mai_pi-33_zakharov/notebooks/lab1.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Работа с NumPy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 270,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "matrix = \n",
      " [[4 5 0]\n",
      " [9 9 9]] \n",
      "\n",
      "tmatrix = \n",
      " [[4 9]\n",
      " [5 9]\n",
      " [0 9]] \n",
      "\n",
      "vector = \n",
      " [4 5 0 9 9 9] \n",
      "\n",
      "tvector = \n",
      " [[4]\n",
      " [5]\n",
      " [0]\n",
      " [9]\n",
      " [9]\n",
      " [9]] \n",
      "\n",
      "list_matrix = \n",
      " [array([4, 5, 0]), array([9, 9, 9])] \n",
      "\n",
      "matrix as str = \n",
      " [[4 5 0]\n",
      " [9 9 9]] \n",
      "\n",
      "matrix type is <class 'numpy.ndarray'> \n",
      "\n",
      "vector type is <class 'numpy.ndarray'> \n",
      "\n",
      "list_matrix type is <class 'list'> \n",
      "\n",
      "str_matrix type is <class 'str'> \n",
      "\n",
      "formatted_vector = \n",
      " 4; 5; 0; 9; 9; 9 \n",
      "\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "\n",
    "matrix = np.array([[4, 5, 0], [9, 9, 9]])\n",
    "print(\"matrix = \\n\", matrix, \"\\n\")\n",
    "\n",
    "tmatrix = matrix.T\n",
    "print(\"tmatrix = \\n\", tmatrix, \"\\n\")\n",
    "\n",
    "vector = np.ravel(matrix)\n",
    "print(\"vector = \\n\", vector, \"\\n\")\n",
    "\n",
    "tvector = np.reshape(vector, (6, 1))\n",
    "print(\"tvector = \\n\", tvector, \"\\n\")\n",
    "\n",
    "list_matrix = list(matrix)\n",
    "print(\"list_matrix = \\n\", list_matrix, \"\\n\")\n",
    "\n",
    "str_matrix = str(matrix)\n",
    "print(\"matrix as str = \\n\", str_matrix, \"\\n\")\n",
    "\n",
    "print(\"matrix type is\", type(matrix), \"\\n\")\n",
    "\n",
    "print(\"vector type is\", type(vector), \"\\n\")\n",
    "\n",
    "print(\"list_matrix type is\", type(list_matrix), \"\\n\")\n",
    "\n",
    "print(\"str_matrix type is\", type(str_matrix), \"\\n\")\n",
    "\n",
    "formatted_vector = \"; \".join(map(str, vector))\n",
    "print(\"formatted_vector = \\n\", formatted_vector, \"\\n\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Работа с Pandas DataFrame\n",
    "\n",
    "https://pandas.pydata.org/docs/user_guide/10min.html"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Работа с данными - чтение и запись CSV"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 271,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "\n",
    "df = pd.read_csv(\"../data/ds_salaries.csv\")\n",
    "\n",
    "df.to_csv(\"../data/test.csv\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Работа с данными - основные команды"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 272,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 3755 entries, 0 to 3754\n",
      "Data columns (total 11 columns):\n",
      " #   Column              Non-Null Count  Dtype \n",
      "---  ------              --------------  ----- \n",
      " 0   work_year           3755 non-null   int64 \n",
      " 1   experience_level    3755 non-null   object\n",
      " 2   employment_type     3755 non-null   object\n",
      " 3   job_title           3755 non-null   object\n",
      " 4   salary              3755 non-null   int64 \n",
      " 5   salary_currency     3755 non-null   object\n",
      " 6   salary_in_usd       3755 non-null   int64 \n",
      " 7   employee_residence  3755 non-null   object\n",
      " 8   remote_ratio        3755 non-null   int64 \n",
      " 9   company_location    3755 non-null   object\n",
      " 10  company_size        3755 non-null   object\n",
      "dtypes: int64(4), object(7)\n",
      "memory usage: 322.8+ KB\n",
      "                count           mean            std     min       25%  \\\n",
      "work_year      3755.0    2022.373635       0.691448  2020.0    2022.0   \n",
      "salary         3755.0  190695.571771  671676.500508  6000.0  100000.0   \n",
      "salary_in_usd  3755.0  137570.389880   63055.625278  5132.0   95000.0   \n",
      "remote_ratio   3755.0      46.271638      48.589050     0.0       0.0   \n",
      "\n",
      "                    50%       75%         max  \n",
      "work_year        2022.0    2023.0      2023.0  \n",
      "salary         138000.0  180000.0  30400000.0  \n",
      "salary_in_usd  135000.0  175000.0    450000.0  \n",
      "remote_ratio        0.0     100.0       100.0  \n"
     ]
    }
   ],
   "source": [
    "df.info()\n",
    "print(df.describe().transpose())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 273,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "  employment_type                 job_title  salary salary_currency  \\\n",
      "0              FT  Principal Data Scientist   80000             EUR   \n",
      "\n",
      "   salary_in_usd employee_residence  remote_ratio company_location  \\\n",
      "0          85847                 ES           100               ES   \n",
      "\n",
      "  company_size  \n",
      "0            L  \n",
      "     employment_type              job_title   salary salary_currency  \\\n",
      "3753              CT  Business Data Analyst   100000             USD   \n",
      "3754              FT   Data Science Manager  7000000             INR   \n",
      "\n",
      "      salary_in_usd employee_residence  remote_ratio company_location  \\\n",
      "3753         100000                 US           100               US   \n",
      "3754          94665                 IN            50               IN   \n",
      "\n",
      "     company_size  \n",
      "3753            L  \n",
      "3754            L  \n"
     ]
    }
   ],
   "source": [
    "cleared_df = df.drop([\"work_year\", \"experience_level\"], axis=1)\n",
    "print(cleared_df.head(1))\n",
    "print(cleared_df.tail(2))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 274,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "     employment_type                      job_title  salary salary_currency  \\\n",
      "1548              FT                   AI Developer    6000             EUR   \n",
      "573               FT  Autonomous Vehicle Technician    7000             USD   \n",
      "2933              CT             Analytics Engineer    7500             USD   \n",
      "\n",
      "      salary_in_usd employee_residence  remote_ratio company_location  \\\n",
      "1548           6304                 MK             0               MK   \n",
      "573            7000                 GH             0               GH   \n",
      "2933           7500                 BO            50               BO   \n",
      "\n",
      "     company_size  \n",
      "1548            S  \n",
      "573             S  \n",
      "2933            M  \n",
      "     employment_type       job_title    salary salary_currency  salary_in_usd  \\\n",
      "3669              FT  Data Scientist  30400000             CLP          40038   \n",
      "\n",
      "     employee_residence  remote_ratio company_location company_size  \n",
      "3669                 CL           100               CL            L  \n"
     ]
    }
   ],
   "source": [
    "\n",
    "sorted_df = cleared_df.sort_values(by=\"salary\")\n",
    "print(sorted_df.head(3))\n",
    "print(sorted_df.tail(1))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Работа с данными - работа с элементами"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 275,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0         80000\n",
      "1         30000\n",
      "2         25500\n",
      "3        175000\n",
      "4        120000\n",
      "         ...   \n",
      "3750     412000\n",
      "3751     151000\n",
      "3752     105000\n",
      "3753     100000\n",
      "3754    7000000\n",
      "Name: salary, Length: 3755, dtype: int64\n"
     ]
    }
   ],
   "source": [
    "print(df[\"salary\"])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 276,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "   work_year experience_level employment_type                 job_title  \\\n",
      "0       2023               SE              FT  Principal Data Scientist   \n",
      "1       2023               MI              CT               ML Engineer   \n",
      "2       2023               MI              CT               ML Engineer   \n",
      "\n",
      "   salary salary_currency  salary_in_usd employee_residence  remote_ratio  \\\n",
      "0   80000             EUR          85847                 ES           100   \n",
      "1   30000             USD          30000                 US           100   \n",
      "2   25500             USD          25500                 US           100   \n",
      "\n",
      "  company_location company_size  \n",
      "0               ES            L  \n",
      "1               US            S  \n",
      "2               US            S  \n"
     ]
    }
   ],
   "source": [
    "print(df[0:3])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 277,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "work_year                                 2023\n",
      "experience_level                            SE\n",
      "employment_type                             FT\n",
      "job_title             Principal Data Scientist\n",
      "salary                                   80000\n",
