List of usage examples for org.apache.mahout.classifier.df.data Dataset isNumerical
public boolean isNumerical(int attr)
From source file:com.wsc.myexample.decisionForest.MyDecisionForest.java
License:Apache License
/** * predicts the label for the instance/*from w w w .j ava 2 s .c o m*/ * * @param rng * Random number generator, used to break ties randomly * @return -1 if the label cannot be predicted */ public double classify(Dataset dataset, Random rng, Instance instance) { if (dataset.isNumerical(dataset.getLabelId())) { double sum = 0; int cnt = 0; for (Node tree : trees) { double prediction = tree.classify(instance); if (prediction != -1) { sum += prediction; cnt++; } } return sum / cnt; } else { int[] predictions = new int[dataset.nblabels()]; for (Node tree : trees) { double prediction = tree.classify(instance); if (prediction != -1) { predictions[(int) prediction]++; } } if (DataUtils.sum(predictions) == 0) { return -1; // no prediction available } return DataUtils.maxindex(rng, predictions); } }
From source file:guipart.view.GUIOverviewController.java
@FXML void handleClassifyRF(ActionEvent event) throws IOException { String outputFile = "data/out"; Path dataPath = new Path(textFieldCSVRF.getText()); // test data path Path datasetPath = new Path(textFieldDatasetRF.getText()); //info file about data set Path modelPath = new Path(textFieldModelRF.getText()); // path where the forest is stored Path outputPath = new Path(outputFile); // path to predictions file, if null do not output the predictions Configuration conf = new Configuration(); FileSystem fs = FileSystem.get(conf); FileSystem outFS = FileSystem.get(conf); System.out.println("Loading the forest"); DecisionForest forest = DecisionForest.load(conf, modelPath); if (forest == null) System.err.println("No decision forest found!"); // load the dataset Dataset dataset = Dataset.load(conf, datasetPath); DataConverter converter = new DataConverter(dataset); System.out.println("Sequential classification"); long time = System.currentTimeMillis(); Random rng = RandomUtils.getRandom(); List<double[]> resList = Lists.newArrayList(); if (fs.getFileStatus(dataPath).isDir()) { //the input is a directory of files Utils.rfTestDirectory(outputPath, converter, forest, dataset, resList, rng, fs, dataPath, outFS, guiPart);/*from w w w . j a v a2s . c o m*/ } else { // the input is one single file Utils.rfTestFile(dataPath, outputPath, converter, forest, dataset, resList, rng, outFS, fs, guiPart); } time = System.currentTimeMillis() - time; //log.info("Classification Time: {}", DFUtils.elapsedTime(time)); System.out.println("Classification time: " + DFUtils.elapsedTime(time)); if (dataset.isNumerical(dataset.getLabelId())) { RegressionResultAnalyzer regressionAnalyzer = new RegressionResultAnalyzer(); double[][] results = new double[resList.size()][2]; regressionAnalyzer.setInstances(resList.toArray(results)); //log.info("{}", regressionAnalyzer); System.out.println(regressionAnalyzer.toString()); } else { ResultAnalyzer analyzer = new ResultAnalyzer(Arrays.asList(dataset.labels()), "unknown"); for (double[] r : resList) { analyzer.addInstance(dataset.getLabelString(r[0]), new ClassifierResult(dataset.getLabelString(r[1]), 1.0)); } //log.info("{}", analyzer); System.out.println(analyzer.toString()); textAnalyze.setText(analyzer.toString()); } }
From source file:imageClassify.TestForest.java
License:Apache License
private void mapreduce() throws ClassNotFoundException, IOException, InterruptedException { if (outputPath == null) { throw new IllegalArgumentException( "You must specify the ouputPath when using the mapreduce implementation"); }//from w w w . ja va 2s . c o m Classifier classifier = new Classifier(modelPath, dataPath, datasetPath, outputPath, getConf()); classifier.run(); if (analyze) { double[][] results = classifier.getResults(); if (results != null) { Dataset dataset = Dataset.load(getConf(), datasetPath); if (dataset.isNumerical(dataset.getLabelId())) { RegressionResultAnalyzer regressionAnalyzer = new RegressionResultAnalyzer(); regressionAnalyzer.setInstances(results); log.info("{}", regressionAnalyzer); } else { ResultAnalyzer analyzer = new ResultAnalyzer(Arrays.asList(dataset.labels()), "unknown"); for (double[] res : results) { analyzer.addInstance(dataset.getLabelString(res[0]), new ClassifierResult(dataset.getLabelString(res[1]), 1.0)); } log.info("{}", analyzer); } } } }
