{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "f0feadba",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import matplotlib.dates as mdates\n",
    "import keras\n",
    "from keras.models import Sequential\n",
    "from keras.layers import Dense, LSTM, Dropout\n",
    "from sklearn.preprocessing import MinMaxScaler\n",
    "from sklearn.metrics import mean_absolute_error, mean_squared_error\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "64329d74",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Loading and preprocessing the data\n",
    "df = pd.read_csv('water_levels.csv', parse_dates=['date'])\n",
    "df.set_index('date', inplace=True)\n",
    "target = df['Water levels'].values.reshape(-1, 1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "3d59f982",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Water levels</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>date</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1941-04-01</th>\n",
       "      <td>6417.24</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1941-05-01</th>\n",
       "      <td>6417.31</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1941-06-01</th>\n",
       "      <td>6417.32</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1941-07-01</th>\n",
       "      <td>6417.48</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1941-08-01</th>\n",
       "      <td>6417.62</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2018-08-01</th>\n",
       "      <td>6382.10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2018-09-01</th>\n",
       "      <td>6381.80</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2018-10-01</th>\n",
       "      <td>6381.40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2018-11-01</th>\n",
       "      <td>6381.30</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2018-12-01</th>\n",
       "      <td>6381.30</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>933 rows × 1 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "            Water levels\n",
       "date                    \n",
       "1941-04-01       6417.24\n",
       "1941-05-01       6417.31\n",
       "1941-06-01       6417.32\n",
       "1941-07-01       6417.48\n",
       "1941-08-01       6417.62\n",
       "...                  ...\n",
       "2018-08-01       6382.10\n",
       "2018-09-01       6381.80\n",
       "2018-10-01       6381.40\n",
       "2018-11-01       6381.30\n",
       "2018-12-01       6381.30\n",
       "\n",
       "[933 rows x 1 columns]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "8fab85ee",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Scaling the data \n",
    "scaler = MinMaxScaler(feature_range=(0, 1))\n",
    "scaled_target = scaler.fit_transform(target)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "430052ea",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Lookback period in months\n",
    "memory_range = 15\n",
    "\n",
    "# Splitting the data\n",
    "training_set = int(len(scaled_target) * 0.8)\n",
    "train_data = scaled_target[:training_set]\n",
    "test_data = scaled_target[training_set - memory_range:]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "2e2dc3dc",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2024-01-07 17:13:15.836477: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcuda.so.1'; dlerror: libcuda.so.1: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /sw/pkgs/arc/cudnn/11.2-v8.1.1/lib64:/sw/pkgs/arc/cuda/11.2.2/lib64\n",
      "2024-01-07 17:13:15.836514: W tensorflow/stream_executor/cuda/cuda_driver.cc:269] failed call to cuInit: UNKNOWN ERROR (303)\n",
      "2024-01-07 17:13:15.836534: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:156] kernel driver does not appear to be running on this host (gl0006.arc-ts.umich.edu): /proc/driver/nvidia/version does not exist\n",
      "2024-01-07 17:13:15.836838: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 AVX512F FMA\n",
      "To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/90\n",
      "10/10 [==============================] - 6s 146ms/step - loss: 0.1118 - val_loss: 0.0023\n",
      "Epoch 2/90\n",
      "10/10 [==============================] - 0s 31ms/step - loss: 0.0300 - val_loss: 0.0108\n",
      "Epoch 3/90\n",
      "10/10 [==============================] - 0s 31ms/step - loss: 0.0098 - val_loss: 7.6592e-04\n",
      "Epoch 4/90\n",
      "10/10 [==============================] - 0s 31ms/step - loss: 0.0040 - val_loss: 0.0033\n",
      "Epoch 5/90\n",
      "10/10 [==============================] - 0s 31ms/step - loss: 0.0037 - val_loss: 0.0014\n",
      "Epoch 6/90\n",
      "10/10 [==============================] - 0s 31ms/step - loss: 0.0030 - val_loss: 9.0248e-04\n",
      "Epoch 7/90\n",
      "10/10 [==============================] - 0s 32ms/step - loss: 0.0034 - val_loss: 8.0541e-04\n",
      "Epoch 8/90\n",
      "10/10 [==============================] - 0s 30ms/step - loss: 0.0023 - val_loss: 0.0012\n",
      "Epoch 9/90\n",
      "10/10 [==============================] - 0s 30ms/step - loss: 0.0026 - val_loss: 0.0013\n",
      "Epoch 10/90\n",
      "10/10 [==============================] - 0s 31ms/step - loss: 0.0025 - val_loss: 0.0011\n",
      "Epoch 11/90\n",
      "10/10 [==============================] - 0s 30ms/step - loss: 0.0029 - val_loss: 0.0015\n",
      "Epoch 12/90\n",
      "10/10 [==============================] - 0s 31ms/step - loss: 0.0030 - val_loss: 0.0014\n",
      "Epoch 13/90\n",
      "10/10 [==============================] - 0s 30ms/step - loss: 0.0028 - val_loss: 0.0013\n",
      "Epoch 14/90\n",
      "10/10 [==============================] - 0s 30ms/step - loss: 0.0031 - val_loss: 0.0019\n",
      "Epoch 15/90\n",
      "10/10 [==============================] - 0s 31ms/step - loss: 0.0039 - val_loss: 0.0011\n",
      "Epoch 16/90\n",
      "10/10 [==============================] - 0s 30ms/step - loss: 0.0035 - val_loss: 0.0016\n",
      "Epoch 17/90\n",
      "10/10 [==============================] - 0s 31ms/step - loss: 0.0028 - val_loss: 0.0013\n",
      "Epoch 18/90\n",
      "10/10 [==============================] - 0s 30ms/step - loss: 0.0023 - val_loss: 0.0012\n",
      "Epoch 19/90\n",
      "10/10 [==============================] - 0s 30ms/step - loss: 0.0023 - val_loss: 0.0014\n",
      "Epoch 20/90\n",
      "10/10 [==============================] - 0s 30ms/step - loss: 0.0028 - val_loss: 0.0022\n",
      "Epoch 21/90\n",
      "10/10 [==============================] - 0s 31ms/step - loss: 0.0030 - val_loss: 0.0017\n",
      "Epoch 22/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0033 - val_loss: 0.0014\n",
      "Epoch 23/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0028 - val_loss: 0.0018\n",
      "Epoch 24/90\n",
      "10/10 [==============================] - 0s 33ms/step - loss: 0.0026 - val_loss: 8.5370e-04\n",
      "Epoch 25/90\n",
      "10/10 [==============================] - 0s 33ms/step - loss: 0.0029 - val_loss: 7.7163e-04\n",
      "Epoch 26/90\n",
      "10/10 [==============================] - 0s 34ms/step - loss: 0.0027 - val_loss: 8.5024e-04\n",
      "Epoch 27/90\n",
      "10/10 [==============================] - 0s 32ms/step - loss: 0.0023 - val_loss: 8.1634e-04\n",
      "Epoch 28/90\n",
      "10/10 [==============================] - 0s 32ms/step - loss: 0.0024 - val_loss: 0.0013\n",
      "Epoch 29/90\n",
      "10/10 [==============================] - 0s 30ms/step - loss: 0.0024 - val_loss: 0.0013\n",
      "Epoch 30/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0025 - val_loss: 8.0726e-04\n",
      "Epoch 31/90\n",
      "10/10 [==============================] - 0s 30ms/step - loss: 0.0020 - val_loss: 9.6482e-04\n",
      "Epoch 32/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0024 - val_loss: 8.2653e-04\n",
      "Epoch 33/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0025 - val_loss: 0.0013\n",
      "Epoch 34/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0023 - val_loss: 0.0012\n",
      "Epoch 35/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0024 - val_loss: 8.5550e-04\n",
      "Epoch 36/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0025 - val_loss: 7.1326e-04\n",
      "Epoch 37/90\n",
      "10/10 [==============================] - 0s 30ms/step - loss: 0.0024 - val_loss: 0.0011\n",
      "Epoch 38/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0021 - val_loss: 8.5282e-04\n",
      "Epoch 39/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0026 - val_loss: 9.1638e-04\n",
      "Epoch 40/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0022 - val_loss: 0.0012\n",
      "Epoch 41/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0034 - val_loss: 0.0017\n",
      "Epoch 42/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0028 - val_loss: 7.8691e-04\n",
      "Epoch 43/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0025 - val_loss: 9.2877e-04\n",
      "Epoch 44/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0018 - val_loss: 0.0011\n",
      "Epoch 45/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0021 - val_loss: 9.8704e-04\n",
      "Epoch 46/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0019 - val_loss: 9.6726e-04\n",
      "Epoch 47/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0019 - val_loss: 8.1688e-04\n",
      "Epoch 48/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0021 - val_loss: 0.0013\n",
      "Epoch 49/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0022 - val_loss: 0.0011\n",
      "Epoch 50/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0015 - val_loss: 8.0450e-04\n",
      "Epoch 51/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0018 - val_loss: 8.6386e-04\n",
      "Epoch 52/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0019 - val_loss: 8.7206e-04\n",
      "Epoch 53/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0018 - val_loss: 0.0018\n",
      "Epoch 54/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0029 - val_loss: 7.6604e-04\n",
      "Epoch 55/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0023 - val_loss: 6.6928e-04\n",
      "Epoch 56/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0023 - val_loss: 0.0010\n",
      "Epoch 57/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0019 - val_loss: 0.0010\n",
      "Epoch 58/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0016 - val_loss: 9.7042e-04\n",
      "Epoch 59/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0020 - val_loss: 6.3277e-04\n",
      "Epoch 60/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0025 - val_loss: 0.0012\n",
      "Epoch 61/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0020 - val_loss: 0.0012\n",
      "Epoch 62/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0019 - val_loss: 7.7589e-04\n",
      "Epoch 63/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0017 - val_loss: 0.0010\n",
      "Epoch 64/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0021 - val_loss: 7.1544e-04\n",
      "Epoch 65/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0018 - val_loss: 9.9004e-04\n",
      "Epoch 66/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0020 - val_loss: 8.8679e-04\n",
      "Epoch 67/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0018 - val_loss: 9.2421e-04\n",
      "Epoch 68/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0017 - val_loss: 7.3960e-04\n",
      "Epoch 69/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0016 - val_loss: 9.1318e-04\n",
      "Epoch 70/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0016 - val_loss: 0.0012\n",
      "Epoch 71/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0022 - val_loss: 0.0010\n",
      "Epoch 72/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0017 - val_loss: 8.5706e-04\n",
      "Epoch 73/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0016 - val_loss: 0.0011\n",
      "Epoch 74/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0017 - val_loss: 7.3462e-04\n",
      "Epoch 75/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0016 - val_loss: 9.8969e-04\n",
      "Epoch 76/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0018 - val_loss: 8.6149e-04\n",
      "Epoch 77/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0017 - val_loss: 7.2631e-04\n",
      "Epoch 78/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0022 - val_loss: 8.6056e-04\n",
      "Epoch 79/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0020 - val_loss: 0.0012\n",
      "Epoch 80/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0020 - val_loss: 9.1323e-04\n",
      "Epoch 81/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0020 - val_loss: 6.0634e-04\n",
      "Epoch 82/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0020 - val_loss: 0.0013\n",
      "Epoch 83/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0026 - val_loss: 5.7875e-04\n",
      "Epoch 84/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0027 - val_loss: 6.9766e-04\n",
      "Epoch 85/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0022 - val_loss: 7.6762e-04\n",
      "Epoch 86/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0016 - val_loss: 7.8220e-04\n",
      "Epoch 87/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0017 - val_loss: 0.0014\n",
      "Epoch 88/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0018 - val_loss: 5.7069e-04\n",
      "Epoch 89/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0018 - val_loss: 0.0013\n",
      "Epoch 90/90\n",
      "10/10 [==============================] - 0s 29ms/step - loss: 0.0022 - val_loss: 0.0013\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<keras.callbacks.History at 0x1491085102e0>"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Preparing training and test sets\n",
    "\n",
    "X_train, y_train = [], []\n",
    "for i in range(memory_range, len(train_data)):\n",
    "    X_train.append(train_data[i - memory_range:i, 0])\n",
    "    y_train.append(train_data[i, 0])\n",
    "X_train, y_train = np.array(X_train), np.array(y_train)\n",
    "X_train = X_train.reshape(X_train.shape[0], X_train.shape[1], 1)\n",
    "\n",
    "# Building the LSTM model\n",
    "model = Sequential()\n",
    "model.add(LSTM(100, return_sequences=True, input_shape=(X_train.shape[1], 1)))\n",
    "model.add(Dropout(0.2))\n",
    "model.add(LSTM(100, return_sequences=True))\n",
    "model.add(Dropout(0.2))\n",
    "model.add(LSTM(100, return_sequences=True))\n",
    "model.add(Dropout(0.2))\n",
    "model.add(LSTM(100))\n",
    "model.add(Dropout(0.2))\n",
    "model.add(Dense(1))\n",
    "model.compile(optimizer='adam', loss='mean_squared_error')\n",
    "\n",
    "# Training the model\n",
    "model.fit(X_train, y_train, epochs=90, batch_size=64, validation_split=0.2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "bf46c049",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Preparing validation data\n",
    "\n",
    "X_test = []\n",
    "y_test = target[training_set:, 0]\n",
    "for i in range(memory_range, len(test_data)):\n",
    "    X_test.append(test_data[i - memory_range:i, 0])\n",
    "X_test = np.array(X_test)\n",
    "X_test = X_test.reshape(X_test.shape[0], X_test.shape[1], 1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "1c5d183b",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "MAE is: 1.1968948445855663\n",
      "RMSE is: 1.6103956277877536\n"
     ]
    }
   ],
   "source": [
    "# Making predictions\n",
    "predicted_WL = model.predict(X_test)\n",
    "predicted_WL = scaler.inverse_transform(predicted_WL)\n",
    "\n",
    "# Calculating MAE and RMSE\n",
    "m = mean_absolute_error(y_test, predicted_WL)\n",
    "print(\"MAE is:\", m)\n",
    "a = np.sqrt(mean_squared_error(y_test, predicted_WL))\n",
    "print(\"RMSE is:\", a)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "5d1b289e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1152x432 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Correcting the padding length\n",
    "len_training = training_set\n",
    "valid_predictions_padded = np.concatenate([np.full(len_training, np.nan), predicted_WL.ravel()])\n",
    "\n",
    "# Check if the lengths match\n",
    "if len(valid_predictions_padded) != len(df):\n",
    "    raise ValueError(\"Length of padded validation predictions does not match the length of the DataFrame.\")\n",
    "\n",
    "# Convert data to NumPy arrays for plotting\n",
    "historical_data = df['Water levels'].to_numpy()\n",
    "dates = df.index.to_numpy()\n",
    "\n",
    "# Plotting the historical data and the predictions\n",
    "plt.figure(figsize=(16, 6))\n",
    "plt.plot(dates, historical_data, color='blue', label='Historical Data')\n",
    "plt.plot(dates, valid_predictions_padded, color='red', label='Validation Data')\n",
    "plt.gca().xaxis.set_major_locator(mdates.YearLocator(4))\n",
    "plt.gca().xaxis.set_major_formatter(mdates.DateFormatter('%Y'))\n",
