Squashed commit of branch 'learner'

- Fixed pattern to parse datetime coming from openHAB.
- add benchmark
- Create RecognitionEvents in component Plan.
- Add expression printing and fix expression tests.
- Fixing tests.
- Remove build artefacts of datasets module.
- Fixing item behavior.
- Fix bug when adding item using REST API.
  - More debug output for REST application and MQTT receiver
  - Flush cache if new MQTT Host is set
- first integration for test
- update integration activity ML
- add item room_brightness
- add ML Items in starter file
- fix import error
- update newData function
- Fix Learner bugs.
  - Let ExternalMachineLearningModel.check() return true instead of throwing an exception
  - In Learner, use temporary files to store encog model
  - In MachineLearningImpl, do not use result for now (as newData won't work at the moment)
  - Minor fixes for base (add logger, add correct input to jastadd gradle task)
- Progressing to integration of machine learning.
  - Added setKnowledgeBase to MachineLearningEncoder and -Decoder, and removed Root argument in other methods
  - Changed Learner-Impl to match new adapters
  - Updated starter to new adapters, and to use CSV files for initialization of learner
- update readercsv
- Fix imports and dependencies.
- Fix errors with changed MachineLearningEncoder interface.
- upate learner
- add ML interfaces
- implement decode encode
- learner with activity and preference

eraser.starter/starter-setting.yaml

@@ -24,28 +24,29 @@ load:
 
 # Model for activity recognition. If dummy is true, then the file parameter is ignored.
 activity:
-  # File to read in. Expected format = eg
-  file: activity.eg
+  # File to read in. Expected format = csv   /Users/boqi/eraser/datasets
+  file: ../datasets/backup/activity_data.csv
+  external: true
   # Use dummy model in which the current activity is directly editable. Default: false.
-  dummy: true
+  dummy: false
   # Model id. Default: 1.
   id: 1
+  # Item to change with classification result
+  affectedItem: activity
 
 # Model for preference learning. If dummy is true, then the file parameter is ignored.
 preference:
-  # File to read in. Expected format = eg
-  file: preference.eg
+  # File to read in. Expected format = csv
+  file: ../datasets/backup/preference_data.csv
+  external: true
   # Use dummy model in which the current activity is directly editable. Default: false.
   dummy: false
   # Model id. Default: 1.
   id: 1
   # Items to connect to inputs
   items:
-    - datetime_month
-    - datetime_day
-    - datetime_hour
-    - datetime_minute
-#    - activity
+    - activity
+    - w_brightness
   # Item to change with classification result
   affectedItem: iris1_item
 

feedbackloop.learner/.settings/org.eclipse.buildship.core.prefs

-connection.project.dir=..
-eclipse.preferences.version=1

feedbackloop.learner_backup/build.gradle

@@ -8,6 +8,13 @@ dependencies {
     testCompile group: 'junit', name: 'junit', version: '4.12'
     testCompile group: 'org.hamcrest', name: 'hamcrest-junit', version: '2.0.0.0'
     compile group: 'org.encog', name: 'encog-core', version: '3.4'
+    implementation group: 'com.opencsv', name: 'opencsv', version: '4.1'
+    implementation group: 'commons-io', name: 'commons-io', version: '2.5'
+    implementation group: 'org.apache.httpcomponents', name: 'httpclient', version: '4.5.8'
+    implementation group: 'org.apache.httpcomponents', name: 'fluent-hc', version: '4.5.8'
+    // https://mvnrepository.com/artifact/org.apache.spark/spark-mllib
+    //runtime group: 'org.apache.spark', name: 'spark-mllib_2.10', version: '1.3.0'
+    compile group: 'com.sparkjava', name: 'spark-core', version: '2.9.0'
 }
 
 run {

feedbackloop.learner_backup/src/main/java/de/tudresden/inf/st/eraser/feedbackloop.learner_backup/CsvTransfer.java

+package de.tudresden.inf.st.eraser.feedbackloop.learner_backup;
+
+import java.io.*;
+import java.util.*;
+
+import com.opencsv.CSVReader;
+import com.opencsv.CSVWriter;
+
+
+public class CsvTransfer {
+    public static void main(String[] args){
+        Learner learner=new Learner();
+        learner.train("datasets/backup/activity_data.csv","datasets/backup/preference_data.csv");
+    }
+
+    //learner.train("datasets/backup/activity_data.csv","datasets/backup/preference_data.csv");
+    /**private static final String CSV_FILE_PATH
+            = "datasets/backup/activity_data_example.csv";
+    private static final String OUTPUT_FILE_PATH
+            = "datasets/backup/activity_data.csv";
+    public static void main(String[] args)
+    {
+        addDataToCSV(CSV_FILE_PATH, OUTPUT_FILE_PATH);
+    }
+    public static void addDataToCSV(String input, String output)
+    {
+        File input_file = new File(input);
+        File output_file = new File(output);
+        try {
+            // create FileWriter object with file as parameter
+            FileReader reader = new FileReader(input_file);
+            CSVReader csv_reader = new CSVReader(reader);
+            String[] nextRecord;
+            FileWriter writer = new FileWriter(output_file);
+            CSVWriter csv_writer = new CSVWriter(writer, ',',
+                    CSVWriter.NO_QUOTE_CHARACTER,
+                    CSVWriter.DEFAULT_ESCAPE_CHARACTER,
+                    CSVWriter.DEFAULT_LINE_END);
+            List<String[]> data = new ArrayList<String[]>();
+
+            while ((nextRecord = csv_reader.readNext()) != null) {
+                data.add(nextRecord);
+
+                for (String cell : nextRecord) {
+                    System.out.print(cell + "\t");
+                }
+                System.out.println();
+            }
+            csv_writer.writeAll(data);
+            writer.close();
+            csv_reader.close();
+        }
+        catch (Exception e) {
+            // TODO Auto-generated catch block
+            e.printStackTrace();
+        }
+    }*/
+}
+
+

feedbackloop.learner_backup/src/main/java/de/tudresden/inf/st/eraser/feedbackloop.learner_backup/DummyPreference.java

+package de.tudresden.inf.st.eraser.feedbackloop.learner_backup;
+import com.opencsv.CSVWriter;
+
+import java.io.FileWriter;
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.List;
+import java.util.Random;
+
+public class DummyPreference {
+    private static String activity;  //Activity: walking, reading, working, dancing, lying, getting up
+    private static String watch_brightness; //dark: <45; dimmer 45-70; bright >70;
+    private static String light_color_openhab_H; //red 7; green 120; blue 240; yellow 60; sky blue 180; purple 300;
+    private static String brightness_output; //1-100**/
+    private static Random random = new Random();
+
+    public static void main(String[] args) {
+        creator();
+    }
+    static void creator(){
+
+
+        try{
+            FileWriter writer = new FileWriter("datasets/backup/preference_data.csv",true);
+            CSVWriter csv_writer = new CSVWriter(writer, ',',
+                    CSVWriter.NO_QUOTE_CHARACTER,
+                    CSVWriter.DEFAULT_ESCAPE_CHARACTER,
+                    CSVWriter.DEFAULT_LINE_END);
+
+
+            //activity="walking" green
+            activity ="walking";
+
+           // activity ="reading";
+            csv_writer.writeAll(generator("walking","green"));
+            csv_writer.writeAll(generator("reading","sky blue"));
+            csv_writer.writeAll(generator("working","blue"));
+            csv_writer.writeAll(generator("dancing","purple"));
+            csv_writer.writeAll(generator("lying","red"));
+            csv_writer.writeAll(generator("getting up","yellow"));
+            csv_writer.close();
+            writer.close();
+        }catch (IOException e){e.printStackTrace();}
+    }
+    static List<String[]> generator(String activity_input, String color){
+        List<String[]> data = new ArrayList<String[]>();
+        activity = activity_input;
+        light_color_openhab_H =color;
+        //100 walking with different lighting intensity
+        for (int i=0; i<100; i++){
+            String[] add_data = new String[4];
+            int brightness = random.nextInt(3000);
+            System.out.println(brightness);
+            if (brightness<45){
+                watch_brightness = "dark";
+                brightness_output ="100";
+            }else if(45<=brightness && brightness<200){
+                watch_brightness = "dimmer";
+                brightness_output ="40";
+            }else if( 200<=brightness && brightness<1000){
+                watch_brightness = "medium";
+                brightness_output ="70";
+            }else{
+                watch_brightness = "bright";
+                brightness_output ="0";
+            }
+            add_data[0] = activity;
+            add_data[1] = watch_brightness;
+            add_data[2] = light_color_openhab_H;
+            add_data[3] = brightness_output;
+            data.add(add_data);
+        }
+        return data;
+    }
+}

