Examples with VectorUDT org.apache.spark.ml.linalg.VectorUDT used on opensource projects

Example 6 with VectorUDT

use of org.apache.spark.ml.linalg.VectorUDT in project incubator-systemml by apache.

the class MLContextTest method testDataFrameSumPYDMLVectorWithNoIDColumn.

@Test
public void testDataFrameSumPYDMLVectorWithNoIDColumn() {
    System.out.println("MLContextTest - DataFrame sum PYDML, vector with no ID column");
    List<Vector> list = new ArrayList<Vector>();
    list.add(Vectors.dense(1.0, 2.0, 3.0));
    list.add(Vectors.dense(4.0, 5.0, 6.0));
    list.add(Vectors.dense(7.0, 8.0, 9.0));
    JavaRDD<Vector> javaRddVector = sc.parallelize(list);
    JavaRDD<Row> javaRddRow = javaRddVector.map(new VectorRow());
    List<StructField> fields = new ArrayList<StructField>();
    fields.add(DataTypes.createStructField("C1", new VectorUDT(), true));
    StructType schema = DataTypes.createStructType(fields);
    Dataset<Row> dataFrame = spark.createDataFrame(javaRddRow, schema);
    MatrixMetadata mm = new MatrixMetadata(MatrixFormat.DF_VECTOR);
    Script script = pydml("print('sum: ' + sum(M))").in("M", dataFrame, mm);
    setExpectedStdOut("sum: 45.0");
    ml.execute(script);
}

Example 7 with VectorUDT

use of org.apache.spark.ml.linalg.VectorUDT in project incubator-systemml by apache.

the class MLContextTest method testDataFrameSumDMLVectorWithNoIDColumnNoFormatSpecified.

@Test
public void testDataFrameSumDMLVectorWithNoIDColumnNoFormatSpecified() {
    System.out.println("MLContextTest - DataFrame sum DML, vector with no ID column, no format specified");
    List<Vector> list = new ArrayList<Vector>();
    list.add(Vectors.dense(1.0, 2.0, 3.0));
    list.add(Vectors.dense(4.0, 5.0, 6.0));
    list.add(Vectors.dense(7.0, 8.0, 9.0));
    JavaRDD<Vector> javaRddVector = sc.parallelize(list);
    JavaRDD<Row> javaRddRow = javaRddVector.map(new VectorRow());
    List<StructField> fields = new ArrayList<StructField>();
    fields.add(DataTypes.createStructField("C1", new VectorUDT(), true));
    StructType schema = DataTypes.createStructType(fields);
    Dataset<Row> dataFrame = spark.createDataFrame(javaRddRow, schema);
    Script script = dml("print('sum: ' + sum(M));").in("M", dataFrame);
    setExpectedStdOut("sum: 45.0");
    ml.execute(script);
}

Example 8 with VectorUDT

use of org.apache.spark.ml.linalg.VectorUDT in project incubator-systemml by apache.

the class DataFrameVectorFrameConversionTest method createDataFrame.

@SuppressWarnings("resource")
private static Dataset<Row> createDataFrame(SparkSession sparkSession, MatrixBlock mb, boolean containsID, ValueType[] schema) {
    // create in-memory list of rows
    List<Row> list = new ArrayList<Row>();
    int off = (containsID ? 1 : 0);
    int clen = mb.getNumColumns() + off - colsVector + 1;
    for (int i = 0; i < mb.getNumRows(); i++) {
        Object[] row = new Object[clen];
        if (containsID)
            row[0] = (double) i + 1;
        for (int j = 0, j2 = 0; j < mb.getNumColumns(); j++, j2++) {
            if (schema[j2] != ValueType.OBJECT) {
                row[j2 + off] = UtilFunctions.doubleToObject(schema[j2], mb.quickGetValue(i, j));
            } else {
                double[] tmp = DataConverter.convertToDoubleVector(mb.slice(i, i, j, j + colsVector - 1, new MatrixBlock()), false);
                row[j2 + off] = new DenseVector(tmp);
                j += colsVector - 1;
            }
        }
        list.add(RowFactory.create(row));
    }
    // create data frame schema
    List<StructField> fields = new ArrayList<StructField>();
    if (containsID)
        fields.add(DataTypes.createStructField(RDDConverterUtils.DF_ID_COLUMN, DataTypes.DoubleType, true));
    for (int j = 0; j < schema.length; j++) {
        DataType dt = null;
        switch(schema[j]) {
            case STRING:
                dt = DataTypes.StringType;
                break;
            case DOUBLE:
                dt = DataTypes.DoubleType;
                break;
            case INT:
                dt = DataTypes.LongType;
                break;
            case OBJECT:
                dt = new VectorUDT();
                break;
            default:
                throw new RuntimeException("Unsupported value type.");
        }
        fields.add(DataTypes.createStructField("C" + (j + 1), dt, true));
    }
    StructType dfSchema = DataTypes.createStructType(fields);
    // create rdd and data frame
    JavaSparkContext sc = new JavaSparkContext(sparkSession.sparkContext());
    JavaRDD<Row> rowRDD = sc.parallelize(list);
    return sparkSession.createDataFrame(rowRDD, dfSchema);
}

Example 9 with VectorUDT

use of org.apache.spark.ml.linalg.VectorUDT in project incubator-systemml by apache.

the class DataFrameVectorScriptTest method createDataFrame.

