Github user jkbradley commented on a diff in the pull request:
https://github.com/apache/spark/pull/20973#discussion_r183865745
--- Diff: mllib/src/main/scala/org/apache/spark/ml/fpm/PrefixSpan.scala ---
@@ -0,0 +1,91 @@
+/*
+ * 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.ml.fpm
+
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.mllib.fpm.{PrefixSpan => mllibPrefixSpan}
+import org.apache.spark.sql.{DataFrame, Dataset, Row}
+import org.apache.spark.sql.functions.col
+import org.apache.spark.sql.types.{LongType, StructField, StructType}
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * :: Experimental ::
+ * A parallel PrefixSpan algorithm to mine frequent sequential patterns.
+ * The PrefixSpan algorithm is described in J. Pei, et al., PrefixSpan:
Mining Sequential Patterns
+ * Efficiently by Prefix-Projected Pattern Growth
+ * (see <a href="http://doi.org/10.1109/ICDE.2001.914830";>here</a>).
+ *
+ * @see <a
href="https://en.wikipedia.org/wiki/Sequential_Pattern_Mining";>Sequential
Pattern Mining
+ * (Wikipedia)</a>
+ */
+@Since("2.4.0")
+@Experimental
+object PrefixSpan {
+
+ /**
+ * :: Experimental ::
+ * Finds the complete set of frequent sequential patterns in the input
sequences of itemsets.
+ *
+ * @param dataset A dataset or a dataframe containing a sequence column
which is
+ * {{{Seq[Seq[_]]}}} type
+ * @param sequenceCol the name of the sequence column in dataset
--- End diff --
You could add a unit test for that too.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