feedbackloop.learner_backup/src/main/java/de/tudresden/inf/st/eraser/feedbackloop.learner_backup/Learner.java

 package de.tudresden.inf.st.eraser.feedbackloop.learner_backup;
 
 import java.io.File;
-import java.net.MalformedURLException;
-import java.net.URL;
-import java.util.Arrays;
-
-import com.sun.javafx.tools.packager.Log;
-import org.encog.ConsoleStatusReportable;
+import java.io.IOException;
+//import java.util.ArrayList;
+//import com.sun.javafx.tools.packager.Log;
+import org.apache.logging.log4j.LogManager;
+import org.apache.logging.log4j.Logger;
+//import org.encog.ConsoleStatusReportable;
 import org.encog.Encog;
-import org.encog.bot.BotUtil;
-import org.encog.ml.MLInput;
-import org.encog.ml.MLRegression;
+import org.encog.ml.MLClassification;
+//import org.encog.ml.MLRegression;
 import org.encog.ml.data.MLData;
 import org.encog.ml.data.versatile.NormalizationHelper;
 import org.encog.ml.data.versatile.VersatileMLDataSet;
@@ -22,8 +21,6 @@ import org.encog.ml.factory.MLMethodFactory;
 import org.encog.ml.model.EncogModel;
 import org.encog.neural.networks.BasicNetwork;
 import org.encog.util.csv.CSVFormat;
-import org.encog.util.csv.ReadCSV;
-import org.encog.util.simple.EncogUtility;
 import static org.encog.persist.EncogDirectoryPersistence.*;
 
 public class Learner {
@@ -31,129 +28,163 @@ public class Learner {
     /**
      * intial train
      * */
-    private String csv_url_activity;
-    private String csv_url_perference;
-    private String save_activity_model_file = "datasets/backup/activity_model.eg";
-    private String save_perference_model_file = "datasets/backup/preference_model.eg";
+    private File save_activity_model_file;
+    private File save_preference_model_file;
     private File csv_file;
-    private VersatileDataSource souce;
-    private VersatileMLDataSet data;
-    private EncogModel model;
+    private VersatileMLDataSet a_data;
+    private VersatileMLDataSet p_data;
+    private EncogModel a_model;
+    private EncogModel p_model;
     private NormalizationHelper activity_helper;
     private NormalizationHelper preference_helper;
-    private MLRegression best_method;
-    private String[] new_data;
-    private String activity_result;
-    private String preference_result;
+    private MLClassification a_best_method;
+    private MLClassification p_best_method;
+    private final Logger logger = LogManager.getLogger(Learner.class);
+
+    public Learner() {
+        try {
+            save_activity_model_file = File.createTempFile("activity_model", "eg");
+        } catch (IOException e) {
+            // use local alternative
+            save_activity_model_file = new File("activity_model.eq");
+        }
+        try {
+            save_preference_model_file = File.createTempFile("preference_model", "eg");
+        } catch (IOException e) {
+            // use local alternative
+            save_preference_model_file = new File("preference_model.eg");
+        }
+        save_activity_model_file.deleteOnExit();
+        save_preference_model_file.deleteOnExit();
+    }
 
     private void activityDataAnalyser(String activity_csv_url){
-        this.csv_url_activity = activity_csv_url;
+        VersatileDataSource a_souce;
+        String csv_url_activity;
+        csv_url_activity = activity_csv_url;
         this.csv_file = new File(csv_url_activity);
-        souce = new CSVDataSource(csv_file,false,CSVFormat.DECIMAL_POINT);
-        data = new VersatileMLDataSet(souce);
-        data.defineSourceColumn("monat", 0, ColumnType.continuous);
-        data.defineSourceColumn("day", 1, ColumnType.continuous);
-        data.defineSourceColumn("hour", 2, ColumnType.continuous);
-        data.defineSourceColumn("minute", 3, ColumnType.continuous);
-        ColumnDefinition outputColumn = data.defineSourceColumn("labels", 4, ColumnType.continuous);
-        data.defineSingleOutputOthersInput(outputColumn);
-        data.analyze();
-        System.out.println("get data ");
-        model = new EncogModel(data);
-        model.selectMethod(data, MLMethodFactory.TYPE_FEEDFORWARD);
-        data.normalize();
-        activity_helper = data.getNormHelper();
-        System.out.println(activity_helper.toString());
+        a_souce = new CSVDataSource(csv_file,false,CSVFormat.DECIMAL_POINT);
+        a_data = new VersatileMLDataSet(a_souce);
+        String[] activity_inputs={"m_accel_x","m_accel_y", "m_accel_z",
+                "m_rotation_x","m_rotation_y", "m_rotation_z",
+                "w_accel_x","w_accel_y", "w_accel_z",
+                "w_rotation_x","w_rotation_y","w_rotation_z"
+        };
+        for(int i=0; i < activity_inputs.length; i++){
+            a_data.defineSourceColumn(activity_inputs[i], i, ColumnType.continuous);
+        }
+        ColumnDefinition outputColumn = a_data.defineSourceColumn("labels", 12, ColumnType.nominal);
+        a_data.defineSingleOutputOthersInput(outputColumn);
+        a_data.analyze();
+        a_model = new EncogModel(a_data);
+        a_model.selectMethod(a_data, MLMethodFactory.TYPE_FEEDFORWARD);
+        a_data.normalize();
+        activity_helper = a_data.getNormHelper();
     }
 
-    private void perferenceDataAnalyser(String perference_csv_url){
-        this.csv_url_perference = perference_csv_url;
-        this.csv_file = new File(this.csv_url_perference);
-        souce = new CSVDataSource(csv_file,false,CSVFormat.DECIMAL_POINT);
-        data = new VersatileMLDataSet(souce);
-        data.defineSourceColumn("activity", 0, ColumnType.continuous);
-        data.defineSourceColumn("brightness", 1, ColumnType.continuous);
-        data.defineSourceColumn("time", 2, ColumnType.continuous);
-        data.defineSourceColumn("minute", 3, ColumnType.continuous);
-        ColumnDefinition outputColumn = data.defineSourceColumn("labels", 4, ColumnType.continuous);
-        data.defineSingleOutputOthersInput(outputColumn);
-        data.analyze();
-        model = new EncogModel(data);
-        model.selectMethod(data, MLMethodFactory.TYPE_FEEDFORWARD);
-        //model.setReport(new ConsoleStatusReportable());
-        data.normalize();
-        preference_helper = data.getNormHelper();
-        System.out.println(activity_helper.toString());
+    private void preferenceDataAnalyser(String preference_csv_url){
+        VersatileDataSource p_source;
+        String csv_url_preference;
+        csv_url_preference = preference_csv_url;
+        this.csv_file = new File(csv_url_preference);
+        p_source = new CSVDataSource(csv_file,false,CSVFormat.DECIMAL_POINT);
+        p_data = new VersatileMLDataSet(p_source);
+        p_data.defineSourceColumn("activity", 0, ColumnType.nominal);
+        p_data.defineSourceColumn("w_brightness", 1, ColumnType.nominal);
+        ColumnDefinition outputColumn1 = p_data.defineSourceColumn("label1", 2, ColumnType.continuous);
+        ColumnDefinition outputColumn2 = p_data.defineSourceColumn("label2", 3, ColumnType.continuous);
+        ColumnDefinition[] outputs = new ColumnDefinition[2];
+        outputs[0] = outputColumn1;
+        outputs[1] = outputColumn2;
+        p_data.defineMultipleOutputsOthersInput(outputs);
+        p_data.analyze();
+        p_model = new EncogModel(p_data);
+        p_model.selectMethod(p_data, MLMethodFactory.TYPE_FEEDFORWARD);
+        p_data.normalize();
+        preference_helper = p_data.getNormHelper();
     }
 
-    void train(String activity_url,String perference_url){
+    void train(String activity_url,String preference_url){
         activity_train(activity_url);
-        Log.info("activity training finished");
-        preference_train(perference_url);
-        Log.info("preference training finished");
+        preference_train(preference_url);
+        Encog.getInstance().shutdown();
 