@SuppressWarnings("resource")
private static Dataset<Row> createDataFrame(SparkSession sparkSession, MatrixBlock mb, boolean containsID, ValueType[] schema) {
    // create in-memory list of rows
    List<Row> list = new ArrayList<Row>();
    int off = (containsID ? 1 : 0);
    int clen = mb.getNumColumns() + off - colsVector + 1;
    for (int i = 0; i < mb.getNumRows(); i++) {
        Object[] row = new Object[clen];
        if (containsID)
            row[0] = (double) i + 1;
        for (int j = 0, j2 = 0; j < mb.getNumColumns(); j++, j2++) {
            if (schema[j2] != ValueType.OBJECT) {
                row[j2 + off] = UtilFunctions.doubleToObject(schema[j2], mb.quickGetValue(i, j));
            } else {
                double[] tmp = DataConverter.convertToDoubleVector(mb.slice(i, i, j, j + colsVector - 1, new MatrixBlock()), false);
                row[j2 + off] = new DenseVector(tmp);
                j += colsVector - 1;
            }
        }
        list.add(RowFactory.create(row));
    }
    // create data frame schema
    List<StructField> fields = new ArrayList<StructField>();
    if (containsID)
        fields.add(DataTypes.createStructField(RDDConverterUtils.DF_ID_COLUMN, DataTypes.DoubleType, true));
    for (int j = 0; j < schema.length; j++) {
        DataType dt = null;
        switch(schema[j]) {
            case STRING:
                dt = DataTypes.StringType;
                break;
            case DOUBLE:
                dt = DataTypes.DoubleType;
                break;
            case INT:
                dt = DataTypes.LongType;
                break;
            case OBJECT:
                dt = new VectorUDT();
                break;
            default:
                throw new RuntimeException("Unsupported value type.");
        }
        fields.add(DataTypes.createStructField("C" + (j + 1), dt, true));
    }
    StructType dfSchema = DataTypes.createStructType(fields);
    // create rdd and data frame
    JavaSparkContext sc = new JavaSparkContext(sparkSession.sparkContext());
    JavaRDD<Row> rowRDD = sc.parallelize(list);
    return sparkSession.createDataFrame(rowRDD, dfSchema);
}

Example 10 with VectorUDT

use of org.apache.spark.ml.linalg.VectorUDT in project net.jgp.labs.spark by jgperrin.

the class SimplePredictionFromTextFile method start.

private void start() {
    SparkSession spark = SparkSession.builder().appName("Simple prediction from Text File").master("local").getOrCreate();
    spark.udf().register("vectorBuilder", new VectorBuilder(), new VectorUDT());
    String filename = "data/tuple-data-file.csv";
    StructType schema = new StructType(new StructField[] { new StructField("_c0", DataTypes.DoubleType, false, Metadata.empty()), new StructField("_c1", DataTypes.DoubleType, false, Metadata.empty()), new StructField("features", new VectorUDT(), true, Metadata.empty()) });
    Dataset<Row> df = spark.read().format("csv").schema(schema).option("header", "false").load(filename);
    df = df.withColumn("valuefeatures", df.col("_c0")).drop("_c0");
    df = df.withColumn("label", df.col("_c1")).drop("_c1");
    df.printSchema();
    df = df.withColumn("features", callUDF("vectorBuilder", df.col("valuefeatures")));
    df.printSchema();
    df.show();
    // .setRegParam(1).setElasticNetParam(1);
    LinearRegression lr = new LinearRegression().setMaxIter(20);
    // Fit the model to the data.
    LinearRegressionModel model = lr.fit(df);
    // Given a dataset, predict each point's label, and show the results.
    model.transform(df).show();
    LinearRegressionTrainingSummary trainingSummary = model.summary();
    System.out.println("numIterations: " + trainingSummary.totalIterations());
    System.out.println("objectiveHistory: " + Vectors.dense(trainingSummary.objectiveHistory()));
    trainingSummary.residuals().show();
    System.out.println("RMSE: " + trainingSummary.rootMeanSquaredError());
    System.out.println("r2: " + trainingSummary.r2());
    double intercept = model.intercept();
    System.out.println("Interesection: " + intercept);
    double regParam = model.getRegParam();
    System.out.println("Regression parameter: " + regParam);
    double tol = model.getTol();
    System.out.println("Tol: " + tol);
    Double feature = 7.0;
    Vector features = Vectors.dense(feature);
    double p = model.predict(features);
    System.out.println("Prediction for feature " + feature + " is " + p);
    System.out.println(8 * regParam + intercept);
}