diff --git a/20260626_CassioLima.ipynb b/20260626_CassioLima.ipynb
new file mode 100644
index 0000000..a3b6db1
--- /dev/null
+++ b/20260626_CassioLima.ipynb
@@ -0,0 +1,2376 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Looqbox Data Challenge\n",
+    "\n",
+    "Candidato: Cássio Lima  \n",
+    "Data:  26/06/2026  "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Comentarios sobre o teste e clarificacao de utilizacao de inteligencia artificial\n",
+    "\n",
+    "De modo geral no teste, nao utilizei de ferramentas de inteligencia artificial para desenvolvimento integral dos blocos de codigo. No entando, potentualmente, devido a feature de \"autocompletar' do Visual Studio Code, algumas vezes utilizei-me da mesma para agilizar descricao de campos e syntax de campo. \n",
+    "\n",
+    "Ponto que fiz o uso de inteligencia artificial (Large Language Model):\n",
+    "\n",
+    "Durante o Desafio 3, ao plotar a tabela \"Movies\", passei a variavel labels e observei o seguinte erro: \n",
+    "\n",
+    "```bash\n",
+    "TypeError: Axes.boxplot() got an unexpected keyword argument 'labels'. Did you mean 'label'?\n",
+    "```\n",
+    "\n",
+    "Ao buscar solucoes na internet, perguntei ao DeepSeek-v4-flash qual seria o problema com meu codigo (entendo que poderia ter aberto a lista de variaveis aceitaveis tambem) e obtive como resposta:\n",
+    "\n",
+    "\"matplotlib atualizou — labels= virou tick_labels= da versao 3.9+.\"\n",
+    "\n",
+    "Entao, troquei labels por tick_labels."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 1. Setup conexoes e rodando uns testes basicos de conexao"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Conectado.\n",
+      "Tabelas disponiveis:\n",
+      "  - IMDB_movies\n",
+      "  - data_product\n",
+      "  - data_product_sales\n",
+      "  - data_store_cad\n",
+      "  - data_store_sales\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import mysql.connector # Importando a biblioteca mysql.connector para conectar ao banco de dados MySQL\n",
+    "import pandas as pd # Importando a biblioteca pandas para manipulação de dados, pandas eh minha preferencia\n",
+    "import matplotlib.pyplot as plt # Classico matplotlib\n",
+    "import seaborn as sns # Seaborn por estilo e praticidade\n",
+    "from typing import Optional, List, Union # \n",
+    "\n",
+    "DB_CONFIG = {\n",
+    "    'host': '35.199.115.174',\n",
+    "    'user': 'looqbox-challenge',\n",
+    "    'password': 'looq-challenge',\n",
+    "    'database': 'looqbox-challenge'\n",
+    "}\n",
+    "\n",
+    "connection = mysql.connector.connect(**DB_CONFIG)\n",
+    "print('Conectado.')\n",
+    "print(f'Tabelas disponiveis:')\n",
+    "cursor = connection.cursor() # Cursor aqui tem a funcao de executar comandos SQL e retornar resultados\n",
+    "cursor.execute('SHOW TABLES') # Vamos executar o comando SQL SHOW TABLES para listar todas as tabelas no banco de dados\n",
+    "for t in cursor.fetchall(): # Interando sobre os resultados retornados pelo comando SQL, para ver todas tabelas\n",
+    "    print(f'  - {t[0]}')\n",
+    "cursor.close() # Fechar a conexao com o cursor, para liberar recursos"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "('Id', 'int', 'NO', 'PRI', None, '')\n",
+      "('Title', 'varchar(255)', 'YES', '', None, '')\n",
+      "('Genre', 'varchar(255)', 'YES', '', None, '')\n",
+      "('Director', 'varchar(255)', 'YES', '', None, '')\n",
+      "('Actors', 'varchar(255)', 'YES', '', None, '')\n",
+      "('Year', 'int', 'YES', '', None, '')\n",
+      "('Runtime', 'int', 'YES', '', None, '')\n",
+      "('Rating', 'decimal(10,0)', 'YES', '', None, '')\n",
+      "('Votes', 'int', 'YES', '', None, '')\n",
+      "('RevenueMillions', 'decimal(10,0)', 'YES', '', None, '')\n",
+      "('Metascore', 'int', 'YES', '', None, '')\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Inspecao basica da primeira tabela que apareceu no print IMDB_movies\n",
+    "\n",
+    "cursor = connection.cursor() # Cursor aqui tem a funcao de executar comandos SQL e retornar resultados\n",
+    "cursor.execute('DESCRIBE IMDB_movies')\n",
+    "for col in cursor.fetchall():\n",
+    "        print(col)\n",
+    "cursor.close()\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## SQL Test\n",
+    "\n",
+    "Agora performamos as operacoes pro teste."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Q1 — Top 10 produtos mais caros"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "('PRODUCT_COD', 'int', 'NO', 'PRI', None, '')\n",
+      "('PRODUCT_NAME', 'varchar(150)', 'YES', 'MUL', None, '')\n",
+      "('PRODUCT_VAL', 'decimal(8,2)', 'YES', '', None, '')\n",
+      "('DEP_NAME', 'varchar(255)', 'YES', '', None, '')\n",
+      "('DEP_COD', 'int', 'YES', '', None, '')\n",
+      "('SECTION_NAME', 'varchar(255)', 'YES', '', None, '')\n",
+      "('SECTION_COD', 'int', 'YES', '', None, '')\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Vamos ver como a tabela data_product se parece, para isso vamos usar o pandas para ler os dados e mostrar as primeiras linhas\n",
+    "cursor = connection.cursor() # Cursor aqui tem a funcao de executar comandos SQL e retornar resultados\n",
+    "cursor.execute('DESCRIBE data_product')\n",
+    "for col in cursor.fetchall():\n",
+    "        print(col)\n",
+    "cursor.close()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Ja que varios calls para o banco de dados serao feitos, vamos criar uma funcao para agializar. \n",
+    "# Dai so passamos o SQL e a funcao retorna um DataFrame do pandas com os resultados\n",
+    "\n",
+    "def query(sql): \n",
+    "        cursor = connection.cursor(dictionary=True)\n",
+    "        cursor.execute(sql)\n",
+    "        df = pd.DataFrame(cursor.fetchall())\n",
+    "        cursor.close()\n",
+    "        return df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "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>product_cod</th>\n",
+       "      <th>product_name</th>\n",
+       "      <th>product_val</th>\n",
+       "      <th>dep_name</th>\n",
+       "      <th>section_name</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>301409</td>\n",
+       "      <td>Whisky Escoces THE MACALLAN Ruby Garrafa 700ml...</td>\n",
+       "      <td>741.99</td>\n",
+       "      <td>BEBIDAS</td>\n",
+       "      <td>BEBIDAS</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>176185</td>\n",
+       "      <td>Whisky Escoces JOHNNIE WALKER Blue Label Garra...</td>\n",
+       "      <td>735.90</td>\n",
+       "      <td>BEBIDAS</td>\n",
+       "      <td>BEBIDAS</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>315481</td>\n",
+       "      <td>Cafeteira Expresso 3 CORACOES Tres Modo Vermelho</td>\n",
+       "      <td>499.00</td>\n",
+       "      <td>BEBIDAS</td>\n",
+       "      <td>BEBIDAS</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>100280</td>\n",
+       "      <td>Vinho Portugues Tinto Vintage QUINTA DO CRASTO...</td>\n",
+       "      <td>445.90</td>\n",
+       "      <td>BEBIDAS</td>\n",
+       "      <td>VINHOS</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>320046</td>\n",
+       "      <td>Escova Dental Eletrica ORAL B D34 Professional...</td>\n",
+       "      <td>399.90</td>\n",
+       "      <td>PERFUMARIA</td>\n",
+       "      <td>HIGIENE BUCAL</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>190817</td>\n",
+       "      <td>Champagne Rose VEUVE CLICQUOT PONSARDIM Garraf...</td>\n",
+       "      <td>366.90</td>\n",
+       "      <td>MERCEARIA</td>\n",
+       "      <td>ARTIGOS-PARA-O-LAR</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>153795</td>\n",
+       "      <td>Champagne Frances Brut Imperial MOET Rose Garr...</td>\n",
+       "      <td>359.90</td>\n",
+       "      <td>MERCEARIA</td>\n",
+       "      <td>ARTIGOS-PARA-O-LAR</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>311397</td>\n",
+       "      <td>Conjunto de Panelas Allegra em Inox TRAMONTINA...</td>\n",
+       "      <td>359.00</td>\n",
+       "      <td>MERCEARIA</td>\n",
+       "      <td>ARTIGOS-PARA-O-LAR</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>147706</td>\n",
+       "      <td>Whisky Escoces CHIVAS REGAL 18 Anos Garrafa 750ml</td>\n",
+       "      <td>329.90</td>\n",
+       "      <td>BEBIDAS</td>\n",
+       "      <td>BEBIDAS</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>154431</td>\n",
+       "      <td>Champagne Frances Brut Imperial MOET &amp; CHANDON...</td>\n",
+       "      <td>315.90</td>\n",
+       "      <td>MERCEARIA</td>\n",
+       "      <td>ARTIGOS-PARA-O-LAR</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   product_cod                                       product_name product_val  \\\n",
+       "0       301409  Whisky Escoces THE MACALLAN Ruby Garrafa 700ml...      741.99   \n",
+       "1       176185  Whisky Escoces JOHNNIE WALKER Blue Label Garra...      735.90   \n",
+       "2       315481   Cafeteira Expresso 3 CORACOES Tres Modo Vermelho      499.00   \n",
+       "3       100280  Vinho Portugues Tinto Vintage QUINTA DO CRASTO...      445.90   \n",
+       "4       320046  Escova Dental Eletrica ORAL B D34 Professional...      399.90   \n",
+       "5       190817  Champagne Rose VEUVE CLICQUOT PONSARDIM Garraf...      366.90   \n",
+       "6       153795  Champagne Frances Brut Imperial MOET Rose Garr...      359.90   \n",
+       "7       311397  Conjunto de Panelas Allegra em Inox TRAMONTINA...      359.00   \n",
+       "8       147706  Whisky Escoces CHIVAS REGAL 18 Anos Garrafa 750ml      329.90   \n",
+       "9       154431  Champagne Frances Brut Imperial MOET & CHANDON...      315.90   \n",
+       "\n",
+       "     dep_name        section_name  \n",
+       "0     BEBIDAS             BEBIDAS  \n",
+       "1     BEBIDAS             BEBIDAS  \n",
+       "2     BEBIDAS             BEBIDAS  \n",
+       "3     BEBIDAS              VINHOS  \n",
+       "4  PERFUMARIA       HIGIENE BUCAL  \n",
+       "5   MERCEARIA  ARTIGOS-PARA-O-LAR  \n",
+       "6   MERCEARIA  ARTIGOS-PARA-O-LAR  \n",
+       "7   MERCEARIA  ARTIGOS-PARA-O-LAR  \n",
+       "8     BEBIDAS             BEBIDAS  \n",
+       "9   MERCEARIA  ARTIGOS-PARA-O-LAR  "
+      ]
+     },
+     "execution_count": 19,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Trazer a tabela para pandas, minha preferencia, para poder manipular os dados e fazer analises\n",
+    "# O query abaixo traz os 10 produtos mais caros, com seus respectivos codigos, nomes, valores, \n",
+    "# departamentos e secoess. A ordenacao eh feita pelo valor do produto em ordem decrescente.\n",
+    "\n",
+    "q1 = \"\"\"\n",
+    "SELECT product_cod, product_name, product_val, dep_name, section_name\n",
+    "FROM data_product\n",
+    "ORDER BY product_val DESC\n",
+    "LIMIT 10\n",
+    "\"\"\"\n",
+    "df_q1 = query(q1)\n",
+    "df_q1\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Q2 — Seções dos departamentos BEBIDAS e PADARIA"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "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>dep_name</th>\n",
+       "      <th>section_name</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>BEBIDAS</td>\n",
+       "      <td>BEBIDAS</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>BEBIDAS</td>\n",
+       "      <td>CERVEJAS</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>BEBIDAS</td>\n",
+       "      <td>REFRESCOS</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>BEBIDAS</td>\n",
+       "      <td>VINHOS</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>PADARIA</td>\n",
+       "      <td>DOCES-E-SOBREMESAS</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>PADARIA</td>\n",
+       "      <td>GESTANTE</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>PADARIA</td>\n",
+       "      <td>PADARIA</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>PADARIA</td>\n",
+       "      <td>QUEIJOS-E-FRIOS</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "  dep_name        section_name\n",
+       "0  BEBIDAS             BEBIDAS\n",
+       "1  BEBIDAS            CERVEJAS\n",
+       "2  BEBIDAS           REFRESCOS\n",
+       "3  BEBIDAS              VINHOS\n",
+       "4  PADARIA  DOCES-E-SOBREMESAS\n",
+       "5  PADARIA            GESTANTE\n",
+       "6  PADARIA             PADARIA\n",
+       "7  PADARIA     QUEIJOS-E-FRIOS"
+      ]
+     },
+     "execution_count": 20,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Abaixo restringimos nossa consulta para trazer apenas os departamentos de BEBIDAS e PADARIA,\n",
+    "#  com suas respectivas secoess. A ordenacao eh feita pelo nome do departamento e da secao.\n",
+    "\n",
+    "q2 = \"\"\"\n",
+    "SELECT DISTINCT dep_name, section_name\n",
+    "FROM data_product\n",
+    "WHERE dep_name IN ('BEBIDAS', 'PADARIA')\n",
+    "ORDER BY dep_name, section_name\n",
+    "\"\"\"\n",
+    "\n",
+    "df_q2 = query(q2)\n",
+    "df_q2"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Q3 — Total vendido por Business Area no Q1 2019"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "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>BUSINESS_NAME</th>\n",
+       "      <th>total_sales</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>Farma</td>\n",
+       "      <td>81776691.73</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>Varejo</td>\n",
+       "      <td>81032347.65</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>Atacado</td>\n",
+       "      <td>80384884.60</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>Proximidade</td>\n",
+       "      <td>80171122.80</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>Posto</td>\n",
+       "      <td>32072326.40</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "  BUSINESS_NAME  total_sales\n",
+       "0         Farma  81776691.73\n",
+       "1        Varejo  81032347.65\n",
+       "2       Atacado  80384884.60\n",
+       "3   Proximidade  80171122.80\n",
+       "4         Posto  32072326.40"
+      ]
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Abaixo selecionamos por business area (nome aqui BUSINESS_NAME) e somamos o valor de vendas (SALES_VALUE) para cada business area, \n",
+    "# no periodo de 01/01/2019 a 31/03/2019. A ordenacao eh feita pelo total de vendas em ordem decrescente.\n",
+    "\n",
+    "q3 = \"\"\"\n",
+    "SELECT c.BUSINESS_NAME,\n",
+    "       ROUND(SUM(v.SALES_VALUE), 2) AS total_sales\n",
+    "FROM data_store_sales v\n",
+    "JOIN data_store_cad c USING (STORE_CODE)\n",
+    "WHERE v.DATE BETWEEN '2019-01-01' AND '2019-03-31'\n",
+    "GROUP BY c.BUSINESS_NAME\n",
+    "ORDER BY total_sales DESC\n",
+    "\"\"\"\n",
+    "\n",
+    "df_q3 = query(q3)\n",
+    "df_q3"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "\n",
+    "## Case Real 1 - Função dinâmica \"retrieve_data\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Objetivo: Criar uma função flexível que monta queries dinamicamente com base em 3 parâmetros (Assumindo aqui que sejam opcionais)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Aqui definimos a funcao retrieve_data que recebe como parametros o codigo do produto, \n",