    "plt.title('Water Levels (Feet) (1941-2018)')\n",
    "plt.xlabel('Date')\n",
    "plt.ylabel('Water Levels (Feet)')\n",
    "plt.legend()\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "64755444",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1152x432 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "residuals = y_test - predicted_WL.flatten()\n",
    "\n",
    "# Create a plot for residuals\n",
    "plt.figure(figsize=(16, 6))\n",
    "plt.plot(dates[training_set:], residuals, color='green', label='Residuals')\n",
    "plt.axhline(y=0, color='black', linestyle='--')  # Horizontal line at y=0\n",
    "plt.title('Residual Plot for Water Levels (Feet)')\n",
    "plt.xlabel('Date')\n",
    "plt.ylabel('Residuals')\n",
    "plt.legend()\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "010ddd4f",
   "metadata": {},
   "outputs": [],
   "source": [
    "# 3. Forecasting future values\n",
    "def predict(num_prediction, model):\n",
    "    prediction_list = scaled_target[-memory_range:]\n",
    "    for _ in range(num_prediction):\n",
    "        x = prediction_list[-memory_range:]\n",
    "        x = x.reshape((1, memory_range, 1))\n",
    "        out = model.predict(x)[0][0]\n",
    "        prediction_list = np.append(prediction_list, out)\n",
    "    return prediction_list[memory_range-1:]\n",
    "\n",
    "# Forecast for 5 years (60 months)\n",
    "num_prediction = 60\n",
    "forecast = predict(num_prediction, model)\n",
    "forecast = forecast.reshape(-1, 1)\n",
    "forecast = scaler.inverse_transform(forecast)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "b3d0c287",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[6381.3       ],\n",
       "       [6380.54500611],\n",
       "       [6380.55446596],\n",
       "       [6380.54589565],\n",
       "       [6380.51402848],\n",
       "       [6380.45549859],\n",
       "       [6380.37377145],\n",
       "       [6380.27743673],\n",
       "       [6380.1572753 ],\n",
       "       [6380.03164105],\n",
       "       [6379.89437083],\n",
       "       [6379.75716562],\n",
       "       [6379.62085272],\n",
       "       [6379.49851448],\n",
       "       [6379.39215617],\n",
       "       [6379.28618798],\n",
       "       [6379.17611794],\n",
       "       [6379.09463774],\n",
       "       [6379.00467161],\n",
       "       [6378.9084863 ],\n",
       "       [6378.80848136],\n",
       "       [6378.70692146],\n",
       "       [6378.60556214],\n",
       "       [6378.50544653],\n",
       "       [6378.4077526 ],\n",
       "       [6378.31261109],\n",
       "       [6378.22032911],\n",
       "       [6378.13063828],\n",
       "       [6378.04327161],\n",
       "       [6377.95746544],\n",
       "       [6377.87251976],\n",
       "       [6377.78853487],\n",
       "       [6377.70579852],\n",
       "       [6377.62319428],\n",
       "       [6377.54134228],\n",
       "       [6377.4606662 ],\n",
       "       [6377.38140466],\n",
       "       [6377.30364759],\n",
       "       [6377.22738186],\n",
       "       [6377.15254555],\n",
       "       [6377.07903283],\n",
       "       [6377.00674894],\n",
       "       [6376.9356036 ],\n",
       "       [6376.86553422],\n",
       "       [6376.79650103],\n",
       "       [6376.72850333],\n",
       "       [6376.66156498],\n",
       "       [6376.59570087],\n",
       "       [6376.53090579],\n",
       "       [6376.46721988],\n",
       "       [6376.40464347],\n",
       "       [6376.34315823],\n",
       "       [6376.2827327 ],\n",
       "       [6376.22333609],\n",
       "       [6376.16494385],\n",
       "       [6376.10753038],\n",
       "       [6376.05108115],\n",
       "       [6375.99558338],\n",
       "       [6375.9410291 ],\n",
       "       [6375.88741036],\n",
       "       [6375.8347199 ]])"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "forecast"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "b41f0138",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Forecast array with the correct length\n",
    "forecast = forecast[:num_prediction]\n",
    "\n",
    "# Define the start date for forecasting (day after the last date in the dataset)\n",
    "start_forecast_date = df.index[-1] + pd.Timedelta(days=1)\n",
    "\n",
    "# Generate forecast dates\n",
    "forecast_dates = pd.date_range(start=start_forecast_date, periods=num_prediction, freq='M')\n",
    "\n",
    "# Convert the forecast dates to a NumPy array\n",
    "forecast_dates_np = forecast_dates.to_pydatetime()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "bc5faaa2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA8YAAAGDCAYAAADpmwk3AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjQuMywgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/MnkTPAAAACXBIWXMAAAsTAAALEwEAmpwYAACDnElEQVR4nOzdeZzN5fvH8ddl33eV5VsUKutgQspSikpkLW2SSipKuzZp3/wSLaSESquyRZtSEaqx74msIWTfZ+b+/XGfYTC7c+acmXk/H4/zOOd81uucmc/Muc5939dtzjlEREREREREcqpc4Q5AREREREREJJyUGIuIiIiIiEiOpsRYREREREREcjQlxiIiIiIiIpKjKTEWERERERGRHE2JsYiIiIiIiORoSoxFRERCwMycmVXJwH5lzWy5mRUIRVzJnPNUM1tqZvlT2a6lmY3LpLCyBDN71cx6hjsOERE5OUqMRUTkpJnZI2Y2+bhlK5JZ1iWVYzU3s/VBji/oxwyhvsAI59wBADP7ycwOmNmeRLfzT+YEZrbazC5JeO6c2wxMBXqksuvzwIuJjvOMmS00s1gz63/cOczMHjOztWa2y8w+MbNiScRSysy2mNn045YPC3xBEG9m3VJ5PdXMbHzgOP+Z2bdmdvZx29xrZpvMbKeZvZfwJYCZ5Tez4Wa2xsx2m9lcM7s80X7VzSzGzLYHblPMrHqiQ78CPGZm+VJ570REJIIpMRYRkWD4BbjAzHIDmNlpQF6g3nHLqgS2DRkzyxPK44dSIFm7CfjwuFW9nHNFEt1mhuD0o4HbU4jtPKC4c25WosV/AQ8Bk5LYpStwI3ABUB4oCLyexHYvAUuTWD4fuBOYk4bYSwATgLOBU4HfgfGJYm+F/8KhBVAJOBN4KrA6D7AOaAYUB54APjOzSoH1/wCdgFJAmcB5Pkk4tnNuI7AMaJuGOEVEJEIpMRYRkWD4A58IRwWeN8W3QC4/btlK59w/ZnZzoOvubjNbZWa3A5hZYeBroHyi1tHyZpbLzPqa2Uoz22Zmn5lZqcA+lQLdlm8xs7XAj+kJPHD8LwKtjX+b2d2Jlu9POE9gWV0z22pmeQPPuwdex/ZAK+UZyZzjCjNbEni9G8zsgWTCaQjscM6l2rodaOkcEGiR3WxmQ82sYKL1V5rZPDPbYWYzzKx2YPkHwOnAxMD7+1Bgl9+AM5N7DcDlwM+JFzjnRjnnvgZ2J7F9G2C4c26dc24PPgG+xswKJYrxfKAmMOL4nZ1zbzrnfgAOpPZeOOd+d84Nd87955w7DAwEzjaz0oFNbgrEstg5tx14BugW2Hevc66/c261cy7eOfcV8DdQP7B+R2CdAwyIw3/Bk9hPQOvU4hQRkcilxFhERE6ac+4QPrFqGljUFJgGTD9uWUJr8b/AlUAx4GZgoJnVc87txSdg/yRqHf0HuBtoh2/VKw9sB948LoxmwLlAq7TGbWa5gIn41skK+BbFPmbWKnDemUDHRLtcB4xxzh02s3bAo0AHoGzg9X6czKmGA7c754riE8Hkkvda+C8T0uIloBr+i4cqgfj7BV5XPeA9fAtwaeBtYIKZ5XfO3QisBdoE3t+XAZxzsfgW4DpBiA18EmnHPc8PVA3EmBv/M+wFuHQcNy2aApucc9sCz2vgf8YJ5gOnJkqcjwZpdir+fV183PId+CT9dXyX8sSWkvz7JiIiWYASYxERCZafOZoEN8EnitOOW/YzgHNuknNupfN+Br4LrE/O7cBjzrn1zrmDQH+g03HdpvsHWv/2pyPm84CyzrmnnXOHnHOrgHeAhHHQHwHXgh8zG1j+UaKYXnDOLQ0klc8DUcm0uB4GqptZMefcdudcct2DS5B06+vgQMvvDjObE4jlNuDeQCvp7sD5E+K+DXjbOfebcy7OOTcKOAg0SuX92B2IIT2xJedr4NZAi35x4OHA8oQW47uB35xzs9NxzFSZWUV8wn1fosVFgJ2Jnic8LnrcvnnxXcpHOeeWJV7nnCuB72rdC5h73GlTet9ERCQLUGIsIiLB8gtwoZmVxCebK4AZQOPAspqBbTCzy81sVqBQ0g7gCvz4zeScAYxNSA7xLXRx+PGkCdZlIOYz8N22dyQ69qOJjjsGON/MyuMTfIdP9hP2HZRov//wraIVkjhPR/xrXGNmP1vyxbO2c1yyFnC3c65E4FYP30JdCJid6PzfBJYnxHb/ca/rf/jW9pQUBXakM7bkvIdvQf8J3/o6NbB8feD9vBt4LB3HO8KOLUR2eqLlZfFfsrzlnEvcer8H3zshQcLj3Yn2zQV8ABzCJ78nCPRoGAq8b2anJFqV0vsmIiJZQJYtUCIiIhFnJr5FrQfwK4BzbpeZ/RNY9o9z7u9Agakv8MWZxge6JY/jaLfbpLrVrgO6O+d+PX5FoiJJGemOuw742zlXNamVzrkdZvYdcDW+m/bHgbGmCfs+55wbndpJnHN/AFcFWiR7AZ/hE9XjLQDuTUPcW4H9QA3n3IYk1ifE9lxyIR2/IND6XoVjuxwfH1u1NMTmT+BcPPBk4IaZtQQ2BG5tgXLAEt/4TUGgoJltAio45+JSOXaRJOIviU+KJyTxuhfjuzp/FnheB9ic0NU60AI/HP+FyBWBccrJyYX/UqICfkgA+N+N5N43ERHJAtRiLCIiQRHowhyD78I6LdGq6YFlCeOL8+HHmm4BYs1PjdMy0fabgdKB7rcJhgLPJXRTNj/X71XpjdHMCiS+4asX7zKzh82soJnlNrOa5iswJ/gIn8R35Gg36oSYHjGzGoFjFzezzkmcM5+ZXW9mxQMJ1y58a3dSfgdKmFlSrc5HBJLOd/Bjs08JnKeC+erLBNb1NLOG5hU2s9ZmltDiuxlfmTmxBsBq59yaZE47GT+OO/Fryxt4H3MBeQLva0IV8lJmdlbg/NWBV4GnA7F/ja8OHRW49cN3T45KSIoD71sB/BcmeQPHTvJzi/lpoL4FfnXO9U1ik/eBW8xPvVQSeBwYmWj9EHxy2+b4rvhmdqn5omu5A+d5Fd96nriSdrPAaxIRkSxKibGIiATTz8Ap+GQ4wbTAsl8AAuNh78a33m3HF7SakLBxYGznx8CqQDfg8sCgwDbfmdluYBa+gnN6VMC3sia+VcZXT47CVyLeCryLb/lOMAFfMGqzc+5Iq6Bzbiy+ANYnZrYLWIQvHJaUG4HVge16AjcktVGgiNnI5NYf52F8saxZgeNOwU9XhHMuBj/O+A38e/wXgSrMAS8Ajwfe34QK2dfjk/0kBcZF7zSzxO/7O/j38Vp8t+j9gdcKvmv8ZGAvPml8zzk3LHCsg865TQk3/Jjfw4HHCb4LHK8xMCzwuClJa48fL35zUt2snXPfAC/ju3OvCdwSWrLPwI8XjwI2Jdr3+sCxS+B/H3cCK/Gt6pclmme6HFAdGJfceyciIpHPjvYIExERkXALjJOdBtRNZyGxkznnKfgvNeomJHzJbNcSuNM51y4z4soKzOz/8NOQvRXuWEREJOOUGIuIiIiIiEiOpq7UIiIiIiIikqMpMRYREREREZEcTYmxiIiIiIiI5GhKjEVERERERCRHyxPuAEKlTJkyrlKlSuEOQ0RERERERIKsTJkyfPvtt9865y4LxvFCmhibWQn8fJA1AQd0d87NDKx7AHgFKOuc22pmlwIvAvmAQ8CDzrkfA9vWx8/rWBA/J+I9LpVy2pUqVSImJiYUL0tERERERETCzMzKBOtYoe5KPQj4xjl3DlAHWApgZv8DLgXWJtp2K9DGOVcLuAn4ING6IUAPoGrgFpRvBURERERERERClhibWTGgKTAcwDl3yDm3I7B6IPAQvhWZwPq5zrl/Ak8XAwXMLL+ZlQOKOedmBlqJ3wfahSpuERERERERyVlC2WJ8JrAFGGFmc83sXTMrbGZtgQ3Oufkp7NsRmOucOwhUANYnWrc+sExERERERETkpIVyjHEeoB7Q2zn3m5kNAvrjW5FbJreTmdUAXkq0jSWxWZLji82sB77LNaeffnqGAxcRERERkazj8OHDrF+/ngMHDoQ7FAmBAgUKULFiRfLmzRuyc4QyMV4PrHfO/RZ4PgafGFcG5psZQEVgjpk1cM5tMrOKwFigq3NuZaLjVEx03IrAPyTBOTcMGAYQHR2dYnEuERERERHJHtavX0/RokWpVKkSgTxDsgnnHNu2bWP9+vVUrlw5ZOcJWVdq59wmYJ2ZnR1Y1AKY45w7xTlXyTlXCZ/01gskxSWAScAjzrlfEx1nI7DbzBqZ/y3vCowPVdwiIiIiIpK1HDhwgNKlSyspzobMjNKlS4e8N0Coq1L3Bkab2QIgCng+hW17AVWAJ8xsXuB2SmDdHfhpn/4CVgJfhy5kERERERHJapQUZ1+Z8bMNaWLsnJvnnIt2ztV2zrVzzm0/bn0l59zWwONnnXOFnXNRiW7/BtbFOOdqOufOcs71Sm0OYxERERERkcxUpEiRY56PHDmSXr16ATB06FDef//9ZPf96aefmDFjRrrPOWHCBF588cV07wdQqVIltm7dmuTyWrVqUatWLapXr87jjz/OwYMHUzzWjh07eOuttzIUR6QIdYuxiIiIiIhIjtazZ0+6du2a7PqMJMaxsbG0bduWvn37nmx4J5g6dSoLFy7k999/Z9WqVfTo0SPF7ZUYi4iIiIiISIr69+/PgAEDABg8eDDVq1endu3adOnShdWrVzN06FAGDhxIVFQU06ZNY82aNbRo0YLatWvTokUL1q5dC0C3bt247777uOiii3j44YePaZXevHkz7du3p06dOtSpU+dIot2uXTvq169PjRo1GDZsWLriLlKkCEOHDmXcuHH8999/7NmzhxYtWlCvXj1q1arF+PG+9FPfvn1ZuXIlUVFRPPjgg8luF8lCWZVaREREREQkU/XpA/PmBfeYUVHw2mspb7N//36ioqKOPP/vv/9o27btCdu9+OKL/P333+TPn58dO3ZQokQJevbsSZEiRXjggQcAaNOmDV27duWmm27ivffe4+6772bcuHEA/Pnnn0yZMoXcuXMzcuTII8e9++67adasGWPHjiUuLo49e/YA8N5771GqVCn279/PeeedR8eOHSldunSaX3uxYsWoXLkyK1asoH79+owdO5ZixYqxdetWGjVqRNu2bXnxxRdZtGgR8wJvfGxsbJLbRfI4cCXG2cy+fbB5M4SwkrmIiIiIiBynYMGCRxJD8GOMY2JiTtiudu3aXH/99bRr14527doleayZM2fy5ZdfAnDjjTfy0EMPHVnXuXNncufOfcI+P/7445FxzLlz56Z48eKAb6EeO3YsAOvWrWPFihXpSozBT5mUcP/oo4/yyy+/kCtXLjZs2MDmzZuT3D6p7U477bR0nTczKTHORuLi4LLL4PffYeZMqFs33BGJiIiIiGSu1Fp2w23SpEn88ssvTJgwgWeeeYbFixenuk/iltbChQun+Vw//fQTU6ZMYebMmRQqVIjmzZune9qj3bt3s3r1aqpVq8bo0aPZsmULs2fPJm/evFSqVCnJ46V1u0iiMcbZxK+/woUXwrRpkD8/XH89HD4c7qhERERERCRBfHw869at46KLLuLll19mx44d7Nmzh6JFi7J79+4j2zVu3JhPPvkE8EnmhRdemOqxW7RowZAhQwCIi4tj165d7Ny5k5IlS1KoUCGWLVvGrFmz0hXvnj17uPPOO2nXrh0lS5Zk586dnHLKKeTNm5epU6eyZs0agBPiT267SKbEOAtJ9Lt2jLfegiZNYO1aGDECPvgAli6Fd945cdtgTnQ1cCA0bw4bNiS/zY8/Qs+e8NtvwTuviIiIiEhWFBcXxw033ECtWrWoW7cu9957LyVKlKBNmzaMHTv2SPGtwYMHM2LECGrXrs0HH3zAoEGDUj32oEGDmDp1KrVq1aJ+/fosXryYyy67jNjYWGrXrs0TTzxBo0aN0hTnRRddRM2aNWnQoAGnn346b7/9NgDXX389MTExREdHM3r0aM455xwASpcuzQUXXEDNmjV58MEHk90ukll2nRI4OjraJdWnPys6fBh694aRI0/sIv3dd777dJs28NFHULiwT37r1fOPp0/32y1YAN26waJF0LEjvPuuX59R8+f7IgQANWvCH39AgQLHbrNjB5xzjh/zXKIELFkC5cpl/JwiIiIiIklZunQp5557brjDkBBK6mdsZrOdc9HBOL5ajCNASt9NvPQSVKkCb78NBw/Cvfce3X7vXrj1Vjj3XPj446OJrhlceaVPov/7D/75By6+GDZtgu7d4dNP4fbbTy7mF1+E4sV9Mr5oEfTo4cc4J/Z//wf//utj278fHn/85M4pIiIiIiISCkqMw+y77+DUU2HKlBPXffUV9O0LlSrB+PG+y/TPP0OgQB3vvQfr1sHQoVCo0LH7XnEFxMf7RLpVK5+YTp3qt33iCRg92o9LzojFi2HMGLjlFrj2WnjmGd99+/XXj26ze7ePt1076NLFJ/AffuiTcxERERERkUiixDhM4uN99ejOnWHLFt+amrjleNIkuO46qFMHvv8e2raF227z3ZYffth3r/7mG6hWzY8vPl7Dhr4V9/33YeNGmDABzj7br3voIZ+MP/NMyjH+95/vCl2rFixc6JeNGwfNmkHp0j7pBh/7RRfByy9DQrG5++6D7dvhkUf88z594NAhGDUqo++YiIiIiIhIaCgxDoMpU3yC27Ch7/78yCO+ONUff/j1H3zgu0KXK+cT5Hz5/PI8eeD552HlSl+G/qef4JJLkj5Hrly++/WuXb6VtkWLo+sKF/bjjX/4wY8DTs5dd8Hy5b6r9O23w7Ztfr+KFeGXX/x9gr59fQI+aRLMnu3HMN9/P5x3nl9fpQrUrw+BKdREREREREQihhLjMFi/3o/HHTzYjwN+6CHIm9dXkd60CXr18lMvLVwIFSocu++VV/piWw89BPv2JZ8YJyha1CfUx2vbFmJjfatzUlat8mOR+/aFV1/1cZYpAzt3+u7Y1aodu/3FF0PJkjBxIjz5JJQq5btsJ9ahg/8CIKUq1iIiIiIiIpktiZRJQu3GG/08w3nzHl122WW+lfXdd/3zYcOOthQnZubHGL/2GhQs6BPljGjY0Ce6Eyf6McDHGzAAcuf2Sfppp/nbuHE+5qSqvOfJA5dffrSrdL9+UKzYsdtceSU89pgfV33zzRmLW0REREREJNjUYhwGuXMfmxSDrz59zz0+Ge7WzVeaTk7Bgr77dZ8+Jx4nPTG0bg1ff+1bjhNs3+6T7mHD/JjmChX8ttde61uQP/ww+WP27Hn0cVKJb61acMopSRcaExERERHJqpo3b8633357zLLXXnuNO++8M8V9EqaXveKKK9iRxBjH/v37M2DAgBTPPW7cOJYsWXLkeb9+/ZgShA/cP/30E8WLF6du3bqcffbZNG3alK+++ipN+82YMeOkz5/Z1GIcIc491yekTz99YoXpUGnb1rfw/vKL7wq9axdUr+67c9euDU89lb7jNWniE+fVq30l7eOZ+a7fU6b44mO59LWMiIiIiGQD1157LZ988gmtWrU6suyTTz7hlVdeSdP+kydPzvC5x40bx5VXXkn16tUBePrppzN8rOM1adLkSDI8b9482rVrR8GCBWmRuIDRcX766SeKFClC48aNgxZHZlBqEmGKFUt6THAotGzpW3B79/ZJ8ejRPin+9luYPx/Klk3/Ma+/3neXTk7btn5u4+TGNouIiIiIZDWdOnXiq6++4uDBgwCsXr2af/75hwsvvJA77riD6OhoatSowZNPPpnk/pUqVWLr1q0APPfcc5x99tlccsklLF++/Mg277zzDueddx516tShY8eO7Nu3jxkzZjBhwgQefPBBoqKiWLlyJd26dWPMmDEA/PDDD9StW5datWrRvXv3I/FVqlSJJ598knr16lGrVi2WLVuW6muMioqiX79+vPHGGwBMnDiRhg0bUrduXS655BI2b97M6tWrGTp0KAMHDiQqKopp06YluV0kUotxDlakCHz0kR/fXLOmnzaqfn249NLQnbN9eyhf3hceu+KK0J1HRERERHKoPn1g3rzgHjMqynfvTEbp0qVp0KAB33zzDVdddRWffPIJ11xzDWbGc889R6lSpYiLi6NFixYsWLCA2rVrJ3mc2bNn88knnzB37lxiY2OpV68e9evXB6BDhw7cdtttADz++OMMHz6c3r1707ZtW6688ko6dep0zLEOHDhAt27d+OGHH6hWrRpdu3ZlyJAh9OnTB4AyZcowZ84c3nrrLQYMGMC7CcWOUlCvXr0jreAXXnghs2bNwsx49913efnll/m///s/evbsSZEiRXjggQcA2L59e5LbRRq1GOdwLVrA+PFQowbccosv7GUWuvPly+fHLn/3HaxbF7rziIiIiIhkpoTu1OC7UV977bUAfPbZZ9SrV4+6deuyePHiY8YDH2/atGm0b9+eQoUKUaxYMdq2bXtk3aJFi2jSpAm1atVi9OjRLF68OMV4li9fTuXKlakWmE7mpptu4pdffjmyvkOHDgDUr1+f1atXp+k1OueOPF6/fj2tWrWiVq1avPLKK8nGk9btwk0txsIVV2Ru6+1NN/nxy++/n3K3axERERGRdEuhZTeU2rVrx3333cecOXPYv38/9erV4++//2bAgAH88ccflCxZkm7dunHgwIEUj2PJtFJ169aNcePGUadOHUaOHMlPP/2U4nESJ7FJyZ8/PwC5c+cmNnE13hTMnTuXcwNVgnv37s19991H27Zt+emnn+jfv3+S+6R1u3BTi7FkusqVfXft116DJIrviYiIiIhkOUWKFKF58+Z07979SGvxrl27KFy4MMWLF2fz5s18/fXXKR6jadOmjB07lv3797N7924mTpx4ZN3u3bspV64chw8fZvTo0UeWFy1alN27d59wrHPOOYfVq1fz119/AfDBBx/QrFmzDL++BQsW8Mwzz3DXXXcBsHPnTipUqADAqIQ5W5OIJ7ntIo0SYwmLl1+G//6DOnWgXDk/ddR990GEjsUXEREREUnVtddey/z58+nSpQsAderUoW7dutSoUYPu3btzwQUXpLh/vXr1uOaaa4iKiqJjx440adLkyLpnnnmGhg0bcumll3LOOeccWd6lSxdeeeUV6taty8qVK48sL1CgACNGjKBz587UqlWLXLly0TPx/KppMG3atCPTNd11110MHjz4SEXq/v3707lzZ5o0aUKZMmWO7NOmTRvGjh17pPhWcttFGkutiT2rio6OdgnzgklkmjgR/u//oEQJWLUKli6FqlVh+nQoVSrc0YmIiIhIVrF06dIjXXwle0rqZ2xms51z0cE4vsYYS9i0aeNvCX7+2U8h1a6dn+s4X76whSYiIiIiIjmIulJLxGjWDIYPh2nT4LPPwh2NiIiIiIjkFEqMJaJcfz1UqQLDhoU7EhERERERySmUGEtEMYObb/atxhs3hjsaERERERHJCZQYS8QJFLrj11/DG4eIiIiIiOQMSowl4tStCwUL+urUIiIiIiIioabEWCJOvnzQoIHvTi0iIiIikhXkzp2bqKioI7fVq1eHOyQAXnvtNfbt23fk+RVXXMGOHTtO+rirV6+mYMGC1K1bl3PPPZcGDRowatSoVPebN28ekydPPunzB5uma5KIdMkl8MQTsGEDVKgQ7mhERERERFJWsGBB5s2bl+79YmNjyZMndGnZa6+9xg033EChQoUAgpqUnnXWWcydOxeAVatW0aFDB+Lj47n55puT3WfevHnExMRwxRVXBC2OYFCLsUSkjh39/dix4Y1DRERERCSj5s2bR6NGjahduzbt27dn+/btADRv3pxHH32UZs2aMWjQIGbPnk2zZs2oX78+rVq1YmOgCu1ff/3FJZdcQp06dahXrx4rV65kz549tGjRgnr16lGrVi3Gjx8PwN69e2ndujV16tShZs2afPrppwwePJh//vmHiy66iIsuugiASpUqsXXrVlavXs25557LbbfdRo0aNWjZsiX79+8H4I8//qB27dqcf/75PPjgg9SsWTPV13rmmWfy6quvMnjwYAB+//13GjduTN26dWncuDHLly/n0KFD9OvXj08//ZSoqCg+/fTTJLcLB3POheXEoRYdHe1iYmLCHYachJo1fZXqefMgd+5wRyMiIiIikWrp0qWce+65APT5pg/zNs0L6vGjTovitcteS3Gb3LlzU6tWLQAqV67M2LFjqV27Nq+//jrNmjWjX79+7Nq1i9dee43mzZtTvXp13nrrLQ4fPkyzZs0YP348ZcuW5dNPP+Xbb7/lvffeo2HDhvTt25f27dtz4MAB4uPjyZcvH/v27aNYsWJs3bqVRo0asWLFCr788ku++eYb3nnnHQB27txJ8eLFqVSpEjExMZQpUwbgyPM9e/ZQpUoVYmJiiIqK4uqrr6Zt27bccMMN1KxZk2HDhtG4cWP69u3LV199xaJFi455vatXr+bKK688ZvmOHTsoV64c+/fvZ9euXRQqVIg8efIwZcoUhgwZwhdffMHIkSOJiYnhjTfeAEh2u+Ml/hknMLPZzrno9P00k6au1BKx+veHzp1h1Cjo3j3c0YiIiIiIJO/4rtQ7d+5kx44dNGvWDICbbrqJzp07H1l/zTXXALB8+XIWLVrEpZdeCkBcXBzlypVj9+7dbNiwgfbt2wNQoEABAA4fPsyjjz7KL7/8Qq5cudiwYQObN2+mVq1aPPDAAzz88MNceeWVNGnSJNWYK1euTFRUFAD169dn9erV7Nixg927d9O4cWMArrvuOr766qs0vQeJG1137tzJTTfdxIoVKzAzDh8+nOQ+ad0u1JQYS8Tq2BFq14bXX4dKlWDNGti3D84/H+rVC3d0IiIiIhKJUmvZjRSFCxcGfDJZo0YNZs6cecz6Xbt2Jbnf6NGj2bJlC7NnzyZv3rxUqlSJAwcOUK1aNWbPns3kyZN55JFHaNmyJf369Usxhvz58x95nDt3bvbv38/J9CieO3fukVbdJ554gosuuoixY8eyevVqmjdvnuQ+ad0u1DTGWCKWGdxyi+9K3aKFbzXu1Qvq14e77oK4uHBHKCIiIiKStOLFi1OyZEmmBaZa+eCDD460Hid29tlns2XLliOJ8eHDh1m8eDHFihWjYsWKjBs3DoCDBw+yb98+du7cySmnnELevHmZOnUqa9asAeCff/6hUKFC3HDDDTzwwAPMmTMHgKJFi7J79+40x12yZEmKFi3KrFmzAPjkk0/StN/q1at54IEH6N27N+BbgisEquiOHDnyyHbHx5PcdplNibFEtK5doUsX+OADWLUK1q2Du++Gt96CwN8IEREREZGINGrUKB588EFq167NvHnzkmzBzZcvH2PGjOHhhx+mTp06REVFMWPGDMAn04MHD6Z27do0btyYTZs2cf311xMTE0N0dDSjR4/mnHPOAWDhwoU0aNCAqKgonnvuOR5//HEAevToweWXX36k+FZaDB8+nB49enD++efjnKN48eJJbrdy5coj0zVdffXV9O7d+0hF6oceeohHHnmECy64gLhELVoXXXQRS5YsOVJ8K7ntMpuKb0mWExcHFStCw4ZKjkVEREQk6cJMknF79uyhSJEiALz44ots3LiRQYMGhTWmUBffUouxZDm5c8N118HkybBtW7ijERERERHJXiZNmkRUVBQ1a9Zk2rRpR1qfszMlxpIl3XgjHD4Mn30W7khERERERLKXa665hnnz5rFo0SImTZpE2bJlwx1SyCkxliypTh0/z/GHH4Y7EhERERERyeqUGEuWZAY33AAzZsDKleGORkRERETCLbvWTpLM+dkqMZYs67rrfIKsVmMRERGRnK1AgQJs27ZNyXE25Jxj27ZtFChQIKTnUVVqydKaNoXdu2Hu3HBHIiIiIiLhcvjwYdavX8+BAwfCHYqEQIECBahYsSJ58+Y9Znkwq1LnCcZBRMLl8svh0Udh82Y49dRwRyMiIiIi4ZA3b14qV64c7jAkC1NXasnSWrb09999F944REREREQk61JiLFla3bpw+unwzjvhjkRERERERLIqJcaSpeXKBffeC9OmwRVXwPbtsHcv7NgR7shERERERCSrUGIsWV6PHnDHHfD991CqFBQpAiVLQq9eEBcX7uhERERERCTSqfiWZHmFCsFbb0H9+jB8OFx2GWzYAG++CfHxfp2IiIiIiEhylBhLtnHLLf6WoHBhGDgQbr0V6tULX1wiIiIiIhLZ1JVasq1+/Xxr8htvhDsSERERERGJZEqMJdsqUQJuugk+/BDWrQt3NCIiIiIiEqmUGEu29vDD/v6VV8Ibh4iIiIiIRC4lxpKtnXEGtG8Pn36qCtUiIiIiIpK0kCbGZlbCzMaY2TIzW2pm5yda94CZOTMrE3he2symmtkeM3vjuOPUN7OFZvaXmQ02Mwtl3JK9tG8P//4LM2eGOxIREREREYlEoW4xHgR845w7B6gDLAUws/8BlwJrE217AHgCeCCJ4wwBegBVA7fLQhizZDNXXAEFCsDbb4c7EhERERERiUQhS4zNrBjQFBgO4Jw75JzbEVg9EHgIcAnbO+f2Ouem4xPkxMcpBxRzzs10zjngfaBdqOKW7KdYMbjnHhg9GhYsgB9/hEmTwh2ViIiIiIhEilC2GJ8JbAFGmNlcM3vXzAqbWVtgg3NufhqPUwFYn+j5+sCyE5hZDzOLMbOYLVu2nFTwkr08/DDkzw9160KLFnDllVC1KnzzTbgjExERERGRcAtlYpwHqAcMcc7VBfYC/YHHgH7pOE5S44ldEstwzg1zzkU756LLli2bznAlOytZElq1gvh4uPRSeO45OHAAOnSAHj0gNjbcEYqIiIiISLiEMjFeD6x3zv0WeD4GnyhXBuab2WqgIjDHzE5L5TgVEz2vCPwT/HAlu+vXD5o3h5Ej4dFH4Y8/oGNHeOcdeP75cEcnIiIiIiLhErLE2Dm3CVhnZmcHFrUA5jjnTnHOVXLOVcInvfUC2yZ3nI3AbjNrFKhG3RUYH6q4JfuqVw+mToXy5f3z006DDz6A66+Hp5/2ibKIiIiIiOQ8oa5K3RsYbWYLgCggxXa5QCvyq0A3M1tvZtUDq+4A3gX+AlYCX4cqYMl53ngDTj0VHkiqHvpxnIPJk+HgwdDHJSIiIiIimSNPKA/unJsHRKewvlJKzxMtjwFqBjE0kSNKlIB774UHH/RVq2vXTn7bn36C1q3hhht8a3Nia9bAxo3QqFEooxURERERkWALdYuxSJbQvTvkywcffpjydpMn+/sPP4Q//zy6/JdfoHFjOP98uPNO37IsIiIiIiJZgxJjEaBUKZ/YTpmS/DaxsfDVV1Crlp/6aeBAv3z4cGjWDLZvh4sugiFD4LXXMiVsEREREREJAiXGIgGXXAJz50JyU2DfcAMsWwb33w833gjvvee7U999t0+MN2zwiXWHDn688q+/Zm78IiIiIiKSMUqMRQIuvdTfJ3SXTmz+fPj0Uz/N0003wQsvwCmnQNeuUKgQfPyxnys5Vy4YNQrKlfMJtLpUi4iIiIhEPiXGIgHnnQdVqvh5jhOLj4fHHoPChY9Wri5TBqZPh2eegfHjfSKcoEgRePxx+O033wItIiIiIiKRTYmxSIAZ3Hyzrzy9cuXR5c8+C5MmwXPP+VbhBGec4RPgxo1PPFabNv7+559DGrKIiIiIiASBEmORRLp29d2hR46EvXt9heknn/Rjiu++O+3HqVABzjpLibGIiIiISFagxFgkkYoVoVUr30pcrRoMHeqT47ff9i3K6dGsmU+MDx4MTawiIiIiIhIcSoxFjjN4sG85vuAC+OYbePNNKFgw/ce5+mrYsQPGjQt2hCIiIiIiEkzmsmnZ3OjoaBcTExPuMCQHi4/3xbxOPRVmzEh/i7OIiIiIiCTPzGY756KDcSy1GIuESK5c8MgjMGsWfP55uKMREREREZHkKDEWCaHu3aFmTV/AKz7eJ8k9e8KAAXDoULijExERERERgDzhDkAkO8udG554Aq65Bq691s95nDcv7NkDW7fCiy+GO0IREREREVGLsUiIdewI3brBZ5/BxRfDmjU+UR4yBHbtCnd0IiIiIiKixFgkxHLnhhEjYNMmmDwZSpWCBx/0SfGwYeGOTkRERERElBiLZJJTTz36uH5933o8cKDGGouIiIiIhJsSY5Ewuf9++OcfmDAh3JGIiIiIiORsSoxFwqRVKzj9dHWnFhEREREJNyXGImGSOzdcfz388IOvUi0iIiIiIuGhxFgkjJo29fMb//FHuCMREREREcm5lBiLhFHDhv5+xozwxiEiIiIikpMpMRYJo5IloXp1+PXXcEciIiIiIpJzKTEWCbOLL4affoJ9+8IdiYiIiIhIzqTEWCTM2raF/fthypRwRyIiIiIikjMpMRYJs2bNoHhx+OijcEciIiIiIpIzKTEWCbN8+eC22+Dzz2HVqnBHIyIiIiKS8ygxFokA994LBQr4btUffggrVsDu3eGOSkREREQkZ1BiLBIBypeHCRNgyxa48UaoVg2KFYOOHWHnznBHJyIiIiKSveUJdwAi4rVoARs3wrx5sGABLF8OAwbAtdfCV19BLn2NJSIiIiISEkqMRSJIrlxQr56/AVSoAL17w8SJcNVV4Y1NRERERCS7UhuUSATr2RMqV4YXXwTnwh2NiIiIiEj2pMRYJILlyQMPPACzZsG0aeGORkREREQke1JiLBLhbr4Zypb1441FRERERCT4lBiLRLiCBX1y/PXX8N9/4Y5GRERERCT7UWIskgV06QKxsfDFF+GOREREREQk+1FiLJIFREXBWWfBuHHhjkREREREJPtRYiySBZhB69YwdSrs3++XHTgAhw+HNy4RERERkexAibFIFnH55T4pTkiOo6OhShUYNAjuvBM2bw53hCIiIiIiWVOecAcgImnTvDmULg1vvw3Tp8Pixb57dZ8+fv1338Eff0DJkuGMUkREREQk61GLsUgWUaAA3HUXTJgAL7wAnTrBkiUwdix8+y2sWQPt2sGmTeGOVEREREQka1FiLJKF3H330cc9ekC+fD4ZbtkSRozwLcbdu5+4n3OwfDn8/TfEx2dauCIiIiIiWYISY5EspHRpn/w+8QS0aHHsuhtu8Mu//hpmzz66fO9euOwyOOccOPNMn0THxWVu3CIiIiIikUyJsUgWEx0NTz8NuZK4eu+6CwoVgnffPbps8GA//vj55+Hxx+GHH/w4ZRERERER8cw5l/IGZgWAK4EmQHlgP7AImOScWxzyCDMoOjraxcTEhDsMkUzXpYtPfjduhH37oFIlaNwYvvrKd6lu0MBv98cfKR9n716fULdpA3lUpk9EREREIoyZzXbORQfjWCm2GJtZf+BX4HzgN+Bt4DMgFnjRzL43s9rBCEREguPaa2HrVnjpJXjySdi+Hfr39+vMfNGumBhYuzb5Y6xZAxdcAB06wHPPZUrYIiIiIiJhk2KLsZm1ds5NSmH9KcDpzrmIa5pVi7HkVPHxfkzx99/75126wMcfH13/559w9tnw+uvQq9eJ++/YAbVqwe7dEBUFv/4KGzbAKadkRvQiIiIiImmTaS3GCUmxmXVOIojOzrl/IzEpFsnJcuWCzz+HUaNg6lQYPfrY9dWq+SJcU6Ykvf/DD/tu2N9/D6++CrGxMHly6OMWEREREQmXtBbfeiSNy0QkAhQvDl27QvPmSRfpuuQSnzTHxh67fNkyX7irVy847zyoWxcqVPBzJye2fz8sWqSpn0REREQke0htjPHlZvY6UMHMBie6jcSPMxaRLOiSS2DXLpg169jlTz7pq1o/9ph/njAmeeJEPw8ywNKlUL26727dpUvmxi0iIiIiEgqptRj/A8QAB4DZiW4TgFahDU1EQqVVKyhQAD799OiyuXPhs8+gTx8oW/bo8kcegYIF4dZbfVGuTp18tes2bXyX7eNbk0VEREREsppUp2sCMLO8QB58oa3lIY8qCFR8SyRlV18NP/3kk908eaBdO5gxA/7+G0qUOHbbTz7x1a4TTJ4Ml17qW46LFIHZs33rsoiIiIhIZsm04luJXAbMA74JBBBlZmonEsnCevWCLVugbVs4/XSf7D788IlJMfgu07/+CoMH+yT48st9Mt23r29p/vnnTA9fRERERCRo0poY9wcaADsAnHPzgEqhCEhEMkfTptC7t69Offiw71b90EPJb9+4sd++Xr2jy665BgoXho8+Cn28IiIiIiKhktbEONY5tzOkkYhIphs0CKZP90W4rr466QrWKSlcGNq392ONDx8OTYwiIiIiIqGW1o/Bi8zsOiC3mVUNVKqeEcK4RCQTmMEFF0CVKhk/Rtu2sGOH71ItIiIiIpIVpTUx7g3UAA4CHwE7gT6p7WRmJcxsjJktM7OlZnZ+onUPmJkzszKJlj1iZn+Z2XIza5VoeX0zWxhYN9hMZX5EIkWTJv7+l1/CG4eIiIiISEalKTF2zu1zzj0GNHfOneece9w5dyANuw4CvnHOnQPUAZYCmNn/gEuBtQkbmll1oAs+Ab8MeMvMcgdWDwF6AFUDt8vSEreIhN5pp0HVqjBtWrgjERERERHJmDQlxmbW2MyWcDSxrWNmb6WyTzGgKTAcwDl3yDm3I7B6IPAQkHiuqKuAT5xzB51zfwN/AQ3MrBxQzDk30/m5pd4H2qXx9YlIJrj4YvjxRz+/sYiIiIhIVpPWrtQDgVbANgDn3Hx80puSM4EtwAgzm2tm75pZYTNrC2wIHCOxCsC6RM/XB5ZVCDw+fvkJzKyHmcWYWcyWLVvS+NJE5GR16QJ79sAETeImIiIiIllQmmvQOufWHbcoLpVd8gD1gCHOubrAXvy0T48B/ZLYPqlxwy6F5UnFOMw5F+2ciy5btmwq4YlIsDRtCv/7H7z5Jrgkr04RERERkciV1sR4nZk1BpyZ5TOzBwh0q07BemC9c+63wPMx+ES5MjDfzFYDFYE5ZnZaYPv/Jdq/IvBPYHnFJJaLSITIlQseecRP/TR+fLijERERERFJn7Qmxj2BuzjarTkq8DxZzrlN+IT67MCiFsAc59wpzrlKzrlKgWPVC2w7AehiZvnNrDK+yNbvzrmNwG4zaxSoRt0V0EdvkQhz661Qqxb06AF//AHx8TBnjp/KSUREREQkkuVJaaWZdXDOfemc22pmvZxz29N5/N7AaDPLB6wCbk5uQ+fcYjP7DFgCxAJ3OecSumvfAYwECgJfB24iEkHy5oVPP4XmzaFhQ6hUCf7+2z+eNs2vFxERERGJROZSGBBoZnOcc/WOf5wVREdHu5iYmHCHIZLj7NoF994LP/0EdevCF19A377wwgvhjkxEREREshMzm+2ciw7GsVJsMebYwldJFcESETlGsWIwfPjR5z16wIsvQseOEB2UP1siIiIiIsGV2hjjgmZW18zqAwUCj+sl3DIjQBHJ2gYMgKJFYeDAcEciIiIiIpK01FqMNwGvJvEY/JRJF4ciKBHJPooVg1tugTfegJdfhgpJzkIuIiIiIhI+KSbGzrnmmRSHiGRjvXvDoEEwZAg8+2y4oxEREREROVaKXanN7MJU1hczs5rBDUlEspszz4Qrr4T33oMU6v2JiIiIiIRFamOMO5rZDDPrZ2atzayBmTU1s+5m9gHwFX4KJRGRFLVvDxs3wqJF4Y5ERERERORYqXWlvtfMSgKdgM5AOWA/sBR42zk3PfQhikh2cOml/v6776BWrfDGIiIiIiKSWIrzGGdlmsdYJPLUqAGlSsG0aeGORERERESyumDOY5xaV2oRkaC5+WaYPh3mzw93JCIiIiIiRykxFpFM0707FCwIr78e7khERERERI5SYiwimaZUKbjxRhg9GhYsgL17wx2RiIiIiEgaE2Mz62xmRQOPHzezL82sXmhDE5Hs6J57/JRNdepAkSJQqBB07gz//hvuyEREREQkp0qxKnUiTzjnPg/Ma9wKGAAMARqGLDIRyZaqV4dly2DqVJ8Mr10Lw4fD4cMwbly4oxMRERGRnCitiXFc4L41MMQ5N97M+ocmJBHJ7ipV8oW4Ej9/6CF47jl47LFwRSUiIiIiOVVaxxhvMLO3gauByWaWPx37ioik6L774IYb4PHH4Ysvwh2NiIiIiOQ0aU1urwa+BS5zzu0ASgEPhiooEclZcuf23anr14c+ffwYZBERERGRzJJiYmxmpcysFFAA+AnYFnh+EIgJfXgiklPkywd33w3r18Ps2eGORkRERERyktTGGM8GHGBJrHPAmUGPSERyrNatfevx2LEQHR3uaEREREQkp0ixxdg5V9k5d2bg/vibkmIRCarSpaFFCxg5Eg4dCnc0IiIiIpJTpHUeYzOzG8zsicDz082sQWhDE5GcqE8f+Ocf+PTTcEciIiIiIjlFWotvvQWcD1wXeL4beDMkEYlIjnbZZVC5Mnz8cbgjEREREZGcIq2JcUPn3F3AAQDn3HYgX8iiEpEcywzat4cffoBdu8IdjYiIiIjkBGlNjA+bWW58wS3MrCwQH7KoRCRH69DBjzGeMOHost27YeBA2LEjbGGJiIiISDaV1sR4MDAWOMXMngOmA8+HLCoRydHOPx8qVYL33z+67PXX4b774KKLYPPmsIUmIiIiItlQmhJj59xo4CHgBWAj0M4593koAxORnCtXLujaFaZMgTlz4PBhGDYMzj4b/vwTLr0UDh4Md5QiIiIikl2ktSr1IKCUc+5N59wbzrmlIY5LRHK4Xr2gYkW44gpfkGvNGhgwAD77DBYuhOfVZ0VEREREgiStXannAI+b2V9m9oqZRYcyKBGRsmXhm2+gaFGIiYEhQ+DKK6F1a+jYEQYN8uOORUREREROVlq7Uo9yzl0BNAD+BF4ysxUhjUxEcrzq1WHRIti4EXr2PLr8wQdh504YNSp8sYmIiIhI9pHWFuMEVYBzgErAsqBHIyJynPz5oVChY5c1bAg1asCXX4YnJhERERHJXtI6xjihhfhpYBFQ3znXJqSRiYikoG1b+OUX2L493JGIiIiISFaX1hbjv4HznXOXOedGOOd2hDAmEZFUtW0LcXEwfny4IxERERGRrC6tifEw4DIz6wdgZqebWYPQhSUikrKGDaFaNXj33XBHIiIiIiJZXVoT4zeB84FrA893B5aJiISFGdx2G/z6KyxY4JctXQqNG/upnA4fDm98IiIiIpJ1pDUxbuicuws4AOCc2w7kC1lUIiJpcMstULgwvPyyf/7GGzBzJjz2GDRqBN9+G974RERERCRrSGtifNjMcgMOwMzKAvEhi0pEJA1KloQ774TRo31S/PHHcO218OmnvijXZZfBsGHhjlJEREREIp0551LfyOx64BqgHjAK6AQ87pz7PLThZVx0dLSLiYkJdxgiEmIHDkDr1vDjj5A3L8yYAdHRcPAgtGwJf/4Jq1ZBwYLhjlREREREgsnMZjvnooNxrDS1GDvnRgMPAS8AG4F2wK/BCEBE5GQUKACTJsGDD8Inn/ikGPz8x08/DZs2wWefhTdGEREREYlsaWoxTnJHs7XOudODHE/QqMVYRJyDM86AevVg3LhwRyMiIiIiwZTpLcbJxRGMAEREQsUM2rXzRbh27Qp3NCIiIiISqU4mMc5YU7OISCbq2tWPQ3711XBHIiIiIiKRKk9KK83sdZJOgA0oEYqARESCKToaOneGAQPg3nuhePFwRyQiIiIikSa1FuMYYHYStxigd2hDExEJjocfhr17YdSocEciIiIiIpEoxRZj55w+RopIlle/Ppx/PjzzjC/EdcEFsHGjL85VoUK4oxMRERGRcDuZMcYiIlnGyJG+GFeTJlC1qk+I69aFHTvCHZmIiIiIhJsSYxHJEapVg+XLYfBgKF0a2reHLVugShX4/vtwRyciIiIi4ZRqYmxmuc3s3swIRkQklEqWhN694bff4Msv4Z13YNs2eP75cEcmIiIiIuGUamLsnIsDrsqEWEREMtWtt8LTT8NPP8GaNeGORkRERETCJa1dqX81szfMrImZ1Uu4hTQyEZFMcMMN/n706PDGISIiIiLhY84lNU3xcRuZTU1isXPOXRz8kIIjOjraxcTEhDsMEckCmjb1442XLPEFukREREQk8pnZbOdcdDCOleJ0TQmccxcF42QiIpGoa1e47TaIiYHzzgt3NCIiIiKS2dLUldrMTjWz4Wb2deB5dTO7JbShiYhkjk6dIH9++OCDcEciIiIiIuGQ1jHGI4FvgfKB538CfUIQj4hIpitRAtq2hY8/hri4cEcjIiIiIpktrYlxGefcZ0A8gHMuFtDHRxHJNjp0gK1bYfbscEciIiIiIpktrYnxXjMrDTgAM2sE7AxZVCIimeySS3zhre++C3ckIiIiIpLZ0poY3wdMAM4ys1+B94G7QxaViEgmK1MG6tWDceMgDcX6RURERCQbSWtivBhoBjQGbgdqAMtS28nMSpjZGDNbZmZLzex8M3vGzBaY2Twz+87Myge2zWdmI8xsoZnNN7PmiY5TP7D8LzMbbKYJVUQk+G67zXel/vHHcEciIiIiIpkprYnxTOdcrHNusXNukXPuMDAzDfsNAr5xzp0D1AGWAq8452o756KAr4B+gW1vA3DO1QIuBf7PzBLiGwL0AKoGbpelMW4RkTTr1g3Kl4dnnoFVq2DfPnjuORg9OtyRiYiIiEgopTiPsZmdBlQACppZXSChpbYYUCiVfYsBTYFuAM65Q8Ch4zYrTGDcMlAd+CGw7b9mtgOINrN1QDHn3MzAcd8H2gFfp/rqRETSIX9+eOgh6NMHzjrLjzl2DnLnhkqV4IILwh1h8nbuhJde8vGXKBHuaERERESylhQTY6AVPrGtCLyaaPlu4NFU9j0T2AKMMLM6wGzgHufcXjN7DuiKL+B1UWD7+cBVZvYJ8D+gfuA+Hlif6Ljr8cn6CcysB75lmdNPPz2V8ERETnTbbfDLLxAVBQcPQrlyMHAgXHMNzJvnxyJHovfegxdegL//9tNOJRYb6+/zpPYXX0RERCSHMpeGKjNm1tE590W6DmwWDcwCLnDO/WZmg4BdzrknEm3zCFDAOfekmeUBXsEnymuAvMDbwD/AC865SwL7NAEecs61Sen80dHRLiYmJj0hi4gkae5caNgQunSB998PdzRJa9XKV9Q2g6VL4eyz/fLPP4eePeHMM33CX7BgeOMUERERCRYzm+2ciw7GsdI0xtg594WZtTazh8ysX8Itld3WA+udc78Fno8B6h23zUdAx8A5Yp1z9zrnopxzVwElgBWB41RMtE9FfLIsIpIp6taFvn3hgw9863Gk2bMHpk6Frl0hb154/XW/fPNm3wK+dy/ExECvXuGNU0RERCRSpSkxNrOhwDVAb/w4487AGSnt45zbBKwzs0C7BS2AJWZWNdFmbQlUtzazQmZWOPD4UiDWObfEObcR2G1mjQLVqLsC49P6AkVEgqFfP+jQAR54AP7889h1c+fCo4/C4sXhiW3ePDh8GK6+Gq6/HoYPh/Xr4e23YdcumD8fnnjCd7f+5JPwxCgiIiISydLalXqBc652ovsiwJfOuZap7BcFvAvkA1YBNween40fO7wG6Omc22BmlYBvA8s3ALc459YEjhMNjAQK4otu9XapBK6u1CISbP/+64twXXXV0XG8P/wArVv78cj16sHvv/tiXZnpjTegd2+fDB8+7LtRN2gA06fDxRf7GOPi/LKtW2H5cihQIHNjFBEREQm2TO9KDewP3O8LzDt8GKic2k7OuXnOuejA9EztnHPbnXMdnXM1A8vaOOc2BLZd7Zw72zl3rnPukoSkOLAuJrDPWc65XqklxSIioXDKKb7q8yef+Cmc/voLOneGqlV99+U5c2DEiJM7h3M+uT54MO37zJ/vi4KVL+8T97ff9q3IALfe6u9z54ZXXoG1a+HNN08uRhEREZHsJq0txk8Ar+O7Q7+Jn2LpHedcauOMw0YtxiISCocP+1bYX3/1ra4FCvhE9qyzoFkzX/hq1SooWjRjxx8wAB58ECpXhp9+grQU2D/vPCheHKZMObrs4EHYuBHOOMMX5Epw+eXw22+wYYMKcYmIiEjWlmktxmbWx8zOw1eF3hGoTH0GcE4kJ8UiIqGSN6+v/tyvH9x0ky9qVaWKTz5feMF3Vf7ss7Qda8UKGDLEj/09dMgX0OrbF047DbZs8a3RcXEpH+PgQVi40BcISyx/ft96nDgpBt/levt2381aRERERLzUZrWsCAwCzjGzBcAM4FdgZqgDExGJVAULQv/+Jy5v3BjOPdcnurfckvpxmjaFTZv844Tty5WDJUvg66/huutg2DC4447kjzF3rk+Ozz8/bbE3a+aT+++/h0svTds+IiIiItldii3GzrkHnHONgdOAR4H/gO7AIjNbkgnxiYhkGWbQvTvMmAHLlqW87c6dPim+7z7fSly0KDz1lO8+XaKEnzO5WTN45hnfmpycGTP8fVoT48KF4cILfau3iIiIiHhpLb5VECgGFA/c/gF+S3EPEZEc6MYbfaGr995Lebu///b355/vu2D/95/vnl2tml9u5hPmjRvh88+TP86MGX48crlyaY+xZUtfsCuhtVpEREQkp0ttjPEwM/sV+BQ4H9+VunOg0vTNmRGgiEhWcuqpcNllMGZMytslJMaVA/X98yQxsKVlSz/10muv+WrVx3MOZs5Me2tx4uPCscW6RERERHKy1FqMTwfyA5vwcwuvB3aEOCYRkSzt8st94rtyZfLbrF7t7yunMPFdrlxwzz2+wNfMJCo7rF0L//zjxzanR1SUn95p0qT07SciIiKSXaU2xvgy4DxgQGDR/cAfZvadmT0V6uBERLKihKJW33+f/DZ//+3HFZcsmfKxbrzRV5j+4osT16V3fHGCXLn8GOYxY3xX7dWr/bzHu3al7zgiIiIi2UWqY4ydtwiYDHyNr0p9FnBPiGMTEcmSqlb1LcETJya/zbJlfpvjp1M6XpEivlhWUt2ex4zxyXXt2umP8e67ITYWypf3cdSt6+dCvuoqP52TiIiISE6S2hjju83sEzNbB/wCXAksBzoApTIhPhGRLMcMOnXylZ//++/YdXv2+OrT338PrVun7XiXXAILFsDmzUeXzZoFX34JDzyQ9Pjk1FSt6qeEeughGDoUPvrIP/7qK78uYQy0iIiISE6QWotxJWAM0MA5d6Zz7kbn3FvOufnOufjQhycikjV16eJbZN9/3z/fts1Xqj7rLD8HcqdOPkFOi8sv9/eJC3p9+KGfT/n++zMe42WXwUsvwe23w7XX+se//+6nknr99YwfV0RERCSrMZdUqdNsIDo62sXExIQ7DBHJoZzzLb3z58O0adCihR/PW6cODBmS/nHB9epBfDzMneufV6rki2iNHx/syH2S/PXXsGaN714tIiIiEonMbLZzLjoYx0rrPMYiIpIOZjBggO9KHR3tW2E//NB3gU5vUgxwxx0+yf7qK1i0yFekvvLK4McN8OCDPt5XXw3N8UVEREQijRJjEZEQqVsXunaFfft8N+rrr4cCBTJ2rG7d4Jxz4N574eOP/bJQJcb16kH79r479cGDoTmHiIiISCRRYiwiEkJDhsBvv8E115zccfLmhbff9kWxXnjBJ93lygUnxqTcdpuvTj15cujOISIiIhIplBiLiIRQwYLQoEFwjtW0KYwc6adYuvXW4BwzOZdeCqeeerR1WkRERCQ7y8AkHyIiEi433uhvoZYnj6+GPWGCL/qVS1+jioiISDamjzoiIpKkiy/2xcMWLgx3JCIiIiKhpcRYRESSdNFF/n7s2PDGISIiIhJq6kotIiJJqlgR2rWDl17yVapnzIA9e+DCC/0UVHnzhjtCERERkeBQYiwiIsl6802IivK3xC6+GCZOhEKFwhGViIiISHCpK7WIiCSrfHmfALdrB999B8uWwaBB8OOP8Pjj4Y5OREREJDjUYiwiIilq2PDYccZnnw1Ll8Jrr8HNN0OtWmELTURERCQo1GIsIiLp9txzULw4PPJIuCMREREROXlKjEVEJN1KlYJevWDyZNi0KdzRiEgk2rMH/vwz3FFEngUL/HsjIpFFibGIiGRIly7gHHz5ZbgjEZFI4xy0aeOHWixZEu5oIseePdCgAdx3X7gjEZHjKTEWEZEMqVEDzj0XPvss3JGISKSYPx+GDoXbboOffoL4eLjlFoiLC3dkkWH2bDh4ED78EP7779h1mzfDpEn+SwURyXxKjEVEJMOuvhp++UXdqUUENmyACy6AO+6A4cPh3nthxAiYNQuGDEl+v7g4nyzmBLNm+fv9+/17lODXX6FuXbjySv+lgohkPiXGIiKSYZ07+9YNtRqL5Dxz5/qELkH//hAbC3Pm+NbQV1+F66+Hpk3hlVeObTXet89P/fbUU1ClCrRsmTNaSmfN8q+3eXN46CEYORJef90/L1wYevTwCfOYMWEOVCQHMpdN/wpFR0e7mJiYcIchIpLtNWoEGzfCihWQL59fFhfnPzTXqwe59BWsSLazeTNUrw4HDsDixfD333DxxdCz54mtw198AZ06+eT4/vth9Wro0AHmzTt2u5kz/d+T7KxyZT8FXrdufgx2bKxf3qYNvP8+FCkC0dH+fV26FMzCGq5IxDOz2c656GAcSx9XRETkpPTvD2vXwhtv+Oc7dsD558N55/lugbt2hTM6EQmFV1+F3bt94hYV5ZNiM7j77hO3veoqaN0aHnzQJ4SXXOKT40mT/Jdou3ZBsWIweHAmv4hMdvCg/1tZrRpcdpl//s47fk74ceOgRAnIk8d/ebB8OXz/fZgDFslhlBiLiMhJadUKrrgC+vWD6dPh9tt9V8o+ffwHu9atfQEeEck+pk/31ZW//RZOP91f/3/84QvyHS9PHpgwwX+J9sEHsGoVjB/v/27kygVFi/oCXZ9/7scpZ1erV/u/hVWq+Oe5csGtt8I99xzbs6ZzZ6hQAR54AA4dCkuoIjmSEmMRETkpZr4K7amnQpMmfrzxc8/BwIG+S+X06RqDLJKdHDrkqys3auSLbS1Y4McK16+f/D65csGTT8IPP8BHH/lxx4n16uVbj4cOPXHfCRP89HADB2btL9n++svfJyTGySlQAN58ExYu9F8WRKJnn/VTTm3efHTZrFlw6aVQpgzcdVfOGDMu2YvGGIuISFBs2wajRkHFir5aNfgPuvXr+66SS5dC/vzhjVFETt4ff/jW4s8+862bwXLVVX6c8dq1PjmMi/PJ9HPPQenS/m/MI4/A888H75yZadAg35Pm33+hbNmUt42P99u0besre0eSfft8oTDwQ2b694eaNeHss6FUKf83f+JE+OQTuOaasIYqOYDGGIuISMQpXdq3ICQkxQC5c8PLL/vCPO+9F77YRCR4Zszw98EulNWnD2zZAgMG+MSwc2efFN96q+9i3bmzb0ndvTu4580sf/3lx1KXKZP6trlywUUXwY8/Rl7L6/z5/r5rV/+4dWufGDvnfzfGjoU6dXwvgkiLXSQlSoxFRCSkWrb0H5rUnVoke5g6Fc48E/73v+Ae96KL/BdrTz/tu+SOHeu/WBs2zPc2uf9+3/tk9Ojgnjez/PCDr9Sf1krTLVr41vM//0x6fWysr2S9d2/wYkyL2bP9/fPP+1b8Xr3glFN8i/gZZ/gvRO+6y/cSmjMnc2MTORlKjEVEJOTatIFp02D79nBHIiInIz4efvnFJ7GhMHSor1r944/QsaMvQJWQSDZo4LvrfvFFaM4dSkuX+lunTmnf54or/P348UeXxcbCE0/4Mde9esFNN/lW9cwUE+NrSpQv76eXev113xp+++1Ht+nUyU/fN3Jk5sYmcjKUGIuISMi1aePHC37zTbgjEZGMOnwY7r3Xf8HVokVozlGyJEye7Mexfv75sa2rZn7+46lT4b//QnP+UHnrLR9/+/Zp3+eMNb/wY/H2tH66Ibz0Evt2Hubyy33hqzFj4O23/XYjRmRu9eqYGD/Xckot3yVL+tb/UaM0ZZ9kHUqMRUQk5Bo08F3tJk4MdyQiklFduvi5hu++O7hFt5JSsGDSiVeHDv5Ltqz0t+TDD/3Y6Dvv9K2sqYqPh4cegmbNOM/9xo69eaBvX3bXasz6KUt55x3f+jxhgi9wtWmT75GTGfbs8eeOTkOpo3vu8ePBVV9CsgolxiIiEnK5c/sCLZMn+1YnEclali6FL7+Exx/3Y0nz5AlPHPXr+3mTv/zy6LIFC3yBrq5d/a17d1i5MjzxHW/hQrjxRj+VXZqqaTsHvXvDK6/AHXeQb+1K7qz9K9fnH0PudX8zL1c9bj1lAlWr+p44V1zhfxY//hjylwLAvHk+b09LYhwd7afzev11/2WGSKRTYiwiIpmiQwfYudOPl9u1y0/NUr26b0U5cCDc0YlISoYM8WNG7747vHEkdKf+5htfvbpyZV8B+bPP/Jzp06f7Ftr+/TM/tuXLYc2aY5e99ZafemrsWF+ROlVPPOF3eughePNN8hUvyNdfw/aLO3JlpcUcqFrbD+CdMAGAokV9j5wffgj+60nKzJn+PqU5qxO75x5YtQomTQpdTCLBonmMRUQkU8TF+cI5xYr57oSTJvkiO1OmwHXXZd1KsyLZTVyc7+WRYM8eqFDBz6n7wQfhiyvBhg2+B8r8+XDWWXDzzf6W0E35nnt8Ir9mDZQrd+y+I0b4Xis9egQ/roSu33v2+Hl+d+3yMV19dRq7E3//vS/jf8st8M47Sfcl37HDbzNvnh9o3LYtzzzj53v+7Tc/rzDAwYO+KFfZsr6KdK5c8NpraUzOk/Hbb9C8OdSqBb//nrZ9YmN9BfMqVTKvVVtylmDOY4xzLlve6tev70REJLJ8+qlzefI4lzu3c2+95Zc9/bRz4Nz48eGNTUScGzXKuVKlnJs9++iy4cP9Nfrrr+GL63iHDzu3YoVzBw+euG7FCufMnOvX79jlv/3mXK5cft0zzzj3/vv+OMHw99/+PQLnnnrKL3vjDf/8jz/ScID9+5076yznqlVzbt++lLfdvt25885zLm9e5776yu3Y4Vz58s41bOhcfLzfpEuXo/Ek3O64I/UwNmxwbs2aE5cfPOhcjRrO/e9/zv37bxpeT6JYf7rseTeBK92/Nz2Qzp1FUgfEuCDlj2oxFhGRTLVsmW+xqVXLPz98GGrXhkKFjs6PKSKZb+tW37K3cydERflWwbx54bLL/HQ8K1akfQ7ecGvTxse/bp3vAj5/PjRr5ltMCxXy3Z7BV3h+7LGTP9977/mG3jJl/FRGixb51tv4+DT+XXv2Wd+N+rvv/CTOqdmxw3e5WbgQJkxgyKpW3HmnP/+11/pxvbffDl9/7e83bvQ9tDdu9IUQk7J7t/9bXKSIP2xizz/v36eJE+HKK9PwesC/lhtugC1bWGLVOZvl5C5amLjnX2J+o9upUNE49dQ0HiuC7d8Pq1f737Mzz8w610h2EcwWY40xFhGRTHXOOUeTYvAfvO+8E+bM8b0DRSQ8vvzSJ8X9+vlr8f/+DzZv9uNXO3bMWh/4e/SAf//1UzsdPgzduvlK19Om+aR1+3ZfWfvpp2HJkpM/31df+YT4scdg8WI/VCQmxlfyTtWqVT7z7NQpbUkxQIkSPvGsXh2uuoruh4aSL69j61afFDdpAgMHwt9/w6OP+uJk8fEwbtyJh5o/H37+Gfr08QneokVHi5c55ytq9+/vfwfSnBR/+qmvDHbaaTBnDm/duZjatojlJRqSu9cd/BR9PxXKOx54wJ8jq9q7F+rW9T+GKlX8y5YsLFhNz5F2U1dqEZGsY+tW5/Lnd65Hj3BHIpJzXXaZc2ee6bvjduzor8kzzvA9dhcsCHd06bN/v3OFCzt3++3OvfCC70r8xRfHbrNpk+823qTJifuvWePcrl1pO9e6dX54yAMPOLd+vXNFix7tvrxyZSo7x8c7d/HFfqd169J2wsS2bnWuZUvnwO25sKX7d+x09+OPzh06dOJpzjrLv9aE7tbx8c5dffWx3a0Tnr/6qt/m2Wf989atnfvvvzTGNHmyHzPTtOmRN3H7dt8NOxdx7osKvZ0DN7nWQw7i3QsvpP9lR4KvvvLXCDj32mu+F3x09NH3VzIHQexKHfYENlQ3JcYiIlnLbbf5DxmbNoU7EpGcZ9MmnwA/8IB/vnGjcyVLOlexonOzZoU3toy6+mrnihf3f1c6dEh6m8GD/afhxK/xo4+cy5fPuUqVnLv1VueefDLlZKdnTz92OSEJXrLEL3vppTQEmTCAe8iQNL6qJMTF+cysdGl/rNq1nXv55RMS7YTXOnq0fz5mjH/+4IP+S4PHHvNfKNSr51z16s5t3uxcuXL+C5O4uDTG8vvvzhUs6A+yc+cxq/791/9eufh4P+AZ3KdnP+GKFnVu27aMv/xwiI93rn59//6NGOGXvfmmf554fL6EnhJjJcYiItnOsmW+KM7jj4c7EpGc5b//fPIDzi1ffnT5hg0n5DZZytKlPikuUcK5f/5Jeptdu3xj7fXX++cHDzpXtqzP6+rU8Y/Bue++O3Hfdet8Czs4d999GQhw4ULnChVyrlmzdGSeKdizx1c1PP98H5SZc23bOrdokXPOudhYX6CrTBmfpNap49y55/rliY0e7Y5pRR4zJo3n37bNdzE44wyfVackLs65W25xDlwvXne9e6fztWaiAwec69vXualT/fOpU5075RT/3iQUkXTOuS1b/Bck+h+WuYKZGKv4loiIRIx27eCXX3zBnMKFwx2NSPYXG+vnwZ0710/HNH58uCMKrh9+8MWkGjZMfps+fXxhqmXLYPJk6N3bz5PcqpWf9uj00/17NHHisftddZVf1q8fPPywH8OcZjt2+IPu3u0LLBw/r9TJWrkSRo2CwYP9OXr2hGefZdGGkkfmID50CIYNg9tuO3bX2Fg/VvrAAT9G+bPP/FzMKYqP93/Av/nGTybdoEHqMcbGQseOxE+YSBf7jKeXdOKcczLyYkPriy/88G+Axo1h1iw/f3bXrn666cTvzUUX+enEpk2DPAX3UqAAFM6nf2ahpOma1GIsIpIt/fij/xb+44/DHYlIzjBwoL/mXnkl9VmCsqsVK45tIW3S5NgG3H79fOPrihVHly1a5Ld95pkMnDA21rk2bfw43GnTTjr+FG3d6lyvXr4ps1Qp5554ws0Yu8ldcIHvJbB3b5DO06+ff0MGD07ffnv3uoP1z3f7ye8+7PFzkIIJrquv9i3E/fv7ngS33pr8+POxY/14c4qvcfTHvTP7nUyNNSdCLcapU4uxiEjWExcH//ufb90ZOzbc0Yhkb//+C2edBU2b+qrKWanq9EmJjfXloq+8Ejp0gGLFGD/eT0lVogTceKOfeifBxo1wxhlw112+0jNAr17w7ruwfr2fIinN9uzx8yl99ZUvH92rVzBfWfLmzfOlpSdM8C/uxht9HE2a+KkBTsYnn/hj3XwzDB+e/l+kbdtYVeFCysZupOjcacdOWxBmcXFQvLifdWro0LTtExMDU3+Kp9/+Ytx+3q28dtlrIY0xp9N0TSIiki