Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/268#discussion_r11271141
--- Diff:
mllib/src/main/scala/org/apache/spark/mllib/rdd/VectorRDDFunctions.scala ---
@@ -0,0 +1,185 @@
+/*
+ * 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.rdd
+
+import breeze.linalg.{Vector => BV, DenseVector => BDV}
+
+import org.apache.spark.mllib.linalg.{Vectors, Vector}
+import org.apache.spark.rdd.RDD
+
+/**
+ * Trait of the summary statistics, including mean, variance, count, max,
min, and non-zero elements
+ * count.
+ */
+trait VectorRDDStatisticalSummary {
+ def mean: Vector
+ def variance: Vector
+ def count: Long
+ def numNonZeros: Vector
+ def max: Vector
+ def min: Vector
+}
+
+/**
+ * Aggregates [[org.apache.spark.mllib.rdd.VectorRDDStatisticalSummary
VectorRDDStatisticalSummary]]
+ * together with add() and merge() function. Online variance solution used
in add() function, while
+ * parallel variance solution used in merge() function. Reference here:
+ * [[http://en.wikipedia.org/wiki/Algorithms_for_calculating_variance
variance-wiki]]. Solution here
+ * ignoring the zero elements when calling add() and merge(), for
decreasing the O(n) algorithm to
+ * O(nnz). Real variance is computed here after we get other statistics,
simply by another parallel
+ * combination process.
+ */
+private class VectorRDDStatisticsAggregator(
+ val currMean: BDV[Double],
+ val currM2n: BDV[Double],
+ var totalCnt: Double,
+ val nnz: BDV[Double],
+ val currMax: BDV[Double],
+ val currMin: BDV[Double])
+ extends VectorRDDStatisticalSummary with Serializable {
+
+ // lazy val is used for computing only once time. Same below.
--- End diff --
remove comment
---
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.
---
