Examples with BufferedString water.parser.BufferedString used on opensource projects

Example 36 with BufferedString

use of water.parser.BufferedString in project h2o-3 by h2oai.

the class Model method testJavaScoring.

public boolean testJavaScoring(Frame data, Frame model_predictions, double rel_epsilon, double abs_epsilon, double fraction) {
    ModelBuilder mb = ModelBuilder.make(_parms.algoName().toLowerCase(), null, null);
    boolean havePojo = mb.havePojo();
    boolean haveMojo = mb.haveMojo();
    Random rnd = RandomUtils.getRNG(data.byteSize());
    assert data.numRows() == model_predictions.numRows();
    Frame fr = new Frame(data);
    boolean computeMetrics = data.vec(_output.responseName()) != null && !data.vec(_output.responseName()).isBad();
    try {
        String[] warns = adaptTestForTrain(fr, true, computeMetrics);
        if (warns.length > 0)
            System.err.println(Arrays.toString(warns));
        // Output is in the model's domain, but needs to be mapped to the scored
        // dataset's domain.
        int[] omap = null;
        if (_output.isClassifier()) {
            Vec actual = fr.vec(_output.responseName());
            // Scored/test domain; can be null
            String[] sdomain = actual == null ? null : actual.domain();
            // Domain of predictions (union of test and train)
            String[] mdomain = model_predictions.vec(0).domain();
            if (sdomain != null && !Arrays.equals(mdomain, sdomain)) {
                // Map from model-domain to scoring-domain
                omap = CategoricalWrappedVec.computeMap(mdomain, sdomain);
            }
        }
        String modelName = JCodeGen.toJavaId(_key.toString());
        boolean preview = false;
        GenModel genmodel = null;
        Vec[] dvecs = fr.vecs();
        Vec[] pvecs = model_predictions.vecs();
        double[] features = null;
        int num_errors = 0;
        int num_total = 0;
        // First try internal POJO via fast double[] API
        if (havePojo) {
            try {
                String java_text = toJava(preview, true);
                Class clz = JCodeGen.compile(modelName, java_text);
                genmodel = (GenModel) clz.newInstance();
            } catch (Exception e) {
                e.printStackTrace();
                throw H2O.fail("Internal POJO compilation failed", e);
            }
            features = MemoryManager.malloc8d(genmodel._names.length);
            double[] predictions = MemoryManager.malloc8d(genmodel.nclasses() + 1);
            // Compare predictions, counting mis-predicts
            for (int row = 0; row < fr.numRows(); row++) {
                // For all rows, single-threaded
                if (rnd.nextDouble() >= fraction)
                    continue;
                num_total++;
                // Native Java API
                for (// Build feature set
                int col = 0; // Build feature set
                col < features.length; // Build feature set
                col++) features[col] = dvecs[col].at(row);
                // POJO predictions
                genmodel.score0(features, predictions);
                for (int col = _output.isClassifier() ? 1 : 0; col < pvecs.length; col++) {
                    // Compare predictions
                    // Load internal scoring predictions
                    double d = pvecs[col].at(row);
                    // map categorical response to scoring domain
                    if (col == 0 && omap != null)
                        d = omap[(int) d];
                    if (!MathUtils.compare(predictions[col], d, abs_epsilon, rel_epsilon)) {
                        if (num_errors++ < 10)
                            System.err.println("Predictions mismatch, row " + row + ", col " + model_predictions._names[col] + ", internal prediction=" + d + ", POJO prediction=" + predictions[col]);
                        break;
                    }
                }
            }
        }
        // EasyPredict API with POJO and/or MOJO
        for (int i = 0; i < 2; ++i) {
            if (i == 0 && !havePojo)
                continue;
            if (i == 1 && !haveMojo)
                continue;
            if (i == 1) {
                // MOJO
                final String filename = modelName + ".zip";
                StreamingSchema ss = new StreamingSchema(getMojo(), filename);
                try {
                    FileOutputStream os = new FileOutputStream(ss.getFilename());
                    ss.getStreamWriter().writeTo(os);
                    os.close();
                    genmodel = MojoModel.load(filename);
                    features = MemoryManager.malloc8d(genmodel._names.length);
                } catch (IOException e1) {
                    e1.printStackTrace();
                    throw H2O.fail("Internal MOJO loading failed", e1);
                } finally {
                    boolean deleted = new File(filename).delete();
                    if (!deleted)