3lzn30M+Pvv4c7mpwjNha+/dZ3JQ22UaOgXj3455/gH1tOzs8/+zztySdzUFIMsHatTxRvvhlKlYJ69bjqmzu4P+9gbikznnxL5/vJaQPKlYOrr/ZzFe/e7W/vv++XpSspXr/eJ6KTJ/u+25mVFIOfmHrcOFi6FG66CT78EFq0gLJl/fswbVr6502KjfXzL19/vX9dQ4Zk7BepdGnG3PINu+IKE39pS1iwIP3HCJENG/yUTPXqpX2f6Gh48IFc1C5Xg4X/Lkx9B4kYSoxFRCSiPP44lC8P7dsfTdRWrvRD17ZtC29s2dVDD8Fll0GNGjBlSvCOO3eunz927lwYMCB4x5XgmDcP8uSB2rXDHUkmO/NMWLECZs70g4NLl4aPP4Z77vHjZKOi/KTEPXv6SYmBu++GXbvg7bfhqad8cnzHHek459y5vivMX3/5b/7StXMQnX22fxFbtvhuOe3a+UG0TZtCtWp+PuX165PeNzbWvx+jR8ODD0L9+vDEE3DNNf4PdP78GQ6r+U1ncAlT2H8oj4/ll18yfKxgSpjP+ayz0r9vzbI1WfTvouAGJCGlrtQiIhJxFi3yjRmFCkHLlr5ADECFCjB1KlStGt74spMVK/zn4Q4d4M8/YetWX3An1WI7aXD77fDBB3DJJfDjj/6LjZP47CxB1rq1bzxdqEYt31q6dSusWQOrVsGkSfD5577l+Kqr4JFHuOzJhnz7rd+8WzffgpymBtKJE31XmFKlfFIcad9E7N3rk+P33vPdCHLlgrp1oXp13836v//8H4e//vIVu8BfyDVrwgMP+G7pJ8k5n3xGn7KWT3e2gr//5scen9J7ylXkywcjR/rvKzLbu+/64mSrVvmCW2m2axevzXqNe2c+yYftPyS6fDTVSlfDclTXjMyhrtQiIpKt1azpP0v++69Pim+/3T/fs8dXS5Xg+fJLfz9woC9gu2kTjBhx8sfdv983wl19Ndx6q//sPXPmsdv89ZfPP3bvPvnzSfrNnx+eZCMimfluxdHR/pd21Cj/rcGTT/rWy0aNGL+5Ef9X4VVGPLU2bUmxczBokG+VPecc+O23yEuKwU8B0LUr/PSTvygffxxKlvTPv/vOJ8XVqvkW9Q8+8N+k7N7tB9MGISkG/17ecw98/tvp3FR5Gn8ViaL56x24Zs9wtmyBjh3935DMtmqV71Xxv/+lcYe4OF+mvHx56k34A4Abxt7AOW+eQ60htZi4fGIqB5CwClYVr6RuQAlgDLAMWAqcDzwDLADmAd8B5QPb5gVGAQsD2z6S6Dj1A8v/AgYTaOlO6aaq1CIiWd+2bc4tWeJcfLx/fv/9vuLn+vXhjSs7adTIuYR/mfHxzl14oXNFijj3/PP+/c+o8eN9kdpvv3Vuxw7/c0s8v+d77zmXL5/fpmpV59auPbnXIemzZo1/7//v/8IdSRawe7cv31237tHS1Y0a+TdvzZqk99mzx5cvBufatfPPJVUDB/pi3YXY4xb9r5Vz4Fbe9oIDXxU6s119tXNVqqRjh3vv9T/za65x8b/95matm+WmrZnmhvwxxJ37xrmO/rjbJtzmDsYeDFnMOQ1BrEod6sR4FHBr4HG+QKJcLNH6u4GhgcfXAZ8EHhcCVgOVAs9/DyTVBnwNXJ7auZUYi4hkPwnTqrz8crgjyR42bPDv57PPHrusRg2/vGZNnxM455PmUaOca9DAudtvT/3Y3bo5V6KEcwcDn/8aN3auXDnn5s93rndvf/wWLZz78kvnChd27oorjn4BIsEXH++/pEj4eQ4a5H8Gy5eHN64sZ8UK51544dgkuUEDP13Rzz8799dfzo0c6b/tMXOub18/PZOk2bp1zv3xh3Nx+w86d+21zoH7pNoTrkTxeLdzZ+bGEh3tXMuWadx41iz/M+/ZM8nVB2MPur7f93X0x7X6oJXbdyiHzo8WZFkiMQaKAX+n1LoLPAIMCTy+FpgI5AFKA38CpYBywLJE+1wLvJ3a+ZUYi4hkT+ed5+eSlJP31lv+k8DixSeumzzZrxs0yLmdO5277rqjeQA498svyR93717nihd3rmvXo8vmzXPutNP850bwrf+HD/t1L73kly1cGNSXJ4kMHerf4zPP9C34zZr5L0DkJCQkyQ0a+HmCE18g1ao5N3VquCPM+mJjneve3TlwL/KQe+7ZzP32rHx5f/pUHTrkv0msWNGllr0PnzPcWX9zLT9o6Q4cPhCcQHOwYCbGoRxjfCawBRhhZnPN7F0zKwxgZs+Z2TrgeqBfYPsxwF5gI7AWGOCc+w+oACQuj7c+sOwEZtbDzGLMLGbLli0heVEiIhJeXbrAnDm+aJScnEmTfCGzc889cd3ll8MFF8CLL/o6PJ9+Cs884yvznnIKvPJK8sf9/HPYuRO6dz+6rE4dmDHDH/fDD32V6jx5/LqEYYo//BC81yZH7d/viy+DHzP50kt+dp6OHcMbV5ZXpQr07evHDm/b5qdDeu89P9fc0qXQvHm4I8z6cueGd96BO+7gYV6mzLP3sGdXfKacOj4eNm/2BcpTNWKErxr5+utQrFiKm3av2533rnqP71Z+R5cvuhAbHxucgOWkhTIxzgPUw7cI18UnvX0BnHOPOef+B4wGEiZxawDEAeWBysD9ZnYmvvv08ZIspe2cG+aci3bORZctWzaoL0ZERCLD1Vf7+08/DW8c2cGcOdC4cfJFhAYO9MVn4+J8/aHHH4eiRX2dnm++ge3bk97v88/9jDhNmx67vHJln4xff/2xy08/3ecYSoxD47vv/BcV333nv+x44QX/ob9Dh3BHlo2UKOGrV998M5x3nq/sLMGRKxe8+SYbr+lDjwOvs6nRVf4XOsT++8//7TvttFQ2PHDAf2vYuLH/HUiDblHdGHzZYMYtG8ctE24h3mVOsi8pC+VVux5Y75z7LfB8DD5RTuwjIOH7yuuAb5xzh51z/wK/AtGB41RMtE9F4J+QRS0iIhGtYkVo0sQXRz14MNzRZF2bN8PGjb4lNznnneeL1K5Y4T/zJbjmGjh82M/wcry4OJg+3U/RlJ6ZSS65xBfB1c80+MaO9Xlb8+a+BwBApUqRWSBZJElmlPv4VV4/+w3OWPoN8Q0bwfLlIT3lpk3+PtUW47ff9nM/P/tsuv7o9W7Ym6ebP83789+n69iuHIo7lPFgJShClhg75zYB68zs7MCiFsASM0s8+2RbfMVq8N2nLzavMNAIP7Z4I7DbzBqZn/yrKzA+VHGLiEjku+8+P4NI27awYUO4o8ma5s/396lN15M7t5/KNLH69f0Up2+95QdUJrZwoW/MOb61ODVt2/oZYKZMSd9+krKFC+Gjj3xPi7x54cIL/Rci06al74sLkbAz45zX7+JSvufQP1v9N3fjxoXsdJs3+/sUW4xjY/24kubN4aKL0n2Ox5s+zvMXP8/ohaO5fPTlbNu3LUOxSnCEup9Hb2C0mS0AooDngRfNbFFgWUvgnsC2bwJFgEXAH8AI59yCwLo7gHfx0zWtxFemFhGRHKpdO/8l/fTpcOWVvpXx0CFYvdq3WErq5s3z9ym1GCfHDO6+G+bOhV9/PXbdtGn+vkmT9B2zRQsoXhw+++zosrg4ePVV3zvg+ARcUrdkCbRs6VuLn3vu6PLTTvM9L0Symksuga01mnPlabNxZ58N7dvDo48e+cO/cmXw/lYktBinmBhPmOC/nb333gydw8x4pMkjvN/ufaavnU6j4Y1Y/O/iDB1LTl5IE2Pn3LzAmN/azrl2zrntzrmOzrmagWVtnHMbAtvucc51ds7VcM5Vd869kug4MYF9znLO9QpUIBMRkRysRw/4+GOf4FWpAmec4cewNmqU/NhXOWryZF90q1SpjO1/ww1QpIivOZPYH39AuXJ+3HB65Mvnjzl6tE+4d+6ENm3g/vv9mOa3385YnDnZq6/Cnj3w449Qpky4oxE5eWbw5JPww4rTGXHzNNytt8ELL/DnmZfx9N1bj9RDC4aEFuMUu1K/9Zb/Y9e69Umd68Y6NzL1pqnsOLCDum/X5cXpL2rccRioMoCIiGRZbdvCV19BgwY+IX7hBd9FOCoK1qwJd3SRa906X0zr2mszfozChX333M8+85WqE8TE+K7WGfHMM1C2rE+Er7sOvv/ef+6MioKRIzMea04UF+cbs1q3hpo1wx2NSPB07Oh7LvfsU4Co34dxC+9y+tppdHm9MaezhpdfDk4hv02bfPHB4sWT2WDZMn+i22/3Y05OUuP/NWbJnUtod047HvnhEVp92Ip/9/570seVtFNiLCIiWVrr1r4I1NixvqXg55994jdqVLgji1xDh/r7k0mMAe68E/btgz59fPfFHTv8LDUZTYxLloQ33vCznkye7FuG7rgDOnXyM+JoPHnazZgBW7b4nqYi2UmuXP7v/fXXQ6FC0PDtW9j15Q9UyLeFFadcQKuKi7n//pPvUr1kiR9ykOxY/OHD/Zxzt9xycidKpGzhsnza6VPeafMO09dOp97b9fh9w+9BO76kTImxiIhkK+ef72uyfK1qFEnasgUGD4bOnX0X9JNRv74f3jdihB/rnTAWr2HDjB+zQwffC+Cjj452iezc2X84ffbZk4s3Jxk71ndPv/zycEciEnwlSvi/OzNn+mE1p7S/gMIxv5Avdzzj/mtCgfmzmD0748f/5x8/JV3nzslsEBvrJ2Rv3TqNEx2nnZlxa71bmXnLTPLkykOTEU0YNntYUM8hSVNiLCIi2c7ll/sWxvXrwx1J5Ln/fl+s7KmngnO8p57yPQknT/ZzF3/xBbRqlfHjmfnPmtde6xtjAKpV863SQ4f67vKSMud8YtyiBRQrFu5oRDJJrVrw66/kPbUUP9CCmf2/zfChXn3VD0dItjH4hx98X+uuXTN8jtREnRbF7B6zuajSRdz+1e3cNO4m9hzaE7LziRJjERHJhm66ybeWPfxwuCOJLNu2+QrPd98N55wTnGPmyuUT1n//9eO7O3Twy4LthRd8t+DHH1dxtdT8/LOv0J5sa5dIdlW5Mrln/sq2klW5fVIbdvV/1U+6nsju3dC9u69RkVR361mz4LXX4LbbUuhVM2qUH/txkkW3UlO6UGkmXTeJfk378cH8D4geFs2ifxeF9Jw5mRJjERHJdipX9rNnfPQRrFoV7mgiR8LUSm3bBv/YZcueON9xMOXP73+m8fE+8ZPkDRoEpUtDly7hjkQkDE49lbgff+Z7a0mxp+7n8Dm1iJs4mZdfcrRp43s+jxgBEyf6iu2J7d3rv9w7/XR46aVkjr99u58/uUsX/4cpxHLnys1TFz3Fjzf9yI4DO4geFs3AmQNVtToElBiLiEi2dNddvuVy+PBwRxI5pk/3LekNGoQ7koxp2NAX2wlGxdns5o8/fBf5Vatg/Hjfvb1gwXBHJRIelaOKYxMnck2hifyzPo7cbVvToO9FFF4wk+7dfVX+U0/1XyIl9vPPsHGjr4ZfsmQyB3/nHdi/319kmah5pebM7zmfVlVacd9399F8ZHP++u+vTI0hu1NiLCIi2VLFin4e3MGD4c8/wx1NZPj5Z4iOhgIFwh1JxuTL56dpGT/e174R7/vv/ZcdVapAu3Z+5pg77wx3VCLhdUVr4/aJV1In92Lu4g3OK7qMT9Y25o2NHWlSYRXduvnaCAnzFQNMmeL/PjZvnsxBDx+G11+Hiy+GOnUy4VUc69QipzLumnGMvGokC/9dSO0htRkwYwCx8fqDGAxKjEVEJNt6/XWfTHXr5rvg5mQbNsDvv8Nll4U7kpNz661+Oq4JE8IdSeQYONDfly3rC5Y99hhUqBDemEQiwcUXw6w5+Wj+2V0U3rgSnn4avv0Wzj2XB7c8ROG4nXz00dHtf/gBLrwwhS8Pv/zSV3Xs0yczwk+SmXFT1E0sumMRl551KQ9+/yAN323IvE3zwhZTdqHEWEREsq3//c8nDTNnwiefhDua8Bo71t9n9YJMbdrAGWf4ngACu3b5aWUefRTmzPG3/v3DHZVI5DjnnMDfvcKF4YknfBei666j9Huv8Heeqhx+5TXYu5edO2HhQmjaNJkDxcXB88/7rhkhLrqVFhWKVWDcNeP4vPPnbNi1gehh0Tz43YPsPbQ33KFlWUqMRUQkW7vxRqhUiWNaBXKiKVOgatXgVaMOlzx5/Pjxn3/2VbBzugULfGXdxo3DHYlIFlG+vK++FRPD/so1eGjjvRwufzo7ut1DbTcv+WvpjTf8Bff886EpvZ8BZkan6p1YetdSbo66mQEzB3Dum+cydunYcIeWJUXGT1VERCREzPw0P99/76fpyKlWrIAaNcIdRXDceqsvwvX66+GOJPzmzfP3UVHhjEIkC6pfn8K/T+WqMr/y9aEWlBs/lHnUpfl9dX1VrrVrj2772Wd+EvjWraFTp/DFnIySBUvyTtt3mH7zdEoVLEWHzzrQ+qPW/LlNBTbSQ4mxiIhke1dfDYcO+e6m48bBxx/75zlFfDysXJnCnJxZTMmSvifA6NGwZYtftm0bPPVUzpuea948KFPGN4KJSPqUKAEv/NyYXmU/o5z7hwFnvE7u3ObHEJ9xhv+jWbUqXHONr3D30Uf+29YIdcHpF/DHbX8w4NIBTFszjRpv1aDPN33Ytm9buEPLEswlNbN1NhAdHe1iYmLCHYaIiESI++47WqQI4IILYNIkKF48fDFllnXr/LycQ4dm+gwjIbN0KdSq5ecc7dDBf+nx99/+g+5HH8Hll4c7wsxRv77/omDKlHBHIpJ1bd/ux+efdx4UKwYsW+b/Qfz2mx9bfPHFvqtKJsxbHCyb92zmialPMHzucIrmK0rfC/tyd8O7KZS3ULhDCyozm+2ciw7KsZQYi4hIThAXBy+95D/vNGsGPXtCo0YwYICfHzc7+/FHaNHCV1y9+OJwRxM8jz4KL7zgH5cv7wtyPfOMr62zeTMULRre+EJt1y4oVQoeecS/bhGR4y36dxGP/PAIX/35FeWKlOOxJo9xW/3byJc7X7hDC4pgJsbqSi0iIjlC7tw+kXr/fbjlFnjtNZg+3SfJ//0X7uhCa8UKf59dulIneO45WLzYt/QsWwYdO/qhgfv3+xlZsrtp0/wXPsnOuSoiOV7NU2oy8dqJTL95OlVKVaHX172o9no13o55m4OxB8MdXkRRYiwiIjnSXXf5glwHD/qxqtnZhx/6rtQVK4Y7kuAyg+rVoW7do63DF17ox9x++WV4Y8sMP/7o5+lWRWoRSc0Fp1/Az91+5pvrv6Fc0XL0nNSTs984m7dj3uZA7IFwhxcRlBiLiEiOdcklfozmu+/6KW+yo99+8y3j998fMTOMhFTu3L7Y2pdfwr//hjua0Dl40H/hcemlULBguKMRkazAzGhVpRUzus/g2xu+5dQip9JzUk8qD6rMi9NfZMeBHeEOMaxywL9IERGR5N16q5+acvbsY5fv2AHXXQf33AN794YltKAYPtxPbXTzzeGOJPP07u0Tx2HDwh1JaDgHL77oE/977gl3NCKS1ZgZLc9qyaxbZjHlxinUPrU2j/zwCBVfrchdk+5i+dbl4Q4xLFR8S0REcrSdO6FcOejWDd566+jyJ56AZ5/1jzt1gk8/zXotrgcOwKmnwlVX+bHVOUnz5rB1KyxadOzytWv9z/ngQV987ZprwhLeSfn5Z//6OnXy06tG8OwxIpJFzNs0j0G/DeKjhR9xKO4QLc9qSZ+Gfbi8amSX+FfxLRERkSApXhxat/Zdb+Pi/LING3wRp06d4OWXYcwY6N8/rGFmyOzZvnJxx47hjiTzderkC3MtW3Z02datvtja//0fvPMOdOniC7EdjLD6M+PG+SlTkysKl/C9/9ChSopFJDiiTotixFUjWNtnLU83f5pF/y7io0UfhTusTKXEWEREcryOHf30PjNm+Od9+kBsrJ8K6IEHfDfkZ56BkSPDGWX6zZrl7xs1Cm8c4dC+vU8aExdW69/fz+k8Y4bvKfD44/Dee/D662EL8wTOQY8e8Mcf0Ldv0tssWeJ7ApQunbmxiUj2d2qRU3mi2ROsvmc1r7V6LdzhZCp1pRYRkRxv925fsfnSS/1cx1Wr+qmdErpSx8b6rqt//w0rV0KBAmENN806d/ati3//He5IwqNNG/j9d1izxnehrlHDjykfMuToNued57vI//Zb+OJMsGYN1KvnW4oLF/Zd4VevPrGa+Pnn+9/BqVPDEqaISMRQV2oREZEgKlrUFzH64gu4/nrIk8dP55QgTx546in45x/4KAv1LPvtN2jYMNxRhE+fPr5A1QUX+C8JChQ4sUt8x44+eT7+u3TnYMsW373+8OHQx+oc9Orli7499RTMneuXJR73nrDdkiV+mioREQkeJcYiIiL4LtONG/sk6dVXfUGuxC6+GM4+20+Rk5hzPmGONDt2+G7DdeuGO5LwadHCF03bv9/fhg/3XZATu/FGKF8eLroIVq06uvzRR+GUU6BKFT8OfejQ4MT0338weDB8882xy8eNg6++8mPa+/XzvRYuv9x3BU/cue/jj/248Zo1gxOPiIh4SoxFRESAYsV8td/Vq33L3fHM