Github user Yunni commented on a diff in the pull request:
https://github.com/apache/spark/pull/15148#discussion_r82871238
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/feature/RandomProjection.scala ---
@@ -0,0 +1,146 @@
+/*
+ * 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 breeze.linalg.normalize
+
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.ml.linalg.{BLAS, Vector, Vectors, VectorUDT}
+import org.apache.spark.ml.param.{DoubleParam, Params, ParamValidators}
+import org.apache.spark.ml.param.shared.HasSeed
+import org.apache.spark.ml.util.{Identifiable, SchemaUtils}
+import org.apache.spark.sql.types.StructType
+
+/**
+ * :: Experimental ::
+ * Params for [[RandomProjection]].
+ */
+@Since("2.1.0")
+private[ml] trait RandomProjectionParams extends Params {
+
+ /**
+ * The length of each hash bucket, a larger bucket lowers the false
negative rate.
+ *
+ * If input vectors are normalized, 1-10 times of pow(numRecords,
-1/inputDim) would be a
+ * reasonable value
+ * @group param
+ */
+ @Since("2.1.0")
+ val bucketLength: DoubleParam = new DoubleParam(this, "bucketLength",
+ "the length of each hash bucket, a larger bucket lowers the false
negative rate.",
+ ParamValidators.gt(0))
+
+ /** @group getParam */
+ @Since("2.1.0")
+ final def getBucketLength: Double = $(bucketLength)
+}
+
+/**
+ * :: Experimental ::
+ * Model produced by [[RandomProjection]]
+ * @param randUnitVectors An array of random unit vectors. Each vector
represents a hash function.
+ */
+@Experimental
+@Since("2.1.0")
+class RandomProjectionModel private[ml] (
+ override val uid: String,
+ val randUnitVectors: Array[Vector])
--- End diff --
I wanted to use `Matrix`. But it turns out that `Array[Vector]` makes
normalizing each vector, and taking floor of the values much cleaner. Is there
any reason we should use `Matrix` here?
---
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
