{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Identification of all the members of the group.\n",
    "Name: Antônio Carlos 8515986\n",
    "\n",
    "Name: Arthur Vieira Barbosa 6482041\n",
    "\n",
    "Name: Camila da Cunha Lopes 8011977\n",
    "\n",
    "Name: Gabriel Baraldi 10336553\n",
    "\n",
    "Name: Thiago Cunha Ferreira 10297605"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Name of the dataset\n",
    "Dataset: Womens Shoe Prices"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Abstract\n",
    "Este dataset descreve quase 10000 ofertas de sapatos femininos, com categorias como preço mínimo e máximo ofertado, tamanho, tipo, marca, loja, entre outros. As entradas são primariamente separadas por tamanho, o que implica em diversas colunas com informações repetidas."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Questions to the dataset\n",
    "### Simple questions\n",
    "1) **Quais são os modelos de sapatos mais caros?**  \n",
    "2) **Quais marcas são geralmente mais caras que outras?**  \n",
    "3) Qual é a cor de sapato mais vendida?  \n",
    "4) Qual é a categoria de sapato mais vendida?  \n",
    "5) **Quais sapatos são mais baratos?**  \n",
    "6) Quais são os sapatos mais leves?  \n",
    "7) Quais sapatos tem maior variação de preço?  \n",
    "### Not so simple questions\n",
    "1) **É possível descobrir a distribuição de tamanhos de pés pelo número de sapatos vendidos?**  \n",
    "2) Sapatos com bons reviews são necessariamente os mais caros?  \n",
    "3) Fabricantes de sapatos mais caros necessariamente vendem e/ou produzem menos?  \n",
    "4) O peso de um sapato afeta a venda de modelos de sapatos?  \n",
    "5) **Ser uma loja grande implica ter mais promoções de sapatos?**"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## EDA\n",
    "Present your EDA strategy: A nossa estratégia de EDA é estudar os tipos de dados contidos no dataset, visualizações e métricas simples com o intuito de entender o que é preciso ser feito para, enfim, obtermos informações interessantes a partir dos dados."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Ao analisar o dataset, percebemos que ele é bastante sujo, com diversas colunas sem entradas, com entradas de tipos diferentes na mesma coluna entre outros problemas. Além disso, a maioria dos seus dados não são númericos, o que dificulta análises mais simples. É possível apartir dos dados extrair informações interessantes, mas isso necessitaria de um préprocessamento que já foge de um EDA básico."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Importando Dados"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "metadata": {},
   "outputs": [],
   "source": [
    "sns.set()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv(\"Datafiniti_Womens_Shoes.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "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>id</th>\n",
       "      <th>dateAdded</th>\n",
       "      <th>dateUpdated</th>\n",
       "      <th>asins</th>\n",
       "      <th>brand</th>\n",
       "      <th>categories</th>\n",
       "      <th>primaryCategories</th>\n",
       "      <th>colors</th>\n",
       "      <th>dimension</th>\n",
       "      <th>ean</th>\n",
       "      <th>...</th>\n",
       "      <th>prices.merchant</th>\n",
       "      <th>prices.offer</th>\n",
       "      <th>prices.returnPolicy</th>\n",
       "      <th>prices.shipping</th>\n",
       "      <th>prices.size</th>\n",
       "      <th>prices.sourceURLs</th>\n",
       "      <th>sizes</th>\n",
       "      <th>sourceURLs</th>\n",
       "      <th>upc</th>\n",
       "      <th>weight</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>AVpfEf_hLJeJML431ueH</td>\n",
       "      <td>2015-05-04T12:13:08Z</td>\n",
       "      <td>2018-01-29T04:38:43Z</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Naturalizer</td>\n",
       "      <td>Clothing,Shoes,Women's Shoes,All Women's Shoes...</td>\n",
       "      <td>Shoes</td>\n",
       "      <td>Silver,Cream Watercolor Floral</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>Overstock.com</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>https://www.overstock.com/Clothing-Shoes/Women...</td>\n",
       "      <td>6W,9W,7.5W,12W,8.5M,9N,9M,9.5M,10.5M,10W,8.5W,...</td>\n",
       "      <td>https://www.walmart.com/ip/Naturalizer-Danya-W...</td>\n",
       "      <td>017136472311</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>AVpi74XfLJeJML43qZAc</td>\n",
       "      <td>2017-01-27T01:23:39Z</td>\n",
       "      <td>2018-01-03T05:21:54Z</td>\n",
