1. Create a method to generate a schema for the user input:

private static Schema generateSchema(){
 Schema schema = new Schema.Builder()
 .addColumnString("RowNumber")
 .addColumnInteger("CustomerId")
 .addColumnString("Surname")
 .addColumnInteger("CreditScore")
 .addColumnCategorical("Geography", Arrays.asList("France","Germany","Spain"))
 .addColumnCategorical("Gender", Arrays.asList("Male","Female"))
 .addColumnsInteger("Age", "Tenure")
 .addColumnDouble("Balance")
 .addColumnsInteger("NumOfProducts","HasCrCard","IsActiveMember")
 .addColumnDouble("EstimatedSalary")
 .build();
 return schema;
 }

2. Create a TransformProcess from the schema:

private static RecordReader applyTransform(RecordReader recordReader, Schema schema){
 final TransformProcess transformProcess = new TransformProcess.Builder(schema)
 .removeColumns("RowNumber","CustomerId","Surname")
 .categoricalToInteger("Gender")
 .categoricalToOneHot("Geography")
 .removeColumns("Geography[France]")
 .build();
 final TransformProcessRecordReader transformProcessRecordReader = new TransformProcessRecordReader(recordReader,transformProcess);
 return transformProcessRecordReader;
}

3. Load the data into a record reader instance:

private static RecordReader generateReader(File file) throws IOException, InterruptedException {
 final RecordReader recordReader = new CSVRecordReader(1,',');
 recordReader.initialize(new FileSplit(file));
 final RecordReader transformProcessRecordReader=applyTransform(recordReader,generateSchema());

4. Restore the model using ModelSerializer:

File modelFile = new File(modelFilePath);
 MultiLayerNetwork network = ModelSerializer.restoreMultiLayerNetwork(modelFile);
 NormalizerStandardize normalizerStandardize = ModelSerializer.restoreNormalizerFromFile(modelFile);
 

5. Create an iterator to traverse through the entire set of input records:

DataSetIterator dataSetIterator = new RecordReaderDataSetIterator.Builder(recordReader,1).build();
 normalizerStandardize.fit(dataSetIterator);
 dataSetIterator.setPreProcessor(normalizerStandardize); 

6. Design an API function to generate output from user input:

public static INDArray generateOutput(File inputFile, String modelFilePath) throws IOException, InterruptedException {
 File modelFile = new File(modelFilePath);
 MultiLayerNetwork network = ModelSerializer.restoreMultiLayerNetwork(modelFile);
   RecordReader recordReader = generateReader(inputFile);
 NormalizerStandardize normalizerStandardize = ModelSerializer.restoreNormalizerFromFile(modelFile);
 DataSetIterator dataSetIterator = new RecordReaderDataSetIterator.Builder(recordReader,1).build();
 normalizerStandardize.fit(dataSetIterator);
 dataSetIterator.setPreProcessor(normalizerStandardize);
 return network.output(dataSetIterator);
 }

For a further example, see: https://github.com/PacktPublishing/Java-Deep-Learning-Cookbook/blob/master/03_Building_Deep_Neural_Networks_for_Binary_classification/sourceCode/cookbookapp/src/main/java/com/javadeeplearningcookbook/api/CustomerRetentionPredictionApi.java 

7. Build a shaded JAR of your DL4J API project by running the Maven command:

mvn clean install

8. Run the Spring Boot project included in the source directory. Import the Maven project to your IDE: https://github.com/PacktPublishing/Java-Deep-Learning-Cookbook/tree/master/03_Building_Deep_Neural_Networks_for_Binary_classification/sourceCode/spring-dl4j.

Add the following VM options in under run configurations:

-DmodelFilePath={PATH-TO-MODEL-FILE}

PATH-TO-MODEL-FILE is the location where you stored the actual model file. It can be on your local disk or in a cloud as well. 

Then, run the SpringDl4jApplication.java file:

9. Test your Spring Boot app at http://localhost:8080/:

10. Verify the functionality by uploading an input CSV file.

Use a sample CSV file to upload into the web application: https://github.com/PacktPublishing/Java-Deep-Learning-Cookbook/blob/master/03_Building_Deep_Neural_Networks_for_Binary_classification/sourceCode/cookbookapp/src/main/resources/test.csv.

The prediction results will be displayed as shown here: