From notifications-return-7449-archive-asf-public=cust-asf.ponee.io@ignite.apache.org Sat Oct 19 06:27:18 2019 Return-Path: X-Original-To: archive-asf-public@cust-asf.ponee.io Delivered-To: archive-asf-public@cust-asf.ponee.io Received: from mail.apache.org (hermes.apache.org [207.244.88.153]) by mx-eu-01.ponee.io (Postfix) with SMTP id 71578180654 for ; Sat, 19 Oct 2019 08:27:18 +0200 (CEST) Received: (qmail 80290 invoked by uid 500); 19 Oct 2019 06:27:17 -0000 Mailing-List: contact notifications-help@ignite.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: dev@ignite.apache.org Delivered-To: mailing list notifications@ignite.apache.org Received: (qmail 80281 invoked by uid 99); 19 Oct 2019 06:27:17 -0000 Received: from ec2-52-202-80-70.compute-1.amazonaws.com (HELO gitbox.apache.org) (52.202.80.70) by apache.org (qpsmtpd/0.29) with ESMTP; Sat, 19 Oct 2019 06:27:17 +0000 From: GitBox To: notifications@ignite.apache.org Subject: [GitHub] [ignite] nizhikov commented on a change in pull request #6963: IGNITE-9732: [Spark] Add joins to Spark Dataframe examples Message-ID: <157146643777.18841.14847223014144067631.gitbox@gitbox.apache.org> Date: Sat, 19 Oct 2019 06:27:17 -0000 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: 8bit nizhikov commented on a change in pull request #6963: IGNITE-9732: [Spark] Add joins to Spark Dataframe examples URL: https://github.com/apache/ignite/pull/6963#discussion_r336724572 ########## File path: examples/src/main/spark/org/apache/ignite/examples/spark/IgniteDataFrameJoinExample.scala ########## @@ -0,0 +1,176 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.ignite.examples.spark + +import java.lang.{Integer => JInt, Long => JLong, String => JString} + +import org.apache.ignite.cache.query.SqlFieldsQuery +import org.apache.ignite.configuration.CacheConfiguration +import org.apache.ignite.spark.IgniteDataFrameSettings._ +import org.apache.ignite.{Ignite, Ignition} +import org.apache.log4j.{Level, Logger} +import org.apache.spark.sql.SparkSession + +/** + * Example application demonstrates the join operations between two dataframes or Spark tables with data saved in Ignite caches. + */ +object IgniteDataFrameJoinExample extends App { + /** + * Ignite config file. + */ + private val CONFIG = "examples/config/example-ignite.xml" + + /** + * Test cache name. + */ + private val CACHE_NAME = "testCache" + + //Starting Ignite server node. + val ignite = setupServerAndData + + closeAfter(ignite) { ignite ⇒ + //Creating spark session. + implicit val spark = SparkSession.builder() + .appName("IgniteDataFrameJoinExample") + .master("local") + .config("spark.executor.instances", "2") + .getOrCreate() + + // Adjust the logger to exclude the logs of no interest. + Logger.getRootLogger.setLevel(Level.ERROR) + Logger.getLogger("org.apache.ignite").setLevel(Level.INFO) + + // Executing examples. + + sparkDSLJoinExample + nativeSparkSqlJoinExample + } + + /** + * Examples of usage Ignite DataFrame implementation. + * Selecting data throw Spark DSL. + * + * @param spark SparkSession. + */ + def sparkDSLJoinExample(implicit spark: SparkSession): Unit = { + println("Querying using Spark DSL.") + println + + val persons = spark.read + .format(FORMAT_IGNITE) + .option(OPTION_TABLE, "person") + .option(OPTION_CONFIG_FILE, CONFIG) + .load() + + persons.printSchema() + persons.show() + + val cities = spark.read + .format(FORMAT_IGNITE) + .option(OPTION_TABLE, "city") + .option(OPTION_CONFIG_FILE, CONFIG) + .load() + + persons.printSchema() + persons.show() + + val joinResult = persons.join(cities, persons("city_id") === cities("id")) + .select(persons("name").as("person"), persons("age"), cities("name").as("city"), cities("country")) + + joinResult.explain(true) + joinResult.printSchema() + joinResult.show() + } + + /** + * Examples of usage Ignite DataFrame implementation. + * Registration of Ignite DataFrame for following usage. + * Selecting data by Spark SQL query. + * + * @param spark SparkSession. + */ + def nativeSparkSqlJoinExample(implicit spark: SparkSession): Unit = { + println("Querying using Spark SQL.") + println + + val persons = spark.read + .format(FORMAT_IGNITE) + .option(OPTION_TABLE, "person") + .option(OPTION_CONFIG_FILE, CONFIG) + .load() + + persons.printSchema() + persons.show() + + val cities = spark.read + .format(FORMAT_IGNITE) + .option(OPTION_TABLE, "city") + .option(OPTION_CONFIG_FILE, CONFIG) + .load() + + persons.printSchema() + persons.show() + + // Registering DataFrame as Spark view. + persons.createOrReplaceTempView("person") + cities.createOrReplaceTempView("city") + + // Selecting data from Ignite throw Spark SQL Engine. + val joinResult = spark.sql("SELECT person.name AS person, age, city.name AS city, country FROM person JOIN city ON person.city_id = city.id") Review comment: Can we use multiline string literal here to make SQL query more readabale? ``` val joinResult = spark.sql(""" | SELECT | person.name AS person, | age, | city.name AS city, | country | FROM | person JOIN | city ON person.city_id = city.id """.stripMargin); ``` ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: users@infra.apache.org With regards, Apache Git Services