Added files for homework 3.

bin/anlp

@@ -0,0 +1,54 @@
+#!/bin/bash
+
+EXIT_CODE=0
+
+if [ -z $ANLP_DIR ] 
+then
+   ANLP_DIR=`dirname $0`/../
+fi
+
+if [ -z $JAVA_MEM_FLAG ] 
+then
+    JAVA_MEM_FLAG=-Xmx4g
+fi
+
+#JARS="`find $HOME/.ivy2/ -name '*.jar' -print | tr '\n' ':'`"
+MANAGED_JARS="`find $ANLP_DIR/lib_managed -name '*.jar' -print | tr '\n' ':'`"
+UNMANAGED_JARS="`find $ANLP_DIR/lib -name '*.jar' -print | tr '\n' ':'`"
+
+SCALA_LIB="$HOME/.sbt/boot/scala-2.10.0/lib/scala-library.jar"
+
+CP="$ANLP_DIR/target/classes:$SCALA_LIB:$ANLP_DIR/src/main/resources:$MANAGED_JARS:$UNMANAGED_JARS"
+
+JAVA="$JAVA_HOME/bin/java"
+JAVA_COMMAND="$JAVA -classpath $CP -Danlp.dir=$ANLP_DIR"
+
+CMD=$1
+shift
+
+help()
+{
+cat <<EOF
+anlp 0.2 commands: 
+
+  run           run the main method of a given class
+  app           run the main method of a class in appliednlp.app
+
+Include --help with any option for more information
+EOF
+}
+
+CLASS=
+
+case $CMD in
+    run) CLASS=$1; shift;;
+    app) CLASS=appliednlp.app.$1; shift;;
+    help) help; exit 1;;
+    *) echo "Unrecognized command: $CMD"; help; exit 1;;
+esac
+
+$JAVA_COMMAND $CLASS ${1+"$@"} 
+(( EXIT_CODE += $? ))
+
+exit $EXIT_CODE
+

build.sbt

@@ -1,9 +1,22 @@
 name := "applied-nlp"
 
-version := "0.1-SNAPSHOT"
+version := "0.2-SNAPSHOT"
 
 organization := "edu.utexas"
 
 scalaVersion := "2.10.0"
 
+retrieveManaged := true
+
 crossPaths := false
+
+resolvers ++= Seq(
+   "Sonatype Snapshots" at "https://oss.sonatype.org/content/repositories/releases/"
+)
+
+libraryDependencies ++= Seq(
+  "org.scalanlp" % "nak" % "1.1.0",
+  "org.scalanlp" % "chalk" % "1.1.1",
+  "org.rogach" %% "scallop" % "0.8.0",
+  "gov.nist.math" % "jama" % "1.0.2"
+)

data/cluster/countries/README.txt

@@ -0,0 +1,10 @@
+Birth and Death Rates
+
+The data set contains
+
+    birth rate (in percent),
+    death rate (in percent), 
+
+of 70 countries. 
+
+Data obtained from: http://www.uni-koeln.de/themen/statistik/data/cluster/

data/cluster/countries/birth.dat

@@ -0,0 +1,70 @@
+ALGERIA        36.4   14.6
+CONGO          37.3    8.0               
+EGYPT          42.1   15.3               
+GHANA          55.8   25.6               
+IVORY COAST    56.1   33.1               
+MALAGASY       41.8   15.8               
+MOROCCO        46.1   18.7               
+TUNISIA        41.7   10.1               
+CAMBODIA       41.4   19.7               
+CEYLON         35.8    8.5               
+CHINA          34.0   11.0               
+TAIWAN         36.3    6.1               
+HONG KONG      32.1    5.5               
+INDIA          20.9    8.8               
+INDONESIA      27.7   10.2               
+IRAQ           20.5    3.9               
+FRANCE         25.0    6.2               
+JAPAN          17.3    7.0               
+JORDAN         46.3    6.4               
+KOREA          14.8    5.7               
+MALAYSIA       33.5    6.4               
+MONGOLIA       39.2   11.2               
+PHILLIPINES    28.4    7.1               
+SYRIA          26.2    4.3               
+THAILAND       34.8    7.9               
+VIETNAM        23.4    5.1               
+CANADA         24.8    7.8               
+COSTA RICA     49.9    8.5               
+DOMINICAN R    33.0    8.4               
+GUATEMALA      47.7   17.3               
+HONDURAS       46.6    9.7               
+MEXICO         45.1   10.5               
+NICARAGUA      42.9    7.1               
+PANAMA         40.1    8.0               
+UNITED STATES  21.7    9.6               
+ARGENTINA      21.8    8.1
+BOLIVIA        17.4    5.8
+BRAZIL         45.0   13.5
+CHILE          33.6   11.8
+COLOMBIA       44.0   11.7
+ECUADOR        44.2   13.5
+PERU           27.7    8.2
+URUGUAY        22.5    7.8
+VENEZUELA      42.8    6.7
+AUSTRIA        18.8   12.8
+BELGIUM        17.1   12.7
+BRITAIN        18.2   12.2
+BULGARIA       16.4    8.2
+CZECHOSLOVAKIA 16.9    9.5
+DENMARK        17.6   19.8
+FINLAND        18.1    9.2
+FRANCE         18.2   11.7
+E.GERMANY      17.5   13.7
+W.GERMANY      18.5   11.4
+GREECE         17.4    7.8
+HUNGARY        13.1    9.9
+IRELAND        22.3   11.9
+ITALY          19.0   10.2
+NETHERLANDS    20.9    8.0
+NORWAY         17.5   10.0
+POLAND         19.0    7.5
+PORTUGAL       23.5   10.8
+ROMANIA        15.7    8.3
+SPAIN          21.5    9.1
+SWEDEN         14.8   10.1
+SWITZERLAND    18.9    9.6
+U.S.S.R.       21.2    7.2
+YUGOSLAVIA     21.4    8.9
+AUSTRALIA      21.6    8.7
+NEW ZEALAND    25.5    8.8