+    "# codigo da loja, data e conexao com o banco de dados.\n",
+    "# A funcao tem como campos opcionais o codigo do produto, codigo da loja e data, que podem ser passados como argumentos.\n",
+    "   \n",
+    "def retrieve_data(      \n",
+    "        product_code: Optional[int] = None,\n",
+    "        store_code: Optional[int] = None,\n",
+    "        date: Optional[List[str]] = None,\n",
+    "        conn=None # conn aqui tem a funcao de receber uma conexao com o banco de dados, caso nao seja passada, a funcao cria uma nova conexao\n",
+    "    ) -> pd.DataFrame: # A funcao retorna um DataFrame do pandas com os resultados da consulta SQL.\n",
+    "        cfg = conn or mysql.connector.connect(**DB_CONFIG) # Conecta ao banco de dados\n",
+    "        close = conn is None  # so fecha se criou aqui\n",
+    "    \n",
+    "        clauses, params = [], [] # definindo listas vazias para armazenar as clausulas e parametros da consulta SQL\n",
+    "        # Logica aqui eh simples, se o parametro for passado, adiciona a clausula e o parametro na lista, caso \n",
+    "        # contrario nao faz nada.\n",
+    "        # A adicao de %s eh uma seguranca para evitar SQL injection, o parametro sera passado separadamente e \n",
+    "        # nao sera concatenado na string SQL.\n",
+    "        if product_code is not None: \n",
+    "            clauses.append(\"AND PRODUCT_CODE = %s\"); params.append(product_code) \n",
+    "        if store_code is not None:\n",
+    "            clauses.append(\"AND STORE_CODE = %s\"); params.append(store_code)\n",
+    "        if date and len(date) == 2:\n",
+    "            clauses.append(\"AND DATE BETWEEN %s AND %s\"); params.extend(date)\n",
+    "    \n",
+    "        # uma vez que todas as clausulas foram adicionadas, podemos montar a query final e executar\n",
+    "        # A funcao pd.read_sql() do pandas eh usada para executar a query e retornar um DataFrame com os resultados.\n",
+    "\n",
+    "        query = \"SELECT * FROM data_product_sales WHERE 1=1 \" + \" \".join(clauses)  # Aqui temos certeza que trazemos todas colunas\n",
+    "        df = pd.read_sql(query, cfg, params=params)\n",
+    "        if close: cfg.close()\n",
+    "        return df\n",
+    "\n",
+    "# OBS: Caso a funcao seja usada por outros times, como sugerido pelo desafio, a funcao pode ser melhorada para receber outros parametros, como por exemplo,\n",
+    "# o nome do produto, o nome da loja, o departamento, a secao. Eh possivel tambem que a funcao seja convertida a um modulo, para que outros times possam \n",
+    "# importar e usar a funcao sem precisar copiar o codigo."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Testes da função"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "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>store_code</th>\n",
+       "      <th>product_code</th>\n",
+       "      <th>date</th>\n",
+       "      <th>sales_value</th>\n",
+       "      <th>sales_qty</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>18</td>\n",
+       "      <td>2019-01-01</td>\n",
+       "      <td>708.50</td>\n",
+       "      <td>65</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>1</td>\n",
+       "      <td>18</td>\n",
+       "      <td>2019-01-02</td>\n",
+       "      <td>1297.10</td>\n",
+       "      <td>119</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>1</td>\n",
+       "      <td>18</td>\n",
+       "      <td>2019-01-03</td>\n",
+       "      <td>1144.50</td>\n",
+       "      <td>105</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>1</td>\n",
+       "      <td>18</td>\n",
+       "      <td>2019-01-04</td>\n",
+       "      <td>1090.00</td>\n",
+       "      <td>100</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>1</td>\n",
+       "      <td>18</td>\n",
+       "      <td>2019-01-05</td>\n",
+       "      <td>893.80</td>\n",
+       "      <td>82</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>1</td>\n",
+       "      <td>18</td>\n",
+       "      <td>2019-01-06</td>\n",
+       "      <td>741.20</td>\n",
+       "      <td>68</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>1</td>\n",
+       "      <td>18</td>\n",
+       "      <td>2019-01-07</td>\n",
+       "      <td>654.00</td>\n",
+       "      <td>60</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>1</td>\n",
+       "      <td>18</td>\n",
+       "      <td>2019-01-08</td>\n",
+       "      <td>741.20</td>\n",
+       "      <td>68</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>1</td>\n",
+       "      <td>18</td>\n",
+       "      <td>2019-01-09</td>\n",
+       "      <td>1373.40</td>\n",
+       "      <td>126</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>1</td>\n",
+       "      <td>18</td>\n",
+       "      <td>2019-01-10</td>\n",
+       "      <td>1068.20</td>\n",
+       "      <td>98</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "  store_code  product_code        date sales_value sales_qty\n",
+       "0          1            18  2019-01-01      708.50        65\n",
+       "1          1            18  2019-01-02     1297.10       119\n",
+       "2          1            18  2019-01-03     1144.50       105\n",
+       "3          1            18  2019-01-04     1090.00       100\n",
+       "4          1            18  2019-01-05      893.80        82\n",
+       "5          1            18  2019-01-06      741.20        68\n",
+       "6          1            18  2019-01-07      654.00        60\n",
+       "7          1            18  2019-01-08      741.20        68\n",
+       "8          1            18  2019-01-09     1373.40       126\n",
+       "9          1            18  2019-01-10     1068.20        98"
+      ]
+     },
+     "execution_count": 23,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Primeiro vamos dar uma olhada na tabela para retirar um produto que existe numa loja\n",
+    "\n",
+    "q4 = \"\"\"\n",
+    "SELECT store_code, product_code, date, sales_value, sales_qty\n",
+    "FROM data_product_sales\n",
+    "LIMIT 10\n",
+    "\"\"\"\n",
+    "df_q4 = query(q4)\n",
+    "df_q4"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/var/folders/gx/xtw1gyms3cd4csdtf8k5bzc80000gn/T/ipykernel_46254/3076841265.py:30: UserWarning: pandas only supports SQLAlchemy connectable (engine/connection) or database string URI or sqlite3 DBAPI2 connection. Other DBAPI2 objects are not tested. Please consider using SQLAlchemy.\n",
+      "  df = pd.read_sql(query, cfg, params=params)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Produtos 18: 31 rows\n"
+     ]
+    },
+    {
+     "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>STORE_CODE</th>\n",
+       "      <th>PRODUCT_CODE</th>\n",
+       "      <th>DATE</th>\n",
+       "      <th>SALES_VALUE</th>\n",
+       "      <th>SALES_QTY</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>18</td>\n",
+       "      <td>2019-01-01</td>\n",
+       "      <td>708.5</td>\n",
+       "      <td>65.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>1</td>\n",
+       "      <td>18</td>\n",
+       "      <td>2019-01-02</td>\n",
+       "      <td>1297.1</td>\n",
+       "      <td>119.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>1</td>\n",
+       "      <td>18</td>\n",
+       "      <td>2019-01-03</td>\n",
+       "      <td>1144.5</td>\n",
+       "      <td>105.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>1</td>\n",
+       "      <td>18</td>\n",
+       "      <td>2019-01-04</td>\n",
+       "      <td>1090.0</td>\n",
+       "      <td>100.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>1</td>\n",
+       "      <td>18</td>\n",
+       "      <td>2019-01-05</td>\n",
+       "      <td>893.8</td>\n",
+       "      <td>82.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>1</td>\n",
+       "      <td>18</td>\n",
+       "      <td>2019-01-06</td>\n",
+       "      <td>741.2</td>\n",
+       "      <td>68.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>1</td>\n",
+       "      <td>18</td>\n",
+       "      <td>2019-01-07</td>\n",
+       "      <td>654.0</td>\n",
+       "      <td>60.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>1</td>\n",
+       "      <td>18</td>\n",
+       "      <td>2019-01-08</td>\n",
+       "      <td>741.2</td>\n",
+       "      <td>68.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>1</td>\n",
+       "      <td>18</td>\n",
+       "      <td>2019-01-09</td>\n",
+       "      <td>1373.4</td>\n",
+       "      <td>126.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>1</td>\n",
+       "      <td>18</td>\n",
+       "      <td>2019-01-10</td>\n",
+       "      <td>1068.2</td>\n",
+       "      <td>98.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10</th>\n",
+       "      <td>1</td>\n",
+       "      <td>18</td>\n",
+       "      <td>2019-01-11</td>\n",
+       "      <td>1057.3</td>\n",
+       "      <td>97.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>11</th>\n",
+       "      <td>1</td>\n",
+       "      <td>18</td>\n",
+       "      <td>2019-01-12</td>\n",
+       "      <td>806.6</td>\n",
+       "      <td>74.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>12</th>\n",
+       "      <td>1</td>\n",
+       "      <td>18</td>\n",
+       "      <td>2019-01-13</td>\n",
+       "      <td>686.7</td>\n",
+       "      <td>63.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>13</th>\n",
+       "      <td>1</td>\n",
+       "      <td>18</td>\n",
+       "      <td>2019-01-14</td>\n",
+       "      <td>697.6</td>\n",
+       "      <td>64.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>14</th>\n",
+       "      <td>1</td>\n",
+       "      <td>18</td>\n",
+       "      <td>2019-01-15</td>\n",
+       "      <td>763.0</td>\n",
+       "      <td>70.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>15</th>\n",
+       "      <td>1</td>\n",
+       "      <td>18</td>\n",
+       "      <td>2019-01-16</td>\n",
+       "      <td>1199.0</td>\n",
+       "      <td>110.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>16</th>\n",
+       "      <td>1</td>\n",
+       "      <td>18</td>\n",
+       "      <td>2019-01-17</td>\n",
+       "      <td>1068.2</td>\n",
+       "      <td>98.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>17</th>\n",
+       "      <td>1</td>\n",
+       "      <td>18</td>\n",
+       "      <td>2019-01-18</td>\n",
+       "      <td>1057.3</td>\n",
+       "      <td>97.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>18</th>\n",
+       "      <td>1</td>\n",
+       "      <td>18</td>\n",
+       "      <td>2019-01-19</td>\n",
+       "      <td>795.7</td>\n",
+       "      <td>73.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>19</th>\n",
+       "      <td>1</td>\n",
+       "      <td>18</td>\n",
+       "      <td>2019-01-20</td>\n",
+       "      <td>697.6</td>\n",
+       "      <td>64.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>20</th>\n",
+       "      <td>1</td>\n",
+       "      <td>18</td>\n",
+       "      <td>2019-01-21</td>\n",
+       "      <td>675.8</td>\n",
+       "      <td>62.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>21</th>\n",
+       "      <td>1</td>\n",
+       "      <td>18</td>\n",
+       "      <td>2019-01-22</td>\n",
+       "      <td>806.6</td>\n",
+       "      <td>74.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>22</th>\n",
+       "      <td>1</td>\n",
+       "      <td>18</td>\n",
+       "      <td>2019-01-23</td>\n",
+       "      <td>1395.2</td>\n",
+       "      <td>128.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>23</th>\n",
+       "      <td>1</td>\n",
+       "      <td>18</td>\n",
+       "      <td>2019-01-24</td>\n",
+       "      <td>1035.5</td>\n",
+       "      <td>95.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>24</th>\n",
+       "      <td>1</td>\n",
+       "      <td>18</td>\n",
+       "      <td>2019-01-25</td>\n",
+       "      <td>1057.3</td>\n",
+       "      <td>97.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>25</th>\n",
+       "      <td>1</td>\n",
+       "      <td>18</td>\n",
+       "      <td>2019-01-26</td>\n",
+       "      <td>850.2</td>\n",
+       "      <td>78.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>26</th>\n",
+       "      <td>1</td>\n",
+       "      <td>18</td>\n",
+       "      <td>2019-01-27</td>\n",
+       "      <td>763.0</td>\n",
+       "      <td>70.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>27</th>\n",
+       "      <td>1</td>\n",
+       "      <td>18</td>\n",
+       "      <td>2019-01-28</td>\n",
+       "      <td>708.5</td>\n",
+       "      <td>65.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>28</th>\n",
+       "      <td>1</td>\n",
+       "      <td>18</td>\n",
+       "      <td>2019-01-29</td>\n",
+       "      <td>730.3</td>\n",
+       "      <td>67.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>29</th>\n",
+       "      <td>1</td>\n",
+       "      <td>18</td>\n",
+       "      <td>2019-01-30</td>\n",
+       "      <td>1384.3</td>\n",
+       "      <td>127.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>30</th>\n",
+       "      <td>1</td>\n",
+       "      <td>18</td>\n",
+       "      <td>2019-01-31</td>\n",
+       "      <td>1177.2</td>\n",
+       "      <td>108.0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   STORE_CODE  PRODUCT_CODE        DATE  SALES_VALUE  SALES_QTY\n",
+       "0           1            18  2019-01-01        708.5       65.0\n",
+       "1           1            18  2019-01-02       1297.1      119.0\n",
+       "2           1            18  2019-01-03       1144.5      105.0\n",
+       "3           1            18  2019-01-04       1090.0      100.0\n",
+       "4           1            18  2019-01-05        893.8       82.0\n",
+       "5           1            18  2019-01-06        741.2       68.0\n",
+       "6           1            18  2019-01-07        654.0       60.0\n",
+       "7           1            18  2019-01-08        741.2       68.0\n",
+       "8           1            18  2019-01-09       1373.4      126.0\n",
+       "9           1            18  2019-01-10       1068.2       98.0\n",
+       "10          1            18  2019-01-11       1057.3       97.0\n",
+       "11          1            18  2019-01-12        806.6       74.0\n",
+       "12          1            18  2019-01-13        686.7       63.0\n",
+       "13          1            18  2019-01-14        697.6       64.0\n",
+       "14          1            18  2019-01-15        763.0       70.0\n",
+       "15          1            18  2019-01-16       1199.0      110.0\n",
+       "16          1            18  2019-01-17       1068.2       98.0\n",
+       "17          1            18  2019-01-18       1057.3       97.0\n",
