Skip to content

Commit

Permalink
mycoSORT: user friendly updated version
Browse files Browse the repository at this point in the history
  • Loading branch information
Marie-Jean Meurs committed May 29, 2015
1 parent ee817fc commit 75e70b1
Show file tree
Hide file tree
Showing 37 changed files with 9,755 additions and 0 deletions.
8 changes: 8 additions & 0 deletions .gitignore
Original file line number Diff line number Diff line change
@@ -0,0 +1,8 @@
# Project source #
###################
*.project
*.classpath

# Package Files #
#################
*.jar
38 changes: 38 additions & 0 deletions arff/triage0_50_ngrams_size1_stopwords.arff
Original file line number Diff line number Diff line change
@@ -0,0 +1,38 @@
% Weka training file - HIV triage - 2015

@RELATION triage
@ATTRIBUTE docID REAL %PMID of paper
@ATTRIBUTE Ngram0trees REAL %trees
@ATTRIBUTE Ngram1model REAL %model
@ATTRIBUTE Ngram2triage REAL %triage
@ATTRIBUTE Ngram3genes REAL %genes
@ATTRIBUTE Ngram4sampling REAL %sampling
@ATTRIBUTE Ngram5classification REAL %classification
@ATTRIBUTE Ngram6processing REAL %processing
@ATTRIBUTE Ngram7fungal REAL %fungal
@ATTRIBUTE Ngram8enzymes REAL %enzymes
@ATTRIBUTE Ngram9manual REAL %manual
@ATTRIBUTE Ngram10literature REAL %literature
@ATTRIBUTE Ngram11annotation REAL %annotation
@ATTRIBUTE Ngram12mycoclapfungalgenomicsca REAL %mycoclapfungalgenomicsca
@ATTRIBUTE Ngram13machine REAL %machine
@ATTRIBUTE Ngram14first REAL %first
@ATTRIBUTE Ngram15features REAL %features
@ATTRIBUTE Ngram16mycoclap REAL %mycoclap
@ATTRIBUTE Ngram17results REAL %results
@ATTRIBUTE Ngram18abstracttext REAL %abstracttext
@ATTRIBUTE Ngram19task REAL %task
@ATTRIBUTE Ngram20http REAL %http
@ATTRIBUTE Ngram21support REAL %support
@ATTRIBUTE Ngram22learning REAL %learning
@ATTRIBUTE Ngram23database REAL %database
@ATTRIBUTE Ngram24curation REAL %curation
@ATTRIBUTE Ngram25logistic REAL %logistic
@ATTRIBUTE Ngram26applications REAL %applications
@ATTRIBUTE Ngram27articletitle REAL %articletitle
@ATTRIBUTE class {positive, negative}
@DATA

25754864,0,0,0,2,0,0,2,5,3,1,1,2,2,0,1,0,6,1,0,0,2,2,0,4,2,0,2,0,negative
25551575,2,4,3,0,2,2,0,0,0,1,2,0,0,4,1,2,0,1,0,2,0,2,3,0,1,2,0,0,negative

38 changes: 38 additions & 0 deletions arff/triage1_50_ngrams_size1_stopwords.arff
Original file line number Diff line number Diff line change
@@ -0,0 +1,38 @@
% Weka test file - HIV triage - 2015

@RELATION triage
@ATTRIBUTE docID REAL %PMID of paper
@ATTRIBUTE Ngram0trees REAL %trees
@ATTRIBUTE Ngram1model REAL %model
@ATTRIBUTE Ngram2triage REAL %triage
@ATTRIBUTE Ngram3genes REAL %genes
@ATTRIBUTE Ngram4sampling REAL %sampling
@ATTRIBUTE Ngram5classification REAL %classification
@ATTRIBUTE Ngram6processing REAL %processing
@ATTRIBUTE Ngram7fungal REAL %fungal
@ATTRIBUTE Ngram8enzymes REAL %enzymes
@ATTRIBUTE Ngram9manual REAL %manual
@ATTRIBUTE Ngram10literature REAL %literature
@ATTRIBUTE Ngram11annotation REAL %annotation
@ATTRIBUTE Ngram12mycoclapfungalgenomicsca REAL %mycoclapfungalgenomicsca
@ATTRIBUTE Ngram13machine REAL %machine
@ATTRIBUTE Ngram14first REAL %first
@ATTRIBUTE Ngram15features REAL %features
@ATTRIBUTE Ngram16mycoclap REAL %mycoclap
@ATTRIBUTE Ngram17results REAL %results
@ATTRIBUTE Ngram18abstracttext REAL %abstracttext
@ATTRIBUTE Ngram19task REAL %task
@ATTRIBUTE Ngram20http REAL %http
@ATTRIBUTE Ngram21support REAL %support
@ATTRIBUTE Ngram22learning REAL %learning
@ATTRIBUTE Ngram23database REAL %database
@ATTRIBUTE Ngram24curation REAL %curation
@ATTRIBUTE Ngram25logistic REAL %logistic
@ATTRIBUTE Ngram26applications REAL %applications
@ATTRIBUTE Ngram27articletitle REAL %articletitle
@ATTRIBUTE class {positive, negative}
@DATA

25754864,0,0,0,2,0,0,2,5,3,1,1,2,2,0,1,0,6,1,0,0,2,2,0,4,2,0,2,0,negative
25551575,2,4,3,0,2,2,0,0,0,1,2,0,0,4,1,2,0,1,0,2,0,2,3,0,1,2,0,0,negative

