Search in sources :

Example 11 with StringObject

use of org.apache.sysml.runtime.instructions.cp.StringObject in project 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;
}
Also used : MatrixBlock(org.apache.sysml.runtime.matrix.data.MatrixBlock) DoubleObject(org.apache.sysml.runtime.instructions.cp.DoubleObject) URL(java.net.URL) RDD(org.apache.spark.rdd.RDD) JavaRDD(org.apache.spark.api.java.JavaRDD) JavaPairRDD(org.apache.spark.api.java.JavaPairRDD) IntObject(org.apache.sysml.runtime.instructions.cp.IntObject) FrameBlock(org.apache.sysml.runtime.matrix.data.FrameBlock) JavaPairRDD(org.apache.spark.api.java.JavaPairRDD) StringObject(org.apache.sysml.runtime.instructions.cp.StringObject) Dataset(org.apache.spark.sql.Dataset) JavaRDD(org.apache.spark.api.java.JavaRDD) MatrixObject(org.apache.sysml.runtime.controlprogram.caching.MatrixObject) DoubleObject(org.apache.sysml.runtime.instructions.cp.DoubleObject) FrameObject(org.apache.sysml.runtime.controlprogram.caching.FrameObject) BooleanObject(org.apache.sysml.runtime.instructions.cp.BooleanObject) IntObject(org.apache.sysml.runtime.instructions.cp.IntObject) StringObject(org.apache.sysml.runtime.instructions.cp.StringObject) Row(org.apache.spark.sql.Row) BooleanObject(org.apache.sysml.runtime.instructions.cp.BooleanObject)

Aggregations

BooleanObject (org.apache.sysml.runtime.instructions.cp.BooleanObject)11 DoubleObject (org.apache.sysml.runtime.instructions.cp.DoubleObject)11 IntObject (org.apache.sysml.runtime.instructions.cp.IntObject)11 StringObject (org.apache.sysml.runtime.instructions.cp.StringObject)11 DMLRuntimeException (org.apache.sysml.runtime.DMLRuntimeException)7 MatrixObject (org.apache.sysml.runtime.controlprogram.caching.MatrixObject)7 ScalarObject (org.apache.sysml.runtime.instructions.cp.ScalarObject)7 DataType (org.apache.sysml.parser.Expression.DataType)4 ValueType (org.apache.sysml.parser.Expression.ValueType)4 Data (org.apache.sysml.runtime.instructions.cp.Data)4 StringTokenizer (java.util.StringTokenizer)3 URL (java.net.URL)2 JavaPairRDD (org.apache.spark.api.java.JavaPairRDD)2 JavaRDD (org.apache.spark.api.java.JavaRDD)2 RDD (org.apache.spark.rdd.RDD)2 Dataset (org.apache.spark.sql.Dataset)2 Row (org.apache.spark.sql.Row)2 DataIdentifier (org.apache.sysml.parser.DataIdentifier)2 VariableSet (org.apache.sysml.parser.VariableSet)2 PDataPartitionFormat (org.apache.sysml.runtime.controlprogram.ParForProgramBlock.PDataPartitionFormat)2