                        Log.warn("Failed to delete the file");
                }
            }
            EasyPredictModelWrapper epmw = new EasyPredictModelWrapper(new EasyPredictModelWrapper.Config().setModel(genmodel).setConvertUnknownCategoricalLevelsToNa(true));
            RowData rowData = new RowData();
            BufferedString bStr = new BufferedString();
            for (int row = 0; row < fr.numRows(); row++) {
                // For all rows, single-threaded
                if (rnd.nextDouble() >= fraction)
                    continue;
                if (genmodel.getModelCategory() == ModelCategory.AutoEncoder)
                    continue;
                // Generate input row
                for (int col = 0; col < features.length; col++) {
                    if (dvecs[col].isString()) {
                        rowData.put(genmodel._names[col], dvecs[col].atStr(bStr, row).toString());
                    } else {
                        double val = dvecs[col].at(row);
                        rowData.put(genmodel._names[col], genmodel._domains[col] == null ? (Double) val : // missing categorical values are kept as NaN, the score0 logic passes it on to bitSetContains()
                        Double.isNaN(val) ? // missing categorical values are kept as NaN, the score0 logic passes it on to bitSetContains()
                        val : //unseen levels are treated as such
                        (int) val < genmodel._domains[col].length ? genmodel._domains[col][(int) val] : "UnknownLevel");
                    }
                }
                // Make a prediction
                AbstractPrediction p;
                try {
                    p = epmw.predict(rowData);
                } catch (PredictException e) {
                    num_errors++;
                    if (num_errors < 20) {
                        System.err.println("EasyPredict threw an exception when predicting row " + rowData);
                        e.printStackTrace();
                    }
                    continue;
                }
                // Convert model predictions and "internal" predictions into the same shape
                double[] expected_preds = new double[pvecs.length];
                double[] actual_preds = new double[pvecs.length];
                for (int col = 0; col < pvecs.length; col++) {
                    // Compare predictions
                    // Load internal scoring predictions
                    double d = pvecs[col].at(row);
                    // map categorical response to scoring domain
                    if (col == 0 && omap != null)
                        d = omap[(int) d];
                    double d2 = Double.NaN;
                    switch(genmodel.getModelCategory()) {
                        case Clustering:
                            d2 = ((ClusteringModelPrediction) p).cluster;
                            break;
                        case Regression:
                            d2 = ((RegressionModelPrediction) p).value;
                            break;
                        case Binomial:
                            BinomialModelPrediction bmp = (BinomialModelPrediction) p;
                            d2 = (col == 0) ? bmp.labelIndex : bmp.classProbabilities[col - 1];
                            break;
                        case Multinomial:
                            MultinomialModelPrediction mmp = (MultinomialModelPrediction) p;
                            d2 = (col == 0) ? mmp.labelIndex : mmp.classProbabilities[col - 1];
                            break;
                        case DimReduction:
                            d2 = ((DimReductionModelPrediction) p).dimensions[col];
                            break;
                    }
                    expected_preds[col] = d;
                    actual_preds[col] = d2;
                }
                // Verify the correctness of the prediction
                num_total++;
                for (int col = genmodel.isClassifier() ? 1 : 0; col < pvecs.length; col++) {
                    if (!MathUtils.compare(actual_preds[col], expected_preds[col], abs_epsilon, rel_epsilon)) {
                        num_errors++;
                        if (num_errors < 20) {
                            System.err.println((i == 0 ? "POJO" : "MOJO") + " EasyPredict Predictions mismatch for row " + rowData);
                            System.err.println("  Expected predictions: " + Arrays.toString(expected_preds));
                            System.err.println("  Actual predictions:   " + Arrays.toString(actual_preds));
                        }
                        break;
                    }
                }
            }
        }
        if (num_errors != 0)
            System.err.println("Number of errors: " + num_errors + (num_errors > 20 ? " (only first 20 are shown)" : "") + " out of " + num_total + " rows tested.");
        return num_errors == 0;
    } finally {
        // Remove temp keys.
        cleanup_adapt(fr, data);
    }
}

