[SPARK-9297] [SQL] Add covar_pop and covar_samp

JIRA: https://issues.apache.org/jira/browse/SPARK-9297

Add two aggregation functions: covar_pop and covar_samp.

Author: Liang-Chi Hsieh <viirya@gmail.com>
Author: Liang-Chi Hsieh <viirya@appier.com>

Closes #10029 from viirya/covar-funcs.

1 files changed, 40 insertions, 0 deletions

diff --git a/sql/core/src/main/scala/org/apache/spark/sql/functions.scala b/sql/core/src/main/scala/org/apache/spark/sql/functions.scala
index 592d79df31..71fea2716b 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/functions.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/functions.scala
@@ -309,6 +309,46 @@ object functions extends LegacyFunctions {
     countDistinct(Column(columnName), columnNames.map(Column.apply) : _*)
 
   /**
+   * Aggregate function: returns the population covariance for two columns.
+   *
+   * @group agg_funcs
+   * @since 2.0.0
+   */
+  def covar_pop(column1: Column, column2: Column): Column = withAggregateFunction {
+    CovPopulation(column1.expr, column2.expr)
+  }
+
+  /**
+   * Aggregate function: returns the population covariance for two columns.
+   *
+   * @group agg_funcs
+   * @since 2.0.0
+   */
+  def covar_pop(columnName1: String, columnName2: String): Column = {
+    covar_pop(Column(columnName1), Column(columnName2))
+  }
+
+  /**
+   * Aggregate function: returns the sample covariance for two columns.
+   *
+   * @group agg_funcs
+   * @since 2.0.0
+   */
+  def covar_samp(column1: Column, column2: Column): Column = withAggregateFunction {
+    CovSample(column1.expr, column2.expr)
+  }
+
+  /**
+   * Aggregate function: returns the sample covariance for two columns.
+   *
+   * @group agg_funcs
+   * @since 2.0.0
+   */
+  def covar_samp(columnName1: String, columnName2: String): Column = {
+    covar_samp(Column(columnName1), Column(columnName2))
+  }
+
+  /**
    * Aggregate function: returns the first value in a group.
    *
    * @group agg_funcs