pyspark estudo

4_spark/spark4.ipynb

@@ -0,0 +1,765 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# <h1 align=\"center\"><font color=\"yellow\">spark</font></h1>"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<font color=\"yellow\">Data Scientist.: Dr.Eddy Giusepe Chirinos Isidro</font>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import findspark\n",
+    "\n",
+    "findspark.init()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "23/07/26 11:36:59 WARN Utils: Your hostname, eddygiusepe resolves to a loopback address: 127.0.1.1; using 192.168.0.141 instead (on interface wlp0s20f3)\n",
+      "23/07/26 11:36:59 WARN Utils: Set SPARK_LOCAL_IP if you need to bind to another address\n",
+      "Setting default log level to \"WARN\".\n",
+      "To adjust logging level use sc.setLogLevel(newLevel). For SparkR, use setLogLevel(newLevel).\n",
+      "23/07/26 11:37:00 WARN NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "\n",
+       "            <div>\n",
+       "                <p><b>SparkSession - in-memory</b></p>\n",
+       "                \n",
+       "        <div>\n",
+       "            <p><b>SparkContext</b></p>\n",
+       "\n",
+       "            <p><a href=\"http://192.168.0.141:4040\">Spark UI</a></p>\n",
+       "\n",
+       "            <dl>\n",
+       "              <dt>Version</dt>\n",
+       "                <dd><code>v3.4.1</code></dd>\n",
+       "              <dt>Master</dt>\n",
+       "                <dd><code>local</code></dd>\n",
+       "              <dt>AppName</dt>\n",
+       "                <dd><code>spark_Eddy4</code></dd>\n",
+       "            </dl>\n",
+       "        </div>\n",
+       "        \n",
+       "            </div>\n",
+       "        "
+      ],
+      "text/plain": [
+       "<pyspark.sql.session.SparkSession at 0x7f46d41b71c0>"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from pyspark.sql import SparkSession\n",
+    "\n",
+    "# Inicializa o SparkSession:\n",
+    "spark = SparkSession.builder.master('local')\\\n",
+    "                            .appName(\"spark_Eddy4\")\\\n",
+    "                            .getOrCreate()\n",
+    "\n",
+    "spark"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+--------+-------------+---------+---------+\n",
+      "|id_carro| modelo_carro|    preco|cod_marca|\n",
+      "+--------+-------------+---------+---------+\n",
+      "|       1|       Avalon|$78401.95|       54|\n",
+      "|       1|       Avalon|$78401.95|       54|\n",
+      "|       2|          RDX|$95987.38|        1|\n",
+      "|       3|         Golf|$61274.55|       55|\n",
+      "|       4|           EX|$84981.12|       23|\n",
+      "|       5|       Escort|$77466.89|       17|\n",
+      "|       6|   Expedition|$84698.71|       17|\n",
+      "|       7|      Voyager|$95567.75|       42|\n",
+      "|       8|        Civic|$84749.22|       20|\n",
+      "|       9|     Defender|$98600.79|       29|\n",
+      "|      10| V8 Vantage S|$94791.61|        2|\n",
+      "|      11|          C70|$97874.76|       56|\n",
+      "|      12|G-Series 1500|$71638.24|       10|\n",
+      "|      13|       Legacy|$95850.12|       52|\n",
+      "|      14|          DB9|$86707.30|        2|\n",
+      "|      15|     Mulsanne|$70453.70|        6|\n",
+      "|      16|           RX|$46752.60|       30|\n",
+      "|      17|       Rabbit|$78048.08|       55|\n",
+      "|      18|            Q|$65193.95|       23|\n",
+      "|      19|          S60|$65396.98|       56|\n",
+      "+--------+-------------+---------+---------+\n",
+      "only showing top 20 rows\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Lendo arquivos:\n",
+    "\n",
+    "df_carros= spark.read.format(\"csv\").option(\"header\", True).option(\"encoding\", \"utf-8\").load(\"./data/modelo_carro.csv\", sep=\",\")\n",
+    "\n",
+    "df_carros.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "                                                                                \r"
+     ]
+    }
+   ],
+   "source": [
+    "# Salvando arquivo:\n",
+    "#df_carros.write.format(\"parquet\").save(\"modelo_carro_parquet\")\n",
+    "\n",
+    "# Para sobreescrever:\n",
+    "df_carros.write.format(\"parquet\").mode(\"overwrite\").save(\"modelo_carro_parquet\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Em outros formatos:\n",
+    "\n",
+    "# df_carros.write.format(\"avro\").save(\"modelo_carro_avro\") --> Não consegui instalar!\n",
+    " \n",
+    "df_carros.write.format(\"json\").save(\"modelo_carro_json\")"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# <font color=\"red\">Select</font>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+--------+-------------+---------+---------+\n",
