private static DataSet<Point> getPointDataSet(ParameterTool params, ExecutionEnvironment env) { DataSet<Point> points; if (params.has("points")) { // read points from CSV file points = env.readCsvFile(params.get("points")) .fieldDelimiter(" ") .pojoType(Point.class, "x", "y"); } else { System.out.println("Executing K-Means example with default point data set."); System.out.println("Use --points to specify file input."); points = KMeansData.getDefaultPointDataSet(env); } return points; }
private static DataSet<Centroid> getCentroidDataSet(ParameterTool params, ExecutionEnvironment env) { DataSet<Centroid> centroids; if (params.has("centroids")) { centroids = env.readCsvFile(params.get("centroids")) .fieldDelimiter(" ") .pojoType(Centroid.class, "id", "x", "y"); } else { System.out.println("Executing K-Means example with default centroid data set."); System.out.println("Use --centroids to specify file input."); centroids = KMeansData.getDefaultCentroidDataSet(env); } return centroids; }
@SuppressWarnings("unchecked") private static DataSet<StringTriple> getDataSet(ExecutionEnvironment env, ParameterTool params) { if (params.has("input")) { return env.readCsvFile(params.get("input")) .fieldDelimiter(";") .pojoType(StringTriple.class); } else { System.out.println("Executing EmptyFieldsCountAccumulator example with default input data set."); System.out.println("Use --input to specify file input."); return env.fromCollection(getExampleInputTuples()); } }
@Test(expected = NullPointerException.class) public void testPOJOTypeWithoutFieldsOrder() throws Exception { final String inputData = ""; final String dataPath = createInputData(inputData); final ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment(); env.readCsvFile(dataPath).pojoType(POJOItem.class, null); }
@Test public void testPOJOType() throws Exception { final String inputData = "ABC,2.20,3\nDEF,5.1,5\nDEF,3.30,1\nGHI,3.30,10"; final String dataPath = createInputData(inputData); final ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment(); DataSet<POJOItem> data = env.readCsvFile(dataPath).pojoType(POJOItem.class, new String[]{"f1", "f3", "f2"}); List<POJOItem> result = data.collect(); expected = "ABC,3,2.20\nDEF,5,5.10\nDEF,1,3.30\nGHI,10,3.30"; compareResultAsText(result, expected); }
@Test public void testPOJOTypeWithFieldsOrder() throws Exception { final String inputData = "2.20,ABC,3\n5.1,DEF,5\n3.30,DEF,1\n3.30,GHI,10"; final String dataPath = createInputData(inputData); final ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment(); DataSet<POJOItem> data = env.readCsvFile(dataPath).pojoType(POJOItem.class, new String[]{"f3", "f1", "f2"}); List<POJOItem> result = data.collect(); expected = "ABC,3,2.20\nDEF,5,5.10\nDEF,1,3.30\nGHI,10,3.30"; compareResultAsText(result, expected); }
@Test public void testPOJOTypeWithFieldsOrderAndFieldsSelection() throws Exception { final String inputData = "3,2.20,ABC\n5,5.1,DEF\n1,3.30,DEF\n10,3.30,GHI"; final String dataPath = createInputData(inputData); final ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment(); DataSet<POJOItem> data = env.readCsvFile(dataPath).includeFields(true, false, true).pojoType(POJOItem.class, new String[]{"f2", "f1"}); List<POJOItem> result = data.collect(); expected = "ABC,3,0.00\nDEF,5,0.00\nDEF,1,0.00\nGHI,10,0.00"; compareResultAsText(result, expected); }
.fieldDelimiter(" ") .includeFields(true, true) .pojoType(Data.class); } else { System.out.println("Executing LinearRegression example with default input data set.");
private static DataSet<Point> getPointDataSet(ParameterTool params, ExecutionEnvironment env) { DataSet<Point> points; if (params.has("points")) { // read points from CSV file points = env.readCsvFile(params.get("points")) .fieldDelimiter(" ") .pojoType(Point.class, "x", "y"); } else { System.out.println("Executing K-Means example with default point data set."); System.out.println("Use --points to specify file input."); points = KMeansData.getDefaultPointDataSet(env); } return points; }
