-
Notifications
You must be signed in to change notification settings - Fork 8
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Adding corpus tests, which take roughly 35 minutes to run, but which …
…pass
- Loading branch information
U-osiris\joeo
committed
Jan 31, 2012
1 parent
55c250e
commit f82f266
Showing
21 changed files
with
76 additions
and
37 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,37 +1,54 @@ | ||
<?xml version="1.0"?> | ||
<project xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd" | ||
xmlns="http://maven.apache.org/POM/4.0.0" | ||
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"> | ||
<modelVersion>4.0.0</modelVersion> | ||
<parent> | ||
<artifactId>ml-parent</artifactId> | ||
<groupId>com.enigmastation.ml</groupId> | ||
<version>4.0-SNAPSHOT</version> | ||
</parent> | ||
<groupId>com.enigmastation.ml</groupId> | ||
<artifactId>bayes</artifactId> | ||
<version>4.0-SNAPSHOT</version> | ||
<name>bayes</name> | ||
<url>http://maven.apache.org</url> | ||
<properties> | ||
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding> | ||
</properties> | ||
<dependencies> | ||
<dependency> | ||
<groupId>org.testng</groupId> | ||
<artifactId>testng</artifactId> | ||
<version>6.3.1</version> | ||
<scope>test</scope> | ||
</dependency> | ||
<dependency> | ||
<groupId>org.apache.lucene</groupId> | ||
<artifactId>lucene-analyzers</artifactId> | ||
<version>3.4.0</version> | ||
</dependency> | ||
<dependency> | ||
<groupId>${parent.groupId}</groupId> | ||
<artifactId>common</artifactId> | ||
<version>${project.version}</version> | ||
</dependency> | ||
</dependencies> | ||
</project> | ||
<?xml version="1.0"?> | ||
<project xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd" | ||
xmlns="http://maven.apache.org/POM/4.0.0" | ||
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"> | ||
<modelVersion>4.0.0</modelVersion> | ||
<parent> | ||
<artifactId>ml-parent</artifactId> | ||
<groupId>com.enigmastation.ml</groupId> | ||
<version>4.0-SNAPSHOT</version> | ||
</parent> | ||
<groupId>com.enigmastation.ml</groupId> | ||
<artifactId>bayes</artifactId> | ||
<version>4.0-SNAPSHOT</version> | ||
<name>bayes</name> | ||
<url>http://maven.apache.org</url> | ||
<properties> | ||
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding> | ||
</properties> | ||
<dependencies> | ||
<!-- testing dependencies --> | ||
<dependency> | ||
<groupId>org.testng</groupId> | ||
<artifactId>testng</artifactId> | ||
<version>6.3.1</version> | ||
<scope>test</scope> | ||
</dependency> | ||
<!-- I like javatar's tar archive much better than commons-compress' --> | ||
<dependency> | ||
<groupId>javatar</groupId> | ||
<artifactId>javatar</artifactId> | ||
<version>[2.5,)</version> | ||
<scope>test</scope> | ||
</dependency> | ||
<!-- however, commons-compress has a much more clear BZip2 inputstream than ant does--> | ||
<dependency> | ||
<groupId>org.apache.commons</groupId> | ||
<artifactId>commons-compress</artifactId> | ||
<version>1.2</version> | ||
<scope>test</scope> | ||
</dependency> | ||
|
||
<!-- runtime dependencies --> | ||
<dependency> | ||
<groupId>org.apache.lucene</groupId> | ||
<artifactId>lucene-analyzers</artifactId> | ||
<version>3.4.0</version> | ||
</dependency> | ||
<dependency> | ||
<groupId>${parent.groupId}</groupId> | ||
<artifactId>common</artifactId> | ||
<version>${project.version}</version> | ||
</dependency> | ||
</dependencies> | ||
</project> |
11 changes: 11 additions & 0 deletions
11
bayes/src/main/java/com/enigmastation/ml/bayes/impl/ThreadLocalMemoizer.java
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,11 @@ | ||
package com.enigmastation.ml.bayes.impl; | ||
|
||
/** | ||
* Created by IntelliJ IDEA. | ||
* User: joeo | ||
* Date: 1/31/12 | ||
* Time: 9:26 AM | ||
* To change this template use File | Settings | File Templates. | ||
*/ | ||
public class ThreadLocalMemoizer { | ||
} |
11 changes: 11 additions & 0 deletions
11
bayes/src/test/java/com/enigmastation/ml/bayes/CorpusTest.java
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,11 @@ | ||
package com.enigmastation.ml.bayes; | ||
|
||
/** | ||
* Created by IntelliJ IDEA. | ||
* User: joeo | ||
* Date: 1/31/12 | ||
* Time: 6:01 AM | ||
* To change this template use File | Settings | File Templates. | ||
*/ | ||
public class CorpusTest { | ||
} |
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file added
BIN
+1.6 MB
bayes/src/test/resources/publiccorpus/publiccorpus/20021010_easy_ham.tar.bz2
Binary file not shown.
Binary file added
BIN
+997 KB
bayes/src/test/resources/publiccorpus/publiccorpus/20021010_hard_ham.tar.bz2
Binary file not shown.
Binary file added
BIN
+1.14 MB
bayes/src/test/resources/publiccorpus/publiccorpus/20021010_spam.tar.bz2
Binary file not shown.
Binary file added
BIN
+1.54 MB
bayes/src/test/resources/publiccorpus/publiccorpus/20030228_easy_ham.tar.bz2
Binary file not shown.
Binary file added
BIN
+1.03 MB
bayes/src/test/resources/publiccorpus/publiccorpus/20030228_easy_ham_2.tar.bz2
Binary file not shown.
Binary file added
BIN
+1010 KB
bayes/src/test/resources/publiccorpus/publiccorpus/20030228_hard_ham.tar.bz2
Binary file not shown.
Binary file added
BIN
+1.13 MB
bayes/src/test/resources/publiccorpus/publiccorpus/20030228_spam.tar.bz2
Binary file not shown.
Binary file added
BIN
+1.96 MB
bayes/src/test/resources/publiccorpus/publiccorpus/20030228_spam_2.tar.bz2
Binary file not shown.
Binary file added
BIN
+1.96 MB
bayes/src/test/resources/publiccorpus/publiccorpus/20050311_spam_2.tar.bz2
Binary file not shown.