       "      <td>NaN</td>\n",
       "      <td>MUK LUKS</td>\n",
       "      <td>Clothing,Shoes,Women's Shoes,Women's Casual Sh...</td>\n",
       "      <td>Shoes</td>\n",
       "      <td>Grey</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3.397705e+10</td>\n",
       "      <td>...</td>\n",
       "      <td>Walmart.com</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Standard</td>\n",
       "      <td>6</td>\n",
       "      <td>https://www.walmart.com/ip/MUK-LUKS-Womens-Jan...</td>\n",
       "      <td>10,7,6,9,8</td>\n",
       "      <td>https://www.walmart.com/ip/MUK-LUKS-Womens-Jan...</td>\n",
       "      <td>033977045743</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>AVpi74XfLJeJML43qZAc</td>\n",
       "      <td>2017-01-27T01:23:39Z</td>\n",
       "      <td>2018-01-03T05:21:54Z</td>\n",
       "      <td>NaN</td>\n",
       "      <td>MUK LUKS</td>\n",
       "      <td>Clothing,Shoes,Women's Shoes,Women's Casual Sh...</td>\n",
       "      <td>Shoes</td>\n",
       "      <td>Grey</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3.397705e+10</td>\n",
       "      <td>...</td>\n",
       "      <td>Slippers Dot Com</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Value</td>\n",
       "      <td>6</td>\n",
       "      <td>https://www.walmart.com/ip/MUK-LUKS-Womens-Jan...</td>\n",
       "      <td>10,7,6,9,8</td>\n",
       "      <td>https://www.walmart.com/ip/MUK-LUKS-Womens-Jan...</td>\n",
       "      <td>033977045743</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>AVpjXyCc1cnluZ0-V-Gj</td>\n",
       "      <td>2017-01-27T01:25:56Z</td>\n",
       "      <td>2018-01-04T11:52:35Z</td>\n",
       "      <td>NaN</td>\n",
       "      <td>MUK LUKS</td>\n",
       "      <td>Clothing,Shoes,Women's Shoes,All Women's Shoes...</td>\n",
       "      <td>Shoes,Shoes</td>\n",
       "      <td>Black</td>\n",
       "      <td>6.0 in x 6.0 in x 1.0 in</td>\n",
       "      <td>3.397705e+10</td>\n",
       "      <td>...</td>\n",
       "      <td>Slippers Dot Com</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Value</td>\n",
       "      <td>6</td>\n",
       "      <td>https://www.walmart.com/ip/MUK-LUKS-Womens-Daw...</td>\n",
       "      <td>10,7,6,9,8</td>\n",
       "      <td>https://www.walmart.com/ip/MUK-LUKS-Womens-Daw...</td>\n",
       "      <td>033977045903</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>AVphGKLPilAPnD_x1Nrm</td>\n",
       "      <td>2017-01-27T01:25:56Z</td>\n",
       "      <td>2018-01-18T03:55:18Z</td>\n",
       "      <td>NaN</td>\n",
       "      <td>MUK LUKS</td>\n",
       "      <td>Clothing,Shoes,Women's Shoes,All Women's Shoes...</td>\n",
       "      <td>Shoes</td>\n",
       "      <td>Grey</td>\n",
       "      <td>6.0 in x 6.0 in x 1.0 in</td>\n",
       "      <td>3.397705e+10</td>\n",
       "      <td>...</td>\n",
       "      <td>Walmart.com</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Expedited</td>\n",
       "      <td>6</td>\n",
       "      <td>https://www.walmart.com/ip/MUK-LUKS-Womens-Daw...</td>\n",
       "      <td>10,7,6,9,8</td>\n",
       "      <td>https://www.walmart.com/ip/MUK-LUKS-Womens-Daw...</td>\n",
       "      <td>033977045958</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 34 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                     id             dateAdded           dateUpdated asins  \\\n",
       "0  AVpfEf_hLJeJML431ueH  2015-05-04T12:13:08Z  2018-01-29T04:38:43Z   NaN   \n",
       "1  AVpi74XfLJeJML43qZAc  2017-01-27T01:23:39Z  2018-01-03T05:21:54Z   NaN   \n",
       "2  AVpi74XfLJeJML43qZAc  2017-01-27T01:23:39Z  2018-01-03T05:21:54Z   NaN   \n",
       "3  AVpjXyCc1cnluZ0-V-Gj  2017-01-27T01:25:56Z  2018-01-04T11:52:35Z   NaN   \n",
       "4  AVphGKLPilAPnD_x1Nrm  2017-01-27T01:25:56Z  2018-01-18T03:55:18Z   NaN   \n",
       "\n",
       "         brand                                         categories  \\\n",
       "0  Naturalizer  Clothing,Shoes,Women's Shoes,All Women's Shoes...   \n",
       "1     MUK LUKS  Clothing,Shoes,Women's Shoes,Women's Casual Sh...   \n",
       "2     MUK LUKS  Clothing,Shoes,Women's Shoes,Women's Casual Sh...   \n",
       "3     MUK LUKS  Clothing,Shoes,Women's Shoes,All Women's Shoes...   \n",
       "4     MUK LUKS  Clothing,Shoes,Women's Shoes,All Women's Shoes...   \n",
       "\n",
       "  primaryCategories                          colors                 dimension  \\\n",
       "0             Shoes  Silver,Cream Watercolor Floral                       NaN   \n",
       "1             Shoes                            Grey                       NaN   \n",