+       "18          1            18  2019-01-19        795.7       73.0\n",
+       "19          1            18  2019-01-20        697.6       64.0\n",
+       "20          1            18  2019-01-21        675.8       62.0\n",
+       "21          1            18  2019-01-22        806.6       74.0\n",
+       "22          1            18  2019-01-23       1395.2      128.0\n",
+       "23          1            18  2019-01-24       1035.5       95.0\n",
+       "24          1            18  2019-01-25       1057.3       97.0\n",
+       "25          1            18  2019-01-26        850.2       78.0\n",
+       "26          1            18  2019-01-27        763.0       70.0\n",
+       "27          1            18  2019-01-28        708.5       65.0\n",
+       "28          1            18  2019-01-29        730.3       67.0\n",
+       "29          1            18  2019-01-30       1384.3      127.0\n",
+       "30          1            18  2019-01-31       1177.2      108.0"
+      ]
+     },
+     "execution_count": 24,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Testando o produce 18 pq ele existe (de acordo com o report acima) para validacao no mes de janeiro de 2019\n",
+    "\n",
+    "df_multi = retrieve_data(product_code=18, store_code=1, date=['2019-01-01', '2019-01-31'])\n",
+    "print(f'Produtos 18: {len(df_multi)} rows')\n",
+    "df_multi"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "\n",
+    "## Case 2 — Queries fixas + visualização"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Instruções do cliente:\n",
+    "- Nao eh permitido modificar as queries\n",
+    "- Filtrar período inteiro de 2019 (2019-01-01 a 2019-12-31)\n",
+    "- Criar visualização: ranking de lojas por TM (ticket médio?)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Cadastro: 20 lojas\n",
+      "Vendas 2019: 7300 registros\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Query 1\n",
+    "\n",
+    "query1 = \"\"\"SELECT\n",
+    "      STORE_CODE,\n",
+    "      STORE_NAME,\n",
+    "      START_DATE,\n",
+    "      END_DATE,\n",
+    "      BUSINESS_NAME,\n",
+    "      BUSINESS_CODE\n",
+    "FROM data_store_cad\"\"\"\n",
+    "\n",
+    "# Query 2\n",
+    "query2 = \"\"\"SELECT\n",
+    "        STORE_CODE,\n",
+    "        DATE,\n",
+    "        SALES_VALUE,\n",
+    "        SALES_QTY\n",
+    "FROM data_store_sales\n",
+    "WHERE DATE BETWEEN '2019-01-01' AND '2019-12-31'\"\"\"\n",
+    "\n",
+    "df_cad = query(query1)\n",
+    "df_sales = query(query2)\n",
+    "\n",
+    "# vamos verificar oq esta retornando e se esta ok, para isso vamos printar o tamanho dos dataframes retornados\n",
+    "print(f'Cadastro: {len(df_cad)} lojas')\n",
+    "print(f'Vendas 2019: {len(df_sales)} registros')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Q4 2019: 1840 registros\n"
+     ]
+    },
+    {
+     "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>STORE_CODE</th>\n",
+       "      <th>DATE</th>\n",
+       "      <th>SALES_VALUE</th>\n",
+       "      <th>SALES_QTY</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>5460</th>\n",
+       "      <td>1</td>\n",
+       "      <td>2019-10-01</td>\n",
+       "      <td>187601.54</td>\n",
+       "      <td>12160</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5461</th>\n",
+       "      <td>10</td>\n",
+       "      <td>2019-10-01</td>\n",
+       "      <td>139038.86</td>\n",
+       "      <td>5223</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5462</th>\n",
+       "      <td>11</td>\n",
+       "      <td>2019-10-01</td>\n",
+       "      <td>252687.35</td>\n",
+       "      <td>8481</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5463</th>\n",
+       "      <td>12</td>\n",
+       "      <td>2019-10-01</td>\n",
+       "      <td>223973.64</td>\n",
+       "      <td>7659</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5464</th>\n",
+       "      <td>13</td>\n",
+       "      <td>2019-10-01</td>\n",
+       "      <td>187601.54</td>\n",
+       "      <td>12160</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7295</th>\n",
+       "      <td>5</td>\n",
+       "      <td>2019-12-31</td>\n",
+       "      <td>193619.94</td>\n",
+       "      <td>12607</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7296</th>\n",
+       "      <td>6</td>\n",
+       "      <td>2019-12-31</td>\n",
+       "      <td>193619.94</td>\n",
+       "      <td>12607</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7297</th>\n",
+       "      <td>7</td>\n",
+       "      <td>2019-12-31</td>\n",
+       "      <td>193619.94</td>\n",
+       "      <td>12607</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7298</th>\n",
+       "      <td>8</td>\n",
+       "      <td>2019-12-31</td>\n",
+       "      <td>191704.64</td>\n",
+       "      <td>12500</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7299</th>\n",
+       "      <td>9</td>\n",
+       "      <td>2019-12-31</td>\n",
+       "      <td>167081.21</td>\n",
+       "      <td>5765</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>1840 rows × 4 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "      STORE_CODE       DATE  SALES_VALUE  SALES_QTY\n",
+       "5460           1 2019-10-01    187601.54      12160\n",
+       "5461          10 2019-10-01    139038.86       5223\n",
+       "5462          11 2019-10-01    252687.35       8481\n",
+       "5463          12 2019-10-01    223973.64       7659\n",
+       "5464          13 2019-10-01    187601.54      12160\n",
+       "...          ...        ...          ...        ...\n",
+       "7295           5 2019-12-31    193619.94      12607\n",
+       "7296           6 2019-12-31    193619.94      12607\n",
+       "7297           7 2019-12-31    193619.94      12607\n",
+       "7298           8 2019-12-31    191704.64      12500\n",
+       "7299           9 2019-12-31    167081.21       5765\n",
+       "\n",
+       "[1840 rows x 4 columns]"
+      ]
+     },
+     "execution_count": 26,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Filtro manual do periodo (sem mexer nas queries)\n",
+    "df_sales['DATE'] = pd.to_datetime(df_sales['DATE']) # Por nao ter certeza que o campo DATE esta no formato datetime, vamos converter para datetime, caso nao esteja.\n",
+    "mask = (df_sales['DATE'] >= '2019-10-01') & (df_sales['DATE'] <= '2019-12-31') # Mask simples de data para so pegar Q4\n",
+    "df_q4 = df_sales[mask].copy() # criar um novo dataframe com os dados filtrados, para nao alterar o dataframe original\n",
+    "\n",
+    "# Verificar se o dataframe se mantem agora pegando apenas uma fatia de 2019\n",
+    "print(f'Q4 2019: {len(df_q4)} registros')\n",
+    "df_q4"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "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>STORE_CODE</th>\n",
+       "      <th>total_value</th>\n",
+       "      <th>total_qty</th>\n",
+       "      <th>TM</th>\n",
+       "      <th>STORE_NAME</th>\n",
+       "      <th>BUSINESS_NAME</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>14</td>\n",
+       "      <td>21213088.57</td>\n",
+       "      <td>1378476</td>\n",
+       "      <td>15.39</td>\n",
+       "      <td>Bahia</td>\n",
+       "      <td>Atacado</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>18</td>\n",
+       "      <td>8376271.00</td>\n",
+       "      <td>612968</td>\n",
+       "      <td>13.67</td>\n",
+       "      <td>Bangkok</td>\n",
+       "      <td>Posto</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>8</td>\n",
+       "      <td>20989553.37</td>\n",
+       "      <td>1365988</td>\n",
+       "      <td>15.37</td>\n",
+       "      <td>Belem</td>\n",
+       "      <td>Proximidade</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>6</td>\n",
+       "      <td>21213088.57</td>\n",
+       "      <td>1378476</td>\n",
+       "      <td>15.39</td>\n",
+       "      <td>Berlin</td>\n",
+       "      <td>Proximidade</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>15</td>\n",
+       "      <td>21213088.57</td>\n",
+       "      <td>1378476</td>\n",
+       "      <td>15.39</td>\n",
+       "      <td>Buenos Aires</td>\n",
+       "      <td>Atacado</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>2</td>\n",
+       "      <td>21928421.28</td>\n",
+       "      <td>1412372</td>\n",
+       "      <td>15.53</td>\n",
+       "      <td>Chicago</td>\n",
+       "      <td>Varejo</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>13</td>\n",
+       "      <td>21213088.57</td>\n",
+       "      <td>1378476</td>\n",
+       "      <td>15.39</td>\n",
+       "      <td>Dubai</td>\n",
+       "      <td>Atacado</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>10</td>\n",
+       "      <td>15039911.54</td>\n",
+       "      <td>570745</td>\n",
+       "      <td>26.35</td>\n",
+       "      <td>Hong Kong</td>\n",
+       "      <td>Farma</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>9</td>\n",
+       "      <td>19471788.15</td>\n",
+       "      <td>671638</td>\n",
+       "      <td>28.99</td>\n",
+       "      <td>London</td>\n",
+       "      <td>Farma</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>12</td>\n",
+       "      <td>24129399.10</td>\n",
+       "      <td>831168</td>\n",
+       "      <td>29.03</td>\n",
+       "      <td>Madri</td>\n",
+       "      <td>Farma</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10</th>\n",
+       "      <td>19</td>\n",
+       "      <td>8376271.00</td>\n",
+       "      <td>612968</td>\n",
+       "      <td>13.67</td>\n",
+       "      <td>Miami</td>\n",
+       "      <td>Posto</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>11</th>\n",
+       "      <td>7</td>\n",
+       "      <td>21213088.57</td>\n",
+       "      <td>1378476</td>\n",
+       "      <td>15.39</td>\n",
+       "      <td>New York</td>\n",
+       "      <td>Proximidade</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>12</th>\n",
+       "      <td>5</td>\n",
+       "      <td>21213088.57</td>\n",
+       "      <td>1378476</td>\n",
+       "      <td>15.39</td>\n",
+       "      <td>Paris</td>\n",
+       "      <td>Proximidade</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>13</th>\n",
+       "      <td>11</td>\n",
+       "      <td>27172082.37</td>\n",
+       "      <td>918336</td>\n",
+       "      <td>29.59</td>\n",
+       "      <td>Rio de Janeiro</td>\n",
+       "      <td>Farma</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>14</th>\n",
+       "      <td>3</td>\n",
+       "      <td>21213088.57</td>\n",
+       "      <td>1378476</td>\n",
+       "      <td>15.39</td>\n",
+       "      <td>Roma</td>\n",
+       "      <td>Varejo</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>15</th>\n",
+       "      <td>16</td>\n",
+       "      <td>21213088.57</td>\n",
+       "      <td>1378476</td>\n",
+       "      <td>15.39</td>\n",
+       "      <td>Salvador</td>\n",
+       "      <td>Atacado</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>16</th>\n",
+       "      <td>1</td>\n",
+       "      <td>21213088.57</td>\n",
+       "      <td>1378476</td>\n",
+       "      <td>15.39</td>\n",
+       "      <td>Sao Paulo</td>\n",
+       "      <td>Varejo</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>17</th>\n",
+       "      <td>17</td>\n",
+       "      <td>8376271.00</td>\n",
+       "      <td>612968</td>\n",
+       "      <td>13.67</td>\n",
+       "      <td>Sidney</td>\n",
+       "      <td>Posto</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>18</th>\n",
+       "      <td>4</td>\n",
+       "      <td>21213088.57</td>\n",
+       "      <td>1378476</td>\n",
+       "      <td>15.39</td>\n",
+       "      <td>Tokio</td>\n",
+       "      <td>Varejo</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>19</th>\n",
+       "      <td>20</td>\n",
+       "      <td>8376271.00</td>\n",
+       "      <td>612968</td>\n",
+       "      <td>13.67</td>\n",
+       "      <td>Vancouver</td>\n",
+       "      <td>Posto</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "    STORE_CODE  total_value  total_qty     TM      STORE_NAME BUSINESS_NAME\n",
+       "0           14  21213088.57    1378476  15.39           Bahia       Atacado\n",
+       "1           18   8376271.00     612968  13.67         Bangkok         Posto\n",
+       "2            8  20989553.37    1365988  15.37           Belem   Proximidade\n",
+       "3            6  21213088.57    1378476  15.39          Berlin   Proximidade\n",
+       "4           15  21213088.57    1378476  15.39    Buenos Aires       Atacado\n",
+       "5            2  21928421.28    1412372  15.53         Chicago        Varejo\n",
+       "6           13  21213088.57    1378476  15.39           Dubai       Atacado\n",
+       "7           10  15039911.54     570745  26.35       Hong Kong         Farma\n",
+       "8            9  19471788.15     671638  28.99          London         Farma\n",
+       "9           12  24129399.10     831168  29.03           Madri         Farma\n",
+       "10          19   8376271.00     612968  13.67           Miami         Posto\n",
+       "11           7  21213088.57    1378476  15.39        New York   Proximidade\n",
+       "12           5  21213088.57    1378476  15.39           Paris   Proximidade\n",
+       "13          11  27172082.37     918336  29.59  Rio de Janeiro         Farma\n",
+       "14           3  21213088.57    1378476  15.39            Roma        Varejo\n",
+       "15          16  21213088.57    1378476  15.39        Salvador       Atacado\n",
+       "16           1  21213088.57    1378476  15.39       Sao Paulo        Varejo\n",
+       "17          17   8376271.00     612968  13.67          Sidney         Posto\n",
+       "18           4  21213088.57    1378476  15.39           Tokio        Varejo\n",
+       "19          20   8376271.00     612968  13.67       Vancouver         Posto"
+      ]
+     },
+     "execution_count": 27,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Calcula TM = total vendido / total qtd\n",
+    "# Para isso vamos agrupar por STORE_CODE e somar o SALES_VALUE e SALES_QTY, \n",
+    "# depois vamos calcular o TM dividindo o total de vendas pelo total de quantidade vendida.\n",
+    "\n",
+    "df_agg = df_q4.groupby('STORE_CODE').agg(\n",
+    "    total_value=('SALES_VALUE', 'sum'),\n",
+    "    total_qty=('SALES_QTY', 'sum')\n",
+    ").reset_index()\n",
+    "\n",
+    "# Agora criando essa columna TM, como esperado e usando round para arredondar para 2 casas \n",
+    "# decimais, como sugerido pelo desafio.\n",
+    "df_agg['TM'] = (df_agg['total_value'] / df_agg['total_qty']).round(2)\n",
+    "\n",
+    "# Junta com dados da loja, para obter o mesmo resultado devemos \n",
+    "# dar sort por ordem alfabetica do nome da loja\n",
+    "\n",
+    "df_rank = df_agg.merge(\n",
+    "    df_cad[['STORE_CODE', 'STORE_NAME', 'BUSINESS_NAME']],\n",
+    "    on='STORE_CODE'\n",
