Examples with FrameBlock org.apache.sysml.runtime.matrix.data.FrameBlock used on opensource projects

Example 91 with FrameBlock

use of org.apache.sysml.runtime.matrix.data.FrameBlock in project incubator-systemml by apache.

the class MLContextConversionUtil method javaRDDStringIJVToFrameObject.

/**
 * Convert a {@code JavaRDD<String>} in IJV format to a {@code FrameObject}
 * . Note that metadata is required for IJV format.
 *
 * @param javaRDD
 *            the Java RDD of strings
 * @param frameMetadata
 *            frame metadata
 * @return the {@code JavaRDD<String>} converted to a {@code FrameObject}
 */
public static FrameObject javaRDDStringIJVToFrameObject(JavaRDD<String> javaRDD, FrameMetadata frameMetadata) {
    JavaPairRDD<LongWritable, Text> javaPairRDD = javaRDD.mapToPair(new ConvertStringToLongTextPair());
    MatrixCharacteristics mc = (frameMetadata != null) ? frameMetadata.asMatrixCharacteristics() : new MatrixCharacteristics();
    JavaPairRDD<LongWritable, Text> javaPairRDDText = javaPairRDD.mapToPair(new CopyTextInputFunction());
    FrameObject frameObject = new FrameObject(OptimizerUtils.getUniqueTempFileName(), new MetaDataFormat(mc, OutputInfo.BinaryBlockOutputInfo, InputInfo.BinaryBlockInputInfo), frameMetadata.getFrameSchema().getSchema().toArray(new ValueType[0]));
    JavaPairRDD<Long, FrameBlock> rdd;
    try {
        ValueType[] lschema = null;
        if (lschema == null)
            lschema = UtilFunctions.nCopies((int) mc.getCols(), ValueType.STRING);
        rdd = FrameRDDConverterUtils.textCellToBinaryBlock(jsc(), javaPairRDDText, mc, lschema);
    } catch (DMLRuntimeException e) {
        e.printStackTrace();
        return null;
    }
    frameObject.setRDDHandle(new RDDObject(rdd));
    return frameObject;
}

Example 92 with FrameBlock

use of org.apache.sysml.runtime.matrix.data.FrameBlock in project incubator-systemml by apache.

the class MLContextConversionUtil method frameObjectTo2DStringArray.

/**
 * Convert a {@code FrameObject} to a two-dimensional string array.
 *
 * @param frameObject
 *            the {@code FrameObject}
 * @return the {@code FrameObject} converted to a {@code String[][]}
 */
public static String[][] frameObjectTo2DStringArray(FrameObject frameObject) {
    FrameBlock fb = frameObject.acquireRead();
    String[][] frame = DataConverter.convertToStringFrame(fb);
    frameObject.release();
    return frame;
}

Example 93 with FrameBlock

use of org.apache.sysml.runtime.matrix.data.FrameBlock in project incubator-systemml by apache.

the class MLContextConversionUtil method frameObjectToListStringCSV.

/**
 * Convert a {@code FrameObject} to a {@code List<String>} in CSV format.
 *
 * @param frameObject
 *            the {@code FrameObject}
 * @param delimiter
 *            the delimiter
 * @return the {@code FrameObject} converted to a {@code List<String>}
 */
public static List<String> frameObjectToListStringCSV(FrameObject frameObject, String delimiter) {
    FrameBlock fb = frameObject.acquireRead();
    int rows = fb.getNumRows();
    int cols = fb.getNumColumns();
    List<String> list = new ArrayList<>();
    for (int i = 0; i < rows; i++) {
        StringBuilder sb = new StringBuilder();
        for (int j = 0; j < cols; j++) {
            if (j > 0) {
                sb.append(delimiter);
            }
            if (fb.get(i, j) != null) {
                sb.append(fb.get(i, j));
            }
        }
        list.add(sb.toString());
    }
    frameObject.release();
    return list;
}

Example 94 with FrameBlock

use of org.apache.sysml.runtime.matrix.data.FrameBlock in project incubator-systemml by apache.

the class MLContextConversionUtil method dataFrameToFrameObject.