      "salary_currency                            EUR\n",
      "salary_in_usd                            85847\n",
      "employee_residence                          ES\n",
      "remote_ratio                               100\n",
      "company_location                            ES\n",
      "company_size                                 L\n",
      "Name: 0, dtype: object\n"
     ]
    }
   ],
   "source": [
    "print(df.loc[0])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 278,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "FT\n"
     ]
    }
   ],
   "source": [
    "print(df.loc[100, \"employment_type\"])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 279,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "     salary employment_type\n",
      "100  104300              FT\n",
      "101  145000              FT\n",
      "102   65000              FT\n",
      "103  165000              FT\n",
      "104  132300              FT\n",
      "..      ...             ...\n",
      "196  230000              FT\n",
      "197  200000              FT\n",
      "198  180000              FT\n",
      "199  115000              FT\n",
      "200  200000              FT\n",
      "\n",
      "[101 rows x 2 columns]\n"
     ]
    }
   ],
   "source": [
    "print(df.loc[100:200, [\"salary\", \"employment_type\"]])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 280,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "work_year                                 2023\n",
      "experience_level                            SE\n",
      "employment_type                             FT\n",
      "job_title             Principal Data Scientist\n",
      "salary                                   80000\n",
      "salary_currency                            EUR\n",
      "salary_in_usd                            85847\n",
      "employee_residence                          ES\n",
      "remote_ratio                               100\n",
      "company_location                            ES\n",
      "company_size                                 L\n",
      "Name: 0, dtype: object\n"
     ]
    }
   ],
   "source": [
    "print(df.iloc[0])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 281,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "   work_year experience_level\n",
      "3       2023               SE\n",
      "4       2023               SE\n"
     ]
    }
   ],
   "source": [
    "print(df.iloc[3:5, 0:2])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 282,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "   work_year experience_level\n",
      "3       2023               SE\n",
      "4       2023               SE\n"
     ]
    }
   ],
   "source": [
    "print(df.iloc[[3, 4], [0, 1]])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Работа с данными - отбор и группировка"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 283,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[2023 2022 2020 2021]\n"
     ]
    }
   ],
   "source": [
    "s_values = df[\"work_year\"].unique()\n",
    "print(s_values)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 284,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2023 count = 1785\n",
      "2022 count = 1664\n",
      "2020 count = 76\n",
      "2021 count = 230\n",
      "Total count =  3755\n"
     ]
    }
   ],
   "source": [
    "s_total = 0\n",
    "for s_value in s_values:\n",
    "    count = df[df[\"work_year\"] == s_value].shape[0]\n",
    "    s_total += count\n",
    "    print(s_value, \"count =\", count)\n",
    "print(\"Total count = \", s_total)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 285,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                         job_title experience_level  total_count\n",
      "1    3D Computer Vision Researcher               MI            1\n",
      "2    3D Computer Vision Researcher               SE            1\n",
      "11              Analytics Engineer               EN            1\n",
      "8                     AI Scientist               EX            1\n",
      "24   Autonomous Vehicle Technician               EN            1\n",
      "..                             ...              ...          ...\n",
      "77                   Data Engineer               MI          205\n",
      "150      Machine Learning Engineer               SE          209\n",
      "59                    Data Analyst               SE          380\n",
      "108                 Data Scientist               SE          608\n",
      "78                   Data Engineer               SE          718\n",
      "\n",
      "[192 rows x 3 columns]\n"
     ]
    }
   ],
   "source": [
    "print(df.groupby([\"job_title\", \"experience_level\"]).size().reset_index(name=\"total_count\").sort_values(by=\"total_count\"))  # type: ignore"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Визуализация - Исходные данные"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 286,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "      work_year   salary employee_residence\n",
      "0          2023    80000                 ES\n",
      "1          2023    30000                 US\n",
      "2          2023    25500                 US\n",
      "3          2023   175000                 CA\n",
      "4          2023   120000                 CA\n",
      "...         ...      ...                ...\n",
      "3750       2020   412000                 US\n",
      "3751       2021   151000                 US\n",
      "3752       2020   105000                 US\n",
      "3753       2020   100000                 US\n",
      "3754       2021  7000000                 IN\n",
      "\n",
      "[3755 rows x 3 columns]\n"
     ]
    }
   ],
   "source": [
    "data = df[[\"work_year\", \"salary\", \"employee_residence\"]].copy()\n",
    "data.dropna(subset=[\"employee_residence\"], inplace=True)\n",
    "print(data)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Визуализация - Сводка пяти чисел\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 287,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "           salary                                                   \n",
      "              min        q1        q2    median        q3        max\n",
      "work_year                                                           \n",
      "2020.0     8000.0   48000.0   88000.0   88000.0  138000.0  1000000.0\n",
      "2021.0     8760.0   59000.0  100000.0  100000.0  165000.0  2500000.0\n",
      "2022.0     6000.0   95000.0  135000.0  135000.0  175000.0  2800000.0\n",
      "2023.0     7000.0  107800.0  145000.0  145000.0  185000.0  1700000.0\n",
      "           salary                    \n",
      "          low_iqr       iqr  high_iqr\n",
      "work_year                            \n",
      "2020.0          0   90000.0  273000.0\n",
      "2021.0          0  106000.0  324000.0\n",
      "2022.0          0   80000.0  295000.0\n",
      "2023.0          0   77200.0  300800.0\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<Axes: title={'center': 'salary'}, xlabel='work_year'>"
      ]
     },
     "execution_count": 287,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "def q1(x):\n",
    "    return x.quantile(0.250)\n",
    "\n",
    "\n",
    "# median = quantile(0.5)\n",
    "def q2(x):\n",
    "    return x.quantile(0.5)\n",
    "\n",
    "\n",
    "def q3(x):\n",
    "    return x.quantile(0.750)\n",
    "\n",
    "\n",
    "def iqr(x):\n",
    "    return q3(x) - q1(x)\n",
    "\n",
    "\n",
    "def low_iqr(x):\n",
    "    return max(0, q1(x) - 1.5 * iqr(x))\n",
    "\n",
    "\n",
    "def high_iqr(x):\n",
    "    return q3(x) + 1.5 * iqr(x)\n",
    "\n",
    "data = data.where(data[\"salary\"] < 3000000)\n",
    "quantiles = (\n",
    "    data[[\"work_year\", \"salary\"]]\n",
    "    .groupby([\"work_year\"])\n",
    "    .aggregate([\"min\", q1, q2, \"median\", q3, \"max\"])\n",
    ")\n",
    "print(quantiles)\n",
    "\n",
    "iqrs = (\n",
    "    data[[\"work_year\", \"salary\"]]\n",
    "    .groupby([\"work_year\"])\n",
    "    .aggregate([low_iqr, iqr, high_iqr])\n",
    ")\n",
    "print(iqrs)\n",
    "\n",
    "data.boxplot(column=\"salary\", by=\"work_year\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Визуализация - Гистограмма"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 288,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Axes: ylabel='Frequency'>"
      ]
     },
     "execution_count": 288,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "df.plot.hist(column=[\"work_year\"], bins=80)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Визуализация - Точечная диаграмма"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 289,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Axes: xlabel='experience_level', ylabel='salary'>"
      ]
     },
     "execution_count": 289,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "df.plot.scatter(x=\"work_year\", y=\"salary\")\n",
    "\n",
    "df.plot.scatter(x=\"experience_level\", y=\"salary\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Визуализация - Столбчатая диаграмма"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 290,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plot = (\n",
    "    df.groupby([\"work_year\", \"remote_ratio\"])\n",
    "    .size()\n",
