Apache OpenNLP:java.io.FileInputStream 无法转换为 opennlp.tools.util.InputStreamFactory
Apache OpenNLP: java.io.FileInputStream cannot be cast to opennlp.tools.util.InputStreamFactory
我正在尝试使用 Apache OpenNLP 1.7 构建自定义 NER。根据可用的文档 Here,我开发了以下代码
import java.io.BufferedOutputStream;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.nio.charset.Charset;
import opennlp.tools.namefind.NameFinderME;
import opennlp.tools.namefind.NameSample;
import opennlp.tools.namefind.NameSampleDataStream;
import opennlp.tools.namefind.TokenNameFinderFactory;
import opennlp.tools.namefind.TokenNameFinderModel;
import opennlp.tools.util.ObjectStream;
import opennlp.tools.util.PlainTextByLineStream;
import opennlp.tools.util.TrainingParameters;
public class PersonClassifierTrainer {
static String modelFile = "/opt/NLP/data/en-ner-customperson.bin";
public static void main(String[] args) throws IOException {
Charset charset = Charset.forName("UTF-8");
**ObjectStream<String> lineStream = new PlainTextByLineStream(new FileInputStream("/opt/NLP/data/person.train"), charset);**
ObjectStream<NameSample> sampleStream = new NameSampleDataStream(lineStream);
TokenNameFinderModel model;
TokenNameFinderFactory nameFinderFactory = null;
try {
model = NameFinderME.train("en", "person", sampleStream, TrainingParameters.defaultParams(),
nameFinderFactory);
} finally {
sampleStream.close();
}
BufferedOutputStream modelOut = null;
try {
modelOut = new BufferedOutputStream(new FileOutputStream(modelFile));
model.serialize(modelOut);
} finally {
if (modelOut != null)
modelOut.close();
}
}
}
上面突出显示的代码显示 - 'Cast argument 'file' to 'insputstreamfactory'
我不得不投这个,否则它会显示错误。
现在,当我 运行 我的代码时,出现以下错误
java.io.FileInputStream cannot be cast to opennlp.tools.util.InputStreamFactory
这里有什么遗漏吗?
编辑 1:Person.train 文件有此数据
<START:person> Hardik <END> is a software Professional.<START:person> Hardik works at company<END> and <START:person> is part of development team<END>. <START:person> Hardik<END> lives in New York
<START:person> Hardik<END> loves R statistical software
<START:person> Hardik<END> is a student at ISB
<START:person> Hardik<END> loves nature
Edit2:我现在遇到空指针异常,有什么帮助吗?
您需要一个 InputStreamFactory
的实例,它将检索您的 InputStream
。此外,TokenNameFinderFactory
不能是 null
。
public class PersonClassifierTrainer {
static String modelFile = "/opt/NLP/data/en-ner-customperson.bin";
public static void main(String[] args) throws IOException {
InputStreamFactory isf = new InputStreamFactory() {
public InputStream createInputStream() throws IOException {
return new FileInputStream("/opt/NLP/data/person.train");
}
};
Charset charset = Charset.forName("UTF-8");
ObjectStream<String> lineStream = new PlainTextByLineStream(isf, charset);
ObjectStream<NameSample> sampleStream = new NameSampleDataStream(lineStream);
TokenNameFinderModel model;
TokenNameFinderFactory nameFinderFactory = new TokenNameFinderFactory();
try {
model = NameFinderME.train("en", "person", sampleStream, TrainingParameters.defaultParams(),
nameFinderFactory);
} finally {
sampleStream.close();
}
BufferedOutputStream modelOut = null;
try {
modelOut = new BufferedOutputStream(new FileOutputStream(modelFile));
model.serialize(modelOut);
} finally {
if (modelOut != null)
modelOut.close();
}
}
}
编辑 1:Person.train 文件有此数据
<START:person> Hardik <END> is a software Professional.<START:person> Hardik works at company<END> and <START:person> is part of development team<END>. <START:person> Hardik<END> lives in New York
<START:person> Hardik<END> loves R statistical software
