6.0 release
Project: http://git-wip-us.apache.org/repos/asf/incubator-predictionio-template-text-classifier/repo Commit: http://git-wip-us.apache.org/repos/asf/incubator-predictionio-template-text-classifier/commit/b24325a3 Tree: http://git-wip-us.apache.org/repos/asf/incubator-predictionio-template-text-classifier/tree/b24325a3 Diff: http://git-wip-us.apache.org/repos/asf/incubator-predictionio-template-text-classifier/diff/b24325a3 Branch: refs/heads/master Commit: b24325a39b396d73c4b99aa300ec49848df4d33e Parents: 6b89e6e Author: Donald Szeto <[email protected]> Authored: Thu May 4 11:24:55 2017 -0700 Committer: Donald Szeto <[email protected]> Committed: Thu May 4 11:24:55 2017 -0700 ---------------------------------------------------------------------- README.md | 11 ++++++++++- build.sbt | 9 +++------ engine.json | 2 +- src/main/scala/DataSource.scala | 2 +- src/main/scala/Engine.scala | 2 +- src/main/scala/Evaluation.scala | 2 +- src/main/scala/LRAlgorithm.scala | 2 +- src/main/scala/NBAlgorithm.scala | 2 +- src/main/scala/Preparator.scala | 5 ++--- src/main/scala/Serving.scala | 2 +- 10 files changed, 22 insertions(+), 17 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/incubator-predictionio-template-text-classifier/blob/b24325a3/README.md ---------------------------------------------------------------------- diff --git a/README.md b/README.md index fb40df2..7acee7a 100644 --- a/README.md +++ b/README.md @@ -1,9 +1,18 @@ # Text Classification Engine -Look at the following [tutorial](https://docs.prediction.io/demo/textclassification/) for a Quick Start guide and implementation details. +Look at the following +[tutorial](http://predictionio.incubator.apache.org/demo/textclassification/) +for a Quick Start guide and implementation details. # Release Information +## Version 6.0 + +- Use Apache Lucene as tokenizer +- Add stopwords filter +- Rename Scala package name +- Update SBT version + ## Version 5.0 **First Apache Version** - Major changes to namespace to reflect donation to the Apache Software Foundation. http://git-wip-us.apache.org/repos/asf/incubator-predictionio-template-text-classifier/blob/b24325a3/build.sbt ---------------------------------------------------------------------- diff --git a/build.sbt b/build.sbt index 594c0de..782ca74 100644 --- a/build.sbt +++ b/build.sbt @@ -1,10 +1,7 @@ -name := "org.template.textclassification" - -organization := "org.apache.predictionio" - -scalaVersion := "2.10.5" +name := "org.example.textclassification" libraryDependencies ++= Seq( "org.apache.predictionio" %% "apache-predictionio-core" % "0.11.0-incubating" % "provided", "org.apache.spark" %% "spark-core" % "1.4.1" % "provided", - "org.apache.spark" %% "spark-mllib" % "1.4.1" % "provided") + "org.apache.spark" %% "spark-mllib" % "1.4.1" % "provided", + "org.apache.lucene" % "lucene-core" % "6.5.1") http://git-wip-us.apache.org/repos/asf/incubator-predictionio-template-text-classifier/blob/b24325a3/engine.json ---------------------------------------------------------------------- diff --git a/engine.json b/engine.json index a6158ba..6192129 100644 --- a/engine.json +++ b/engine.json @@ -1,7 +1,7 @@ { "id": "default", "description": "Default settings", - "engineFactory": "org.template.textclassification.TextClassificationEngine", + "engineFactory": "org.example.textclassification.TextClassificationEngine", "datasource": { "params": { "appName": "MyTextApp" http://git-wip-us.apache.org/repos/asf/incubator-predictionio-template-text-classifier/blob/b24325a3/src/main/scala/DataSource.scala ---------------------------------------------------------------------- diff --git a/src/main/scala/DataSource.scala b/src/main/scala/DataSource.scala index d8bbf01..80b6344 100644 --- a/src/main/scala/DataSource.scala +++ b/src/main/scala/DataSource.scala @@ -1,4 +1,4 @@ -package org.template.textclassification +package org.example.textclassification import org.apache.predictionio.controller.PDataSource import org.apache.predictionio.controller.EmptyEvaluationInfo