Examples with ParquetFileReader org.apache.parquet.hadoop.ParquetFileReader used on opensource projects

Example 11 with ParquetFileReader

use of org.apache.parquet.hadoop.ParquetFileReader in project ignite by apache.

the class SparkModelParser method loadLinearSVMModel.

/**
 * Load SVM model.
 *
 * @param pathToMdl Path to model.
 * @param learningEnvironment Learning environment.
 */
private static Model loadLinearSVMModel(String pathToMdl, LearningEnvironment learningEnvironment) {
    Vector coefficients = null;
    double interceptor = 0;
    try (ParquetFileReader r = ParquetFileReader.open(HadoopInputFile.fromPath(new Path(pathToMdl), new Configuration()))) {
        PageReadStore pages;
        final MessageType schema = r.getFooter().getFileMetaData().getSchema();
        final MessageColumnIO colIO = new ColumnIOFactory().getColumnIO(schema);
        while (null != (pages = r.readNextRowGroup())) {
            final long rows = pages.getRowCount();
            final RecordReader recordReader = colIO.getRecordReader(pages, new GroupRecordConverter(schema));
            for (int i = 0; i < rows; i++) {
                final SimpleGroup g = (SimpleGroup) recordReader.read();
                interceptor = readSVMInterceptor(g);
                coefficients = readSVMCoefficients(g);
            }
        }
    } catch (IOException e) {
        String msg = "Error reading parquet file: " + e.getMessage();
        learningEnvironment.logger().log(MLLogger.VerboseLevel.HIGH, msg);
        e.printStackTrace();
    }
    return new SVMLinearClassificationModel(coefficients, interceptor);
}

Example 12 with ParquetFileReader

use of org.apache.parquet.hadoop.ParquetFileReader in project ignite by apache.

the class SparkModelParser method loadDecisionTreeModel.

/**
 * Load Decision Tree model.
 *
 * @param pathToMdl Path to model.
 * @param learningEnvironment Learning environment.
 */
private static Model loadDecisionTreeModel(String pathToMdl, LearningEnvironment learningEnvironment) {
    try (ParquetFileReader r = ParquetFileReader.open(HadoopInputFile.fromPath(new Path(pathToMdl), new Configuration()))) {
        PageReadStore pages;
        final MessageType schema = r.getFooter().getFileMetaData().getSchema();
        final MessageColumnIO colIO = new ColumnIOFactory().getColumnIO(schema);
        final Map<Integer, NodeData> nodes = new TreeMap<>();
        while (null != (pages = r.readNextRowGroup())) {
            final long rows = pages.getRowCount();
            final RecordReader recordReader = colIO.getRecordReader(pages, new GroupRecordConverter(schema));
            for (int i = 0; i < rows; i++) {
                final SimpleGroup g = (SimpleGroup) recordReader.read();
                NodeData nodeData = extractNodeDataFromParquetRow(g);
                nodes.put(nodeData.id, nodeData);
            }
        }
        return buildDecisionTreeModel(nodes);
    } catch (IOException e) {
        String msg = "Error reading parquet file: " + e.getMessage();
        learningEnvironment.logger().log(MLLogger.VerboseLevel.HIGH, msg);
        e.printStackTrace();
    }
    return null;
}

Example 13 with ParquetFileReader

use of org.apache.parquet.hadoop.ParquetFileReader in project ignite by apache.

the class SparkModelParser method loadLogRegModel.

/**
 * Load logistic regression model.
 *
 * @param pathToMdl Path to model.
 * @param learningEnvironment Learning environment.
 */
private static Model loadLogRegModel(String pathToMdl, LearningEnvironment learningEnvironment) {
    Vector coefficients = null;
    double interceptor = 0;
    try (ParquetFileReader r = ParquetFileReader.open(HadoopInputFile.fromPath(new Path(pathToMdl), new Configuration()))) {
        PageReadStore pages;
        final MessageType schema = r.getFooter().getFileMetaData().getSchema();
        final MessageColumnIO colIO = new ColumnIOFactory().getColumnIO(schema);
        while (null != (pages = r.readNextRowGroup())) {
            final long rows = pages.getRowCount();
            final RecordReader recordReader = colIO.getRecordReader(pages, new GroupRecordConverter(schema));
            for (int i = 0; i < rows; i++) {
                final SimpleGroup g = (SimpleGroup) recordReader.read();
                interceptor = readInterceptor(g);
                coefficients = readCoefficients(g);
            }
        }
    } catch (IOException e) {
        String msg = "Error reading parquet file: " + e.getMessage();
        learningEnvironment.logger().log(MLLogger.VerboseLevel.HIGH, msg);
        e.printStackTrace();
    }
    return new LogisticRegressionModel(coefficients, interceptor);
}

Example 14 with ParquetFileReader

use of org.apache.parquet.hadoop.ParquetFileReader in project ignite by apache.

the class SparkModelParser method loadLinRegModel.