       "2             Shoes                            Grey                       NaN   \n",
       "3       Shoes,Shoes                           Black  6.0 in x 6.0 in x 1.0 in   \n",
       "4             Shoes                            Grey  6.0 in x 6.0 in x 1.0 in   \n",
       "\n",
       "            ean  ...   prices.merchant prices.offer prices.returnPolicy  \\\n",
       "0           NaN  ...     Overstock.com          NaN                 NaN   \n",
       "1  3.397705e+10  ...       Walmart.com          NaN                 NaN   \n",
       "2  3.397705e+10  ...  Slippers Dot Com          NaN                 NaN   \n",
       "3  3.397705e+10  ...  Slippers Dot Com          NaN                 NaN   \n",
       "4  3.397705e+10  ...       Walmart.com          NaN                 NaN   \n",
       "\n",
       "  prices.shipping prices.size  \\\n",
       "0             NaN           S   \n",
       "1        Standard           6   \n",
       "2           Value           6   \n",
       "3           Value           6   \n",
       "4       Expedited           6   \n",
       "\n",
       "                                   prices.sourceURLs  \\\n",
       "0  https://www.overstock.com/Clothing-Shoes/Women...   \n",
       "1  https://www.walmart.com/ip/MUK-LUKS-Womens-Jan...   \n",
       "2  https://www.walmart.com/ip/MUK-LUKS-Womens-Jan...   \n",
       "3  https://www.walmart.com/ip/MUK-LUKS-Womens-Daw...   \n",
       "4  https://www.walmart.com/ip/MUK-LUKS-Womens-Daw...   \n",
       "\n",
       "                                               sizes  \\\n",
       "0  6W,9W,7.5W,12W,8.5M,9N,9M,9.5M,10.5M,10W,8.5W,...   \n",
       "1                                         10,7,6,9,8   \n",
       "2                                         10,7,6,9,8   \n",
       "3                                         10,7,6,9,8   \n",
       "4                                         10,7,6,9,8   \n",
       "\n",
       "                                          sourceURLs           upc weight  \n",
       "0  https://www.walmart.com/ip/Naturalizer-Danya-W...  017136472311    NaN  \n",
       "1  https://www.walmart.com/ip/MUK-LUKS-Womens-Jan...  033977045743    NaN  \n",
       "2  https://www.walmart.com/ip/MUK-LUKS-Womens-Jan...  033977045743    NaN  \n",
       "3  https://www.walmart.com/ip/MUK-LUKS-Womens-Daw...  033977045903    NaN  \n",
       "4  https://www.walmart.com/ip/MUK-LUKS-Womens-Daw...  033977045958    NaN  \n",
       "\n",
       "[5 rows x 34 columns]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "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>ean</th>\n",
       "      <th>prices.amountMax</th>\n",
       "      <th>prices.amountMin</th>\n",
       "      <th>prices.returnPolicy</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>6.710000e+02</td>\n",
       "      <td>10000.000000</td>\n",
       "      <td>10000.000000</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>7.714302e+11</td>\n",
       "      <td>69.223544</td>\n",
       "      <td>51.131209</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>1.847119e+11</td>\n",
       "      <td>19.487286</td>\n",
       "      <td>21.267446</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>3.397705e+10</td>\n",
       "      <td>5.870000</td>\n",
       "      <td>4.880000</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>7.276810e+11</td>\n",
       "      <td>59.990000</td>\n",
       "      <td>37.490000</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>8.701910e+11</td>\n",
       "      <td>64.990000</td>\n",
       "      <td>49.990000</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>8.860660e+11</td>\n",
       "      <td>79.990000</td>\n",
       "      <td>59.990000</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>8.898850e+11</td>\n",
       "      <td>359.950000</td>\n",
       "      <td>359.950000</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                ean  prices.amountMax  prices.amountMin  prices.returnPolicy\n",
       "count  6.710000e+02      10000.000000      10000.000000                  0.0\n",
       "mean   7.714302e+11         69.223544         51.131209                  NaN\n",
       "std    1.847119e+11         19.487286         21.267446                  NaN\n",
       "min    3.397705e+10          5.870000          4.880000                  NaN\n",
       "25%    7.276810e+11         59.990000         37.490000                  NaN\n",
       "50%    8.701910e+11         64.990000         49.990000                  NaN\n",