    "    .unstack()\n",
    "    .plot.bar(color=[\"pink\", \"green\", \"red\"])\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Визуализация - Временные ряды"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 291,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAigAAAHGCAYAAABeq3DqAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjkuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8hTgPZAAAACXBIWXMAAA9hAAAPYQGoP6dpAAChdUlEQVR4nOzdd3xT9foH8M/JaNK994aWvRHKEhCZooBywYEyHCBe9aL3yhWvoIheRP2J4zq5iqgo6FVBVEAEWbIrlA2lLbRQ2tKZDrqS5/dHmkPTpOOkSXvSPu/Xqy9Ncs75PpyTnDz5ToGICIwxxhhjMqJo7QAYY4wxxuriBIUxxhhjssMJCmOMMcZkhxMUxhhjjMkOJyiMMcYYkx1OUBhjjDEmO5ygMMYYY0x2VK0dgC0MBgMyMzPh6ekJQRBaOxzGGGOMNQERobi4GGFhYVAoGq4jccoEJTMzE5GRka0dBmOMMcZskJGRgYiIiAa3ccoExdPTE4DxH+jl5dXK0TDGGGOsKXQ6HSIjI8Xv8YY4ZYJiatbx8vLiBIUxxhhzMk3pnsGdZBljjDEmO5ygMMYYY0x2OEFhjDHGmOw4ZR8UxhhjbY9er0dVVVVrh8GaQa1WQ6lU2uVYnKAwxhhrVUSErKwsFBYWtnYozA58fHwQEhLS7HnKOEFhjDHWqkzJSVBQENzc3HgCTidFRCgrK0NOTg4AIDQ0tFnH4wSFMcZYq9Hr9WJy4u/v39rhsGZydXUFAOTk5CAoKKhZzT3cSZYxxlirMfU5cXNza+VImL2YrmVz+xNxgsIYY6zVcbNO22Gva8kJCmOMMcZkhxMUxlibVF6lb+0QGGPNwAkKY6zNWbPvIros3oKd53JaOxTGZOPixYsQBAHHjh1r7VCahBMUxlibYjAQPtyVAgA4kJrfytEwxmzFCQpjrE05kJqHq0XlAIDCsspWjoYxZitOUBhzcuezi5F4qaC1w5CN7/68Iv5/AScoTomIUFZZ3Sp/RNTkOEeOHIknnngCCxYsgK+vL4KDg7Fq1SqUlpZizpw58PT0RFxcHDZv3gwiQlxcHN544w2zYxw7dgyCIODChQsNlnXffffh7rvvNnuuqqoKAQEB+PzzzwEAW7ZswbBhw+Dj4wN/f3/cfvvtSElJqfeYn332GXx8fMye27Bhg8UonI0bN6Jfv37QarXo0KEDli5diurq6sZOT7PxRG2MOTEiwn2rDqDoehUSF4+Bl1bd2iG1qrLKamw+eVV8XFDG67o4o+tVenRbsrVVyj790ji4uTT9q3HNmjVYuHAhDh06hPXr12P+/Pn44YcfcOedd+K5557DypUr8cADDyA9PR0PPvggVq9ejX/84x/i/qtXr8bw4cMRFxfXYDkzZszAtGnTUFJSAg8PDwDA1q1bUVZWhjvvvBMAUFpaiqeffhq9evVCSUkJlixZgjvvvBPHjh2DQmFbfcSePXswc+ZMvPPOO7j55puRkpKCuXPnAgBeeOEFm47ZVFyDwpgTKyirQm5JJar0hMJS/jLeeioLZZV6mH4AchMPc7TevXvj+eefR3x8PBYtWgStVouAgAA88sgjiI+Px5IlS5CXl4fjx49j9uzZOHfuHA4dOgTAWAPy1Vdf4cEHH2y0nHHjxsHd3R0//PCD+NxXX32FSZMmwdPTEwAwdepU3HXXXYiLi0OfPn3w6aef4sSJEzh9+rTN/76lS5fi2WefxaxZs9ChQweMGTMGy5Ytw0cffWTzMZuKa1AYc2KZhdfF/6+o5mG139c074zpGoxfT2dzDYqTclUrcfqlca1WthS9evUS/1+pVMLf3x89e/YUnwsODgZgnPp90KBBmDhxIj799FMMHDgQmzZtQkVFBaZNm9ZoOSqVCtOnT8fatWvxwAMPoLS0FBs3bsS6devEbZKTk7FkyRIcPHgQubm5MBgMAID09HT06NFD0r/LJCkpCX/88QdeeeUV8Tm9Xo/y8nKUlZU5dAZgTlAYc2KmzqAAUFFtaMVIWl9WUTn2XsgFADw4LBa/ns5GYVkliIhnKXUygiBIamZpTWq1ebOqIAhmz5nee6Zk4eGHH8YDDzyAlStXYvXq1bj77rub/CU/Y8YMjBgxAjk5Odi2bRtcXV0xfvx48fU77rgD0dHRWLVqFcLCwmAwGNCjRw9UVlqvSVQoFBZ9bupOT19SUoKlS5firrvusthfq9U2KW5bOcc7gDFm1dWi2jUo7TtB2XDsCoiAgTF+6BXhDQCo0hNKK/Xw0PCtjsnDbbfdBnd3d3zwwQfYsmULdu/e3eR9hwwZgsjISKxfvx6bN2/GtGnTxGQoLy8P586dw6pVq3DzzTcDAPbu3dvg8QIDA1FcXIzS0lK4u7sDgMUcKf369cO5c+ca7SPjCPypZcyJZRbWrkFpv008RITvEi8DAO7sFw5XtRIuKgUqqw0oKK3kBIXJhlKpxOzZs7Fo0SLEx8dj8ODBkva/77778OGHH+L8+fP4/fffxed9fX3h7++Pjz/+GKGhoUhPT8ezzz7b4LESEhLg5uaG5557Dk8++SQOHjyIzz77zGybJUuW4Pbbb0dUVBT+8pe/QKFQICkpCSdPnsTLL78sKXapuJMsY06sdg1KZTuuQTl9VYfknBK4qBS4rWcoBEGAr5vxlyUPNWZy89BDD6GyshJz5syRvO+MGTNw+vRphIeHY+jQoeLzCoUC69atQ2JiInr06IGnnnoKr7/+eoPH8vPzw5dffolffvkFPXv2xNdff40XX3zRbJtx48bhp59+wq+//ooBAwZg0KBBWLlyJaKjoyXHLhX/rGDMiV0t5D4oAHDichEAICHWD96uxsTE180F2boK7ijLHGbnzp0Wz128eNHiubr9PK5cuQK1Wo2ZM2dKLrNr1671ztUyevRoixE7tbeNiYmx2HfKlCmYMmWK2XOPPPKI2eNx48Zh3LiW77TMCQpjTiyTa1AAAOn5ZQCAGH938TlfNxcAPNSYyUdFRQWuXbuGF198EdOmTRNH+DDrJDfx7N69G3fccQfCwsIgCAI2bNhg9joRYcmSJQgNDYWrqytGjx6N5ORks23y8/MxY8YMeHl5wcfHBw899BBKSkqa9Q9hrL0xGAjZOq5BAYCMAmOiFunnKj7n617TxFPKCQqTh6+//hrR0dEoLCzEa6+9Zvba2rVr4eHhYfWve/furRRx65Jcg1JaWorevXvjwQcftDrs6LXXXsM777yDNWvWIDY2FosXL8a4ceNw+vRpcUjSjBkzcPXqVWzbtg1VVVWYM2cO5s6di6+++qr5/yLG2onckgpU6W9U17bnGpSMmhqUKL8bwzV9ampQuImHycXs2bMxe/Zsq69NmjQJCQkJVl+rO5S5vZCcoEyYMAETJkyw+hoR4a233sLzzz+PyZMnAwA+//xzBAcHY8OGDbjnnntw5swZbNmyBYcPH8ZNN90EAHj33Xdx22234Y033kBYWFgz/jmMtR+ZteZAAdr3KB5TghLheyNBqd1J1mAgKBQ8F4qcSVkDpy3y9PQUZ4R1dva6lnYdxZOWloasrCyMHj1afM7b2xsJCQnYv38/AGD//v3w8fERkxPA2LFHoVDg4MGDVo9bUVEBnU5n9sdYe3e11iyyQPutQSmtqEZeTTNOlH/tBMVYg/L5/ku4/xPr9xbW+ky1A2VlZa0cCbMX07Vsbs2PXTvJZmVlAYBFx5/g4GDxtaysLAQFBZkHoVLBz89P3Kau5cuXY+nSpfYMlTGnZ1mD0j4TlIwC483Q21VttlhisNeNWS73peS1eFysaZRKJXx8fJCTkwMAcHNz45l/nRQRoaysDDk5OfDx8YFSKW3ZgLqcYhTPokWL8PTTT4uPdTodIiMjWzEixlof16AYZeRbdpAFgDHdgvHXWzrivd+Ny83rDQQlN/PIUkhICACISQpzbj4+PuI1bQ67JiimgLKzsxEaGio+n52djT59+ojb1H0TVldXIz8/v95/kEajgUajsWeojDk90zo8GpUCFdWGdtsHJd1KB1kA0KqVePyWeDFBKa/Sw51nlJUlQRAQGhqKoKAgi7VgmHNRq9XNrjkxseunNTY2FiEhIdi+fbuYkOh0Ohw8eBDz588HAAwePBiFhYVITExE//79AQA7duyAwWCotwczY8ySaQ6UaH83nM8uabc1KIfT8gEAUX7uFq9pVDe62XGCIn9KpdJuX27M+Un+tJaUlODChQvi47S0NBw7dgx+fn6IiorCggUL8PLLLyM+Pl4cZhwWFibOVNe1a1eMHz8ejzzyCD788ENUVVXh8ccfxz333MMjeBiTwDSLbLS/O85nl7TLPigXcoqx9bSx79qdfcMtXlcoBHFNnutV7bOGiTFnJTlBOXLkCG655RbxsalvyKxZs/DZZ59h4cKFKC0txdy5c1FYWIhhw4Zhy5YtZssyr127Fo8//jhuvfVWKBQKTJ06Fe+8844d/jmMtQ/VegNyio0JSmyAseagPSYo7/2eAiJgbLdgdA6xPkRTW5OglFe1v/PDmDOTnKCMHDmywTHOgiDgpZdewksvvVTvNn5+fjwpG2PNkF1cAQMBaqWAUG9j8t/emnhOXinChmNXAACPj6p/KXitWgldeTXKuQaFMafCqxkz5oRMI3hCvLXQqo1t9u2tk+zLP58GETC5Txh6RfjUu117PT+MOTtOUBhzQqY5UEK9XcWOoO2piaegtBIHUo2dYxeO79Lgtlq18fxwEw9jzoUTFMackKkGJdRbC5d2mKBcqhlaHOKlRbiPa4PbutbUoHATD2POhRMUxpzQVbMaFOMXcHvqg1Lf3CfWaMQEpf2cH8baAk5QGHNCmTU1KGE+7bMGJT2vFID52jv10XINCmNOiRMUxpzQVSt9UCrbUSfQS3lNr0HR1pyf8nZ0fhhrC3haRcac0NWiG31QqvTGmpN2VYNS08QTLaEG5XolJyiMOROuQWHMyVRU65FbUgkACPNxFZt42mMflMim1KCo218TGGNtAScojDmZrFqLBPq6qcVOsu3lC7i8So8sXc00/01KULgPCmPOiBMUxpxMZs0aPGE+rhAEoVYflPaRoFwuuA4iwN1FCT93l0a35wSFMefECQpjTqZ2/xMAtSZqax9fwGezdACMiyQKgtDo9mInWR5mzJhT4QSFMSdTewQPALEPioGMiwi2dTvO5AAAhsb5N2l7rQvXoDDmjDhBYczJ1J4DBYDYBwVo2X4oabmlKLpe1WLlAYDeQPj9nDFBubVrcJP20dacn/J20gTGWFvBCQpjTiarnhoUoOUSlDNXdRjz5i7MWX2owdXN7e1oegEKyqrg7arGTdG+TdqH+6Aw5pw4QWHMyYgLBdbUoCgVAlQKY1+Mluoo+/Pxq6g2EP5ML8Txy0UtUiYA/FbTvDOycyBUyqbdvm4sFsgJCmPOhBMUxpyMqZNsmPeNRfJcWrij7G9nssX/X3c4o0XKBIDtNeWO6hLU5H24BoUx58QJCmNO5HqlHoVlxn4fphoUAC061PhyQRnOZhWLj388dqVFvvzT88qQnFMCpULAyE5SEhQexcOYM+IEhTEnkllTe+KhUcFLqxafb8kFA387bazFGBDjiwAPDUor9ThxxfHNPKZamwExvvB2Uzey9Q1iJ1muQWHMqXCCwpgTuVpo6iCrNXu+JWeT3XT8KgBgXPcQ9I/2AQAkXipweLk7zhr7n4xu4ugdE42piaedzBPDWFvBCQpjTsRUgxLq42r2fEv1QblcUIbESwUQBOCO3mHoXzOS5k8HJyjF5VU4mJYHoOnDi01cxT4o3MTDmDPhBIUxJ2KqQQmzqEFpmT4om5KMtScJsX4I9tLeSFDSCxw63Hj3+VxU6QkdAtwRG+AuaV8excOYc+IEhTEnQUS1prmvrwbFsQnKHxdyAQATe4YCALqHeUOtFJBbUimuMOwIptE7t3ZteudYE9MongquQWHMqahaOwDGWOPKq/SY9J+9OJ9dAsB8BA9wowbF0bUEV2pmsY0P9gRg/PLvEe6No+mF+DO9ANH+0mo3msJgw+yxtZkSlEq9AXoDQam4sX5Ptq4cPx7LRHJOMUZ3DcaYbsFNWt+HMeZ4nKAw5gTOZhWLyQlg2Uk2xMv42LTSsSMQkZighNfqA9M/yhdH0wuReKkAd/aNsHu5p6/qUFBWBXcXpdikJIWpiQcA+iz9FT7uani7quGlVeNoeiGu1yR13xy5jNlDYvDipO52i50xZjtu4mHMCeSXVpg9rtsPIzbAAwCQllsCR8krrURltQGCAAR73UiQTElD4qVCh5S7P8XYOTahgz/UTZw9tjZtrbWKiiuqkZF/HSev6LAvJQ/Xq/ToE+mDu/qGAwB+PnHVPkEzxpqNa1AYcwL5pcbJ2Xzc1Pi/ab0R4etm9npsoDFhScstdVgMpg66gR4as/V/+tUkKOeydCipqIaHxr63lX0pxn4vQzo2bfXiuhQK8yabdXMH4XqlHkXXqxDgocHQOH9kFpXj+6NXUFhWCSLiZh7GZIATFMacgKkGZWSnQKv9MDoEOD5BuSKuomzeQTfYS4twH1dcKbyOpIxCDI0LsFuZVXoDDqXlAwAG25ig1BYf5IFBHSyP4+fmUlMeoaSiGp7apk8ExxhzDG7iYcwJmGpQfN1drL4eU5Og5JZUouh6lUNiyLTS/8TkRjOPfedDOZWpQ2mlHj5uanQN8Wr28e7qZ72PjKuLUuxobFpKgDHWujhBYcwJmGpQ/OtJUDw0KgR5agAAFx1Ui2JKUOp20AWAflE+AIzzodjT0Zrj9Y/ytWiqkeK1qb0wIyEKDw2LrXcbv5pzm19aaXM5jDH74QSFMSfQWA0KcKPjrKOaea4W1UwSZ7UGxQ+AcUZZg8F+E7YlZRQCAHpH+jTrONMHROKVO3ua9Z2py6emmaegjBMUxuSAExTGnEBjNSgA0KGmo2zqNceM5KmvDwoAdAn1hKtaCV15NVLqlF9WWY2M/DKczy5GUkYhTmfqmjzr7DE7JShN4edu7HfCTTyMyQN3kmVMxsqr9Ei5ViI2O/i61Z+gmGaXvVZSUe82tiq6XoVLecaamTAfyyYetVKBXhHeOJiWjz/TC8SJ3M5lFWPye3st1sFZMbUndp2/hmh/d/xzfBerZRaWVeJinnF22t4R3vb851hlqkHhJh7G5IFrUBiTsZXbzmPiO3vFL2p/j/oTFEctinel8DqmfbgPBWVV8HVTo2Ogh9XtrHWU/fVUFsqrDFApBPi6GSdIA4DXt57HLyey8OGuFJRVVls9XtLlIgDGpiufBhIze/F1M9WgcILCmBxwgsKYjO2tWfvGxM9dU++2jlgU7+SVItz53h84n12CIE8Nvnw4Ae71zHNiaoY5c7VYfC6xppPrvyZ2xdElY/Hp7AEAgNyaWh4i4HSmzurx9py/ZjxuC9SeADeGGudzgsKYLHATD2MyVa03ILnW9PaCALEGwhqNWIPS/ARlx9ls/HT8KraezEJppR6dgz3x6ZwBVocYm5j6x+jKjX04DAbC0fRCADdqV3pFeMNVrRSnlweMSdBNMX5mxyqv0uN/f14GANzRO6zZ/56muNFJlvugMCYHnKAwJlOpuaWo1N9orlEIgtlCd3Vp7dTEU6U34G9fH0NxhbHpZWicPz64vz+8Gpm8zDS5WXF5dU38JSi6XgWtWoGuocY5TNRKBW6K8cWe5Bs1Qyet1KBsPnkVhWVVCPPWYmRn6SsY28I0zJibeBiTB05QGJOpM1fNv7j1jQzfNfVBud7MGpSkjEIxOXn7nj6Y0CO0weG5Jp5a4+1Ed70KRIQ/a9bm6RXhY7aGzuCO/tiTnAulQoDeQDh5pUh8rVpvwPazOXhh4ykAwD0DoxpMyuzJp6YPimlIN2OsdXGCwphMnc0qbnyjWuzVB+WPC8bF+W7rGYLJfcKbvJ8pQak2EK5X6fFtYgYA4KY6KxDfNzAKZ68WY3inQPzj2yQk55RgU1Im9iRfw6+ns8Vhvv2ifDBnaEyz/i1ScA0KY/LCCQpjMmWqQXF3UaK0Uo/uYQ1P9W5q4qmobl4Tzx/i4nzS1tRxd1FBIQAGAr46mI7DFwugVStw/6Bos+183Fzwzr19QUR4fetZZOsq8MTXR8XX/dxdMKVPOBaO7yz+m1qCLw8zZkxWOEFhTKbO1oyGWTXrJqTlluKWRvpiaFXN7yRbWlEtTi8vddE/hUKAh0YFXXk13tmeDAB4bGSc1YndAEAQBLw/oz9W/5GG89nFSIj1x4SeIRgY4weVsuUHGJqaeCqqDbheqYerS8slR4wxS5ygMCZDBaWVyNIZp5bvGe7dpNoMVxfjl3pz+qB8eyQDVXpCjL8bYvzdJO/vqVVDV14NXU1H2caSqv7RvuIIn9bmoVFBq1agvMqAjIIydKqZbI4x1jp4HhTGZOhMlrF5J9LPVRwd0xhNM2tQKqsN+Gh3KgDg4Zs7QBCkd0419UMx8WtgYjm5EQRBTJb21Zl/hjHW8jhBYUyGTJOddQ1puN9JbbWHGTd1rZvaNh67gqtF5Qjy1OAv/SMk7w/AYihyQ2sHydGwuEAAwN6ajsKMsdbDCQpjMnS2poNsl1ApCcqNj7PUjrJEhM/2XQQAzBkaa3Pn1No1KO4uyhbt5GoPw2r63RxIzUO13r5LBjDGpOEEhTEZMg0x7hrS9H4QtZOBComTtSVeKsCpTB20agXuHRgpad/aaicoztS8Y9ItzAs+bmqUVFSLawExxloHJyiMyUy13oBz2TUJioQaFLVSAVXNpGZSO8qurqk9mdInvFkL89XuL+PfwLpBcqVUCBjS0R8AsDeZ+6Ew1po4QWFMZi7mlaKy2gA3FyWi/KSNpNHasB7P1aLr2HIyCwAwa0iMpPLqql2D4mz9T0xM/VD+4I6yjLUqhyQoxcXFWLBgAaKjo+Hq6oohQ4bg8OHD4uuzZ8+GIAhmf+PHj3dEKIw5ndM1HWQ7h3hCIXGad3E22eqmJyhrD6RDbyAkxPpJqrGxpnYNip/TJijGfih/phegtGbKf8ZYy3NIgvLwww9j27Zt+OKLL3DixAmMHTsWo0ePxpUrV8Rtxo8fj6tXr4p/X3/9tSNCYczpiB1kJYzgMbkx1LhpfVDKq/T4+lA6AGB2M2tPgDo1KB7O18QDAFH+boj0c0W1gXAoLb+1w2Gs3bJ7gnL9+nV89913eO211zB8+HDExcXhxRdfRFxcHD744ANxO41Gg5CQEPHP11cekzUx1tpMU9x3DZU+UZjU9Xh+On4VeaWVCPPWYky3YMnl1eXlWrsPinPWoAA3alH2cD8UxlqN3ROU6upq6PV6aLVas+ddXV2xd+9e8fHOnTsRFBSEzp07Y/78+cjLq3/egYqKCuh0OrM/xtoqcQSPDc0tpunZm9JJloiwpqZz7P2Do+0yvbzZKB6nTlC4Hwpjrc3uCYqnpycGDx6MZcuWITMzE3q9Hl9++SX279+Pq1evAjA273z++efYvn07VqxYgV27dmHChAnQ663fVJcvXw5vb2/xLzLS9mGQjMlZYVklrhYZp7jvLGGIsYlpPZ6KJiQof6YX4MSVIrioFLhnQJTksqzxMmvicd4EZXBHfwgCcC67GDnF5a0dDmPtkkP6oHzxxRcgIoSHh0Oj0eCdd97BvffeC4XCWNw999yDSZMmoWfPnpgyZQp++uknHD58GDt37rR6vEWLFqGoqEj8y8jIcETYjLU60wyyEb6uFrOyNkXt2WQb89m+SwCAKX3C7Fbb4ezDjE383F3E1aP38ayyjLUKhyQoHTt2xK5du1BSUoKMjAwcOnQIVVVV6NChg9XtO3TogICAAFy4cMHq6xqNBl5eXmZ/jLVFabmlAID4IA+b9m9qH5RsXTk2nzDWaDZ3aHFtzj5RW22mZh7uh8JY63DoPCju7u4IDQ1FQUEBtm7dismTJ1vd7vLly8jLy0NoaKgjw2FM9rJrVjAO8Xa1af+mzoPyw9ErqDYQbor2Rfcwb5vKssbXzQUalQJatcKpO8kCQEIHPwBA0uXC1g2EsXZK1fgm0m3duhVEhM6dO+PChQt45pln0KVLF8yZMwclJSVYunQppk6dipCQEKSkpGDhwoWIi4vDuHHjHBEOY05DTFC8tI1saZ0pQbneSBPPpqRMAMBd/WxbFLCh8lfPHgBBEJxuHZ66wn2MSeK14opWjoSx9skhCUpRUREWLVqEy5cvw8/PD1OnTsUrr7wCtVqN6upqHD9+HGvWrEFhYSHCwsIwduxYLFu2DBqN87ZZM2YPpgQl2Mu2z0JjTTwnLhfhq0PpOJWpg1IhYHyPENsCbcCQmiG6zi6gZh6XoutVqKw2wEXFE28z1pIckqBMnz4d06dPt/qaq6srtm7d6ohiGXN6WTrjr/VgbxtrUEwTtVmZSdZgIDz6ZSKuFF4HYJzrw5mHAjuaj6saSoUAvYGQV1qBUBub3RhjtuGfBIzJSI6pBsWzeU081lYzTrpcKCYn7i5KzBtuvdM6M1IoBLEfTW5xZStHw1j745AaFMaYdBXVeuSVGr8IQ2ysQTFN1Fa3iUdvIPxSM2pnUu8wvHNv32ZE2n4EeGiQU1yB3BLuh8JYS+MEhTGZMHXGdFEq4OsmfQ4UANDU9JOoPZNscnYx7np/H4prFr67raf9+520VQGeGuAqcI0TFMZaHDfxMCYTpg6yQV4aCIK0VYxNrA0z/nBXqpic+Lu7YESnoGZG2n4E1MzlwjUojLU8rkFhTCayTR1kbRxiDFjOJHutuEIcUrxscneM7hYsNgOxxgXWjOThPiiMtTxOUBiTiayi5s2BAlgOM/76UDoq9Qb0ifTBA4Njmh1je2Maasw1KIy1PG7iYUwmsotNc6DYnqC4mmpQqg2orDbgiwPG9XbmDI1pdnztUYCnsYknr5QTFMZaGicojMmEqQbF1knaAMDNxVgpmldSgV9OXMW14goEeWowoQcvI2GLAG7iYazVcILCmExcLTQmKKE+tk8I1iPcCy5KBS4XXMfrW88BAB4YFM2zoNqodhOP3kA4frkQBgO1clSMtQ9812JMJjKLjJOohdk4BwoAeGrVGBLnDwC4UngdLioF7kuIskt87ZEpQckvq8THu1Mx6T9/YNWe1FaOirH2gRMUxmTAYCBxmHFzalAAYEy3YPH/J/UOg78Hr3FlKz93F7i5KEEE/LcmMfnh6JVWjoqx9oETFMZkILekAlV6gkIAgj2bl1CM6RoM0zQqs4fEND+4dkypEDCko3HxQ9Msv2ezipGeV2axLRGBiJt/GLMXHmbMmAxk1nSQDfLUQqVs3u+GIC8t/nNvP1Tq9egR7m2P8Nq1kZ0D8duZbLPn3t2RjM4hnmLSMmdIDGavPgx3jRIfP3ATfHkRRsaajRMUxmTgas0ifqE+tvc/qW1iLx61Yy8jOweK/++hUaGkohrfJl422ya7qBynr+oAADP+exDr5w2Cp9a25QoYY0bcxMOYDJhqUMK8m9f/hNlfhK8bOgd7AgCen9gVY7oFY1hcACb1DkPvSB8AwIkrReL2p6/q8M/vjnNzD2PNxDUojMmAWIPSjBE8zHHeuqcPDl/Mx/SbInHPwBujor7YfxFJGYVIyy0FYOyzohCAX05k4csDl3j2XsaagWtQGJOBq0X2GcHDHKNrqBdmDo6BQmG+iKNphFR1zdwoo7sG4dkJXQEAr/xyRkxcGGPScYLCmAzYYw4U1vIC6gzh9nPXYM6QGAyN80d5lQFPf3MM1XpDK0VXv8pqgzhzMWN1ERH+uJCLwrLWnUGZExTGZCDbtFAgJyhOxd/DfLROgIcLFAoBr/+lNzw1KhxNL8RHu+U3sduSjScx5NXt+P1cTmuH0i5VVhvw17V/4t6PD+CDnSk4nalrlT5L1obGH76Yj3tXHcCM/x5s9UkJOUFhrJUZDIRrNavlNmehQNbyAtzNa1D8a4YXh/m44sVJ3QEAb/12Hqcyiyz2bU3rDmfAQMCc1Ye5M28r2HX+Gn4+cRX7U/OwYstZ3PbOHgz893b849skHE0vaLE4PtyVik7Pb8aJy0U4cbkIsz49hGkf7seB1Hy4KBVo7VUdOEFh7Vp5lR7/+DYJW05mtVoMBWWVqNIb7wSBzZykjbUsL1cV1Mob/VL8ajX53NUvHGO7BaNKT3h6fRIqqvWtEWKj9l7Ibe0Q2qSi61VYe/ASkrOLLV77+XgmAGBIR3/c2iUIrmolrhVX4H+JlzH/yz9bLMYVW86iSk94ct1RTHn/D+w6fw0qhYB7B0bi92dG4p/ju7RYLNbwKB7Wrq07lI7/JV7G/xIv4+KrE1slhpxiY+1JgIcL1M2cpI21LEEQ4O+uQVbNMgUBtSZoEwQB/76rJxIvFeBcdjFWbkvGsxNa94YPAHqDccZi06/jLSezcHN8YMM7Mck+2JmCD3elAABujg/Ag0NjMaJTICr1Bmw7bZz47x/jOqNflC8qqvU4lJaPWZ8eQpauHNeKKxz+YyW/9Eb/ElNn7hh/N6x5cCCi/d0dWnZT8d2QtWuF16vE/2+tqm7TGjyBnty844xq90Opu+5RgIcG/76rJwDgo90pLVp9X5/80kqzqvvMmiHuzL5ME/cBwJ7kXMz57DDGrNyFhf87jtJKPcJ9XNG3Zh4djUqJm+MDERNgTAzOZumsHdKuEi9ZvhcHxPjJJjkBOEFh7ZyP643ZPgvLqhrY0nFMNSjBXty844xqj+TxszLF/bjuIZjSJwxEwJvbzrdkaFbllVaYPc4s5NE8jnCxplbi/6b1xiM3x8JTq0LKtVL8mGRs3nny1jgIgvmw9a4hXgCAs1ctm4Xs7cilfIvn4oI8HF6uFJygsHZNX+uX5JVW+iWZozOtw8MJijMy1aAIAuDrZn16+6fHdIZSIWBPci6OZRS2YHSWcouNVfumKV1MQ9yZ/VRWG3C5wLig5M2dAvCvid2w79lRmD+yIzoHe+K9+/rh7gFRFvt1CTHOWHzmagvUoFy0rEHhBIUxGSmtqBb/v9USlGIewePMTDUovm4u9S70GOXvhil9wgEAH9X0SwAAXXkV9qXkYs2+izhvpTOlI+TWjBjrWbOQZHF5NYrLW6f2sK1Kzy+DgQB3FyUCa94fnlo1/jm+C7Y+NbzetbK6hBprUM5kOfa9cLmgDH9aaW6UW4LCnWRZu1ZaWStBKWidBCWba1CcmmlosbXmndoevjkW3/15GdtOZ2PZT6fx+7kcpF67MdNsj3Av/PTEzQ6NFbiRoET5uyMttxS68mpcLSrnxQ3tyNTpNDbQ3aIZpyFdQ401KBdyilGlNzis0/yafRdhIGBonD+q9YSDaflwUSkQ4evmkPJsxTUorF0rq7gx9LO1a1CCuAbFKZlqvgI9Gk4wu4Z6oXekD6oNhE/2ponJianv0YWckhbpqJ1bYmziCfBwQVjN0grNfe+fzy7Gf/ekYvkvZ/D0+mOY9ekhrD+c3uxYnVVabgkAIEZih9NwH1f4uKlRpSf8eCzTEaGhuLwK6w5nAAAeGhaL2JqOuR0DPaBUND2Zaglcg8LaNTnUoOToahIUrkFxSrd2DcK9A6MwqXdYo9veMyASSTV9UJ4a3Qn3D4qCp1aNzos3o7zKgLzSSovp8+3NVIMS4KFBmI8rzmYV42ozOsqWVlTj7o/2o6BOJ/MDqXkY1z0EPm4N1yy1RWm5xv4nHQKkJSiCIGDe8I5YseUs/v3LGYzuGgzvevo12erdHRdQXF6NuCAPjOwUJMbatab/i5xwgsLatdauQSEi5BQbvxy4D4pz8tSqsbxmKHFjpvQJx57ka+gU7Gk2iiPYU4ssXTkuF1x3eIKSV3Jj3p0wH+N77mozOsquP5yBgrIqBHtpcHuvMAR5avDNkQykXCvFd39ewUPDYu0StzNJvWasQYkNlD5k96Fhsfg2MQOp10qx9VQWpg+ItGtcq/9IAwD8a2JXKBQCpt8UgWq9Abf1tN4vpjVxgsLaNbMalMLrICJJbcbN9Wd6Aar0BJVCcPgXE2t9ri5KvD+jv8XzEb6uNQlKGfrUzI3hKDeaeDQI9W5eE0+13oBP9hq/8J68NR4zEqIBAO4aFZ7fcBLLfjqN1GsleO62rnDXtI+vm4pqPZIuFwIAutQMG5bCRaVAQqw/Uq+V2n2E1cs/n0GVnnBL50Dc0jkIgDHBnjeio13LsRfug8LatdqjePJLKzHjvwdxIaekRco2GAgvbToNALizbzhcVPxxbK/CfWsShRZoZjQ18fh7aMQaFFvLPZ9dgiuF1+GpUWFqvwjx+Sl9w+GpNSYkaw+mY8fZ9rMoYeKlApRXGRDgoRGHDUtl6pdk6kBvD7+fy8GOszlQKQQ8f3s3ux3XkfiOyNq1skpjE8+EHiHQqBTYl5KHCW/vxutbz6K8yrFrp2xMuoKky0Xw0KjwzPjODi2LyVtETYJy2cEJChEhr1Yn2a41w1qPXCpARn6Z5OOZkp1wX1do1UrxeQ+NCt/NH2KxXXuwN9m4ttHN8QE218aG1DT3Zuvsc96q9AYs+8n4Y2jO0Bh0DJTXcOL6cILC2jVTE88jwztg21MjcEvnQFTpCe/9noKXfz7tsHKr9Aas3JYMAJg/siOCeJr7di3cxzi809H9oPJKK1GpN0AQgCBPLbqEeOHm+ADoDYQPas3P0lSm9VysDbHuFOyJ+wcZJyMrqLXuS1u3p1aCYitTf7SsIvvUoKzZdxGp10rh7+6CJ26Nt8sxW0L7aBRkrB6lNZ1kPTQqRPm74dPZA/D5/kt44cdTOJhqORW0vXx75DLS88sQ4OGCOUNjHFYOcw43alCk12JIYVp3J9BDIzYpPjEqHnuSc/G/I5fxxKg4sV9KU+TVJB6+9cwB41czgqfuCJ+26mJuKU5mFgEAhsU1P0HJKS5H4qV8nM8uge56FXTlVajSE2YOjm7ynCW5JRV4e7vxx9Az4zrDy4nmu+EEhbVrpj4obi7G6mlBEDA0zh+A/X691FVepce7O4w3jMdGxsHNhT+G7V3tPiiO7KhtSlBM858AwMBYPyTE+uFgWj4+2pWKFyd1b/Lx8mvW9fGvJ0ExDTHOL3PuGpS03FJ4u6rh5+6CsspqbD2VhVs6B1kMof5odwqIgFs6BzZrXqMQb+O+uSWVmPrBfovXkzIKsW7uoCa9T/7v1/MoLq9Gj3AvTLvJfiOCWgI38bB2q1pvQEW1AQDgXitJCKn5BVlcUY2SWp1oramsNuBv647ig51Nrx5fezAdV4vKEeqtxX0JlutxsPYnvCZhKK3UQ3e94fdcc1ypme8k3Me8luSJUcZq/68PpYvD3puioSae2s8XOnGCkpRRiLErd2H26kMoLq/C3R8dwFPrk7D8l7Nm22Xkl+G7xCsAgMduiWtWmb5uarjUmkU2zFuLqf0iMHtIDDQqBQ6m5Tep4/HJK0VYVzNh3gt3dJfdRGyN4QSFtVtltTrBumnMO/h51AyJbKwW5WBaHjYey8Qbv55DUROqsUsrqvH+7xcAGIdl1u5YyNovrVoJ15r3QtF1xzWHXBVrUMx/3Q+N80ffKB9UVBvw3z1pTT6eqcNt/TUoxuaEglLnbOIhIrzyi3Fo7vHLRXjm2+M4ccXYhPPDsSswGIwz/5ZWVGPeF4mo1BuQEOuHATF+zSpXEAQE1Vrd/O4BUfi/6b3x4qTumDPUOK/Mh430GSIyjhIkAib1Dmt2TK2BExTWbpkmaVMpBLNfK8CNKtbGhvkdv2y8WekNhJ3nG/9F89m+i8grrUS0vxv+0j+i0e1Z+2Ealqtz4MJ9pnk1wurUoAiCgCdralG+PHBJrBlpzI0aFOtz+JhqUAqctAbltzM5OJR2oy/allNZ4v9XVhtw/EoRNiVlYsybu3D6qg4BHi548+4+dim79sSNfaJ8xP+f0tc4Y/H57IanQ/j5xFUcupgPrVqBZyd0sUtMLY0TFNZuldTqf1K3Ldc0zO9qIzUopmnLAePNrCHVegM+3p0KwDjNuaMWAmPOyZSgFJc7vomnboICACM7B6JHuBfKKvX45khGk47XWBOPr5vzJijVegNe3XwGAMyaRlQKAbd0DgQAzFl9CE98fRSZReUI93HFqpk3WTSf2UpTa16kPhE+4v9H1nSOLarpNGvN9Uo9/v2zMfb5I+KsXm9nwHdI1m6V1Qwx9rAyw6XUGhQA2HkuB1V6Q73b5hRXoOh6FdRKAXc0Yd0W1r6YVhN2aA1KTROPtS9RQRDE6c7PZRU36XimUTz+HvUkKDWJS3mVAdcrHTuvkL2tO2ycrt/P3QVzhsSIz3cP98aEHsbzVFBWBa1agadGd8L2v49A3yhfu5Vfu3m59no87hqV2KRW39w1n/6RJiZN80Z0sFtMLY0TFNZumYYYu1lLULwaX6MkR1eOLF05FALgpVWhuLzaLGGpy3SsYC+t03VWY47n6BqUimo9rtWsnF3fL+poP+PaMZfyShs9XpXeIPaXqa8Gxd1FCbXS+F53plqUkopqvPXbeQDAk6PikNDBX3ztpmhfTOgZghGdAnFX33Bs//tI/G20/fuTTepj/BHTt1bzjkmEn7EWZdvpbHy4KwVHLuZDX9MfpkpvwOf7LwIA/j62k1P3c+PxjazdMtWguLtYfoBNNShZReWorDZYnYY+qSYZiQvyQJSfO347k42j6QXoH239V5SpuSjUmydlY5ZM81MUO6gGxfSLXKtWwLeeFXKj/Y1ffJfyGp+PxZRwCMKNppy6BEGAr5sLcoorkF9a6TRNDR/vTkVuSSVi/N1wX0I0rtWaCbd/tC88tWqseXCgQ2N4dERHRPu7YUSnIIvXIn1dkZRRiLd+Sxaf83FTY0SnQAR6aJCtq0CAhwtu7+XcNbVcg8LarRt9UOqvQfntTA5uenmb1dE8m09eBQDcFOMnJiWJlwrqLc+0pL2UibBY++HoGhRT7V6Un1u982dE1SQoeaWVjQ6xN/U/8XFVN1gjaEpeCp1ksjaDgcQaiIXju8BFpUCYtxYdA93hqVFhYGzLjIbRqpW4s2+E1dqpSD/zSdq8tCoUllVh47FM/Ldm8ca7B0Q6/fpeXIPC2i3TOjzumvprUABAV16NnedycM/AG3OWFF2vwi8njAnKX/pHoFpvrF5NvFQAIkJBWRV2nM2Bv7sLbuli/AXENSisIV6ujq1B+TEpEwAwumtw/TFojZOR5ZdW4lJeKbqHede7bWMdZE183WuGGjtJE8/ZrGIUllXBQ6PC2G7GcyUIAtbPG4zyKr0sVh2PrDWLbLdQL/z4+FAczSjEjrM5+P2ssS/czMExrRegnXCCwtqt0gZqUKL83aBRKcSJ3A5dzDdLUL49koHyKgM6B3uib6Rx/giVQkBOcQXu/ugAEtMLoDcQFAKw65lbEOnnJvZB4QSFWeOpcVwNSlFZFXaduwYAmNwnvMFto/3dahKUMqsJypaTWUjOLkZMgLG/in89Q4xNmjOS53x2MfYm52L6gEirndkd4WBaHgBjU46q1kg7OSQmJlG1alCGxvlDpVRgQIxx/pV/jnfOIcXWcILC2q0bNSiWHwMvrRrfzR+CA6l5ePnnMzh88cZcCBuPXcHyzcZZJGcMioIgCNCqlege7o2kjEIcqtnWRaVAZbUBe5JzcV9CFDJralBCuImHWeHIJp4tp66iUm9AlxBPdA7xbHDbaD83HE0vtNoPJa+kAk+uO4rKagMGxBibNQM9G0lQTHOhSJisrbSiGm9vT8Yne9OgNxCUCgGzao2kcSTTGlwt1ZRji0i/G/eQIR1tX/NH7py7gYqxZjBVUXu5Ws/Te4R74+4BkVAIQEb+dWQVlePrQ+lYsP4Y9AbCXX3DcV+tWpW/j+mE0V2DsGhCF+x+5hY8NrIjAGDvBeMv16wi67N4MgY4dpjxxmPG5p2mDG+P8jfWjKTnW47kWXswHZU1tYqHLxr7WzW2aq9pwcDcWh1N60NE2HIyC2Pe3IWPd6eKI1PS6xlOa29EJP7AGNRBvglKmI8rAjw0EARggIwTqeZySIJSXFyMBQsWIDo6Gq6urhgyZAgOHz4svk5EWLJkCUJDQ+Hq6orRo0cjOTm5gSMyZn+mOQQiG1gV1FOrRtdQLwDAM/9LwqLvT4AIuH9QFN6Y1tusCnh4p0D8d9YAzBvREVH+buKN+48Leaio1iOnZohnCDfxMCscVYOSoyvH/lRjs8WkJiQoMTUdZevOVFpRrcfn+y+ZPadUCBjbPaTB45lGBqXmNjzzaXpeGR787DAe/TIRmUXliPB1xW09jcfOamQ+IntJzS1FfmkltGoFeob7tEiZtlArFfjlb8NwYNGtLdb01RockqA8/PDD2LZtG7744gucOHECY8eOxejRo3HlinEhpddeew3vvPMOPvzwQxw8eBDu7u4YN24cystb5k3IGHDjV1mUX/0JCgBM6GG8Se5JzgUAzBvRAcsm94CikblMekf4wFOjQtH1Kjz7nTGxUSsFBDTSZs/aJ08HDTPedPwqiIB+UT4Woz+sMTVtHE0vEOdNAYAfj2Uit6QCIV5acZjykI7+jXaSNTUp1Tf5W0W1Hu9uT8aYlbvw+7lrUCsFPH5LHLY9NQITexoTqmwHrSxe18madXa6hXrJfgRMkKfWbDr8tsjuV+D69ev47rvv8Nprr2H48OGIi4vDiy++iLi4OHzwwQcgIrz11lt4/vnnMXnyZPTq1Quff/45MjMzsWHDBqvHrKiogE6nM/tjrDmIqMkJyvyRcfj3nT3RI9wL/7qtK54d36VJy5yrlArc2c/YIfGHo8bkPNhL22hiw9qnG2vx2LcG5cdjxvdeY51jTSJ83dA7whsGAn49bVx7hojwSc3w1VlDYsR1pO4Z0Phq3HFBHhAEILek0qKZ548LuZjw1h7837bzqKg2YHAHf2z+23D8Y1xnuLooEeJtTOZbqgbl9FXjd0u3MK8WKY81zO51Q9XV1dDr9dBqzTM7V1dX7N27F2lpacjKysLo0aPF17y9vZGQkID9+/fjnnvusTjm8uXLsXTpUnuHytqxnOIKVFQboBCAcN+GO60qFQLuS4jCfQmN34zrWnx7N/SL8sW3iRk4nanDnX2b9iXB2h9HTNSWlluKpMtFUCpuTGPfFBN6hiLpchF+OXEVMxKisS8lD2eziuGqVuK+gVFw0yhxX0I0YmtG8jTEzUWFKD83XMorw/nsYgR4aJCjK8fLP58Rhz4HeGiw+PaumNQ7zCz5N9UQ5OgqQERN+mHQHKczjQlKQ8OrWcuxe4Li6emJwYMHY9myZejatSuCg4Px9ddfY//+/YiLi0NWljEjDw42H4sfHBwsvlbXokWL8PTTT4uPdTodIiMj7R06a0dMtSdhPq4OXbRPrVRgSt9wTOHEhDXC1Fm7vMqAKr3BLu/LTTUJwJCO/o2Otqntth6heHXzWexPyUNabin+u8e4yOW0myLEdWGakpyYdA72xKW8Mpy5WozzWcX4v1/Po7iiGgoBeGBQNJ4e2xnerpaz2wZ5GhOUSr0B+aWV8HfgUF8iEhOUbqFcgyIHDuld88UXX+DBBx9EeHg4lEol+vXrh3vvvReJiYk2HU+j0UCj4XZ7Zj/pNUMoTR34GGtttTs7FpdXN9q3oylMCUpTm3dMovzdMKpLEHaczcH8LxNxNqsYggDMGRprUxydQzzx6+lsvLr5DKpqJjXsFeGNV6b0RM+I+msrXFQKBHi4ILekElm6cocmKDnFFcgrrYRSITQ6FJu1DIf8dOzYsSN27dqFkpISZGRk4NChQ6iqqkKHDh0QEmLscJidnW22T3Z2tvgaY452qYn9TxhrKSqlAm4160LZo5lHbyCkXDOOnGlsKLA1j4+KA2CcWRUAbu0SLKnWpLZOwcYv/Co9wVOrwrIpPfDDY0MbTE5MTM08ja0sbqurRdeRkV+GU5nGDrIdA92deoG9tsSh45Pc3d3h7u6OgoICbN26Fa+99hpiY2MREhKC7du3o0+fPgCMTTYHDx7E/PnzHRkOYyJxiDEnKExGPLUqlFXq7TLUOL+0EgYyLubnb0NtTL8oX9zROwy/nLiK7mFe+Me4TjbHMjw+EP2ifBAX5IFnxnWR1NwU4qXFqUwdsooan0elKYgIiZcKsL1mWvizWcVQKwUMjw8EAPSK8LFLOaz5HJKgbN26FUSEzp0748KFC3jmmWfQpUsXzJkzB4IgYMGCBXj55ZcRHx+P2NhYLF68GGFhYZgyZYojwmHMTLXegCOXjJMxxfrb9ouQMUfw1KqRrauwy2RtphEzfm4uZvP1SPHuvX3x1t19GlwMsCm83dT4/rGhNu0bbFpZ3E41KJ/+cRHLfjpt9lyVnrD9bA4A43xGTB4ckqAUFRVh0aJFuHz5Mvz8/DB16lS88sorUKuNnaAWLlyI0tJSzJ07F4WFhRg2bBi2bNliMfKHMUf4+cRVZORfh6+bmm9GTFZMHUXzSpq/sJ4pQWnuGjLNTU6ay7SyuL3mQkm8dGMq+/sGRkFXXoUlG08BMNY23RzXdqeOdzYOSVCmT5+O6dOn1/u6IAh46aWX8NJLLzmieMbqRUR47/cLAICHhsVaXYeHsdbSKdgTiZcKcDKzqEnT0jdETFA8m9/ZtjWF+RinAcgosM9095cLjEtOPDQsFuO6h6Ckohov/3wGldUG9I7wEdcOYq1P3lPlMWZnJ64U4Xx2CVzVSjzQBpYjZ21Ln0hjp9HjGUXNPlZusbEWRk6r8NoiLsgDgOXU+7a6UpOgRNTMf+ShUWFU5yAAwC01/2XywD8fWbvy0/GrAIBRXYOszrvAWGsyddBMTC/AO9uTMbijPwbE2LYY3DU7NfG0tviaBCW3pAIFpZXNquEoq6xGXs0ioRG11uB6aXJ39I/2xf2DopsXLLMrrkFh7QYR4eeaBOWOXk2fVZOxlhIf5AGtWoHKagPe3HYej36RiLJK20b05Ba3jQTFXaMSazvOZ1tfz6epMguNtSeeGpXZD5QgLy0eGd4Bri48vFhOOEFh7caf6YW4Ungd7i5KjOSqXCZDKqXC7Iszr7TSYgXhprpRg+L8fSpM86icz2leM09GTfNOY8tbMHngBIW1G6bak9HdgnkiJiZbdZdF+GhXCkoqml6LkpFfhlmfHhJX3w6QMOeIXMUHG5t5kptZg3JZ7H/C8x85A05QWLtgMBB+OWFMUG7v1bzREYw50mMj4rD49m448vxodAhwR0FZFdbsu2ix3U/HMzHgld/w8Joj2HjsCkprkph3dyRj1/lr4naBTt7EAwCdgmpqUJqZoNTtIMvkjTvJsnbhyKUCZOnK4alRYXgnnueAyZe3mxoPDTOuefO30fH427pj+Hh3Kh4YHC2ueAwA3/95BdeKK/DbmWz8diYbWrUCIzsFYcsp80VXnb0PClCriaeRkTxZReUI9NTUO3fL5ZqhypygOAeuQWHtwk/HjYumjekeDI2Km3eYc7i9VxjigjxQdL0Kq/deNHsttWadnTt6hyHG3w3lVQaL5AQA/NtAH5S4IA8IgnH6ftP8LnV9/+dlDFq+HXe9/4d4buoyLXER7sMJijPgBIW1eXoD4ZcTxhv3Hdy8w5yIUiFgweh4AMB/96aiqMw4BX5FtR7pNV+2z0/sit//MRLfzBss1pZE+t34AlbbOM29nLi6KBFZ02+kvmYeUzNY0uUizF59GJXVBrPXdeVVOJmpAwD0CG98kULW+pz/nctYIw6m5SG3pALermoM5WmsmZO5rUcoOgd7ori8GuuPpAMA0vPKYCDA3UWJIE8NBEHAwFg//PzkMLwxrTd+XTACMwdHY8XUnq0cvf10EjvKWtaOXMorRdJl4+R2ggCk55fh28QMs232JudCbyB0DHTnRUKdBCcorM0zdY4d3z0ELip+yzPnolAIuLOfcWTPiSvGGoCUa6UAgI5BHhCEG/0tgr20+Ev/CLi6KPHS5B64e0BUywfsIDf6oVjWoGxKMjbh3hwfgBdu7wYAeHf7BZRX6cVtfq9ZDJBni3UefLdmbd75LOMvriFx/q0cCWO2MdUenM8yfjmn5hrf0x0C2s9q3A0lKLtrhlTf1jMU9yZEIcxbiyxdOdYeNNY4GQyEnTUjm27pwgmKs+AEhbV5+WXGqa3bwnBL1j6ZvpxTc0twIDUPn/1xEQDQIdCjFaNqWaa5UM5nl4CIzF5LralR6h7mBY1KiSdvNfbb+WDnBZRWVOP0VR2uFVfA3UWJm2J8WzZwZjNOUFibV1Cz9gavUsqcVbiPK9xdlKjSE+75+AByaqax79iOEpSOgR5QCEDR9Sqk5ZaKz+vKq8SRPbE1NUpT+0cg2t8NuSWVWLP/oti8MzQugEfxORFOUFibZjAQCq8bRz74unGCwpyTIAiIr6lFMfHUqDCgHdUGaNVKDO5obKZ99vsT0BuMtShpNbUngZ4aeNbME6NWKsTRTx/tSsXGmj4q3LzjXDhBYW1acXm1eCPzcePVi5nzMvVDAYBX7+qJw8+PRpCXthUjann/vrMn3F2UOJSWj1V7UgFArE2p2x9nUu9wxNfMIXOhZg2fkZ0DWzZg1iycoLA2zdT/xN1FyevvMKdWexbZ23uHtcv3c7S/O5bcYRyl83+/nsPJK0XipGwdAs0TFKVCwLIpPaBVG7/meoR7IdSbJ2hzJjzVPWvTCmoSFB9u3mFObsagaKw/nIH7B0fDQ9N+b93Tb4rE9jM5+PV0Np5afwzR/sbEpEOAZX+cQR38cfC50fj1VBYGxPi1dKismdrvu5y1C6YOsn7cQZY5udgAdxx/cWxrh9HqBEHA8rt64s/0QiTnlCC5pvkmtp4h196uaky7KbIlQ2R2wk08rE3L5xE8rA0RBMFsYrb2yt9Dg9en9ULtUxEX1H5GNLUXXIPC2rTCmrVL/LiDLGNtyi2dg/D9/CH4+fhVBHlpENOOJq1rLzhBYW1aPvdBYazN6hvli75R7WeodXvDTTysTeM+KIwx5pw4QWFtGvdBYYwx58QJCmvTTH1QfLkPCmOMORVOUFibZuqD4sd9UBhjzKlwgsLaNF4okDHGnBMnKKzN4oUCGWPMeXGCwtosXiiQMcacFycorM3ihQIZY8x5cYLC2izTQoHc/4QxxpwPJyiszRI7yHL/E8YYczqcoLA2iydpY4wx58UJCmuzeKFAxhhzXpygsDaLFwpkjDHnxQkKa7N4oUDGGHNenKCwNotH8TDGmPPiBIW1WQWlvFAgY4w5K05QWJvFCwUyxpjz4gSFtVm8UCBjjDkvTlBYm1R7oUDuJMsYY86HExTWJvFCgYwx5tw4QWFtUu2FAjUqXiiQMcacDScorE3KLLwOAAj01LRyJIwxxmzBCQprk05n6gAAXUO9WjkSxhhjtuAEhbVJp68aE5RunKAwxphT4gSFtUlnTAlKGCcojDHmjOyeoOj1eixevBixsbFwdXVFx44dsWzZMhCRuM3s2bMhCILZ3/jx4+0dCmunyqv0uJBTAoATFMYYc1Yqex9wxYoV+OCDD7BmzRp0794dR44cwZw5c+Dt7Y0nn3xS3G78+PFYvXq1+Fij4c6MzD4u5JSg2kDwcVMjxEvb2uEwxhizgd0TlH379mHy5MmYOHEiACAmJgZff/01Dh06ZLadRqNBSEhIk45ZUVGBiooK8bFOp7NfwKzNOXmlCICx/4kgCK0cDWOMMVvYvYlnyJAh2L59O86fPw8ASEpKwt69ezFhwgSz7Xbu3ImgoCB07twZ8+fPR15eXr3HXL58Oby9vcW/yMhIe4fN2pD9qcb3Ut8on9YNhDHGmM0Eqt05xA4MBgOee+45vPbaa1AqldDr9XjllVewaNEicZt169bBzc0NsbGxSElJwXPPPQcPDw/s378fSqXlpFrWalAiIyNRVFQELy/uY8BuMBgIN73yG/JLK7F+7iAkdPBv7ZAYY4zV0Ol08Pb2btL3t92beL755husXbsWX331Fbp3745jx45hwYIFCAsLw6xZswAA99xzj7h9z5490atXL3Ts2BE7d+7ErbfeanFMjUbDfVRYk5y+qkN+aSXcXZToF+3b2uEwxhizkd0TlGeeeQbPPvusmIT07NkTly5dwvLly8UEpa4OHTogICAAFy5csJqgMNZUu85fAwAM7hgAtZJH0TPGmLOy+x28rKwMCoX5YZVKJQwGQ737XL58GXl5eQgNDbV3OKwdqajWY93hdADAyM6BrRwNY4yx5rB7Dcodd9yBV155BVFRUejevTuOHj2KN998Ew8++CAAoKSkBEuXLsXUqVMREhKClJQULFy4EHFxcRg3bpy9w2HtyNoD6cjIv44gTw3u6hfe2uEwxhhrBrsnKO+++y4WL16Mxx57DDk5OQgLC8O8efOwZMkSAMbalOPHj2PNmjUoLCxEWFgYxo4di2XLlnE/E2YzXXkV3t2RDAB4akwnuLnY/a3NGGOsBdl9FE9LkNILmDmfjPwyvLsjGU+Mikekn1uT9nlty1m8vzMFHQPdsXXBcKi4/wljjMlOq47iYay5/vFtEg6m5WNPci72LzLvNE1EeH9nCval5MLPXYP/m9YbeaUV+GRvGgDg2QldOTlhjLE2gBMUJjt/phcAAK4WlUNvICgVN2aDPZiWj9e3nhMfT+sfgU1JmaioNmBgjB9Gdw1q8XgZY4zZH//UZLLj7eoi/v+xjAKz1z7746LZ419OXMV3f14GADx7Wxee2p4xxtoITlCYrJRUVCO35MaswTvO5oj/n3qtBL+ezgIATOhhXMfpmyMZMBAwqksQ+kXxxGyMMdZWcILCZCXtWqnZ499OGxOUbF05Zq8+DAMBN8cH4LaexjlzDDVdvEd04nlPGGOsLeEEhclKyrUSAECXEE+olQLOZRfjYGoe7v/vQaTnlyHKzw1vTOuNTsGeZvtx7QljjLUt3EmWyYopQekb5YtwH1dsP5uDBz49hMpqA0K8tFj7cAKCvbTwcVNDqRCgNxBc1Up0CfVs5MiMMcacCdegMFlJrWni6Rjojtt7G5txKqsN8Hd3wZcPJ4jzomhUSsT4G/+/d6Q3r7vDGGNtDN/VmWyUV+mxLyUXANAlxAtjuoXA390FXloVPn9oIOKCPMy27xxirDXpz6sWM8ZYm8NNPEw2fjyWiYKyKoT7uGJwR38oFQJ+fWo4FIIAX3cXi+2fvDUe3q5qPDSsQytEyxhjzJE4QWGyQET4bN9FAMADg6PFydn8Pepfn6lLiBeW39WrJcJjjDHWwriJh8nCkUsFOH1VB41KgbtvimztcBhjjLUyTlCYLJhqT6b0CbfanMMYY6x94QSFtbqsonJsOWmcIXbWkJjWDYYxxpgscILCWt3ag5egNxAGxvihW1jDy28zxhhrHzhBYa2qolqPrw+lA+DaE8YYYzdwgsJa1c/HryK3pBKh3lqM7R7c2uEwxhiTCU5QWKtaU9M59v5B0TwbLGOMMRF/I7BWczS9AEmXi+CiUuCeATy0mDHG2A2coLBWs/agse/JHb3CGpyQjTHGWPvDCQprNYfS8gEAU/qGtXIkjDHG5IYTFDsoq6xGWm5pa4fhVIquVyE9vwwA0DPcu5WjYYwxJjecoNjBou9P4Nb/24md53JaOxSncTpTBwAI93GFjxvPHMsYY8wcJyh2cC6rGAYCVm47DyJq7XCcwqnMIgBAj3CemI0xxpglTlDsQHe9CgCQdLkIe5JzAQC/nLiKhf9LQrauvDVDk61TNTUoPcK4eYcxxpglTlDsQFdeLf7/uzuSQUR48cdT+ObIZdz82u/cP8WKk1eMNSjduQaFMcaYFZygNJPeQCipMCYoCgE4fLEA6w9nIKe4AgBQWW3AJ3tTWzNE2Smv0iPlWgkAoDvXoDDGGLOCE5RmKqlVe3J3zWRjL246ZbbN/pS8Fo1J7lKvlcJAgLerGkGePP8JY4wxS5ygNJOu3Nj/xFWtxOOj4qFSCCivMgAAHhgUDUEAUq6VIof7ooiSc4oBAJ2CPSAIQitHwxhjTI44QWmmopoOsp5aFcJ9XDG1X4T42phuwegWauxjsT+Va1FMzmcbE5T4YM9WjoQxxphccYLSTKYaFC9XNQDgsVs6Qq0U4O6iRP9oXwzu4A8A+ONCrrhPZbUBhy/mI+VaCb48cAn/9+s5nLhcVG8ZpzN1yCupcOC/omWdzzb2P4kP8mjlSBhjjMmVqrUDcHbFNX1QvLTGUxnt747v5g+BQhDgrlHhli5B+O/eNGw4molx3UNwIDUP3/95BXmllWbHeXfHBSyd1B2zhsSIz1VU6/Hij6fx9aF0eGhUeGlyd9xVq4bGWSVnm5p4uAaFMcaYdVyD0kymOVBMNSgA0CvCBz1qpm8f0tEfIzsHolJvwENrjmDVnjTklVbCx00NtVJAuI8rbu0SBAB46afT+PVUlnicVbtT8fUh44J6JRXV+Od3x1FYZp7YOJvyKj0u1UxxHx/MNSiMMcas4xqUZjLNgeKpVVt9XRAELJvcA7e9swdllXrc0jkIdw+IxC2dAwEASoWxk+jT3yThh6NXMPeLRNx9UySeu60rvj6UAQBYNqUH3tp2HnmllbhSeN2pp4b/M70ARICPmxqBvIIxY4yxenCC0kxiDYq2/lMZ6eeGnf8YCUEQ4OduPbl4dWpPeLuq8dm+i1h/JAObT16FrrwanloVpvWPwLpD6cgrrUSOrgLdnXDx3y0nr2LtwXTsqxlyPaFHCI/gYYwxVi9u4mkmsQ+Kq/UaFBN/D029yQkAaFRKvDipO76ZNxgx/m5izcyUPuHQqpUI9tICgFNOnX8hpxh/W3cMe5JzoTcY1yr66y1xrRwVY4wxOeMEpZnEUTz1NPFINTDWD5v/NhzzhnfAwBg/zB3eAQAQ7GVsDsnWOddonspqA/627hgqqg0IrJmU7bGRHRHh69bKkTHGGJMzbuJpJl2teVDsxdVFiUW3dTV7LtCzpgal2LlqUFb+dh6nMnXwcVPjpyeGQaNSwLuR2ibGGGOME5RmqjsPiqOYalDkPiPtq5vP4rcz2UiI9cPgjv74cFeK8fm7eorNVIwxxlhjOEFpJt1183lQHCXYVIMi4yaea8UV+Hh3CgwEXMgpwdqDxiHS0/pHYHyP0FaOjjHGmDPhPijNVFzRUjUoxgQlx4FNPFcKr6OssrrxDevxy4mrqOkDi46B7gCAKD83vDCpuz3CY4wx1o5wDUoztVgNSk0Tz7XiCugNJM6fYi8Z+WUY+cZODIjxxbq5g206xo9JmQCAxbd3w1/6ReC7Py9jTLdgeGj4bcYYY0wa/uZoBoOBUFxu6iTr2BoUfw8NFAJgICCvpAJBdu7PceJKEfQGwp/phTAYCAqJCdC14gokXiqAIAATe4bC202NB4fF2jVGxhhj7Qc38TRD0fUqsUnDx82xCYpSIYjDdB3RD+VSnnH6+cpqAzKLrkve/8xVHQAgNsAdId7cGZYxxljzcILSDLk1Kwx7u6qhUSkdXp6pH8qhi/l2P3Z6fqn4/xdzyyTvf960AGAQLwDIGGOs+ThBaYZrNQlKgEfLrI0zuU84AGDFlrM4cbnIrsdOz7+RlKTllkjePznbuE8nXgCQMcaYHXCC0gzXik0JSsssejdnSAxGdw1GZbUBj36ZaNeVjU1NPACQZksNSo6xBiU+mGtQGGOMNZ/dExS9Xo/FixcjNjYWrq6u6NixI5YtWwYiErchIixZsgShoaFwdXXF6NGjkZycbO9QHC63xJggBHi2TIKiUAj4v+m9Ee3vhiuF17Fg/TEYDNT4jo2orDYgs/BGvxNrNSjF5VW4kGO9ZoWIcEGsQeEEhTHGWPPZPUFZsWIFPvjgA/znP//BmTNnsGLFCrz22mt49913xW1ee+01vPPOO/jwww9x8OBBuLu7Y9y4cSgvl/csqXWZ+qAEtlANCmDs7/LBjP7QqhXYee4a3tnR/MTuSuF11M5zLuaZ16AQER5ecwRjVu7CznM5FvtfLSpHcUU1VAoBsQHuzY6HMcYYs3uCsm/fPkyePBkTJ05ETEwM/vKXv2Ds2LE4dOgQAOOX3VtvvYXnn38ekydPRq9evfD5558jMzMTGzZssHc4DpVb08QT2EI1KCbdwrzwypSeAIC3tydbTRqkuJRn7CBrGomUkV+Gimq9+PrBtHwcTMsHEfDvX84gI78MJRXVSMstxZp9F/H3b5IAGEfwuKi41ZAxxljz2X0elCFDhuDjjz/G+fPn0alTJyQlJWHv3r148803AQBpaWnIysrC6NGjxX28vb2RkJCA/fv345577rE4ZkVFBSoqbgyt1el09g7bJrkt3Em2tqn9I5CYXoCvDqZjwfpj+O3pETb3hcmo6SB7U7QvjmUUIrekEgv/dxwJsf7ILanA5pNZ4rbns0tw82u/Wz3OqK5BNpXPGGOM1WX3BOXZZ5+FTqdDly5doFQqodfr8corr2DGjBkAgKws45ddcHCw2X7BwcHia3UtX74cS5cutXeozSb2QWnBJp7aXrijGw6k5iH1Win2peRhUu8wm45zucDY/yTSzw0zEqLx0JrD2HgsExuPZYrbKBUCZg6Oxuo/LkKlEFBtIKiVAm6K9sPwToEY3ikA3UK97PLvYowxxuyeoHzzzTdYu3YtvvrqK3Tv3h3Hjh3DggULEBYWhlmzZtl0zEWLFuHpp58WH+t0OkRGRtorZJu19CieujQqJQZE+yH1Wmm9HVib4nJNB9lwH1fc0iUIr97VC98cyYCPmxoBHhoEeGiQ0MEPN8cH4slR8fByVaOkvBpqlQA3F56MmDHGmP3Z/dvlmWeewbPPPis21fTs2ROXLl3C8uXLMWvWLISEhAAAsrOzERp6Y4Xb7Oxs9OnTx+oxNRoNNJrWSQLqQ0TIK22dPii1xQUZ5x1JuWZ7gnKlpgYlwtcVADB9QCSmD7CeAPq6G5uzvB08cy5jjLH2ze49GsvKyqBQmB9WqVTCYDAAAGJjYxESEoLt27eLr+t0Ohw8eBCDB9u2SF1rKLpehSq9ceiLfyv0QTHpGGQcNZPSjBqUK2INiptdYmKMMcaay+41KHfccQdeeeUVREVFoXv37jh69CjefPNNPPjggwAAQRCwYMECvPzyy4iPj0dsbCwWL16MsLAwTJkyxd7hOIypg6yXVtUi09zXJy7QOO9Iam6pTascl1fpxaaq8JoaFMYYY6y12T1Beffdd7F48WI89thjyMnJQVhYGObNm4clS5aI2yxcuBClpaWYO3cuCgsLMWzYMGzZsgVarfMsMrf1VDYAtPrCeOG+rnBRKVBZbcDlgjJE+0ubh+RqkXHuGVe1Er7cbMMYY0wm7J6geHp64q233sJbb71V7zaCIOCll17CSy+9ZO/iW0RSRiH+79dzAICHhsW2aixKhYAOAe44m1WMlGslkhMUU/+TcF9XCIK02hfGGGPMUXhWLRtsO50NAwGjuwZj+k2tP5qoY01HWVtG8lwpNM6BEu7DzTuMMcbkgxMUG+TXLNLXI9xLFrUOcYE1I3lySiXvW7sGhTHGGJMLTlBsYFpF2Net9Ubv1NaxGUONa8+BwhhjjMkFJyg2KCitAnBjTpDWZqpBuXCtxGzV6Ka4VLMwYKQfDzFmjDEmH5yg2KBArEGRx6iX2AB3CAJQWFaF/NLKJu9HRDifXQwA6BTs4ajwGGOMMck4QbFBgcyaeFxdlGITjZSOstm6ChSXV0OpEBAbIG30D2OMMeZInKBIREQoKJNXEw9Qe8r7pneUNdWexPi7tepkc4wxxlhdnKBIVFapR2W1cdp+uTTxAEDHQOlDjW8073g6JCbGGGPMVpygSGRq3nFRKeCqlk+tgy2LBpoSlHhOUBhjjMkMJygSFdY07/i5uchiDhSTYC/jispSOsmezzYmM9xBljHGmNxwgiKRKQHwkVHzDgB4ao3xFJdXNWl7IhKbg7iJhzHGmNxwgiKRqYnHT0YdZAHAS0xQqpu0fWZROUoqqqFSCIiRuH4PY4wx5micoEhUUCqvIcYmnlrjuo/F5dVNmqzN1P8kNsAdLip+GzDGGJMX/maSyDTEWH5NPMYEpVJvQEXNKKOGJPMIHsYYYzLGCYpEhTJt4nF3UcHUZ1fXhH4oNzrIcoLCGGNMfjhBkShfrEGRV4KiUAjw0Nxo5mlMMk9xzxhjTMY4QZHAYCCcvaoDAAR4yCtBAZreUdZgILEGhedAYYwxJkecoEiw5VQWknNK4KlRYUSnwNYOx8KNjrINN/FcKbyO61V6uCgViPHnVYwZY4zJDycoTaQ3EFZuOw8AeHBYrOyaeIAbNSi66w3XoJhG8HQIdIdKyW8Bxhhj8sPfTk300/FMJOeUwEurwkM3x7Z2OFY1tQaFm3cYY4zJHScoTVCtN+Dt35IBAHOHdxBrKuSm9lwoDRE7yAZxB1nGGGPyxAlKE/yYlInU3FL4uKkxe6g8a0+Apk93fz6HFwlkjDEmb5ygNKJKb8Db2421J/OGdxSH8sqRqQZF10ANisFQew0erkFhjDEmT5ygNGLD0Su4lFcGf3cXzBwc3drhNMjLtaaTbAM1KBkFZSivMsBFpUA0r8HDGGNMpjhBaQAR4b970gAAD9/cAe4yrj0BmtYHxdRBtmOgB5QKoUXiYowxxqTiBKUBe5JzcS67GO4uStyXENXa4TSqKX1QLuWVAjAOMWaMMcbkihOUehgMhJW/Gec9mT4gEt6u8hy5U1tTalDya1ZjDvTQtEhMjDHGmC04QanH+iMZOJpeCHcXJeYN79ja4TSJl9hJtv4aFFOCIrfFDhljjLHaOEGxIq+kAq9uPgsAeHpsZ4R4a1s5oqbxrDWTbJXeYHUbU4LiywkKY4wxGZN3r89WsnzzWRRdr0K3UC/MkvnIndp8apqhiq5XodeLv6J/tC8GxPhhYKwf+kb5QKtWigmKPycojDHGZIwTlDoOpeXjf4mXIQjAy3f2cKq1agI9NZg5OBobj2Wi6HoV9l7Ixd4LuQAAtVLA8PhAZBeXAwB8ZbiWEGOMMWbCCUotVXoDnt9wAgBwz4Ao9IvybeWIpBEEAS9N7oEX7+iO8znFOJyWj4Np+TiUlo+c4gpsP5sjbuvvwQkKY4wx+eIEpZZP9qbhfHYJ/N1d8M/xnVs7HJspFAK6hHihS4gXHhgcAyLCvasO4EBqvrgNd5JljDEmZ87TftECBsT4oUuIJxbd1hU+bagJRBAExNSZNdbHCYZNM8YYa7+4BqWW/tG++OmJYW1yhtVIPzfx/33c1E7Vt4Yxxlj7wwlKHW31i7t2gsLNO4wxxuSubX4bMwtRtROUNtR8xRhjrG3iBKWdqJ2gyH3RQ8YYY4wTlHbC1+1Gp9jrlfpWjIQxxhhrHCco7YQg3Oj4W1JR/2KCjDHGmBxwgtIOdQvzau0QGGOMsQZxZ4R25KcnhuHbIxl48tb41g6FMcYYaxAnKO1Ij3Bv9Aj3bu0wGGOMsUZxEw9jjDHGZIcTFMYYY4zJDicojDHGGJMdTlAYY4wxJjt2T1BiYmIgCILF31//+lcAwMiRIy1ee/TRR+0dBmOMMcacmN1H8Rw+fBh6/Y2ZSk+ePIkxY8Zg2rRp4nOPPPIIXnrpJfGxm5sbGGOMMcZM7J6gBAYGmj1+9dVX0bFjR4wYMUJ8zs3NDSEhIfYumjHGGGNthEP7oFRWVuLLL7/Egw8+aDbV+tq1axEQEIAePXpg0aJFKCsra/A4FRUV0Ol0Zn+MMcYYa7scOlHbhg0bUFhYiNmzZ4vP3XfffYiOjkZYWBiOHz+Of/7znzh37hy+//77eo+zfPlyLF261JGhMsYYY0xGBCIiRx183LhxcHFxwaZNm+rdZseOHbj11ltx4cIFdOzY0eo2FRUVqKioEB/rdDpERkaiqKgIXl68rgxjjDHmDHQ6Hby9vZv0/e2wGpRLly7ht99+a7BmBAASEhIAoMEERaPRQKPR2D1GxhhjjMmTwxKU1atXIygoCBMnTmxwu2PHjgEAQkNDm3xsU6UP90VhjDHGnIfpe7spjTcOSVAMBgNWr16NWbNmQaW6UURKSgq++uor3HbbbfD398fx48fx1FNPYfjw4ejVq1eTj19cXAwAiIyMtHvsjDHGGHOs4uJieHs3vHitQ/qg/Prrrxg3bhzOnTuHTp06ic9nZGTg/vvvx8mTJ1FaWorIyEjceeedeP755yX1JTEYDMjMzISnpycEQRD7pGRkZDTpOFK3t2UfOZYhx5haogyOST5lyDGmlihDjjG1RBkck3zKkEtMRITi4mKEhYVBoWh4ILFDalDGjh1rtfomMjISu3btavbxFQoFIiIiLJ738vKSlOhI3b6tlCHHmFqiDI5JPmXIMaaWKEOOMbVEGRyTfMqQQ0yN1ZyY8Fo8jDHGGJMdTlAYY4wxJjttIkHRaDR44YUXmjwUWer2baUMOcbUEmVwTPIpQ44xtUQZcoypJcrgmORThhxjaoxDJ2pjjDHGGLNFm6hBYYwxxljbwgkKY4wxxmSHExTGGGOMyQ4nKIwxxhiTHU5QGGOMMSY7nKAwxhhjTHY4QWGMMTshIuj1eqcvoyWkpaWhurpaVsd3dEy2lNESM4FILaMlzhPQhhKUM2fOYPXq1Th79iwA4OzZs5g/fz4efPBB7Nixw277ODouOcb03//+F7NmzcLq1asBAOvXr0fXrl3RoUMHvPDCC00ut6Ebq9Qytm3bhhdeeEGMd/fu3ZgwYQJGjRolHqO5WqIMOcYkx+stt5iqq6vx/PPPY8SIEeJrr7/+Ojw8PODm5oZZs2ahsrKySTFlZ2cjPT3d4nlbypDbeWpI586dkZyc3OTtAWDnzp24fv26w47v6JhsKUOj0eDMmTOSYpKaQEgtw5bzZBOSsV9//ZWWLFlC27dvJyKiXbt20fjx4+mWW26hTz/9VNxu8+bN5OLiQn5+fqTVamnz5s0UGBhIo0ePplGjRpFSqRSP0Zx9pMRkSxlyjGnlypXk7u5Od911F4WGhtLLL79M/v7+9PLLL9PSpUvJy8uLPvroI7Myqqqq6F//+hcNHz6clixZQkREr732Grm5uZGLiwvNnDmTKioqbC7jiy++IJVKRf369SMPDw9avXo1+fj40MMPP0wPPvggubi40LfffmtxnlatWkUzZ84Uz8m6deuoS5cuFBsbK8bZ3DKkXAs5xiTH6y3HmJ5//nkKDg6mp59+mrp160aPPvooRUZG0pdffklr1qyh8PBwWrFihVlMOp2OZsyYQVFRUWL5jz32GAmCQAqFgoYPH05FRUU2lyHH80REdOedd1r9UygUNHr0aPFxU6jVajp9+nSzj+/omGwp46mnnrL6p1AoaObMmeLj5sQktQx7nidbyDZBkXIzHjx4MP3rX/8iIqKvv/6afH196bnnnhOP9eyzz9KYMWPMjm/LPlK/IKSWIceYunTpQmvXriUioj///JNUKhX997//FV//73//S/379zeLSeqNVWoZffr0obfffpuIiH777TdydXWlN998U3z9jTfeoKFDh5rFJPXGaksZUq+FHGOS4/WWY0wdOnSgTZs2ERFRcnIyKRQKWrdunfj6+vXrqUePHmYxPf7449SlSxd65513aOTIkTR58mTq0aMH7d27l3bt2kXdunUz+yxKLUOO54mISBAEGjFiBM2ePdvsT6FQ0JQpU8THtfXt29fqnyAI1LVrV/Gxrcd3dEy2lCEIAvXp04dGjhxp9icIAg0YMIBGjhxJt9xyi1lMUhMIqWXYcp7sSbYJipSbsZeXFyUnJxMRkV6vJ5VKRX/++ae47YkTJyg4ONjs+LbsI/ULQmoZcozJ1dWVLl26JD7WaDR08uRJ8XFycjL5+PiYxST1xiq1DHd3d0pNTRUfq9VqSkpKEh+fOXOG/P39zWKSemO1pQyp10KOMcnxessxJq1WS+np6WaPz5w5Iz5OTU0lT09Ps5giIyNpx44dRER05coVEgRBjJGI6KeffqLOnTvbXIYczxOR8YdQRESERW2dSqWiU6dOkTUqlYrGjx9PL774ovj3wgsvkEKhoMcee0x8ztbjOzomW8pYvnw5xcbGWtSSNxST1ARCahm2nCd7km2CIuVm7OXlRRcuXBBf8/DwoJSUFPHxxYsXSavVmh3fln2kfkFILUOOMfn7+5tVFUZERNDFixfFx8nJyeTh4WEWk9Qbq9QyfHx86OzZs/X+G1JTU8nNzc0sJqk3VlvKkHot5BiTHK+3HGMKDg6m48ePi4+HDBlCly9fFh+fOXOGvLy8zGLSaDRmMbm5udG5c+fExxcvXjS7flLLkON5MklLS6OhQ4fSXXfdRfn5+UTU8Jfc3r17qWPHjrRkyRLS6/Xi8/XtI/X4LRGTLWUcOnSIOnXqRH//+9+psrKy0e1tSSCklmHLubUX2XaSVavVZh3ANBoNPDw8zB6bOibFxMSYddjZv38/oqKixMfp6ekIDQ01O74t+0iJyZYy5BhTly5dcPz4cfFxRkYGoqOjxcdnz55FTEyMWUze3t4oLCwUH/fr1w+enp7i44qKCgiCYHMZcXFxYgdfALhy5QpiY2PFxykpKYiIiDCLyc3NDaWlpeLjwMBAs/MEwKxTmS1lSL0WcoxJjtdbjjF169YNf/75p/j4jz/+QHh4uPj4xIkTiI+PN4vJ398f165dEx9PnjwZPj4+4uOSkhKzVWClliHH82QSExOD3bt3o0ePHujduze2bt1qdty6hg4disTERJw/fx5DhgxBSkpKvdvacvyWiMmWMgYMGIDExERcu3YNN910E06ePNng9vfccw/27NmDTz75BFOnTkVBQUGjMUktw5Zzay+qFinFBqabcefOnQEYb8a1Pzi1b8bz588363Heo0cPs2Nt3rwZo0aNMnvOln2kxGRLGXKMacWKFXB3d0d90tPTMW/ePLPnTDfWnj17AjDeWGure2OVWsZzzz0HX19f8bGXl5fZ9keOHMH06dPNnjPdWLt27QrAeGOtre6N1ZYypF4LOcYkx+stx5g+/PBDqNXqerevqqrCwoULzZ7r1asXDh8+jH79+gEAvvrqK7PXDx8+LL4XbClDjuepNoVCgaVLl2LMmDGYOXNmo0Olvb298fXXX2P16tUYNmwYli5d2uAXo9Tjt0RMtpTh4eGBNWvWYN26dRg9enSj25sSiKVLl6J3795YtWpVozFJLcOWc2sXDq+jsdH3339Pu3btqvf15cuX0/PPP9+CEXFMTXXu3DmzZoW61q5dS+vXr2/BiIzVs0ePHq339ffee4/efffdZpUh9VrIMSZbyPF6yzGmvLw8KigoqPf1X375hX7//fcWi4eo9c5TcXExHTt2zGyEUEPOnz9PAwYMIEEQmtS0IPX4LRGTLWVkZGTQhg0bqKSkpEnb79mzh2JjY0mhUDQ5Jqll2HJubSUQtcAsMIwxxlgzGAwGFBcXw8vLq8WaGBojx5hKSkqQkpKCrl27wsXFpbXDaRbZ9kGRKikpCS+//DLef/995Obmmr2m0+nw4IMP2mUfR8clx5jef/99jB49GtOnT8f27dvNXsvNzUWHDh2aHZPUMn755Rc8/PDDWLhwoVm/DAAoKCiwaAqzRUuUIceY5Hi95RaTqXklLi4OAwcOxKeffmq2fXZ2NpRKpdVyDAaD1eeJyGzCNlvKkNt5Mqn9vq07IVhT37cKhQLe3t5WEwFbju/omGwpwx73fw8PD/Tu3bve5ERqGfY4TzZzeB1NM/z888/00EMP0TPPPGPWs5yIKD8/XxyvvXXrVnJxcaHu3btTVFQU+fv7i8P5iIiysrJIoVCY7W/LPlJisqUMOcb09ttvk5ubG/31r3+l+++/n1xcXOjf//53gzFVVlbSM888Qx07dqQBAwbQJ598YvZ6c8tYu3YtKZVKmjhxIg0bNoy0Wi19+eWXjZ6n9957j2699VaaNm0a/fbbb2avXbt2jWJjY5tdhpRrIceY5Hi95RjTCy+8QMHBwfT666/Tv/71L/L29qa5c+eabS8IglmZRUVFNG3aNNJqtRQUFESLFy+m6upqu5Uhx/NE5PjPqy3Hl+M9xB73/7qTszX3/m/rebIX2SYoUk7M4MGDxQmODAYDrVixgjw8PGjz5s0W25rYso/UiyW1DDnG1K1bN3GuDiKiP/74gwIDA2nx4sX1xiT1xiq1jNpzexAZ52pwd3cX5xCxFpPUG6stZUi9FnKMSY7XW44xxcXFmc1hkpycTHFxcTR79mwyGAxWY3ryySepU6dO9O2339KqVasoOjqaJk6cKLbl141JahlyPE9Ejv+82nJ8Od5D5Hj/t+U82ZNsExQpJ6bu3B5Exgvn7u5OmzZtsnoSbdlH6sWSWoYcY3J1daW0tDSz7U2TuT377LNWY5J6Y5VaRt25PYiIduzYQR4eHvTBBx9YjUnqjdWWMqReCznGJMfr7SwxXb58mTp16kQzZsygK1euWMQUFRVl1gn22rVrNHDgQBo7diyVl5c3uww5nicix39ebTm+HO8hcrz/23Ke7Em2CYqUExMYGEhHjhyxOMbXX39Nbm5u9MEHH1icRFv2kXqxpJYhx5giIyNp9+7dFtufOnWKgoODaebMmRYxSb2xSi0jNDSU9u/fb7H9zp07ycPDg/71r381KaaGbqy2lCH1WsgxJjlebznGFBsba1HFT2ScIbZTp040ZswYqzHVvRY6nY4GDx5Mo0aNotTU1GaVIcfzROT4z6stx5fjPUSO939bzpM9yTZBkXJixowZQ6+//rrV43z11VekVqstTqIt+0i9WFLLkGNM9957Ly1YsMDq9idPnqTAwECLmKTeWKWWMXnyZIuF9Ex+//13cnd3t4hJ6o3VljKkXgs5xiTH6y3HmB566CF68MEHrW5/+fJliouLs4ipc+fO9PPPP1tsX1xcTIMHD6bevXs3qww5nicix39ebTm+HO8hcrz/23Ke7Em2CYqUE/P999/X+6EhMlZhjRw50uw5W/aRerGkliHHmJKSkqyuwmty4sQJs/UniKTfWKWWsXPnTrO237p27NhhsYCV1BurLWVIvRZyjEmO11uOMV28eJG2bNlS7/ZXrlyhzz77zOy5J554gv7yl79Y3V6n01FCQoJZTFLLkON5InL859WW48vxHiLH+78t58meZJugtPaJsYZjahpbbt6OZsuNVSqp10KOMdlCjtdbjjHl5+ebrbVUl06no507d7ZgRPI8T0Qt89mQSo4xyfH+b09taqK26upqnDp1CllZWQCAkJAQdOvWrcHpom3Zx9FxyTGmQ4cOYf/+/WbbDx48GAMHDrRbTFLLyMrKwsGDB822T0hIQEhIiN1iaoky5BiTHK+33GKqrKzEhg0bLLYfMmQIJk+ebJdJsmwpQ27nycTR71tbji/He4gc7/+tdR+UfYLSlBNjMBiwZMkSvPfeeygqKjLb39vbG48//jiWLl0KhULRrH2kxGRLGXKMKScnB3fddRf27duHqKgoBAcHAzBOEpWeno6hQ4fiu+++Q1BQkNmxpNxYpZZRWlqKefPmYd26dRAEAX5+fgCA/Px8EBHuvfdefPTRR3Bzc7M4T029sTanDKkfZjnFJMfrLceYLly4gHHjxiEzMxMJCQlm2x88eBARERHYvHkz4uLizGLKzc3Fp59+ajWm2bNnIzAwUNxWahlyPE+A4z+vthxfjvcQOd7/m3Oe7KJ1Km4aV1JSQjNmzCClUkkqlYqCgoIoKCiIVCoVKZVKuv/++6m0tJSIiJ555hkKDAykDz/8kNLS0qisrIzKysooLS2NPvroIwoKCqKFCxeaHd+WfaTEZEsZcoxp6tSpNHjwYDp79qzFNTp79iwNGTLEol09OTmZOnToQFqtlkaMGEHTp0+n6dOn04gRI0ir1VJcXBwlJyfbXMZDDz1E8fHxtGXLFrOJrqqrq2nr1q3UqVMnevjhh82Ok52dTUOHDiVBECg6OpoGDhxIAwcOpOjoaBIEgYYNG0bZ2dnNKkPqtZBjTHK83nKMafTo0TR58mQqKiqy2L6oqIgmT55MY8eONXv+0KFD5OvrS+Hh4TRr1ixauHAhLVy4kGbNmkURERHk5+dHhw8ftrkMOZ4nIsd/Xm05vhzvIXK8/9tynuxJtgmKlBMTHBzcYDvqli1bKCgoyOw5W/aRerGkliHHmDw8POjPP/+sd/sjR46Qh4eH2XNSb6xSy/Dx8aE//vij3u337t1LPj4+Zs9JvbHaUobUayHHmOR4veUYk6urK504caLe7Y8fP06urq5mzyUkJNDcuXPJYDBYbG8wGGju3Lk0aNAgm8uQ43kicvzn1Zbjy/EeIsf7vy3nyZ5km6BIOTFubm50/PjxerdNSkoid3d3s+ds2UfqxZJahhxj8vf3b7Dj3u+//07+/v5mz0m9sUotw8vLy+yXZl2HDh0iLy8vs+ek3lhtKUPqtZBjTHK83nKMKTQ01GyCs7p+/PFHCg0NNXtOq9VaLDVQ25kzZ0ir1dpchhzPE5HjP6+2HF+O9xA53v9tOU/2JNvFAg0GQ4OdzFxcXMRFt0aOHIl//OMfFgsfAcY233/+858YOXKk2fO27CMlJlvKkGNMd999N2bNmoUffvgBOp1OfF6n0+GHH37AnDlzcO+995odx8fHBxcvXqw3posXL8LHx8fmMm6//XbMnTsXR48etTj20aNHMX/+fNxxxx1mz2s0GrNj11VcXAyNRtOsMqReCznGJMfrLceYHn74YcycORMrV67E8ePHkZ2djezsbBw/fhwrV67E7NmzMXfuXLMyQ0JCcOjQoXpjOnTokNinw5Yy5HieAMd/Xm05vhzvIXK8/9tynuzKYalPM913333Ut29fqxnrn3/+Sf3796cZM2YQEVF6ejr16NGDVCoV9e3bl8aPH0/jx4+nvn37kkqlol69elF6errZMWzZR0pMtpQhx5jKy8vp0UcfJRcXF1IoFKTVakmr1ZJCoSAXFxeaP38+lZeXm5W7ePFi8vX1pTfffJOSkpIoKyuLsrKyKCkpid58803y8/OjF154weYy8vPzafz48SQIAvn5+VGXLl2oS5cu5OfnRwqFgiZMmEAFBQVmMT322GMUHR1N33//vVl1dlFREX3//fcUExNDjz/+eLPKkHot5BiTHK+3HGMiInr11VcpNDSUBEEghUJBCoWCBEGg0NBQWrFihcX5/s9//kMajYaefPJJ2rhxIx04cIAOHDhAGzdupCeffJJcXV3pvffes7kMuZ4nR39ebTm+HO8hcrz/23Ke7Em2o3gKCgpw3333YevWrfD19TXr0V9YWIhx48bhq6++ErN7g8GArVu34sCBAxa9q8eOHWu157PUfaTGZEsZcowJMP5CSkxMNNu+f//+8PLysnb5sGLFCrz99tvIysoSlyInIoSEhGDBggVYuHBhs8s4c+aM1X9Dly5dLLatqKjAggUL8Omnn6K6ulr81VFZWQmVSoWHHnoIK1euNPsFJLUMqddCjjHZei1a4nrLMSYASEtLM9s+Nja23m3Xr1+PlStXIjExEXq9HgCgVCrRv39/PP3005g+fXqzy5DreXL051XK8VsqJqllyPX+b8u5tQfZJigmrXViOCb7kHJjbQm23Filknot5BiTreR2vQF5xlRVVSVWswcEBNh1jgtbyfE8tcRnoy3EJNf7f7M5rG6mFej1+nqfv3Tpkt32cXRccouprKyM9uzZQ6dOnbLY/vr167RmzZpmx2NLGRkZGVRcXGzxfGVlJe3atavZMbVUGVI5OiY5Xm85xpSZmUlffPEF/fzzz1RRUWH2WklJCS1durTZMUktQ47nycTR71tbji/He4jc7v9ErXcflH2C0pQTU1RURNOmTSOtVktBQUG0ePFisyFX1paEtmUfKTHZUoYcYzp37pw4zl+hUNDw4cPpypUrjcYk5cYqtYzMzEwaMGAAKRQKUiqV9MADD5j92+uLScqN1dYyiKR9mOUWkxyvtxxjOnToEPn4+JCXlxe5urpSXFyc2TT29cV07NgxWrZsGb333nt07do1s9eKiopozpw5Npchx/NkOr4jP6+2HF+O9xA53v+bc8+xB9kmKFJOzJNPPkmdOnWib7/9llatWkXR0dE0ceJE8cOWlZVFgiCYHd+WfaReLKllyDGmKVOm0MSJE+natWuUnJxMEydOpNjYWDHLtvYGlXpjlVrGzJkzKSEhgQ4fPkzbtm2j/v3700033UT5+fn1niepN1ZbypB6LeQYkxyvtxxjGj16NM2ZM4f0ej3pdDqaP38++fv7i50VrcW0detWcnFxoe7du1NUVBT5+/vTjh076o1JahlyPE9Ejv+82nJ8Od5D5Hj/t+U82ZNsExQpJyYqKop+//13cd9r167RwIEDaezYsVReXm71Q2PLPlIvltQy5BhTUFCQ2bh5g8FAjz76KEVFRVFKSorVmKTeWKWWERYWRgcPHhQfl5eX0x133EF9+vShvLw8qzFJvbHaUobUayHHmOR4veUYk6+vL507d86szOXLl5Ovry8dOnTIakyDBw+m5557Tjz+ihUryMPDgzZv3mw1JqllyPE8ETn+82rL8eV4D5Hj/d+W82RPsk1QpJwYV1dXSk1NNdtfp9PR4MGDadSoUZSammpxEm3ZR+rFklqGHGPy9PSk06dPU11//etfKSIignbv3m0Rk9Qbq9Qy3N3d6fz582bbVlVV0ZQpU6hXr150/Phxi5ik3lhtKUPqtZBjTHK83nKMydfXl5KSkiy2f/3118nHx4e+//57i5i8vLzowoULZs+tXbuW3N3dadOmTVYTFCllyPE8ETn+82rL8eV4D5Hj/d+W82RPsk1QpJyYzp07088//2xxjOLiYho8eDD17t3b4iTaso/UiyW1DDnGNGDAAPr8888tticy3pR8fHys3vSk3FilltGzZ0/63//+Z7Gt6d8dFRVlEZPUG6stZUi9FnKMSY7XW44x3XzzzfTBBx9Y3X7FihWk0WgsYgoMDKQjR45YbP/111+Tm5sbffDBB80qQ47nicjxn1dbji/He4gc7/+2nCd7km2CIuXEPPHEExYLVJnodDpKSEiwOIm27CP1YkktQ44x/fvf/6YJEyZY3Z6IaP78+RZtkFJvrFLLWLhwocVCbCZVVVU0adIki/Mk9cZqSxlSr4UcY5Lj9ZZjTKtWraL777+/3u1fffVViomJMXtuzJgx9Prrr1vd/quvviK1Wm0Wk9Qy5HieiBz/ebXl+HK8h8jx/m/LebIn2SYoUk5Mfn6+WceuunQ6ncX6EbbsI/ViSS1DjjHZwpabtxRVVVVWFzer/frFixfNnpN6Y7WlDKnXQo4x2cLR19sWcozp+++/pwULFtT7+tq1a2nkyJEtGFHLnCdHf15tOb4c7yFyvP/bcp7sSbYTtVVXV6OsrKzeyW+qq6tx5coVREdHc0wyi6m9kuO1kGNMjDH7aOufb9kuFqhSqRqcmU+lUjX5pB85cgS7d++WVL61fewZky1xyTGm999/Hy+99FKTt7eF1DI2btyIzz//3IERWS/D3tdCjjHJ8XrLMabnnnsODz74oAMjkl6GHM8T4PjPqy3Hb617SEPkeP93+HlyWN2Mg23YsKHJsyJ26dJFcjW2LftIicmWMuQY06hRoyg2NlZSTIsWLTKbkMreZXTu3FnyeXrvvfckzfxpSxlSr4UcY5Lj9ZZjTDNnzqRbbrlFUkxS95G6vRzPE5HjP6+2HF+O9xA53v9tOU9SyLaJpzFdunRBcnKyuOBWQzIzM1FVVSUpk7RlHykx2VKGHGOyxaxZs5CRkYEdO3Y4rAypbr31VqSlpSE1NdVhZUi9FnKMyRZyvN5yjOm5557D1atXsXr16tYORSTH8wS0zGdDKkfH1Fbu/1I4bYLCGGOMsbZL1doB2JNer4dSqRQfHzx4EBUVFRg8eHCTVwudM2cOXnnlFYSFhTkqTEllVFVV4eLFiwgKCoK3t7dD4mmojIqKCigUCvH8paSk4NNPP0V6ejqio6Px0EMPNXvVU6llfPfdd5gwYQLc3NyaVW5DWqIMW+Tk5ODkyZPo378/vL29kZ2djTVr1sBgMGDixIno2bOnXcrZsWMH9u7di6tXr0KhUKBDhw6YNGkS4uPj7XJ8qWVUVlZiw4YN2L9/v9mKrUOGDMHkyZPh4uLS7HjsWUZ2djY++ugjLFmypNlxSS3j8uXL8PHxgYeHh9nzVVVV2L9/P4YPH97ssu1ZRmlpKRITE+0Sl9TjGwwGKBSWXTENBgMuX76MqKioZpcvtQx7fI81prlljBo1CqtXr3Z8TYvDGo/swGAwUGpqKlVVVRERUUVFBa1bt47WrFljttBWZmYmDR06lJRKJQ0fPpzy8/Np4sSJJAgCCYJAnTp1oszMTLNjJyUlWf1Tq9X0ww8/iI+b4pZbbrE61EpqGStWrKCysjIiIqqurqa///3v5OLiQgqFglQqFc2ZM4cqKysbjSc1NZV+/fVXOnHihMVrUssYMWIEffvtt0REtHfvXtJoNNSrVy+6++67qW/fvuTm5kb79u0zKyMjI8Ps+uzevZvuu+8+GjZsGM2YMcNie6llCIJAXl5e9Mgjj9CBAwcaPR9ERG+88Yak4XC2lPG///2PSktLm1wGkXHxuE8++YRSUlKIiOjkyZM0f/58mjdvHm3ZssVs299//53c3d1JEAQKCQmhY8eOUUREBMXHx1Pnzp1Jo9HQ1q1bLcrIzs6m7du3U2FhIREZp79esWIFLV++3GxmTNO2AwcOFN8PCoWC+vfvTyEhIaRUKumZZ56x+u8oKyujTz75hObMmUPjx4+n2267jR5//HH67bffrMYjpYzk5GTq0KEDabVaGjFiBE2fPp2mT59OI0aMIK1WS3FxcZScnGxRzrVr12jFihU0ZcoUGjRoEA0aNIimTJlCr732GuXk5NiljPocO3ZMctt8enq6pP4edcuQ4wJ4tvw7miI/P7/JfSusHV+uC/NJ/R4javr3pC1lbNy40eqfUqmk//znP+JjR5FtgnL27FmKjo4mhUJBcXFxlJqaSv379yd3d3dyc3OjgIAAcQa9Bx54gIYMGUI//vgj3X333TRkyBC6+eab6fLly3Tp0iUaOnQo/fWvfzU7vmnBJ9OFqf1ner7uG1TqxZJahkKhoOzsbCIyzuTo6+tLn376KZ06dYq+/PJLCgoKohUrVpjFNH/+fPHDUlZWRlOnTjU79i233GL2YZJahpeXl3ieR4wYQU899ZRZ+c8//zwNHTrU7LmBAwfSpk2biMjYSUuhUNCkSZPon//8J915552kVqvF120pQxAEeumll6hv374kCAJ1796dVq5cSbm5uVQfQRBIqVTS6NGjad26dRartlrb3pYypCQ13333HSmVSvL39ycPDw/atm0b+fj40OjRo2ncuHGkVCpp7dq14vbDhg2jv/71r1RcXEyvv/46hYeHm72v//GPf9CQIUPMypCa1Nx99900ZcoUKioqovLycnr88cdp5syZRES0fft28vf3p7feesusjOTkZIqOjqagoCCKjIwkQRBo4sSJlJCQQEqlkqZNmybePG0pY/To0TR58mSr8zEUFRXR5MmTLeaCOHToEPn6+lJ4eDjNmjWLFi5cSAsXLqRZs2ZRREQE+fn50eHDh20uo74fH6a/9evXN/uLWmoZ9loAr/YXlD0WrJT677b3Pta2lePCfLZ8j0n5nrSljIa+w2p/lzmKbBOUyZMn06RJk+j48eO0YMEC6tq1K02ePJkqKyvF9QZMEwyFhobS/v37iYgoLy+PBEEw++W2fft26tChg9nxe/fuTRMnTqQzZ87QxYsX6eLFi5SWlkYqlYq2bdsmPleb1IsltQxBEMTkoW/fvvTRRx+Zlf/ll19S9+7dzZ6rnXAsWrSIIiIiaMeOHVRaWkp79+6ljh070rPPPmtzGe7u7nTmzBkiIgoODqZjx46ZbX/hwgXy8PAwe87d3V1c7yEhIYFeffVVs9ffffdd6tu3r81l1P43HDlyhObPn08+Pj6k0Who2rRp9Ouvv1JdgiDQ6tWrafLkyaRWq8nf35/+9re/Wa1lak4ZUpKafv360csvv0xExunOfXx86KWXXhJff+ONN6hPnz7i49pruVRVVZFKpaKjR4+Kr58/f568vb3NypCa1Hh5eZlN5FRSUkJqtVr84v7iiy+oc+fOZmVMmDCB5s2bRwaDgYiMk3uZJrQ6f/48xcTE0AsvvGBzGa6urvVeJyKi48ePk6urq9lzCQkJNHfuXDGm2gwGA82dO5cGDRpkcxn2/IFj+lu5cqXZPlLLkOMCeETG6fQb+vPy8rJaw9HQ3549e8R9bDm+HBfms+V7TMr3pC1ljB8/niZOnCjeC01UKpXVGjd7k22CEhgYKN58S0pKSBAE2rNnj/j6H3/8QVFRUUREpNVqKT09XXzN3d3drDr20qVLFjewiooK+tvf/kbdunUTV+4kavjES71YUssQBEGsevb397e4YaamppKbm5vFPqZ4evToQV999ZXZ6xs3bqROnTrZXMaoUaPotddeIyKiIUOGWFSr/u9//xOvg4m3t7fYdBUUFGTRVHbhwoVmlVH732xy/fp1+vzzz2nkyJGkUCgsZr+svU92djatWLFCHFI3YMAA+vjjj0mn09mtjKYkNe7u7pSWlkZExi9NtVpt1uSSkpJilpgFBASIX+ylpaWkUCjEmw2R8Rd3QECAWRlSk5rAwECz92ZZWRkpFArKy8sTY9JoNGZluLm5mf1Kq6ioILVaLSZmGzZsMDtXUssIDQ01q3Gr68cff6TQ0FCz57RarZj0WnPmzBnSarU2l+Hv70+ffPKJ+COj7t/PP/9s8QUn9QeO1DLkuAAekfH98fe//50+++wzq39Lly6t91zV91f7XNlyfDkuzGfL95iU70lby3jzzTcpMjLS7PPR7hMUV1dXMYsnIvLw8DBbCTQ9PV28iUVFRZm9cf75z3+KNzsiYxVf3Ru3yS+//EIRERH073//m/R6faMn3paL1dQyBEGgV155hd5++20KDQ01a88kMn4B+fr6WuxjSjhqf4GZXLx40eKXn5Qy9u3bR97e3vTCCy/Qu+++SwEBAfT888/T2rVracmSJeTj42PR7DRp0iSx1mbcuHH09ttvm72+atUqio+Pt7mM2rVG1iQnJ4vL2tf+d1vbZ/fu3TRr1ixyd3cnd3d3u5fRUFITEhIiLh6Xn59PgiCY/eI6dOgQhYSEiI8nT55Mt99+O+3du5fmzp1LN910E02cOJFKSkqotLSU/vKXv9D48ePNypea1Nx55500depUKikpocrKSlqwYAHFxcWJrx84cMAsJiLjjTsxMVF8XFBQQIIgiAlfamqqWcIhtYzFixeTr68vvfnmm5SUlERZWVmUlZVFSUlJ9Oabb5Kfn59ZDQ0RUUxMTIN9FNasWUPR0dE2lzF27FhatmxZvcc/duyYRRNBWFgYbdiwod59jh49avaFJbUMOS6AR2T80VG3WbDuv6PuPl5eXrRixQrauXOn1b9Vq1aJ+9hyfDkuzGfL95iU70lbyyAyvje7detGc+fOpdLSUk5QOnbsaJYJvv/++2a/cBMTE8Wb2KRJkxp8g/7nP/+hUaNG1ft6VlYWTZgwgW6++eYmnXhbLlZTyoiOjqaYmBjxb+XKlWavv/XWW2bV0kTGL8V58+bRU089RUFBQRa/0hMTE83ecLaUsW/fPho0aJDFr73w8HCr5/306dPk7+9PM2fOpGXLlpGHhwfdf//99Morr9DMmTNJo9HQ6tWrbS6jvmSjIY0lHEVFRfTxxx87tIy6Sc39999PCQkJ9OWXX9Idd9xB48aNo0GDBtGZM2fo7NmzNGLECLOFvc6fP0/x8fEkCAJ17dqVLl++TJMmTSKVSkUqlYoCAwPNEgUi6UlNSkoKdezYkVQqFanVavLx8aFt27aJr69evdqsyZCIaNasWTRixAg6c+YMpaamip2bTXbu3EmRkZHNKuPVV1+l0NBQs1/WgiBQaGioRYJMZPzMazQaevLJJ2njxo104MABOnDgAG3cuJGefPJJcnV1pffee8/mMr7//nv64osvLMo1yc/Pp88++8zsuTvuuIMWL15c7z51Ew6pZchxATwioldeeYVefPHFev8d6enpNHv2bLPnRo4cafW6mtQ+V7YcX44L89nyPSble9LWMkzKyspo3rx5FB8fT0qlsn0nKPPmzaNVq1bV+/ry5cvptttua9KxDh482GD7ssnbb79NU6ZMoYyMjEa3tfViSSmjrv3795s1FREZO5WOHDlS/Kt7zpYtW0YjRoxoVhkmOTk5dODAAdq3b5/YNFGfCxcu0D333EOenp5isqFWq2nIkCH0ww8/1LtfU8q4ePGi1b4FDZGacLREGVlZWTRmzBjy8PCgcePGUWFhIT3++OPiF2R8fLzZryGTun1afvvtN9q0aZPVvi62JDWlpaW0detW2rRpk8UoAGuys7PF5FKhUFB0dLTZe+jbb7+ld955p1llmKSmptK+ffto3759FtXnda1bt44SEhJIpVKJ70GVSkUJCQm0fv16u5Qhxe7du2nz5s31vl5SUtKshTrluACerT7++GOLmtfasrKyGkxKGiPHhfkaY+17zJ7fk/WVUdfGjRtpwYIFkn/A2cJpJ2pLS0uDVqtFaGhoq8bx448/4vfff8eiRYsQFBTUqrFYk5qaChcXF0RERLRK+USEnJwcGAwGBAQE2G0cvxxdunQJUVFREAShWcdJTU1FWVkZunTpApXKPlMV5eXlwd/fX3y8fft2XL9+HYMHDzZ7vjmSk5NRUVFh17jtoaqqCrm5uQDQ5t+DzHGccWE+uXxP2sppE5S6bJlkSY6TP8kxptzcXHz66acW2