http://git-wip-us.apache.org/repos/asf/incubator-predictionio-template-text-classifier/blob/b24325a3/src/main/scala/Engine.scala ---------------------------------------------------------------------- diff --git a/src/main/scala/Engine.scala b/src/main/scala/Engine.scala index dece797..16d47ac 100644 --- a/src/main/scala/Engine.scala +++ b/src/main/scala/Engine.scala @@ -1,4 +1,4 @@ -package org.template.textclassification +package org.example.textclassification import org.apache.predictionio.controller.IEngineFactory import org.apache.predictionio.controller.Engine http://git-wip-us.apache.org/repos/asf/incubator-predictionio-template-text-classifier/blob/b24325a3/src/main/scala/Evaluation.scala ---------------------------------------------------------------------- diff --git a/src/main/scala/Evaluation.scala b/src/main/scala/Evaluation.scala index 9850ae8..979d976 100644 --- a/src/main/scala/Evaluation.scala +++ b/src/main/scala/Evaluation.scala @@ -1,4 +1,4 @@ -package org.template.textclassification +package org.example.textclassification import org.apache.predictionio.controller.AverageMetric import org.apache.predictionio.controller.Evaluation http://git-wip-us.apache.org/repos/asf/incubator-predictionio-template-text-classifier/blob/b24325a3/src/main/scala/LRAlgorithm.scala ---------------------------------------------------------------------- diff --git a/src/main/scala/LRAlgorithm.scala b/src/main/scala/LRAlgorithm.scala index 3bc1373..e056cf9 100644 --- a/src/main/scala/LRAlgorithm.scala +++ b/src/main/scala/LRAlgorithm.scala @@ -1,4 +1,4 @@ -package org.template.textclassification +package org.example.textclassification import org.apache.predictionio.controller.P2LAlgorithm import org.apache.predictionio.controller.Params http://git-wip-us.apache.org/repos/asf/incubator-predictionio-template-text-classifier/blob/b24325a3/src/main/scala/NBAlgorithm.scala ---------------------------------------------------------------------- diff --git a/src/main/scala/NBAlgorithm.scala b/src/main/scala/NBAlgorithm.scala index 1cd01fc..9a408c5 100644 --- a/src/main/scala/NBAlgorithm.scala +++ b/src/main/scala/NBAlgorithm.scala @@ -1,4 +1,4 @@ -package org.template.textclassification +package org.example.textclassification import org.apache.predictionio.controller.P2LAlgorithm import org.apache.predictionio.controller.Params http://git-wip-us.apache.org/repos/asf/incubator-predictionio-template-text-classifier/blob/b24325a3/src/main/scala/Preparator.scala ---------------------------------------------------------------------- diff --git a/src/main/scala/Preparator.scala b/src/main/scala/Preparator.scala index 8a5cb5c..1f4d51d 100644 --- a/src/main/scala/Preparator.scala +++ b/src/main/scala/Preparator.scala @@ -1,4 +1,4 @@ -package org.template.textclassification +package org.example.textclassification import org.apache.predictionio.controller.PPreparator import org.apache.predictionio.controller.Params @@ -13,7 +13,6 @@ import org.apache.spark.rdd.RDD import org.apache.lucene.analysis.standard.StandardAnalyzer import org.apache.lucene.analysis.tokenattributes.CharTermAttribute -import org.apache.lucene.util.Version import java.io.StringReader @@ -74,7 +73,7 @@ class TFHasher( /** Use Lucene StandardAnalyzer to tokenize text **/ def tokenize(content: String): Seq[String] = { val tReader = new StringReader(content) - val analyzer = new StandardAnalyzer(Version.LATEST) + val analyzer = new StandardAnalyzer() val tStream = analyzer.tokenStream("contents", tReader) val term = tStream.addAttribute(classOf[CharTermAttribute]) tStream.reset() http://git-wip-us.apache.org/repos/asf/incubator-predictionio-template-text-classifier/blob/b24325a3/src/main/scala/Serving.scala ---------------------------------------------------------------------- diff --git a/src/main/scala/Serving.scala b/src/main/scala/Serving.scala index 58c6330..2f69b73 100644 --- a/src/main/scala/Serving.scala +++ b/src/main/scala/Serving.scala @@ -1,4 +1,4 @@ -package org.template.textclassification +package org.example.textclassification import org.apache.predictionio.controller.LServing
