Merge pull request #147 from navinrathore/zFindLabeller

Introduced new phase findLabel

client/src/main/java/zingg/client/ClientOptions.java

@@ -229,7 +229,7 @@ public final static String getHelp() {
 		  s.append("zingg.sh --phase findTrainingData --conf config.json --zinggDir /location \n");
 		  s.append("zingg.sh --phase label --conf config.json --zinggDir /location \n");
 		  s.append("zingg.sh --phase trainMatch --conf config.json --email [email protected]\n");
-
+		  s.append("zingg.sh --phase findAndLabel --conf config.json --zinggDir /location\n");
 		  s.append("options\n");
 		  for (Option o: optionMaster.values()) {
 			  s.append("\t " + o.optionName + ":\t\t" + o.desc + "\n");

client/src/main/java/zingg/client/ZinggOptions.java

@@ -13,7 +13,8 @@ public enum ZinggOptions {
     LABEL("label"),
     LINK("link"),
     GENERATE_DOCS("generateDocs"),
-    UPDATE_LABEL("updateLabel");
+    UPDATE_LABEL("updateLabel"),
+    FIND_AND_LABEL("findAndLabel");
 
     private String value;
 

core/src/main/java/zingg/FindAndLabeller.java

@@ -0,0 +1,33 @@
+package zingg;
+
+import org.apache.commons.logging.Log;
+import org.apache.commons.logging.LogFactory;
+
+import zingg.client.Arguments;
+import zingg.client.ZinggClientException;
+import zingg.client.ZinggOptions;
+
+public class FindAndLabeller extends Labeller {
+	protected static String name = "zingg.FindAndLabeller";
+	public static final Log LOG = LogFactory.getLog(FindAndLabeller.class);
+
+	private TrainingDataFinder finder;
+
+	public FindAndLabeller() {
+		setZinggOptions(ZinggOptions.FIND_AND_LABEL);
+		finder = new TrainingDataFinder();
+	}
+
+	@Override
+	public void init(Arguments args, String license)
+			throws ZinggClientException {
+		super.init(args, license);
+		finder.copyContext(this);
+	}
+
+	@Override
+	public void execute() throws ZinggClientException {
+		finder.execute();
+		super.execute();
+	}
+}

core/src/main/java/zingg/ZFactory.java

@@ -21,6 +21,7 @@ public ZFactory() {}
         zinggers.put(ZinggOptions.LINK, Linker.name);
         zinggers.put(ZinggOptions.GENERATE_DOCS, Documenter.name);
         zinggers.put(ZinggOptions.UPDATE_LABEL, LabelUpdater.name);
+        zinggers.put(ZinggOptions.FIND_AND_LABEL, FindAndLabeller.name);
     }
 
     public IZingg get(ZinggOptions z) throws InstantiationException, IllegalAccessException, ClassNotFoundException {

docs/SUMMARY.md

@@ -9,6 +9,7 @@
   * [**Creating training data**](setup/training/createTrainingData.md)
     * [findTrainingData](setup/training/findTrainingData.md)
     * [label](setup/training/label.md)
+    * [findAndLabel](setup/training/findAndLabel.md)
     * [Using preexisting training data](setup/training/addOwnTrainingData.md)
     * [Exporting labeled data as csv](setup/training/exportLabeledData.md)
   * [Building and saving the model](setup/train.md)

docs/setup/training/findAndLabel.md

@@ -0,0 +1,14 @@
+---
+layout: default
+parent: Creating training data
+title: Find training data and labelling
+grand_parent: Step By Step Guide
+nav_order: 2
+---
+## Find training data and labelling them 
+
+This phase is composed of two phases namely [findTrainingData](./findTrainingData.md) and [label](./label.md). This will help experienced users to quicken the process of creating Training data.
+
+`./zingg.sh --phase findAndLabel --conf config.json`
+
+  It's note that this option is good for small datasets else if your findTrainingData takes a long time, the user will have to wait for the console for labelling. For details, refer to the individual phases: [findTrainingData](./findTrainingData.md) and [label](./label.md)