macrobase-lib 0.1 (stanford-futuredata#192)

* Initial DataFrame code

* Change ItemsetEncoder to encode columns

* Add get column method for dataframes

* Adding select and filter to dataframe

* Initial test based on seen usage

* Initial refactor of BatchSummarize, FPGrowth, FPGrowthEmerging etc.

* dataframe CSV loader

* fixing dependencies

* dataframe csv loader

* updating supervisedtest

* Move ItemsetEncoder to summarizer

* percentile classifier and unsupervised csv test

* support for building source and javadoc jars

`mvn verify` will now build two associated jars:
one for sources and one for javadocs, which we can upload
to maven to make it easier to use the library

* Addressed some of Peter's comments
- renamed core -> runtime
- changed groupId in pom.xml
- Rename EncodedItemsetResult->ItemsetResult, ItemsetResult->AttributeSet, ItemsetEncoder->AttributeEncoder
- Throw MacrobaseException instead of RuntimeException
- Renamed all filter methods in DataFrame to filter()
- Removed Apriori and dead code
CSVParser and DataFrame not finished

* Minor tweaks in filter API

* Removing unstable csv parser

* Add getRows() in DataFrame; enable attr combinations by default

* improving test coverage

* changing loadrows to a constructor

Trying to make dataframes as immutable as possible

* core=>runtime renaming clean up

* Rename modules

* More javadoc comments

* pgp plugin

* Changed exception in DataFrame

* test coverage, bugfix for summarizer

* Add deploy plugins to lib module
You can upload the SNAPSHOT module right now by 'mvn clean deploy'!

* independent maven package

* adding full package namespace

.travis.yml

@@ -1,5 +1,6 @@
 language: java
 jdk: oraclejdk8
+install: mvn install -DskipTests=true -Dgpg.skip=true -Dmaven.javadoc.skip=true -B -V
 notifications:
   slack: stanford-futuredata:qmO6Keu8ifOyXHsmSQ97CeLH
 after_success:

assembly/pom.xml

@@ -2,7 +2,7 @@
     <modelVersion>4.0.0</modelVersion>
 
     <parent>
-        <groupId>macrobase</groupId>
+        <groupId>edu.stanford.futuredata</groupId>
         <artifactId>macrobase</artifactId>
         <version>0.1-SNAPSHOT</version>
     </parent>
@@ -12,17 +12,17 @@
 
     <dependencies>
         <dependency>
-            <groupId>macrobase</groupId>
-            <artifactId>macrobase-core</artifactId>
+            <groupId>edu.stanford.futuredata</groupId>
+            <artifactId>macrobase-legacy</artifactId>
             <version>0.1-SNAPSHOT</version>
         </dependency>
         <dependency>
-            <groupId>macrobase</groupId>
+            <groupId>edu.stanford.futuredata</groupId>
             <artifactId>macrobase-frontend</artifactId>
             <version>0.1-SNAPSHOT</version>
         </dependency>
         <dependency>
-            <groupId>macrobase</groupId>
+            <groupId>edu.stanford.futuredata</groupId>
             <artifactId>macrobase-contrib</artifactId>
             <version>0.1-SNAPSHOT</version>
         </dependency>

bin/batch.sh

@@ -2,4 +2,4 @@
 conf_file=${1:-"conf/batch.yaml"}
 
 set -x
-java ${JAVA_OPTS} -cp "core/target/classes:frontend/target/classes:frontend/src/main/resources/:contrib/target/classes:assembly/target/*:$CLASSPATH" macrobase.MacroBase pipeline $conf_file
+java ${JAVA_OPTS} -cp "legacy/target/classes:frontend/target/classes:frontend/src/main/resources/:contrib/target/classes:assembly/target/*:$CLASSPATH" macrobase.MacroBase pipeline $conf_file

bin/server.sh

@@ -3,4 +3,4 @@ conf_file=${1:-"conf/macrobase.yaml"}
 
 set -x
 
-java ${JAVA_OPTS} -cp "core/target/classes:frontend/target/classes:frontend/src/main/resources/:contrib/target/classes:assembly/target/*:$CLASSPATH" macrobase.runtime.MacroBaseServer server $conf_file
+java ${JAVA_OPTS} -cp "legacy/target/classes:frontend/target/classes:frontend/src/main/resources/:contrib/target/classes:assembly/target/*:$CLASSPATH" macrobase.runtime.MacroBaseServer server $conf_file