       "75%    8.860660e+11         79.990000         59.990000                  NaN\n",
       "max    8.898850e+11        359.950000        359.950000                  NaN"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Limpando Dados"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "df2 = df[df[\"prices.size\"].str.contains(\"[0-9]\").fillna(False)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "<ipython-input-22-270255caf9ed>:1: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  df2['prices.size'] = pd.to_numeric(df2['prices.size'],errors='coerce')\n"
     ]
    }
   ],
   "source": [
    "df2['prices.size'] = pd.to_numeric(df2['prices.size'],errors='coerce')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1        6.0\n",
       "2        6.0\n",
       "3        6.0\n",
       "4        6.0\n",
       "5        5.0\n",
       "        ... \n",
       "9995     7.5\n",
       "9996     7.0\n",
       "9997    11.0\n",
       "9998     6.5\n",
       "9999    40.0\n",
       "Name: prices.size, Length: 9986, dtype: float64"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df2[\"prices.size\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "<ipython-input-25-c8281c5dc47e>:1: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  df2[\"prices.size\"] = df2[\"prices.size\"].astype('float64')\n"
     ]
    }
   ],
   "source": [
    "df2[\"prices.size\"] = df2[\"prices.size\"].astype('float64')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Int64Index: 9986 entries, 1 to 9999\n",
      "Data columns (total 34 columns):\n",
      " #   Column               Non-Null Count  Dtype  \n",
      "---  ------               --------------  -----  \n",
      " 0   id                   9986 non-null   object \n",
      " 1   dateAdded            9986 non-null   object \n",
      " 2   dateUpdated          9986 non-null   object \n",
      " 3   asins                3 non-null      object \n",
      " 4   brand                9986 non-null   object \n",
      " 5   categories           9986 non-null   object \n",
      " 6   primaryCategories    9986 non-null   object \n",
      " 7   colors               2625 non-null   object \n",
      " 8   dimension            117 non-null    object \n",
      " 9   ean                  667 non-null    float64\n",
      " 10  imageURLs            9986 non-null   object \n",
      " 11  keys                 9986 non-null   object \n",
      " 12  manufacturer         526 non-null    object \n",
      " 13  manufacturerNumber   2476 non-null   object \n",
      " 14  name                 9986 non-null   object \n",
      " 15  prices.amountMax     9986 non-null   float64\n",
      " 16  prices.amountMin     9986 non-null   float64\n",
      " 17  prices.availability  432 non-null    object \n",
      " 18  prices.color         9986 non-null   object \n",
      " 19  prices.condition     436 non-null    object \n",
      " 20  prices.currency      9986 non-null   object \n",
      " 21  prices.dateAdded     9211 non-null   object \n",
      " 22  prices.dateSeen      9986 non-null   object \n",
      " 23  prices.isSale        9986 non-null   bool   \n",
      " 24  prices.merchant      431 non-null    object \n",
      " 25  prices.offer         121 non-null    object \n",
      " 26  prices.returnPolicy  0 non-null      float64\n",
      " 27  prices.shipping      410 non-null    object \n",
      " 28  prices.size          4067 non-null   float64\n",
      " 29  prices.sourceURLs    9986 non-null   object \n",
      " 30  sizes                9986 non-null   object \n",
      " 31  sourceURLs           9986 non-null   object \n",
      " 32  upc                  9626 non-null   object \n",
      " 33  weight               299 non-null    object \n",
      "dtypes: bool(1), float64(5), object(28)\n",
      "memory usage: 2.6+ MB\n"
     ]
    }
   ],
   "source": [
    "df2.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [],
   "source": [
    "df3 = df2.drop([\"id\",\"dateAdded\",\"dateUpdated\",\"asins\",\"dimension\", \"ean\", \"imageURLs\", \"keys\", \"prices.returnPolicy\",\"upc\"], axis = 1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Int64Index: 9986 entries, 1 to 9999\n",
      "Data columns (total 24 columns):\n",
      " #   Column               Non-Null Count  Dtype  \n",
      "---  ------               --------------  -----  \n",
      " 0   brand                9986 non-null   object \n",
      " 1   categories           9986 non-null   object \n",
      " 2   primaryCategories    9986 non-null   object \n",
      " 3   colors               2625 non-null   object \n",