private static DataSet<Point> getPointDataSet(ParameterTool params, ExecutionEnvironment env) { DataSet<Point> points; if (params.has("points")) { // read points from CSV file points = env.readCsvFile(params.get("points")) .fieldDelimiter(" ") .pojoType(Point.class, "x", "y"); } else { System.out.println("Executing K-Means example with default point data set."); System.out.println("Use --points to specify file input."); points = KMeansData.getDefaultPointDataSet(env); } return points; }
private static DataSet<Centroid> getCentroidDataSet(ParameterTool params, ExecutionEnvironment env) { DataSet<Centroid> centroids; if (params.has("centroids")) { centroids = env.readCsvFile(params.get("centroids")) .fieldDelimiter(" ") .pojoType(Centroid.class, "id", "x", "y"); } else { System.out.println("Executing K-Means example with default centroid data set."); System.out.println("Use --centroids to specify file input."); centroids = KMeansData.getDefaultCentroidDataSet(env); } return centroids; }
@SuppressWarnings("unchecked") private static DataSet<StringTriple> getDataSet(ExecutionEnvironment env, ParameterTool params) { if (params.has("input")) { return env.readCsvFile(params.get("input")) .fieldDelimiter(";") .pojoType(StringTriple.class); } else { System.out.println("Executing EmptyFieldsCountAccumulator example with default input data set."); System.out.println("Use --input to specify file input."); return env.fromCollection(getExampleInputTuples()); } }
private static DataSet<Centroid> getCentroidDataSet(ParameterTool params, ExecutionEnvironment env) { DataSet<Centroid> centroids; if (params.has("centroids")) { centroids = env.readCsvFile(params.get("centroids")) .fieldDelimiter(" ") .pojoType(Centroid.class, "id", "x", "y"); } else { System.out.println("Executing K-Means example with default centroid data set."); System.out.println("Use --centroids to specify file input."); centroids = KMeansData.getDefaultCentroidDataSet(env); } return centroids; }
private static DataSet<Centroid> getCentroidDataSet(ParameterTool params, ExecutionEnvironment env) { DataSet<Centroid> centroids; if (params.has("centroids")) { centroids = env.readCsvFile(params.get("centroids")) .fieldDelimiter(" ") .pojoType(Centroid.class, "id", "x", "y"); } else { System.out.println("Executing K-Means example with default centroid data set."); System.out.println("Use --centroids to specify file input."); centroids = KMeansData.getDefaultCentroidDataSet(env); } return centroids; }
@SuppressWarnings("unchecked") private static DataSet<StringTriple> getDataSet(ExecutionEnvironment env, ParameterTool params) { if (params.has("input")) { return env.readCsvFile(params.get("input")) .fieldDelimiter(";") .pojoType(StringTriple.class); } else { System.out.println("Executing EmptyFieldsCountAccumulator example with default input data set."); System.out.println("Use --input to specify file input."); return env.fromCollection(getExampleInputTuples()); } }
private static DataSet<Point> getPointDataSet(ParameterTool params, ExecutionEnvironment env) { DataSet<Point> points; if (params.has("points")) { // read points from CSV file points = env.readCsvFile(params.get("points")) .fieldDelimiter(" ") .pojoType(Point.class, "x", "y"); } else { System.out.println("Executing K-Means example with default point data set."); System.out.println("Use --points to specify file input."); points = KMeansData.getDefaultPointDataSet(env); } return points; }
@SuppressWarnings("unchecked") private static DataSet<StringTriple> getDataSet(ExecutionEnvironment env, ParameterTool params) { if (params.has("input")) { return env.readCsvFile(params.get("input")) .fieldDelimiter(";") .pojoType(StringTriple.class); } else { System.out.println("Executing EmptyFieldsCountAccumulator example with default input data set."); System.out.println("Use --input to specify file input."); return env.fromCollection(getExampleInputTuples()); } }
.fieldDelimiter(" ") .includeFields(true, true) .pojoType(Data.class); } else { System.out.println("Executing LinearRegression example with default input data set.");
.fieldDelimiter(" ") .includeFields(true, true) .pojoType(Data.class); } else { System.out.println("Executing LinearRegression example with default input data set.");
.fieldDelimiter(" ") .includeFields(true, true) .pojoType(Data.class); } else { System.out.println("Executing LinearRegression example with default input data set.");