Github user ron8hu commented on a diff in the pull request:
https://github.com/apache/spark/pull/15637#discussion_r86647571
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/MapAggregate.scala
---
@@ -0,0 +1,310 @@
+/*
+ * 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.spark.sql.catalyst.expressions.aggregate
+
+import java.nio.ByteBuffer
+
+import scala.collection.immutable.TreeMap
+import scala.collection.mutable
+
+import com.google.common.primitives.{Doubles, Ints, Longs}
+
+import org.apache.spark.sql.catalyst.InternalRow
+import org.apache.spark.sql.catalyst.analysis.TypeCheckResult
+import
org.apache.spark.sql.catalyst.analysis.TypeCheckResult.{TypeCheckFailure,
TypeCheckSuccess}
+import org.apache.spark.sql.catalyst.expressions.{Expression,
ExpressionDescription}
+import org.apache.spark.sql.catalyst.util.ArrayBasedMapData
+import org.apache.spark.sql.types.{DataType, _}
+import org.apache.spark.unsafe.types.UTF8String
+
+/**
+ * The MapAggregate function Computes frequency for each distinct non-null
value of a column.
+ * It returns: 1. null if the table is empty or all values of the column
are null.
+ * 2. (distinct non-null value, frequency) pairs if the number of distinct
non-null values is
+ * less than or equal to the specified threshold.
+ * 3. an empty result if the number of distinct non-null values exceeds
that threshold.
+ *
+ * @param child child expression that can produce column value with
`child.eval(inputRow)`
+ * @param numBinsExpression The maximum number of pairs.
+ */
+@ExpressionDescription(
+ usage = """
+ _FUNC_(col, numBins) - Computes frequency for each distinct non-null
value of column `col`.
+ It returns: 1. null if the table is empty or all values of column
`col` are null.
+ 2. (distinct non-null value, frequency) pairs if the number of
distinct non-null values
--- End diff --
Frequency usually means the rate something occurs. In statistics,
frequency means the number of items occurring in a given category. Here
frequency actually is equivalent to count. We use frequency and count
interchangeably.
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
