{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Exercícios"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 1) Considerando o código abaixo, faça:\n",
    "    -> Crie um df a partir de data cujo index seja labels. Faça os imports necessários\n",
    "    -> Preencha os valores faltantes com a média dos valores\n",
    "    -> Retorne uma lista única dos animais\n",
    "    -> Compute as estatísticas básicas (contagem, soma, média, desvio padrão e variância)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "      age animal priority  visits\n",
      "a  2.5000    cat      yes       1\n",
      "b  3.0000    cat      yes       3\n",
      "c  0.5000  snake       no       2\n",
      "d  3.4375    dog      yes       3\n",
      "e  5.0000    dog       no       2\n",
      "f  2.0000    cat       no       3\n",
      "g  4.5000  snake       no       1\n",
      "h  3.4375    cat      yes       1\n",
      "i  7.0000    dog       no       2\n",
      "j  3.0000    dog       no       1\n",
      "a      cat\n",
      "b      cat\n",
      "c    snake\n",
      "d      dog\n",
      "e      dog\n",
      "f      cat\n",
      "g    snake\n",
      "h      cat\n",
      "i      dog\n",
      "j      dog\n",
      "Name: animal, dtype: object\n",
      "             age     visits\n",
      "count  10.000000  10.000000\n",
      "mean    3.437500   1.900000\n",
      "std     1.770711   0.875595\n",
      "min     0.500000   1.000000\n",
      "25%     2.625000   1.000000\n",
      "50%     3.218750   2.000000\n",
      "75%     4.234375   2.750000\n",
      "max     7.000000   3.000000\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "from pandas import DataFrame\n",
    "\n",
    "\n",
    "\n",
    "data = {'animal': ['cat', 'cat', 'snake', 'dog', 'dog', 'cat', 'snake', 'cat', 'dog', 'dog'],\n",
    "        'age': [2.5, 3, 0.5, np.nan, 5, 2, 4.5, np.nan, 7, 3],\n",
    "        'visits': [1, 3, 2, 3, 2, 3, 1, 1, 2, 1],\n",
    "        'priority': ['yes', 'yes', 'no', 'yes', 'no', 'no', 'no', 'yes', 'no', 'no']}\n",
    "\n",
    "\n",
    "\n",
    "labels = ['a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j']\n",
    "\n",
    "obj = DataFrame(data, index=labels)\n",
    "\n",
    "print(obj.fillna(obj.mean()))\n",
    "print(obj.animal)\n",
    "print(obj.fillna(obj.mean()).describe())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# resposta 1"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 2) Considerando o mesmo código, faça:\n",
    "    -> Crie uma função que multiplique o número de visitas por 2. Retorne o data frame completo com valores atualizados\n",
    "    -> Crie uma função que insere uma coluna que contenha um ranking dos animais mais visitados. Retorne o dataframe ordenado de forma descendente\n",
    "    -> Verifique se os animais da seguinte lista pertencem aos dados originais: New_animals = [‘cow’,’horse’,shark’]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "   age animal priority  visits  ranked_animal\n",
      "a  2.5    cat      yes       1            8.5\n",
      "g  4.5  snake       no       1            8.5\n",
      "h  NaN    cat      yes       1            8.5\n",
      "j  3.0    dog       no       1            8.5\n",
      "c  0.5  snake       no       2            5.0\n",
      "e  5.0    dog       no       2            5.0\n",
      "i  7.0    dog       no       2            5.0\n",
      "b  3.0    cat      yes       3            2.0\n",
      "d  NaN    dog      yes       3            2.0\n",
      "f  2.0    cat       no       3            2.0\n",
      "   age animal priority  visits  ranked_animal  validation\n",
      "a  2.5    cat      yes       1            8.5       False\n",
      "b  3.0    cat      yes       3            2.0       False\n",
      "c  0.5  snake       no       2            5.0       False\n",
      "d  NaN    dog      yes       3            2.0       False\n",
      "e  5.0    dog       no       2            5.0       False\n",
      "f  2.0    cat       no       3            2.0       False\n",
      "g  4.5  snake       no       1            8.5       False\n",
      "h  NaN    cat      yes       1            8.5       False\n",
      "i  7.0    dog       no       2            5.0       False\n",
      "j  3.0    dog       no       1            8.5       False\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\ipykernel_launcher.py:8: FutureWarning: by argument to sort_index is deprecated, please use .sort_values(by=...)\n",
      "  \n"
     ]
    }
   ],
   "source": [
    "# resposta 2\n",
    "\n",
    "#obj['visits'] = obj['visits'].map(lambda x: x*2)\n",
    "#print(obj)\n",
    "\n",
    "obj['ranked_animal'] = obj['visits'].rank(ascending=0)\n",
    "\n",
    "print(obj.sort_index(by='ranked_animal',ascending=False))\n",
    "\n",
    "obj['validation'] = obj['animal'].isin(['cow','horse','shark'])\n",
    "print(obj)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 3) Crie uma função que filtre as linhas do df no código abaixo de acordo com a palavra-chave passada como parâmetro (apenas estado):"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "          DateofBirth State\n",
      "Jane       1986-11-11    NY\n",
      "Nick       1999-05-12    TX\n",
      "Aaron      1976-01-01    FL\n",
      "Penelope   1986-06-01    AL\n",
      "Dean       1983-06-04    AK\n",
      "Christina  1990-03-07    TX\n",
      "Cornelia   1999-07-09    TX\n"
     ]
    }
   ],
   "source": [
    "df = pd.DataFrame({'DateofBirth':['1986-11-11','1999-05-12','1976-01-01',\n",
    "                                  '1986-06-01','1983-06-04','1990-03-07',\n",
    "                                  '1999-07-09'],\n",
    "                   'State':['NY','TX','FL','AL','AK','TX','TX']},\n",
    "                 index=['Jane','Nick','Aaron','Penelope','Dean',\n",
    "                        'Christina','Cornelia'])\n",
    "print(df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "          DateofBirth State\n",
      "Nick       1999-05-12    TX\n",
      "Christina  1990-03-07    TX\n",
      "Cornelia   1999-07-09    TX\n"
     ]
    }
   ],
   "source": [
    "\n",
    "def filtra_estado(df,estado):\n",
    "    return df.loc[df['State'] == estado]\n",
    "\n",
    "print(filtra_estado(df,'TX'))\n",
    "    "
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.6.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}