From a8acd53fdd5aa0c539bcf699cc652f07bdeb48d1 Mon Sep 17 00:00:00 2001 From: Juliusz Sompolski Date: Wed, 7 Mar 2018 21:44:42 +0100 Subject: [PATCH] Use DECIMAL and DATE in the default TPCDS notebooks. (#130) A long time ago, DECIMAL was substituted by DOUBLE and DATE by STRING to workaround some problems. There is no reason to do it anymore. --- src/main/notebooks/tpcds_datagen.scala | 4 ++-- src/main/notebooks/tpcds_run.scala | 15 +++++++++++++-- 2 files changed, 15 insertions(+), 4 deletions(-) diff --git a/src/main/notebooks/tpcds_datagen.scala b/src/main/notebooks/tpcds_datagen.scala index 22019ec..be00fe1 100644 --- a/src/main/notebooks/tpcds_datagen.scala +++ b/src/main/notebooks/tpcds_datagen.scala @@ -22,9 +22,9 @@ val scaleFactor = "1" // data format. val format = "parquet" // If false, float type will be used instead of decimal. -val useDecimal = false +val useDecimal = true // If false, string type will be used instead of date. -val useDate = false +val useDate = true // If true, rows with nulls in partition key will be thrown away. val filterNull = false // If true, partitions will be coalesced into a single file during generation. diff --git a/src/main/notebooks/tpcds_run.scala b/src/main/notebooks/tpcds_run.scala index 5eaa6ef..6e681d0 100644 --- a/src/main/notebooks/tpcds_run.scala +++ b/src/main/notebooks/tpcds_run.scala @@ -4,9 +4,20 @@ // COMMAND ---------- +// Database to be used: +// TPCDS Scale factor val scaleFactor = "1" -val databaseName = s"tpcds_sf${scaleFactor}_nodecimal_nodate_withnulls" -val iterations = 1 // how many times to run the whole set of queries. +// If false, float type will be used instead of decimal. +val useDecimal = true +// If false, string type will be used instead of date. +val useDate = true +// name of database to be used. +val databaseName = s"tpcds_sf${scaleFactor}" + + s"""_${if (useDecimal) "with" else "no"}decimal""" + + s"""_${if (useDate) "with" else "no"}date""" + + s"""_${if (filterNull) "no" else "with"}nulls""" + +val iterations = 2 // how many times to run the whole set of queries. val timeout = 60 // timeout in hours