+      "|id_carro| modelo_carro|    preco|cod_marca|\n",
+      "+--------+-------------+---------+---------+\n",
+      "|       1|       Avalon|$78401.95|       54|\n",
+      "|       1|       Avalon|$78401.95|       54|\n",
+      "|       2|          RDX|$95987.38|        1|\n",
+      "|       3|         Golf|$61274.55|       55|\n",
+      "|       4|           EX|$84981.12|       23|\n",
+      "|       5|       Escort|$77466.89|       17|\n",
+      "|       6|   Expedition|$84698.71|       17|\n",
+      "|       7|      Voyager|$95567.75|       42|\n",
+      "|       8|        Civic|$84749.22|       20|\n",
+      "|       9|     Defender|$98600.79|       29|\n",
+      "|      10| V8 Vantage S|$94791.61|        2|\n",
+      "|      11|          C70|$97874.76|       56|\n",
+      "|      12|G-Series 1500|$71638.24|       10|\n",
+      "|      13|       Legacy|$95850.12|       52|\n",
+      "|      14|          DB9|$86707.30|        2|\n",
+      "|      15|     Mulsanne|$70453.70|        6|\n",
+      "|      16|           RX|$46752.60|       30|\n",
+      "|      17|       Rabbit|$78048.08|       55|\n",
+      "|      18|            Q|$65193.95|       23|\n",
+      "|      19|          S60|$65396.98|       56|\n",
+      "+--------+-------------+---------+---------+\n",
+      "only showing top 20 rows\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "df_carros= spark.read.format(\"csv\").option(\"header\", True).load(\"./data/modelo_carro.csv\")\n",
+    "\n",
+    "df_carros.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "root\n",
+      " |-- id_carro: string (nullable = true)\n",
+      " |-- modelo_carro: string (nullable = true)\n",
+      " |-- preco: string (nullable = true)\n",
+      " |-- cod_marca: string (nullable = true)\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "df_carros.printSchema()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+-------------+--------+\n",
+      "| modelo_carro|id_carro|\n",
+      "+-------------+--------+\n",
+      "|       Avalon|       1|\n",
+      "|       Avalon|       1|\n",
+      "|          RDX|       2|\n",
+      "|         Golf|       3|\n",
+      "|           EX|       4|\n",
+      "|       Escort|       5|\n",
+      "|   Expedition|       6|\n",
+      "|      Voyager|       7|\n",
+      "|        Civic|       8|\n",
+      "|     Defender|       9|\n",
+      "| V8 Vantage S|      10|\n",
+      "|          C70|      11|\n",
+      "|G-Series 1500|      12|\n",
+      "|       Legacy|      13|\n",
+      "|          DB9|      14|\n",
+      "|     Mulsanne|      15|\n",
+      "|           RX|      16|\n",
+      "|       Rabbit|      17|\n",
+      "|            Q|      18|\n",
+      "|          S60|      19|\n",
+      "+-------------+--------+\n",
+      "only showing top 20 rows\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "df_carros_spark = df_carros.select(\"modelo_carro\", \"id_carro\")\n",
+    "\n",
+    "df_carros_spark.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+-------------+--------+\n",
+      "|  eddy_modelo|id_carro|\n",
+      "+-------------+--------+\n",
+      "|       Avalon|       1|\n",
+      "|       Avalon|       1|\n",
+      "|          RDX|       2|\n",
+      "|         Golf|       3|\n",
+      "|           EX|       4|\n",
+      "|       Escort|       5|\n",
+      "|   Expedition|       6|\n",
+      "|      Voyager|       7|\n",
+      "|        Civic|       8|\n",
+      "|     Defender|       9|\n",
+      "| V8 Vantage S|      10|\n",
+      "|          C70|      11|\n",
+      "|G-Series 1500|      12|\n",
+      "|       Legacy|      13|\n",
+      "|          DB9|      14|\n",
+      "|     Mulsanne|      15|\n",
+      "|           RX|      16|\n",
+      "|       Rabbit|      17|\n",
+      "|            Q|      18|\n",
+      "|          S60|      19|\n",
+      "+-------------+--------+\n",
+      "only showing top 20 rows\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Posso colocar um Alias:\n",
+    "from pyspark.sql.functions import col \n",
+    "\n",
+    "df_carros_spark = df_carros.select(col(\"modelo_carro\").alias(\"eddy_modelo\"), \"id_carro\")\n",
+    "\n",
+    "df_carros_spark.show()"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# <font color=\"red\">Filtros</font>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+--------+------------+---------+---------+\n",
+      "|id_carro|modelo_carro|    preco|cod_marca|\n",
+      "+--------+------------+---------+---------+\n",
+      "|       1|      Avalon|$78401.95|       54|\n",
+      "|       1|      Avalon|$78401.95|       54|\n",
+      "|       2|         RDX|$95987.38|        1|\n",
+      "|       3|        Golf|$61274.55|       55|\n",
