Changeset 34800

Timestamp:

2021-02-02T23:36:58+13:00 (3 years ago)

Author:

davidb

Message:

Perform Arousal and Valence prediction at the same time

Location:

main/trunk/model-sites-dev/mars

Files:

• RUN-APPLY-AV-MODELS.sh (added)
• src/java/org/greenstone/mars/WekaApplyAVModels.java (added)
• src/java/org/greenstone/mars/WekaUtil.java (modified) (6 diffs)

main/trunk/model-sites-dev/mars/src/java/org/greenstone/mars/WekaUtil.java

@@ -38 +38 @@
     if (args.length != 2) {
         System.err.println("Error: incorrect number of command-line arguments");
-        System.err.println("Usage: input_training_data.arff output-model.{model|ser}");
+        System.err.println("Usage: input_training_data.arff output-serialized.model");
         System.exit(1);
     }
@@ -48 +48 @@
         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);
-    }
-    }
-    
+        System.err.println("Usage: trained-serialized.model unclassified-data.{arff|csv} classified-data.{arff|csv}");
+        System.exit(1);
+    }
+    }
+
+    public static void checkUsageApplyAVModels(String[] args)
+    {
+        if (args.length != 4) {
+        System.err.println("Error: incorrect number of command-line arguments");
+        System.err.println("Usage: arousal-serialized.model valence-serialized.model unclassified-data.{arff|csv} classified-data.{arff|csv}");
+        System.exit(1);
+    }
+    }
+
     public static Instances applyFilter(Instances data_instances, String additional_remove)
     {
@@ -246 +255 @@
     {
     Instances filtered_unlabeled_instances = null;
-
-        
-    // Work out if we're dealing with a ground-truth ARFF file or not
-    // (i.e. already has the desired attribute)
-
-    //Attribute predict_attribute = unlabeled_instances.attribute(predict_attribute_name);
-
+        
     if (!has_groundtruth_data) {
 
-        filtered_unlabeled_instances = WekaUtil.applyFilter(unlabeled_instances,null); // no additional top-up to remove        
+        filtered_unlabeled_instances = applyFilter(unlabeled_instances,null); // no additional top-up to remove     
         int num_attributes = filtered_unlabeled_instances.numAttributes();
         
@@ -270 +273 @@
         
         // Need to massage instances into same form as an unclassified data input file
-        filtered_unlabeled_instances = WekaUtil.applyFilter(unlabeled_instances,additional_attribute_remove); 
+        filtered_unlabeled_instances = applyFilter(unlabeled_instances,additional_attribute_remove); 
         
         // reference share this as 'groundtruth_instances' to trigger error calculation and output
@@ -282 +285 @@
     filtered_unlabeled_instances.setClassIndex(num_attributes - 1);
     
-    // ***** Do I still want to run the check????
-    WekaUtil.checkDatasetInstancesCompatible(filtered_unlabeled_instances, additional_attribute_remove);
-    
     return filtered_unlabeled_instances;
+    }
+
+    public static void appendUnclassifiedAttribute(Instances data_instances, String predict_attribute_name)
+    {
+    Instances filtered_unlabeled_instances = null;
+        
+    int num_attributes = data_instances.numAttributes();
+        
+    Attribute new_predict_attribute = new Attribute(predict_attribute_name);
+    data_instances.insertAttributeAt(new_predict_attribute,num_attributes);
+    num_attributes++;       
+
+    // Set class attribute
+    data_instances.setClassIndex(num_attributes - 1);
     }
 
@@ -328 +342 @@
     return labeled_instances;
     }
-    
+
+
+    // https://waikato.github.io/weka-wiki/formats_and_processing/save_instances_to_arff/
 }