/**
 * Convert a {@code DataFrame} to a {@code FrameObject}.
 *
 * @param dataFrame
 *            the Spark {@code DataFrame}
 * @param frameMetadata
 *            the frame metadata
 * @return the {@code DataFrame} frame converted to a converted to a
 *         {@code FrameObject}
 */
public static FrameObject dataFrameToFrameObject(Dataset<Row> dataFrame, FrameMetadata frameMetadata) {
    try {
        // setup meta data and java spark context
        if (frameMetadata == null)
            frameMetadata = new FrameMetadata();
        determineFrameFormatIfNeeded(dataFrame, frameMetadata);
        boolean containsID = isDataFrameWithIDColumn(frameMetadata);
        MatrixCharacteristics mc = frameMetadata.asMatrixCharacteristics();
        if (mc == null)
            mc = new MatrixCharacteristics();
        // convert data frame and obtain column names / schema
        // TODO extend frame schema by column names (right now dropped)
        Pair<String[], ValueType[]> ret = new Pair<>();
        JavaPairRDD<Long, FrameBlock> binaryBlock = FrameRDDConverterUtils.dataFrameToBinaryBlock(jsc(), dataFrame, mc, containsID, ret);
        frameMetadata.setFrameSchema(new FrameSchema(Arrays.asList(ret.getValue())));
        // required due to meta
        frameMetadata.setMatrixCharacteristics(mc);
        return MLContextConversionUtil.binaryBlocksToFrameObject(binaryBlock, frameMetadata);
    } catch (DMLRuntimeException e) {
        throw new MLContextException("Exception converting DataFrame to FrameObject", e);
    }
}

Example 95 with FrameBlock

use of org.apache.sysml.runtime.matrix.data.FrameBlock in project incubator-systemml by apache.

the class MLContextUtil method convertInputType.