     }
-    private void activity_train(String activity_csv_url){
+
+    void activity_train(String activity_csv_url){
+        logger.info("Activity training is beginning ... ...");
         activityDataAnalyser(activity_csv_url);
-        model.holdBackValidation(0.3, true, 1001);
-        model.selectTrainingType(data);
-        best_method = (MLRegression)model.crossvalidate(5, true);
-        System.out.println(best_method);
+        a_model.holdBackValidation(0.3, true, 1001);
+        a_model.selectTrainingType(a_data);
+        a_best_method = (MLClassification)a_model.crossvalidate(5, true);
         saveEncogModel(save_activity_model_file);
+        logger.info("Activity training is finished ... ...");
+        Encog.getInstance().shutdown();
     }
-    private void preference_train(String perfence_csv_url){
-        perferenceDataAnalyser(perfence_csv_url);
-        model.holdBackValidation(0.3, true, 1001);
-        model.selectTrainingType(data);
-        best_method = (MLRegression)model.crossvalidate(5, true);
-        System.out.println(best_method);
-        saveEncogModel(save_perference_model_file);
+    void preference_train(String prefence_csv_url){
+        logger.info("Preference training is beginning ... ...");
+        preferenceDataAnalyser(prefence_csv_url);
+        p_model.holdBackValidation(0.3, true, 1001);
+        p_model.selectTrainingType(p_data);
+        p_best_method = (MLClassification)p_model.crossvalidate(5, true);
+        saveEncogModel(save_preference_model_file);
+        logger.info("Preference training is finished ... ...");
+        Encog.getInstance().shutdown();
     }
 
     String[] predictor(String[] new_data){
-        this.new_data = new_data;
-        activityDataAnalyser("datasets/backup/activity_data.csv");
-        perferenceDataAnalyser("datasets/backup/preference_data.csv");
-        String[] result = new String[2];
-        result[0] = activity_predictor();
-        result[1] = perference_predictor();
+        String[] preference_data = new String[2];
+        String[] result = new String[3];
+        String[] activity_data= new String[12];
+        for(int i=0; i<new_data.length;i++){
+            activity_data[i]=new_data[i];
+        }
+        result[0] = activity_predictor(activity_data);
+        preference_data[0]=result[0];
+        preference_data[1]=new_data[12];
+        result[1] = preference_predictor(preference_data)[0];
+        result[2] = preference_predictor(preference_data)[1];
         Encog.getInstance().shutdown();
         return result;
     }
 
-    private String activity_predictor(){
-        BasicNetwork activity_method = (BasicNetwork) loadObject(new File(save_activity_model_file));
+    String activity_predictor(String[] new_data){
+        logger.info("Activity predicting ... ...");
+        String activity_result;
+        activityDataAnalyser("../datasets/backup/activity_data.csv");
+        BasicNetwork activity_method = (BasicNetwork) loadObject(save_activity_model_file);
         MLData input = activity_helper.allocateInputVector();
-        String[] activity_new_data = new String[4];
-        activity_new_data[0] = new_data[0];
-        activity_new_data[1] = new_data[1];
-        activity_new_data[2] = new_data[2];
-        activity_new_data[3] = new_data[3];
-        activity_helper.normalizeInputVector(activity_new_data,input.getData(),false);
+        activity_helper.normalizeInputVector(new_data,input.getData(),false);
         MLData output = activity_method.compute(input);
-        System.out.println("input:"+input);
-        System.out.println("output"+output);
         activity_result = activity_helper.denormalizeOutputVectorToString(output)[0];
-        System.out.println("output activity"+ activity_result);
+        Encog.getInstance().shutdown();
+        logger.debug("Activity Predictor result is: {}",activity_result);
         return activity_result;
     }
 
-    private String perference_predictor(){
-        BasicNetwork preference_method = (BasicNetwork)loadObject(new File(save_perference_model_file));
+    String[] preference_predictor(String[] new_data){
+        logger.info("Activity predicting ... ...");
+        String[] preference_result;
+        preference_result = new String[2];
+        preferenceDataAnalyser("../datasets/backup/preference_data.csv");
+        BasicNetwork preference_method = (BasicNetwork)loadObject(save_preference_model_file);
         MLData input = preference_helper.allocateInputVector();
-        String[] perference_new_data = new String[4];
-        perference_new_data[0] = activity_result;
-        perference_new_data[1] = new_data[4];
-        perference_new_data[2] = new_data[5];
-        perference_new_data[3] = new_data[6];
-        preference_helper.normalizeInputVector(perference_new_data, input.getData(),false);
+        preference_helper.normalizeInputVector(new_data, input.getData(),false);
         MLData output = preference_method.compute(input);
-        preference_result = preference_helper.denormalizeOutputVectorToString(output)[0];
+        preference_result[0] = preference_helper.denormalizeOutputVectorToString(output)[0];
+        preference_result[1] = preference_helper.denormalizeOutputVectorToString(output)[1];
+        Encog.getInstance().shutdown();
+        logger.debug("Preference Predictor result is, Color:  {}",Math.round(Float.valueOf(preference_result[0])));
+        logger.debug("Preference Predictor result is, Brightness: {} ",Math.round(Float.valueOf(preference_result[1])));
         return preference_result;
     }
+    private void saveEncogModel(File modelFile){
+        if (modelFile.equals(save_activity_model_file)) {
+          saveObject(modelFile, this.a_best_method);
+        } else {
+            saveObject(modelFile, this.p_best_method);
+        }
 
-    private void saveEncogModel(String model_file_url){
-        saveObject(new File(model_file_url), this.best_method);
     }
 }
 

feedbackloop.learner_backup/src/main/java/de/tudresden/inf/st/eraser/feedbackloop.learner_backup/MachineLearningImpl.java

