Github user Yunni commented on a diff in the pull request:
https://github.com/apache/spark/pull/15148#discussion_r85444781
--- Diff: mllib/src/main/scala/org/apache/spark/ml/feature/MinHash.scala ---
@@ -0,0 +1,192 @@
+/*
+ * 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.hadoop.fs.Path
+
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.ml.linalg.{Vector, Vectors, VectorUDT}
+import org.apache.spark.ml.param.ParamMap
+import org.apache.spark.ml.param.shared.HasSeed
+import org.apache.spark.ml.util._
+import org.apache.spark.sql.types.StructType
+
+/**
+ * :: Experimental ::
+ * Model produced by [[MinHash]], where multiple hash functions are
stored. Each hash function is
+ * a perfect hash function:
+ * g_i(x) = (x * k_i mod prime) mod numEntries
+ * where c_i is the i-th coefficient
+ *
+ * Reference:
+ * https://en.wikipedia.org/wiki/Perfect_hash_function
+ *
+ * @param numEntries The number of entries of the hash functions.
+ * @param randCoefficients An array of random coefficients, each used by
one hash function.
+ */
+@Experimental
+@Since("2.1.0")
+class MinHashModel private[ml] (
+ override val uid: String,
+ @Since("2.1.0") val numEntries: Int,
+ @Since("2.1.0") val randCoefficients: Array[Int])
+ extends LSHModel[MinHashModel] {
+
+ @Since("2.1.0")
+ override protected[ml] val hashFunction: Vector => Vector = {
+ elems: Vector =>
+ require(elems.numNonzeros > 0, "Must have at least 1 non zero
entry.")
+ val elemsList = elems.toSparse.indices.toList
+ val hashValues = randCoefficients.map({ randCoefficient: Int =>
+ elemsList.map({elem: Int =>
+ (1 + elem) * randCoefficient.toLong % MinHash.prime %
numEntries
+ }).min.toDouble
+ })
+ Vectors.dense(hashValues)
+ }
+
+ @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
+ }
+
+ @Since("2.1.0")
+ override def copy(extra: ParamMap): this.type = defaultCopy(extra)
+
+ @Since("2.1.0")
+ override def write: MLWriter = new MinHashModel.MinHashModelWriter(this)
+}
+
+/**
+ * :: Experimental ::
+ * LSH class for Jaccard distance.
+ *
+ * The input can be dense or sparse vectors, but it is more efficient if
it is sparse. For example,
+ * `Vectors.sparse(10, Array[(2, 1.0), (3, 1.0), (5, 1.0)])`
+ * means there are 10 elements in the space. This set contains elem 2,
elem 3 and elem 5.
+ * Also, any input vector must have at least 1 non-zero indices, and all
non-zero values are treated
+ * as binary "1" values.
+ *
+ * References:
+ * https://en.wikipedia.org/wiki/MinHash
--- End diff --
Fixed in 3 places.
---
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]
