Comparing two LinkedHashMaps with values as a list

Question

I've asked this question in different ways a couple of times already. Each time I get a breakthrough I encounter another issue. This is also due to the fact that I am not proficient in Java yet and have difficulty with collections like Maps. So please bear with me.

I have two maps like this:

Map1 -{ORGANIZATION=[Fulton Tax Commissioner 's Office, Grady Hospital, Fulton Health Department], LOCATION=[Bellwood, Alpharetta]}

Map2 - {ORGANIZATION=[Atlanta Police Department, Fulton Tax Commissioner, Fulton Health Department], LOCATION=[Alpharetta], PERSON=[Bellwood, Grady Hospital]}

The maps are defined as : LinkedHashMap<String, List<String>> sampleMap = new LinkedHashMap<String, List<String>>();

I am comparing these two maps based on the values and there are only 3 keys i.e ORGANIZATION, PERSON and LOCATION. Map1 is my goldset that I am comparing Map2 against. Now the problem that I am facing is when I iterate over the values of ORGANIZATION key in Map1 and check for matches in Map2, even though my first entry does have a partial match in Map2 (Fulton Tax Commissioner) but because the first entry of Map2 (Atlanta Police Department) is not a match I get an incorrect result(I am looking for exact and partial matches both). The result here being increment the true positive, false positive and false negative counters which enable me to ultimately calculate precision and recall for this i.e. Named Entity Recognition.

EDIT

The result I am expecting for this is

Organization: 
True Positive Count = 2
False Negative Count = 1
False Positive Count = 1

Person:
False Positive Count = 2

Location:
True Positive Count = 1
False Negative Count = 1

The output I am currently getting is :

Organization: 
    True Positive Count = 1
    False Negative Count = 2
    False Positive Count = 0

    Person:
    True Positive Count = 0
    False Negative Count = 0
    False Positive Count = 2

    Location:
    True Positive Count = 0
    False Negative Count = 1
    False Positive Count = 0

CODE

private static List<Integer> compareMaps(LinkedHashMap<String, List<String>> annotationMap, LinkedHashMap<String, List<String>> rageMap) 
    {
        List<Integer> compareResults = new ArrayList<Integer>();  

         if (!annotationMap.entrySet().containsAll(rageMap.entrySet())){
               for (Entry<String, List<String>> rageEntry : rageMap.entrySet()){
                   if (rageEntry.getKey().equals("ORGANIZATION") && !(annotationMap.containsKey(rageEntry.getKey()))){
                       for (int j = 0; j< rageEntry.getValue().size(); j++) {
                           orgFalsePositiveCount++;
                       }
               }
                   if (rageEntry.getKey().equals("PERSON") && !(annotationMap.containsKey(rageEntry.getKey()))){
                      // System.out.println(rageEntry.getKey());
                      // System.out.println(annotationMap.entrySet());
                       for (int j = 0; j< rageEntry.getValue().size(); j++) {
                           perFalsePositiveCount++;
                       }
               }
                   if (rageEntry.getKey().equals("LOCATION") && !(annotationMap.containsKey(rageEntry.getKey()))){
                       for (int j = 0; j< rageEntry.getValue().size(); j++) {
                           locFalsePositiveCount++;
                     }
                 }
              }
           }



               for (Entry<String, List<String>> entry : annotationMap.entrySet()){

                   int i_index = 0;
                   if (rageMap.entrySet().isEmpty()){
                       orgFalseNegativeCount++;
                       continue;
                   }

                  // for (Entry<String, List<String>> rageEntry : rageMap.entrySet()){

                   if (entry.getKey().equals("ORGANIZATION")){
                       for(String val : entry.getValue()) {
                           if (rageMap.get(entry.getKey()) == null){
                               orgFalseNegativeCount++;
                               continue;
                       }
            recusion:      for (int i = i_index; i< rageMap.get(entry.getKey()).size();){
                                String rageVal = rageMap.get(entry.getKey()).get(i);
                               if(val.equals(rageVal)){
                                   orgTruePositiveCount++;
                                   i_index++;
                                   break recusion;
                       }

                           else if((val.length() > rageVal.length()) && val.contains(rageVal)){  //|| dataB.get(entryA.getKey()).contains(entryA.getValue())){
                               orgTruePositiveCount++;
                               i_index++;
                               break recusion;
                       }
                           else if((val.length() < rageVal.length()) && rageVal.contains(val)){
                               orgTruePositiveCount++;
                                i_index++;
                                break recusion;
                           }

                           else if(!val.contains(rageVal)){
                               orgFalseNegativeCount++;
                               i_index++;
                               break recusion;
                           }
                           else if(!rageVal.contains(val)){
                                 orgFalsePositiveCount++;
                                 i_index++;
                                 break recusion;
                             }


                      }
                    }
                   }

                  ......................... //(Same for person and location)


                    compareResults.add(orgTruePositiveCount); 
                    compareResults.add(orgFalseNegativeCount); 
                    compareResults.add(orgFalsePositiveCount);  
                    compareResults.add(perTruePositiveCount); 
                    compareResults.add(perFalseNegativeCount);  
                    compareResults.add(perFalsePositiveCount); 
                    compareResults.add(locTruePositiveCount); 
                    compareResults.add(locFalseNegativeCount);  
                    compareResults.add(locFalsePositiveCount); 

                    System.out.println(compareResults);
                    return compareResults;

            }  

Answer 1

here if i got this right it may help.

i created a custom String to override the equals for partial match

public class MyCustomString {

    private String myString;

    public MyCustomString(String myString) {
        this.myString = myString;
    }

    public String getMyString() {
        return myString;
    }

    public void setMyString(String myString) {
        this.myString = myString;
    }

