weka.core.converters.ArffSaver Java Examples

/**
 * @param args the command line arguments
 */
public static void main(String[] args) {
    // TODO code application logic here
    try{
        DataSource src = new DataSource("/Users/admin/Documents/NetBeansProjects/Datasets/weather.arff");
        Instances dt = src.getDataSet();
        
        String[] op = new String[]{"-R","2-4"};
        Remove rmv = new Remove();
        rmv.setOptions(op);
        rmv.setInputFormat(dt);
        Instances nd = Filter.useFilter(dt, rmv);
        
        ArffSaver s = new ArffSaver();
        s.setInstances(nd);
        s.setFile(new File("fw.arff"));
        s.writeBatch();
    }
    catch(Exception e){
        System.out.println(e.getMessage());
    }
}
 

/**
 *  Simple util to saveDatasets out. Useful for shapelet transform.
 *
 * @param dataSet
 * @param fileName
 */
public static void saveDataset(Instances dataSet, String fileName) {
    try {
        ArffSaver saver = new ArffSaver();
        saver.setMaxDecimalPlaces(MAX_DECIMAL_PLACES);
        saver.setInstances(dataSet);
        if (fileName.endsWith(".arff")) {
            saver.setFile(new File(fileName));
        } else {
            saver.setFile(new File(fileName + ".arff"));
        }
        saver.writeBatch();
    } catch (IOException ex) {
        System.out.println("Error saving transformed dataset" + ex);
    }
}
 

/** 
 * @param args the command line arguments
 */
public static void main(String[] args) {
    // TODO code application logic here
    try {
            DataSource src = new DataSource("/Users/admin/wekafiles/data/weather.numeric.arff");
            Instances dt= src.getDataSet();
            
            System.out.println(dt.toSummaryString());
            
            ArffSaver as = new ArffSaver();
            as.setInstances(dt);
            as.setFile(new File("weather.arff"));
            as.writeBatch();
        
    }
    catch(Exception e)
    {
        System.out.println(e.getMessage());
    }
}
 

/**
 * @param args the command line arguments
 */
public static void main(String[] args) {
    // TODO code application logic here
    try {
          DataSource src = new DataSource("/Users/admin/Documents/NetBeansProjects/Datasets/weather.arff");
          Instances dt = src.getDataSet();
          
          AttributeSelection asel = new AttributeSelection();
          
          CfsSubsetEval evl = new CfsSubsetEval();
          GreedyStepwise sh = new GreedyStepwise();
          
          asel.setEvaluator(evl);
          asel.setSearch(sh);
          asel.setInputFormat(dt);
          
          Instances nd = Filter.useFilter(dt, asel);
          ArffSaver as = new ArffSaver();
          as.setInstances(nd);
          as.setFile(new File("weather-sel.arff"));
          as.writeBatch();
    }
    catch(Exception e){
        System.out.println(e.getMessage());
    }
}
 

/**
 *  When the score changes, rewrite the file.
 *  This is really rare in practice, so don't bother optimizing it.
 */
private static void dump_from_scratch(Collection<String> names, Timestamp start_time) throws IOException {
	saved_schema_version = names.size();
	
	FastVector attributes = new FastVector();
	// Answer score names
	for (String name: names)
		attributes.addElement(new Attribute(name));
	Instances data = new Instances("Watsonsim captured question stream", attributes, 0);
	
	// Save the results to a file
	saver = new ArffSaver();
	saver.setStructure(data);
	saver.setRetrieval(Saver.INCREMENTAL);
	saver.setFile(new File("data/weka-log." + start_time + ".arff"));
	for (Score row : dataset)
		saver.writeIncremental(new Instance(1.0, row.getEach(names)));
}
 

private void convertCSVtoArff(String filename) throws Exception {

		// load CSV
		CSVLoader loader = new CSVLoader();
		loader.setSource(new File(filename));

		// CSV uses no header
		String[] options = new String[1];
		options[0] = "-H";
		loader.setOptions(options);

		Instances data = loader.getDataSet();

		// save ARFF
		ArffSaver saver = new ArffSaver();
		saver.setInstances(data);

		filename = filename.replace(".csv", ".arff");

		// saver.setDestination(new File(filename));
		saver.setFile(new File(filename));
		saver.writeBatch();

	}
 

public static void main(String[] args) throws Exception {
  if (args.length != 3)
    throw new IllegalArgumentException("Required parameters: <input> <attribute_indices> <output>");

  System.out.println("Loading input data: " + args[0]);
  Instances input = DataSource.read(args[0]);

  System.out.println("Applying filter using indices: " + args[1]);
  MekaClassAttributes filter = new MekaClassAttributes();
  filter.setAttributeIndices(args[1]);
  filter.setInputFormat(input);
  Instances output = Filter.useFilter(input, filter);

