From 4c868b9943a2d86107d1f15f8df9830aac36fb75 Mon Sep 17 00:00:00 2001 From: Reynold Xin Date: Mon, 1 Jun 2015 21:29:39 -0700 Subject: [minor doc] Add exploratory data analysis warning for DataFrame.stat.freqItem API Author: Reynold Xin Closes #6569 from rxin/freqItemsWarning and squashes the following commits: 7eec145 [Reynold Xin] [minor doc] Add exploratory data analysis warning for DataFrame.stat.freqItem API. --- .../scala/org/apache/spark/sql/DataFrameStatFunctions.scala | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'sql') diff --git a/sql/core/src/main/scala/org/apache/spark/sql/DataFrameStatFunctions.scala b/sql/core/src/main/scala/org/apache/spark/sql/DataFrameStatFunctions.scala index b624eaa201..edb9ed7bba 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/DataFrameStatFunctions.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/DataFrameStatFunctions.scala @@ -97,6 +97,9 @@ final class DataFrameStatFunctions private[sql](df: DataFrame) { * [[http://dx.doi.org/10.1145/762471.762473, proposed by Karp, Schenker, and Papadimitriou]]. * The `support` should be greater than 1e-4. * + * This function is meant for exploratory data analysis, as we make no guarantee about the + * backward compatibility of the schema of the resulting [[DataFrame]]. + * * @param cols the names of the columns to search frequent items in. * @param support The minimum frequency for an item to be considered `frequent`. Should be greater * than 1e-4. @@ -114,6 +117,9 @@ final class DataFrameStatFunctions private[sql](df: DataFrame) { * [[http://dx.doi.org/10.1145/762471.762473, proposed by Karp, Schenker, and Papadimitriou]]. * Uses a `default` support of 1%. * + * This function is meant for exploratory data analysis, as we make no guarantee about the + * backward compatibility of the schema of the resulting [[DataFrame]]. + * * @param cols the names of the columns to search frequent items in. * @return A Local DataFrame with the Array of frequent items for each column. * @@ -128,6 +134,9 @@ final class DataFrameStatFunctions private[sql](df: DataFrame) { * frequent element count algorithm described in * [[http://dx.doi.org/10.1145/762471.762473, proposed by Karp, Schenker, and Papadimitriou]]. * + * This function is meant for exploratory data analysis, as we make no guarantee about the + * backward compatibility of the schema of the resulting [[DataFrame]]. + * * @param cols the names of the columns to search frequent items in. * @return A Local DataFrame with the Array of frequent items for each column. * @@ -143,6 +152,9 @@ final class DataFrameStatFunctions private[sql](df: DataFrame) { * [[http://dx.doi.org/10.1145/762471.762473, proposed by Karp, Schenker, and Papadimitriou]]. * Uses a `default` support of 1%. * + * This function is meant for exploratory data analysis, as we make no guarantee about the + * backward compatibility of the schema of the resulting [[DataFrame]]. + * * @param cols the names of the columns to search frequent items in. * @return A Local DataFrame with the Array of frequent items for each column. * -- cgit v1.2.3