/**
 * Load linear regression model.
 *
 * @param pathToMdl Path to model.
 * @param learningEnvironment Learning environment.
 */
private static Model loadLinRegModel(String pathToMdl, LearningEnvironment learningEnvironment) {
    Vector coefficients = null;
    double interceptor = 0;
    try (ParquetFileReader r = ParquetFileReader.open(HadoopInputFile.fromPath(new Path(pathToMdl), new Configuration()))) {
        PageReadStore pages;
        final MessageType schema = r.getFooter().getFileMetaData().getSchema();
        final MessageColumnIO colIO = new ColumnIOFactory().getColumnIO(schema);
        while (null != (pages = r.readNextRowGroup())) {
            final long rows = pages.getRowCount();
            final RecordReader recordReader = colIO.getRecordReader(pages, new GroupRecordConverter(schema));
            for (int i = 0; i < rows; i++) {
                final SimpleGroup g = (SimpleGroup) recordReader.read();
                interceptor = readLinRegInterceptor(g);
                coefficients = readLinRegCoefficients(g);
            }
        }
    } catch (IOException e) {
        String msg = "Error reading parquet file: " + e.getMessage();
        learningEnvironment.logger().log(MLLogger.VerboseLevel.HIGH, msg);
        e.printStackTrace();
    }
    return new LinearRegressionModel(coefficients, interceptor);
}

Example 15 with ParquetFileReader

use of org.apache.parquet.hadoop.ParquetFileReader in project ignite by apache.

the class SparkModelParser method parseTreesForRandomForestAlgorithm.

/**
 * Parse trees from file for common Random Forest ensemble.
 *
 * @param pathToMdl Path to model.
 * @param learningEnvironment Learning environment.
 */
private static List<IgniteModel<Vector, Double>> parseTreesForRandomForestAlgorithm(String pathToMdl, LearningEnvironment learningEnvironment) {
    try (ParquetFileReader r = ParquetFileReader.open(HadoopInputFile.fromPath(new Path(pathToMdl), new Configuration()))) {
        PageReadStore pages;
        final MessageType schema = r.getFooter().getFileMetaData().getSchema();
        final MessageColumnIO colIO = new ColumnIOFactory().getColumnIO(schema);
        final Map<Integer, TreeMap<Integer, NodeData>> nodesByTreeId = new TreeMap<>();
        while (null != (pages = r.readNextRowGroup())) {
            final long rows = pages.getRowCount();
            final RecordReader recordReader = colIO.getRecordReader(pages, new GroupRecordConverter(schema));
            for (int i = 0; i < rows; i++) {
                final SimpleGroup g = (SimpleGroup) recordReader.read();
                final int treeID = g.getInteger(0, 0);
                final SimpleGroup nodeDataGroup = (SimpleGroup) g.getGroup(1, 0);
                NodeData nodeData = extractNodeDataFromParquetRow(nodeDataGroup);
                if (nodesByTreeId.containsKey(treeID)) {
                    Map<Integer, NodeData> nodesByNodeId = nodesByTreeId.get(treeID);
                    nodesByNodeId.put(nodeData.id, nodeData);
                } else {
                    TreeMap<Integer, NodeData> nodesByNodeId = new TreeMap<>();
                    nodesByNodeId.put(nodeData.id, nodeData);
                    nodesByTreeId.put(treeID, nodesByNodeId);
                }
            }
        }
        List<IgniteModel<Vector, Double>> models = new ArrayList<>();
        nodesByTreeId.forEach((key, nodes) -> models.add(buildDecisionTreeModel(nodes)));
        return models;
    } catch (IOException e) {
        String msg = "Error reading parquet file: " + e.getMessage();
        learningEnvironment.logger().log(MLLogger.VerboseLevel.HIGH, msg);
        e.printStackTrace();
    }
    return null;
}