  System.out.println("Saving filtered data to: " + args[2]);
  ArffSaver saver = new ArffSaver();
  saver.setFile(new File(args[2]));
  DataSink.write(saver, output);
}
 

/**
 * Keep the words we want.
 * 
 * @param out
 * @param options
 * @throws Exception 
 */
private void removeWords(String output, String[] options, boolean inverse) throws Exception
{
       Remove remove = new Remove(); 
       
       if(inverse)
       {
           remove.setAttributeIndices(options[1]);
           remove.setInvertSelection(true);
       }else
       {
       	remove.setOptions(options); 
       }
       
       remove.setInputFormat(m_instances); 
       
       Instances newData = Filter.useFilter(m_instances, remove);
       
       ArffSaver saver = new ArffSaver();
       saver.setInstances(newData);
       saver.setFile(new File(output));
       saver.writeBatch();
	
}
 

/**
 * Main method for testing this class.
 * 
 * 
 *            should contain the path of input dataset and the name of
 *            target file scheme (see Evaluation)
 *@param args arguments            
 */
static public void main(String args[]) {

	if (args.length == 2) {

		TweetCollectionToArff ta = new SemEvalToArff();

		try {
			Instances dataset = ta.createDataset(args[0]);
			ArffSaver saver = new ArffSaver();
			saver.setInstances(dataset);

			saver.setFile(new File(args[1]));
			saver.writeBatch();

		} catch (Exception e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}

	}

}
 

/**
 * Main method for testing this class.
 * 
 * should contain the path of input dataset and the name of
 *            target file scheme (see Evaluation)
 * @param args arguments           
 */
static public void main(String args[]) {

	if (args.length == 2) {

		TweetCollectionToArff ta = new HumanCodedToArff();

		try {
			Instances dataset = ta.createDataset(args[0]);
			ArffSaver saver = new ArffSaver();
			saver.setInstances(dataset);

			saver.setFile(new File(args[1]));
			saver.writeBatch();

		} catch (Exception e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}

	}

}
 

public void ProcessTables(int[] table_array)
{
	
	DataBase();
	int execCount = 0;
	try {
		String SQL = "SELECT * from ArtTable where HasXML='yes' and idTable in "+Arrays.toString(table_array);
		SQL = SQL.replace("[", "(").replace("]", ")");
		Statement st = conn.createStatement();
		Instances instances = CreateInstances();
		FastVector fvWekaAttributes = new FastVector(48);
		rs = st.executeQuery(SQL);
		while (rs.next()) {
			Instance iExample = processTable(rs.getInt(1));
			instances.add(iExample);
			

			execCount ++;
			if(execCount>10000){
				conn.close();
				DataBase();
				execCount = 0;	
			}

		}
		System.out.println(instances.toString());
		ArffSaver saver = new ArffSaver();
		 saver.setInstances(instances);
		 saver.setFile(new File("spptest10.arff"));
		 //saver.setDestination(new File("./data/test.arff"));   // **not** necessary in 3.5.4 and later
		 saver.writeBatch();
	} catch (Exception ex) {
		ex.printStackTrace();
	}
}
 

public void ProcessTables(String tableType)
{
	
	DataBase();
	int execCount = 0;
	try {
		String SQL = "SELECT * from ArtTable where HasXML='yes' and specPragmatic='"+tableType+"' order by RAND() limit 200";
		Statement st = conn.createStatement();
		Instances instances = CreateInstances();
		FastVector fvWekaAttributes = new FastVector(128);
		rs = st.executeQuery(SQL);
		while (rs.next()) {
			Instance iExample = processTable(rs.getInt(1));
			instances.add(iExample);
			

			execCount ++;
			if(execCount>10000){
				conn.close();
				DataBase();
				execCount = 0;	
			}

		}
		System.out.println(instances.toString());
		ArffSaver saver = new ArffSaver();
		 saver.setInstances(instances);
		 saver.setFile(new File("spptest.arff"));
		 //saver.setDestination(new File("./data/test.arff"));   // **not** necessary in 3.5.4 and later
		 saver.writeBatch();
	} catch (Exception ex) {
		ex.printStackTrace();
	}
}
 

public void saveFile(Instances dataset, String type){
	ArffSaver saver = new ArffSaver();
	saver.setInstances(dataset);
	try {
		saver.setFile(new File(folder+"train/"+type+".arff"));
		saver.writeBatch();
	} catch (IOException e) {
		e.printStackTrace();
	}
}
 

public static void shuffle(String file, int classindex, String outputFile)
		throws IOException {