+package de.tudresden.inf.st.eraser.feedbackloop.learner_backup;
+
+
+
+//import com.sun.javafx.tools.packager.Log;
+import de.tudresden.inf.st.eraser.jastadd.model.*;
+import org.apache.logging.log4j.LogManager;
+import org.apache.logging.log4j.Logger;
+
+import java.time.Instant;
+import java.util.*;
+import java.util.stream.Collectors;
+
+
+public class MachineLearningImpl implements MachineLearningDecoder, MachineLearningEncoder {
+
+  private List<Item> target_item_list;
+  private List<Item> relevant_item_list;
+  private String[] preference_result;
+
+  private Root root;
+  private final Logger logger = LogManager.getLogger(MachineLearningImpl.class);
+  private final Learner learner;
+  private final int goal;
+
+  public static final int GOAL_ACTIVITY_PHONE_AND_WATCH = 1;
+  public static final int GOAL_PREFERENCE_BRIGHTNESS_IRIS = 2;
+  public String activity_result;
+  private String[] activites= new String[]{"working", "walking", "dancing", "lying", "getting up", "reading"};
+  public MachineLearningImpl(Learner learner, int goal) {
+    this.learner = learner;
+    this.goal = goal;
+  }
+
+  @Override
+  public void setKnowledgeBaseRoot(Root root) {
+    this.root = root;
+    updateItems();
+  }
+
+  private void updateItems() {
+    OpenHAB2Model model = root.getOpenHAB2Model();
+    List<String> targetItemNames, relevantItemNames;
+    switch (this.goal) {
+      case GOAL_ACTIVITY_PHONE_AND_WATCH:
+        targetItemNames = Collections.singletonList("activity");
+        relevantItemNames = Arrays.asList(
+            "m_accel_x",
+            "m_accel_y",
+            "m_accel_z",
+            "m_rotation_x",
+            "m_rotation_y",
+            "m_rotation_z",
+            "w_accel_x",
+            "w_accel_y",
+            "w_accel_z",
+            "w_rotation_x",
+            "w_rotation_y",
+            "w_rotation_z"
+        );
+        break;
+      case GOAL_PREFERENCE_BRIGHTNESS_IRIS:
+        targetItemNames = Collections.singletonList("iris1_item");
+        relevantItemNames = Arrays.asList(
+            "activity",
+            "w_brightness"
+        );
+        break;
+      default:
+        logger.error("Unknown goal value ({}) set", this.goal);
+        targetItemNames = Collections.emptyList();
+        relevantItemNames = Collections.emptyList();
+    }
+    target_item_list = targetItemNames.stream()
+        .map(name -> resolve(model, name))
+        .filter(Objects::nonNull)
+        .collect(Collectors.toList());
+    relevant_item_list = relevantItemNames.stream()
+        .map(name -> resolve(model, name))
+        .filter(Objects::nonNull)
+        .collect(Collectors.toList());
+  }
+
+  private Item resolve(OpenHAB2Model model, String id) {
+    Optional<Item> maybeItem = model.resolveItem(id);
+    if (maybeItem.isPresent()) {
+      return maybeItem.get();
+    } else {
+      logger.warn("Could not find item with id {}", id);
+      return null;
+    }
+  }
+
+  @Override
+  public void newData(List<Item> changedItems) {
+    /* String topic = changedItems.get(0).getTopic().toString();
+     if(topic.equals("oh2/samsung/items1")){
+     new_data[0]=changedItems.get(0).influxMeasurementName();
+     }
+     model.getOpenHAB2Model().items();
+     Item iris_item=model.getOpenHAB2Model().resolveItem("iris_item").get();
+     iris_item.getStateAsString();*/
+    /* FIXME either save state of unchanged items here (if only changed items are reported) <- pull model
+             or let knowledge base pass all relevant items <- push model
+    */
+    if(this.goal==GOAL_ACTIVITY_PHONE_AND_WATCH){
+      String[] new_data = new String[12];
+      for (int i =0; i< new_data.length; i++){
+        new_data[i] ="0";
+      }
+      for(Item item: changedItems){
+        int i = 0;
+        for(Item item1: relevant_item_list){
+          if(item.getTopic().toString().equals(item1.getTopic().toString())){
+            new_data[i]=item.getStateAsString();
+          }
+          i++;
+        }
+      }
+      this.activity_result = learner.activity_predictor(new_data);
+
+    }else if(this.goal==GOAL_PREFERENCE_BRIGHTNESS_IRIS){
+      String[] new_data = new String[2];
+      for(Item item: changedItems){
+        if(root.getOpenHAB2Model().getActivityItem().equals(item))
+        {
+          String test=item.getStateAsString();
+          int index = Math.round(Float.valueOf(test));
+          new_data[0]=activites[index];
+        }
+        if(item.getID().equals("w_brightness")){
+          new_data[1]=item.getStateAsString();
+        }
+      }
+      this.preference_result=learner.preference_predictor(new_data);
+    }
+  }
+
+  @Override
+  public List<Item> getTargets() {
+    return target_item_list;
+  }
+
+  @Override
+  public List<Item> getRelevantItems() {
+    return relevant_item_list;
+  }
+
+  @Override
+  public void triggerTraining() {
+    logger.debug("Ignore trigger training call");
+  }
+
+  @Override
+  public Instant lastModelUpdate() {
+    return null;
+  }
+
+  @Override
+  public MachineLearningResult classify() {
+    switch (this.goal) {
+      case GOAL_ACTIVITY_PHONE_AND_WATCH:
+        String activityStringValue = activity_result;
+        Item activityItem = resolve(this.root.getOpenHAB2Model(), "activity");
+        //activityItem.setStateFromString(activityStringValue);
+        // FIXME how to translate activityStringValue to a number? or should activity item state better be a String?
+        for (int i=0; i< activites.length;i++){
+          if(activites[i].equals(activityStringValue)){
+            activityItem.setStateFromString(String.valueOf(i));
+          }
+        }
+        logger.debug("Classify would return activity: {}", activityStringValue);
+        ItemPreference classifiedActivity = new ItemPreferenceDouble(activityItem, 0);
+        return new MachineLearningResultImpl(classifiedActivity);
+      case GOAL_PREFERENCE_BRIGHTNESS_IRIS:
+//        String[] preference = {result[1], result[2]};
+        // FIXME what is the meaning of result[1] and result[2]
+        Item iris1 = resolve(this.root.getOpenHAB2Model(), "iris1_item");
+        int color = 0;
+        int brightness = 0;
+        if (preference_result != null){
+          color = Math.round(Float.valueOf(preference_result[0]));
+          brightness = Math.round(Float.valueOf(preference_result[1]));
+        }
+
+        ItemPreference classifiedPreference = new ItemPreferenceColor(iris1, TupleHSB.of(color, 100, brightness));
+        return new MachineLearningResultImpl(classifiedPreference);
+      default:
+        logger.error("Unknown goal value ({}) set in classify", this.goal);
+        return new EmptyMachineLearningResult();
+    }
+  }
+
+  public void initActivities(String filenameOfCsv) {
+    logger.debug(filenameOfCsv);
+    learner.activity_train(filenameOfCsv);
+  }
+
+  public void initPreferences(String filenameOfCsv) {
+    learner.preference_train(filenameOfCsv);
+  }
+
+  class EmptyMachineLearningResult implements MachineLearningResult {
+
+    @Override
+    public List<ItemPreference> getPreferences() {
+      return Collections.emptyList();
+    }
+  }
+
+}

feedbackloop.learner_backup/src/main/java/de/tudresden/inf/st/eraser/feedbackloop.learner_backup/MachineLearningResultImpl.java

+package de.tudresden.inf.st.eraser.feedbackloop.learner_backup;
+
+import de.tudresden.inf.st.eraser.jastadd.model.ItemPreference;
+import de.tudresden.inf.st.eraser.jastadd.model.MachineLearningResult;
+
+import java.util.Collections;
+import java.util.List;
+
+/**
+ * TODO: Add description.
+ *
+ * @author rschoene - Initial contribution
+ */
+public class MachineLearningResultImpl implements MachineLearningResult {
+
+  private final ItemPreference preference;
+
+  MachineLearningResultImpl(ItemPreference preference) {
+    this.preference = preference;
+  }
+
+  @Override
+  public List<ItemPreference> getPreferences() {
+    return Collections.singletonList(preference);
+  }
+}

feedbackloop.learner_backup/src/main/java/de/tudresden/inf/st/eraser/feedbackloop.learner_backup/Main.java

 package de.tudresden.inf.st.eraser.feedbackloop.learner_backup;
 
-import de.tudresden.inf.st.eraser.jastadd.model.*;
+import org.encog.util.csv.CSVFormat;
+import org.encog.util.csv.ReadCSV;
+
+import java.util.Arrays;
 