Example 37 with BufferedString

use of water.parser.BufferedString in project h2o-3 by h2oai.

the class WordCountTaskTest method testWordCountText8.

@Test
public void testWordCountText8() {
    String fName = "bigdata/laptop/text8.gz";
    // only run if text8 is present
    assumeThat("text8 data available", locateFile(fName), is(notNullValue()));
    Frame fr = parse_test_file(fName, "NA", 0, new byte[] { Vec.T_STR });
    try {
        Map<BufferedString, IcedLong> counts = new WordCountTask().doAll(fr.vec(0))._counts;
        assertEquals(253854, counts.size());
        assertEquals(303L, counts.get(new BufferedString("anarchism"))._val);
        assertEquals(316376L, counts.get(new BufferedString("to"))._val);
        assertNotNull(counts);
    } finally {
        fr.remove();
    }
}

Example 38 with BufferedString

use of water.parser.BufferedString in project h2o-3 by h2oai.

the class WordCountTaskTest method testWordCount.

@Test
public void testWordCount() {
    String[] strData = new String[10000];
    for (int i = 0; i < strData.length; i++) {
        int b = i % 10;
        if (b < 3)
            strData[i] = "A";
        else if (b < 5)
            strData[i] = "B";
        else
            strData[i] = "C";
    }
    Frame fr = new TestFrameBuilder().withName("data").withColNames("Str").withVecTypes(Vec.T_STR).withDataForCol(0, strData).withChunkLayout(100, 900, 5000, 4000).build();
    try {
        Map<BufferedString, IcedLong> counts = new WordCountTask().doAll(fr.vec(0))._counts;
        assertEquals(3, counts.size());
        assertEquals(3000L, counts.get(new BufferedString("A"))._val);
        assertEquals(2000L, counts.get(new BufferedString("B"))._val);
        assertEquals(5000L, counts.get(new BufferedString("C"))._val);
        System.out.println(counts);
    } finally {
        fr.remove();
    }
}

Example 39 with BufferedString

use of water.parser.BufferedString in project h2o-3 by h2oai.

the class AstRecAssignTestUtils method strVec2array.

static String[] strVec2array(Vec v) {
    Vec.Reader ovr = v.new Reader();
    assert ovr.length() < Integer.MAX_VALUE;
    final int len = (int) ovr.length();
    BufferedString bs = new BufferedString();
    String[] array = new String[len];
    for (int i = 0; i < len; i++) {
        BufferedString s = ovr.atStr(bs, i);
        if (s != null)
            array[i] = s.toString();
    }
    return array;
}

Example 40 with BufferedString

use of water.parser.BufferedString in project h2o-3 by h2oai.

the class Word2VecModel method buildModelOutput.

void buildModelOutput(Word2VecModelInfo modelInfo) {
    IcedHashMapGeneric<BufferedString, Integer> vocab = ((Vocabulary) DKV.getGet(modelInfo._vocabKey))._data;
    BufferedString[] words = new BufferedString[vocab.size()];
    for (BufferedString str : vocab.keySet()) words[vocab.get(str)] = str;
    _output._vecSize = _parms._vec_size;
    _output._vecs = modelInfo._syn0;
    _output._words = words;
    _output._vocab = vocab;
}