bin/streaming.sh

@@ -2,4 +2,4 @@
 conf_file=${1:-"conf/streaming.yaml"}
 
 set -x
-java ${JAVA_OPTS} -cp "core/target/classes:frontend/target/classes:frontend/src/main/resources/:contrib/target/classes:assembly/target/*:$CLASSPATH" macrobase.MacroBase pipeline $conf_file
+java ${JAVA_OPTS} -cp "legacy/target/classes:frontend/target/classes:frontend/src/main/resources/:contrib/target/classes:assembly/target/*:$CLASSPATH" macrobase.MacroBase pipeline $conf_file

contrib/pom.xml

@@ -1,22 +1,22 @@
 <project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
   xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd">
   <modelVersion>4.0.0</modelVersion>
-  <groupId>macrobase</groupId>
+  <groupId>edu.stanford.futuredata</groupId>
   <artifactId>macrobase-contrib</artifactId>
   <packaging>jar</packaging>
   <version>0.1-SNAPSHOT</version>
   <name>macrobase-contrib</name>
   <url>http://maven.apache.org</url>
     <parent>
-        <groupId>macrobase</groupId>
+        <groupId>edu.stanford.futuredata</groupId>
         <artifactId>macrobase</artifactId>
         <version>0.1-SNAPSHOT</version>
     </parent>
 
     <dependencies>
     <dependency>
-        <groupId>macrobase</groupId>
-        <artifactId>macrobase-core</artifactId>
+        <groupId>edu.stanford.futuredata</groupId>
+        <artifactId>macrobase-legacy</artifactId>
         <version>0.1-SNAPSHOT</version>
     </dependency>
     <dependency>

frontend/pom.xml

@@ -1,22 +1,22 @@
 <project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
   xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd">
   <modelVersion>4.0.0</modelVersion>
-  <groupId>macrobase</groupId>
+  <groupId>edu.stanford.futuredata</groupId>
   <artifactId>macrobase-frontend</artifactId>
   <packaging>jar</packaging>
   <version>0.1-SNAPSHOT</version>
   <name>macrobase-frontend</name>
   <url>http://maven.apache.org</url>
     <parent>
-        <groupId>macrobase</groupId>
+        <groupId>edu.stanford.futuredata</groupId>
         <artifactId>macrobase</artifactId>
         <version>0.1-SNAPSHOT</version>
     </parent>
 
     <dependencies>
     <dependency>
-        <groupId>macrobase</groupId>
-        <artifactId>macrobase-core</artifactId>
+        <groupId>edu.stanford.futuredata</groupId>
+        <artifactId>macrobase-legacy</artifactId>
         <version>0.1-SNAPSHOT</version>
     </dependency>
     </dependencies>

core/pom.xml → legacy/pom.xml

@@ -1,14 +1,14 @@
 <project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
   xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd">
   <modelVersion>4.0.0</modelVersion>
-  <groupId>macrobase</groupId>
-  <artifactId>macrobase-core</artifactId>
+  <groupId>edu.stanford.futuredata</groupId>
+  <artifactId>macrobase-legacy</artifactId>
   <packaging>jar</packaging>
   <version>0.1-SNAPSHOT</version>
-  <name>macrobase-core</name>
+  <name>macrobase-legacy</name>
   <url>http://maven.apache.org</url>
     <parent>
-        <groupId>macrobase</groupId>
+        <groupId>edu.stanford.futuredata</groupId>
         <artifactId>macrobase</artifactId>
         <version>0.1-SNAPSHOT</version>
     </parent>
@@ -61,6 +61,26 @@
             <version>1.1.1</version>
             <scope>test</scope>
         </dependency>
+        <dependency>
+            <groupId>io.dropwizard</groupId>
+            <artifactId>dropwizard-core</artifactId>
+            <version>${dropwizard.version}</version>
+        </dependency>
+        <dependency>
+            <groupId>io.dropwizard</groupId>
+            <artifactId>dropwizard-assets</artifactId>
+            <version>${dropwizard.version}</version>
+        </dependency>
+        <dependency>
+            <groupId>io.dropwizard</groupId>
+            <artifactId>dropwizard-logging</artifactId>
+            <version>${dropwizard.version}</version>
+        </dependency>
+        <dependency>
+            <groupId>io.dropwizard</groupId>
+            <artifactId>dropwizard-db</artifactId>
+            <version>${dropwizard.version}</version>
+        </dependency>
     </dependencies>
 