w8ePBhz5sxBYGBgs2OSWkZ92w8ZMgSzZ892aEz2LEOqlnh/ONu5zcjIwAsvvIBPP/202XHZqwyOybwMR79vbTm+HN/nznT/b4n7oKwTlKaemAsXLmDcuHHIzMxEQkICgoODARhnWjx48CAiIiKwefNmxMXFice2ZR8pMdlShhxjOnz4MMaNGwc3NzeMHj3abPvt27ejrKwMW7duxU033WQW0+nTp/Gf//zHasLx+OOPo1u3buK2UsuQY0y2XAtHXzsTKTckOZ/b+iQlJaFfv36S1hNKSUnBI4880uQ1ZqSWwTHdKMPR9zVbji/H93lbuv/bi2wTFCknZsyYMXB3d8fnn39uUf2m0+kwc+ZMXL9+HVu3bhWft2UfqRdLahlyjGnQoEHo3bs3PvzwQ4umCyLCo48+iuPHj2P//v3i85s3b8aUKVPQr18/jBs3ziymbdu2ITExERs3bsS4ceNsKkOOMdlyLRx97QDpNyQ5ntsff/wRDUlNTcXf//53SV+8db9IpZbBMTW9DEff12w5vhzf523l/m9XDu/lYiMpEy3ZMpGTHCd/kmNMUueTICLq1atXg6MVXnjhBerZs6fNZcgxJiLp18LR145I+gypcjy3tsxm+fbbbzf4t3DhwiZPimatDI6p6WU4+r5my/Hl+D5vK/d/e5JtgiLlxNgykZMcJ3+SY0xS55MwxXT27Nl69zl79qxZTFLLkGNMpjIcmWjZ8v6QekOS47mVOn8IkfGLNCwszGxIfe2/sLAwixlSpZTBMTW9DEff12w5vhzf523l/m9P8ulqX0dISAgOHTqELl26WH390KFDYnXWww8/jJkzZ2Lx4sW49dZbLaq5Xn75ZTzxxBNm+9uyj5SYbClDjjH94x//wNy5c5GYmGh1+1WrVuGNN94wKzMmJgY///wzOnfubDWmn3/+2aynu9Qy5BgTIP1aOPraAYCPjw8uXryIHj16WC3j4sWL8PHxada/29Hntn///khMTMTkyZOtHl8QBFCdluro6GisWLEC06dPt7rPsWPH0L9/f5vL4JiaXoaj72u2HF+O7/O2cv+3K4elPs0kdaIlqRM52bKPoyd/kmtMUueT+Oabb0ilUtEdd9xBb7/9Nq1bt47WrVtHb7/9Nk2aNIlcXFwsJjySWoYcY5J6LVri2tkyC6vczq0t84dMnTqVFi5cWO8+dSdFk1oGx9T0Mogcf1+z5f4vt/d5S5wnW8qwdT4he5BtgkJk24mxZZIlOU7+JMeYKisrKTMzkzIzM6mysrLBbf/44w+6++67KSoqilxcXMjFxYWioqLo7rvvpn379tmlDDnG5OhEy0TKtbPl5i31391S17upTp06ZbZasbVy7TGhmBQck+Pva7bc/+X4Pnf2+7+9yHYUT21ynGiJY2INkXotWuLapaWlmQ1DjI2NtXsZjNkb39eapi2eJ6dIUJpr48aNKCoqwsyZMx26j6PjkmNM77//PnJzc7FkyRKHxSS1DDnG1BJa4v0hx3PLMTlvTIDj37e2HF+O56pd3v9bpJ7GAd577z1aunRpk7bt3LmzRc9yR+wjJSZbypBjTKNGjaLY2FhJMS1atIjmzJnjsDLkGBOR9Gvh6GtHRLRhw4YGe+nXJcdzyzE5b0xEjr+v2XJ8OZ6rtnL/l8Jpa1BuvfVWpKWlITU1tbVDEXFMTTNr1ixkZGQ0eXbKltASMUm9Fi1x7bp06YLk5GRJk3dJ1V6vt1QcU9Pxfa1p5HiepHDaBIUxxhhjbZds50GRiohw8eJFREZGQqVSobKyEj/88AMqKipw2223ISAgwOp+BoMBCoXC6vOXL19GVFRUs2OTWoYcY6pPQUEBNm3a5NB2UallyDEmezp06JDVtUAGDhxotzJ27NiBvXv34urVq1AoFOjQoQMmTZqE+Pj4VitDbjElJSUhMTERI0eORIcOHXDq1Cm89957MBgMuPPOO8Upz5tDahlyjOm7777DhAkT4Obm1uyyrbHl+BUVFVAoFGJH0pSUFHz66adIT09HdHQ0HnrooWZ3IpdahqPPky1ltMR5apDDGo/sIDc3l3bs2EF5eXlERHTt2jV69dVXaenSpXT69Glxu7Nnz1J0dDQpFAqKi4uj1NRU6t+/P7m7u5ObmxsFBATQ+fPnzY5dVFRE06ZNI61WS0FBQbR48WKqrq4WX8/Kyqq3LS4jI4OKi4stnq+srKRdu3bZXIYcY2rMsWPHJLeLZmVlSWoXlVqGHGMiIsrPz7fo71FRUUHr16+nBQsW0D333EP33HMPLViwgL755huqqKgw2zY7O5uGDRtGgiBQdHQ0DRw4kAYOHEjR0dEkCAINGzaMsrOzrZZ98OBBeuutt+jZZ5+lZ599lt566y06ePCgxXbZ2dk0cOBAUigUpFKpSKFQUP/+/SkkJISUSiU988wzVo9fVlZGn3zyCc2ZM4fGjx9Pt912Gz3++OP022+/NbsMOcb03XffkVKpJH9/f/Lw8KBt27aRj48PjR49msaNG0dKpZLWrl1rUc6mTZto8eLFtHfvXiIi2r59O02YMIHGjRtHH330UbPKkGNMRMbZar28vOiRRx6hAwcOWL1Wdb3xxhtNHt5sy/FHjBhB3377LRER7d27lzQaDfXq1Yvuvvtu6tu3L7m5uVkMG87IyKBr166Jj3fv3k333XcfDRs2jGbMmGGxvdQyHH2ebCnDlvNkT7JNUA4ePEje3t4kCAL5+vrSkSNHKDY2luLj46ljx47k6upKiYmJREQ0efJkmjRpEh0/fpwWLFhAXbt2pcmTJ1NlZSWVl5fTHXfcQffff7/Z8Z988knq1KkTffvtt7Rq1SqKjo6miRMnil8KWVlZZhMUERFlZmbSgAEDSKFQkFKppAceeMAsKaj75S61DDnGVFRU1ODfnj17JH9R1/1yl1qGHGOypYzk5GTq0KEDabVaGjFiBE2fPp2mT59OI0aMIK1WS3FxcZScnCxuP3XqVBo8eLDV6bbPnj1LQ4YMob/85S9mz0tNau6++26aMmUKFRUVUXl5OT3++OM0c+ZMIjJ+cfn7+9Nbb71lVkZycjJFR0dTUFAQRUZGkiAINHHiREpISCClUknTpk2jqqoqm8uQY0z9+vWjl19+mYiIvv76a/Lx8aGXXnpJfP2NN96gPn36mMX04Ycfkkqlov79+5OXlxd98cUX5OnpSQ8//DDNmzePXF1dm1WGHGMiMn4pvvTSS9S3b18SBIG6d+9OK1eupNzcXKqPIAikVCpp9OjRtG7dOotkvbnH9/LyEn+0jhgxgp566imz159//nkaOnSo2XMDBw4Up4nfsGEDKRQKmjRpEv3zn/+kO++8k9Rqtdk08lLLcPR5sqUMW86TPck2QRk9ejQ9/PDDpNPp6PXXX6eIiAh6+OGHxdfnzJlDU6ZMISKiwMBAOnr0KBEZZzIUBIH27NkjbvvHH39QVFSU2fGjoqLo999/Fx9fu3aNBg4cSGPHjqXy8nKrNQkzZ86khIQEOnz4MG3bto369+9PN910E+Xn5xOR5Ze71DLkGFPtyb2s/VlbHCwpKanBv/Xr1zerDDnGRCQ9qZG6kJ+Hhwf9+eefFtuaHDlyhDw8PMyek5rUeHl50cmTJ8XHJSUlpFarxRi/+OIL6ty5s9lxJkyYQPPmzRMXLHv11VdpwoQJRER0/vx5iomJMZutVmoZcozJ3d2d0tLSiMi4KJtarabjx4+Lr6ekpFhci27dutHHH39MREQ7duwgrVZrNsvn6tWrqWvXrjaXIceYiIyfJVMSfOTIEZo/fz75+PiQRqOhadOm0a+//kp1CYJAq1evpsmTJ5NarSZ/f3/629/+ZnVdKVuO7+7uLq5hExwcTMeOHTN7/cKFCxb/Dnd3d3FCs4SEBHr11VfNXn/33Xepb9++Npfh6PNkSxm2nCd7km2C4uvrKzbjVFZWkkKhMKuSTkxMpPDwcCIyLoh26dIl8TUPDw+6cOGC+Dg9PZ00Go3Z8V1dXS1mz9PpdDR48GAaNWoUpaamWnwBhYWFmcVgqp3p06cP5eXlWXy5Sy1DjjF5eXnRihUraOfOnVb/Vq1aZXUBMtOXuLWVTut+uUstQ44x1S6jqUmN1IX8/P39rU4jbvL777+Tv7+/2XNSk5rAwEA6deqU+LisrIwUCoXYzJqSkmLxWXJzczNrQq2oqCC1Wi3+KtuwYQPFxMTYXIYcYwoJCaEjR44QkbHpThAEs8T/0KFDFBISYhZT3fuUWq02u/5paWnk5uZmcxlyjInI/EvR5Pr16/T555/TyJEjSaFQmF2LuvtkZ2fTihUrqEuXLqRQKGjAgAH08ccfk06ns/n4o0aNotdee42IiIYMGWLR9Pq///3P4kett7c3JSUlERFRUFCQ+P8mFy5cMDtXUstw9HmypQxbzpM9yTZBqZ2pExlvtCkpKeLjS5cuias0duzY0azG5P333ze7KImJiRYfms6dO9PPP/9sUW5xcTENHjyYevfubfEF5O7ubtGXpaqqiqZMmUK9evWi48ePm+0jtQw5xjRy5MgGp0Ovu1YHkfGL9JNPPqGLFy9a/fv555+bVYYcYyKSntRIXVn0scceo+joaPr+++/Nal2Kioro+++/p5iYGHr88cct/t1Skpo777yTpk6dSiUlJVRZWUkLFiyguLg48fUDBw5YfJbCwsLE5lYiooKCAhIEQfwMpqammn25Sy1DjjHdf//9lJCQQF9++SXdcccdNG7cOBo0aBCdOXOGzp49SyNGjLBobouIiKDdu3cTEdGVK1dIEASzz+LOnTspIiLC5jLkGBMRkUKhqLdvFJGxOe65554ze87aFymRsd/HrFmzyN3dndzd3W0+/r59+8jb25teeOEFevfddykgIICef/55Wrt2LS1ZsoR8fHwsPv+TJk2iZ599loiIxo0bR2+//bbZ66tWraL4+Hiby3D0ebKlDFvOkz3JNkHp0qULbd++XXz8008/UVlZmfj4wIED4gdn3rx5tGrVqnqPtXz5crrtttvMnnviiScsPkgmOp2OEhISLJKBnj17WiwGRXQjIYiKijLbR2oZcozp448/tmjfry0rK4tefPFFs+fGjh1Ly5Ytq3eful/uH3/8scWHvaEy5BgTkfSkRupCfuXl5fToo4+Si4sLKRQK0mq1pNVqSaFQkIuLC82fP5/Ky8vNypSa1KSkpFDHjh1JpVKRWq0mb29vs2rf1atXizdpk1mzZtGIESPozJkzlJqaKnagM9m5cydFRkbWW4aPjw9t27at3jLkGFNWVhaNGTOGPDw8aNy4cVRYWEiPP/64WCsXHx9vVotLRPTXv/6V4uPj6eWXX6aBAwfSrFmzqEuXLrR582basmUL9ezZkx588MEmlaFQKCzKkGNMRPV/iTaksS/SoqIisWnKluMTGb98Bw0aZFGjGh4ebvX+cvr0afL396eZM2fSsmXLyMPDg+6//3565ZVXaObMmaTRaGj16tU2l+Ho82RrGVLPkz3JNkF58cUX6euvv6739eeee47uuuuuJh0rNTWVMjMzzZ7Lz883a3OuS6fTWfzyXLhwoVmfgNqqqqpo0qRJZl9AUsuQY0y2+P777+mLL76o9/X8/Hz67LPPmlWGVC0Rky2Jky0L+RUVFdGOHTvoq6++oq+++op27NhhtR8LkW1JTWlpKf3666+0adOmBjvomWRnZ4s3MIVCQdHR0WbNSt9++y298847FmVs3bqVNm3aZDYyoj5yjMmalP9v795Cmn7jOI5/lvMETktZpqYmUZpIISZLMU8YRuBFF0FFlGmJZohSQhJCYqVgQVlQV2V2wA6ShiJIFyoVRpqIZVoaw1BJMq08Tt3zvwiH89A/5zZ/s8/rzs1t79/T0i9zv2ednaKlpUXvDbjThoaGxPHjx0VAQIBISkoS4+PjoqCgQNjY2AiZTCYiIyP/6pfHnx5Dik1qtVpMTU39Veu0xfwiVavVuvcaGaKvr0/U19eLV69e6b1qP5+Ojg6xf/9+oVAodL+ora2tRWhoqHj69OmSHsPU6zT9GIau1WLWyVgsdqO2kZERWFlZwdbW1uD7+PbtG27dujVnT4nQ0FDEx8dDqVTqff/k5CRGRkbg6Og47/1NTk6iu7sb3t7e/3STOUixaSlM/UF+P3/+RGNjo95jBAUFzfu8MXRtP336hPHxcfj5+UEuN+4WS5bWdPTo0QX3XpptbGwMExMTUCgUK7Lp/7os8WeIEAJ9fX3QarVG/WC+lbZOSzV3py4L0d/fj5SUFN3Xo6OjePHiBVpbW+d879jYGIqLi/Uue/PmDTZv3ozCwkI4OTkhPDwc4eHhcHJyQmFhIfz8/NDQ0KB3G7lcvuAgAAC9vb3IycnRu2wxXSul6f98+fIFCQkJK6pp2ocPH3D79m20tbUBANra2pCSkoKEhIQ/boHt4+ODkJAQhISE6IYTYzaVlpbCzc0NBw4cQGBgIB49eoT09PQ5TUtZ202bNiEgIGDOILCc/97L1eTr6/vXz0E7OzsoFIoV2fQ3Xcb4/2ruJplMBldXV7i5uemGk5X4c80UTYtiltdpTGDmnhLt7e26fR1WrVolwsPD9f6kM9/puSqVSiQlJc37cpdWqxVJSUlix44dBjcZ0sUmy20SQoiqqiphY2MjnJ2dhZ2dnaiqqhJKpVLExMSI6OhoYWVlpfe+KmM0dXd3G7VJimvLJsttMkeXFJsM6fpXmhZDsn/iefbs2R+v//z5M06dOoWpqSns3bsXExMTKCoqwuDgINLT09Ha2oqamhp4eXnh69evcHd31/tANHt7ezQ1NcHPz2/e+29ra0NgYCBGR0cNagKw6C42WW4TAISGhiI6Ohrnz59HSUkJTpw4gZSUFFy4cAEAkJWVhcbGRlRXV0u2SYpryybLbTJHlxSbDFmrldJkVCYbfZboT/tWzNy/Qojf56TP3CxIq9WK5ORk4eXlJTo7O+edoDds2PDHj5m/c+eO8Pb2NrjJkC42WW6TEL9PM57e+XVqakrI5XK9N2a2tLQIV1dXSTdJcW3ZZLlN5uiSYpMhXSulyZgkO6C4u7uLsrKyBa9vamrSLaRCodD7bJ5pqampuvP8Zz9Br1+/LmxtbUVaWpooLy8X9fX1or6+XpSXl4u0tDRhb2+vt6PiYpsM6WKT5TYJ8XsYmHmK5ey9e9RqtW7vHqk2SXFt2WS5TebokmKTIV0rpcmYJDugxMXFiezs7AWvn7mnRHBwsCguLp73+1JTU8Xq1avnPEGFEKKkpESoVCohl8t106ZcLhcqlUo8fPhwSU2GdrHJcpu2bt0qqqqqdF/PPu2yrq5O+Pj4SLpJCGmuLZsst8nUXVJsMrRrJTQZk2QHlLq6Or0frLMNDQ3p9uu4ePGi7nM25pOSkqL3jzSbRqMRPT09oqenR2g0GqM0LbWLTZbXdOPGDVFRUbHgbbKyskRiYqKkm2aS0tqyyfKbTNUlxaaldllykzFJ9k2yRERE9O+y2H1QiIiIaOXigEJERESSwwGFiIiIJIcDChEREUkOBxQiMqvIyEikp6cvdwYRSRwHFCKSrJqaGshkMgwODi53ChGZGQcUIiIikhwOKERkMsPDwzh8+DAcHBzg5uaGy5cv611/9+5dbN++HQqFAuvWrcPBgwfR19cHAFCr1YiKigIArFmzBjKZDPHx8QAArVaLvLw8+Pj4wN7eHtu2bcOTJ0/MemxEZFocUIjIZDIzM1FbW4vy8nJUV1ejpqYGb9++1V0/MTGB3NxcNDc3o6ysDGq1WjeEeHp6orS0FADQ3t6O3t5eXL16FQCQl5eH4uJi3Lx5E+/fv0dGRgYOHTqE2tpasx8jEZkGd5IlIpMYGhqCi4sL7t27h3379gEAvn//jvXr1yMpKQlXrlyZc5uGhgYEBwfj169fcHBwQE1NDaKiojAwMIDVq1cDAMbHx+Hs7Iznz58jJCREd9tjx45hZGQEDx48MMfhEZGJyZc7gIhWps7OTmg0GqhUKt1lzs7O8PX11X3d2NiIc+fOobm5GQMDA9BqtQCArq4u+Pv7z3u/HR0dGBkZwa5du/Qu12g0CAwMNMGRENFy4IBCRMtieHgYsbGxiI2Nxf3796FUKtHV1YXY2FhoNJoFbzc0NAQAqKyshIeHh951tra2Jm0mIvPhgEJEJrFx40ZYW1vj9evX8PLyAgAMDAzg48ePiIiIQFtbG/r7+5Gfnw9PT08Av//EM5ONjQ0AYGpqSneZv78/bG1t0dXVhYiICDMdDRGZGwcUIjIJBwcHJCYmIjMzEy4uLli7di3Onj2LVat+vzffy8sLNjY2uHbtGpKTk/Hu3Tvk5ubq3Ye3tzdkMhkqKiqwZ88e2NvbQ6FQ4PTp08jIyIBWq0VYWBh+/PiBly9fwtHREUeOHFmOwyUiI+NZPERkMgUFBdi5cyfi4uIQExODsLAwBAUFAQCUSiWKiorw+PFj+Pv7Iz8/H5cuXdK7vYeHB3JycnDmzBm4urri5MmTAIDc3FxkZ2cjLy8PW7Zswe7du1FZWQkfHx+zHyMRmQbP4iEiIiLJ4SsoREREJDkcUIiIiEhyOKAQERGR5HBAISIiIsnhgEJERESSwwGFiIiIJIcDChEREUkOBxQiIiKSHA4oREREJDkcUIiIiEhyOKAQERGR5PwHrY4Ma1v0NxgAAAAASUVORK5CYII=",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from datetime import datetime\n",
    "import matplotlib.dates as md\n",
    "\n",
    "ts = pd.read_csv(\"../data/dollar.csv\")\n",
    "ts[\"date\"] = ts.apply(lambda row: datetime.strptime(row[\"my_date\"], \"%d.%m.%Y\"), axis=1)\n",
    "\n",
    "plot = ts.plot.line(x=\"date\", y=\"my_value\")\n",
    "plot.xaxis.set_major_locator(md.DayLocator(interval=10))\n",
    "plot.xaxis.set_major_formatter(md.DateFormatter(\"%d.%m.%Y\"))\n",
    "plot.tick_params(axis=\"x\", labelrotation=90)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".venv",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.12.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}