From source file:imageClassify.TestForest.java
License:Apache License
private void sequential() throws IOException { log.info("Loading the forest..."); DecisionForest forest = DecisionForest.load(getConf(), modelPath); if (forest == null) { log.error("No Decision Forest found!"); return;//from w w w. ja v a 2s. c o m } // load the dataset Dataset dataset = Dataset.load(getConf(), datasetPath); DataConverter converter = new DataConverter(dataset); log.info("Sequential classification..."); long time = System.currentTimeMillis(); Random rng = RandomUtils.getRandom(); List<double[]> resList = Lists.newArrayList(); if (dataFS.getFileStatus(dataPath).isDir()) { //the input is a directory of files testDirectory(outputPath, converter, forest, dataset, resList, rng); } else { // the input is one single file testFile(dataPath, outputPath, converter, forest, dataset, resList, rng); } time = System.currentTimeMillis() - time; log.info("Classification Time: {}", DFUtils.elapsedTime(time)); if (analyze) { if (dataset.isNumerical(dataset.getLabelId())) { RegressionResultAnalyzer regressionAnalyzer = new RegressionResultAnalyzer(); double[][] results = new double[resList.size()][2]; regressionAnalyzer.setInstances(resList.toArray(results)); log.info("{}", regressionAnalyzer); } else { ResultAnalyzer analyzer = new ResultAnalyzer(Arrays.asList(dataset.labels()), "unknown"); for (double[] r : resList) { analyzer.addInstance(dataset.getLabelString(r[0]), new ClassifierResult(dataset.getLabelString(r[1]), 1.0)); } log.info("{}", analyzer); } } }
From source file:javaapplication3.RunRandomForestSeq.java
public static void main(String[] args) throws IOException { String outputFile = "data/out"; String inputFile = "data/DataFraud1MTest.csv"; String modelFile = "data/forest.seq"; String infoFile = "data/DataFraud1M.info"; Path dataPath = new Path(inputFile); // test data path Path datasetPath = new Path(infoFile); Path modelPath = new Path(modelFile); // path where the forest is stored Path outputPath = new Path(outputFile); // path to predictions file, if null do not output the predictions Configuration conf = new Configuration(); FileSystem fs = FileSystem.get(conf); FileSystem outFS = FileSystem.get(conf); //log.info("Loading the forest..."); System.out.println("Loading the forest"); DecisionForest forest = DecisionForest.load(conf, modelPath); if (forest == null) System.err.println("No decision forest found!"); //log.error("No Decision Forest found!"); // load the dataset Dataset dataset = Dataset.load(conf, datasetPath); DataConverter converter = new DataConverter(dataset); //log.info("Sequential classification..."); System.out.println("Sequential classification"); long time = System.currentTimeMillis(); Random rng = RandomUtils.getRandom(); List<double[]> resList = Lists.newArrayList(); if (fs.getFileStatus(dataPath).isDir()) { //the input is a directory of files testDirectory(outputPath, converter, forest, dataset, resList, rng, fs, dataPath, outFS); } else {/*from w ww. j av a 2s. co m*/ // the input is one single file testFile(dataPath, outputPath, converter, forest, dataset, resList, rng, outFS, fs); } time = System.currentTimeMillis() - time; //log.info("Classification Time: {}", DFUtils.elapsedTime(time)); System.out.println("Classification time: " + DFUtils.elapsedTime(time)); if (dataset.isNumerical(dataset.getLabelId())) { RegressionResultAnalyzer regressionAnalyzer = new RegressionResultAnalyzer(); double[][] results = new double[resList.size()][2]; regressionAnalyzer.setInstances(resList.toArray(results)); //log.info("{}", regressionAnalyzer); System.out.println(regressionAnalyzer.toString()); } else { ResultAnalyzer analyzer = new ResultAnalyzer(Arrays.asList(dataset.labels()), "unknown"); for (double[] r : resList) { analyzer.addInstance(dataset.getLabelString(r[0]), new ClassifierResult(dataset.getLabelString(r[1]), 1.0)); } //log.info("{}", analyzer); System.out.println(analyzer.toString()); } }