ufmlo07n+noQAWSyTlMh1yOR0yDGNMoWSo+LwvmlAwElc8mVIwEld/NKHFM6fyBgAAAACnbMxb0ZYuXaqlS5cOO2bbtn7605/qrrvu0nXXXSdJeuqpp1RZWakXXnhBX/va1yY22wIzVD8TPe6NxGi+c0WjpMGamt5wTJbp1JVNU9PXR9IVjOipjXv08rudSh2Xnc6vLtYtixp1cX3ZmOYykpqAR1c2TdWrH3TJGU2MuyMWxecAAADIhqzW2LS1tamzs1NLlixJXwsEAlqwYIE2btx4VgSbVMpWKPLJG4jx8LtN3bakadQ2ykOO9Mf09Ka9+sM7BxVPZiaaxil+rVjUoMs+VTHs+TFjZRiGSjyDHczu+uL5skzHhEIJxecAAADIhqwGm87OTklSZWVlxvXKysr02PGi0aii0Wj662AwmM0pTZp4MqVgOK5QJHHSrWZjUVl88oM5Q5G4nt2yX/++db8iicwQNb3Uq29d1qDPnjdVjiwEGknyWabK/ZYsc3AH43hCyUifpfgcAAAAE5H3rmgPPvig7rvvvnxPY9wi8aSC4bj6oolJe2Y4ltR//HW/fvfW/hOeO7XIrW801+sLF1TKdI65hGpYLqdD5X5rxMNBTyWUcBAnAAAAcimrwaaqqkqS1NXVperq6vT1rq4uXXTRRcN+z5133qnbb789/XUwGNSMGTOyOa2c6P+4fub4jl65FEuk9Id3DurpTXt1dCCeMVbqdemfF9TpS3Nr0m9UJsowDJX5XAp4XRPexsZBnAAAAMilrAabxsZGVVVV6dVXX00HmWAwqE2bNul73/vesN/jdrvldo/9wMl8SKVshaIJBcPjr58Zj2TK1svvduqpjXt0KBTNGPO7nbrxkhn68sW18lrOrD2zyD247Swbb3227jmqV97rlNvl5CBOAAAA5MSYg01fX592796d/rqtrU3btm1TeXm56urqtGrVKj3wwANqampSY2Oj7r77btXU1GjZsmXZnPekSiRTCkYSo7ZqzraUbesvO7u1ekO79h/NPBfGYzp0w8XT9d8umaESb/a2crmcDk0pcmclJA1tP3vl3U5190XlNAyFY0lVlXjkdBgcxAkAAICsGXOw2bJliz772c+mvx7aRrZ8+XKtXr1ad9xxh/r7+/Xd735XPT09uvzyy/XSSy/J4zn1gyVPJ33RhLpDUdmTGGhs29abHx7RE2+06cPu/owx02Hoi3Oq9fWF9Sr3W1l7psMwVOazVOI1s9I9Tfpk+5nHdMjpMGTbUjA8uIVueqmXgzgBAACQNYY9mb+xn4JgMKhAIKDe3l6VlJTkezrqDcf1UV909A9myV/3HtUTr7fpvY5QxnWHIV19QZW+0VyvqpLshsRsbjsbcqAnrJv+z5tyGIPd0w70hNOhxpA0LeBRNJ7U0tnV1NgAAABgWGPJBnnvioZB73cE9cvX27R1b88JY/8wc6q+dVmD6ip8WX2mZQ5uO/O4slebM6SzN6xoIqky3+BbpaEwForElUzZSiRTHMQJAACArCHY5NmH3X168o12vfH3j04YW3hOuVYsatS504qy+kynw1Cpz1Igi7U5x6sKeOU2nYrEk3I5B7eiTS/16ki/Q4mkrf998zzNqy/L2fMBAABwdiHY5MmBo2Gt3tCuP39wSMfvBZxbG9Atlzdq9vRA1p9b7HGp3G/J6chOHc1Ippd6tXjmVL24o0O2JK/LqXA8qWhi8E0NoQYAAADZRLCZZIeCEf36zb16cUeHUsclmlmVxbrl8gbNqy/LWgH/ELfLqQq/lZNtZyMZ2mbWsqtbRwdicptOtp8BAAAgJwg2k6RnIKanN+/V77cdVDyZmWjqK3xasahRl59bkfVA43QYKvdb6fNjJlOxx6X7l83WgZ6wOnvDqgp4aesMAACAnCDY5FhfJKFnt+7T81v3KxLPPNSzOuDR8ssadNV507K+NcwwDJV4TJX5LDlyvO1sNNNLCTQAAADILYJNjoTjSa15+4B+t2WfQpFExliF39I3muu1dHaVXFlssTzEazlV4XfLMrN/bwAAAOB0RLDJslgipT9t79Bv3tyjowPxjLESj6mb5tdp2UU1cueg1sV0OFReZKnIzV8rAAAAzi78BpwlyZStV97r0q82tOtQKPNAT5/l1Ffn1eor82rlz0HoMAxDAa9LZT5X1mt0AAAAgEJAsJmglG1r3a7DevKNNu07Gs4Ys0yHll1Uo5vm1+XszBifZaqiyMrJljYAAACgUBBsxsm2bW1qO6Jfvt6u3d19GWNOh6EvXlitmxfWaUqROyfPdzkdqiiy5LP4KwQAAAD4rXgc/ra/R0+sb9OOg8GM6w5DWnJ+pb7ZXK+aHHUBcxiGSn0uBbxsOwMAAACGEGzGYGdnSE+83qYte46eMHZl0xR9a1GDGir8WXteVyiqw6GIphR7VFnsVpHbVLnfksm2MwAAACADweYUtB3u1+oN7VrfeviEsUsbyrRiUaNmVRVn7Xn90YQeX9+mze1HFEsk5TadWjxzqv7lmvMJNQAAAMAwCDYnsfejAT388gf60zsdso8bu3B6iVZc3qi5taVZf+7j69u0rrVbPsupcr9bsURSa9/vkul06P5ls7P+PAAAAKDQEWxG8Or7Xfrvv96qRCoz0pw7rUi3XN6g+Q3lOalx6QpFtbn9iPxup0q9lgzDkMfllIy4WnZ160BPWNNzVL8DAAAAFCqCzQgubSxXkcdUz8eHbNaV+/TtRQ26ommKHDks2j/aH1UylVLA684ITl6XU0cHYursJdgAAAAAxyPYjKDE49L3Fn9Kv9rQrm8012vJ+ZVyOnIXaAzDUJnPpTm1pfK4TEXiyYyzacLxwVqbqgChBgAAADgeweYkvrWoQTdcXKtQJJ7T5xzb7azUZ2nxzKl6ccdgXY/X5VQ4nlR/NKGls6t5WwMAAAAMg2BzEm7TqY/6+9XaFUq3XM4ml9OhKUVueS1nxvU7vjBLktSyq1tHB2Jym04tnV2dvg4AAAAgE8FmBKFIXA+/tFOvfXBI4XhClunU/IZyfeeKRvndE/vP5jAMlfkslXjNYRsQFHtcun/ZbB3oCauzN6yqgJc3NQAAAMBJEGxG8PBLO/Xijg55XU4FvJaiiaTWtXZLkm5b0jTu+xZ7XCr3W6dUrzO9lEADAAAAnAqCzTAO9ITVsqtbRW5TPstUIpmSaZmyJW1uP6KuUHTM29K8llPlfktu0zn6hwEAAACMCcfYD6OzN6xoIjl4fswxPKZTsURSh0ORU76Xy+lQZYlH1QEvoQYAAADIEd7YDKPq4xASiSflsz75TxRJJGWZTk0p9ox6D4dhqNTnUsDryslBngAAAAA+wRubYUwv9WrxzKnqiyYUisSVSNnqiyUUjiU1v6F81G1oRR5TtWVelfosQg0AAAAwCXhjM4Kh1sqvfXBIveGYLNOpK5um6jtXNI74PZY52L75+C1sAAAAAHKLYDOCoZbLH3QGRz3HxukwVOqzFPC6JnmWAAAAACSCzaiqA15ZzpF37I2lfTMAAACA3CDYjJPH5VRFEe2bAQAAgNMBwWaMTIdDZX6Xij1sOwMAAABOFwSbU2QYhko8psp8lhxsOwMAAABOKwSbU+C1nKrwu2WZdMcGAAAATkcEm1EUu026nQEAAACnOV5BjIJtZwAAAMDpj2ADAAAAoOARbAAAAAAUPIINAAAAgIJHsAEAAABQ8Ag2AAAAAAoewQYAAABAwSPYAAAAACh4BBsAAAAABY9gAwAAAKDgEWwAAAAAFDyCDQAAAICCR7ABAAAAUPAINgAAAAAKHsEGAAAAQMEj2AAAAAAoeAQbAAAAAAWPYAMAAACg4BFsAAAAABQ8M98TOJ5t25KkYDCY55kAAAAAyKehTDCUEU7mtAs2oVBIkjRjxow8zwQAAADA6SAUCikQCJz0M4Z9KvFnEqVSKR08eFDFxcUyDCPf08E4BYNBzZgxQ/v27VNJSUm+p4MzHOsNk401h8nGmsNkOp3Wm23bCoVCqqmpkcNx8iqa0+6NjcPhUG1tbb6ngSwpKSnJ+/8QOHuw3jDZWHOYbKw5TKbTZb2N9qZmCM0DAAAAABQ8gg0AAACAgkewQU643W7de++9crvd+Z4KzgKsN0w21hwmG2sOk6lQ19tp1zwAAAAAAMaKNzYAAAAACh7BBgAAAEDBI9gAAAAAKHgEGwAAAAAFj2CDCVm3bp2uvfZa1dTUyDAMvfDCCxnjtm3rnnvuUXV1tbxer5YsWaLW1tb8TBYF78EHH9Sll16q4uJiTZs2TcuWLdPOnTszPhOJRLRy5UpVVFSoqKhIX/7yl9XV1ZWnGaOQ/fznP9ecOXPSB9Q1NzfrxRdfTI+z1pBLDz30kAzD0KpVq9LXWHPIph//+McyDCPjz3nnnZceL8T1RrDBhPT392vu3Ll69NFHhx1/+OGH9cgjj+ixxx7Tpk2b5Pf7dfXVVysSiUzyTHEmaGlp0cqVK/Xmm29q7dq1isfj+vznP6/+/v70Z374wx/qD3/4g5577jm1tLTo4MGDuuGGG/I4axSq2tpaPfTQQ9q6dau2bNmiz33uc7ruuuv07rvvSmKtIXfeeust/eIXv9CcOXMyrrPmkG0XXHCBOjo60n9ef/319FhBrjcbyBJJ9po1a9Jfp1Ipu6qqyv7JT36SvtbT02O73W77t7/9bR5miDPNoUOHbEl2S0uLbduD68vlctnPPfdc+jPvv/++LcneuHFjvqaJM0hZWZn9+OOPs9aQM6FQyG5qarLXrl1rL1682L7tttts2+bnG7Lv3nvvtefOnTvsWKGuN97YIGfa2trU2dmpJUuWpK8FAgEtWLBAGzduzOPMcKbo7e2VJJWXl0uStm7dqng8nrHmzjvvPNXV1bHmMCHJZFLPPPOM+vv71dzczFpDzqxcuVLXXHNNxtqS+PmG3GhtbVVNTY3OOecc3Xzzzdq7d6+kwl1vZr4ngDNXZ2enJKmysjLjemVlZXoMGK9UKqVVq1Zp0aJFmj17tqTBNWdZlkpLSzM+y5rDeG3fvl3Nzc2KRCIqKirSmjVr9OlPf1rbtm1jrSHrnnnmGb399tt66623Thjj5xuybcGCBVq9erVmzZqljo4O3Xfffbriiiu0Y8eOgl1vBBsABWnlypXasWNHxn5gINtmzZqlbdu2qbe3V88//7yWL1+ulpaWfE8LZ6B9+/bptttu09q1a+XxePI9HZwFli5dmv7nOXPmaMGCBaqvr9ezzz4rr9ebx5mNH1vRkDNVVVWSdEIHja6urvQYMB633nqr/vjHP+q1115TbW1t+npVVZVisZh6enoyPs+aw3hZlqVzzz1X8+bN04MPPqi5c+fqZz/7GWsNWbd161YdOnRIF198sUzTlGmaamlp0SOPPCLTNFVZWcmaQ06VlpZq5syZ2r17d8H+jCPYIGcaGxtVVVWlV199NX0tGAxq06ZNam5uzuPMUKhs29att96qNWvW6M9//rMaGxszxufNmyeXy5Wx5nbu3Km9e/ey5pAVqVRK0WiUtYasu+qqq7R9+3Zt27Yt/eeSSy7RzTffnP5n1hxyqa+vT3//+99VXV1dsD/j2IqGCenr69Pu3bvTX7e1tWnbtm0qLy9XXV2dVq1apQceeEBNTU1qbGzU3XffrZqaGi1btix/k0bBWrlypZ5++mn9/ve/V3FxcXqfbyAQkNfrVSAQ0C233KLbb79d5eXlKikp0Q9+8AM1Nzdr4cKFeZ49Cs2dd96ppUuXqq6uTqFQSE8//bT+8pe/6OWXX2atIeuKi4vT9YJD/H6/Kioq0tdZc8imH/3oR7r22mtVX1+vgwcP6t5775XT6dRNN91UuD/j8t2WDYXttddesyWd8Gf58uW2bQ+2fL777rvtyspK2+1221dddZW9c+fO/E4aBWu4tSbJfvLJJ9OfCYfD9ve//327rKzM9vl89vXXX293dHTkb9IoWCtWrLDr6+tty7LsqVOn2ldddZX9yiuvpMdZa8i1Y9s92zZrDtl144032tXV1bZlWfb06dPtG2+80d69e3d6vBDXm2Hbtp2nTAUAAAAAWUGNDQAAAICCR7ABAAAAUPAINgAAAAAKHsEGAAAAQMEj2AAAAAAoeAQbAAAAAAWPYAMAAACg4BFsAAAAABQ8gg0AAACAgkewAQAAAFDwCDYAAAAACh7BBgAAAEDB+/93SoGXAoikfwAAAABJRU5ErkJggg==\n"
296
          },
297
          "metadata": {}
298
        }
299
      ]
300
    },
301
    {
302
      "cell_type": "code",
303
      "source": [
304
        "mse = mean_squared_error(y_test, y_pred)\n",
305
        "print(\"Mean Squared Error:\", mse)"
306
      ],
307
      "metadata": {
308
        "colab": {
309
          "base_uri": "https://localhost:8080/"
310
        },
311
        "id": "fEx9UCU8YxAn",
312
        "outputId": "eec37ce6-8733-4b10-effe-d0a312c5672d"
313
      },
314
      "execution_count": 55,
315
      "outputs": [
316
        {
317
          "output_type": "stream",
318
          "name": "stdout",
319
          "text": [
320
            "Mean Squared Error: 8.883987158812726\n"
321
          ]
322
        }
323
      ]
324
    },
325
    {
326
      "cell_type": "code",
327
      "source": [],
328
      "metadata": {
329
        "id": "WjzdGpQRZXRd"
330
      },
331
      "execution_count": 55,
332
      "outputs": []
333
    }
334
  ]
335
}