Updates in Python classes and 'assessModel' python phase

client/src/main/java/zingg/client/Arguments.java

@@ -18,7 +18,9 @@
 import com.fasterxml.jackson.annotation.JsonSetter;
 import com.fasterxml.jackson.core.JsonParser;
 import com.fasterxml.jackson.databind.ObjectMapper;
+import com.fasterxml.jackson.databind.SerializationFeature;
 import com.fasterxml.jackson.module.scala.DefaultScalaModule;
+import com.fasterxml.jackson.core.json.JsonWriteFeature;
 
 import org.apache.commons.logging.Log;
 import org.apache.commons.logging.LogFactory;
@@ -171,10 +173,33 @@ public static final Arguments createArgumentsFromJSON(String filePath, String ph
 		} catch (Exception e) { 
 			//e.printStackTrace();
 			throw new ZinggClientException("Unable to parse the configuration at " + filePath + 
-					". The error is " + e.getMessage());
+					". The error is " + e.getMessage(), e);
 		}
 	}
 
+	/**
+	 * Write arguments to a json file
+	 * 
+	 * @param filePath
+	 *            json file where arguments shall be written to
+	 * @return Arguments object
+	 * @throws ZinggClientException
+	 *             in case there is an error in writing to file
+	 */
+	public static final void writeArgumentsToJSON(String filePath, Arguments args)
+			throws ZinggClientException {
+		try {
+			ObjectMapper mapper = new ObjectMapper();
+			mapper.enable(SerializationFeature.INDENT_OUTPUT);
+			mapper.getFactory().configure(JsonWriteFeature.QUOTE_FIELD_NAMES.mappedFeature(),true);
+			LOG.warn("Arguments are written to file: " + filePath);		
+			mapper.writeValue(new File(filePath), args);
+		} catch (Exception e) { 
+			throw new ZinggClientException("Unable to write the configuration to " + filePath + 
+					". The error is " + e.getMessage(), e);
+		}
+	}
+
 	public static void checkValid(Arguments args, String phase) throws ZinggClientException {
 		if (phase.equals("train") || phase.equals("match") || phase.equals("trainMatch") || phase.equals("link")) {
 			checkIsValid(args);
@@ -635,6 +660,7 @@ public void setBlockSize(long blockSize){
 		this.blockSize = blockSize;
 	}
 
+	@JsonIgnore
 	public String[] getPipeNames() {
 		Pipe[] input = this.getData();
 		String[] sourceNames = new String[input.length];

client/src/main/java/zingg/client/Client.java

@@ -253,5 +253,8 @@ public Dataset<Row> getMarkedRecords() {
 		return zingg.getMarkedRecords();
 	}
 
-
+	public Dataset<Row> getUnMarkedRecords() {
+		return zingg.getUnMarkedRecords();
+	}
+
 }

client/src/main/java/zingg/client/IZingg.java

@@ -22,6 +22,8 @@ public void init(Arguments args, String license)
 
 	public Dataset<Row> getMarkedRecords();
 
+	public Dataset<Row> getUnMarkedRecords();
+
 	public Long getMarkedRecordsStat(Dataset<Row> markedRecords, long value);
 
     public Long getMatchedMarkedRecordsStat(Dataset<Row> markedRecords);

client/src/test/java/zingg/client/TestArguments.java

@@ -7,6 +7,7 @@
 import java.nio.charset.StandardCharsets;
 import java.nio.file.Files;
 import java.nio.file.Paths;
+import java.util.Arrays;
 import java.util.HashMap;
 import java.util.List;
 import java.util.Map;
@@ -15,6 +16,9 @@
 import org.apache.commons.logging.LogFactory;
 import org.junit.jupiter.api.Test;
 
+import zingg.client.pipe.Format;
+import zingg.client.pipe.Pipe;
+
 public class TestArguments {
 
 	private static final String KEY_HEADER = "header";
@@ -241,4 +245,49 @@ public void testMatchTypeWrong() {
 
 
 	}
-}
+
+	@Test
+	public void testWriteArgumentObjectToJSONFile() {
+			Arguments args = new Arguments();
+            try {
+				FieldDefinition fname = new FieldDefinition();
+				fname.setFieldName("fname");
+				fname.setDataType("\"string\"");
+				fname.setMatchType(Arrays.asList(MatchType.EXACT, MatchType.FUZZY, MatchType.PINCODE));
+				//fname.setMatchType(Arrays.asList(MatchType.EXACT));
+				fname.setFields("fname");
+				FieldDefinition lname = new FieldDefinition();
+				lname.setFieldName("lname");
+				lname.setDataType("\"string\"");
+				lname.setMatchType(Arrays.asList(MatchType.FUZZY));
+				lname.setFields("lname");
+				args.setFieldDefinition(Arrays.asList(fname, lname));
+
+				Pipe inputPipe = new Pipe();
+				inputPipe.setName("test");
+				inputPipe.setFormat(Format.CSV);
+				inputPipe.setProp("location", "examples/febrl/test.csv");
+				args.setData(new Pipe[] {inputPipe});
+
+				Pipe outputPipe = new Pipe();
+				outputPipe.setName("output");
+				outputPipe.setFormat(Format.CSV);
+				outputPipe.setProp("location", "examples/febrl/output.csv");
+				args.setOutput(new Pipe[] {outputPipe});
+
+				args.setBlockSize(400L);
+				args.setCollectMetrics(true);
+				args.setModelId("500");
+                Arguments.writeArgumentsToJSON("configFromArgObject.json", args);
+				//List<MatchType> fNameMatchType = args.getFieldDefinition().get(0).getMatchType();
+
+				// Arguments newArgs = Arguments.createArgumentsFromJSON("configFromArgObject.json", "test");
+				// assertEquals(newArgs.getModelId(), "500", "Model id is different");
+				// assertEquals(newArgs.getBlockSize(), 400L, "Block size is different");
+				// assertEquals(newArgs.getFieldDefinition().get(0).getFieldName(), "fname", "Field Definition[0]'s name is different");
+				//TODO add check for MatchType
+            } catch (Exception | ZinggClientException e) {
+               e.printStackTrace();				
+            }
+	}
+}