+      "|       4|          EX|$84981.12|       23|\n",
+      "+--------+------------+---------+---------+\n",
+      "only showing top 5 rows\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "df_carros= spark.read.format(\"csv\").option(\"header\", True).load(\"./data/modelo_carro.csv\")\n",
+    "\n",
+    "df_carros.show(5)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+--------+------------+---------+---------+\n",
+      "|id_carro|modelo_carro|    preco|cod_marca|\n",
+      "+--------+------------+---------+---------+\n",
+      "|       1|      Avalon|$78401.95|       54|\n",
+      "|       1|      Avalon|$78401.95|       54|\n",
+      "+--------+------------+---------+---------+\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "df_carros.where(\"id_carro = '1'\").show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+--------+------------+---------+---------+\n",
+      "|id_carro|modelo_carro|    preco|cod_marca|\n",
+      "+--------+------------+---------+---------+\n",
+      "|       1|      Avalon|$78401.95|       54|\n",
+      "|       1|      Avalon|$78401.95|       54|\n",
+      "+--------+------------+---------+---------+\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "# ou\n",
+    "df_carros.filter(\"id_carro = '1'\").show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+--------+------------+---------+---------+\n",
+      "|id_carro|modelo_carro|    preco|cod_marca|\n",
+      "+--------+------------+---------+---------+\n",
+      "|       1|      Avalon|$78401.95|       54|\n",
+      "|       1|      Avalon|$78401.95|       54|\n",
+      "+--------+------------+---------+---------+\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "from pyspark.sql.functions import *\n",
+    "\n",
+    "df_carros.where(col(\"id_carro\") == '1').show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+--------+------------+-----+---------+\n",
+      "|id_carro|modelo_carro|preco|cod_marca|\n",
+      "+--------+------------+-----+---------+\n",
+      "+--------+------------+-----+---------+\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "df_carros.where((col(\"id_carro\") == '1') & (col(\"modelo_carro\") == 'Golf')).show()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+--------+------------+---------+---------+\n",
+      "|id_carro|modelo_carro|    preco|cod_marca|\n",
+      "+--------+------------+---------+---------+\n",
+      "|       1|      Avalon|$78401.95|       54|\n",
+      "|       1|      Avalon|$78401.95|       54|\n",
+      "|       3|        Golf|$61274.55|       55|\n",
+      "|     237|        Golf|$66249.75|       55|\n",
+      "|     330|        Golf|$82099.83|       55|\n",
+      "+--------+------------+---------+---------+\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "df_carros.where((col(\"id_carro\") == '1') | (col(\"modelo_carro\") == 'Golf')).show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+--------+------------+---------+---------+\n",
+      "|id_carro|modelo_carro|    preco|cod_marca|\n",
+      "+--------+------------+---------+---------+\n",
+      "|       1|      Avalon|$78401.95|       54|\n",
+      "|       1|      Avalon|$78401.95|       54|\n",
+      "+--------+------------+---------+---------+\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Também:\n",
+    "\n",
+    "df_carros.where(df_carros[\"id_carro\"]== \"1\").show()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+--------+-------------------+---------+---------+\n",
+      "|id_carro|       modelo_carro|    preco|cod_marca|\n",
+      "+--------+-------------------+---------+---------+\n",
+      "|       5|             Escort|$77466.89|       17|\n",
+      "|       6|         Expedition|$84698.71|       17|\n",
+      "|      33|            Mustang|$49088.78|       17|\n",
+      "|      46|     Crown Victoria|$91605.58|       17|\n",
+      "|      52|           Freestar|$52971.00|       17|\n",
+      "|      59| LTD Crown Victoria|$94694.22|       17|\n",
+      "|      94|           E-Series|$54544.30|       17|\n",
+      "|      97|Explorer Sport Trac|$77874.85|       17|\n",
+      "|     118|             Taurus|$80544.37|       17|\n",
+      "|     126|             Taurus|$66074.65|       17|\n",
+      "|     141|            Mustang|$51926.66|       17|\n",
+      "|     168|             Escort|$53343.40|       17|\n",
+      "|     176|        Thunderbird|$62453.21|       17|\n",
+      "|     199|     Econoline E250|$62348.12|       17|\n",
+      "|     206|            Mustang|$93492.30|       17|\n",
+      "|     209|             Bronco|$67474.88|       17|\n",
+      "|     215|       Five Hundred|$69267.39|       17|\n",
+      "|     221|               F250|$98421.52|       17|\n",