/**
 * Convert input types to internal SystemML representations
 *
 * @param parameterName
 *            The name of the input parameter
 * @param parameterValue
 *            The value of the input parameter
 * @param metadata
 *            matrix/frame metadata
 * @return input in SystemML data representation
 */
public static Data convertInputType(String parameterName, Object parameterValue, Metadata metadata) {
    String name = parameterName;
    Object value = parameterValue;
    boolean hasMetadata = (metadata != null) ? true : false;
    boolean hasMatrixMetadata = hasMetadata && (metadata instanceof MatrixMetadata) ? true : false;
    boolean hasFrameMetadata = hasMetadata && (metadata instanceof FrameMetadata) ? true : false;
    if (name == null) {
        throw new MLContextException("Input parameter name is null");
    } else if (value == null) {
        throw new MLContextException("Input parameter value is null for: " + parameterName);
    } else if (value instanceof JavaRDD<?>) {
        @SuppressWarnings("unchecked") JavaRDD<String> javaRDD = (JavaRDD<String>) value;
        if (hasMatrixMetadata) {
            MatrixMetadata matrixMetadata = (MatrixMetadata) metadata;
            if (matrixMetadata.getMatrixFormat() == MatrixFormat.IJV) {
                return MLContextConversionUtil.javaRDDStringIJVToMatrixObject(javaRDD, matrixMetadata);
            } else {
                return MLContextConversionUtil.javaRDDStringCSVToMatrixObject(javaRDD, matrixMetadata);
            }
        } else if (hasFrameMetadata) {
            FrameMetadata frameMetadata = (FrameMetadata) metadata;
            if (frameMetadata.getFrameFormat() == FrameFormat.IJV) {
                return MLContextConversionUtil.javaRDDStringIJVToFrameObject(javaRDD, frameMetadata);
            } else {
                return MLContextConversionUtil.javaRDDStringCSVToFrameObject(javaRDD, frameMetadata);
            }
        } else if (!hasMetadata) {
            String firstLine = javaRDD.first();
            boolean isAllNumbers = isCSVLineAllNumbers(firstLine);
            if (isAllNumbers) {
                return MLContextConversionUtil.javaRDDStringCSVToMatrixObject(javaRDD);
            } else {
                return MLContextConversionUtil.javaRDDStringCSVToFrameObject(javaRDD);
            }
        }
    } else if (value instanceof RDD<?>) {
        @SuppressWarnings("unchecked") RDD<String> rdd = (RDD<String>) value;
        if (hasMatrixMetadata) {
            MatrixMetadata matrixMetadata = (MatrixMetadata) metadata;
            if (matrixMetadata.getMatrixFormat() == MatrixFormat.IJV) {
                return MLContextConversionUtil.rddStringIJVToMatrixObject(rdd, matrixMetadata);
            } else {
                return MLContextConversionUtil.rddStringCSVToMatrixObject(rdd, matrixMetadata);
            }
        } else if (hasFrameMetadata) {
            FrameMetadata frameMetadata = (FrameMetadata) metadata;
            if (frameMetadata.getFrameFormat() == FrameFormat.IJV) {
                return MLContextConversionUtil.rddStringIJVToFrameObject(rdd, frameMetadata);
            } else {
                return MLContextConversionUtil.rddStringCSVToFrameObject(rdd, frameMetadata);
            }
        } else if (!hasMetadata) {
            String firstLine = rdd.first();
            boolean isAllNumbers = isCSVLineAllNumbers(firstLine);
            if (isAllNumbers) {
                return MLContextConversionUtil.rddStringCSVToMatrixObject(rdd);
            } else {
                return MLContextConversionUtil.rddStringCSVToFrameObject(rdd);
            }
        }
    } else if (value instanceof MatrixBlock) {
        MatrixBlock matrixBlock = (MatrixBlock) value;
        return MLContextConversionUtil.matrixBlockToMatrixObject(name, matrixBlock, (MatrixMetadata) metadata);
    } else if (value instanceof FrameBlock) {
        FrameBlock frameBlock = (FrameBlock) value;
        return MLContextConversionUtil.frameBlockToFrameObject(name, frameBlock, (FrameMetadata) metadata);
    } else if (value instanceof Dataset<?>) {
        @SuppressWarnings("unchecked") Dataset<Row> dataFrame = (Dataset<Row>) value;
        dataFrame = MLUtils.convertVectorColumnsToML(dataFrame);
        if (hasMatrixMetadata) {
            return MLContextConversionUtil.dataFrameToMatrixObject(dataFrame, (MatrixMetadata) metadata);
        } else if (hasFrameMetadata) {
            return MLContextConversionUtil.dataFrameToFrameObject(dataFrame, (FrameMetadata) metadata);
        } else if (!hasMetadata) {
            boolean looksLikeMatrix = doesDataFrameLookLikeMatrix(dataFrame);
            if (looksLikeMatrix) {
                return MLContextConversionUtil.dataFrameToMatrixObject(dataFrame);
            } else {
                return MLContextConversionUtil.dataFrameToFrameObject(dataFrame);
            }
        }
    } else if (value instanceof Matrix) {
        Matrix matrix = (Matrix) value;
        if ((matrix.hasBinaryBlocks()) && (!matrix.hasMatrixObject())) {
            if (metadata == null) {
                metadata = matrix.getMatrixMetadata();
            }
            JavaPairRDD<MatrixIndexes, MatrixBlock> binaryBlocks = matrix.toBinaryBlocks();
            return MLContextConversionUtil.binaryBlocksToMatrixObject(binaryBlocks, (MatrixMetadata) metadata);
        } else {
            return matrix.toMatrixObject();
        }
    } else if (value instanceof Frame) {
        Frame frame = (Frame) value;
        if ((frame.hasBinaryBlocks()) && (!frame.hasFrameObject())) {
            if (metadata == null) {
                metadata = frame.getFrameMetadata();
            }
            JavaPairRDD<Long, FrameBlock> binaryBlocks = frame.toBinaryBlocks();
            return MLContextConversionUtil.binaryBlocksToFrameObject(binaryBlocks, (FrameMetadata) metadata);
        } else {
            return frame.toFrameObject();
        }
    } else if (value instanceof double[][]) {
        double[][] doubleMatrix = (double[][]) value;
        return MLContextConversionUtil.doubleMatrixToMatrixObject(name, doubleMatrix, (MatrixMetadata) metadata);
    } else if (value instanceof URL) {
        URL url = (URL) value;
        return MLContextConversionUtil.urlToMatrixObject(url, (MatrixMetadata) metadata);
    } else if (value instanceof Integer) {
        return new IntObject((Integer) value);
    } else if (value instanceof Double) {
        return new DoubleObject((Double) value);
    } else if (value instanceof String) {
        return new StringObject((String) value);
    } else if (value instanceof Boolean) {
        return new BooleanObject((Boolean) value);
    }
    return null;
}