Changeset 34774

Timestamp:

2021-02-01T00:25:56+13:00 (3 years ago)

Author:

davidb

Message:

Development of code and resulting test runs to train and apply model

Location:

main/trunk/model-sites-dev/mars

Files:

• RUN-APPLY-AROUSAL-MODEL.sh (modified) (1 diff)
• WekaApplyArousalModel.java (modified) (4 diffs)
• WekaTrainArousalModel.java (modified) (3 diffs)

main/trunk/model-sites-dev/mars/RUN-APPLY-AROUSAL-MODEL.sh

@@ -3 +3 @@
 . ./_set_weka_classpath.bash
 
-java -cp "$cp_args" \
-     WekaApplyArousalModel "reptree-arousal-serialized.model"
+java -cp "$cp_args" WekaApplyArousalModel \
+     "reptree-arousal-serialized.model" \
+     "collect/deam/etc/deam-essentia-features-arousal-valence.arff" \
+     "predicted-arousal.csv"
 
 

main/trunk/model-sites-dev/mars/WekaApplyArousalModel.java

@@ -1 +1 @@
 //import java.util.Random;
 
+import java.io.BufferedInputStream;
+import java.io.FileInputStream;
+
+import java.io.BufferedReader;
+import java.io.BufferedWriter;
+import java.io.FileReader;
+import java.io.FileWriter;
+
 import weka.core.converters.ConverterUtils.DataSource;
+import weka.core.Instance;
 import weka.core.Instances;
 import weka.core.SerializationHelper;
@@ -13 +22 @@
 
 
-import java.io.BufferedInputStream;
-import java.io.FileInputStream;
 
-//import java.io.BufferedReader;
-//import java.io.BufferedWriter;
-//import java.io.FileReader;
-//import java.io.FileWriter;
-import weka.core.Instances;
+//import weka.core.Instances;
 
 
@@ -30 +33 @@
     public static void main(String[] args)
     {
-    String classifier_input_filename = args[0];
-        System.out.println("Loading Weka saved Classifier:" + classifier_input_filename);
+    if (args.length != 3) {
+        System.err.println("Error: incorrect number of command-line arguments");
+        System.err.println("Usage: trained-model.{model|ser} unclassified-data.{arff|csv} classified-data.{arff|csv}");
+        System.exit(1);
+    }
+        
+    String classifier_input_filename        = args[0];
+    String unclassified_data_input_filename = args[1];
+    String classified_data_output_filename  = args[2];
+
+        System.out.println("Loading Weka saved Classifier: " + classifier_input_filename);
 
     try {
@@ -38 +50 @@
         Classifier classifier = (Classifier)SerializationHelper.read(bis);
     
-    /*
+    
 
-    // load unlabeled data
-    Instances unlabeled = new Instances(
-                        new BufferedReader(
-                                   new FileReader("/some/where/unlabeled.arff")));
+        // load unlabeled data
+        System.out.println("Loading unlabeled instances: " + unclassified_data_input_filename);
+        FileReader fr = new FileReader(unclassified_data_input_filename);
+        BufferedReader br = new BufferedReader(fr);
+        Instances gt_instances = new Instances(br);
+        br.close();
+
+        // set class attribute
+        gt_instances.setClassIndex(gt_instances.numAttributes() - 2);
+        
+        // create copy
+        Instances unlabeled_instances = new Instances(gt_instances);    
+        Instances labeled_instances = new Instances(unlabeled_instances);
     
-    // set class attribute
-    unlabeled.setClassIndex(unlabeled.numAttributes() - 1);
-    
-    // create copy
-    Instances labeled = new Instances(unlabeled);
-    
-    // label instances
-    for (int i = 0; i < unlabeled.numInstances(); i++) {
-        double clsLabel = tree.classifyInstance(unlabeled.instance(i));
-        labeled.instance(i).setClassValue(clsLabel);
-    }
-    // save labeled data
-    BufferedWriter writer = new BufferedWriter(
-                           new FileWriter("/some/where/labeled.arff"));
-    writer.write(labeled.toString());
-    writer.newLine();
-    writer.flush();
-    writer.close();
-    */
-    
-    /*
+        // label instances
+        final int num_instances = unlabeled_instances.numInstances();       
+        for (int i=0; i<num_instances; i++) {
+        Instance unlabeled_instance = unlabeled_instances.instance(i);
+        System.out.print("Making prediction for: " + i + "/" + num_instances);
+        double classified_label = classifier.classifyInstance(unlabeled_instance);
+        labeled_instances.instance(i).setClassValue(classified_label);
 