	// create the stream to read the data
	ArffFileStream stream = new ArffFileStream(file, classindex);
	InstancesHeader header = stream.getHeader();
	ArrayList<Instance> instanceList = new ArrayList<Instance>();
	System.out.println("Loading data ...");
	int cnt = 0;
	while (stream.hasMoreInstances()) {
		if (++cnt % 10000 == 0) {
			System.out.println("Read " + cnt + " items.");
		}
		instanceList.add(stream.nextInstance());
	}
	System.out.println("Read all items ... shuffling.");
	Collections.shuffle(instanceList);
	ArrayList<Attribute> attributeList = new ArrayList<Attribute>();
	for (int i = 0; i < header.numAttributes(); i++) {
		attributeList.add(header.attribute(i));
	}
	Instances dataSet = new Instances("reduced", attributeList, 2);
	for (Instance inst : instanceList) {
		dataSet.add(inst);
		inst.setDataset(dataSet);
	}
	System.out.println("Writing output ...");
	ArffSaver saver = new ArffSaver();
	saver.setInstances(dataSet);
	saver.setFile(new File(outputFile));
	saver.writeBatch();
	System.out.println("Done.");
}
 

@Test
public void test() throws Exception {
	// MLPlan4BigFileInput mlplan = new MLPlan4BigFileInput(new File("testrsc/openml/41103.arff"));

	String origDataSrcName = "testrsc/openml/1240.arff";

	if (true) {
		Instances data = new Instances(new FileReader(new File(origDataSrcName)));
		data.setClassIndex(data.numAttributes() - 1);
		List<Instances> split = WekaUtil.getStratifiedSplit(data, 0, .7f);
		ArffSaver saver = new ArffSaver();
		saver.setInstances(split.get(0));
		saver.setFile(new File(origDataSrcName + ".train"));
		saver.writeBatch();
		saver.setInstances(split.get(1));
		saver.setFile(new File(origDataSrcName + ".test"));
		saver.writeBatch();
		System.exit(0);
	}

	MLPlan4BigFileInput mlplan = new MLPlan4BigFileInput(new File(origDataSrcName + ".train"));
	mlplan.setTimeout(new Timeout(5, TimeUnit.MINUTES));
	mlplan.setLoggerName("testedalgorithm");
	long start = System.currentTimeMillis();
	Classifier c = mlplan.call();
	System.out.println("Observed output: " + c + " after " + (System.currentTimeMillis() - start) + "ms. Now validating the model");

	/* check quality */
	Instances testData = new Instances(new FileReader(new File(origDataSrcName + ".test")));
	testData.setClassIndex(testData.numAttributes() - 1);
	Evaluation eval = new Evaluation(testData);
	eval.evaluateModel(c, testData);
	System.out.println(eval.toSummaryString());

	assertNotNull(c);
}
 

public static void saveSingleInstances(final Instances dataSet, final String filePath) throws IOException {
	ArffSaver saver = new ArffSaver();
	saver.setInstances(dataSet);
	File destFile = new File(filePath);
	saver.setFile(destFile);

	saver.writeBatch();
}
 

public void generateArffFile(Instances instances, String path) {
    ArffSaver saver = new ArffSaver();
    saver.setInstances(instances);
    try {
        saver.setFile(new File(path));
        saver.writeBatch();
    } catch (IOException e) {
        e.printStackTrace();
    }
}
 

/**
 * Save @param data to the Arff file at @param path
 */
public static void saveDataToArffFile(String path, Instances data) throws IOException{
	    System.out.println("\nSaving to file " + path + "...");
	    ArffSaver saver = new ArffSaver();
	    saver.setInstances(data);
	    saver.setFile(new File(path));
	    saver.writeBatch();
}
 

/**
 * @param args the command line arguments
 */
public static void main(String[] args) throws Exception {
    CSVLoader loader = new CSVLoader();
    loader.setSource(new File("/Users/admin/Documents/NetBeansProjects/Arff2CSV/weather.csv"));
    Instances data = loader.getDataSet();

    ArffSaver saver = new ArffSaver();
    saver.setInstances(data);

    saver.setFile(new File("weather.arff"));
    saver.writeBatch();
}
 

public static void runExperiment(ExperimentalArguments expSettings, Instances train, Instances test, SimpleBatchFilter transformer, String fullWriteLocation, String additionalDataFilePath) throws Exception{
    
        //this is hacky, but will do.
        Instances[] transforms = setContractDataAndProcess(expSettings, train, test, transformer);
    
        //Filter.useFilter is wekas weird way
        Instances transformed_train = transforms[0];
        Instances transformed_test = transforms[1];

        ArffSaver saver = new ArffSaver();

        String transformed_train_output = fullWriteLocation + expSettings.datasetName +"_TRAIN.arff";
        String transformed_test_output = fullWriteLocation + expSettings.datasetName +"_TEST.arff";

        saver.setInstances(transformed_train);
        saver.setFile(new File(transformed_train_output));
        saver.writeBatch();

        saver.setInstances(transformed_test);
        saver.setFile(new File(transformed_test_output));
        saver.writeBatch();

        
        writeAdditionalTransformData(expSettings, transformer, additionalDataFilePath);
}