      " 4   manufacturer         526 non-null    object \n",
      " 5   manufacturerNumber   2476 non-null   object \n",
      " 6   name                 9986 non-null   object \n",
      " 7   prices.amountMax     9986 non-null   float64\n",
      " 8   prices.amountMin     9986 non-null   float64\n",
      " 9   prices.availability  432 non-null    object \n",
      " 10  prices.color         9986 non-null   object \n",
      " 11  prices.condition     436 non-null    object \n",
      " 12  prices.currency      9986 non-null   object \n",
      " 13  prices.dateAdded     9211 non-null   object \n",
      " 14  prices.dateSeen      9986 non-null   object \n",
      " 15  prices.isSale        9986 non-null   bool   \n",
      " 16  prices.merchant      431 non-null    object \n",
      " 17  prices.offer         121 non-null    object \n",
      " 18  prices.shipping      410 non-null    object \n",
      " 19  prices.size          4067 non-null   float64\n",
      " 20  prices.sourceURLs    9986 non-null   object \n",
      " 21  sizes                9986 non-null   object \n",
      " 22  sourceURLs           9986 non-null   object \n",
      " 23  weight               299 non-null    object \n",
      "dtypes: bool(1), float64(3), object(20)\n",
      "memory usage: 2.2+ MB\n"
     ]
    }
   ],
   "source": [
    "df3.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Estatísticas básicas dos valores númericos"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "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>prices.amountMax</th>\n",
       "      <th>prices.amountMin</th>\n",
       "      <th>prices.size</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>9986.000000</td>\n",
       "      <td>9986.000000</td>\n",
       "      <td>4067.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>69.257087</td>\n",
       "      <td>51.153279</td>\n",
       "      <td>8.940251</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>19.413397</td>\n",
       "      <td>21.199086</td>\n",
       "      <td>5.273939</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>5.870000</td>\n",
       "      <td>4.880000</td>\n",
       "      <td>4.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>59.990000</td>\n",
       "      <td>37.490000</td>\n",
       "      <td>6.500000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>64.990000</td>\n",
       "      <td>49.990000</td>\n",
       "      <td>8.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>79.990000</td>\n",
       "      <td>59.990000</td>\n",
       "      <td>9.500000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>359.950000</td>\n",
       "      <td>359.950000</td>\n",
       "      <td>42.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       prices.amountMax  prices.amountMin  prices.size\n",
       "count       9986.000000       9986.000000  4067.000000\n",
       "mean          69.257087         51.153279     8.940251\n",
       "std           19.413397         21.199086     5.273939\n",
       "min            5.870000          4.880000     4.000000\n",
       "25%           59.990000         37.490000     6.500000\n",
       "50%           64.990000         49.990000     8.000000\n",
       "75%           79.990000         59.990000     9.500000\n",
       "max          359.950000        359.950000    42.000000"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df3.describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Qual os sapatos mais caros? E os mais baratos?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 135,
   "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>brand</th>\n",
       "      <th>name</th>\n",
       "      <th>prices.amountMax</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>9701</th>\n",
       "      <td>Red Wing</td>\n",
       "      <td>Red Wing Harriet Boots - Women's</td>\n",
       "      <td>359.95</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9702</th>\n",
       "      <td>Red Wing</td>\n",
       "      <td>Red Wing Harriet Boots - Women's</td>\n",
       "      <td>359.95</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9704</th>\n",
       "      <td>Red Wing</td>\n",
       "      <td>Red Wing Harriet Boots - Women's</td>\n",
       "      <td>359.95</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9703</th>\n",
       "      <td>Red Wing</td>\n",
       "      <td>Red Wing Harriet Boots - Women's</td>\n",
       "      <td>359.95</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9717</th>\n",
       "      <td>Red Wing</td>\n",
       "      <td>Red Wing 6-inch Classic Moc Boots - Women's</td>\n",
