blank label support for fpof and better error message for pbad

src/main/java/be/uantwerpen/datamining/pattern_mining/RunPBADEmbeddingOnly.java

@@ -113,6 +113,12 @@ public class RunPBADEmbeddingOnly {
 		status = CommandLineUtils.runCommandInUserDir(command, log, 10);
 		if(status != 0) {
 			String logStr = IOUtils.readFileFlat(log);
+
+
+			if(logStr.contains("Expecting column label")) {
+				throw new RuntimeException("The data is not labelled you need a column named 'label'");
+			}
+
 			System.err.println("Error running PBAD. Log:");
 			System.err.println(logStr);
 			System.err.println(usagePBADInstall);

src/main/java/be/uantwerpen/mime_webapp/controller/PatternMiningController.java

@@ -196,15 +196,19 @@ public class PatternMiningController {
 	}
 
 	private Map<Integer, Integer> getWindowLabels(File itemFile) throws IOException {
-		// timestamp,value,label,Window
 		Table window2label = MakePatternOccurrences.groupByWindow(itemFile,0,Integer.MAX_VALUE);
 		Map<Integer,Integer> window2LabelMap = new HashMap<>();
+		// timestamp,value,label,Window
 		List<String> columns = window2label.getRows().get(0);
 		int windowIdx = columns.indexOf("Window");
 		int labelIdx = columns.indexOf("label");
 		for(List<String> row: window2label.getRowsStartingFrom1()) {
+			if (labelIdx == -1) {
+				window2LabelMap.put(Integer.valueOf(row.get(windowIdx)), -1);
+			} else {
 				List<String> labels = Arrays.asList(row.get(labelIdx).split(";"));
 				int label = -1;
+				//TODO: dangerous aproximation
 				if(labels.contains("1.0")) {
 					label = 1;
 				}
@@ -216,6 +220,7 @@ public class PatternMiningController {
 				}
 				window2LabelMap.put(Integer.valueOf(row.get(windowIdx)), label); //window->label
 			}
+		}
 		return window2LabelMap;
 	}
 
@@ -537,7 +542,7 @@ public class PatternMiningController {
 			File patternOccFile = new File(Settings.FILE_FOLDER + patternSet.get().getFilenameOccurrences());
 			Table occ = CSVUtils.loadCSV(patternOccFile);
 			for(int i=1; i<occ.getRows().size(); i++) {
-				int windowId = Integer.valueOf(occ.getRows().get(i).get(0));
+				int windowId = Integer.parseInt(occ.getRows().get(i).get(0));
 				//int patternId = Integer.valueOf(occ.getRows().get(i).get(1));
 				countsPerWindow.add(windowId);
 				if(i == 1) {
@@ -631,8 +636,7 @@ public class PatternMiningController {
 		Table scores = CSVUtils.loadCSV(scoreFile);
 		scores.getRows().get(0).add("Label");
 		for(List<String> row: scores.getRowsStartingFrom1()) {
-			Integer window = Integer.valueOf(row.get(0));
-			Double score = Double.valueOf(row.get(1));
+			int window = Integer.parseInt(row.get(0));
 			Integer label = window2LabelMap.get(window);
 			row.add(String.valueOf(label));
 		}
@@ -673,7 +677,7 @@ public class PatternMiningController {
 			//AP: 0.259
 			//<Finished took  1.04 seconds
 
-			Map<String,Double> evalMap = new HashMap<String,Double>();
+			Map<String,Double> evalMap = new HashMap<>();
 			try {
 				Double auc = Double.valueOf(logStr.get(logStr.size()-3).split(":")[1]);
 				Double ap = Double.valueOf(logStr.get(logStr.size()-2).split(":")[1]);

src/main/python/compute_anomaly_evaluation.py

+#!/bin/python3
 """
 Compute evaluation scores in python
 
 authors: Len Feremans
 created: July 2019
 
-Used for integration with TIPM: A tool voor Interactive time series 
+Used for integration with TIPM: A tool for Interactive time series
 pattern mining and anomaly detection. (https://bitbucket.org/len_feremans/tipm_pub).
 
 Compute evaluation scores in Python, since Java libraries for computing those are harder to find/use?
 """
-import sys,os
+import sys
+import os
 import pandas as pd
 import numpy as np
-import sklearn
 from sklearn.metrics import roc_auc_score, average_precision_score
+
+
+def has_multiple_values(data_block) -> bool:
+    prev_val = data_block[0]
+    for val in data_block:
+        if prev_val != val:
+            return True
+    return False
+
+
 if __name__ == '__main__':
     # get file argument
     arguments = sys.argv
@@ -27,7 +38,7 @@ if __name__ == '__main__':
     df = pd.read_csv(score_and_labels_file)
     if list(df.columns.values) != ["Window", "Score", "Label"]:
         print("Error: expecting [Window,Score,Label] as columns")
-        print(cols)
+        print(df.columns.values)
         sys.exit(-1)
     # compute evaluation score
     windows = df['Window'].values
@@ -37,7 +48,10 @@ if __name__ == '__main__':
         scores = 1.0 - scores
     window_labels = df['Label'].values
     ixl = np.where(window_labels != 0)[0]
-    auc = roc_auc_score(y_true=window_labels[ixl], y_score=scores[ixl])
+
+
+    # the roc score is a methode of evaluating reliability but it doesn't work if we didn't properly fill in the labels
+    auc = roc_auc_score(y_true=window_labels[ixl], y_score=scores[ixl]) if has_multiple_values(window_labels) else 0
     ap = average_precision_score(y_true=window_labels[ixl], y_score=scores[ixl])
     print("AUC: {:.3f}".format(auc))
     print("AP: {:.3f}".format(ap))