[
https://issues.apache.org/jira/browse/MAHOUT-1541?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14037704#comment-14037704
]
ASF GitHub Bot commented on MAHOUT-1541:
----------------------------------------
Github user dlyubimov commented on a diff in the pull request:
https://github.com/apache/mahout/pull/22#discussion_r13987451
--- Diff:
spark/src/main/scala/org/apache/mahout/cf/examples/Recommendations.scala ---
@@ -0,0 +1,172 @@
+/*
+ * 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.mahout.cf.examples
+
+import scala.io.Source
+import org.apache.mahout.math._
+import scalabindings._
+import RLikeOps._
+import drm._
+import RLikeDrmOps._
+import org.apache.mahout.sparkbindings._
+
+import org.apache.mahout.cf.CooccurrenceAnalysis._
+import scala.collection.JavaConversions._
+
+/**
+ * The Epinions dataset contains ratings from users to items and a
trust-network between the users.
+ * We use co-occurrence analysis to compute "users who like these items,
also like that items" and
+ * "users who trust these users, like that items"
+ *
+ * Download and unpack the dataset files from:
+ *
+ *
http://www.trustlet.org/datasets/downloaded_epinions/ratings_data.txt.bz2
+ * http://www.trustlet.org/datasets/downloaded_epinions/trust_data.txt.bz2
+ **/
+object RunCrossCooccurrenceAnalysisOnEpinions {
+
+ def main(args: Array[String]): Unit = {
+
+ if (args.length == 0) {
+ println("Usage: RunCooccurrenceAnalysisOnMovielens1M
<path-to-dataset-folder>")
+ println("Download the dataset from
http://www.trustlet.org/datasets/downloaded_epinions/ratings_data.txt.bz2 and")
+
println("http://www.trustlet.org/datasets/downloaded_epinions/trust_data.txt.bz2";)
+ sys.exit(-1)
+ }
+
+ val datasetDir = args(0)
+
+ val epinionsRatings = new SparseMatrix(49290, 139738)
+
+ var firstLineSkipped = false
+ for (line <- Source.fromFile(datasetDir +
"/ratings_data.txt").getLines()) {
+ if (line.contains(' ') && firstLineSkipped) {
+ val tokens = line.split(' ')
+ val userID = tokens(0).toInt - 1
+ val itemID = tokens(1).toInt - 1
+ val rating = tokens(2).toDouble
+ epinionsRatings(userID, itemID) = rating
+ }
+ firstLineSkipped = true
+ }
+
+ val epinionsTrustNetwork = new SparseMatrix(49290, 49290)
+ firstLineSkipped = false
+ for (line <- Source.fromFile(datasetDir +
"/trust_data.txt").getLines()) {
+ if (line.contains(' ') && firstLineSkipped) {
+ val tokens = line.trim.split(' ')
+ val userID = tokens(0).toInt - 1
+ val trustedUserId = tokens(1).toInt - 1
+ epinionsTrustNetwork(userID, trustedUserId) = 1
+ }
+ firstLineSkipped = true
+ }
+
+ System.setProperty("spark.kryo.referenceTracking", "false")
+ System.setProperty("spark.kryoserializer.buffer.mb", "100")
+/* to run on local, can provide number of core by changing to local[4] */
+ implicit val distributedContext = mahoutSparkContext(masterUrl =
"local", appName = "MahoutLocalContext",
+ customJars = Traversable.empty[String])
--- End diff --
again, no need to specify customJars if no jars are added.
> Create CLI Driver for Spark Cooccurrence Analysis
> -------------------------------------------------
>
> Key: MAHOUT-1541
> URL: https://issues.apache.org/jira/browse/MAHOUT-1541
> Project: Mahout
> Issue Type: Bug
> Components: CLI
> Reporter: Pat Ferrel
> Assignee: Pat Ferrel
>
> Create a CLI driver to import data in a flexible manner, create an
> IndexedDataset with BiMap ID translation dictionaries, call the Spark
> CooccurrenceAnalysis with the appropriate params, then write output with
> external IDs optionally reattached.
> Ultimately it should be able to read input as the legacy mr does but will
> support reading externally defined IDs and flexible formats. Output will be
> of the legacy format or text files of the user's specification with
> reattached Item IDs.
> Support for legacy formats is a question, users can always use the legacy
> code if they want this. Internal to the IndexedDataset is a Spark DRM so
> pipelining can be accomplished without any writing to an actual file so the
> legacy sequence file output may not be needed.
> Opinions?
--
This message was sent by Atlassian JIRA
(v6.2#6252)