153 changes: 153 additions & 0 deletions build.xml
Original file line number Diff line number Diff line change
@@ -0,0 +1,153 @@
<?xml version="1.0" encoding="UTF-8"?>
<project name="mycoSORTtriage.makejar" basedir="." default="makejar">
<path id="build.classpath">
<fileset dir="jars">
<include name="*.jar"/>
</fileset>
</path>
<manifestclasspath property="jar.classpath" jarfile="executables/*.jar">
<classpath refid="build.classpath"/>
</manifestclasspath>
<target name="clean">
<delete dir="bin" />
<mkdir dir="bin" />
</target>

<target name="copy">
<copy todir="bin" includeemptydirs="false">
<fileset dir="." includes="*.cfg, *.txt" />
</copy>
</target>

<target name="compile" depends="clean,copy">
<javac srcdir="src" destdir="bin" debug="true"
includes="analyse/**, arffmatrix/**,
arffvector/**, classifier/**,
configure/**, filter/**, preprocessing/**"
classpathref="build.classpath"
/>
</target>

<target name ="makejar" depends="compile" description="Create jars for the mycoSORT Triage project.">
<jar destfile="executables/CorpusHandler.jar">
<fileset dir="bin/">
<include name="preprocessing/CorpusHandler*.class"/>
<include name="configure/ConfigConstants.class"/>
<include name="config.cfg"/>
</fileset>

<manifest>
<attribute name="Main-Class" value="preprocessing.CorpusHandler"/>
<attribute name="Class-Path" value="${jar.classpath}"/>
</manifest>
</jar>
<jar destfile="executables/SampleCorpus.jar">
<fileset dir="bin/">
<include name="preprocessing/SampleCorpus*.class"/>
<include name="configure/ConfigConstants.class"/>
<include name="config.cfg"/>
</fileset>
<manifest>
<attribute name="Main-Class" value="preprocessing.SampleCorpus"/>
<attribute name="Class-Path" value="${jar.classpath}"/>
</manifest>
</jar>
<jar destfile="executables/NgramExtractor.jar">
<fileset dir="bin/">
<include name="analyse/Extractor.class"/>
<include name="analyse/NgramExtractor.class"/>
<include name="filter/NaiveFilter.class"/>
<include name="configure/ConfigConstants.class"/>
<include name="config.cfg"/>
<include name="stopList.txt"/>
</fileset>
<manifest>
<attribute name="Main-Class" value="analyse.NgramExtractor"/>
<attribute name="Class-Path" value="${jar.classpath}"/>
</manifest>
</jar>
<jar destfile="executables/FeatureExtractor.jar">
<fileset dir="bin/">
<include name="analyse/Extractor.class"/>
<include name="analyse/FeatureExtractor.class"/>
<include name="filter/NaiveFilter.class"/>
<include name="configure/ConfigConstants.class"/>
<include name="config.cfg"/>
<include name="stopList.txt"/>
</fileset>
<manifest>
<attribute name="Main-Class" value="analyse.FeatureExtractor"/>
<attribute name="Class-Path" value="${jar.classpath}"/>
</manifest>
</jar>
<jar destfile="executables/BuildModel.jar">
<fileset dir="bin/">
<include name="arffmatrix/BuildModel.class"/>
<include name="arffvector/CreateVector.class"/>
<include name="analyse/Extractor.class"/>
<include name="configure/ConfigConstants.class"/>
<include name="config.cfg"/>
</fileset>
<manifest>
<attribute name="Main-Class" value="arffmatrix.BuildModel"/>
<attribute name="Class-Path" value="${jar.classpath}"/>
</manifest>
</jar>
<jar destfile="executables/Trainer.jar">
<fileset dir="bin/">
<include name="classifier/Trainer.class"/>
<include name="filter/InformedFilter.class"/>
<include name="configure/ConfigConstants.class"/>
<include name="config.cfg"/>
</fileset>
<manifest>
<attribute name="Main-Class" value="classifier.Trainer"/>
<attribute name="Class-Path" value="${jar.classpath}"/>
</manifest>
</jar>
</target>
<target name="corpus-handler">
<java fork="true" classname="preprocessing/CorpusHandler">
<classpath>
<path location="executables/CorpusHandler.jar"/>
</classpath>
<arg value="${options}"/>
</java>
</target>
<target name="sample-corpus">
<java fork="true" classname="preprocessing/SampleCorpus">
<classpath>
<path location="executables/SampleCorpus.jar"/>
</classpath>
</java>
</target>
<target name="ngram-extractor">
<java fork="true" classname="analyse/NgramExtractor">
<classpath>
<path location="executables/NgramExtractor.jar"/>
</classpath>
</java>
</target>
<target name="annotation-extractor">
<java fork="true" classname="analyse/FeatureExtractor">
<classpath>
<path location="executables/FeatureExtractor.jar"/>
</classpath>
</java>
</target>
<target name="build-model">
<java fork="true" classname="arffmatrix/BuildModel">
<classpath>
<path location="executables/BuildModel.jar"/>
</classpath>
</java>
</target>
<target name="trainer">
<java fork="true" classname="classifier/Trainer">
<classpath>
<path location="executables/Trainer.jar"/>
</classpath>
<arg value="${classifier}"/>
</java>
</target>
</project>
Loading

0 comments on commit 75e70b1

Please sign in to comment.