+    ").sort_values('STORE_NAME').reset_index(drop=True)\n",
+    "\n",
+    "df_rank"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Axes: xlabel='TM', ylabel='Loja'>"
+      ]
+     },
+     "execution_count": 28,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAABDYAAAISCAYAAAA3Pk9WAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjExLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlcelbwAAAAlwSFlzAAAPYQAAD2EBqD+naQAAlCpJREFUeJzt3Qd0VNX39vGd0HvvvSpVqihFqthQilJEFBuCYsGC2AURsYuKAgqiKIggSFFQxIKACIiCIL33Kr1D8q7n/N87v0lIyBAmyUzy/aw1K5nb5uZymOTu2WfviOjo6GgDAAAAAAAIQ5EpfQIAAAAAAACJRWADAAAAAACELQIbAAAAAAAgbBHYAAAAAAAAYYvABgAAAAAACFsENgAAAAAAQNgisAEAAAAAAMJW+pQ+AYS+v//+26Kjoy1DhgwpfSoAAAAAgDTg9OnTFhERYTVr1kxwWzI2kCAFNbwHECwaT6dOnWJcIagYVwg2xhSSAuMKjCuEg+gU/nv9Qu5BydhAgpSpoQFdvnx5y5o1K1cMQXHs2DFbsWIF4wpBxbhCsDGmkBQYV2BcIRwcS+G/15cuXRrwtmRsIGBKAwKCOZ6yZMnCuEJQMa4AAADSHjI2EJCMGTO6m1AgWDSeKleuzAVFUDGuwldUVLRFRhJABwAAF47ABgL2wZdzbdvug1wxAEBQFSuYy3re2oCrCgAAEoXABgKmoMbGbfu5YgAAAACAkJGqa2z88ssv9vTTT7uiJ3H5559/3PoDBw4k+7kBAAAAAICLl6ozNooXL24TJ060K6+80m666aZz1n/22We2YcMGy507d4qcHwAAAACkBWfPnrXTp0+n9GngApw8edL3NTIyMkm6b6ZLly4ox0rVgY0KFSpY1apVbcqUKecENo4cOWIzZ8603r17p9j5AQAAAEBqFh0dbTt37iRLPgxFRUVZ+vTpbfv27UkS2BAlGRQuXPiiOyWm6sCGtGvXzgYMGGD79u2zfPny+ZZPmzbN/UPdeOON7j/brFmzbNmyZbZr1y7LmTOnNW3a1OrUqeO2fffdd61Bgwa2e/duW7BggWXLls3atm3r+vl61q9fb99++617ndKlS1vr1q0tb968vvWbNm1y63X8smXLuvPS68hbb71lNWvWtGbNmvm217LatWvbmTNnbOHChW7KjL9+/fpZy5YtXTaKbNy40QVw9u/fb+XKlXPnp/OUd955x+rWreum3hw8eNA6depkZcqUSbJrDgAAAADiBTUKFixoWbNmvegbWCRvls3JkyctU6ZMQcus8OgeXCUjdI8tRYoUuajjpeoaG9KqVSv3j/Ddd9/FWK4pKi1atLBcuXJZ3759rX///q5NYKVKlWzdunXWpUsXW7Rokdv2559/tieeeMImT57sggYrVqywm2++2bZt2+bWKyjSpk0b27Fjh1s/f/58t/6///7zBVF0HlqvYMiPP/7oMkgU+RI9X7lyZYzz07LVq1db0aJF7dNPP7U1a9b41v3111/25ZdfWsmSJd1zvZ4CJXo9vf7s2bNdwGbv3r1u/U8//WS9evWyw4cPu0ibfmYAAAAASOobYy+ooQ+Zdb+VOXNmHmF0DTJlypQkx9VY0JjQ2NAY0Vi5GKk+sKGbeAUwlM3gUXbD33//7YIPUqtWLRs5cqTdc8891rlzZ/vwww/dRfYCG5InTx4bOnSo3X777e6r/jFmzJjh1r388svWsWNHGzhwoN1xxx1u/WOPPWZHjx61U6dOuewKHVvbaf2oUaNcyo2yMhJSuXJlq1ixosv28EydOtUuv/xyK1asmIt0vfjii3bfffe5AI0CMsOGDXNBj0GDBvn2UcCmT58+7uGfSQIAAAAAScGrqaFMDSAu3ti42PorqX4qimhaRrdu3VyhUE3B+Oabb1yqS/369d16TRvRtBRNF9FDmRIKSPhHjRT88NKmMmbM6CJLhw4dclkXmzdvtmuuuSbGaypjQpYsWeIiUDfccINvnTJIrr/+epeJEej5jxkzxh599FE3NWX69On25JNP+lK79HMpCPPUU0/59lH2hpexIZdcckkirx4AAAAAJB7TT5DUYyNNBDYaNmxohQoVclkbDz30kJtSomCBVwBFU0WUbaEMC2VHVKtWzQUvlA3hyZ49e4xjal8FQ7SPxDe9w2s1G7vzijJAjh8/Hu85+7+2giRvvvmmC5KohsaJEyd8gZQ9e/a4r6oHUqBAAd8+yuhQ2pCH6ScAAAAAgNQoTQQ2FIRQDQwFMK644gqX5aCaFF5mgzqjPPDAA3b//ff7gh2xa3LERzUwREVB1YUlrpazoswO/8DDli1bfM+VwRF7TpHqYXi0nYIzytRQcdKrr77aVxjUe31loqiYKAAAAADgXCqEqXtC1SDU/ZnqPKhGocoRXHrppRd0yfQB9+DBg61r166uq0eoeOutt1zTiM8++8zSklRfY8OjDA3V1tDgU4eQEiVKuOWqwqrpHepK4gU1JkyY4AIIgczzUYBBU1pGjx7tC07oqzJA5s2b5wIbajk7fPhw33plWeg1vKwLTYv5999/fcecM2eOe31/CsyooOivv/7qfhZP/vz5XbaGju+fAfLxxx8HPNUFAAAAAFIz3QuqxuKIESNcB0zVQVQ2v+75dK+lOogXYubMmfbJJ5+4e8lQcvvtt7vGGGlNmsjY8DIaFLxQu9bXXnvNt1xTTxo1auS6hihAocwLZUuoaKfX9SQhKt559913u1odOt7y5ctdgc4HH3zQzRlSkEPFPdUZRRFBtW9VK9eePXu6/bVvjx497LbbbrMcOXLY1q1b3ev7UwFUvY6iiso68aeipKohojoeCqKsXbvWBTlUxBQAAAAA0jLdGylDXx9KK5PBv5ip7q1UdmDAgAFWo0YNq169uoWzggULWlqUZgIbosCAWrVee+21vmXK0lB2g4pvKntDmRxVqlRx7Ve9wMbDDz98Tl9d/2WlS5e277//3gVNDh48aHfddZer0+FRsEMdVLz12lfLPAqoKOL3559/uv9sV155pTsf/+4lqvnx7rvvWoYMGXyZJf5BG01T0f4qGKoAiYqdaltR0EYdVAAAAAAgrZk0aZKtW7fONWSIq0OLShLow21NVfGsWrXKPv/8c3f/qKyMUqVKuQ6XypZX9v0777zjtrvzzjtdSQD/5g66v1QXTt23abaAPoT2v7dTtr4yR9QEQqUFOnToYOPGjXNBle7du8c4jrbV6+uDcXXa9AIXr7/+ujtnlS347bff3PE1O+H9998/ZyrK+X6W1CJNBTbU8lSP2JRVEfsfVRkTXtZE8+bNz9kn9jIFHlQHIz4JrdcAVacUj4IbsXldXOKiIEZc+3jZHgAAAACQFulDZDVz0Ie/cVFQ4NVXX/U9V2CgS5cu7tG3b18X8FBQRPU0fvjhB3cvqKYOb7zxhpv2oax8b7pLp06d3AffTzzxhLtHGzRokLVv397Gjx/vXmfx4sXuOCpL8Pzzz7t9VPNRNTu8+ol6fW1Tr1491xlTHTsVsFCdyC+//NJ9GK8P5VUvpHHjxvbCCy/Y0qVL3T2nyh6onmOgP4tXEzLcpanABgAAAAAgbdFUf93AB9pa9KOPPnIZ9l4WhugDcjWYUDBAmRNeIwgFGbwsCgVH9BrKtFCJAVF5ANX0+OCDD1wgQ5kWOra+ioItmgqjeh8eBUuUcf/hhx/6svVVVkEBFe2nIIeohqOCFYUKFYp3Ck0gP0tqQGADAStWMO6WtgAAXAx+vwAAkpICAOpEGag+ffpYpkyZXHmC9evXu4cyH+TIkSNx7qOsCjWBuPHGG31BDdH3yrz45ZdfXPDir7/+chka/tT1MnPmzO57ZYLotVROwL8EgYIfysT/9ttvLSoqyi3LmTOnC2oE+2cJRwQ2ELCetzbgagEAkkRUVLRFRgb2SRoAABdCtRGVtREoTQtR3Q3V5Shfvrxr0KDOKbNmzfIFFWJTQEIdVn7++ecYNR1FHS9VwFTTR6Kjo33ZHh5leXhZH6qZKHEFLNRW9sSJE3bs2DH3PF++fEnys4QjAhsIiCKQ+s+orixAMGg8qWCSit8yrhAsjKvwRVADAJBUVItQjRjUHCKupgrK6FCmhTIn1OhB3SuV5fDrr7/6Agz6G+N8vL9n1alSzRxiU/AiV67/y4A/dOjQOeu9ZV5x07i2UfBEmSdqOBGIs2fPJupnCUcx22sA56HoIhDM8aQ3VcYVgolxBQAAYlPRTQUMhg0bFufFmTp1qstoUL0MZUwou0NZF/5ZE8uWLYuxT+xOlZoWoqKhmuqhYqL+D69biTIsFFhRAVF/+rDvwIED7nutV0aHOmrG/htn4cKFroNnoLVC9gb4s6QGBDYAAAAAAKmWpnA899xzrjOJCnx6QQRNxVArWBXgVP0KTdFQUCF//vw2d+5c35QPBQcGDBjgvtdUEPGyJg4ePOjLgNCUj3nz5tknn3zi+/BOXUymT5/um56ibfT8p59+cs/VslWvL17AQttoSovOV8dR5oW6q6xevdp69OgR8M9dIMCfJTVgKgoCFmhkEAh0PCllj3GFYGJcAQCAuNx8880uwDFkyBBr2LChu+n/77//XKbFAw88YHfeeaelT/9/t8dvv/22PfXUU9agQQPLkyePm5avlq2aBrJ8+XK3Te3atV2Gxh133GE1atSwESNGuMCI6mwoO0NZGioIqsyOV155xbV3FR1n586drh2s/hZWcKFz586uqKg3nUVTWRTQeOedd1xLWR1T56vpNOqMEqjIyMiAfpbUICKaPHAkQD2RpVq1alwrAECaKh6qT7hWrFjhWuN5854BxhVCUSi+X+mm3aup5nX9CAUKFOzZs8d1GlFgIy66TVaxz4wZM7qAgGgfdRLRz+NlfKhuh7I38ubNG2PfXbt2ueBB7EKhHgUYdHwFW86cOeOCIy+99JJ16NDBt42OryBIhgwZzjmO9j158qSbPhN7ua57yZIlL+hniYsyRXQs/dtdSFeZYI2RC7kPJWMDAfvgy7m2bfdBrhgAIOjtXum8BQBILgoUFC1aNMEs0NidSRRc8A8wKCMidmDB21cBi7io5ateX1kcxYsXd0EWZWKosGjsbAwdP77z9LqoBLI8IoCfJdwR2EDAFNTYuG0/VwwAAAAAEuGuu+6yfv36Wb169XzTYSpUqGAjR44MqH0r4kZgI5bJkye7SrYeRdMU3WrSpEmyRrTGjBnj5mzVr18/RfYHAAAAAARXrVq13D2nioaqiKkyNeKbDoPA0RUllmnTptn333/vev3qodQgLWvZsqX9/ffflly+/vprmz9/fortDwAAAABIGjly5HDTWAhqBAcZG3HQXCdVxvV3++23u6q0o0aNCtKlBwAAAAAAF4vARoCqVq1qv/76a4xlK1eudJVaVfFWKUSNGjVy0z9k9OjRVrNmTdfTeOHCha5SrnoX+09nUQXdmTNnuqIwV111lS1btsxF7vR9bD/++KN7PbUh0jayf/9+199Yr68qsuq9rKkzcYlrfwAAAAAAwh1TUQKkoIP6EnvUl1hBgtWrV7vpKpon1apVKxc8kHHjxlmfPn1swIABbv7UhAkT3Pq9e/e69XPnzrXrrrvOFi1aZJs2bXK9it98802bN2/eOa+tfR999FErV66cLyjx+++/u17I06dPd2163nvvPdebWcGOQPYHAAAAACA1IGMjDgo0aNqJKGixZMkS1yNYwQdPlixZbMSIEValShX3vGfPni5jY/bs2XbppZf69v3mm28sffr0dv/997sCpApE6DjPP/+8+6rgh9x4440xehb7ByVefPFFe/311+366693y9Tn+KmnnnLP+/bt62sb1Lp1a3v77betf//+590fAAAAAIDUgsBGHNKlS+cKh7oLlD69q7mhgIRa84wdO9atv+eee9z6EydO2ObNm13mhqaUKOjgueKKK9z+kj17ditSpIhr56OsDk1DueWWW3zbXnbZZb6AiEfTTNasWWNdunSJEZTQ/pp+0qlTpxiBFmWU6PwS2h8AAAAAgNSCwEaAxUMbN27spnNoColqYPzxxx8uC2LFihVWuHBhq1atmkVFRVl0dLRvH9Xd8KfAh7bxpqPkzZs3xvr8+fPHeL5u3Tr3Wsr6uPfee93ryKFDh+LcXvU7Dh48mOD+AAAAAACkFgQ2AlS7dm33VRkXqpnRo0cPV9Ni5MiRvgCGpqIEwgsw7Nmzx/LkyeNbroBHxYoVfc81VeXJJ590mRiacjJ06FC3XJkfsnv37hjBDWVx5MuXL8H9AQAAAACB2b59uw0fPtz3PCIiwmXx64PlZs2auVqGwXLq1Ck3CyBr1qz881wAiocGSMU6lXFRq1Yt27Jli+t2ouKfXlBj1qxZLtDgPxUlPhr46p7y9ddf+5apu8qqVatibKfBrC4nL730kuvIMnXqVLe8ZMmSrgvKmDFjfNsePXrUJk6c6Op4JLQ/AAAAAKSkqKjosHndffv2ua6XKldQtmxZdy9WtGhRVyLgpptush9++CEo56bse9VeVM1HXBgyNhIoHipbt2519SpUIFRBBRUFVdFQZUO0bNnSZUr89ddfLlih4EZCFN174YUXXEFR1ecoVKiQ64ai7A0FT+LKFmnfvr3rsNKgQQM3hUXf33fffW5/ZXkosKLsjV69egW0PwAAAACklMjICPvgy7m2bff/ptIntWIFc1nPWxsken91paxRo0aMZaq5qAYOWnexNDNg48aNF32ctIjARizqLOI/mBSEuPzyy13AoESJEm6ZsiBUpHPGjBluOkmdOnVc0EDdUxRoEBXsLFWqVIxj+y9TgGHatGkuk0KRvwcffNAVJ1WRUencubMLonieeOIJFxXcsGGDC0woWPHjjz+6gIsie+qyomPqfAPZHwAAAABSkoIaG7ftD+t/BH3IrOx+j2oq6j5x+fLlljFjRmvRokWMJhFqOvHTTz+5gIgyP7Re94BHjhyx999/323z0UcfuUyQpk2bJng8/B8CG7EE2j1Eg6pVq1Yxll155ZXuIcqQiM1bpgKjGrTXXnutC3bIzp07XaZI1apV3XP/jimiKS/K8PCnAEXs7TyB7A8AAAAASByVIZgzZ47rcCkKTqh75oEDB1xgQpn9ui977rnnXEdLZelrFkDHjh1dfY7x48e7OohTpkxxH1B7H6SrmYXu9RI6Hv6HwEYKULGZ9evX29133+1SlvRc87IU6Ai0ACkAAAAAIPl88sknvuYNCjqoHIEyLz799FO3TF/1YbUyLHLmzOmWXXLJJfbyyy9b8+bNXc3Dhg0bWp8+fdw6BSdUJ1FTUNQEQk0f9AG4PmyvVKmSDR48+LzHU3AE/4fARgpRDY8FCxa4gjMyaNAgX+eVUKU5aQAA8PsFAJAWFStWzD28DH5lUdStW9eVFhBlb6hLiheEkHbt2rlmDgsXLnSZHepW2bt3bzfNpH79+r4M/rgkdLxAZxukBQQ2UoiyNOrVq+ce4eJiCu0AAJBQlXoVkgMAIFTFVTzUn7I4lHnhL0uWLK5bpdZpCkru3Lldlsazzz7rWrvecMMNLtgRV3vXhI6H/6HdKwKi/3RqcQsEi8aTiiAxrhBMjKvwRVADABDulM2xffv2GMtUH+PYsWO+KSwKjgwbNszmz59v7777rptm8sUXXyT6ePg/BDYQMBU9BYI5nnQTyrhCMDGuAABASlHHEnU82bJli2/ZiBEjLEeOHC5Tf+TIkS6Q4U1lueqqq9w6ZfN73TdFnVACOR7+h6koAAAAAIBUX8MvqV9PHUtUF0N1MBS02L17t6up+Pbbb1u2bNmsZMmS9vjjj9s333zjMi4WL17sup906NDB7a9pJyoI+sorr7j6GZ07dz7v8fA/BDYQMC+SCARrPGmOIOMKwcS4AgAgfGorpUQNv8TUdNKUkOeff961YU3o7xBNL/nnn39cAEJFP9UFJXv27G69OpkoA0NNJA4dOuS6YirzIn36/7st19evvvrKfv/9dytdunSCx8P/ENhAQJQqpZtQIFg0nipXrswFRVAxrsIXxUMBIG1JqdpKiXldZVWcr3tJbNWrV3ePuCgr47rrrjtvEKV9+/YBHw//h8AGAvbBl3Nt2+6DXDEAQNBTg+m8BQAAEovABgKmoMbGbfu5YgAAAACAkEFgI4jWrl1ry5YtszNnzlipUqWsZs2avvlSMm3aNJdadNlll8W5/5QpU6xcuXJWpUqVYJ4WAAAAAACpFoGNIDh58qQ99thj9vfff9uVV17p2vR8/PHHrk3PBx98YBUrVnTbqQfx+epUfPjhh67iLYENAAAAAAACQ2AjCD755BNbvny5/fDDD66nsCio8cADD7h2PlOnTnXL7r333mC8HAAAAAAA+P8IbASBpp+ULVvWF9SQyMhIe/DBB23ixIkuoyNTpkznTEU5cOCA60usIEjTpk1jHFPbXnLJJe44ixYtcn2KGzdubFmzZvVto+POnTvX9u/f76aw1KhRwy1funSprVixwtcP2fPtt9+63slU1AUAAAAApBYENoJAU0fef/99Gzx4sJtKUrRoUbe8atWq7uEZPny4NWrUyAU2/vrrL7vvvvvs0ksvdS1/NGXl4MH/dRwZNmyYC2bs2bPHatWqZQsXLrTXX3/dJk2aZLly5bKNGzfa3Xff7fZVUEPTWNTrWF9Pnz7t+izrvLxpLfv27bMnn3zSRo0aFYwfGQAAAACAkEBgIwg0xWTz5s0usKEAhwIMqrXRqlUrq1OnTpz7PPPMM65/cf/+/d3zmTNnWs+ePWNss3PnTvvuu+9cXY7//vvPmjdvbtOnT7dOnTrZCy+8YA0bNrSXXnrJbXv8+HGXoTFkyBDr1auXK16qIIgX2NB+RYoUsdq1awfjRwYAAAAAICREpvQJpAYZM2a0V1991X766SeXKaEMCtXVuO2221wAIrZ169bZhg0brGPHjr5lLVq0cIEHfwpceMVG8+bNa8WLF7ddu3a5IMf8+fPd637xxRfuMWHCBMufP7/99ttvbvubbrrJBUXUocWbhqJlERERSXw1AAAAAABIPmRsBJHqZ3Tp0sU9Tp065aaOfP7553bjjTda3bp1fdvt3r3bfS1QoECM/WMHNvLkyRPjueptqB7H1q1b3XNNXVm/fr1vfZkyZSx79uzu+9atW7vskdmzZ1uFChVs8eLFNnDgwGD+uAAAAACQ6qm75dChQ33P9WFx+vTp3f1cs2bNfF0wk8I///zjPjR/9tlnk2T/P//803755Rfr3bt3oo5/sfsHC4GNi3TixAn7+uuvrUmTJi6jwqNsCtW0GDt2rJum4h/Y8AIWKvpZqFAh3/JDhw4F9JqqqyFt27a1+vXrx7lNiRIlXG0OZW2UL1/eFQxV4AMAAAAAUlp0VJRFREaGxeuqXuFXX33lShB493xnz551TRvatGljb775pl1//fVJcr45c+a8qMBJzgT2X7NmjSthkNjAxMXuHywENi6Sup2o3euSJUvsjTfeiLFOU0aUYVGzZs0YyzWwChcubFOmTHHFQ70B4Z99cT4qTqo6Hgqa+Ac21GFFtTauvvpq91z/yXRO+g93xx13XOyPCgAAAABBoeDChm8/tuP7diTbFc2Sr4iVadUt0fvrPsvrROk5duyYDRo0KMkCG7rv0yOl9g8XBDYuktKQFDxQ4U91RFFmhlKSVPhTNTf69OnjWsHGnlKioqFqB6usDU1hUY2M3LlzB/yaKhqqriqKGl5++eUuMPLjjz+6/1QeFSd9+eWXbdu2bUn2Hw0AAAAAEkNBjeO7Nof1xVN2vD5glkWLFrmpGcqWV+3DypUru7IEyu74/vvv7d9//3WZ/QqQeE0e1IBCy3RvJ9pWGSCXXHKJ+6DafyrJ33//bX/88YcrOzBx4kQ7fPiwmzlw5ZVX2qxZs+z33393dRdVy1GZGnFNRTly5IhNnjzZddn0zsGfajpqasmWLVtct03dy6pWY9asWQPaX+evxhV6XdWJ1Pl5H+YnJYqHBoE6jairidqvZs6c2bVoVb2MTz/91Lp27erbTsEFL8J31VVXuZQdBTVUj0PtXrt37+4bHDfccMM50UD/ZfXq1XPTTBTUUGqUBosGrAaOR4NZg7xx48bn1OsAAAAAACSebvwVwPAy9JWB//HHH7taiyofoGwOBQLUvVIBjFy5crnyAwo8jB492u1TrVo1e+utt3xNIDQbQNNevG6Wajqh0gfe96NGjXL3jenSpXPZ+nfeeaf16NHD1XbUa+oeU/elHv/9vXNRUEQfxuv+UfehnlWrVrl7Vs1GUMkEfSD/2muv2XPPPRfQ/pqtcNddd9mwYcNcgEU1IdVQY/z48Uk+zMjYCBIV7VR71/NRdoU/Rb+UteFRRM/jRez8xV6m+V1xbedRR5QVK1a4rA0AAAAAQOINHz7cZSHI0aNHXQaF7rkUyPAoi0L3X94H1u+9954rPqrseq/Rg5o7DBgwwGVu6EPoW265xWXkK1NDDSDUaVM1E+Oicgfapk6dOu65umVu27bNlTlQZr+W33rrra5hRcGCBWPsq+CHzu+bb75xJRW6devmGl8o+0JOnjzpzl2Z/172hT649wITCe2vAIrqS06bNs2X4aEAjepvqAtoUn7YTmAjlVKkb+HChS4jRNkhAAAAAIDEK1WqlK94qKaPKCChG3d971GWgwIXHk0PUecUL6jhNYHo27evu19TVv7TTz/tpnt07tzZGjVqZO3bt4/3HHR8NYnwKHhRpkwZF9TwbzShbInYgQ2di46voIRoH72+l3WhKTR6KNNk06ZNtm7dOlevUQGOQPbXlBxlkrz66qu+19TsBB1v5cqVbjZBUiGwkUopDUhpTUr98Qb5xSpWMFdQjgMAAL9fAADhJq7iobFly5YtRqBD0ze8LA+PsiCU0aCsD1HQ44orrnB1FxP6UFr7KrjhL9P/DzT4i46OPmfZgQMHrGrVqjGWeYEQb72CLKrXoakoqvOhe0nvWAntrywRNcmoVKlSjG0uu+wyV6ohKRHYSKViT3sJhp63Ngj6MQEAkKioaIuMDE4gHgCAUKEMD01F8acGEspiUJ0KmTdvnqtboUyMt99+25o2beo6YQZboUKFXJMLf6oP6dGUGtUJUf1Ivb4yNYYMGeKyNgLZX0EN1X/UVJjkRvFQBEQpRCpOAwSLxtPy5csZVwgqxlX4IqgBAEitWR4KFHh1KEQFRtXoQY0glNHxzDPPuCkdn332mQseqINJXBkXF+u6666zn3/+2XU88e7xlCXi0XLVgfSCKsrQUIFQFUkNZP+WLVu66TV6eFavXm0vvviiC3gkJTI2ELCk+M+FtD2edBPKuALjCgCAtClLviKp+vWkXbt2rjaF6nE0bNjQTddYu3atDRo0yE1b6dOnjytA+sILL7gpLKpP0alTJxszZowrKxDsc5k3b547lwYNGrgPGb0in6JMCxX6vOeee1yhTxUmVfdN1dtQzY6E9ldHlblz57quLCqKqoCIghz6efynrCQFAhsAAAAAgGQVHRVlZVp1S5HXjYhVoyIhasigYp/xdSrxaCqJalT4U40KtXNVEEAdK9XyVUU0FdTQdBS1ir3jjjvcclHxzg8//NAFErz6FMroENX38L73qN1rHr9uIwog6FyV+RF7f52LOq/8888/LrjStWtXV/9j0aJFvsCEamgsXrzYnd8TTzzhgi3Tp093H0jqHM+3v6jbi5b/+++/bl+1ik3ougVDRDQflyIBmlOlNCO1o82SJQvXC0GhN0f11VYVZ8YVgoVxhWDTH536Q1SF0Pw/lQIYVwg1ofh+deLECd/feyp6ifBy9uxZ92+ofzt1O0nuMeLV9lBTjISQsYGAKNrGzSeCSeNJwTKAcQWheCgAAEgsAhsI2AdfzrVtu/8vJQoAgGBRO3E6bwEAgMQisIGAKaixcdt+rhgAAAAAIGTQ7jWJLFmyxLX1WbduXZzrt23b5tavWrXKt2zBggXxbh8MSX18AAAAAACSG4GNJDJs2DB7+OGH7ZVXXolz/fvvv+/Wf/31175lv/zyi6uWm1SS+vgAAAAAACQ3pqIkIbXjUd/e/fv3x2jBow4jaolTrly5GNurh3FSSurjAwAAAACQ3MjYSEK5c+d2fYN//PHHGMt/++03q1OnjkXG6p8ce6qIWt+sXLnSZs2aZX///bcLiHj++OMP2759uwuazJ492/UJ9qxevdp+//13+++//857fAAAAAAAwh0ZG0msefPmNn36dOvQoYNv2bRp0+z6668/Z1rIq6++ao0aNbJHH33U7fPiiy+6rA71oVYPX/X1HT9+vBUqVMgGDhzo1qmWR8mSJe2vv/6ya6+91s6cOWPr1693XxX4GDVqlFWpUuWc4wMAAAAAkBqQsZEMgQ1lSnjZE8ePH7d58+ZZgwYNzrufsjr69etnX375pY0YMcIFOg4fPuyCIp4///zTJkyYYCNHjrQXXnjBJk2aZPny5bNvvvnGpkyZYhUrVrQvvvgiqX9EAAAAAABSDIGNJFaiRAmXWeFNR1EBz5o1a1qWLFnOu58yMq677jr3fXR0tAtq5MyZ001P8TRp0sRNd5FLLrnEfW3Tpo37GhER4Zbt2rUryX42AAAAAEjNdu7caU899ZQrDRCXkydP2jPPPONKBQTbjBkzbPDgwUE/bmrEVJRknI7SsWNH++6779zzhGzdutU++ugjN8Vky5YtLhPj0KFDLsjh8S9Imi5dOvdVwQ+PanhERUUF/ecBAAAAgIuh+5TYNQdD8XVVBkANIVTvUB9Qx6YPsJUxr46XwVa8eHHLkCFD0I+bGhHYSAYtWrRw7V83bdrkinr279//vNvrP02XLl1cpsfTTz9tlSpVsrx58wYUEAEAAACAUKfgwrBZo2z7weTLMC+aq5B1b3zHBe2jTPi2bdva8OHD7ciRI5Y9e/YY6xXUqF+/vhUuXDjIZ2tWuXJl90DCCGwkAxXvVKTvueeec98rSHE+a9eutR07dti7777ruqqIupmoGCgZGAAAAABSAwU1Nu3baqFOgQ1NCVF2hr73aNq/Prh+66233PNVq1bZnDlzXPa9AjfVq1e3Vq1auex6ZfCro6XXGKJhw4bWtGlTFyyZOHGiuwdUcETlCMqUKeObiqKOlw8++KB7fvToURdI0b2hMvVvvPFGK1++fApdldBCjY1k0qxZM1dENJCsi1KlSlmBAgXcf5Bvv/3WFQ+966673OA9cOBAspwvAAAAAMCsWLFiVq9ePZs6dWqMy6HmDbpHU4b+Tz/9ZJ06dXL3a5deeqmlT5/enn32Wfdhtfz777/29ttvu2PoeMoEUamBdu3a2a+//uoaP6jhxM033+zqMnr7/Pzzz+57lSdQ0OP77793gY+9e/e6+ooKfoCMjSTjZVp4Wrdu7bIwrr76at8y/eeoUKFCjOeKuGXLls11Qxk9erQb1JpbpeCGWrsqOue/rUcpUQqa+Bcl1X8or7hoXPsAAAAAABKmAITKBOzevdsKFizolil7QlkTGTNmtBw5ctjQoUPdPZdHgQvV5/CoQ+agQYPctvLqq6+6Woq611OgQ3Tvp46X6pLpT0GR/Pnz26hRo3w1QrSvtm3SpIk7h7SMqShJpHv37jGeKw3pww8/jLFM1XP99enTJ0Y3FVXf9ecfBIm9r7aPffwOHTrEe3wAAAAAQGBatmxpL730kmsGoWx6dUnZsGGDvfPOO2795Zdf7r4qk2Ljxo22fv16NzXFv/inppp4QQ3RNBY1h1DAxKPpKgqebNu2Lcbrz5s3z+6+++4YhU8VVFEtx5UrV7r7zbSMwAYAAAAAAOehzHhNBZkyZYoLbChbQ4U91ehBFMjQB8nLly+3smXLuuXKxFc7WE+uXLliHHPPnj0uw8MLiniuueYaV4vD37Fjx2J0xRQvO//48eNp/t+OwAYCVqxgzP+IAAAEA79fAADhMh1l/PjxtmbNGlfr4qGHHoqRUa/gx/z5832dU7RMRUHjU7RoUbePjpsQTVGJncWhuhtSoEABS+sIbCBgPW9twNUCACSJqKhoi4z8v/nFAACEolq1alnp0qXdlBRlSWgqiGfnzp2unqIX1FAGx8yZM12h0Phce+21rtvKvffea+XKlXPLZs+e7bqvqKOmP2WLjBs3zrp06eJqbZw5c8Y+/vhjV3S0bNmyltYR2EBATp065f7z+hcnBS6GxpPmJaqqM+MKwcK4Cl8ENQAg7Smaq1DYvZ6yK1TIU4EG/0YNd955p73xxhuuvoY6oqilqwIhixcvtqioqDiPpX3++usvu+WWW+zKK690HVVWrFjhMj1iFwPt1q2bq+uh9rF16tRxTSXOnj17Tp3FtIrABgKmwjZAMMeTbkIZVwgmxhUAAOFBN/vdG9+RIq/rX4DzQrVv395N/ahZs+Y5QYqrrrrKFQxVLYyqVau6D4fVylX1MZSdUbt27Rj7qLDokCFDXPFPTW9RtoeO6x8w8c41c+bM9sknn7iAyaZNm9w5KMCRLl26RP8sqQmBDQAAAABAsrqY4EJKvm7evHnjrYmhKSGxp4V42yrQEZ9LL73UPWI7fPjwOQVHq1Wr5h6IKWVGE8KS11sZCNZ40hQUxhWCiXGFYGNMAQCSmzI9HnnkEZs6dao1a9aMf4AAkLGBgGiOF3UQEEwaT2qRBTCukJreq6KjoiwihT6FBACkDqqdoRoet99+u5tugoQR2EDANnz7sR3ft4MrBgBAHLLkK2JlWnXj2gAALjqorpocCByBDQRMQY3juzZzxQAAAAAAIYPARpCpX/GhQ4f+d4HTp7eCBQu6x4VQZVxV0y1UKHlbIAEAAAAAEE4IbATZa6+9ZosWLfJVwz158qRrx6PKte+++66rohuIXr162U033WQPPPBAsE8RAAAAAIBUg8BGErjssstsxIgRvucHDhywm2++2QYOHGhvvPFGUrwkAAAAAABpEmW7k0Hu3LmtRYsW9s8//5yzbteuXbZq1So7ceJEgseJb1st+++//1xbIE1h0Xaeffv22erVq906AAAAAABSGzI2kokCD5qO4jl48KD17t3b/vrrLytcuLBt27bN7rjjDjcFJSIiIsa+CW375JNPuiyRuXPnWtasWV2dj65du1pUVJR9//33dubMGbfdp59+auXKlUuuHxkAAAAAgCRHYCMJHDlyxBYvXuy+P336tP3999+2ZcsWGzp0qG+bV155xa379ddfLXv27LZ582br3LmzFSlSxDp16hTjeIFsO2PGDJswYYIVK1bMPv/8c3v55Zetbdu29vPPP7sAR4cOHeyzzz6zl156KSl+ZAAAAABI9f78808bO3astW/f3urVq3fO+qNHj1p0dLS7b0sJ8+bNsx9//NFeeOEFS0uYipIE1q1b54IReqiuxieffOICHR9//LEv8DF58mRr3LixrV271q1TRsfll19uU6ZMiXGsQLdt3ry5C2pIjRo13FcFPyIjI11nFmWLKNMDAAAAAFJadFRUWL6usuAVPPjoo4/OWbd//3677rrr3IfaKWXjxo32ww8/WFpDxkYyFA9VxoS6pQwfPtxuuOEGF8HTY9KkSTZt2rQY+8bumqKOKoFsmy9fPt/3CmTEXp8uXTo7e/ZsEH9KAAAAAEiciMhIWzxkmB3ZviPZLmH2okWsxv3dE72/AhfKon/ooYfsnXfesa1bt1rx4sVjZGv41ztE8iGwkQyUNXHXXXe56J4KfSrwIc8//7zVrl37vPtmyZIloG1j1+UAAAAAgFCmoMahTZssXEydOtUyZ87s7u00/X/8+PH26KOPunWHDx922fqioEe7du3s2muvdWUEZs6c6bI4VPvw0ksvtTZt2li2bNnctmoMoUz8ZcuWuXu/Zs2axZjiktD+6sA5btw494F4lSpV3Ifi/tREQjMA/v33X8uYMaO1bNnS6tSpY6kNU1GSiaJ5UqJECfdQpxTVxfCnqSIKfPi7kG0BAAAAAEnjm2++sSZNmvgCBKpxqGCDaFndunXd97Vq1bLSpUu7YEXr1q1t+/btLuhQqFAhGzRokD399NNuu5MnT7ryAQqSlC9f3gU2Hn74YRszZoxbn9D+ajJxyy232KxZs6xy5cpuisx7773nO1+tV4Bl9OjRromEzvHuu+92MwlSGzI2krh4qCJmCkK8//77LvKmrAtlV6jLiQq6aPCqXsaaNWvsgw8+sAceeMAuueQS37EyZMgQ8LYAAAAAgODTh8rLly9392ByzTXXuICBmjUoyJEpUyZr0aKFy9pQfURlVqxYscIFIvTcv2yAAhny1VdfuQ/Af/rpJ8uRI4dbpiwPbzqLygmcb/9Ro0a5wMrIkSNd0OK2226zO++8090visojKKNDxUS9mQBly5Z1swFatWrlOm6mFgQ2gkwDZdGiRa5wqDcNRRkXas968803+6aMKLKWP39+mzhxoi1cuNAKFizo/hOoCKhUqlTJN9AS2lbBDXVI8WjQarqLBrdHc790LgAAAACAC6N7Md1nNWrUyD1XdobqHCo4ocBGXHRPp4eaP6xfv94V9lRWhZflsWDBAvfhtxfUEAVE9Ahk/z/++MMaNmwY475PARcvsKH1TZs29QU1RDUfn3nmGdfdRcGN1ILARpD16dMn4G2VxqRHXDQvK9BtX3/99RjPlfakeVb+lHIEAAAAALgwCiR49TWee+65GNkTc+fOdfUvVEIgtn379tljjz3mggi6R1PAIleuXDGKjXqdLeOS0P6q6+EfFIndQOL48eMxthdllujnOHbsmKUmBDYAAAAAAIiHalgoyKBCof6Z8ioz0K9fP1dEVAGI2NQZc8+ePTZ79mxfwGHo0KE2f/58933RokVt586d8V73hPbXuajsgT//riwKmni1Hj179+51AQ/V60hNCGwgYFny/e8/MQAA4PckAKSVoqGlSpWy7t27n9ONUk0eVERULWBVH1G8qSIKWqgkgBeUUJBC254+fdo3beT+++939Tu82onqgKLSBpoJkND+mlby7LPP2rp161xxUGVhKMgSe9rJ6tWrrWLFim7Zhx9+aHny5HG1G1MTAhsIWJlW3bhaAACcR3RUlEVQ0woAApK9aJGQf739+/fbr7/+ao888sg5QQ1Rwc6ePXu6IqIqHqosCTV+UFCha9eu1qtXL7v11ltdMGHJkiUuoDB9+nRXN+Oqq65yXVE6derkam2oS4oKlL766qvu2Antf9NNN7lpKu3bt3fLFcBQJobWyY033ujqeHTs2NHVBNm9e7fL2Bg8eHCMuhupQUR07Ea3QCxLly51/Y/VQii1/QdAylEK3IYNG6xMmTKMKzCuELJ4r0JS0Keq6pagooBZs2blIiPVjqsTJ074/t5TXYdQCARf6Osqa0JTP1TvMHa9Cjl79qx99913LqNDDRw0ZUUNHxTgqFatmpsaovupbNmy+e6nFJi44oorfNNBVBRU/3bZs2d3rWK1rSeQ/deuXeseamShY2h7ZYN4vOPr/OvUqROj2Oj56GfTv6H+7dShJbnHiH4O0XVMCBkbCBgxMAR7POmGgXEFxhVCGe9VAJA0Uiq77UJfV50qW7duHe963fArc8KjTilq2epR8CF2PYvYx1NhUD3iEsj+5cuXdw+PancEevzUgv6fAAAAAAAgbBHYQMDimlMGXMx4Uiod4wrBxLhCsDGmAAAIfUxFQUA0D4v6GggmjSfNEwQYV0ht71VRUVEWSQFRAACSDYENBGzYrFG2/eD/+iIDAICYiuYqZN0b38FlAQAgGRHYQMAU1Ni0bytXDAAAAAAQMtJsYOPAgQOufY36ASd1uqj6CKv9kkevp1Y2efPmDerrqBWQWjvlyJEjqMcFAAAAACBUpbnAxvjx423o0KG2f/9+y5Ahg5sHe+ONN9oTTzyRZP2eX3nlFfv++++tYMGCvmVHjx619OnT24MPPmi33nprUF6na9eurtXQAw88EJTjAQAAAAAQ6tJUYEPBhQEDBtiHH35o9evXd8vWrVtn999/v8uqGDRoUJK9tgqPjRs3Lsayzz77zPr27WsVKlSwOnXqJNlrAwAAAACQWqWpdq/Tpk2zyy+/3BfUkHLlylmvXr1s6dKldvLkyRjba6qKpnf4TyPxd+bMGduzZ4/bLjHuuOMOlyUye/bsgF5Xyw4fPpzgsmCeIwAAAAAAoSxNZWyonsb06dNt2bJlVrVqVd/y66+/3j08CnIok2Lr1q2WLl06N23liiuusMGDB1u2bNns0KFDNnDgQPv22299LVB79Ohhd9999wWdj6ajKJiSL1++gF43rqkmWtauXTu77777Yhw7WOcIAAAAAGmZsvt1nxafl156yXLnzp2s54Q0HNjo3r27y464+eab7ZJLLnGZG1deeaV7ZMyY0bfd66+/bo0bN3b1L1To859//rHOnTvb5MmT3dfevXvbjh077Mcff7TChQvb3Llz3XQWFe1s3759nK996tQpF7CQ6Oho27lzp3300UeWM2dOu+GGGwJ63QuRmHMEAAAAgOQQFRVtkZERYfG6yqT/4Ycf3IfJVapUOWe9GkMgZaWpwEbRokVt6tSpLlDw008/2dixY23kyJEuY6Jfv3529dVXu+0+//zzGPtp8BYqVMgOHjxo27dvt19//dUFJRQwkAYNGljbtm3tiy++iDdosHbtWjf1RCIiIix79uzuuKNHj/ZlbJzvdS9EYs8RAAAAAJKDgguTx823vXvin1YfbPkL5LDWHeolev9atWpZ06ZNg3pOCI40FdgQTelQ9oMeyqL4888/7c0333R1NlSDo1SpUnb8+HGbNGmSLVq0yDZv3mwbNmxwUTplWmzcuNEdRxkf/i699FIXMLmQ4qGxne91L0RizxEAAAAAkouCGru2H0g1F1yNKWbMmGFbtmxxtQ51/6UPlZU1P2/ePJszZ44rifDbb79Z9erVrWzZsu4Dac0o+PLLL13txCZNmth1113n7tt+//13y58/vys/oA+8A3mdtCrNFA9V8UxNBVEww6PpJ5qOoswGrVeQQ181cD799FM3QB555BE3nUPZHqJMC/E/jqhWxsWkICX0ul6mR+wghwZybEl1jgAAAACAcy1ZssTVPlRwQqUOypcvb8OGDbM+ffq49boXVba+OmOqI6ZKEmzbts0mTJhgjz/+uOuUqWz7Rx991H0IrxIKdevWtYULF9q9997ruw9M6HXSqjSTsaHAgWpZ9OzZ85xCmxpU6dOnt2LFitmaNWvcYFHETKlGXrEY1auIiopyUbVMmTLZ/PnzrWTJkr5j/PHHH1apUqVEn19Cryt63SNHjsQoPqpaHbEl1TkCAAAAQFqlD8S/+eabGMvUnKFGjRquYcPQoUNdsMGfAhn+Gfr9+/d3QQyZOHGiKzswYsQIq1atmls2c+ZM9wH1W2+95cvCVzaGumEq8BHI66RFaSawoewMRb/eeecdO3HihIt+FSxY0AUOFExQ5oY6kCiYoKwGDdhcuXK5AaSpKgouaFqIsiEUGNEybadBqU4rSitSvY7E0rmc73VFg3fKlCl21VVXuTQjdUvJkCHDOcdKqnMEAAAAgLRKmRaxi4cWKVLEfa1YsaL7qvtLlRTQY9asWTEy7NX5skyZMjH21zL/jp2qv6gPqj26N/S6XiqwEcjrpEVpJrAhd955pxsISvdR8VAFOBRQuOaaa6xTp05um7x587oImB4PPfSQlShRwqX+rF692tavX++2UdaHWscqlejAgQPumGPGjHHzpOKiYyo6dz6BvK66pWjAKsqnWiEdO3Z0+3lTTzTvStkniTlHAAAAAEDiiofqg2mVE1i2bJm791Kmhe7P1ETCkzVrVjdTwJ8y7VVywJ9/x87EvE5alKYCG6LMDD3Ox2sB6+/666/3fa+Bd9ttt7lHIJ555pmAtkvodRXMePbZZ2Osv+WWW+JMP7rQcwQAAAAAJM7rr7/uSgWo4Kf3YfOQIUNs7ty5Yfk64SbNFA8FAAAAACAp7N27180G8IINqoU4fvx4O336dFi+TrhJcxkbAAAAAICUl79AjlTzeioiqiki6liikgArV660hg0b2qRJk2zfvn3J9jr58uWztIjABgJWNNf/eicDAAB+VwJAYkVFRVvrDvVS5HUjI2PWtEiIggXvvvtujCKfsTVu3Nh+/vln+/fff10JAdW+UKMH1eRQQwiVHHjttddi7FOvXj174403YixTvUUvG0MKFCjgXrto0aIBvU5aFRHtNcQF4rF06VL31WtBBAAA4qc/LCMjme2L+Knj3YoVK6xSpUqumCCQWseVmjWoa4c6gahbI8LL2bNn3b+h/u3UvSW5x8iF3IfyWxcBUS/lhDq7ABdC42n58uWMKwQV4wqhMKYIagAAkLwIbCBgJPcg2ONJNwqMKzCuEMp4rwIAIPQR2EDAYvdXBi52PGXJkoVxhaBiXCHYGFMAAIQ+iociIBkzZnQ3oUCwaDxVrlyZC4qgYlwhFMZUdFSURVBjAwCAZENgAwFbPGSYHdm+gysGAEA8shctYjXu7871AQAgGRHYQMAU1Di0aRNXDAAAAEDAqKmGpB4b1NhIwtY4SfkfOKmPDwAAAAAXI0OGDL5WtEBcvLHhjZXEImMjDrNmzbKPPvrIli1b5gIIJUuWtDZt2tjdd99t6dMHdsluuOEGu+mmm+yBBx64qH+g8x2/Xbt2dt999yXJ8QEAAADgYqRLl85y585tu3fvds+zZs1K4fgwcvbsWTt58qTv3zKY9CG9ghoaGxojF3t8AhuxzJ071x588EHr16+fDRs2zEWOFi1aZE8++aRt377d+vbte1EXHAAAAADSisKFC7uvXnAD4SMqKsrOnDnjPtyPTKKi2ApqeGPkYhDYiGXChAlWr149lw3hqV+/vj300EM2YMAAe/rppy1TpkwXNBgUjYodgVL0Sy3kkmqAxH4tvQ7tWgEAAAAkJ92DFClSxAoWLGinT5/m4oeR48eP2/r1690MhqTokKkkgmBlghDYiEVBi5UrV9qOHTvcf0BPx44d3cOzadMme/311910lT179liOHDmsWbNmLtNDrVE9X375pQ0aNMhlgnjLjx496oIlAwcOtOuvvz7BY2lAvfLKKzZt2jQXJOncubMLmHiUHjR06FCbNGmSi4SWLl3aevbs6Y4trVu3tlq1atmcOXPs4MGD9sknn9hll10WlAEEAAAAAAnRDWywpzMgaUX9/3tO3SNnzpw5pC83xUNjueeee+zUqVN29dVXu/oVn376qQt0xPbII49Yrly5bOrUqbZ48WKXzTF58mSbMmXKObUwFJiYPXu2b9mPP/7oolPNmzcP6FjPP/+8mw4zbtw4+/nnn23nzp0uGOLRem2rAMqff/7paoH07t3bZsyY4dvmu+++s+HDh9v48eOtatWqwRo/AAAAAACkKDI2YilfvrwLMIwZM8Z++uknl1UhFSpUcPU16tSp454rO8JfixYtrHjx4rZ3795z5gw1bdrUvv32W18gQ8e/7rrrfFNaznes/fv3u0yN9957z8qVK+fW6zx0bqIMDy+o4WVh3HzzzbZgwQIXyGjZsqVb1rhxYytbtmywxg0AAAAAACGBwEYcChUqZI8++qh7KHCgbIsPP/zQunXrZt9//71br7QcdU9RJsXmzZtt1apVLovCf4qIRx1VHn/8cVf1VY958+bZ559/7lt/vmOtW7fO1ci45JJLfNtnz57dypQp475fu3atm55SvXr1GK+p5/4ZG8WKFQvOiAEAAAAAIIQwFSUWVX31V6BAAVdIdOTIkS4o8fvvv7tAQo8ePezZZ5+1EydOuGyI999/30qVKhXnRb7qqqtcsRVlWSj7QkGG2rVru3WBHkvb+fPaznpznWKvVzDEvxewf90PAAAAAABSCzI2/KgWhqaaPPXUU3b77bfHuFAKRihQkDdvXpdFoQyLzz77zK644gpfQdBdu3adE2AQ7deqVStXW0MZICrm6UnoWBUrVnT7L1261FWj9c5zw4YN7ntlbqgIz5IlS2JkZei5ptUAAAAAAJCaEdjwo6yKu+66ywYPHuzqX9StW9dlbKhYp6aOVKlSxRo2bOhqXyhjQlNKVIhTQQh1LVHGhR5xadu2retmosKk6oDiUQeU8x0rZ86c1qFDB3vrrbdc3Q0FL/T9oUOHfDU8dNw33njDnatqgUyfPt09lPkBAAAAAEBqRmAjlieeeMIV2Zw4caILICi4oJ7L11xzjY0YMcJlR6jGxmuvveYCBwp4lChRwmVhqD2sMivchU2f3iIj/zfTp3Llyq4NqwIZ2t4TyLGeeeYZy5Ytm2vhqsDIjTfe6Nq3qie0PPnkk5Y1a1bXCUXtXBXc+OCDD1zRUtE5e9sCAAAAAJCaRETHNXcC8OMFWA6Om2CH/NrMAgCAmHKWKmUN+/flsuC8VLdtxYoVVqlSJffhFBAMjCuktjHl3YdWq1YtwW0pHgoAAAAAAMIWgQ0AAAAAABC2qLGBgGUvWoSrBQAAvysBAAgpBDYQsBr3d+dqAQCQgOioKIvwKyAOAACSFr91ERB1Yzl+/DhXC0Gj8bR8+XLGFYKKcYVQGFMENQAASF4ENhAwGugg2ONJNwqMKzCuEMp4rwIAIPQR2EDAIiIiuFoI6njKkiUL4wpBxbhCsDGmAAAIfdTYQEAyZszobkKBYNF4qly5MhcUQcW4QiiMqaioKIukxgYAAMmGwAYCNmzWKNt+cBdXDACAeBTNVci6N76D6wMAQDIisIGAKaixad9WrhgAAAAAIGRQYwMAAAAAAIQtMjaSSP/+/e3bb7+NsSxDhgyWP39+a9GihfXo0cPSp+fyAwAAAABwMbizTiJHjx61woUL28iRI33L1Nry999/t379+tmZM2esV69eSfXyAAAAAACkCUxFSULp0qWzvHnz+h7FihWz9u3b20033WSTJk1KypcGAAAAACBNIGMjBWTKlMm1gvOcPXvWxo4d64Idu3btsjJlyripKldeeaVbf/vtt9v1119vf/31ly1YsMAFSZTtocDJe++9Z3v37rW6deva888/b9mzZ3f77NmzxwYPHmzLli1zx8yVK5c1a9bMtx8AAAAAAKkBGRvJKDo62ubPn2+TJ0+2a6+91rd84MCB9uGHH1r37t1t9OjRVr9+fbv33nvdtBU5dOiQvfbaa1avXj0bM2aMVaxY0QUo3n33XXvhhRfs7bfftjlz5tgnn3ziO+aDDz7oghuvv/66jR8/3rp06WIff/yxTZs2LTl/ZAAAAAAAkhQZG0lo1apVLhjhX2Mja9as1rFjR199jf3797tgxSuvvOKKiooCHP/++68LdijIIQ0bNrRbbrnFfa/9ld3xyCOPWNWqVd2yJk2a2PLly32vNWTIEMuRI4crWCq33nqrjRgxwrZt25aUPzIAAAAAAMmKwEYSKl++vK946OLFi+3pp5+2rl272v333x8j+KGpKLVr146xb506dWzQoEG+56VKlfJ9nyVLFve1ZMmSMaa3nDhxwvdc01WWLl1qixYtss2bN9vq1att+/btMabAAAAAAAAQ7piKkkzFQ1Xf4v3333c1Mfw7pXgtX73MCv99IyP/988TV2tY//WxKYhyxx13uIBKoUKF7IEHHrAiRYoE6ScDAAAAACA0kLGRjC6//HKXsaF6GdWqVXNZGWXLlrWIiAg39UTtYT16riKiibFx40abOHGiffTRR9a4cWO37NSpU/bff/+5Oh8AAAAAAKQWZGwks4cffthlTrz44osu2KBsjjZt2tibb75p69evd4GHmTNn2pQpU1zBz8RQ9oeCJRs2bHDPDxw44DI4jh07ZidPngzyTwQAAAAAQMohsJHMVDxUnUzWrl3rinnKc889ZzVq1LC2bdta9erVXSFRBT5at26dqNcoVqyYPfPMM67dq47bqlUrK1iwoOvE4l9gFAAAAACAcBcRzdyEJHH06FFXqFOdSeKibiiqo5EzZ07fMhURVQHQbNmyxdhW7V6VheEVDdV2Bw8etNy5c/vqbCgbQ6+XPXv2GPuqE4u3n46tjI1cuXJd0M+iIqTy9YbvbdO+rRe0LwAAaUmpfMWt3029U/o0EOL0d9uKFSusUqVK7kMvgHGFUHQshd+rvPtQlXFICDU2kkjs4ERsefLkOWeZAh1x7ecf/PC20xQWf/ENNC+oIZkzZ3YPAAAAAABSC6aiAAAAAACAsEXGBgJWNFchrhYAAPyuBAAgpBDYQMC6N76DqwUAQAJU88qrgQUAAJIev3URELWmVSFSIFg0ntSlh3GFYGJcIRTGFEENAACSF4ENBIwGOgj2eNKNAuMKjCuEMt6rAAAIfQQ2ELCIiAiuFoI6ntS1h3GFYGJcIdgYUwAAhD5qbCAgGTNmjNE6FrhYGk+VK1fmQiKoGFcIhTEVHRVlEdTYAAAg2RDYQMA2fPuxHd+3gysGAEA8suQrYmVadeP6AACQjAhsIGAKahzftZkrBgAAAAAIGdTYAAAAAAAAYYuMjWT2zjvv2K+//hqjJVzmzJmtQoUKduedd1rZsmUTfezHH3/catWqZbfddluQzhYAAAAAgNBGYCOZbdu2zaKiouz111/3LTty5IiNGDHCOnToYFOnTrUiRYok6tgPPvigZc+ePYhnCwAAAABAaCOwkUIV1itVqhRjmZ7Xq1fPBTbuu+++RB23TJkyQTpDAAAAAADCA4GNEJEtWzZLnz69nT592j0/evSojRo1ypYtW2a7du2yXLlyWbNmzXzTTB5++GEXCJk/f74dOHDAnn76aRs+fLhvKor2GTZsmK1YscJy585tNWvWtK5du1qmTJlS+CcFAAAAACB4CGyEgOjoaPv000/t1KlT1rhxY1/g4sSJE9azZ0+X4aG6HC+99JIVKlTIWrRoYevXr7dffvnFBgwY4LYvXbq0bdiwwYoXL+6e33vvvValShV78skn7dChQ/baa6/Zzp077YUXXkjRnxUAAAAAgGAisJECVq9eba1bt3bfq97G7t27LSIiwl588UWrWrWqW967d28rVqyY5ciRwz1XxoWmqaxdu9YFNqRhw4Z20003nXN8BTL0Gr169XL7iYIchw8fTsafEgAAAACApEdgIwWUKFHCXn31Vfe9Ahoq+Kkghr73XHrppW46ydy5c23z5s22atUq27t3rwuEeJSlEZecOXPa9ddfb4888ojVrVvXGjVqZE2bNqUGBwAAAAAg1YlM6RNIy8VD9VAAQ9NH/IMaMmjQIJeZoSkqO3bssAYNGli+fPlibJM1a9Z4X+Ptt9+2wYMHW8mSJW306NF27bXX2htvvJFkPxMAAAAAACmBjI0QbQk7ZMgQe+utt6xVq1ZumTI1Bg4c6OpxBEKBkiZNmriHjBw50mWJqPZGnjx5kvT8AQAAAABILmRshCAVERVv2ok6paj4p2pneOvOZ+vWrdamTRtbvny5b9mxY8dcdxR1XwEAAAAAILUgYyMElSlTxmVWqIXrBx98YAcPHrT69eu7YqEqHpoQTW257rrr7Pbbb7f8+fO7YIiCJJqekjFjxmT5GQAAAAAASA4ENpLZY489FlDWhbqidO/e3fbt2+cKiyogoeKhBw4ccOvfe+89X8cUj6auqBCpaN8777zT1eeIjIx0BUtj1/EAAAAAACDcEdhIZkWLFg14W3U30cOj7As9pGzZsnFmevjLlClTvJ1TAAAAAABIDaixAQAAAAAAwhYZGwhYlnxFuFoAAPC7EgCAkEJgAwEr06obVwsAgARER0VZRCRJsQAAJBd+6yIgKnh6/PhxrhaCRuNJLYkZVwgmxhVCYUwR1AAAIHkR2EDAoqOjuVoI6njSjQLjCsHEuEKwMaYAAAh9BDYQMNrFItjjKUuWLIwrMK4Q0nivAgAg9FFjAwHJmDGjuwkFgkXjqXLlylxQBBXjCqEwpqixAQBA8iKwgYBt+PZjO75vB1cMAIDzdBCj2DYAAMmLwAYCpqDG8V2buWIAAAAAgJBBjQ0AAAAAABC20nRgo0ePHjZ48OA41/Xp08cmT56cpK+/d+9e6969u33++edxrp8zZ47dc889tnLlygs+9ssvv2yTJk0KwlkCAAAAABC60nRgY+7cuTZ8+HBbunTpOesWLlxomzcn7bSL/PnzW9myZe21116z9evXx1inNpgvvPCCZc2a1S699NILPvZff/1lGzZsCOLZAgAAAACQimpsbNu2zX788Uc7cuSI6/Hu3+v933//tQEDBliJEiUs1HXp0sVef/11GzVqVIq0nXzkkUfsp59+sr59+7pz8CiTRNeyX79+yX5OAAAAAACk6sDG/Pnz7e6777YzZ87Eub5KlSou0yAclCpVyn3VtJM2bdrEu11UVJRNmTLFZs2aZZGRkVanTh3r0KGD+/6hhx6yjh07WqNGjdy2P/zwg40fP94GDRpk2bNnd8sGDhzorstNN90U47iZM2d200buuOMON3VE56CpJ59++qm99dZbljdvXrfdkiVL3Ppdu3ZZmTJlXECmSJEibp0yO6644gr7888/7eDBg26KTWw6ly1btrgASo4cOYJ4BQEAAAAACLOpKMosuPbaa910jSuvvNLee+89d1Otm/EKFSrY1Vdfbfny5bNwcf/997uf6ejRo/Fu8/zzz9uQIUOsfv36dtVVV9mECRNc/Qs5ffq0TZ8+3bftt99+a7Nnz3bTQeTYsWM2evRoK1q0aJzHvvzyy11g5JVXXrGNGze6+h66vnrImDFjXCAjV65c1qpVKzdFpnXr1rZu3Tq3Xq/z9NNPW/HixV3wpHDhwjGO379/f3cMnS9BDQAAAACApfXAhm6+b7/9dsuZM6fVqFHD1arQDbMX5FC2QjjJli2bde3a1T788MM416sGx8SJE23EiBHWvn17F1QYOXKky6JQdkaTJk3sjz/+8E3HWbBggVWsWNF9lXnz5rnMjVq1asV7Dr1793ZZLjr2vn37XCBFNB3ljTfesIcffth69epl119/vb3//vtWrlw5e+edd3z7161b12XR6OEfvFBQY+rUqS7oVLly5aBdMwAAAAAAwjawkT59ejeFQlT80r/4pp4rg+F82Q+hSAEF/RwK2sS2aNEiS5cunb344osu60EPBRlUk2PZsmXWtGlTV3NEmRQrVqxw10fHU0aL/Pbbby74oWkr8VHg46mnnrITJ064r7lz53bLly9f7jI+mjdvHmP7Fi1a+I7vXffYvvrqK/viiy9cMISgBgAAAAAgNUpUjQ116fj+++/dV91Qr1692mUZaPqJiokeOnTITp486TIhwommgLz66qs2dOjQGMv3799vefLkcVkd/vRcdS409UPX4vfff3dBiHr16rmaF8qoUIBH01IUrEhIsWLF3FdNKfEoSCRerQ6Pnp86dcr3PK4pJqoLonay6vxyyy23WNWqVQO+FgAAAAAApNrAhgpdqiaEpl+oe4dqR9x5552uJoSyExTg8IpehhPVpyhQoIArEOpPgQYFNzSVJHaAwaOMDE3JUUBH2RXKkNC2Y8eOtT179liDBg0SdU4lS5Z0Xzdt2mQFCxb0LVdmiVc8ND633nqrPfroo65LzbPPPuvqgiibBAAAAACAND0VRQEAFdtUMUvdyKt7h7pxqL6GpmOoA0i4UiBAwRovU0IUqFD9izfffNPX2lbdSVR0VPUzRNNRlLGh6SHK1tC0E31V3Q59TWz2ioJGygD54IMP3DQV2bBhg3399dd24403BnQMdUJRIOTjjz9O1DkAAAAAAJCqAhui7IVhw4a56RPVq1e3n3/+2X755RebM2eOuxEPV8o0UcBg9+7dMZapgKem36i2hQqIKjtF01PU9lV0DTJlyuSCPV4LWXVQ0dScZs2aXdQ5DRgwwGWMKMDSqVMna9eunV133XXWrVu3gPYvUaKEC8IoyOJ1UgEAAAAAIDUI2rwETXGIr51pqFItDXUXia1z585WpkwZ3zQQady4sZtmo2KeyuYoXbq0m7biUYaGAj3+FHzQdJGaNWsGdD56TWVVxD4nBSYmTZpkq1atcpkxWp8/f37f+n79+sV4LuqqosCLRwVPlWmjgqcAAAAAAKS5wIZujNU6VMELfa8uIOej7AXd1N97772+rIZQE1/dCwVpGjVqdM7yjBkzuva28alWrVqM52qHe9VVVwV8PqrJEd/2CkioQGlcateufc6y2MGUDBkyxPkzAQAAAACQJgIb6n6iG3vve920n8/Zs2dt69atbgqEioyqXSoAAAAAAECKBDbUVSOu7+X48eOWJUuWOPdTnYm9e/daoUKFLuY8EQKy5Dt/FxYAANI6flcCABBGNTa2bNniCmrOnj3bjh075qY6qIBmjx49YkynUJcR/1oPCF9lWgVWrBQAgLQsOirKIiITXZ8dAABcoET91lWr044dO9r8+fNddxAFM9SpQ5077rvvPvv1119926qDiDeFBeHr1KlTLjMHCBaNJxXjZVwhmBhXCIUxRVADAIAwyNj46KOPXKeOESNGuIKXnqioKJfF8eabb1qTJk2CeZ4IAdHR0Sl9Ckhl40k3CowrMK4QynivAgAglWZsLFq0yB555JEYQQ13sMhIe+yxx2zz5s124MCBYJ0jAAAAAABA8AIbaoeaOXPmeNep3sbJkycTc2iEMLWcBYI5nlR0mHGFYGJcIdgYUwAApNLARuXKlW3UqFFxrhs/fry7WSlYsODFnhtCiOqkxNf5BkgMjSe9lzCuEEyMK4TCmFLxUAAAEOI1Nrp162atWrWytm3b2vXXX++CGAcPHrQFCxbYzJkz7fnnn+dT2FRo8ZBhdmT7jpQ+DQAAQlb2okWsxv3dU/o0AABIUxIV2PAKh7788suuUKgnf/78Lqhx2223BfMcESIU1Di0aVNKnwYAAAAAABcX2JA6derYpEmTbM+ePbZv3z7Lli2bFS9e3GVqKHsjR44crpgozD799FNbuXLl/y56+vRWqFAh1yq3QoUKAV+id9991ypVqmQtW7aMc/3gwYOtYsWK8a4HAAAAACC1uejIQ4ECBezSSy91WRxeEcBbbrnFtmzZEozzSxXmzZtn//77r11++eXuUaVKFdu+fbu1adPGZs2aFfBxfv75Z3ec+Oi4Ci4BAAAAAJBWJDpjAxdGdUjatWvne37rrbfaf//9Z0OGDLHGjRsH5XI2bdqUfxYAAAAAQJpCYCMFlS1b1ubMmeN7Hh0d7TI4li1bZrt27bKcOXO6YIWm/cTO3Jg/f76b0qKsD286i/9UlECPBQAAAABAOKMIRgo5c+aMC07cfvvtvmV9+/a1/v37u5ZyqqWxbt0669Kliy1atMi3zdixY+3LL7+0UqVK2YYNG+zmm2+2Tf+/oKf/VJVAjgUAAAAAQLgjYyOZrF692p566in3/enTp10mhQqsNmvWzLdNrVq17J577rGSJUu65506dbJGjRq5YETt2rXdMtUy+fjjj9337du3d+sV0LjrrrtivF4gxwIAAAAAIM0ENlQP4uzZswFtG+h2aUnu3Lld4VDv+qjIp7Iv1Bp36tSpljFjRmvdurVFRUW5DAw9FAw5depUjOtZt25d3/cZMmSwokWL2v79+895vUCOBQAAAABAmglsdOzY0TZv3py0Z5OGioeKMie6detmv/32m7Vo0cKmTZtmAwcOtKNHj7paGdWqVXMBD9XL8Oh5bApgxBbIsQAAAAAASDOBDWUWxJUZEJ9cuXIl9pzSDK/op4IPyojp3bu3PfDAA3b//fdbZOT/lT/57rvvLvi4wTwWAAAAAACpIrBx5513Ju2ZpEEzZsxw00muuOIK2717tysoWrNmTV8gYsKECbZv3z5Xk+NCBPNYAAAAAACEMoqHpkDxUE0H2bZtm61cudKef/55K1SokBUoUMAV9+zVq5fVr1/ftWg9fPiwVa5c2W17ITT1JFjHAgAAAAAglBHYSAbKdtmxY4fvubIo8uTJ4zqXqDOKt0zdTtS1RBkX6n5SpUoVF/zwghEPP/ywFSlSJMaxH3roIRcU8b5XkCSQYwEAAAAAkBoQ2EgGV155ZUDbRUREWJ06dWIsU5aFHtK8efNz9mnatGmc3yd0LAAAAAAAUoP/K8AAAAAAAAAQhsjYQMCyF405DQYAAPC7EgCAlEZgAwGrcX93rhYAAAmIjoqyiP/flQwAACQ9fusiIKdOnbLjx49ztRA0Gk/Lly9nXCGoGFcIhTFFUAMAgORFYAMBU5taIJjjSTcKjCsEE+MKwcaYAgAg9BHYAAAAAAAAYYvABgKmFrJAMMdTlixZGFcIKsYVgo0xBQBA6KN4KAKSMWNGdxMKBIvGU+XKlbmgCCrGFUJhTFE8FACA5EVgAwFbPGSYHdm+gysGAMB5WqPTRQwAgORFYAMBU1Dj0KZNXDEAAAAAQMggsJHEvv/+e1uxYoXveYYMGSxXrlx2xRVXWIUKFS7oWKNHj7ayZcvalVdemahzGTNmjJUuXdrq16+fqP0BAAAAAAg1FA9NYjNnzrRJkyZZpkyZ3OPs2bO2dOlSa9eunQ0cOPCCjjVu3Dj7888/L6pORvr0xLIAAAAAAKkHd7nJoFChQvbAAw/EWNahQwfr2rWrlS9f3tq3b58cp2G33HJLsrwOAAAAAADJhYyNFFKnTh279tprbfjw4b5ln332mS1YsCDGdloWO0vjr7/+so8++sgmTJhgJ06ciLFu5cqVNn78eBs8eLB9/vnntnHjxhhTUX7//fck+5kAAAAAAEhuBDZSUKNGjVzgYffu3e75l19+eU4QQ8sUyPBoWssLL7xg+/fvt08//dRlfhw4cMCtUzDjzjvvtNWrV9vp06dt8uTJ1qpVKxfskK+//trmz5+frD8jAAAAAABJicBGCipQoID76gU2AhEREeEyMvr06eO+HjlyxEaMGOHWZcmSxX3/7LPP2qOPPuoyNLJly2azZ89Osp8BAAAAAICURGAjBChYEagbb7zRBTAkc+bMbjrLnDlz3PN77rnHqlSp4qanKGtjxowZFhkZaWfOnEmycwcAAAAAICVRPDQF7dy5030tWrToBWd5ePLly2d79uxx3//xxx/2+uuvu/ayhQsXtmrVqllUVJRFR0cH+cwBAAAAAAgNBDZSkAp5KsMiT5487rmyKxSI8KepJv5UW8OfprEUL17cDh8+bD169LCbb77ZRo4cably5fLV8QAAAAAAILViKkoKmTdvnn3//ffWrVs337L8+fPbhg0bfM+XLVvmy8bwaB8VBpVDhw7Zd999Z82aNbMtW7bY8ePH7brrrvMFNWbNmuUCH0xFAQAAAACkVmRsJNOUk3feecd9ryDD+vXrbe7cua7ApwIRns6dO7tlkj17dhf8KFeuXIxjaf+OHTu6drE///yzy9ZQJxTV6VD2x5NPPmktW7a0Xbt2uW4qpUuXvqDipAAAAAAAhBMCG0lMxT3Lli3re65sisqVK1v//v1dhkbsbRWIUEBD3UweeeQRVzdD9TKkS5cubl9NO1E2R+/eva1FixaWLl06t37s2LGuYKiyPBT4GDBggC1ZssQ2b97sC5yULFkyqX9kAAAAAACSTUQ0lSWRgKVLl7qvB8dNsEObNnG9AACIR85Spaxh/75cH5zXsWPHXLH3SpUqWdasWblaCArGFVLbmPLuQ9UUIyHU2AAAAAAAAGGLqSgIWPaiRbhaAADwuxIAgJBCYAMBq3F/d64WAAAJiI6KsohIkmIBAEgu/NZFQE6dOuXayQLBovG0fPlyxhWCinGFUBhTBDUAAEheBDYQMOrMItjjSTcKjCswrhDKeK8CACD0EdgAAAAAAABhi8AGAhYREcHVQlDHU5YsWRhXCCrGFYKNMQUAQOijeCgCkjFjRncTCgSLxlPlypW5oAgqxhVCYUxRPBQAgORFYAMBWzxkmB3ZvoMrBgDAeVqj00UMAIDkRWADAVNQ49CmTVwxAAAAAEDICOnAxuTJk+3w4cMxpkMUL17c6tataxkyZLBwN2PGDDt06JDdcsst56ybNm2aFStWzC677LIUOTcAAAAAAMJBSAc2Bg8ebFmzZrXatWu758eOHbNhw4ZZ5syZbdSoUZYvXz4LVwpo9O7d27WRq1SpklWpUiXG+u3bt1PTAgAAAACAcA5syOWXX27PPvus7/nRo0etZcuWLsDxzDPPWLj69ttvrXDhwla0aFH76quv7KWXXoqx/t57702xcwMAAAAAIFyEXbvXbNmyWbVq1WzLli2+ZV988YVt3rw5xnZa5r+NMiSmT59ukyZNstWrV8fY9ssvv7S9e/fa0qVLbfz48fbLL7/YmTNnYmxz8OBBmzlzplu/YsWKGOuUdfHnn3/a119/bbNnz3bbJuSbb76xK6+80po3b+6CHArYxJ6KsmTJEve91q9fv95+++03mzp1qjtXOXnypP388882YcIEW7x48TmvsXz5cps4caLbZvfu3QmeEwAAAAAA4SbsAhtnz561DRs22NVXX+1b1r9/f3cT70/LVq1a5b5fuHChtWjRwmVGzJ071+6880574YUXfNu+8sor9uijj7rMkAULFrhMkM6dO7uAhSigodf77LPP7I8//rDbb7/dnnrqKYuKinKPHj162HPPPeeCC59++qk1bdrU/vnnn3h/hnXr1rn1OqdrrrnGjh8/bt99912MbYYPH+4CEjJ06FC7//777ZNPPrFx48a5IMjGjRvtuuuusyFDhrif7/HHH7d77rnHBTtk4MCBdt9997mAi4IoOn8FdgAAAAAASE1CfirKypUrXfaFnDhxwmbNmmWXXnqptWvXLqD9daOvIIQCA3fddZdbtmfPHmvVqpXVqVPHbrrpJt+2yuaIjIx0QZK2bdu6gEHFihVdLYy7777bHnroIbedsifatGljNWvWtOrVq9uvv/5qv//+u6/mh+p/bN261a2Li7IocuXKZfXq1XNFUHWcsWPHWocOHeL9OTJlyuQCGzo/ueOOO6xhw4a+KSwKjmh/BToU0Pj8889dIEaFVr0MEP3cAAAAAACkJiGfsaEpJAok6LFp0yY7ffq0ff/99/byyy8HtL+mlyjIoKCIAiR6/PDDD1awYEE3tcOjKSFe0KBy5cqWPn1627VrlwtYqGipFxSRsmXLWrNmzVxXkzx58rhuLcoAUYBDAQYFHa6//vp4M06mTJni9vc6uyhr499//3WP+NSoUcN3fv/995/Nnz/fva73M2k6Sv78+d3PpOPqvN566y0X0NDUGJ2PzgsAAAAAgNQk7IqHyquvvuqmfKjApgpwno+CGhERES5bwT9jQZkMpUqV8j1XIMCfggiaZnLgwAHLmTOnZc+ePcb6IkWKuECLXl/n8v7779uDDz7o1imTQoEOFQaNbc6cOa7ehQIcXiaKAhUSVxFRj4IW/j+TKGChgI+nTJky7jwV2NCx33zzTXftFNSpVauWm2ITu/sKAAAAAADhLOQDG3Fp3LixjRw50mVUeIENBSE8yrDwaHqIamVoekZCQZC4FCpUyA4fPmynTp1yGRIeFfDMnTu3+17taBXcUO2LefPm2XvvvWfdu3d3hT5jU70LnVOOHDliBCXU8lXb9+nTxxVIjU3BGf+fSTRdpn79+nGet4IcH3zwgTvvRYsW2UcffeQyNpSBomktAAAAAACkBiE/FSUuKtKZJUsWK1eunHuuAMO2bdt86xVc8FStWtVlMajziT9N0dB0joRoCkjmzJlt8uTJvmX79+93007U1WTt2rWuG4ooIKGCoKrfoW3imlajgqAdO3Z0GR3+DwU0FJBRB5SEKBOkdOnSri5H7GyQH3/80WWEjB492heM0XnedtttLvCi7A0AAAAAAFKLsCoeqqwMBRJU5POJJ57wTQ9RIVF1DlFgQDfzP/30ky+bQlNMNAVDXUu2b99u5cuXt7///ts9VFwzIarFodfq16+fq4FRoEAB9/oqKtq1a1c3VWXQoEEuYKFipApoKIjiTUvxp6CFaoTccsst56xT8EGBGk1HUeDjfJS9oSkrykLRdBxN11mzZo0Lauhc9LMr6KHXUy0PFVBVm1oVF1XRUgAAAAAAUouQDmy0bt3a1Z/wpmykS5fOihcv7gILKuDpUdcSdSBZsmSJCzyMGTPGPbSt3Hzzza62hNq2KhDRqFEjGzBggG9Kx6233uqmbvjzX9alSxe77LLL7JdffnHBEwU6lJmh89FUFRUDVStV1b5QdseIESPc9nEFJB577DErVqxYnD/vk08+6Yp/esU+vYwUZYBoqoo/dVRRi1hlnuzbt891inn44YetRIkSbr0CJCqSqkCQ6oUoEKIpPAAAAAAApCYR0SpAASTQWUYOjptghzZt4loBABCPnKVKWcP+fbk+OC99ULZixQr3wVXWrFm5WggKxhVS25jy7kOrVauWOmtsAAAAAAAAhPxUFISW7EWLpPQpAAAQ0vhdCQBA8iOwgYDVuL87VwsAgARER0VZRCRJsQAAJBd+6yIg6jZz/PhxrhaCRuNp+fLljCsEFeMKoTCmCGoAAJC8CGwgYNSZRbDHk24UGFdgXCGU8V4FAEDoI7ABAAAAAADCFoENBCwiIoKrhaCOpyxZsjCuEFSMKwQbYwoAgNBH8VAEJGPGjO4mFAgWjafKlStzQRFUjCuEwpiieCgAAMmLwAYCtuHbj+34vh1cMQAA4pElXxEr06ob1wcAgGREYAMBU1Dj+K7NXDEAAAAAQMggsJEMFi9ebHv37v3fRU+f3goVKmSXXHKJRV5kn/t58+ZZ4cKFrUyZMrZgwQLLly+flStXLghnDQAAAABA6COwkQyGDBliS5cutRo1arjnJ0+etFWrVlmuXLns448/tqJFiyb62P369bObbrrJHnjgAfvll1/cPGACGwAAAACAtILARjKpVKmSffjhh77nCm60bdvWBg4caO+//35QXqNPnz5BOQ4AAAAAAOGCdq8pJFOmTNa4cWNbvXp1jOXR0dG2fPlymzt3ru3YseOcaSc7d+50+yxcuNCOHDkSY72moqxbt859/8cff9j27dvtwIEDNmfOHPv7778tKioqGX4yAAAAAACSDxkbKWjbtm1Wr1493/Ndu3a5KSX//feflSpVygU4rr76anvppZcsXbp0NmDAANd27vjx43bmzBl79913Yxzv1VdftUaNGtmjjz7qMkGKFCnijqH6G/pavHhxGz16tGXNmjUFfloAAAAAAIKPwEYyUbBi5syZ7vtTp065gqLKvnjttdd82yiAUaxYMRs7dqxlyJDB9u3bZx07drRPP/3U7rnnHrfNoUOHbOrUqa4AaUKFR//55x+3rQqKbtmyxW644Qb74Ycf3BQYAAAAAABSAwIbyUTZGBMnTnTfnz171rZu3Wpr1661vn37uuDGwYMHXeDjoYceslmzZvn2q1ixos2YMcMX2Khdu7ZlzJgxoNds2rSpC2pIiRIl3EMBDgAAAAAAUgsCGylUPNTrljJo0CDr1KmTy8CQv/76y00b8Ve2bFnf92oTG6j8+fPHeK7XUFAFAAAAAIDUgsBGCmrXrp0LbGzcuNFlYkiPHj3s8ssvj3efhKafAAAAAACQlnCXnILWrFnjvpYrV87V1ihYsKBNmTIlxjYrVqxw3U4AAAAAAMC5yNhIgeKhaumqjiiffPKJtWzZ0qpXr+6WP//889arVy/3fd26dV0Nji+++MJefPHF5DpNAAAAAADCCoGNZFCjRg1bunSpr3ioWrfmzp3bnnvuOWvRooVvOwU51BFl8uTJ9vPPP7sMjpEjR7r95YorrohRb0Pq16/v2rmKWseWL1/+nO89cS0DAAAAACCcRUQrfQA4DwVlJN1f39jxXZu5VgAAxCNLoZJWuesLXB+c17Fjx9x0YxWXz5o1K1cLQcG4QmobU959aLVq1RLclhobAAAAAAAgbDEVBQHLkq8IVwsAAH5XAgAQUghsIGBlWnXjagEAkIDoqCiLoD07AADJhqkoCMipU6fs+PHjXC0EjcbT8uXLGVcIKsYVQmFMEdQAACB5EdhAwKgzi2CPJ90oMK7AuEIo470KAIDQR2ADAAAAAACELQIbCFhERARXC0EdT1myZGFcIagYVwg2xhQAAKGP4qEISMaMGd1NKBAsGk+VK1fmgiKoGFcIhTEVFRVlkRQPBQAg2RDYQMCGzRpl2w/u4ooBABCPorkKWffGd3B9AABIRgQ2EDAFNTbt28oVAwAAAACEDAIbyWjt2rV25MiReNdnz57dypcvH+/61atXW86cOa1w4cKJWg8AAAAAQGpDYCMZffHFF7Z8+XL3/bFjx2zNmjVWsWJFX+0KzeHt27dvvPs/9dRT1qhRI3v00UfjXD9y5Ei77LLLrFOnTkn0EwAAAAAAEFoIbCQj/6DF4sWLrWPHjvbKK69YtWrVgnL8gQMHBuU4AAAAAACEC9q9hqD//vvPVqxYYYcPHz7vdrt27XIBEm96i6ai7Ny5M1HHAgAAAAAgHBHYCCG7d++2bt26WfPmze3xxx+3hg0b2muvvebaxsVVr6Nt27b21VdfWbZs2XxTVb788ssLPhYAAAAAAOGKqSghpFevXi7w8Ntvv1mOHDlcPY7bbrvNChYsaHfddVeMoMYdd9xhjRs3dlNZIiIiEn0sAAAAAADCGRkbIWLTpk22aNEie+SRR1wgwism2r59exs/frxvu/Xr17ugRp06deINagR6LAAAAAAAwh2BjRCxdetW97Vs2bIxlpcrV862b9/uez5jxgyXibFu3To7ffr0RR0LAAAAAIBwR2AjROTJk8fXBtafCoNmzZrV97xp06Y2efJkVzh0yJAhF3UsAAAAAADCHYGNEFG6dGlXBHT27NkxlqtGRvXq1X3PL7nkEitUqJA9+uij9vHHH9vKlSsTfSwAAAAAAMIdxUNDhDIpFKx4++237ezZs1ahQgWbPn26/fPPPzZmzJhztr/11lttypQp9uyzz9q4ceMsXbp0iT4WAAAAAADhioyNFKKMissuuyzG1JDbb7/dtWRV4c9hw4ZZpkyZbNKkSVapUiVftkaRIkX+7x8uMtL69etn6dOnt1mzZp2zPqFjAQAAAACQGkRER0dHp/RJILQtXbrUff16w/e2ad//FSYFAADnKpWvuPW7qTeXBuelOmgrVqxwHzhR/wzBwrhCahtT3n1otWrVEtyWjA0AAAAAABC2qLGBgBXNVYirBQAAvysBAAgpBDYQsO6N7+BqAQCQgKioKFcLCwAAJA9+6yIgp06dsuPHj3O1EDQaT8uXL2dcIagYVwiFMUVQAwCA5EVgAwGjziyCPZ50o8C4AuMKoYz3KgAAQh+BDQAAAAAAELYIbCBgERERXC0EdTxlyZKFcYWgYlwh2BhTAACEPoqHIiAZM2Z0N6FAsGg8Va5cmQuKoGJcIRTHFMVEAQBIWgQ2ELBhs0bZ9oO7uGIAAFxAq3S6igEAkLQIbCBgCmps2reVKwYAAAAACBnU2LhAhw4dssOHD8e5bteuXW59fHbv3n3e9QAAAAAA4MIQ2AjAmTNnbMiQIdakSRNr1qyZNW7c2D0+++yzGNvdd999NmLEiHiP88ILL9jXX399gf9EAAAAAAAgPkxFCaDgV/fu3W3Hjh323nvvWfXq1d3ymTNn2uOPP2779u2zxx57zAIxdOjQgLYDAAAAAACBIWMjAWPHjrUFCxa4TAwvqCEtWrSwhx9+2D799FP777//ztlP01WOHj2a4FSUU6dO2d69e10AJS5nz551U1yOHTsW53q9hrdO53Hw4MFzsk327NnjjgMAAAAAQGpDxkYCJk6caE2bNrUiRYqcs+62226zDh06WI4cOXzL1q5da+3atbOdO3e6IMMNN9xgAwcOtHTp0lmPHj2sUaNG9uijj7qAxMsvv2zffvutayXnZYZ069bNHWfp0qXWt29f27p1q9t3//79dsUVV9jgwYMtW7ZsduDAAXvqqads9uzZbv+aNWvaiRMnrGrVqtanTx8XQNHrescXvf7dd98d3BEEAAAAAEAKImMjAWvWrLFKlSrFuS5z5swxghry+++/u1oa+jpmzBgXWPjhhx/O2bd///62ePFi+/77711GiDI/VH/jn3/+cetff/11V8dj3rx57lhfffWVLVy40CZPnuzWP/30024ajAIb2v/SSy91Xz29e/e2f//913788Ue3/J133rFBgwbZ+PHjL3yUAAAAAAAQosjYOI/Tp0+7LAgv4yEQ1157rdWoUcN9f9lll1np0qVt3bp1MbbR1BEFPF599VUrVqyYW6ZMC/8AyOeffx5jnypVqlihQoVcFoimpvz8888uGJI3b163/pFHHrFvvvnGfb99+3b79ddf7aOPPrLChQu7ZQ0aNLC2bdvaF198Ye3btw/45wEAAAAAIJQR2DiPDBkyWO7cueOsoRGfAgUKnJPVcfLkyRjLFHhQ0KR8+fLxHuf48eM2adIkW7RokW3evNk2bNjgAiLR0dFuuotUrFjxf/+Q6dP7jrdx40b39ZJLLolxTGV1eBkfAAAAAACkBkxFSUCdOnXs77//jnPdpk2brFWrVr7pIxIREZHgRfcyQFQ4NC4q9Nm1a1eXkaFghLIxNKWkaNGivmCJxA6YeMfLnj17nMfX9t6+AAAAAACkBgQ2EqACoapR4V+/wjN8+HDX6aRChQoXdNFViDRnzpy2ZMmSGMvVvURTTVTXQ+tU/PPee+9100hUXFQtZ/VVr6cAhbI5PEeOHLHVq1e778uWLWuZMmWy+fPnxzj+H3/8EW+9EAAAAAAAwhFTURJQv35910lEHUUeeugh91xTQtQtRY8hQ4ZcUA0OiYyMtJ49e7oOJ/ny5XNZGV4XFB1PU0wUuFDNjFy5crmaGm+++aYLaui1FRS5/fbb7bXXXrOsWbO62hs6ltdeVhkb9913n9tHx1EgZPr06TZnzhwbOXJk4kcLAAAAAAAhhsBGANQ+tW7dur5ghupZePUq/OtkFCxY0AUi/GmZAhGx1995550uIDJq1CjXurVUqVIuOKGWrjJ06FD3UDClRIkSLnNDGRnr169369UyVkGN9957zwUvVBhUGR3K1BAFTvLkyWOjR492x1ewRF1aqlevHqyxAwAAAABAiouIVjVKhBX9k23bts0VKvUCGarL0bBhQ3vssceC3vVE2STy9YbvbdO+rUE9NgAAqVmpfMWt3029U/o0EGKUgbtixQo3RVgfVAGMK4SiYyn8XuXdh1arVi3BbcnYCEMqUNqlSxerVauWm3IiysxIly6dXX311Sl9egAAAAAAJBuKh4apESNGuFodvXv3do8zZ87Y2LFjXXtaAAAAAADSCjI2wlS5cuVccdDkVDRXoWR9PQAAwh2/OwEASHoENhCw7o3v4GoBAHCB1NVMWZYAACBp8FsWATl16pQdP36cq4Wg0Xhavnw54wpBxbhCKI4pghoAACQtAhsIGA10EOzxpBsFxhUYVwhlvFcBABD6CGzggrqxAMEcT1myZGFcIagYVwg2xhSSAuMKjCsguKixgYBkzJjR3YQCwaLxVLlyZS4ogopxhWBjTCEpMK6QVsdVVFS0RUbyYSmCj8AGAjZ53Hzbu+cwVwwAAADABclfIIe17lCPq4YkQWADAVNQY9f2A1wxAAAAAEDIiEytbdXOnj17weuSg15fj7jovFLy3AAAAAAACDepMrDRt29fa9269QWvSw7333+/devW7Zzlw4YNc3PiPvnkkxQ5LwAAAAAAwhFTUULAoEGDbMiQIfbUU0/ZXXfdldKnAwAAAABA2CCwkQBNDYmMjLyglpTeVBPtl5DXXnvNZWk888wz1rVr15A5LwAAAAAAwkGaD2ycPHnShg4dapMmTbLdu3db6dKlrWfPnnb99de7C9SuXTtr2rSpLVmyxBYuXGjZsmWzTp06Wa9evVxQ4cSJEzZw4ED77rvvLF26dNayZUvbsWOHVahQwfr06RPvhY+OjraXXnrJxowZY88//7x16dIlJM4LAAAAAIBwkqo/uj9z5sw5j9gUVJgyZYqbDvLnn3/a3Xffbb1797YZM2b4thk+fLh17tzZBRCUWaF6GL///ruvZseCBQtcgEL76DVmz5593vNSUEPH0T7NmjU7J6iRUucFAAAAAEC4SbWBjTVr1lj16tXPeYwbN863zZ49e1zwQAGDyy67zLJkyWI333yztWrVygUNPAo+XH311W69Co+WKFHCFi9ebP/9959NnjzZnnzySatYsaLlypXLXnzxRcuTJ895z23evHluv8aNG9svv/zinvtLqfMCAAAAACDcpNrAhqZcLF++/JxHhw4dfNusXbvWZU8o4OFPzxUY8Shg4C9r1qx2+vRpW7lypatbUaVKFd+6zJkzu9c+n4wZM9r777/vpprUrFnTTQ05cOBAip8XAAAAAADhJtUGNgKhm31RECF2Yc4MGTL4nqdPf24pEu3jLY+9f0Lq1KljzZs3d0U8VTz08OHD9txzz6X4eQEAAAAAEG7SdGCjTJkyrrCmCnD60/Py5csnuL+2URBh6dKlMYp++mdVJKRkyZJuysiPP/7omyYTCucFAAAAAEA4SNNdUXLnzu2Kb77xxhtWoEABN1Vj+vTp7qGpIgnJmzevq32h/YsUKWKFChWyt99+2/bv339B53HrrbfaTz/9ZK+88orVrVvXBTZC4bwAAAAAAAh1qTKwoWwHPQJZp2wJ1aZQoc6DBw+6IMIHH3zgWqnGdyz/ZepGooCEupZoCknbtm1dwU7V0YiLpp/EdW4DBgxwBUBVb2P06NHJfl4AAAAAAISjiGgKMVwUtVGNXeuiUaNG9sADD7hMjNRwXt6UlgW/7bJd2/9X5BQAAAAAAlGoaG67p2cLLlYYOXbsmK1YscIqVarkPnRPbt59aLVq1RLcNk3X2LhYigk1aNDAXn75ZTfNQ51N3nvvPTt+/Lhrxcp5AQAAAACQtFLlVJTkEhER4aaHvPvuu9ayZUu3rGrVqvbZZ5+5uhacFwAAAAAASYvAxkVS69bPP//c0sJ55S+QI6jHAwAAAJA2cC+BpERgAwFr3aEeVwsAAABAokRFRVtkZARXD0FHjQ0E5NSpU652CBAsGk/Lly9nXCGoGFcINsYUkgLjCml1XBHUQFIhsIGA0UAHwR5P+sXLuALjCqGM9yowrhAueL9CWkZgAxdULBUI5njKkiUL4wpBxbhCsDGmkBQYV2BcAcFFjQ0EJGPGjO4mFAgWjafKlStzQRFUjCsEG2MKSYFxBcYVLhT1Sc6PwAYCNnncfNu75zBXDAAAAACSsaMMjRzOj8AGAqagxq7tB7hiAAAAAICQQY0NAAAAAAAQtghsJNLjjz9uvXr1suTUsWNHGzVqVLK+JgAAAAAAoYypKIl05MgRO3PmjCWngwcP2okTJ5L1NQEAAAAACGVkbAAAAAAAgLBFxkYSOXv2rI0dO9YmTZpku3btsjJlyliPHj3syiuvdOtvv/12a968uf3777+2cOFCy5Ytm3Xq1MktF2WDfPDBBzZt2jSLjo62zp07B/X4AAAAAACkBmRsJJGBAwfahx9+aN27d7fRo0db/fr17d5777Xff//drT906JC9+eabVrNmTfv888+tXbt29vLLL9uff/7p1r/yyis2efJk69evnzvO3LlzbcOGDUE7PgAAAAAAqQGBjSSwf/9+GzNmjPXu3dtatGhhJUqUcAEIZVAoGOFp2LChy8TQ+nvuuceKFStmCxYscPU7xo0b5wqUXnHFFVa+fHl77bXXLHPmzEE5PgAAAAAAqQWBjSSwatUqN1Wkdu3aMZbXqVPHli9f7nuu6SP+cuTIYadOnXL7nz592qpVq+ZblzdvXitdunRQjg8AAAAAQGpBYCMJpE//f6VLMmTIEGN5unTpLDLyf5c8Y8aM5+yrehp6uH8cv20lS5YsQTk+AAAAAACpBYGNJFC2bFmLiIhwhTv96XnsLIr49leAYuXKlb5lyrTYuHFjUI4PAAAAAEBqQWAjCWjaSJs2bVzxzvXr17ssiZkzZ9qUKVOsS5cuAe1/ww032DvvvGNbt25101L0vWprBOP4AAAAAACkFrR7vQjz58+3evXqnbNcnUmee+45GzBggLVt29aioqKsQIEC9uKLL1rr1q0DOnb//v3tpZdesmuvvdZlbzRp0sSqVKniW3+xxwcAAAAAIDWIiKboQqKoc0l8hTiVUeFRkc8TJ05YtmzZYmyjdqyqkeHVzYhv2ZkzZ9wxMmXKZIcPH3brve4owTh+IJYuXeq+Lvhtl+3afuCC9gUAAAAAJF6horntnp4tkv0SHjt2zFasWGGVKlWyrFmzJvvre/eh/k014kPGRiJlz549oO1U0DN20EFy5swZ0DIVCvWKhaqrSbCPDwAAAABAOKPGBgAAAAAACFtkbCBg+QucmzECAAAAAEg63IcljMAGAta6w7mFUgEAAAAASSsqKtoiIyO4zPFgKgoCokKpx48f52ohaDSeli9fzrhCUDGuEGyMKSQFxhUYV7hQBDXOj8AGAkYDHQR7POkPO8YVGFcIZbxXgXGFcMH7FdIyAhsIWEQEqU8I7nhS62HGFYKJcYVgY0whKTCuwLgCgosaGwhIxowZ3U0oECwaT5UrV+aCIqgYVwg2xhSSAuMKjCskBnU24kdgAwGbPG6+7d1zmCsGAAAAAMncGYVmDvEjsIGAKaixa/sBrhgAAAAAIGRQYwMAAAAAAIQtAhvJ4JVXXrHWrVvb0KFD41w/fvx4t3748OEX9To9e/a0CRMmxLv+8ccft9GjR1/UawAAAAAAEEoIbCSDrVu32r59+2zs2LFxtrb86quv3Ppdu3Zd1OusW7fOHSc+Dz74oLVs2fKiXgMAAAAAgFBCYCOZVKtWzc6cOWN///13jOWbN2+29OnTW758+ZL8HMqUKWMFChRI8tcBAAAAACC5UDw0GfuVN2vWzKZPn261atXyLf/uu+/ccn31d/ToURs1apQtW7bMZXLkypXLbXfbbbfFyPSYNm2aRUVFWefOnWPs//DDD1u9evVs/vz5duDAAXv66afdVBe9tv8xAAAAAAAIZ2RsJKPmzZvbDz/8EGM6igITWh6bAhNz5sxxQYhnn33Wqlatai+99JLNnDnTrX///fft7bfftrZt21r37t3tk08+sS1btvj2X79+vb366qvWokULu+WWW6x06dK2YcMG2717dzL9tAAAAAAAJD0yNpLRlVdeaUeOHLFFixZZnTp1bO3atXb69GkrV67cOdv27t3bihUrZjly5HDPa9asaVOnTnX7NGjQwGVfPPfcc9amTRu3vnz58i6I4a9hw4Z20003JdNPBwAAAABA8iOwkYwyZsxoV111lX3//fcusPHtt9+eE4zwXHrppW4Kyty5c10djlWrVtnevXvdtBN9f+LECXcMT+HChV0NDX/K0gAAAAAAIDVjKkoKTUdRgEL1NuKahiKDBg1yQY9PP/3UduzY4bI0vAKjp06dcl8zZcoUY59s2bLFeJ41a9Yk+zkAAAAAAAgFBDaSWZMmTWz//v32xRdfuGkpNWrUOGebbdu22ZAhQ2zgwIGuReyLL77oppxoe9XnKFWqlK+9q0eBErWVBQAAAAAgLSGwkcxUM6Nu3br2zjvvuC4n6pYSm5eRoWCFqA7Ha6+9ZocOHXLrChUq5AIkgwcPtsOHD7ttRo4caXv27EnmnwYAAAAAgJRFYCMFaIrJsWPH4q2voVoZ9957r2vRes0111ijRo1c0ELFQFU8VJTNoakmqtnRuHFjmzFjhlWsWDGZfxIAAAAAAFJWRLR/71EkCa8Na4kSJdxXBTU2bdrkOplkyJDB155VNTKUjeFRhsa+fftcdxQVHlXx0AMHDrj9PCowqiwOHVvHzJ49u6vFoeMpO6RAgQK+bdXuVev9lwVi6dKl7uuC33bZru0HLvJqAAAAAAAuRKGiue2ennF/MJ5UdN+6YsUKq1SpUorUb/TuQ6tVq5bgtnRFSQZeQMOjQaHB4a9s2bLn7JczZ0738OTPn989/PkHQrzaG/EdL3bXFAAAAAAAwh1TUQAAAAAAQNgiYwMBy18gB1cLAAAAAJIZ92LnR2ADAWvdoR5XCwAAAABSQFRUtEVGnttVE0xFQYBUoPT48eNcLwSNxtPy5csZVwgqxhWCjTGFpMC4AuMKiUFQI37U2EDAaKCDYI8n/WHHuALjCqGM9yowrhAueL9CWkZgAwGLiCDtCcEdT1myZGFcIagYVwg2xhSSAuMKjCsguKixgYBkzJjR3YQCwaLxVLlyZS4ogopxhWBjTCEpMK7AuEJKiUqldToIbCBgk8fNt717DnPFAAAAACAMO6u0TqUNIQhsIGAKauzafoArBgAAAAAIGdTYAAAAAAAAYSvFMzY++eQTmzt3boxlGTJksPz581uLFi2sSZMmvuUvv/yyVa1a1dq0aROU137uueesfv36dv3111/0sfr06WOXX3653XzzzZYcgn0tAAAAAAAIRyke2Fi9erVt3brVnn32Wd8ytYBUsKN79+7uBr59+/Zu+Q033GB58uQJ2mv/+eefVrJkyaAca+HChVagQAFLLsG+FgAAAAAAhKMUD2xItmzZ7Kqrroqx7JprrrG9e/e6jA4vsFGzZs0UOsPQw7UAAAAAACBEAhvxKVWqlP3111/xTr9YsmSJTZo0yXbt2mVlypSxLl26WJEiReI93syZM2369OkWHR1tnTp1Omf94sWLbeLEibZ//34rW7as3X777W5KTGKcPn3anduyZcvc+eXKlcuaNWvmAjbSr18/a9y4sW3atMlleyi4owBOnTp1Ajof/2vxwgsv2BVXXOEyUA4ePGg9evSwChUqXPD1AQAAAAAg3IRs8VBlaygIUa/e/9rRKMixYcMG9/2YMWPcjboCBq1atbLNmzdb69atbd26dXEeb9SoUda7d2+rVKmSyw7p27evbd++3bf+p59+srvvvtsKFizopnns2bPHfdU0mcR48skn7YsvvrBatWq5uhvp06e3hx9+2ObMmeP7WVSXY9WqVe51zpw5Y3fccYetX78+oPPxvxb6/umnn7bixYtblSpVrHDhwhd8fQAAAAAACEchkbGhrIV77rnH9/zYsWO2cuVKl5GgAp+xqQbHG2+84QIF3bp1c8tUAPTWW2+1d955xwYPHhxj+1OnTtm7775rjz76qAseSI0aNXxFQ6OiolwGRK9evXzrr732Wpf5MGjQIHvzzTcv+GdSMOOSSy7x1d24+uqrbfbs2fbvv/9aw4YN3TJlUbzyyivue2Vy/PHHHy6gUbp06Qs+n7p167pASGKuDwAAAAAA4SokAhuaXtG1a1c3RUTTJ4YNG+YyEJRxEJfly5e74Efz5s1jLFcXlY8++uic7RUkOXLkiDVo0MC3TMEDPWTbtm0ue+O7776zWbNm+bZRlkO6dOkS9TMpeHH06FE3PUTHUZHUw4cP29mzZ33bVKtWzfd9ZGSk5cuXz+2TmPPRVJXEXh8AAAAAAMJVyBUPVd0J1YFQDQp1LIldVNSrXyHZs2ePsVzPlZ0Rm27yvdfxp2kaohoW0rZtWytatOg5rWcDpeCER9NQ3nrrLRes0PQXBTFy5MgRY/usWbPGeB4REeGCO4k5H/9jX+j1AQAAAAAgXIVEYCM2FdH89ddf7ZFHHnHFL1VE1J/XolVTWFSDwrNx48Y4i2Oq9oS3vepPeHbs2BFjvW784wqkxLZixQobPny4C1x4FDDwAgkq1tm/f3978cUXrXPnzr5tRowY4QIXCbnQ84ntQq8PAAAAAADhKmSLh6rThzIgVOQzNmUxqKjoBx98YCdOnHDLVEjz66+/thtvvDHOQIFqUGiKi5ex8M033/gCG3nz5rUmTZrY0KFDfdkSKuY5cOBA+/DDD885noIT3377rf3zzz++QIeKe3pTSw4dOuS++gdRNAXkwIEDvmyK87nQ87nY6wMAAAAAQLgKyYwNKVSokCueqSKaU6ZMsZtuuinG+gEDBtiDDz7o6kiUKFHCdRfRTbtXLDO2119/3bp37+7qTKigp6aneDU25KWXXrKePXtay5YtrXz58i67QYGJ995775xjVa5c2W677Ta78847rWLFiu61b7nlFrvyyivderVaVRtWZZxcdtllLoNDx6pdu7bLogjEhZxPXC70+gAAAAAAEI4iogOZG5GEdMOtIEPNmjXPWaduJXPnznW1MKpXr25///235cmTxxeQ0Klr/4MHD1q5cuVcEdLz0fYqrHny5EnXcUWZFsqO0I2/Z82aNa7VrKZw6JjnowKfar+qDAlv+og/BSOUyaHjKyihoIae16lTx7Vo1Wv7B1fiWhbf+fhfi0WLFrmfPfaUnQu9PvFZunSp+7rgt122a/uBRB0DAAAAAJByChXNbff0bBHw9rpP1z2zakbGrg+ZHLz7UP+mGyEb2EDoI7ABAAAAAOGtUCoObIRsjQ0AAAAAAICwrbGB0JO/QMx2tQAAAACA8JA/Fd/PEdhAwFp3qMfVAgAAAIAwFRUVbZGREZbaENhAgtSiVqVY1N42IiL1/SdAytCYUhvj9OnTM67AuELI4r0KjCuEC96vEGxeOc61a9emyN/rp06dCvh1CWwgQd5gIqiBYNJ4ypAhAxcVjCuENN6rwLhCuOD9CkkxpjJmzJiirx/oPShdUQAAAAAAQNiiKwoAAAAAAAhbBDYAAAAAAEDYIrABAAAAAADCFoENAAAAAAAQtghsAAAAAACAsEVgAwAAAAAAhC0CGwAAAAAAIGwR2AAAAAAAAGGLwAYAAAAAAAhbBDYAAAAAAEDYIrABAAAAAADCVvqUPgGEviVLltj69eutRIkSVqdOnZQ+HYS5kydP2sSJE89Z3rhxYytatGiKnBPC25w5c6x06dJWvHjxGMt37NhhixYtssyZM1uDBg0sS5YsKXaOCC9nz55171Pt27ePsfynn36y3bt3x1hWpkwZu+KKK5L5DBFO9u/fb3///bcdPXrULr30UqtQocI5vxfnzp1rhw4dsrp161qxYsVS7FwRPtatW2crV660TJkyWa1atSxv3ry+datXr3a///ylT5/+nPc0wF90dLQtXLjQtm/f7t6r9Iht8eLFtmHDBitVqpQbd6EkIlo/ARAHDY0nn3zS/vjjDxfQ0ECvWbOmDRo0yNKlS8c1Q6IsXbrUOnTocM4v19tuu80uueQSriouiP5wu/POO+2dd96xFi1a+JZ/99139txzz7mAhn5B68Zi1KhRLkALJOTNN9+0Tz75xJYvXx5jebNmzVwgw//GU78X27Zty0VFnH755Rfr3bu3VatWzfLkyWOzZs2yNm3a2PPPP+/W6/2pS5culj9/fsuXL5/NmzfP+vbt67YB4vPyyy/bpEmTrFGjRnbw4EH3IeQbb7zh3qPktddes59//tnq1avn20cBkGeffZaLijgpwHrvvffa3r17rXLlyu5Do+uuu869H0lUVJR7L9P9YO3atW3BggUuEPv2229bZGSITAJRYAOIy9SpU6Pr1q0bvXv3bvd8586d0fXq1Yv++uuvuWBItAkTJkQ3a9aMK4iL9t1330XXqFEjumLFitE//vijb/mBAwfc8smTJ7vnZ8+ejb7//vuju3XrxlXHeR0/fjy6b9++bkxVqlQpxrrDhw9HX3LJJdHLli3jKiIgp0+fjr788sujR4wY4Vu2atWq6CpVqkT/8ssv7nmPHj2ie/bsGR0VFeWef/PNN+79a9++fVxlxGn27NluDK1bt863bMiQIe5vdr2Hyd133x391ltvcQURsPfffz/6hhtuiD558qR7vmbNGvd7UOPNe2/S+9nevXvd8+3bt7vnWh4qQiS8glD07bffWvPmza1AgQLueaFChVzkTp+EAom1Zs0aK1++PBcQF0WfTD399NP22GOPxfkJqbLKWrVq5Z7rk4Q77rjDffpw4MABrjzipTHz+++/u0+tYlu7dq37WrZsWa4gArJv3z675ppr7MYbb/Qtq1ixopUrV87++usvO3LkiP3666/WsWNHi4iIcOtbt25tGTNmdJ+2A3E5ffq09ejRI8Z7kf4+V+aGpqd4f2tpnAGB0nTdXr16ufcf0d/qugdUprXo/u/qq692mWVSpEgR9/4WSveFBDYQL83bi/2mqOcrVqzgqiHRNO9TqdxKZVMapfeGCVwIpf/PmDHDbr311nPW6T1KY8w/NVLvXaqboD/2gPh0797dpk6d6tJwY9PYUR2gXbt22ZQpU1yg7MSJE1xMxEsfCL300ku+D4i8dG/V/8mZM6f7faj0bv9gvwIcumHV32BAXJo2bWoPPvhgjGWqeSAaV6rVovepggUL2o8//mjTp093z4Hzueeee2JM6d22bZvt2bPH/T3l/W0V+4NJvVeF0n0hxUMRL0V+c+XKFWNZ9uzZ3XIgsXRzoE+qNm7c6OZ76o++hg0buhoJ1G5BoLxfvmfOnInzvUt/3PnLkSOHbx0Qn/MV1tNNqAqHKktIf9ypgJoMHTqULA4ETLVb9Im7sji8Gi5xvV+RXYZA6ffg4MGD3d9SqiP1559/uuXPPPOMq4GgQNpTTz1lL774orVr144Li/PauXOnffPNNzZu3DiXQdayZcvz/m0VSn9XEdhAvPTpppca6QmZ4jAI21+++qRBxa3UBcX7lEG/aFXY8a677krpU0Qqee+K/V7lPadeNhJLnXceeugh69atmxtPp06dcp9w6eZh7NixXFgkSNNLPvjgA1ecVtkcXsZiXO9XvFchUApYqOCjxpbX/UQFaZWBpqwNGTlypNtOgQ6KaCOhKXSigv4Kki1btsyqV6/usstC/b2Ku1TES1G5Y8eOxVimVmXK2gASQ79s+/Xr5wtqiFLcVNVbre6ApHrv0lx24f0LiaXOTbpR8P6w0zzkTp06ucwNb3wB8VE3lMcff9x1s7j22mt971US199aXpYZEB/dUCrrVXWBPv30Uxcskxo1ariuO15Qw3v/UtDfy+YA4lOlShW7//77XTaiAhqqZyZ6T9J7Uyi/VxHYQLx0w7l58+YYy/ScYkRILM3x/PLLL895Y9QvZwU9gGDQnM/Y711btmxxXylci8SaOHHiOXUPvE+qeP/C+ajOgaYwqeixfxtXr/hjXH9r8V6F89Gn52pprvbAY8aMcRllHtUwmzlz5jn76P2KKb+Iz9dff+0rPuupU6eOrV+/3o03vV95f0uF6nsVgQ3ESx1RlDZ5/Phx91xF0vRG6fXIBi5UhgwZrH///jZt2jTfMhUm0i9mZW0AwaCMIKXl+n8ypYKQ1apVi1HED7gQKhiqKQT+NK6U2p05c2YuJuKk33eqb6BpAv6F+SR//vzuE1H/rgJ639LvRf/MRsCfbjJ79+5t//77rwtqqDtF7A5OWq/fg/6dDvU32OWXX87FRLy/41Tvzp+KZF966aUuU1H3fz/99JOvaLbuD0PtvjBCPV9T+iQQmjRwVUhN6bYqHKPBrGreehPNli1bSp8ewtTw4cNdkSt1s1Aa7vjx4918zxEjRvCpJxJVt0Vpk7FvGnQDqsJXmmeswmm6uVCqrrqpAAnRjaZuDLzijqJsDaVz16tXz32KpT/4tP7zzz+3ChUqcFFxDt1gKkNDYyZ2UENjRuNIgYy7777bbrjhBtd154svvnBTnB599FGuKOL00Ucf2VtvveXq/RQrVizGOt1k5smTx7U4VwHam2++2f0O1O9DBdj0OxGIy6pVq9z4aNCggQu4aoqTfscNGzbMfTCkKXO6L8yaNat7P1MmmoJso0ePdq1iQwGBDZyXpgwo/VapRkpzU5HHUBm8CF9Lliyx3377zc1Lv+yyy1wfbNIjkRj6pdq3b1/r3Lmz+1TB3y+//OKygRRAUweCUqVKcZEREBV11O8+FduLXVRNn2pt377d3VDcdNNNljdvXq4q4qT3H7XajIsyffS+JEr/VvaPPjy64ooryNbAeemDoE2bNsW5rmvXrr725gro68ZUHeiuvvpq9yEAcD7e7zhNHS9ZsqR7j/KvoaH7wgkTJrgpKSpZ0LZt25C6LySwAQAAAAAAwhY1NgAAAAAAQNgisAEAAAAAAMIWgQ0AAAAAABC2CGwAAAAAAICwRWADAAAAAACELQIbAAAAAAAgbBHYAAAAAAAAYSt9Sp8AAABAONm1a5eNGzcuwe0aNWpkWbNmtR9++ME9v+222yxv3rznbBcVFWVDhw61s2fPWps2baxEiRJJct4AAKRWBDYAAAAuwu7du12go0mTJla1atUY69asWWODBw+2zJkzW/78+e3WW289Z/8FCxbYRx99ZMePH7fatWsT2AAA4AIR2AAAALgAhQoVsoceesj3fOnSpb7ARuzAxbZt29zXhg0b2vTp0+MMbEybNs1ld8yYMYN/BwAAEoEaGwAAAEmsZcuW9ueff9q+fftiLD9z5ozNnDnTmjdvzr8BAACJRGADAAAgiZUtW9ZKlSp1TlbG3LlzrVy5cnHW3gAAAIEhsAEAAJBMWRuajuLvu+++c8sBAEDiEdgAAABIBldffXWM6SgnT560n3/+2S0HAACJR2ADAAAgGahjSuHChX3TUX799Vc3RUXLAABA4hHYAAAASCYqEupNR1E3FKahAABw8QhsAAAAJHN3lC1bttisWbMIbAAAEAQENgAAAJJJ7dq1LXfu3Pbiiy+6LiklS5bk2gMAcJEIbAAAACSTyMhINx1FbV4pGgoAQHCkD9JxAAAA0qSCBQvagw8+6IqDxlahQgW3Ttt4brvtNve8TZs2vmXK3tB2JUqUSLbzBgAgtYiIjo6OTumTAAAAAAAASAymogAAAAAAgLBFYAMAAAAAAIQtAhsAAAAAACBsEdgAAAAAAABhi8AGAAAAAAAIWwQ2AAAAAABA2CKwAQAAAAAAwhaBDQAAAAAAELYIbAAAAAAAgLBFYAMAAAAAAIQtAhsAAAAAACBsEdgAAAAAAAAWrv4f3uaVCWC/+vMAAAAASUVORK5CYII=",
+      "text/plain": [
+       "<Figure size 1200x600 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Proximo passar visualizar o plot acima, considerando apenas as colunas STORE_NAME, TM e BUSINESS_NAME\n",
+    "#  para isso vamos usar o seaborn para plotar um grafico de barras, com o eixo x sendo o nome da loja e o eixo y \n",
+    "\n",
+    "import seaborn as sns\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "\n",
+    "# Inicializando o estilo do seaborn para melhor visualizacao\n",
+    "sns.set(style=\"whitegrid\")\n",
+    "f, ax = plt.subplots(figsize=(12, 6))\n",
+    "\n",
+    "# Renome as colunas para facilitar o plot e bater com o desafio, que pede para mostrar Loja, Categoria e TM\n",
+    "df_rank = df_rank.rename(columns={'STORE_NAME': 'Loja', 'BUSINESS_NAME': 'Categoria'})\n",
+    "\n",
+    "# Plottando \n",
+    "sns.barplot(\n",
+    "    data=df_rank.sort_values('TM'),  # ordena crescente pro horizontal ficar maior em cima\n",
+    "    x='TM',\n",
+    "    y='Loja',\n",
+    "    hue='Categoria',\n",
+    "    dodge=False  # barras lado a lado, nao empilhadas\n",
+    ")\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "\n",
+    "# Case 3 - Visualização com IMDB_movies"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Shape: (1000, 11)\n"
+     ]
+    },
+    {
+     "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>Id</th>\n",
+       "      <th>Title</th>\n",
+       "      <th>Genre</th>\n",
+       "      <th>Director</th>\n",
+       "      <th>Actors</th>\n",
+       "      <th>Year</th>\n",
+       "      <th>Runtime</th>\n",
+       "      <th>Rating</th>\n",
+       "      <th>Votes</th>\n",
+       "      <th>RevenueMillions</th>\n",
+       "      <th>Metascore</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>Guardians of the Galaxy</td>\n",
+       "      <td>Action,Adventure,Sci-Fi</td>\n",
+       "      <td>James Gunn</td>\n",
+       "      <td>Chris Pratt, Vin Diesel, Bradley Cooper, Zoe S...</td>\n",
+       "      <td>2014</td>\n",
+       "      <td>121</td>\n",
+       "      <td>8</td>\n",
+       "      <td>757074</td>\n",
+       "      <td>333</td>\n",
+       "      <td>76.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2</td>\n",
+       "      <td>Prometheus</td>\n",
+       "      <td>Adventure,Mystery,Sci-Fi</td>\n",
+       "      <td>Ridley Scott</td>\n",
+       "      <td>Noomi Rapace, Logan Marshall-Green, Michael Fa...</td>\n",
+       "      <td>2012</td>\n",
+       "      <td>124</td>\n",
+       "      <td>7</td>\n",
+       "      <td>485820</td>\n",
+       "      <td>126</td>\n",
+       "      <td>65.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>3</td>\n",
+       "      <td>Split</td>\n",
+       "      <td>Horror,Thriller</td>\n",
+       "      <td>M. Night Shyamalan</td>\n",
+       "      <td>James McAvoy, Anya Taylor-Joy, Haley Lu Richar...</td>\n",
+       "      <td>2016</td>\n",
+       "      <td>117</td>\n",
+       "      <td>7</td>\n",
+       "      <td>157606</td>\n",
+       "      <td>138</td>\n",
+       "      <td>62.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>4</td>\n",
+       "      <td>Sing</td>\n",
+       "      <td>Animation,Comedy,Family</td>\n",
+       "      <td>Christophe Lourdelet</td>\n",
+       "      <td>Matthew McConaughey,Reese Witherspoon, Seth Ma...</td>\n",
+       "      <td>2016</td>\n",
+       "      <td>108</td>\n",
+       "      <td>7</td>\n",
+       "      <td>60545</td>\n",
+       "      <td>270</td>\n",
+       "      <td>59.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>5</td>\n",
+       "      <td>Suicide Squad</td>\n",
+       "      <td>Action,Adventure,Fantasy</td>\n",
+       "      <td>David Ayer</td>\n",
+       "      <td>Will Smith, Jared Leto, Margot Robbie, Viola D...</td>\n",
+       "      <td>2016</td>\n",
+       "      <td>123</td>\n",
+       "      <td>6</td>\n",
+       "      <td>393727</td>\n",
+       "      <td>325</td>\n",
+       "      <td>40.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>995</th>\n",
+       "      <td>996</td>\n",
+       "      <td>Secret in Their Eyes</td>\n",
+       "      <td>Crime,Drama,Mystery</td>\n",
+       "      <td>Billy Ray</td>\n",
+       "      <td>Chiwetel Ejiofor, Nicole Kidman, Julia Roberts...</td>\n",
+       "      <td>2015</td>\n",
+       "      <td>111</td>\n",
+       "      <td>6</td>\n",
+       "      <td>27585</td>\n",
+       "      <td>None</td>\n",
+       "      <td>45.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>996</th>\n",
+       "      <td>997</td>\n",
+       "      <td>Hostel: Part II</td>\n",
+       "      <td>Horror</td>\n",
+       "      <td>Eli Roth</td>\n",
+       "      <td>Lauren German, Heather Matarazzo, Bijou Philli...</td>\n",
+       "      <td>2007</td>\n",
+       "      <td>94</td>\n",
+       "      <td>6</td>\n",
+       "      <td>73152</td>\n",
+       "      <td>18</td>\n",
+       "      <td>46.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>997</th>\n",
+       "      <td>998</td>\n",
+       "      <td>Step Up 2: The Streets</td>\n",
+       "      <td>Drama,Music,Romance</td>\n",
+       "      <td>Jon M. Chu</td>\n",
+       "      <td>Robert Hoffman, Briana Evigan, Cassie Ventura,...</td>\n",
+       "      <td>2008</td>\n",
+       "      <td>98</td>\n",
+       "      <td>6</td>\n",
+       "      <td>70699</td>\n",
+       "      <td>58</td>\n",
+       "      <td>50.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>998</th>\n",
+       "      <td>999</td>\n",
+       "      <td>Search Party</td>\n",
+       "      <td>Adventure,Comedy</td>\n",
+       "      <td>Scot Armstrong</td>\n",
+       "      <td>Adam Pally, T.J. Miller, Thomas Middleditch,Sh...</td>\n",
+       "      <td>2014</td>\n",
+       "      <td>93</td>\n",
+       "      <td>6</td>\n",
+       "      <td>4881</td>\n",
+       "      <td>None</td>\n",
+       "      <td>22.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>999</th>\n",
+       "      <td>1000</td>\n",
+       "      <td>Nine Lives</td>\n",
+       "      <td>Comedy,Family,Fantasy</td>\n",
+       "      <td>Barry Sonnenfeld</td>\n",
+       "      <td>Kevin Spacey, Jennifer Garner, Robbie Amell,Ch...</td>\n",
+       "      <td>2016</td>\n",
+       "      <td>87</td>\n",
+       "      <td>5</td>\n",
+       "      <td>12435</td>\n",
+       "      <td>20</td>\n",
+       "      <td>11.0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>1000 rows × 11 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       Id                    Title                     Genre  \\\n",
+       "0       1  Guardians of the Galaxy   Action,Adventure,Sci-Fi   \n",
+       "1       2               Prometheus  Adventure,Mystery,Sci-Fi   \n",
+       "2       3                    Split           Horror,Thriller   \n",
+       "3       4                     Sing   Animation,Comedy,Family   \n",
+       "4       5            Suicide Squad  Action,Adventure,Fantasy   \n",
+       "..    ...                      ...                       ...   \n",
+       "995   996     Secret in Their Eyes       Crime,Drama,Mystery   \n",
+       "996   997          Hostel: Part II                    Horror   \n",
+       "997   998   Step Up 2: The Streets       Drama,Music,Romance   \n",
+       "998   999             Search Party          Adventure,Comedy   \n",
+       "999  1000               Nine Lives     Comedy,Family,Fantasy   \n",
+       "\n",
+       "                 Director                                             Actors  \\\n",
+       "0              James Gunn  Chris Pratt, Vin Diesel, Bradley Cooper, Zoe S...   \n",
+       "1            Ridley Scott  Noomi Rapace, Logan Marshall-Green, Michael Fa...   \n",
+       "2      M. Night Shyamalan  James McAvoy, Anya Taylor-Joy, Haley Lu Richar...   \n",
+       "3    Christophe Lourdelet  Matthew McConaughey,Reese Witherspoon, Seth Ma...   \n",
+       "4              David Ayer  Will Smith, Jared Leto, Margot Robbie, Viola D...   \n",
+       "..                    ...                                                ...   \n",
+       "995             Billy Ray  Chiwetel Ejiofor, Nicole Kidman, Julia Roberts...   \n",
+       "996              Eli Roth  Lauren German, Heather Matarazzo, Bijou Philli...   \n",
+       "997            Jon M. Chu  Robert Hoffman, Briana Evigan, Cassie Ventura,...   \n",
+       "998        Scot Armstrong  Adam Pally, T.J. Miller, Thomas Middleditch,Sh...   \n",
+       "999      Barry Sonnenfeld  Kevin Spacey, Jennifer Garner, Robbie Amell,Ch...   \n",
+       "\n",
+       "     Year  Runtime Rating   Votes RevenueMillions  Metascore  \n",
+       "0    2014      121      8  757074             333       76.0  \n",
+       "1    2012      124      7  485820             126       65.0  \n",
+       "2    2016      117      7  157606             138       62.0  \n",
+       "3    2016      108      7   60545             270       59.0  \n",
+       "4    2016      123      6  393727             325       40.0  \n",
+       "..    ...      ...    ...     ...             ...        ...  \n",
+       "995  2015      111      6   27585            None       45.0  \n",
+       "996  2007       94      6   73152              18       46.0  \n",
+       "997  2008       98      6   70699              58       50.0  \n",
