Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/5799#discussion_r29449175
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/stat/FrequentItems.scala
---
@@ -0,0 +1,121 @@
+/*
+* 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.execution.stat
+
+import org.apache.spark.Logging
+import org.apache.spark.sql.{Column, DataFrame, Row}
+import org.apache.spark.sql.catalyst.plans.logical.LocalRelation
+import org.apache.spark.sql.types.{ArrayType, StructField, StructType}
+
+import scala.collection.mutable.{Map => MutableMap}
+
+private[sql] object FrequentItems extends Logging {
+
+ /** A helper class wrapping `MutableMap[Any, Long]` for simplicity. */
+ private class FreqItemCounter(size: Int) extends Serializable {
+ val baseMap: MutableMap[Any, Long] = MutableMap.empty[Any, Long]
+
+ /**
+ * Add a new example to the counts if it exists, otherwise deduct the
count
+ * from existing items.
+ */
+ def add(key: Any, count: Long): this.type = {
+ if (baseMap.contains(key)) {
+ baseMap(key) += count
+ } else {
+ if (baseMap.size < size) {
+ baseMap += key -> count
+ } else {
+ // TODO: Make this more efficient... A flatMap?
+ baseMap.retain((k, v) => v > count)
+ baseMap.transform((k, v) => v - count)
+ }
+ }
+ this
+ }
+
+ /**
+ * Merge two maps of counts.
+ * @param other The map containing the counts for that partition
+ */
+ def merge(other: FreqItemCounter): this.type = {
+ other.baseMap.foreach { case (k, v) =>
+ add(k, v)
+ }
+ this
+ }
+ }
+
+ /**
+ * Finding frequent items for columns, possibly with false positives.
Using the
+ * frequent element count algorithm described in
+ * [[http://dx.doi.org/10.1145/762471.762473, proposed by Karp,
Schenker, and Papadimitriou]].
+ * The `support` should be greater than 1e-4.
+ * For Internal use only.
+ *
+ * @param df The input 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.
+ * @return A Local DataFrame with the Array of frequent items for each
column.
+ */
+ private[sql] def singlePassFreqItems(
+ df: DataFrame,
+ cols: Seq[String],
+ support: Double): DataFrame = {
+ require(support >= 1e-4, s"support ($support) must be greater than
1e-4.")
+ val numCols = cols.length
+ // number of max items to keep counts for
+ val sizeOfMap = (1 / support).toInt
+ val countMaps = Seq.tabulate(numCols)(i => new
FreqItemCounter(sizeOfMap))
+ val originalSchema = df.schema
+ val colInfo = cols.map { name =>
+ val index = originalSchema.fieldIndex(name)
+ (name, originalSchema.fields(index).dataType)
+ }
+
+ val freqItems =
df.select(cols.map(Column(_)):_*).rdd.aggregate(countMaps)(
+ seqOp = (counts, row) => {
+ var i = 0
+ while (i < numCols) {
+ val thisMap = counts(i)
+ val key = row.get(i)
+ thisMap.add(key, 1L)
+ i += 1
+ }
+ counts
+ },
+ combOp = (baseCounts, counts) => {
+ var i = 0
+ while (i < numCols) {
+ baseCounts(i).merge(counts(i))
+ i += 1
+ }
+ baseCounts
+ }
+ )
+ val justItems = freqItems.map(m => m.baseMap.keys.toSeq)
+ val resultRow = Row(justItems:_*)
+ // append frequent Items to the column name for easy debugging
+ val outputCols = colInfo.map{ v =>
--- End diff --
space before `{`
---
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]
