Github user Yunni commented on a diff in the pull request:
https://github.com/apache/spark/pull/15148#discussion_r81695220
--- Diff: mllib/src/main/scala/org/apache/spark/ml/feature/LSH.scala ---
@@ -0,0 +1,338 @@
+/*
+ * 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.ml.{Estimator, Model}
+import org.apache.spark.ml.linalg.{Vector, VectorUDT}
+import org.apache.spark.ml.param.{IntParam, ParamMap, ParamValidators}
+import org.apache.spark.ml.param.shared.{HasInputCol, HasOutputCol}
+import org.apache.spark.ml.util.SchemaUtils
+import org.apache.spark.sql._
+import org.apache.spark.sql.expressions.UserDefinedFunction
+import org.apache.spark.sql.functions._
+import org.apache.spark.sql.types._
+
+/**
+ * Params for [[LSH]].
+ */
+private[ml] trait LSHParams extends HasInputCol with HasOutputCol {
+ /**
+ * Param for the dimension of LSH OR-amplification.
+ *
+ * In this implementation, we use LSH OR-amplification to reduce the
false negative rate. This
+ * param is the dimension of the amplification. The higher the dimension
is, the lower the false
+ * negative rate.
+ * @group param
+ */
+ final val outputDim: IntParam = new IntParam(this, "outputDim", "output
dimension",
+ ParamValidators.gt(0))
+
+ /** @group getParam */
+ final def getOutputDim: Int = $(outputDim)
+
+ setDefault(outputDim -> 1, outputCol -> "lsh_output")
+
+ /**
+ * Transform the Schema for LSH
+ * @param schema The schema of the input dataset without outputCol
+ * @return A derived schema with outputCol added
+ */
+ protected[this] final def validateAndTransformSchema(schema:
StructType): StructType = {
+ SchemaUtils.appendColumn(schema, $(outputCol), new VectorUDT)
+ }
+}
+
+/**
+ * Model produced by [[LSH]].
+ */
+abstract class LSHModel[T <: LSHModel[T]] private[ml]
+ extends Model[T] with LSHParams {
+ override def copy(extra: ParamMap): T = defaultCopy(extra)
+ /**
+ * :: DeveloperApi ::
+ *
+ * The hash function of LSH, mapping a predefined KeyType to a Vector
+ * @return The mapping of LSH function.
+ */
+ protected[this] val hashFunction: Vector => Vector
+
+ /**
+ * :: DeveloperApi ::
+ *
+ * Calculate the distance between two different keys using the distance
metric corresponding
+ * to the hashFunction
+ * @param x One of the point in the metric space
+ * @param y Another the point in the metric space
+ * @return The distance between x and y in double
+ */
+ protected[ml] def keyDistance(x: Vector, y: Vector): Double
+
+ /**
+ * :: DeveloperApi ::
+ *
+ * Calculate the distance between two different hash Vectors. By
default, the distance is the
+ * minimum distance of two hash values in any dimension.
+ *
+ * @param x One of the hash vector
+ * @param y Another hash vector
+ * @return The distance between hash vectors x and y in double
+ */
+ protected[ml] def hashDistance(x: Vector, y: Vector): Double
+
+ /**
+ * Transforms the input dataset.
+ */
+ override def transform(dataset: Dataset[_]): DataFrame = {
+ transformSchema(dataset.schema, logging = true)
+ val transformUDF = udf(hashFunction, new VectorUDT)
+ dataset.withColumn($(outputCol), transformUDF(dataset($(inputCol))))
+ }
+
+ /**
+ * :: DeveloperApi ::
+ *
+ * Check transform validity and derive the output schema from the input
schema.
+ *
+ * Typical implementation should first conduct verification on schema
change and parameter
+ * validity, including complex parameter interaction checks.
+ */
+ override def transformSchema(schema: StructType): StructType = {
+ validateAndTransformSchema(schema)
+ }
+
+ /**
+ * Given a large dataset and an item, approximately find at most k items
which have the closest
+ * distance to the item.
+ *
+ * This method has implemented two way of fetching k nearest neighbors:
+ * Single Probing: Fast, return at most k elements (Probing only one
buckets)
+ * Multiple Probing: Slow, return exact k elements (Probing multiple
buckets close to the key)
+ *
+ * @param dataset the dataset to look for the key
+ * @param key The key to hash for the item
+ * @param k The maximum number of items closest to the key
+ * @param singleProbing True for using Single Probing; false for
multiple probing
+ * @param distCol The column to store the distance between pairs
+ * @return A dataset containing at most k items closest to the key. A
distCol is added to show
+ * the distance between each record and the key.
+ */
+ def approxNearestNeighbors(
+ dataset: Dataset[_],
+ key: Vector,
+ k: Int,
+ singleProbing: Boolean,
+ distCol: String): Dataset[_] = {
+ assert(k > 0, "The number of nearest neighbors cannot be less than 1")
+ // Get Hash Value of the key v
--- End diff --
Removed.
---
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
