/** * Load Decision Tree model. * * @param pathToMdl Path to model. */ private static Model loadDecisionTreeModel(String pathToMdl) { 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) { System.out.println("Error reading parquet file."); e.printStackTrace(); } return null; }
/** * @param requestedSchema the requestedSchema we want to read/write * @param fileSchema the file schema (when reading it can be different from the requested schema) * @return the corresponding serializing/deserializing structure */ public MessageColumnIO getColumnIO(MessageType requestedSchema, MessageType fileSchema) { return getColumnIO(requestedSchema, fileSchema, true); }
public void initialize(ParquetFileReader reader, Configuration configuration) throws IOException { // initialize a ReadContext for this file this.reader = reader; FileMetaData parquetFileMetadata = reader.getFooter().getFileMetaData(); this.fileSchema = parquetFileMetadata.getSchema(); Map<String, String> fileMetadata = parquetFileMetadata.getKeyValueMetaData(); ReadSupport.ReadContext readContext = readSupport.init(new InitContext( configuration, toSetMultiMap(fileMetadata), fileSchema)); this.columnIOFactory = new ColumnIOFactory(parquetFileMetadata.getCreatedBy()); this.requestedSchema = readContext.getRequestedSchema(); this.columnCount = requestedSchema.getPaths().size(); this.recordConverter = readSupport.prepareForRead( configuration, fileMetadata, fileSchema, readContext); this.strictTypeChecking = configuration.getBoolean(STRICT_TYPE_CHECKING, true); this.total = reader.getRecordCount(); this.unmaterializableRecordCounter = new UnmaterializableRecordCounter(configuration, total); this.filterRecords = configuration.getBoolean(RECORD_FILTERING_ENABLED, true); reader.setRequestedSchema(requestedSchema); LOG.info("RecordReader initialized will read a total of {} records.", total); }
/** * @param requestedSchema the requestedSchema we want to read/write * @param fileSchema the file schema (when reading it can be different from the requested schema) * @return the corresponding serializing/deserializing structure */ public MessageColumnIO getColumnIO(MessageType requestedSchema, MessageType fileSchema) { return getColumnIO(requestedSchema, fileSchema, true); }
public void initialize(ParquetFileReader reader, Configuration configuration) throws IOException { // initialize a ReadContext for this file this.reader = reader; FileMetaData parquetFileMetadata = reader.getFooter().getFileMetaData(); this.fileSchema = parquetFileMetadata.getSchema(); Map<String, String> fileMetadata = parquetFileMetadata.getKeyValueMetaData(); ReadSupport.ReadContext readContext = readSupport.init(new InitContext( configuration, toSetMultiMap(fileMetadata), fileSchema)); this.columnIOFactory = new ColumnIOFactory(parquetFileMetadata.getCreatedBy()); this.requestedSchema = readContext.getRequestedSchema(); this.columnCount = requestedSchema.getPaths().size(); this.recordConverter = readSupport.prepareForRead( configuration, fileMetadata, fileSchema, readContext); this.strictTypeChecking = configuration.getBoolean(STRICT_TYPE_CHECKING, true); this.total = reader.getFilteredRecordCount(); this.unmaterializableRecordCounter = new UnmaterializableRecordCounter(configuration, total); this.filterRecords = configuration.getBoolean(RECORD_FILTERING_ENABLED, true); reader.setRequestedSchema(requestedSchema); LOG.info("RecordReader initialized will read a total of {} records.", total); }
final MessageColumnIO colIO = new ColumnIOFactory().getColumnIO(schema); final Map<Integer, TreeMap<Integer, NodeData>> nodesByTreeId = new TreeMap<>();
/** * @param schema the schema we want to read/write * @return the corresponding serializing/deserializing structure */ public MessageColumnIO getColumnIO(MessageType schema) { return this.getColumnIO(schema, schema); }
