Github user jkbradley commented on a diff in the pull request:
https://github.com/apache/spark/pull/15148#discussion_r84588285
--- Diff: mllib/src/main/scala/org/apache/spark/ml/feature/MinHash.scala ---
@@ -0,0 +1,118 @@
+/*
+ * 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.feature
+
+import scala.util.Random
+
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.ml.linalg.{Vector, Vectors, VectorUDT}
+import org.apache.spark.ml.param.shared.HasSeed
+import org.apache.spark.ml.util.{Identifiable, SchemaUtils}
+import org.apache.spark.sql.types.StructType
+
+/**
+ * :: Experimental ::
+ * Model produced by [[MinHash]]
+ * @param hashFunctions An array of hash functions, mapping elements to
their hash values.
+ */
+@Experimental
+@Since("2.1.0")
+class MinHashModel private[ml] (override val uid: String, hashFunctions:
Array[Int => Long])
+ extends LSHModel[MinHashModel] {
+
+ @Since("2.1.0")
+ override protected[this] val hashFunction: Vector => Vector = {
+ elems: Vector =>
+ require(elems.numNonzeros > 0, "Must have at least 1 non zero
entry.")
+ val elemsList = elems.toSparse.indices.toList
+ Vectors.dense(hashFunctions.map(func =>
elemsList.map(func).min.toDouble))
+ }
+
+ @Since("2.1.0")
+ override protected[ml] def keyDistance(x: Vector, y: Vector): Double = {
+ val xSet = x.toSparse.indices.toSet
+ val ySet = y.toSparse.indices.toSet
+ val intersectionSize = xSet.intersect(ySet).size.toDouble
+ val unionSize = xSet.size + ySet.size - intersectionSize
+ assert(unionSize > 0, "The union of two input sets must have at least
1 elements")
+ 1 - intersectionSize / unionSize
+ }
+
+ @Since("2.1.0")
+ override protected[ml] def hashDistance(x: Vector, y: Vector): Double = {
+ // Since it's generated by hashing, it will be a pair of dense vectors.
+ x.toDense.values.zip(y.toDense.values).map(pair => math.abs(pair._1 -
pair._2)).min
+ }
+}
+
+/**
+ * :: Experimental ::
+ * LSH class for Jaccard distance.
+ *
--- End diff --
Could you please link to Wikipedia? That tends to be useful:
[https://en.wikipedia.org/wiki/MinHash]
---
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 infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