 public class Main {
 
@@ -8,22 +11,154 @@ public class Main {
     /**
      * new data from KB
      * */
-    String[] new_data = new String[7];
-    new_data[0]="7";
-    new_data[1]="20";
-    new_data[2]="12";
-    new_data[3]="13";
-    new_data[4]="7";
-    new_data[5]="25";
-    new_data[6]="12";
+    //ReaderCSV reader = new ReaderCSV("datasets/backup/activity_data.csv","preference");
+    //reader.updater();
+    Learner learner=new Learner();
+    //learner.preference_train("../datasets/backup/preference_data.csv");
+    //learner.train("datasets/backup/activity_data.csv","datasets/backup/preference_data.csv");
+    //0.5793968,1.2126632,-4.6244006,-0.030779,0.801127,0.590978,-3.1411927,-0.93373865,-0.31124622,-0.35992432,0.33746338,-0.79608154,dancing
+    /**String[] new_data = new String[12];
+    new_data[0]="0.5793968";
+    new_data[1]="1.2126632";
+    new_data[2]="-4.6244006";
+    new_data[3]="-0.030779";
+    new_data[4]="0.801127";
+    new_data[5]="0.590978";
+    new_data[6]="-3.1411927";
+    new_data[7]="-0.93373865";
+    new_data[8]="-0.31124622";
+    new_data[9]="-0.35992432";
+    new_data[10]="0.33746338";
+    new_data[11]="-0.79608154";
+
+    String result =learner.activity_predictor(new_data);
+    System.out.println(result);
+
+    List k=new ArrayList();
+
+    k.add(new_data);*/
+
+    //learner.preference_train("datasets/backup/preference_data.csv");
+    //learner.train("datasets/backup/activity_data.csv","datasets/backup/preference_data.csv");
+    //walking,medium,120,70
+    //reading,bright,180,0
+
+    //activity_validation_learner();
+    //0.10654198,8.6574335,4.414908,0.040269,0.516884,0.853285,1.2066777,-1.1444284,9.648633,1.2207031E-4,-0.055358887,0.5834961 working
+    String[] new_data = new String[12];
+    new_data[0]="0.010773907";
+    new_data[1]="8.610746";
+    new_data[2]="4.4963107";
+    new_data[3]="0.047136";
+    new_data[4]="0.515427";
+    new_data[5]="0.852877";
+    new_data[6]="0.9720459";
+    new_data[7]="-1.3694834";
+    new_data[8]="9.696517";
+    new_data[9]="-0.0056152344";
+    new_data[10]="-0.049438477";
+    new_data[11]="0.5576782";
+    //0.010773907,8.610746,4.4963107,0.047136,0.515427,0.852877,0.9720459,-1.3694834,9.696517,-0.0056152344,-0.049438477,0.5576782 working
+    //0.9999999988939648,-0.9995820798966354,-0.9999999999999997,-0.9999988062118802,-0.9974031940544938,-1.0
+
+    //String result =learner.activity_predictor(new_data);
+    //System.out.println(result);
+
+    /**String[] new_data_1 =new String[12];
+    //-2.6252422,8.619126,-2.7030537,0.552147,0.5078,0.450302,-8.1881695,-1.2641385,0.038307227,-0.34222412,0.49102783,-0.016540527,walking
+    new_data_1[0]="-2.6252422";
+    new_data_1[1]="8.619126";
+    new_data_1[2]="-2.7030537";
+    new_data_1[3]="0.552147";
+    new_data_1[4]="0.5078";
+    new_data_1[5]="0.450302";
+    new_data_1[6]="-8.1881695";
+    new_data_1[7]="-1.2641385";
+    new_data_1[8]="0.038307227";
+    new_data_1[9]="-0.34222412";
+    new_data_1[10]="0.49102783";
+    new_data_1[11]="-0.016540527";
+    String result1 =learner.activity_predictor(new_data_1);
+    System.out.println(result1);
     /**
      * learner.train(activity_csv_url, preference_data_url)
      * learner.predictor get the result from predictor for new data
      * */
+    /**String[] new_data_2 = new String[12];
+    //-6.5565214,5.717354,5.6658783,0.185591,0.464146,0.413321,-20.580557,3.8498764,-0.4261679,0.7647095,-0.4713745,0.23999023,dancing
+    new_data_2[0]="-6.5565214";
+    new_data_2[1]="5.717354";
+    new_data_2[2]="5.6658783";
+    new_data_2[3]="0.185591";
+    new_data_2[4]="0.464146";
+    new_data_2[5]="0.413321";
+    new_data_2[6]="-20.580557";
+    new_data_2[7]="3.8498764";
+    new_data_2[8]="-0.4261679";
+    new_data_2[9]="0.7647095";
+    new_data_2[10]="-0.4713745";
+    new_data_2[11]="0.23999023";
+
+    String[] new_data_3 = new String[12];
+    new_data_3[0]="-5.3881507";
+    new_data_3[1]="0.25378537";
+    new_data_3[2]="7.69257";
+    new_data_3[3]="-0.122974";
+    new_data_3[4]="0.247411";
+    new_data_3[5]="0.439031";
+    new_data_3[6]="4.9224787";
+    new_data_3[7]="-10.601525";
+    new_data_3[8]="-4.927267";
+    new_data_3[9]="0.7946167";
+    new_data_3[10]="0.35272217";
+    new_data_3[11]="0.16192627";
+    //"-5.3881507","0.25378537","7.69257","-0.122974","0.247411","0.439031","4.9224787","-10.601525","-4.927267","0.7946167","0.35272217","0.16192627","lying"
     Learner learner=new Learner();
-    //learner.train("datasets/activity_data.csv", "datasets/preference_data.csv");
-    String[] result = learner.predictor(new_data);
+    //learner.train("datasets/backup/activity_data.csv", "datasets/preference_data.csv");
+    String[] result = learner.predictor(new_data_3);
     System.out.println("activity is:" + result[0]);
-    System.out.println("perference is: "+ result[1]);
+    //System.out.println("perference is: "+ result[1]);**/
+  }
+  public static void activity_validation_learner(){
+    ReadCSV csv = new ReadCSV("datasets/backup/activity_data.csv", false, CSVFormat.DECIMAL_POINT);
+    String[] line = new String[12];
+    Learner learner=new Learner();
+    int wrong=0;
+    int right=0;
+    while(csv.next()) {
+      StringBuilder result = new StringBuilder();
+      line[0] = csv.get(0);
+      line[1] = csv.get(1);
+      line[2] = csv.get(2);
+      line[3] = csv.get(3);
+      line[4] = csv.get(4);
+      line[5] = csv.get(5);
+      line[6] = csv.get(6);
+      line[7] = csv.get(7);
+      line[8] = csv.get(8);
+      line[9] = csv.get(9);
+      line[10] = csv.get(10);
+      line[11] = csv.get(11);
+      String correct = csv.get(12);
+      String irisChosen = learner.predictor(line)[0];
+      result.append(Arrays.toString(line));
+      result.append(" -> predicted: ");
+      result.append(irisChosen);
+      result.append("(correct: ");
+      result.append(correct);
+      result.append(")");
+      if (irisChosen.equals(correct)!=true){
+        System.out.println(correct);
+        System.out.println(irisChosen);
+        ++wrong;
+      }else{
+        ++right;
+      }
+      System.out.println(result.toString());
+    }
+    System.out.println("wrong number"+wrong);
+    System.out.println("right number"+right);
+    //double validation = (double(right))/(double(wrong+right));
+    //System.out.println("%.2f"+validation);
   }
 }

feedbackloop.learner_backup/src/main/java/de/tudresden/inf/st/eraser/feedbackloop.learner_backup/ReaderCSV.java

+package de.tudresden.inf.st.eraser.feedbackloop.learner_backup;
+
+import java.awt.*;
+import java.io.FileReader;
+import java.io.*;
+import java.util.Arrays;
+
+import com.opencsv.CSVReader;
+import org.apache.http.client.fluent.Request;
+import org.apache.http.HttpResponse;
+import org.apache.http.entity.ContentType;
+import org.apache.logging.log4j.LogManager;
+import org.apache.logging.log4j.Logger;
+import java.util.concurrent.locks.Lock;
+import java.util.concurrent.locks.Condition;
+import java.util.concurrent.locks.ReentrantLock;
+
+public class ReaderCSV{
+
+    //read every 5 s from csv
+    //activity CSV
+    /**
+     * Col 1: smartphone acceleration x
+     * Col 2: smartphone acceleration y
+     * Col 3: smartphone acceleration z
+     * Col 4: smartphone rotation x
+     * Col 5: smartphone rotation y
+     * Col 6: smartphone rotation z
+     * Col 7: watch acceleration x
+     * Col 8: watch acceleration y
+     * Col 9: watch acceleration z
+     * Col 10: watch rotation x
+     * Col 11: watch rotation y
+     * Col 12: watch rotation z/*/
+    //preference CSV
+    /**
+     * Col 1: Activity
+     * Col 2: watch brightness range "bright, medium, dimmer, dark"*/
+
+    private static int TIME_PERIOD = 5000; //5 second update new value
+    private String csv_file_path;
+    private String csv_typ;
+    private File file;
+    private FileReader file_reader;
+    private CSVReader csv_reader;
+    private String[] next_record;
+    private static final Logger logger = LogManager.getLogger(ReaderCSV.class);
+    private static final String ERASER_ITEM_URI = "http://localhost:4567/model/items/";
+    //TODO ITEM_NAME HAS TO BE DISCUSSED
+    private static final String[] ACTIVITY_ITEM_NAME = {
+            "m_accel_x", "m_accel_y", "m_accel_z", "m_rotation_x",
+            "m_rotation_y", "m_rotation_z", "w_accel_x", "w_accel_y",
+            "w_accel_z", "w_rotation_x", "w_rotation_y", "w_rotation_z"};
+    private static final String[] PREFERENCE_ITEM_NAME = {
+           "w_brightness"
+    };
+
+    //csv_type is activity or preference
+    public ReaderCSV(String csv_file_path, String csv_type) {
+        this.csv_file_path = csv_file_path;
+        this.csv_typ = csv_type;
+    }
+
+    public void updater(){
+        file=new File(csv_file_path);
+        try {
+            file_reader =new FileReader(file);
+            csv_reader = new CSVReader(file_reader);
+            while ((next_record = csv_reader.readNext()) != null) {
+                Thread.sleep(TIME_PERIOD);
+                if (csv_typ =="activity"){
+                    String[] values = Arrays.copyOf(next_record,12);
+                    setNewValue(values, ACTIVITY_ITEM_NAME);
+
+               } else {
+                    String[] values = Arrays.copyOf(next_record,2);
+                    setNewValue(values, PREFERENCE_ITEM_NAME);
+                    }
+                }
+            }
+        catch (Exception e){
+            e.printStackTrace();
+        }
+    }
+    private void setNewValue(String[] values, String[] name){
+        if(this.csv_typ.equals("activity"))
+        {
+            int i = 0;
+            for(String value : values){
+                String uri = ERASER_ITEM_URI + name[i] + "/state";
+                logger.info("reader:",value);
+                try {
+                    HttpResponse httpResponse = Request.Put(uri)
+                            .bodyString(value, ContentType.TEXT_PLAIN)
+                            .execute().returnResponse();
+                }catch (Exception e){
+                    e.printStackTrace();
+                }
+                i+=1;
+            }
+
+        }else{
+            String uri= ERASER_ITEM_URI + "w_brightness" +"/state";
+            logger.info("reader:",values[1]);
+            try {
+                HttpResponse httpResponse = Request.Put(uri)
+                        .bodyString(values[1], ContentType.TEXT_PLAIN)
+                        .execute().returnResponse();
+            }catch (Exception e){
+                e.printStackTrace();
+            }
+
+        }
+
+    }
+}
\ No newline at end of file

feedbackloop.learner_backup/src/test/java/de/tudresden/inf/st/eraser/feedbackloop.learner_backup/ATest.java

