[GitHub] incubator-carbondata pull request #624: [CARBONDATA-747][WIP] Add simple per...

[jarray888 <gi...@git.apache.org>]

Github user jarray888 commented on a diff in the pull request:

    https://github.com/apache/incubator-carbondata/pull/624#discussion_r104369679
  
    --- Diff: examples/spark2/src/main/scala/org/apache/carbondata/examples/CompareTest.scala ---
    @@ -0,0 +1,122 @@
    +/*
    + * 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.carbondata.examples
    +
    +import org.apache.spark.sql.{DataFrame, Row, SaveMode, SparkSession}
    +
    +import org.apache.carbondata.core.util.CarbonProperties
    +
    +// scalastyle:off println
    +object CompareTest {
    +
    +  val parquetTableName = "comparetest_parquet"
    +  val carbonTableName = "comparetest_carbon"
    +
    +  private def generateDataFrame(spark: SparkSession): DataFrame = {
    +    import spark.implicits._
    +    spark.sparkContext.parallelize(1 to 10 * 1000 * 1000, 4)
    +        .map(x => ("i" + x, "p" + x % 10, "j" + x % 100, x, x + 1, (x + 7) % 21, (x + 5) / 43, x
    +            * 5))
    +        .toDF("id", "country", "city", "c4", "c5", "c6", "c7", "c8")
    +  }
    +
    +  private def loadParquetTable(spark: SparkSession, input: DataFrame): Long = timeit {
    +    input.write.mode(SaveMode.Overwrite).parquet(parquetTableName)
    +  }
    +
    +  private def loadCarbonTable(spark: SparkSession, input: DataFrame): Long = {
    +    spark.sql(s"drop table if exists $carbonTableName")
    +    timeit {
    +      input.write
    +          .format("carbondata")
    +          .option("tableName", carbonTableName)
    +          .option("tempCSV", "false")
    +          .option("single_pass", "true")
    +          .option("dictionary_exclude", "id") // id is high cardinality column
    +          .mode(SaveMode.Overwrite)
    +          .save()
    +    }
    +  }
    +
    +  private def prepareTable(spark: SparkSession): Unit = {
    +    val df = generateDataFrame(spark).cache()
    +    println(s"loading dataframe into table, schema: ${df.schema}")
    +    val loadParquetTime = loadParquetTable(spark, df)
    +    val loadCarbonTime = loadCarbonTable(spark, df)
    +    println(s"load completed, time: $loadParquetTime, $loadCarbonTime")
    +    spark.read.parquet(parquetTableName).registerTempTable(parquetTableName)
    +  }
    +
    +  private def runQuery(spark: SparkSession): Unit = {
    +    val test = Array(
    +      "select count(*) from $table",
    +      "select sum(c4) from $table",
    +      "select sum(c4), sum(c5) from $table",
    +      "select sum(c4), sum(c5), sum(c6) from $table",
    +      "select sum(c4), sum(c5), sum(c6), sum(c7) from $table",
    +      "select sum(c4), sum(c5), sum(c6), sum(c7), avg(c8) from $table",
    +      "select * from $table where id = 'i9999999' ",
    +      "select * from $table where country = 'p9' ",
    +      "select * from $table where city = 'j99' ",
    +      "select * from $table where c4 < 1000 "
    --- End diff --
    
    please add more testcase, for example:
     "select sum(c4) from $table where id like 'i1%' "
     "select sum(c4) from $table where id like '%10' "
     "select sum(c4) from $table where id like '%xyz%' "



---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---