4Npr4aef4LvvfDfX2Fi4/XaoUAEeeiiy5kJeutTfn3tueOMIt6uv9i2sf/7pHx+vQgU/5jhXLt9bYNs237X+rbfgjDN8a/H+/XDffb4o28lwzv8O3XOPT3qffPLo8sce88lu4umXOnXyXcATWrOd81NRNWwIN9xwcrGIiMixlBiLiIgE5MkDp5+e/Ppbb/XrW7WCWrUgOtpXNwZ45RU/PjlSJCTG6nKbujPOgHffhTlzoH59n5Du2uWnQlq7FpYv98nxp59m/BxxcXDbbf5LlZde8i3VzzwD06bBxIn+5/Xgg/53MEHbtv75xx/75ytW+Bbn227z3f9FRCR4lBiLiIikUYUKsGCBn+5n1SrfEvnppxAfD1de6bvBHjoU7ii9pUshf36oXDnckWQNnTvD9Ol+HPKsWTBwoJ8yKVcuqFYN6tTxY9CPt2ULbNyY+vGHDvVduR9+2Hfbf+MNqFTJd9Hv2BHOOuvEOZVLlYIOHWDECNi372iV8Zw8blxEJFRUlVpERCQDPvvMt9pdfrl/PmmST44nTvT34daqFWzaBPPnhzuS7OHZZ+GJJ3xV8jPP9MtmzvQ/68OHYdQoP0VUUg4fhtNO8xWnv/vu6NzDW7ce7WXw8MNQpsyJ+06fDk2a+Cm39u3zFca3b4fcuYP/GkVEshpVpRYREQmzq68+mhQDtGzpE5u33055v19/9d1zQ+nwYX+eCy8M7Xlykptv9slo4irRDz3kp1U65xzfsvvmmzBv3on7Tp3qu0D37n00KQb/+/LKK/6WVFIM/mc4fLhPordvh+7dlRSLiISCEmMREZEgyJvXF+366itYtCjpbd591yc6Z5zhu2V//31oYpk9G/bu9ZWWJTgqVPDdrQcO9F3mv//et+bec48fJ9ykif/516174rzRY8ZAkSL+y5OM6N7djy9euxZee+2kX4qIiCRBibGIiEiQ3HWXL5b0wQcnrjt4EPr2hfPOg4oV/RRP7dv7KZWCbepUf9+0afCPnZMNG+bHAz/8sE9yzzzTtyTnz+9bdROmUEo8FnnfPt/t/qqr/PhlERGJTEqMRUREgqRMGd9KO27cietGj/ZTAT37rE+G//7bd3l+/PGj27z3ni/IVKIEvPBCxuOYNMm3XJ5ySsaPIScqWtQXWxszxnepjonxBbLAzzu8cKGvav3xx0en7hozBnbu9JWkRUQkcikxFhERCaJ27fycuUuWHF32ww8+MapXDy65xC+rVMnPjfv++/D11z6ZvuUW32W3dm149FH45pv0n3/rVl8Uqk2bILwYOYGZbzW+4w4oWfLE9T17+mmfRo70zz/5xP+s1XovIhLZlBiLiIgEUceOvjv1iBFHl737rm9Z/PlnP/1PgiefhBo1/Ly5N9/sE+cff4QpU3wylZFW48mT/fRRSozDo3t3P974/vv9/MdTpvjficRFt0REJPIoMRYREQmiU0/1SenIkXDgAOzf76dwat/eF2BKrEABnzi1bAkXXOBbF/Pnh3z54O674ZdffPfc9PjqKyhXzifZkvly5YJ33vFji6OjfXf5q68Od1QiIpIaJcYiIiJBdvfdvkvzO+/47tB79/qKxkk57TQYO9YntFWrHl1+/fW+lXHs2LSf99Ahf77WrY9tmZbMdfbZ/ud55pkwZAg0aBDuiEREJDXmEqpDZDPR0dEuJiYm3GGIiEgO1bw5LF3qu0ovWACbNvku1ulxwQW+1Xn27LRtP2UKXHopjB8PbdumO2QREZEsxcxmO+eig3EsfZ8sIiISAoMG+VbjqVN9N+r0JsXgp/iZMyftUzpNnOi7ZycU+BIREZG0UWIsIiISAnXq+G7QAwbAc89l7BgJrb4TJ6a8nXN+7tw334QWLaBQoYydT0REJKdSYiwiIhIibdv66sQZnU/4nHOgWjXfNTopCaOhnnrKV7Y+7TR48MGMnUtERCQnU2IsIiISwTp29PMgr19/7PJVq+CMM+C11+DVV6FDB1izBpo1C0uYIiIiWZoSYxERkQh2660QF+crXCd47z0/HdO6dXDvvbB7NzzyCOTOHb44RUREsrIMlAIRERGRzHLmmb5L9ksv+QrXTZtCr15+fuSnn4Zt2+C88/ycuSIiIpIxSoxFREQi3IABfn7ia66BwoV9UrxwIdSsGe7IREREsgclxiIiIhGualWYN8/fJk6ENm2UFIuIiASTEmMREZEs4Nxz/e3aa8MdiYiISPaj4lsiIiIiIiKSoykxFhERERERkRxNibGIiIiIiIjkaEqMRUREREREJEdTYiwiIiIiIiI5mhJjERERERERydGUGIuIiIiIiEiOFtLE2MxKmNkYM1tmZkvN7Hwze8bMFpjZPDP7zszKB7a9PrAs4RZvZlGBdfXNbKGZ/WVmg83MQhm3iIiIiIiI5ByhbjEeBHzjnDsHqAMsBV5xztV2zkUBXwH9AJxzo51zUYHlNwKrnXPzAscZAvQAqgZul4U4bhEREREREckhQpYYm1kxoCkwHMA5d8g5t8M5tyvRZoUBl8Tu1wIfB45TDijmnJvpnHPA+0C7UMUtIiIiIiIiOUueEB77TGALMMLM6gCzgXucc3vN7DmgK7ATuCiJfa8Brgo8rgCsT7RufWCZiIiIiIiIyEkLZVfqPEA9YIhzri6wF+gL4Jx7zDn3P2A00CvxTmbWENjnnFuUsCiJYyfVyoyZ9TCzGDOL2bJlS5BehoiIiIiIiGRnoUyM1wPrnXO/BZ6PwSfKiX0EdDxuWRcC3agTHadioucVgX+SOqFzbphzLto5F122bNkMBy4iIiIiIiI5R8i6UjvnNpnZOjM72zm3HGgBLDGzqs65FYHN2gLLEvYxs1xAZ/zY5ITjbDSz3WbWCPgN3wX79dTOP3v27K1mtiaILyk1ZYCtmXi+9Ijk2CCy41NsGRPJsUFkx6fYMiaSY4PIjk+xZVwkx6fYMiaSY4PIjk+xZVwkxxfJsRUgiLGFcowxQG9gtJnlA1YBNwPvmtnZQDywBuiZaPum+FbmVccd5w5gJFAQ+DpwS5FzLlObjM0sxjkXnZnnTKtIjg0iOz7FljGRHBtEdnyKLWMiOTaI7PgUW8ZFcnyKLWMiOTaI7PgUW8ZFcnxZILagzVYU0sQ4MN3S8W/k8V2nE2//E9AoieUxQM1gxiYiIiIiIiICoZ/HWERERERERCSiKTEOnmHhDiAFkRwbRHZ8ii1jIjk2iOz4FFvGRHJsENnxKbaMi+T4FFvGRHJsENnxKbaMi+T4ckxs5lySMx+JiIiIiIiI5AhqMRYREREREZEcTYlxMszsPTP718wWJVpWx8xmmtlCM5toZsWO2+d0M9tjZg8kWlY/sP1fZjbYzCyS4ku0bkLiY0VCbGZ2bWD7BWb2jZmVyczYzKySme03s3mB29DA8kJmNsnMlpnZYjN78WTjClZsgXX5zGyYmf0ZiDHZgnehii+wrnZg3eLA+gKB5UG/JoIVW6L1YbseUnjfgn49pDc+M7s+0e/cPDOLN7OoCLkmkowtsC7o10Q6Y8trZqMCy5ea2SOJ9gnr9ZBSbIn2Ddr1EMz4QnFNpDO2fGY2IrB8vpk1DyyPhOshydgSrQv29fA/M5sa+BktNrN7AstLmdn3ZrYicF8y0T6PBH7vl5tZq0TLg3pNBDO2ROuD+T8imO9dUK+J9MZmZqUD2+8xszcSHSfo10SwYgusC/s1YWaXmtnswM9vtpldnOhYYb0mUoot0TGDck0E+X1L//XgnNMtiRt+6qh6wKJEy/4AmgUedweeOW6fL4DPgQcSLfsdOB8w/DRTl0dSfIHlHYCPEh8r3LHhK6b/C5QJPH8Z6J+ZsQGVknpPgELARYHH+YBpwfi5BiO2wLqngGcDj3MlvIeZHF8eYAFQJ/C8NJDbheiaCFZsLszXQ3Kxhep6SG98x+1XC1jlIuSaSC42F6JrIp0/1+uATxK9V6uBShFyPSQbWyiuh2DFF6prIp2x3QWMCDw+BZgd+P0K+/WQXGwhvB7KAfUCj4sCfwLVAz+XvoHlfYGXAo+rA/OB/EBlYCUh+h8RzNhCcU0EK75QXBMZiK0wcCF+KtY3Eh0n6NdEsGKLoGuiLlA+8LgmsCHRscJ9TSQbW7CviWDFltHr4aQv6Ox847jkA9jF0XHZ/wOWJFrXDngF6M/R5K4csCzRNtcCb0dKfIHlRYDpgV+6YH7wOdn3Li+wBTgj8IdgKNAjM2M7frsUjjcIuC1SYgPWAYWD9bPMYHxXAB8msX/IromTjS2wLqzXQwrvW8iuh/TEd9w+zwPPJXO8TL8mUootVNdEOn6u1wIT8f+oS+P/0ZeKkOshydgC60JyPQTpvYuE/xFvAjck2u4HoEEkXA8pxRaq6+G4OMcDlwLLgXKBZeWA5YHHjwCPJNr+W/wH/5B+bjqZ2EJ9TQThvQvp/4m0xJZou24cl3wetz5o10QwYouEa+K4bQ3Yhv/yI+zXRHKxBZ6H9Jo4ifctQ9eDulKnzyKgbeBxZ/w/IcysMPAw/hunxCoA6xM9Xx9YFinxATwD/B+wL4RxpTs259xh4A5gIfAP/oIbnpmxBVQ2s7lm9rOZNTl+RzMrAbTBf+gIe2yBeACeMbM5Zva5mZ0aothSiq8a4Mzs20AcDwWWZ+Y1kd7YIMzXQ3KxZfL1kFJ8iV0DfHz8wjBfEyfElsnXRHKxjQH2AhuBtcAA59x/RMb1kFxskHnXQ7rji5D/EfOBq8wsj5lVBupz3O9jGK+HJGPLjOvBzCrhW3F+A051zm0ECNyfEtisAj4ZSZDwux/Sa+IkY4MQXxMnE1+or4k0xpaW45QgyNfEycQWQddEYh2Buc65g0TGNZFcbBDCa+JkYsvo9aDEOH26A3eZ2Wx88/6hwPKngIHOuT3HbZ/UGAAXKfGZH39XxTk3NoQxZTS2vPhf6LpAeXz30hPGvoU4to3A6c65usB9wEd27FjQPPgP34Odc6siJLY8QEXgV+dcPWAmMCBEsaUUXx58l6XrA/ftzawFmXtNpCu2CLkekostM6+HlOIDwMwaAvucc4uOWx7OayK52DLzmkgutgZAHP5nVxm438zOJDKuhyRjy+TrISPxRcL/iPfwH1JjgNeAGUBswk5hvh6Siy2k14OZFcEPjerjnNuV0qZJLHMpLA97bKG+JoIQX8iuiXTEltpxgn5NBCG2SLkmEravAbwE3J6wKInNMvuaSDK2UF4TQYgtQ9dDnpOIOcdxzi0DWgKYWTWgdWBVQ6CTmb0MlADizewA/gdaMdEhKuK/tYiU+OKA+ma2Gv+7cIqZ/eScax4Bsf0W2G9lYJ/P8GMKgi652ALfhh0MPJ5tZivxLXoxgV2HASucc6+FIq4MxjYb/61dwh+pz4FbMjs+/Aeyn51zWwPrJuPHxn1IJl0TGYhtD+G/HpKLbVdgv5BfD6nEl6ALSbQWE8ZrIoXYtpFJ10QKsV0HfBP4BvtfM/sViMaPswv39ZBcbKXJpOvhJOIL9/+IWODehO3MbAawItGu4fwfkVxsIbseAh9EvwBGO+e+DCzebGblnHMbzawcfswf+L91iVvXE3731xOCayJIsZ1PiK6JIMUXBcG/JtIZW2qCek0EKbZIuSYws4qBOLom/ByJjGsiudhCck0EKbYoSP/1oBbjdDCzUwL3uYDH8f3Vcc41cc5Vcs5Vwn8z+7xz7o1AU/9uM2tkZgZ0xfeVj5T4hjjnygeWXwj8GaoPPemNDdgAVDezsoFDXAoszczYzKysmeUOPD4TqAqsCjx/FigO9AlFTBmNzTnn8OPxmgcO0QJYktnx4cc81TZfiTIP0Aw/9i3TrokMxBb26yG52MjE6yGV+BKWdQY+OW6fsF4TycWWmddECrGtBS42rzDQCD9mLBKuh+Riy7TrISPxERn/IwoFYsLMLgVinXNLAs/D/T8iydhCdT0Efn+HA0udc68mWjUBuCnw+CaO/n5PALqYWX7zXb2rAr+H4poIYmwhuSaCFR8huCYyEFtKxwrqNRGs2CLlmjDfpXsSfvz4r4niC/s1kUJsQb8mghUbGb0eXAgHmmflG77FYSNwGP9tzS3APfjCH38CL4IveHHcfv05trhVNH4M0ErgjaT2CWd8iZZXIngVFoP13vUM/BIvwP/RKp2ZseHHKizGj9WaA7QJLK+I78ayFJgXuN0aCbEF1p0B/BJ4337Ad7nO9J8rcEMgxkXAy6G8JoIVWyRcDym8b0G/HjIYX3Ng1nHHCPs1kVxsobom0hMbvjjJ54Gf6xLgwUi5HlKKLRTXQ5Dfu3D/j6iELwizFJgCnBEp10NysYXwergw8JoXJHrNV+Bb9n/At1b/QKCwW2CfxwK/98tJVGU32NdEMGMLxTUR5PcuqNdEBmNbDfyH74W1Hj+2M+jXRLBii5RrAv/F1t5E284DTomEayKl2IJ9TQT5fUv39ZDwB1REREREREQkR1JXahEREREREcnRlBiLiIiIiIhIjqbEWERERERERHI0JcYiIiIiIiKSoykxFhERERERkRxNibGIiEiEMrM4M5tnZovNbL6Z3ReYszalfSqZ2XWZFaOIiEh2oMRYREQkcu13zkU552oAl+Lnc3wylX0qAUqMRURE0kHzGIuIiEQoM9vjnCuS6PmZwB9AGeAM4AOgcGB1L+fcDDObBZwL/A2MAgYDLwLNgfzAm865tzPtRYiIiGQBSoxFREQi1PGJcWDZduAcYDcQ75w7YGZVgY+dc9Fm1hx4wDl3ZWD7HsApzrlnzSw/8CvQ2Tn3d2a+FhERkUiWJ9wBiIiISLpY4D4v8IaZRQFxQLVktm8J1DazToHnxYGq+BZlERERQYmxiIhIlhHoSh0H/Isfa7wZqIOvGXIgud2A3s65bzMlSBERkSxIxbdERESyADMrCwwF3nB+HFRxYKNzLh64Ecgd2HQ3UDTRrt8Cd5hZ3sBxqplZYUREROQItRiLiIhEroJmNg/fbToWX2zr1cC6t4AvzKwzMBXYG1i+AIg1s/nASGAQvlL1HDMzYAvQLnPCFxERyRpUfEtERET+v107IAEAAAAQ9P91Q9IXQQCwZqUGAABgTRgDAACwJowBAABYE8YAAACsCWMAAADWhDEAAABrwhgAAIA1YQwAAMBa1s+GhhRYUmkAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<Figure size 1152x432 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Adjusted code for forecasting plot\n",
    "plt.figure(figsize=(16, 6))\n",
    "\n",
    "# Entire Historical Data Plot\n",
    "historical_dates = df.index.to_pydatetime()\n",
    "historical_data = df['Water levels'].values  # The entire 'Water levels' data\n",
    "plt.plot(historical_dates, historical_data, color='blue', label='Historical Data')\n",
    "\n",
    "# Validation Data Plot\n",
    "validation_dates = df.index[training_set:].to_pydatetime()\n",
    "validation_data = valid_predictions_padded[training_set:]  # Assuming this is a NumPy array\n",
    "plt.plot(validation_dates, validation_data, color='red', label='Validation Data')\n",
    "\n",
    "# Forecasting Data Plot\n",
    "plt.plot(forecast_dates_np, forecast, color='green', label='Forecasting Data')\n",
    "\n",
    "# Plot Configurations\n",
    "plt.gca().xaxis.set_major_locator(mdates.YearLocator(4))\n",
    "plt.gca().xaxis.set_major_formatter(mdates.DateFormatter('%Y'))\n",
    "plt.title('Water Levels (Feet) (1941-2023)')\n",
    "plt.xlabel('Date')\n",
    "plt.ylabel('Water Levels (Feet)')\n",
    "plt.legend()\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "03c529dd",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.9.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}