-package de.tudresden.inf.st.eraser.feedbackloop.learner_backup;
-
-import de.tudresden.inf.st.eraser.jastadd.model.*;
-import org.junit.Test;
-
-import java.util.Set;
-
-import static org.hamcrest.Matchers.*;
-import static org.junit.Assert.fail;
-
-/**
- * TODO: Add description.
- *
- * @author rschoene - Initial contribution
- */
-public class ATest {
-
-  @Test
-  public void test1() {
-    fail();
-  }
-}

feedbackloop.plan/src/main/java/de/tudresden/inf/st/eraser/feedbackloop/plan/PlanImpl.java

@@ -2,9 +2,7 @@ package de.tudresden.inf.st.eraser.feedbackloop.plan;
 
 import de.tudresden.inf.st.eraser.feedbackloop.api.Execute;
 import de.tudresden.inf.st.eraser.feedbackloop.api.Plan;
-import de.tudresden.inf.st.eraser.jastadd.model.Activity;
-import de.tudresden.inf.st.eraser.jastadd.model.ItemPreference;
-import de.tudresden.inf.st.eraser.jastadd.model.Root;
+import de.tudresden.inf.st.eraser.jastadd.model.*;
 import org.apache.logging.log4j.LogManager;
 import org.apache.logging.log4j.Logger;
 
@@ -38,9 +36,15 @@ public class PlanImpl implements Plan {
 
   @Override
   public void planToMatchPreferences(Activity activity) {
-    // TODO actually use activity
     logger.info("Plan got new activity [{}]: {}", activity.getIdentifier(), activity.getLabel());
     List<ItemPreference> preferences = knowledgeBase.currentPreferences();
+    knowledgeBase.getMachineLearningRoot().addChangeEvent(createRecognitionEvent(activity));
     informExecute(preferences);
   }
+
+  private ChangeEvent createRecognitionEvent(Activity activity) {
+    RecognitionEvent result = RecognitionEvent.createRecognitionEvent(knowledgeBase.getMachineLearningRoot().getActivityRecognition());
+    result.setActivity(activity);
+    return result;
+  }
 }

gradle/wrapper/gradle-wrapper.properties

+#Tue May 07 14:40:56 CEST 2019
 distributionBase=GRADLE_USER_HOME
 distributionPath=wrapper/dists
 zipStoreBase=GRADLE_USER_HOME
 zipStorePath=wrapper/dists
-distributionUrl=https\://services.gradle.org/distributions/gradle-4.10.2-bin.zip
+distributionUrl=https\://services.gradle.org/distributions/gradle-4.10.2-all.zip

learner_test/.gitignore

+/build/

learner_test/build.gradle

+repositories {
+    mavenCentral()
+}
+
+sourceCompatibility = 1.8
+
+apply plugin: 'java'
+apply plugin: 'application'
+
+dependencies {
+    compile project(':eraser-base')
+    compile group: 'com.fasterxml.jackson.core', name: 'jackson-databind', version: '2.8.8.1'
+    compile group: 'org.apache.logging.log4j', name: 'log4j-api', version: '2.10.0'
+    compile group: 'org.apache.logging.log4j', name: 'log4j-core', version: '2.10.0'
+    testCompile group: 'junit', name: 'junit', version: '4.12'
+    testCompile group: 'org.hamcrest', name: 'hamcrest-junit', version: '1.0.0.0'
+
+    compile 'org.encog:encog-core:3.4'
+}
+
+run {
+    mainClassName = 'de.tudresden.inf.st.eraser.learner_test.Main'
+    standardInput = System.in
+    if (project.hasProperty("appArgs")) {
+        args Eval.me(appArgs)
+    }
+}
+
+sourceSets {
+    main {
+        java {
+            srcDir 'src/main/java'
+        }
+    }
+}

learner_test/src/main/java/de/tudresden/inf/st/eraser/learner_test/Main.java

+package de.tudresden.inf.st.eraser.learner_test;
+import org.encog.Encog;
+import org.encog.ml.MLClassification;
+import org.encog.ml.data.MLData;
+import org.encog.persist.EncogDirectoryPersistence;
+import org.encog.util.csv.CSVFormat;
+import org.encog.util.csv.ReadCSV;
+import org.encog.util.simple.EncogUtility;
+
+import org.encog.ml.data.versatile.NormalizationHelper;
+import org.encog.ml.data.versatile.VersatileMLDataSet;
+import org.encog.ml.data.versatile.columns.ColumnDefinition;
+import org.encog.ml.data.versatile.columns.ColumnType;
+import org.encog.ml.data.versatile.sources.VersatileDataSource;
+import org.encog.ml.data.versatile.sources.CSVDataSource;
+import org.encog.ml.factory.MLMethodFactory;
+import org.encog.ml.model.EncogModel;
+import org.encog.ConsoleStatusReportable;
+import org.encog.ml.MLRegression;
+import java.io.File;
+import java.util.Arrays;
+import static org.encog.persist.EncogDirectoryPersistence.*;
+
+public class Main {
+
+  public static void main(String[] args) {
+    //mapping the data into model
+    String savefile = "src/main/java/de/tudresden/inf/st/eraser/learner_test/save_model.eg";
+    String File = "src/main/java/de/tudresden/inf/st/eraser/learner_test/preference_data.csv";
+    File file = new File(File);
+    VersatileDataSource source = new CSVDataSource(file, false, CSVFormat.DECIMAL_POINT);
+    VersatileMLDataSet data = new VersatileMLDataSet(source);
+    data.defineSourceColumn("monat", 0, ColumnType.continuous);
+    data.defineSourceColumn("day", 1, ColumnType.continuous);
+    data.defineSourceColumn("hour", 2, ColumnType.continuous);
+    data.defineSourceColumn("minute", 3, ColumnType.continuous);
+    ColumnDefinition outputColumn = data.defineSourceColumn("labels", 4, ColumnType.continuous);
+    data.defineSingleOutputOthersInput(outputColumn);
+    data.analyze();
+    System.out.println("get data ");
+    EncogModel model = new EncogModel(data);
+    model.selectMethod(data, MLMethodFactory.TYPE_FEEDFORWARD);
+    //model.setReport(new ConsoleStatusReportable());
+    data.normalize();
+    NormalizationHelper helper = data.getNormHelper();
+    System.out.println(helper.toString());
+    model.holdBackValidation(0.3, true, 1001);
+    model.selectTrainingType(data);
+    MLRegression bestMethod = (MLRegression)model.crossvalidate(5, true);
+    MLClassification bestMethodtest=(MLClassification)model.crossvalidate(5,true);
+    /**System.out.println( "Training error: " + EncogUtility.calculateRegressionError(bestMethod, model.getTrainingDataset()));
+    System.out.println( "testTraining error: " + EncogUtility.calculateClassificationError(bestMethodtest, model.getTrainingDataset()));
+    System.out.println( "Validation error: " + EncogUtility.calculateRegressionError(bestMethod, model.getValidationDataset()));
+    System.out.println( "testValidation error: " + EncogUtility.calculateClassificationError(bestMethodtest, model.getValidationDataset()));
+
+    System.out.println(helper.getClass());
+    System.out.println(helper.toString());
+    System.out.println("Final model: " + bestMethod);
+    System.out.println("Final testmodel: " + bestMethodtest);**/
+    //NormalizationHelper helper = data.getNormHelper();
+
+    //test
+    String helperstr=helper.toString();
+    String [] split=helperstr.split(";");
+    String [] finalStr = split[split.length-1].replace("]","").replace("[","").
+            split(",");
+    System.out.println(helper);
+
+    // save network...
+    //to delete
+    saveObject(new File(savefile), bestMethodtest);
+    ReadCSV csv = new ReadCSV(File, false, CSVFormat.DECIMAL_POINT);
+    String[] line = new String[4];
+    MLData input = helper.allocateInputVector();
+    System.out.println("input test---------------");
+    System.out.println(input);
+    while(csv.next()) {
+      StringBuilder result = new StringBuilder();
+      line[0] = csv.get(0);
+      line[1] = csv.get(1);
+      line[2] = csv.get(2);
+      line[3] = csv.get(3);
+      String correct = csv.get(4);
+      helper.normalizeInputVector(line,input.getData(),false);
+
+      MLData output = bestMethod.compute(input);
+      System.out.println("inputs:");
+      System.out.println(input);
+      System.out.println("outputs:");
+      System.out.println(output);
+      String brightnessChosen = helper.denormalizeOutputVectorToString(output)[0];
+
+      result.append(Arrays.toString(line));
+      result.append(" -> predicted: ");
+      result.append(brightnessChosen);
+      result.append("(correct: ");
+      result.append(correct);
+      result.append(")");
+      System.out.println(result.toString());
+      break;
+
+    }
+    // Delete data file and shut down.
+    //File.delete();
+    Encog.getInstance().shutdown();
+    /**Training error: 0.299928703107046
+    testTraining error: 0.9931740614334471
+    Validation error: 0.41277024952020763
+    testValidation error: 0.992*/
+
+  }
+}

learner_test/src/main/java/de/tudresden/inf/st/eraser/learner_test/final_data.csv