       "      <td>289.95</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>134</th>\n",
       "      <td>Faded Glory</td>\n",
       "      <td>Faded Glory Women's Printed Twin Gore Canvas Shoe</td>\n",
       "      <td>12.44</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>133</th>\n",
       "      <td>Unbranded</td>\n",
       "      <td>Women's Essential Light Weight Athletic Shoe</td>\n",
       "      <td>9.62</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>162</th>\n",
       "      <td>Faded Glory</td>\n",
       "      <td>Faded Glory Women's Casual Lace-up Canvas Sneaker</td>\n",
       "      <td>8.97</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>136</th>\n",
       "      <td>Unbranded</td>\n",
       "      <td>Women's Essential Ballet Flat</td>\n",
       "      <td>5.87</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>132</th>\n",
       "      <td>Unbranded</td>\n",
       "      <td>Time and Tru Women's Basic Ballet Flat</td>\n",
       "      <td>5.87</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>9986 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "            brand                                               name  \\\n",
       "9701     Red Wing                   Red Wing Harriet Boots - Women's   \n",
       "9702     Red Wing                   Red Wing Harriet Boots - Women's   \n",
       "9704     Red Wing                   Red Wing Harriet Boots - Women's   \n",
       "9703     Red Wing                   Red Wing Harriet Boots - Women's   \n",
       "9717     Red Wing        Red Wing 6-inch Classic Moc Boots - Women's   \n",
       "...           ...                                                ...   \n",
       "134   Faded Glory  Faded Glory Women's Printed Twin Gore Canvas Shoe   \n",
       "133     Unbranded       Women's Essential Light Weight Athletic Shoe   \n",
       "162   Faded Glory  Faded Glory Women's Casual Lace-up Canvas Sneaker   \n",
       "136     Unbranded                      Women's Essential Ballet Flat   \n",
       "132     Unbranded             Time and Tru Women's Basic Ballet Flat   \n",
       "\n",
       "      prices.amountMax  \n",
       "9701            359.95  \n",
       "9702            359.95  \n",
       "9704            359.95  \n",
       "9703            359.95  \n",
       "9717            289.95  \n",
       "...                ...  \n",
       "134              12.44  \n",
       "133               9.62  \n",
       "162               8.97  \n",
       "136               5.87  \n",
       "132               5.87  \n",
       "\n",
       "[9986 rows x 3 columns]"
      ]
     },
     "execution_count": 135,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df3.sort_values([\"prices.amountMax\"],ascending = False, inplace = False)[[\"brand\",\"name\",\"prices.amountMax\"]]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Quais as marcas mais caras?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 133,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "brand\n",
       "Red Wing       345.95\n",
       "Lowa           199.95\n",
       "Free People    178.00\n",
       "Arc'teryx      170.00\n",
       "Scarpa         169.70\n",
       "Frye           165.45\n",
       "On Footwear    159.99\n",
       "La Sportiva    152.50\n",
       "Name: prices.amountMax, dtype: float64"
      ]
     },
     "execution_count": 133,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(df3.groupby([\"brand\"]).mean().sort_values([\"prices.amountMax\"],ascending = False, inplace = False)[\"prices.amountMax\"][0:8])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Distribuição dos sapatos"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0, 0.5, 'Número de ofertas')"
      ]
     },
     "execution_count": 74,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "df3[df3[\"prices.size\"]<15][\"prices.size\"].hist()\n",
    "plt.title(\"Distribuição de tamanhos de sapato\")\n",
    "plt.xlabel(\"Tamanho do sapato\")\n",
    "plt.ylabel(\"Número de ofertas\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Preço médio de cada vendedor"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 113,
   "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>prices.amountMax</th>\n",
       "      <th>prices.amountMin</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>prices.merchant</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Backcountry.com</th>\n",
       "      <td>118.978239</td>\n",
       "      <td>100.889744</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Shoebuy.com</th>\n",
       "      <td>95.000000</td>\n",