+       "998  2014       93      6    4881            None       22.0  \n",
+       "999  2016       87      5   12435              20       11.0  \n",
+       "\n",
+       "[1000 rows x 11 columns]"
+      ]
+     },
+     "execution_count": 29,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Primeiro vamos pegar toda tabela e entender que colunas temos disponiveis \n",
+    "df_movies = query('SELECT * FROM IMDB_movies')\n",
+    "print(f'Shape: {df_movies.shape}')\n",
+    "df_movies"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Top 6 generos: ['Action', 'Drama', 'Comedy', 'Adventure', 'Crime', 'Biography']\n"
+     ]
+    },
+    {
+     "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>Id</th>\n",
+       "      <th>Title</th>\n",
+       "      <th>Genre</th>\n",
+       "      <th>Director</th>\n",
+       "      <th>Actors</th>\n",
+       "      <th>Year</th>\n",
+       "      <th>Runtime</th>\n",
+       "      <th>Rating</th>\n",
+       "      <th>Votes</th>\n",
+       "      <th>RevenueMillions</th>\n",
+       "      <th>Metascore</th>\n",
+       "      <th>main_genre</th>\n",
+       "      <th>MetaNorm</th>\n",
+       "      <th>Diff</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>Guardians of the Galaxy</td>\n",
+       "      <td>Action,Adventure,Sci-Fi</td>\n",
+       "      <td>James Gunn</td>\n",
+       "      <td>Chris Pratt, Vin Diesel, Bradley Cooper, Zoe S...</td>\n",
+       "      <td>2014</td>\n",
+       "      <td>121</td>\n",
+       "      <td>8.0</td>\n",
+       "      <td>757074</td>\n",
+       "      <td>333</td>\n",
+       "      <td>76.0</td>\n",
+       "      <td>Action</td>\n",
+       "      <td>7.6</td>\n",
+       "      <td>0.4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2</td>\n",
+       "      <td>Prometheus</td>\n",
+       "      <td>Adventure,Mystery,Sci-Fi</td>\n",
+       "      <td>Ridley Scott</td>\n",
+       "      <td>Noomi Rapace, Logan Marshall-Green, Michael Fa...</td>\n",
+       "      <td>2012</td>\n",
+       "      <td>124</td>\n",
+       "      <td>7.0</td>\n",
+       "      <td>485820</td>\n",
+       "      <td>126</td>\n",
+       "      <td>65.0</td>\n",
+       "      <td>Adventure</td>\n",
+       "      <td>6.5</td>\n",
+       "      <td>0.5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>5</td>\n",
+       "      <td>Suicide Squad</td>\n",
+       "      <td>Action,Adventure,Fantasy</td>\n",
+       "      <td>David Ayer</td>\n",
+       "      <td>Will Smith, Jared Leto, Margot Robbie, Viola D...</td>\n",
+       "      <td>2016</td>\n",
+       "      <td>123</td>\n",
+       "      <td>6.0</td>\n",
+       "      <td>393727</td>\n",
+       "      <td>325</td>\n",
+       "      <td>40.0</td>\n",
+       "      <td>Action</td>\n",
+       "      <td>4.0</td>\n",
+       "      <td>2.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>6</td>\n",
+       "      <td>The Great Wall</td>\n",
+       "      <td>Action,Adventure,Fantasy</td>\n",
+       "      <td>Yimou Zhang</td>\n",
+       "      <td>Matt Damon, Tian Jing, Willem Dafoe, Andy Lau</td>\n",
+       "      <td>2016</td>\n",
+       "      <td>103</td>\n",
+       "      <td>6.0</td>\n",
+       "      <td>56036</td>\n",
+       "      <td>45</td>\n",
+       "      <td>42.0</td>\n",
+       "      <td>Action</td>\n",
+       "      <td>4.2</td>\n",
+       "      <td>1.8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>7</td>\n",
+       "      <td>La La Land</td>\n",
+       "      <td>Comedy,Drama,Music</td>\n",
+       "      <td>Damien Chazelle</td>\n",
+       "      <td>Ryan Gosling, Emma Stone, Rosemarie DeWitt, J....</td>\n",
+       "      <td>2016</td>\n",
+       "      <td>128</td>\n",
+       "      <td>8.0</td>\n",
+       "      <td>258682</td>\n",
+       "      <td>151</td>\n",
+       "      <td>93.0</td>\n",
+       "      <td>Comedy</td>\n",
+       "      <td>9.3</td>\n",
+       "      <td>-1.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>994</th>\n",
+       "      <td>995</td>\n",
+       "      <td>Project X</td>\n",
+       "      <td>Comedy</td>\n",
+       "      <td>Nima Nourizadeh</td>\n",
+       "      <td>Thomas Mann, Oliver Cooper, Jonathan Daniel Br...</td>\n",
+       "      <td>2012</td>\n",
+       "      <td>88</td>\n",
+       "      <td>7.0</td>\n",
+       "      <td>164088</td>\n",
+       "      <td>55</td>\n",
+       "      <td>48.0</td>\n",
+       "      <td>Comedy</td>\n",
+       "      <td>4.8</td>\n",
+       "      <td>2.2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>995</th>\n",
+       "      <td>996</td>\n",
+       "      <td>Secret in Their Eyes</td>\n",
+       "      <td>Crime,Drama,Mystery</td>\n",
+       "      <td>Billy Ray</td>\n",
+       "      <td>Chiwetel Ejiofor, Nicole Kidman, Julia Roberts...</td>\n",
+       "      <td>2015</td>\n",
+       "      <td>111</td>\n",
+       "      <td>6.0</td>\n",
+       "      <td>27585</td>\n",
+       "      <td>None</td>\n",
+       "      <td>45.0</td>\n",
+       "      <td>Crime</td>\n",
+       "      <td>4.5</td>\n",
+       "      <td>1.5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>997</th>\n",
+       "      <td>998</td>\n",
+       "      <td>Step Up 2: The Streets</td>\n",
+       "      <td>Drama,Music,Romance</td>\n",
+       "      <td>Jon M. Chu</td>\n",
+       "      <td>Robert Hoffman, Briana Evigan, Cassie Ventura,...</td>\n",
+       "      <td>2008</td>\n",
+       "      <td>98</td>\n",
+       "      <td>6.0</td>\n",
+       "      <td>70699</td>\n",
+       "      <td>58</td>\n",
+       "      <td>50.0</td>\n",
+       "      <td>Drama</td>\n",
+       "      <td>5.0</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>998</th>\n",
+       "      <td>999</td>\n",
+       "      <td>Search Party</td>\n",
+       "      <td>Adventure,Comedy</td>\n",
+       "      <td>Scot Armstrong</td>\n",
+       "      <td>Adam Pally, T.J. Miller, Thomas Middleditch,Sh...</td>\n",
+       "      <td>2014</td>\n",
+       "      <td>93</td>\n",
+       "      <td>6.0</td>\n",
+       "      <td>4881</td>\n",
+       "      <td>None</td>\n",
+       "      <td>22.0</td>\n",
+       "      <td>Adventure</td>\n",
+       "      <td>2.2</td>\n",
+       "      <td>3.8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>999</th>\n",
+       "      <td>1000</td>\n",
+       "      <td>Nine Lives</td>\n",
+       "      <td>Comedy,Family,Fantasy</td>\n",
+       "      <td>Barry Sonnenfeld</td>\n",
+       "      <td>Kevin Spacey, Jennifer Garner, Robbie Amell,Ch...</td>\n",
+       "      <td>2016</td>\n",
+       "      <td>87</td>\n",
+       "      <td>5.0</td>\n",
+       "      <td>12435</td>\n",
+       "      <td>20</td>\n",
+       "      <td>11.0</td>\n",
+       "      <td>Comedy</td>\n",
+       "      <td>1.1</td>\n",
+       "      <td>3.9</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>819 rows × 14 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       Id                    Title                     Genre  \\\n",
+       "0       1  Guardians of the Galaxy   Action,Adventure,Sci-Fi   \n",
+       "1       2               Prometheus  Adventure,Mystery,Sci-Fi   \n",
+       "4       5            Suicide Squad  Action,Adventure,Fantasy   \n",
+       "5       6           The Great Wall  Action,Adventure,Fantasy   \n",
+       "6       7               La La Land        Comedy,Drama,Music   \n",
+       "..    ...                      ...                       ...   \n",
+       "994   995                Project X                    Comedy   \n",
+       "995   996     Secret in Their Eyes       Crime,Drama,Mystery   \n",
+       "997   998   Step Up 2: The Streets       Drama,Music,Romance   \n",
+       "998   999             Search Party          Adventure,Comedy   \n",
+       "999  1000               Nine Lives     Comedy,Family,Fantasy   \n",
+       "\n",
+       "             Director                                             Actors  \\\n",
+       "0          James Gunn  Chris Pratt, Vin Diesel, Bradley Cooper, Zoe S...   \n",
+       "1        Ridley Scott  Noomi Rapace, Logan Marshall-Green, Michael Fa...   \n",
+       "4          David Ayer  Will Smith, Jared Leto, Margot Robbie, Viola D...   \n",
+       "5         Yimou Zhang      Matt Damon, Tian Jing, Willem Dafoe, Andy Lau   \n",
+       "6     Damien Chazelle  Ryan Gosling, Emma Stone, Rosemarie DeWitt, J....   \n",
+       "..                ...                                                ...   \n",
+       "994   Nima Nourizadeh  Thomas Mann, Oliver Cooper, Jonathan Daniel Br...   \n",
+       "995         Billy Ray  Chiwetel Ejiofor, Nicole Kidman, Julia Roberts...   \n",
+       "997        Jon M. Chu  Robert Hoffman, Briana Evigan, Cassie Ventura,...   \n",
+       "998    Scot Armstrong  Adam Pally, T.J. Miller, Thomas Middleditch,Sh...   \n",
+       "999  Barry Sonnenfeld  Kevin Spacey, Jennifer Garner, Robbie Amell,Ch...   \n",
+       "\n",
+       "     Year  Runtime  Rating   Votes RevenueMillions  Metascore main_genre  \\\n",
+       "0    2014      121     8.0  757074             333       76.0     Action   \n",
+       "1    2012      124     7.0  485820             126       65.0  Adventure   \n",
+       "4    2016      123     6.0  393727             325       40.0     Action   \n",
+       "5    2016      103     6.0   56036              45       42.0     Action   \n",
+       "6    2016      128     8.0  258682             151       93.0     Comedy   \n",
+       "..    ...      ...     ...     ...             ...        ...        ...   \n",
+       "994  2012       88     7.0  164088              55       48.0     Comedy   \n",
+       "995  2015      111     6.0   27585            None       45.0      Crime   \n",
+       "997  2008       98     6.0   70699              58       50.0      Drama   \n",
+       "998  2014       93     6.0    4881            None       22.0  Adventure   \n",
+       "999  2016       87     5.0   12435              20       11.0     Comedy   \n",
+       "\n",
+       "     MetaNorm  Diff  \n",
+       "0         7.6   0.4  \n",
+       "1         6.5   0.5  \n",
+       "4         4.0   2.0  \n",
+       "5         4.2   1.8  \n",
+       "6         9.3  -1.3  \n",
+       "..        ...   ...  \n",
+       "994       4.8   2.2  \n",
+       "995       4.5   1.5  \n",
+       "997       5.0   1.0  \n",
+       "998       2.2   3.8  \n",
+       "999       1.1   3.9  \n",
+       "\n",
+       "[819 rows x 14 columns]"
+      ]
+     },
+     "execution_count": 30,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Como a coluna Genre tem varios generos, separador por virgula, vamos so consider o primeiro.\n",
+    "\n",
+    "df_movies['main_genre'] = df_movies['Genre'].str.split(',').str[0].str.strip()\n",
+    "\n",
+    "# Pra melhor visualizacao, vamos Normalizar metascore pra mesma escala (0-10) pra comparacao direta\n",
+    "df_plot = df_movies.dropna(subset=['Rating', 'Metascore']).copy() # Nao parece ter Na, mas pra evitar problemas\n",
+    "df_plot['Rating'] = pd.to_numeric(df_plot['Rating']) # Garantir que os campos sao numericos\n",
+    "df_plot['Metascore'] = pd.to_numeric(df_plot['Metascore'])\n",
+    "df_plot['MetaNorm'] = df_plot['Metascore'] / 10 # Normal\n",
+    "\n",
+    "# Calcula diferenca publico vs critica e adiciona como coluna\n",
+    "df_plot['Diff'] = df_plot['Rating'] - df_plot['MetaNorm']\n",
+    "\n",
+    "# Top 6 generos pra nao poluir (Outras visualizacoes ficaram muito densas)\n",
+    "top6 = df_plot['main_genre'].value_counts().head(6).index\n",
+    "print(f'Top 6 generos: {top6.tolist()}') # Printando pq vamos hardcodar as cores no proximo\n",
+    "\n",
+    "df_plot = df_plot[df_plot['main_genre'].isin(top6)]\n",
+    "df_plot\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Explicacao de visualizacao\n",
+    "\n",
+    "1. Data o shape do dataframe acima, acredito que seria interessante dois graficos que ilustrem a relacao Rating x Metacritica, para saber se existe uma correlacao entre a nota dada entre o publico e a nota dada pelos criticos de cinema ao filme. Entao um scatter plot com ambas notas em X e Y axis ficaria interessante, tracando uma linha de tentencia e\n",
+    "\n",
+    "2. Se em geral o publico da uma nota acima ou abaixo media para os generos que os criticos. Para isso, boxplot com umas estatistcas de variacao podem ser bem informativas sobre a dispersao dos dados."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1600x700 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import numpy as np # aqui numpy realmente ajuda a calcular a linha de tendencia\n",
+    "\n",
+    "# Comecando o grafico com subplots\n",
+    "fig, axes = plt.subplots(1, 2, figsize=(16, 7))\n",
+    "\n",
+    "colors = {'Action':'#E74C3C','Comedy':'#F39C12','Drama':'#3498DB',\n",
+    "          'Horror':'#2C3E50','Thriller':'#9B59B6','Adventure':'#27AE60'}\n",
+    "\n",
+    "ax = axes[0]\n",
+    "for genre in top6:\n",
+    "    sub = df_plot[df_plot['main_genre'] == genre].dropna(subset=['Metascore', 'Rating'])\n",
+    "    ax.scatter(sub['Metascore'], sub['Rating'], c=colors.get(genre,'#999'),\n",
+    "               label=genre, alpha=0.5, s=25, edgecolors='none')\n",
+    "\n",
+    "# Linha de tendencia\n",
+    "clean = df_plot[['Metascore', 'Rating']].dropna()\n",
+    "z = np.polyfit(clean['Metascore'], clean['Rating'], 1)\n",
+    "p = np.poly1d(z)\n",
+    "ax.plot(sorted(clean['Metascore']), p(sorted(clean['Metascore'])),\n",
+    "        color='gray', linestyle='--', alpha=0.6, linewidth=1.5)\n",
+    "ax.set_xlabel('Metascore (critica)', fontsize=12)\n",
+    "ax.set_ylabel('IMDB Rating (publico)', fontsize=12)\n",
+    "ax.set_title('Rating vs Metascore por Genero', fontsize=14, fontweight='bold')\n",
+    "ax.legend(title='Genero', bbox_to_anchor=(1.05, 1), loc='upper left')\n",
+    "\n",
+    "ax2 = axes[1]\n",
+    "order = df_plot.groupby('main_genre')['Diff'].median().sort_values().index\n",
+    "bp = ax2.boxplot([df_plot[df_plot['main_genre']==g]['Diff'].dropna() for g in order],\n",
+    "                 tick_labels=order, patch_artist=True, widths=0.5)\n",
+    "for patch, genre in zip(bp['boxes'], order):\n",
+    "    patch.set_facecolor(colors.get(genre, '#999'))\n",
+    "    patch.set_alpha(0.7)\n",
+    "ax2.axhline(y=0, color='gray', linestyle=':', alpha=0.5)\n",
+    "ax2.set_ylabel('Diferenca (Rating - Metascore/10)', fontsize=11)\n",
+    "ax2.set_title('Publico gosta mais (+) ou menos (-) que a critica?', fontsize=13, fontweight='bold')\n",
+    "ax2.tick_params(axis='x', rotation=45)\n",
+    "\n",
+    "plt.tight_layout()\n",
+    "plt.show()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "base",
+   "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": "3.13.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/20260626_CassioLima.pdf b/20260626_CassioLima.pdf
new file mode 100644
index 0000000..27aee40
Binary files /dev/null and b/20260626_CassioLima.pdf differ