     <build>

lib/pom.xml

@@ -0,0 +1,147 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project xmlns="http://maven.apache.org/POM/4.0.0"
+         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
+    <modelVersion>4.0.0</modelVersion>
+    <groupId>edu.stanford.futuredata</groupId>
+    <artifactId>macrobase-lib</artifactId>
+    <version>0.1-SNAPSHOT</version>
+    <name>macrobase</name>
+    <url>https://github.com/stanford-futuredata/macrobase</url>
+    <description>
+        MacroBase is an anomaly detection engine designed to prioritize human attention
+        in large-scale datasets and data streams.
+        macrobase-lib provides operators for standalone API usage of classifiers and summarizers.
+    </description>
+    <licenses>
+        <license>
+            <name>Apache License, Version 2.0</name>
+            <url>http://www.apache.org/licenses/LICENSE-2.0.txt</url>
+            <distribution>repo</distribution>
+        </license>
+    </licenses>
+    <developers>
+        <developer>
+            <name>Peter Bailis</name>
+            <email>[email protected]</email>
+            <organization>Stanford</organization>
+            <organizationUrl>http://www.bailis.org</organizationUrl>
+        </developer>
+    </developers>
+    <scm>
+        <connection>scm:git:git://github.com/stanford-futuredata/macrobase.git</connection>
+        <developerConnection>scm:git:ssh://github.com/stanford-futuredata/macrobase.git</developerConnection>
+        <url>https://github.com/stanford-futuredata/macrobase</url>
+    </scm>
+
+
+
+    <dependencies>
+        <dependency>
+            <groupId>junit</groupId>
+            <artifactId>junit</artifactId>
+            <version>4.12</version>
+            <scope>test</scope>
+        </dependency>
+        <dependency>
+            <groupId>com.google.guava</groupId>
+            <artifactId>guava</artifactId>
+            <version>21.0</version>
+        </dependency>
+        <dependency>
+            <groupId>org.apache.commons</groupId>
+            <artifactId>commons-math3</artifactId>
+            <version>3.6</version>
+        </dependency>
+        <dependency>
+            <groupId>org.apache.commons</groupId>
+            <artifactId>commons-csv</artifactId>
+            <version>1.2</version>
+        </dependency>
+    </dependencies>
+
+    <distributionManagement>
+        <snapshotRepository>
+            <id>ossrh</id>
+            <url>https://oss.sonatype.org/content/repositories/snapshots</url>
+        </snapshotRepository>
+    </distributionManagement>
+
+    <build>
+    <plugins>
+        <plugin>
+            <groupId>org.apache.maven.plugins</groupId>
+            <artifactId>maven-compiler-plugin</artifactId>
+            <version>3.3</version>
+            <configuration>
+                <source>1.8</source>
+                <target>1.8</target>
+            </configuration>
+        </plugin>
+    </plugins>
+    </build>
+
+    <profiles>
+        <profile>
+            <id>release</id>
+            <build>
+            <plugins>
+                <plugin>
+                    <groupId>org.apache.maven.plugins</groupId>
+                    <artifactId>maven-source-plugin</artifactId>
+                    <version>3.0.1</version>
+                    <executions>
+                        <execution>
+                            <id>attach-sources</id>
+                            <phase>verify</phase>
+                            <goals>
+                                <goal>jar-no-fork</goal>
+                            </goals>
+                        </execution>
+                    </executions>
+                </plugin>
+              <plugin>
+                    <groupId>org.apache.maven.plugins</groupId>
+                    <artifactId>maven-javadoc-plugin</artifactId>
+                    <version>2.10.4</version>
+                    <executions>
+                        <execution>
+                            <id>attach-javadocs</id>
+                            <phase>verify</phase>
+                            <goals>
+                                <goal>jar</goal>
+                            </goals>
+                        </execution>
+                    </executions>
+                </plugin>
+                <plugin>
+                    <groupId>org.apache.maven.plugins</groupId>
+                    <artifactId>maven-gpg-plugin</artifactId>
+                    <version>1.5</version>
+                    <executions>
+                        <execution>
+                            <id>sign-artifacts</id>
+                            <phase>deploy</phase>
+                            <goals>
+                                <goal>sign</goal>
+                            </goals>
+                        </execution>
+                    </executions>
+                </plugin>
+                <plugin>
+                    <groupId>org.sonatype.plugins</groupId>
+                    <artifactId>nexus-staging-maven-plugin</artifactId>
+                    <version>1.6.7</version>
+                    <extensions>true</extensions>
+                    <configuration>
+                        <serverId>ossrh</serverId>
+                        <nexusUrl>https://oss.sonatype.org/</nexusUrl>
+                        <autoReleaseAfterClose>false</autoReleaseAfterClose>
+                    </configuration>
+                </plugin>
+            </plugins>
+            </build>
+        </profile>
+    </profiles>
+
+</project>