Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/4304#discussion_r23957801
--- Diff: mllib/src/main/scala/org/apache/spark/mllib/feature/PCA.scala ---
@@ -0,0 +1,79 @@
+/*
+ * 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.mllib.feature
+
+import org.apache.spark.annotation.Experimental
+import org.apache.spark.api.java.JavaRDD
+import org.apache.spark.mllib.linalg._
+import org.apache.spark.mllib.linalg.distributed.RowMatrix
+import org.apache.spark.rdd.RDD
+
+/**
+ * :: Experimental ::
+ * Transformer a vector use PCA
+ */
+
+object PCA {
+ /**
+ * Compute a Principal Components from RDD[Vector]
+ */
+ def create(k: Int, sources: RDD[Vector]): PCAModel = {
+ require(k > 1 && k <= sources.first().size)
+
+ val mat = new RowMatrix(sources)
+ val pc = mat.computePrincipalComponents(k) match {
+ case pc: DenseMatrix =>
+ pc
+ /*
+ * Convert Sparse Vector to Dense Vector.
+ *
+ * Following code is for possible compatibility.
+ * RowMatrix.computePrincipalComponents is always returned a Dense
Vector
+ */
+ case v =>
+ Matrices.dense(v.numRows, v.numCols, v.toArray)
+ }
+ new PCAModel(k, pc.asInstanceOf[DenseMatrix])
+ }
+
+ /**
+ * Compute a Principal Components from JavaRDD[Vector]
+ */
+ def create(k: Int, sources: JavaRDD[Vector]): PCAModel =
+ create(k, sources.rdd)
+}
+
+/**
+ * This class is wrapper of RowMatrix.computePrincipalComponents and
Matrix.multiply
+ *
+ * @param k count of principal components.
+ * @param pc a principal components Matrix
+ */
+@Experimental
+class PCAModel private[mllib](val k: Int, val pc: DenseMatrix) extends
VectorTransformer {
+ /**
+ * Transform a vector by computed Principal Components.
+ *
+ * @param vector vector to be transformed.
+ * @return transformed vector.
+ */
+ override def transform(vector: Vector): Vector = {
+ val mat = Matrices.dense(1, vector.size, vector.toArray).multiply(pc)
--- End diff --
`BLAS.gemv` should work. We might miss the implementation of dense matrix *
sparse vector, but it should be easy to add.
---
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]