<START:person> Hardik<END> is a student at ISB
<START:person> Hardik<END> loves nature
我正在尝试使用 Apache OpenNLP 1.7 构建自定义 NER。根据可用的文档 Here,我开发了以下代码
import java.io.BufferedOutputStream;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.nio.charset.Charset;
import opennlp.tools.namefind.NameFinderME;
import opennlp.tools.namefind.NameSample;
import opennlp.tools.namefind.NameSampleDataStream;
import opennlp.tools.namefind.TokenNameFinderFactory;
import opennlp.tools.namefind.TokenNameFinderModel;
import opennlp.tools.util.ObjectStream;
import opennlp.tools.util.PlainTextByLineStream;
import opennlp.tools.util.TrainingParameters;
public class PersonClassifierTrainer {
static String modelFile = "/opt/NLP/data/en-ner-customperson.bin";
public static void main(String[] args) throws IOException {
Charset charset = Charset.forName("UTF-8");
**ObjectStream<String> lineStream = new PlainTextByLineStream(new FileInputStream("/opt/NLP/data/person.train"), charset);**
ObjectStream<NameSample> sampleStream = new NameSampleDataStream(lineStream);
TokenNameFinderModel model;
TokenNameFinderFactory nameFinderFactory = null;
try {
model = NameFinderME.train("en", "person", sampleStream, TrainingParameters.defaultParams(),
nameFinderFactory);
} finally {
sampleStream.close();
}
BufferedOutputStream modelOut = null;
try {
modelOut = new BufferedOutputStream(new FileOutputStream(modelFile));
model.serialize(modelOut);
} finally {
if (modelOut != null)
modelOut.close();
}
}
}
上面突出显示的代码显示 - 'Cast argument 'file' to 'insputstreamfactory'
我不得不投这个,否则它会显示错误。
现在,当我 运行 我的代码时,出现以下错误
java.io.FileInputStream cannot be cast to opennlp.tools.util.InputStreamFactory
这里有什么遗漏吗?
编辑 1:Person.train 文件有此数据
<START:person> Hardik <END> is a software Professional.<START:person> Hardik works at company<END> and <START:person> is part of development team<END>. <START:person> Hardik<END> lives in New York
<START:person> Hardik<END> loves R statistical software
<START:person> Hardik<END> is a student at ISB
<START:person> Hardik<END> loves nature
Edit2:我现在遇到空指针异常,有什么帮助吗?
您需要一个 InputStreamFactory
的实例,它将检索您的 InputStream
。此外,TokenNameFinderFactory
不能是 null
。
public class PersonClassifierTrainer {
static String modelFile = "/opt/NLP/data/en-ner-customperson.bin";
public static void main(String[] args) throws IOException {
InputStreamFactory isf = new InputStreamFactory() {
public InputStream createInputStream() throws IOException {
return new FileInputStream("/opt/NLP/data/person.train");
}
};
Charset charset = Charset.forName("UTF-8");
ObjectStream<String> lineStream = new PlainTextByLineStream(isf, charset);
ObjectStream<NameSample> sampleStream = new NameSampleDataStream(lineStream);
TokenNameFinderModel model;
TokenNameFinderFactory nameFinderFactory = new TokenNameFinderFactory();
try {
model = NameFinderME.train("en", "person", sampleStream, TrainingParameters.defaultParams(),
nameFinderFactory);
} finally {
sampleStream.close();
}
BufferedOutputStream modelOut = null;
try {
modelOut = new BufferedOutputStream(new FileOutputStream(modelFile));
model.serialize(modelOut);
} finally {
if (modelOut != null)
modelOut.close();
}
}
}
编辑 1:Person.train 文件有此数据
<START:person> Hardik <END> is a software Professional.<START:person> Hardik works at company<END> and <START:person> is part of development team<END>. <START:person> Hardik<END> lives in New York
<START:person> Hardik<END> loves R statistical software
<START:person> Hardik<END> is a student at ISB
<START:person> Hardik<END> loves nature