├── .gitignore
├── README.md
├── input
    └── content.txt
├── output
    └── .gitignore
├── pom.xml
└── src
    └── main
        └── java
            └── com
                └── technobium
                    └── word2vec
                        └── Word2VecDemo.java


/.gitignore:
--------------------------------------------------------------------------------
 1 | *.class
 2 | 
 3 | # Mobile Tools for Java (J2ME)
 4 | .mtj.tmp/
 5 | 
 6 | # Package Files #
 7 | *.jar
 8 | *.war
 9 | *.ear
10 | 
11 | # virtual machine crash logs, see http://www.java.com/en/download/help/error_hotspot.xml
12 | hs_err_pid*
13 | 
14 | # Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio and Webstorm
15 | # Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839
16 | 
17 | # User-specific stuff:
18 | .idea/workspace.xml
19 | .idea/tasks.xml
20 | 
21 | # Sensitive or high-churn files:
22 | .idea/dataSources/
23 | .idea/dataSources.ids
24 | .idea/dataSources.xml
25 | .idea/dataSources.local.xml
26 | .idea/sqlDataSources.xml
27 | .idea/dynamic.xml
28 | .idea/uiDesigner.xml
29 | 
30 | # Gradle:
31 | .idea/gradle.xml
32 | .idea/libraries
33 | 
34 | # Mongo Explorer plugin:
35 | .idea/mongoSettings.xml
36 | 
37 | ## File-based project format:
38 | *.iws
39 | 
40 | ## Plugin-specific files:
41 | 
42 | # IntelliJ
43 | /out/
44 | 
45 | # mpeltonen/sbt-idea plugin
46 | .idea_modules/
47 | 
48 | # JIRA plugin
49 | atlassian-ide-plugin.xml
50 | 
51 | # Crashlytics plugin (for Android Studio and IntelliJ)
52 | com_crashlytics_export_strings.xml
53 | crashlytics.properties
54 | crashlytics-build.properties
55 | fabric.properties
56 | .idea/
57 | target/
58 | word2vec-demo.iml
59 | output/word2vec.bin
60 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
1 | # dl4j-word2vec
2 | Deeplearning4j Word2Vec Demo
3 | 
4 | Get the content of the War and Peace book from the following location http://www.textfiles.com/etext/FICTION/warpeace.txt. Copy and paste it into input/content.txt file.
5 | 
6 | 


--------------------------------------------------------------------------------
/input/content.txt:
--------------------------------------------------------------------------------
1 | # TODO - copy content from http://www.textfiles.com/etext/FICTION/warpeace.txt


--------------------------------------------------------------------------------
/output/.gitignore:
--------------------------------------------------------------------------------
1 | # Ignore everything in this directory
2 | *
3 | # Except this file
4 | !.gitignore
5 | 
6 | 


--------------------------------------------------------------------------------
/pom.xml:
--------------------------------------------------------------------------------
 1 | <?xml version="1.0" encoding="UTF-8"?>
 2 | <project xmlns="http://maven.apache.org/POM/4.0.0"
 3 |          xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
 4 |          xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
 5 |     <modelVersion>4.0.0</modelVersion>
 6 | 
 7 |     <groupId>com.technobium</groupId>
 8 |     <artifactId>dl4j-word2vec</artifactId>
 9 |     <version>1.0-SNAPSHOT</version>
10 | 
11 |     <properties>
12 |         <nd4j.version>0.7.1</nd4j.version>
13 |         <dl4j.version>0.7.1</dl4j.version>
14 |     </properties>
15 | 
16 |     <dependencies>
17 |         <dependency>
18 |             <groupId>org.deeplearning4j</groupId>
19 |             <artifactId>deeplearning4j-ui-model</artifactId>
20 |             <version>${dl4j.version}</version>
21 |         </dependency>
22 |         <dependency>
23 |             <groupId>org.deeplearning4j</groupId>
24 |             <artifactId>deeplearning4j-nlp</artifactId>
25 |             <version>${dl4j.version}</version>
26 |         </dependency>
27 |         <dependency>
28 |             <groupId>org.nd4j</groupId>
29 |             <artifactId>nd4j-native</artifactId>
30 |             <version>${nd4j.version}</version>
31 |         </dependency>
32 |     </dependencies>
33 | 
34 | </project>
35 | 


--------------------------------------------------------------------------------
/src/main/java/com/technobium/word2vec/Word2VecDemo.java:
--------------------------------------------------------------------------------
 1 | package com.technobium.word2vec;
 2 | 
 3 | import org.deeplearning4j.models.embeddings.learning.impl.elements.SkipGram;
 4 | import org.deeplearning4j.models.embeddings.loader.WordVectorSerializer;
 5 | import org.deeplearning4j.models.word2vec.VocabWord;
 6 | import org.deeplearning4j.models.word2vec.Word2Vec;
 7 | import org.deeplearning4j.text.sentenceiterator.FileSentenceIterator;
 8 | import org.deeplearning4j.text.sentenceiterator.SentenceIterator;
 9 | import org.deeplearning4j.text.tokenization.tokenizer.preprocessor.CommonPreprocessor;
10 | import org.deeplearning4j.text.tokenization.tokenizerfactory.DefaultTokenizerFactory;
11 | import org.deeplearning4j.text.tokenization.tokenizerfactory.TokenizerFactory;
12 | 
13 | import java.io.File;
14 | import java.io.IOException;
15 | import java.util.Collection;
16 | 
17 | public class Word2VecDemo {
18 | 
19 |     private String inputFilePath = "input/content.txt";
20 |     private String modelFilePath = "output/word2vec.bin";
21 | 
22 |     public static void main(String[] args) throws IOException {
23 | 
24 |         Word2VecDemo word2VecDemo = new Word2VecDemo();
25 |         // Before starting the training, don't forget to add the text into input/content.txt
26 |         word2VecDemo.train();
27 | 
28 |         Word2Vec word2VecModel = WordVectorSerializer.readWord2VecModel(new File(word2VecDemo.modelFilePath));
29 | 
30 |         Collection<String> list = word2VecModel.wordsNearest("boy" , 10);
31 |         System.out.println(" boy: "+ list);
32 | 
33 |         list = word2VecModel.wordsNearest("girl" , 10);
34 |         System.out.println("girl: " + list);
35 | 
36 |         Collection<String> stringList = word2VecModel.wordsNearest("day", 10);
37 |         System.out.println(" day: " + stringList);
38 |     }
39 | 
40 |     public  void train() throws IOException {
41 |         SentenceIterator sentenceIterator = new FileSentenceIterator(new File(inputFilePath));
42 |         TokenizerFactory tokenizerFactory = new DefaultTokenizerFactory();
43 |         tokenizerFactory.setTokenPreProcessor(new CommonPreprocessor());
44 | 
45 |         Word2Vec vec = new Word2Vec.Builder()
46 |                 .minWordFrequency(2)
47 |                 .layerSize(300)
48 |                 .windowSize(5)
49 |                 .seed(42)
50 |                 .epochs(3)
51 |                 .elementsLearningAlgorithm(new SkipGram<VocabWord>())
52 |                 .iterate(sentenceIterator)
53 |                 .tokenizerFactory(tokenizerFactory)
54 |                 .build();
55 |         vec.fit();
56 | 
57 |         WordVectorSerializer.writeWordVectors(vec, "output/word2vec.bin");
58 |     }
59 | }
60 | 


--------------------------------------------------------------------------------