-    try {
-        DataSource data_source = new DataSource(arff_input_filename);
-        Instances data_instances = data_source.getDataSet();
+        Instance gt_instance = gt_instances.instance(i);
+        double gt_class_value = gt_instance.classValue();
+        System.out.println("  error: " + Math.abs(classified_label-gt_class_value));
+        }
 
 
-        // Filter out Valence
-        String[] filter_options = weka.core.Utils.splitOptions("-R 472");
-        //String[] filter_options = weka.core.Utils.splitOptions("-R 472 -R 458-466");
-        Remove filter_remove = new Remove();
-        filter_remove.setOptions(filter_options);
-        filter_remove.setInputFormat(data_instances);
-        Instances filtered_data_instances = Filter.useFilter(data_instances, filter_remove);
-        filtered_data_instances.setClassIndex(filtered_data_instances.numAttributes() - 1);
+        // save labeled data            
+        System.out.println("Saving labeled instances: " + classified_data_output_filename);     
+        FileWriter fw = new FileWriter(classified_data_output_filename);
+        BufferedWriter bw = new BufferedWriter(fw);
         
-
-        // Build scheme/classifier
-        REPTree classifier = new REPTree(); // scheme
-        String[] reptree_options = weka.core.Utils.splitOptions("-M 2 -V 0.001 -N 3 -S 1 -L -1 -I 0.0");
-        classifier.setOptions(reptree_options);
-
-        classifier.buildClassifier(filtered_data_instances);
-        System.out.println(classifier);
-
-
-        Evaluation eval = new Evaluation(filtered_data_instances);
-        Random rand = new Random(1);
-        int folds = 10;
-        eval.crossValidateModel(classifier, filtered_data_instances, folds, rand);
-        System.out.println(eval.toSummaryString());
-
-        weka.core.SerializationHelper.write("reptree-model.ser", classifier);
-    */
-        
-         
+        bw.write(labeled_instances.toString());
+        bw.newLine();
+        bw.flush();
+        bw.close();
+             
     }
     catch (Exception e) {

main/trunk/model-sites-dev/mars/WekaTrainArousalModel.java

@@ -42 +42 @@
     String output_model_filename = args[1];
     
-        System.out.println("Training on ARFF file:" + input_arff_filename);
+        System.out.println("Training on ARFF file: " + input_arff_filename);
 
     try {
@@ -48 +48 @@
         Instances data_instances = data_source.getDataSet();
 
-
         // Filter out Valence
-        String[] filter_options = weka.core.Utils.splitOptions("-R 472");
+        //String[] filter_options = weka.core.Utils.splitOptions("-R 472");
         //String[] filter_options = weka.core.Utils.splitOptions("-R 472 -R 458-466");
+        String[] filter_options = weka.core.Utils.splitOptions("-R 472,458-466");
         Remove filter_remove = new Remove();
         filter_remove.setOptions(filter_options);
         filter_remove.setInputFormat(data_instances);
         Instances filtered_data_instances = Filter.useFilter(data_instances, filter_remove);
+
+        // **** have removed R472, so class to predict is numAttributes()-1
         filtered_data_instances.setClassIndex(filtered_data_instances.numAttributes() - 1);
         
@@ -74 +76 @@
         System.out.println(eval.toSummaryString());
 
-        System.out.println("Saving REPTree classifier model as:" + output_model_filename);
+        System.out.println("Saving REPTree classifier model as: " + output_model_filename);
         weka.core.SerializationHelper.write(output_model_filename, classifier);