+7,20,12,13,2
+7,20,14,40,1
+7,20,14,40,2
+7,21,13,2,2
+7,21,13,2,2
+7,21,14,23,2
+7,21,14,23,2
+7,21,15,41,2
+7,21,16,54,2
+7,21,16,54,2
+7,21,17,45,3
+7,22,12,28,3
+7,22,15,35,2
+7,22,15,35,2
+7,22,18,59,3
+7,22,18,59,3
+7,23,12,32,2
+7,23,12,32,2
+7,23,16,7,2
+7,23,16,7,2
+7,23,16,7,2
+7,23,16,7,2
+7,23,16,7,2
+7,24,12,4,0
+7,24,12,4,0
+7,24,12,4,1
+7,24,14,38,2
+7,24,14,38,2
+7,24,18,54,3
+7,25,12,31,0
+7,25,12,32,1
+7,25,12,32,1
+7,25,15,6,3
+7,25,18,56,3
+7,26,13,41,2
+7,26,19,14,3
+7,27,11,39,2
+7,27,11,39,3
+7,27,11,46,3
+7,27,11,46,2
+7,27,13,8,2
+7,27,13,8,2
+7,27,13,9,2
+7,27,13,45,2
+7,27,13,45,2
+7,27,15,38,3
+7,28,12,12,2
+7,28,12,13,2
+7,28,12,41,2
+7,28,12,41,2
+7,28,12,41,2
+7,28,14,0,1
+7,28,14,0,2
+7,28,15,21,3
+7,28,18,56,3
+7,29,10,9,1
+7,29,10,9,1
+7,29,10,9,1
+7,29,11,54,0
+7,29,11,54,0
+7,29,11,54,0
+7,29,11,54,1
+7,29,14,10,2
+7,29,16,44,2
+7,29,16,44,2
+7,30,16,7,3
+7,30,18,45,3
+7,31,13,2,0
+7,31,13,2,1
+7,31,13,3,1
+7,31,13,3,1
+7,31,13,3,1
+7,31,18,39,3
+8,1,12,22,0
+8,1,12,22,1
+8,1,14,20,2
+8,1,14,20,2
+8,1,14,20,2
+8,1,15,55,3
+8,1,18,31,3
+8,1,18,37,3
+8,1,18,37,3
+8,1,19,2,3
+8,1,19,2,3
+8,1,20,5,3
+8,2,10,9,2
+8,2,10,9,1
+8,2,10,9,2
+8,2,10,9,2
+8,2,13,58,2
+8,2,13,58,2
+8,2,15,44,3
+8,2,15,44,3
+8,2,15,44,3
+8,2,17,21,3
+8,2,17,21,3
+8,2,17,21,3
+8,3,13,31,1
+8,3,13,31,2
+8,3,13,32,2
+8,3,16,43,3
+8,4,13,20,1
+8,4,13,20,2
+8,4,18,27,3
+8,5,13,37,2
+8,5,13,37,2
+8,5,18,33,3
+8,6,11,24,3
+8,6,11,24,3
+8,6,11,24,3
+8,6,13,50,3
+8,7,13,4,2
+8,7,13,4,2
+8,7,14,56,3
+8,8,12,13,2
+8,8,12,13,2
+8,8,15,51,2
+8,8,15,51,2
+8,8,15,51,3
+8,9,13,32,2
+8,9,13,32,2
+8,9,13,32,2
+8,9,15,8,2
+8,9,15,8,2
+8,9,15,8,2
+8,9,16,19,2
+8,10,11,32,0
+8,10,11,32,1
+8,10,11,32,1
+8,10,13,13,1
+8,10,13,13,1
+8,10,13,13,2
+8,10,16,42,3
+8,10,16,42,3
+8,11,14,6,2
+8,11,14,7,2
+8,11,18,54,3
+8,11,18,54,3
+8,11,18,54,3
+8,12,12,27,1
+8,12,12,27,1
+8,12,12,28,1
+8,12,13,53,2
+8,12,13,53,2
+8,12,13,53,2
+8,12,15,21,3
+8,13,13,16,1
+8,13,13,16,1
+8,13,13,16,1
+8,13,14,14,2
+8,13,14,14,2
+8,13,16,11,3
+8,13,17,18,3
+8,14,13,7,1
+8,14,13,7,1
+8,14,13,7,1
+8,14,13,7,1
+8,14,13,7,2
+8,14,13,7,2
+8,14,15,6,3
+8,15,14,5,2
+8,15,14,5,2
+8,15,14,6,2
+8,15,14,6,2
+8,15,16,41,3
+8,15,16,41,3
+8,15,17,30,3
+8,16,13,40,2
+8,16,13,40,2
+8,16,17,52,3
+8,16,17,53,3
+8,17,13,34,1
+8,17,13,35,2
+8,17,14,7,2
+8,17,19,2,3
+8,18,10,21,3
+8,18,11,14,2
+8,18,11,14,2
+8,18,11,14,2
+8,18,11,14,2
+8,18,14,25,2
+8,18,14,25,3
+8,18,14,25,2
+8,18,18,18,3
+8,18,18,19,3
+8,19,18,33,3
+8,19,18,33,3
+8,19,18,33,3
+8,19,18,33,3
+8,20,14,28,2
+8,20,14,28,2
+8,20,14,28,2
+8,20,14,28,2
+8,20,17,8,3
+8,20,18,22,3
+8,21,11,24,1
+8,21,11,24,1
+8,21,11,24,1
+8,21,15,34,3
+8,21,18,55,3
+8,22,12,3,1
+8,22,12,4,2
+8,22,12,4,2
+8,22,13,51,2
+8,22,13,51,2
+8,22,13,51,2
+8,22,18,12,3
+8,22,18,12,3
+8,22,18,12,3
+8,22,18,12,3
+8,22,18,40,3
+8,22,18,40,3
+8,23,13,42,1
+8,23,13,42,1
+8,23,17,32,3
+8,23,19,28,3
+8,23,20,27,3
+8,23,20,27,3
+8,23,21,49,3
+8,24,14,0,2
+8,24,14,0,2
+8,24,14,0,2
+8,24,14,0,2
+8,24,15,4,3
+8,24,15,4,3
+8,24,16,2,3
+8,24,16,3,3
+8,24,16,37,3
+8,24,17,9,3
+8,24,17,14,3
+8,25,13,34,1
+8,25,13,34,1
+8,25,13,34,1
+8,25,13,34,1
+8,25,13,34,1
+8,25,15,1,3
+8,25,17,58,3
+8,26,10,29,0
+8,26,10,29,0
+8,26,10,29,0
+8,26,10,29,0
+8,26,10,29,0
+8,26,16,42,3
+8,26,16,42,3
+8,26,18,41,3
+8,26,18,41,3
+8,27,13,41,2
+8,27,13,41,2
+8,27,13,41,2
+8,27,13,41,2
+8,27,17,42,3
+8,28,11,9,1
+8,28,11,9,1
+8,28,12,14,0
+8,28,12,14,1
+8,28,12,14,0
+8,28,15,3,2
+8,28,15,3,2
+8,28,16,31,3
+8,28,17,40,3
+8,29,14,44,3
+8,29,17,25,3
+8,30,12,5,0
+8,30,12,5,0
+8,30,12,5,0
+8,30,13,32,1
+8,30,13,32,1
+8,30,13,56,2
+8,30,14,23,2
+8,30,14,23,2
+8,30,14,23,2
+8,30,14,23,2
+8,30,14,41,2
+8,30,14,41,2
+8,30,14,41,2
+8,30,15,50,3
+8,30,17,0,3
+8,30,18,59,3
+8,30,18,59,3
+8,31,14,31,2
+8,31,14,31,2
+8,31,14,31,2
+8,31,17,59,3
+8,31,18,0,3
+9,1,16,13,3
+9,1,16,13,3
+9,1,16,13,3
+9,1,17,41,3
+9,2,13,44,1
+9,2,13,44,1
+9,2,13,44,1
+9,2,14,49,2
+9,2,14,49,2
+9,2,14,49,2
+9,2,16,6,3
+9,2,16,6,3
+9,2,17,2,3
+9,3,16,9,3
+9,3,17,35,3
+9,3,17,36,3
+9,4,12,57,1
+9,4,12,57,1
+9,4,15,8,3
+9,4,15,34,3
+9,4,16,26,3
+9,4,16,26,3
+9,4,18,37,3
+9,4,18,37,3
+9,4,18,37,3
+9,6,11,18,0
+9,6,11,18,0
+9,6,12,54,1
+9,6,12,54,1
+9,6,14,21,2
+9,6,14,21,2
+9,6,19,20,3
+9,7,11,50,0
+9,7,14,17,2
+9,7,14,57,3
+9,7,14,57,3
+9,7,16,56,3
+9,7,16,56,3
+9,7,16,56,3
+9,7,16,56,3
+9,7,18,38,3
+9,7,18,38,3
+9,8,11,4,2
+9,8,11,4,2
+9,8,11,13,0
+9,8,11,13,0
+9,8,11,13,0
+9,8,11,13,0
+9,8,11,13,0
+9,8,11,14,0
+9,8,11,14,1
+9,8,11,14,1
+9,8,12,1,0
+9,8,12,1,0
+9,8,12,1,0
+9,8,12,1,0
+9,8,12,1,0
+9,8,12,1,1
+9,8,12,36,0
+9,8,12,36,0
+9,8,12,36,0
+9,8,12,36,0
+9,8,12,36,0
+9,8,13,37,1
+9,8,13,37,1
+9,8,13,37,1
+9,8,14,20,2
+9,8,14,20,2
+9,8,18,20,3
+9,9,12,47,1
+9,9,12,47,2
+9,9,12,47,2
+9,9,19,5,3
+9,10,13,15,1
+9,10,13,15,1
+9,10,13,15,0
+9,10,16,49,3
+9,10,19,6,3
+9,10,21,5,3
+9,11,14,16,2
+9,11,14,16,2
+9,11,14,16,2
+9,11,18,41,3
+9,12,14,43,2
+9,12,14,43,2
+9,12,14,43,2
+9,12,16,14,3
+9,12,17,12,3
+9,12,17,12,2
+9,12,17,12,3
+9,12,17,12,2
+9,12,20,44,3
+9,13,19,52,3
+9,14,14,39,2
+9,14,14,39,2
+9,14,15,14,3
+9,14,17,29,3
+9,14,17,29,3
+9,14,17,29,3
+9,15,11,41,1
+9,15,11,41,1
+9,15,13,4,1
+9,15,14,3,1
+9,15,14,3,2
+9,16,12,36,1
+9,16,12,36,1
+9,16,12,36,1
+9,16,12,36,1
+9,16,12,48,1
+9,16,12,48,1
+9,16,13,51,1
+9,16,13,51,2
+9,16,13,51,1
+9,16,15,13,3
+9,16,15,14,3
+9,16,15,14,3
+9,17,10,27,0
+9,17,10,27,0
+9,17,11,10,0
+9,17,11,10,0
+9,17,11,10,0
+9,17,12,43,1
+9,17,12,43,1
+9,17,12,43,1
+9,17,13,32,1
+9,17,13,32,1
+9,17,14,5,1
+9,17,14,5,2
+9,17,14,6,2
+9,17,15,7,3
+9,17,15,49,3
+9,17,15,49,3
+9,17,18,12,3
+9,17,18,13,3