public void initialize(FileMetaData parquetFileMetadata, Path file, List<BlockMetaData> blocks, Configuration configuration) throws IOException { // initialize a ReadContext for this file Map<String, String> fileMetadata = parquetFileMetadata.getKeyValueMetaData(); ReadSupport.ReadContext readContext = readSupport.init(new InitContext( configuration, toSetMultiMap(fileMetadata), fileSchema)); this.columnIOFactory = new ColumnIOFactory(parquetFileMetadata.getCreatedBy()); this.requestedSchema = readContext.getRequestedSchema(); this.fileSchema = parquetFileMetadata.getSchema(); this.file = file; this.columnCount = requestedSchema.getPaths().size(); this.recordConverter = readSupport.prepareForRead( configuration, fileMetadata, fileSchema, readContext); this.strictTypeChecking = configuration.getBoolean(STRICT_TYPE_CHECKING, true); List<ColumnDescriptor> columns = requestedSchema.getColumns(); reader = new ParquetFileReader(configuration, parquetFileMetadata, file, blocks, columns); for (BlockMetaData block : blocks) { total += block.getRowCount(); } this.unmaterializableRecordCounter = new UnmaterializableRecordCounter(configuration, total); LOG.info("RecordReader initialized will read a total of " + total + " records."); }
PageReadStore pagesMetaData; final MessageType schema = r.getFooter().getFileMetaData().getSchema(); final MessageColumnIO colIO = new ColumnIOFactory().getColumnIO(schema); 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())) {
/** * @param schema the schema we want to read/write * @return the corresponding serializing/deserializing structure */ public MessageColumnIO getColumnIO(MessageType schema) { return this.getColumnIO(schema, schema); }
public void initialize(ParquetFileReader reader, ParquetReadOptions options) { // copy custom configuration to the Configuration passed to the ReadSupport Configuration conf = new Configuration(); if (options instanceof HadoopReadOptions) { conf = ((HadoopReadOptions) options).getConf(); } for (String property : options.getPropertyNames()) { conf.set(property, options.getProperty(property)); } // initialize a ReadContext for this file this.reader = reader; FileMetaData parquetFileMetadata = reader.getFooter().getFileMetaData(); this.fileSchema = parquetFileMetadata.getSchema(); Map<String, String> fileMetadata = parquetFileMetadata.getKeyValueMetaData(); ReadSupport.ReadContext readContext = readSupport.init(new InitContext(conf, toSetMultiMap(fileMetadata), fileSchema)); this.columnIOFactory = new ColumnIOFactory(parquetFileMetadata.getCreatedBy()); this.requestedSchema = readContext.getRequestedSchema(); this.columnCount = requestedSchema.getPaths().size(); this.recordConverter = readSupport.prepareForRead(conf, fileMetadata, fileSchema, readContext); this.strictTypeChecking = options.isEnabled(STRICT_TYPE_CHECKING, true); this.total = reader.getRecordCount(); this.unmaterializableRecordCounter = new UnmaterializableRecordCounter(options, total); this.filterRecords = options.useRecordFilter(); reader.setRequestedSchema(requestedSchema); LOG.info("RecordReader initialized will read a total of {} records.", total); }
/** * Load SVM model. * * @param pathToMdl Path to model. */ private static Model loadLinearSVMModel(String pathToMdl) { 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) { System.out.println("Error reading parquet file."); e.printStackTrace(); } return new SVMLinearClassificationModel(coefficients, interceptor); }
if (LOG.isInfoEnabled()) LOG.info("block read in memory in {} ms. row count = {}", timeSpentReading, pages.getRowCount()); LOG.debug("initializing Record assembly with requested schema {}", requestedSchema); MessageColumnIO columnIO = columnIOFactory.getColumnIO(requestedSchema, fileSchema, strictTypeChecking); recordReader = columnIO.getRecordReader(pages, recordConverter, filterRecords ? filter : FilterCompat.NOOP);
public void initialize(ParquetFileReader reader, ParquetReadOptions options) { // copy custom configuration to the Configuration passed to the ReadSupport Configuration conf = new Configuration(); if (options instanceof HadoopReadOptions) { conf = ((HadoopReadOptions) options).getConf(); } for (String property : options.getPropertyNames()) { conf.set(property, options.getProperty(property)); } // initialize a ReadContext for this file this.reader = reader; FileMetaData parquetFileMetadata = reader.getFooter().getFileMetaData(); this.fileSchema = parquetFileMetadata.getSchema(); Map<String, String> fileMetadata = parquetFileMetadata.getKeyValueMetaData(); ReadSupport.ReadContext readContext = readSupport.init(new InitContext(conf, toSetMultiMap(fileMetadata), fileSchema)); this.columnIOFactory = new ColumnIOFactory(parquetFileMetadata.getCreatedBy()); this.requestedSchema = readContext.getRequestedSchema(); this.columnCount = requestedSchema.getPaths().size(); this.recordConverter = readSupport.prepareForRead(conf, fileMetadata, fileSchema, readContext); this.strictTypeChecking = options.isEnabled(STRICT_TYPE_CHECKING, true); this.total = reader.getFilteredRecordCount(); this.unmaterializableRecordCounter = new UnmaterializableRecordCounter(options, total); this.filterRecords = options.useRecordFilter(); reader.setRequestedSchema(requestedSchema); LOG.info("RecordReader initialized will read a total of {} records.", total); }