+      "|     230|        Thunderbird|$78179.55|       17|\n",
+      "|     231|           Aerostar|$83764.41|       17|\n",
+      "+--------+-------------------+---------+---------+\n",
+      "only showing top 20 rows\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Posso até criar um DataFrame:\n",
+    "\n",
+    "df_carros_marca =  df_carros.where(df_carros[\"cod_marca\"] == \"17\").show()"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# <font color=\"red\">Duplicados e replace</font>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+--------+------------+---------+---------+\n",
+      "|id_carro|modelo_carro|    preco|cod_marca|\n",
+      "+--------+------------+---------+---------+\n",
+      "|       1|      Avalon|$78401.95|       54|\n",
+      "|       1|      Avalon|$78401.95|       54|\n",
+      "|       2|         RDX|$95987.38|        1|\n",
+      "|       3|        Golf|$61274.55|       55|\n",
+      "|       4|          EX|$84981.12|       23|\n",
+      "+--------+------------+---------+---------+\n",
+      "only showing top 5 rows\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "df_carros= spark.read.format(\"csv\").option(\"header\", True).load(\"./data/modelo_carro.csv\")\n",
+    "\n",
+    "df_carros.show(5)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+--------+------------+---------+---------+\n",
+      "|id_carro|modelo_carro|    preco|cod_marca|\n",
+      "+--------+------------+---------+---------+\n",
+      "|       1|      Avalon|$78401.95|       54|\n",
+      "|       1|      Avalon|$78401.95|       54|\n",
+      "+--------+------------+---------+---------+\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "df_carros.where(df_carros['id_carro'] == '1').show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+--------+------------+---------+---------+\n",
+      "|id_carro|modelo_carro|    preco|cod_marca|\n",
+      "+--------+------------+---------+---------+\n",
+      "|      81|         928|$75144.55|       44|\n",
+      "|      87|       Truck|$57007.15|       39|\n",
+      "|     319|      Vision|$80349.11|       15|\n",
+      "+--------+------------+---------+---------+\n",
+      "only showing top 3 rows\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "df_carros_duplicates = df_carros.distinct() # Com isto removemos as linhas duplicadas \n",
+    "\n",
+    "# Posso usar também (fazem a mesma coisas) --> df_carros_duplicates = df_carros.dropDuplicates()\n",
+    "df_carros_duplicates.show(3)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+--------+------------+---------+---------+\n",
+      "|id_carro|modelo_carro|    preco|cod_marca|\n",
+      "+--------+------------+---------+---------+\n",
+      "|       1|      Avalon|$78401.95|       54|\n",
+      "+--------+------------+---------+---------+\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "df_carros_duplicates.where(df_carros_duplicates['id_carro'] == '1').show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+--------+------------+--------+---------+\n",
+      "|id_carro|modelo_carro|   preco|cod_marca|\n",
+      "+--------+------------+--------+---------+\n",
+      "|       1|      Avalon|78401.95|       54|\n",
+      "|       1|      Avalon|78401.95|       54|\n",
+      "|       2|         RDX|95987.38|        1|\n",
+      "+--------+------------+--------+---------+\n",
+      "only showing top 3 rows\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Vamos remover o \"$\":\n",
+    "from pyspark.sql.functions import *  # posso usar * ou regexp_replace\n",
+    "\n",
+    "df_carros_cifrao = df_carros\n",
+    "\n",
+    "df_carros_cifrao = df_carros_cifrao.withColumn(\"preco\", regexp_replace(\"preco\", \"\\$\", \"\")) # Tem colocar a contra barra \"\\\" para reconhecer o caráter especial\n",
+    "\n",
+    "df_carros_cifrao = df_carros_cifrao.withColumn(\"preco\", col(\"preco\").cast(\"float\")) # Troquei a coluna \"preco\" de str para float (32bits - 7 dígitos decimais) ou double (64bits - 15 ou 16 dígitos decimais).\n",
+    "\n",
+    "df_carros_cifrao.show(3)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "root\n",
+      " |-- id_carro: string (nullable = true)\n",
+      " |-- modelo_carro: string (nullable = true)\n",
+      " |-- preco: float (nullable = true)\n",
+      " |-- cod_marca: string (nullable = true)\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "df_carros_cifrao.printSchema()"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# <font color=\"red\">Tipagem de Dados</font>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "venv_spark",
+   "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": "3.10.6"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}