learner_test/src/main/java/de/tudresden/inf/st/eraser/learner_test/save_model.eg

+encog,BasicNetwork,java,3.4.0,1,1554196571101
+[BASIC]
+[BASIC:PARAMS]
+[BASIC:NETWORK]
+beginTraining=0
+connectionLimit=0
+contextTargetOffset=0,0,0
+contextTargetSize=0,0,0
+endTraining=2
+hasContext=f
+inputCount=4
+layerCounts=1,8,5
+layerFeedCounts=1,7,4
+layerContextCount=0,0,0
+layerIndex=0,1,9
+output=0.2537517424,0.3154675575,-0.8739039638,-0.4408848221,-0.8484433638,-0.999915299,-0.6964984771,-0.208278439,1,0,0,-0.4545454545,0.3559322034,1
+outputCount=1
+weightIndex=0,8,43
+weights=0.5976774048,-0.7925906525,0.7127327881,-0.9611660362,0.8031350986,-0.7286657218,1.0990482817,-0.5985785536,-0.0783115433,0.575612931,1.1267500918,1.7184744034,0.2271044512,-1.0525796764,0.0900869671,1.1492323512,0.6141715555,-1.0455927965,-0.0925453451,0.2471651431,2.3634316872,0.3939369257,0.4607437082,-0.1435186798,0.8428535365,-0.0848896791,-0.070602589,-1.2640263565,2.4899996734,-0.2185394776,10.3421332361,-0.1650898311,-0.2750133571,-0.79680959,-0.8051139953,0.8219933747,-0.0727160299,-0.4609522002,-1.0410685492,-0.5354063412,0.3028724456,-0.6835374219,0.169591233
+biasActivation=0,1,1
+[BASIC:ACTIVATION]
+"org.encog.engine.network.activation.ActivationTANH"
+"org.encog.engine.network.activation.ActivationTANH"
+"org.encog.engine.network.activation.ActivationLinear"

learner_test/src/main/java/de/tudresden/inf/st/eraser/learner_test/save_model_test.eg

+encog,BasicNetwork,java,3.4.0,1,1548158734516
+[BASIC]
+[BASIC:PARAMS]
+[BASIC:NETWORK]
+beginTraining=0
+connectionLimit=0
+contextTargetOffset=0,0,0
+contextTargetSize=0,0,0
+endTraining=2
+hasContext=f
+inputCount=4
+layerCounts=4,8,5
+layerFeedCounts=4,7,4
+layerContextCount=0,0,0
+layerIndex=0,4,12
+output=0.6991387348,-0.8711034513,-0.996886038,-0.832747291,-0.0935682806,-0.9996163977,0.5399150265,0.9411173394,-0.5084989975,0.4850010791,0.9999999957,1,0,-0.6666666667,-0.4545454545,0.6949152542,1
+outputCount=4
+weightIndex=0,32,67
+weights=-2.6901880743,0.6512821123,-1.2270002115,1.63124668,0.1982387305,-0.2994789552,1.5833040739,-0.9450411677,2.0541422847,-0.718279397,-1.1761952241,0.5028631512,0.0690323612,-1.496141565,-0.1955149568,-0.7453976822,-0.3691141073,0.9854755554,2.2113850088,-1.5216550292,0.9652087936,-1.3028209693,-1.3346156171,0.4142247818,1.0821207364,0.1987534858,0.6202881884,-0.2940331887,-1.4643282498,2.6960334656,-0.0167663298,-2.9907087565,0.3469960227,-0.0441249736,-2.5998575813,-0.7106361301,-0.8111809962,2.2216158678,-0.5482762437,-1.7996398291,-3.6734127565,-2.9102547958,0.4845401914,0.3760471288,-0.0124987546,0.3784047483,0.5860932613,-0.2682876707,0.7429004186,-7.559247176,-3.4421363532,1.1989747484,-2.3340717496,-1.4740773042,-0.7795788072,-1.8241693655,-0.630132295,-0.8191869009,-0.4060569987,-1.0997423162,-0.5495165849,0.1407829068,-2.2964930412,0.0798893221,-19.5271913755,2.0474187009,-0.2622671892
+biasActivation=0,1,1
+[BASIC:ACTIVATION]
+"org.encog.engine.network.activation.ActivationTANH"
+"org.encog.engine.network.activation.ActivationTANH"
+"org.encog.engine.network.activation.ActivationLinear"

learner_test/src/main/resources/log4j2.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<Configuration>
+    <Appenders>
+        <Console name="Console">
+            <PatternLayout pattern="%highlight{%d{HH:mm:ss.SSS} %-5level} %c{1.} - %msg%n"/>
+        </Console>
+        <RollingFile name="RollingFile" fileName="logs/jastadd-mquat.log"
+                    filePattern="logs/jastadd-mquat-%i.log">
+            <PatternLayout pattern="%d{HH:mm:ss.SSS} %-5level %logger{36} - %msg%n"/>
+            <Policies>
+                <OnStartupTriggeringPolicy/>
+            </Policies>
+            <DefaultRolloverStrategy max="20"/>
+        </RollingFile>
+    </Appenders>
+    <Loggers>
+        <Root level="debug">
+            <AppenderRef ref="Console"/>
+            <AppenderRef ref="RollingFile"/>
+        </Root>
+    </Loggers>
+</Configuration>