/** * Load linear regression model. * * @param pathToMdl Path to model. */ private static Model loadLinRegModel(String pathToMdl) { 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) { System.out.println("Error reading parquet file."); e.printStackTrace(); } return new LinearRegressionModel(coefficients, interceptor); }
if (LOG.isInfoEnabled()) LOG.info("block read in memory in {} ms. row count = {}", timeSpentReading, pages.getRowCount()); LOG.debug("initializing Record assembly with requested schema {}", requestedSchema); MessageColumnIO columnIO = columnIOFactory.getColumnIO(requestedSchema, fileSchema, strictTypeChecking); recordReader = columnIO.getRecordReader(pages, recordConverter, filterRecords ? filter : FilterCompat.NOOP);
public void initialize(FileMetaData parquetFileMetadata, Path file, List<BlockMetaData> blocks, Configuration configuration) throws IOException { // initialize a ReadContext for this file Map<String, String> fileMetadata = parquetFileMetadata.getKeyValueMetaData(); ReadSupport.ReadContext readContext = readSupport.init(new InitContext( configuration, toSetMultiMap(fileMetadata), fileSchema)); this.columnIOFactory = new ColumnIOFactory(parquetFileMetadata.getCreatedBy()); this.requestedSchema = readContext.getRequestedSchema(); this.fileSchema = parquetFileMetadata.getSchema(); this.file = file; this.columnCount = requestedSchema.getPaths().size(); this.recordConverter = readSupport.prepareForRead( configuration, fileMetadata, fileSchema, readContext); this.strictTypeChecking = configuration.getBoolean(STRICT_TYPE_CHECKING, true); List<ColumnDescriptor> columns = requestedSchema.getColumns(); reader = new ParquetFileReader(configuration, parquetFileMetadata, file, blocks, columns); for (BlockMetaData block : blocks) { total += block.getRowCount(); } this.unmaterializableRecordCounter = new UnmaterializableRecordCounter(configuration, total); LOG.info("RecordReader initialized will read a total of " + total + " records."); }
/** * Load logistic regression model. * * @param pathToMdl Path to model. */ private static Model loadLogRegModel(String pathToMdl) { 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) { System.out.println("Error reading parquet file."); e.printStackTrace(); } return new LogisticRegressionModel(coefficients, interceptor); }
if (Log.INFO) LOG.info("block read in memory in " + timeSpentReading + " ms. row count = " + pages.getRowCount()); if (Log.DEBUG) LOG.debug("initializing Record assembly with requested schema " + requestedSchema); MessageColumnIO columnIO = columnIOFactory.getColumnIO(requestedSchema, fileSchema, strictTypeChecking); recordReader = columnIO.getRecordReader(pages, recordConverter, filter); startedAssemblingCurrentBlockAt = System.currentTimeMillis();
private static Model loadKMeansModel(String pathToMdl) { Vector[] centers = null; 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 int rows = (int)pages.getRowCount(); final RecordReader recordReader = colIO.getRecordReader(pages, new GroupRecordConverter(schema)); centers = new DenseVector[rows]; for (int i = 0; i < rows; i++) { final SimpleGroup g = (SimpleGroup)recordReader.read(); // final int clusterIdx = g.getInteger(0, 0); Group clusterCenterCoeff = g.getGroup(1, 0).getGroup(3, 0); final int amountOfCoefficients = clusterCenterCoeff.getFieldRepetitionCount(0); centers[i] = new DenseVector(amountOfCoefficients); for (int j = 0; j < amountOfCoefficients; j++) { double coefficient = clusterCenterCoeff.getGroup(0, j).getDouble(0, 0); centers[i].set(j, coefficient); } } } } catch (IOException e) { System.out.println("Error reading parquet file."); e.printStackTrace(); } return new KMeansModel(centers, new EuclideanDistance()); }