       "      <td>62.800000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Slippers Dot Com</th>\n",
       "      <td>39.000000</td>\n",
       "      <td>39.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>AmazingBasics</th>\n",
       "      <td>37.410000</td>\n",
       "      <td>37.410000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Walmart.com</th>\n",
       "      <td>35.488169</td>\n",
       "      <td>28.858592</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Tasharina Corp</th>\n",
       "      <td>29.750000</td>\n",
       "      <td>29.750000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Style Unlimited</th>\n",
       "      <td>24.990000</td>\n",
       "      <td>24.990000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>DAILYWEAR  SPORTSWEAR CORP.</th>\n",
       "      <td>15.880000</td>\n",
       "      <td>15.880000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                             prices.amountMax  prices.amountMin\n",
       "prices.merchant                                                \n",
       "Backcountry.com                    118.978239        100.889744\n",
       "Shoebuy.com                         95.000000         62.800000\n",
       "Slippers Dot Com                    39.000000         39.000000\n",
       "AmazingBasics                       37.410000         37.410000\n",
       "Walmart.com                         35.488169         28.858592\n",
       "Tasharina Corp                      29.750000         29.750000\n",
       "Style Unlimited                     24.990000         24.990000\n",
       "DAILYWEAR  SPORTSWEAR CORP.         15.880000         15.880000"
      ]
     },
     "execution_count": 113,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "merch = df3.groupby([\"prices.merchant\"]).mean().sort_values([\"prices.amountMax\"],ascending = False, inplace = False)[[\"prices.amountMax\",\"prices.amountMin\"]]\n",
    "merch\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Relação entre a loja e promoção\n",
    "\n",
    "A coluna `prices.merchant` está bastante incompleta, fazendo com que a os dados não representem o dataset. \n",
    "\n",
    "É possível completar essa tabela usando os dados de URL, porém esse tipo de análise não está no escopo desse notebook."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 126,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "prices.merchant            \n",
       "Backcountry.com                352\n",
       "Walmart.com                     71\n",
       "Slippers Dot Com                 3\n",
       "Tasharina Corp                   1\n",
       "Style Unlimited                  1\n",
       "Shoebuy.com                      1\n",
       "DAILYWEAR  SPORTSWEAR CORP.      1\n",
       "AmazingBasics                    1\n",
       "dtype: int64"
      ]
     },
     "execution_count": 126,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df3.value_counts([\"prices.merchant\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 122,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "prices.merchant\n",
       "AmazingBasics                    0\n",
       "Backcountry.com                121\n",
       "DAILYWEAR  SPORTSWEAR CORP.      0\n",
       "Shoebuy.com                      1\n",
       "Slippers Dot Com                 0\n",
       "Style Unlimited                  0\n",
       "Tasharina Corp                   0\n",
       "Walmart.com                     47\n",
       "Name: prices.isSale, dtype: int64"
      ]
     },
     "execution_count": 122,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sale = df3.groupby([\"prices.merchant\"]).sum()[\"prices.isSale\"]\n",
    "sale"
   ]
  }
 ],
 "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": "3.8.5"
  },
  "latex_envs": {
   "LaTeX_envs_menu_present": true,
   "bibliofile": "biblio.bib",
   "cite_by": "apalike",
   "current_citInitial": 1,
   "eqLabelWithNumbers": true,
   "eqNumInitial": 1,
   "hotkeys": {
    "equation": "Ctrl-E",
    "itemize": "Ctrl-I"
   },
   "labels_anchors": false,
   "latex_user_defs": false,
   "report_style_numbering": false,
   "user_envs_cfg": false
  },
  "toc": {
   "colors": {
    "hover_highlight": "#DAA520",
    "running_highlight": "#FF0000",
    "selected_highlight": "#FFD700"
   },
   "moveMenuLeft": true,
   "nav_menu": {
    "height": "134.4px",
    "width": "252px"
   },
   "navigate_menu": true,
   "number_sections": true,
   "sideBar": true,
   "threshold": 4,
   "toc_cell": false,
   "toc_section_display": "block",
   "toc_window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}