    @Override
    public boolean equals(Object obj) {
        if (obj == null) {
            return false;
        }
        if (getClass() != obj.getClass()) {
            return false;
        }
        final MyCustomString other = (MyCustomString) obj;
        if (!Objects.equals(this.myString, other.myString) && !other.myString.contains(this.myString)) {
            return false;
        }
        return true;
    }

    // add getter and setter for myString 
    // or delegate needed methods to myString object.
    @Override
    public int hashCode() {
        int hash = 3;
        hash = 47 * hash + Objects.hashCode(this.myString);
        return hash;
    }
}

and here the code i tried with the first part of your map

LinkedHashMap<String, List<MyCustomString>> sampleMap1 = new LinkedHashMap<String, List<MyCustomString>>();
        sampleMap1.put("a", new ArrayList<>());
        sampleMap1.get("a").add(new MyCustomString("Fulton Tax Commissioner 's Office"));
        sampleMap1.get("a").add(new MyCustomString("Grady Hospital"));
        sampleMap1.get("a").add(new MyCustomString("Fulton Health Department"));

        LinkedHashMap<String, List<MyCustomString>> sampleMap2 = new LinkedHashMap<String, List<MyCustomString>>();
        sampleMap2.put("a", new ArrayList<>());
        sampleMap2.get("a").add(new MyCustomString("Atlanta Police Department"));
        sampleMap2.get("a").add(new MyCustomString("Fulton Tax Commissioner"));
        sampleMap2.get("a").add(new MyCustomString("Fulton Health Department"));

        HashMap<String, Integer> resultMap = new HashMap<String, Integer>();

        for (Map.Entry<String, List<MyCustomString>> entry : sampleMap1.entrySet()) {
            String key1 = entry.getKey();
            List<MyCustomString> value1 = entry.getValue();
            List<MyCustomString> singleListOfMap2 = sampleMap2.get(key1);
            if (singleListOfMap2 == null) {
                // all entry are false negative
                System.out.println("Number of false N" + value1.size());
            }
            for (MyCustomString singleStringOfMap2 : singleListOfMap2) {
                if (value1.contains(singleStringOfMap2)) {
                    //True positive
                    System.out.println("true");
                } else {
                    //false negative
                    System.out.println("false N");
                }
            }
            int size = singleListOfMap2.size();
            System.out.println(size + " - numero di true");
            //false positive = size - true
        }
        for (String string : sampleMap2.keySet()) {
            if (sampleMap1.get(string) == null) {
                //all these are false positive
                System.out.println("numero di false P: " + sampleMap2.get(string).size());
            }
        }

Answer 2

I wrote this class to compare the maps:

public class MapComparison<K, V> {
    private final Map<K, Collection<ValueCounter>> temp;
    private final Map<K, Collection<V>> goldMap;
    private final Map<K, Collection<V>> comparedMap;
    private final BiPredicate<V, V> valueMatcher;

    public MapComparison(Map<K, Collection<V>> mapA, Map<K, Collection<V>> mapB, BiPredicate<V, V> valueMatcher) {
        this.goldMap = mapA;
        this.comparedMap = mapB;
        this.valueMatcher = valueMatcher;

        this.temp = new HashMap<>();

        goldMap.forEach((key, valueList) -> {
            temp.put(key, valueList.stream().map(value -> new ValueCounter(value, true)).collect(Collectors.toList()));
        });

        comparedMap.entrySet().stream().forEach(entry -> {

            K key = entry.getKey();
            Collection<V> valueList = entry.getValue();

            if(temp.containsKey(key)) {
                Collection<ValueCounter> existingMatches = temp.get(key);

                Stream<V> falsePositives = valueList.stream().filter(v -> existingMatches.stream().noneMatch(mv -> mv.match(v)));

                falsePositives.forEach(fp -> existingMatches.add(new ValueCounter(fp, false)));
            } else {
                temp.putIfAbsent(key, valueList.stream().map(value -> new ValueCounter(value, false)).collect(Collectors.toList()));
            }
        });
    }

    public String formatMatchedCounters() {
        StringBuilder sb = new StringBuilder();

        for(Entry<K, Collection<ValueCounter>> e : temp.entrySet()) {
            sb.append(e.getKey()).append(":");

            int[] counters = e.getValue().stream().collect(() -> new int[3], (a, b) -> {
                a[0] += b.truePositiveCount;
                a[1] += b.falsePositiveCount;
                a[2] += b.falseNegativeCount;
            }, (c, d) -> {
                c[0] += d[0];
                c[1] += d[1];
                c[2] += d[2];
            });
            sb.append(String.format("\ntruePositiveCount=%s\nfalsePositiveCount=%s\nfalseNegativeCount=%s\n\n", counters[0], counters[1], counters[2]));
        }
        return sb.toString();
    }


    private class ValueCounter {
        private final V goldValue;

        private int truePositiveCount = 0;
        private int falsePositiveCount = 0;
        private int falseNegativeCount = 0;

        ValueCounter(V value, boolean isInGoldMap) {
            this.goldValue = value;

            if(isInGoldMap) {
                falseNegativeCount = 1;
            } else {
                falsePositiveCount = 1;
            }
        }

        boolean match(V otherValue) {
            boolean result = valueMatcher.test(goldValue, otherValue);

            if(result) {
                truePositiveCount++;

                falseNegativeCount = 0;
            }
            return result;
        }
    }
}

What is does is basically creating a union of map items, and each item has it's own mutable counter to calculate matching values. The method formatMatchedCounters() just iterates and sums these counters for each of the keys.

The following test:

public class MapComparisonTest {

    private Map<String, Collection<String>> goldMap;
    private Map<String, Collection<String>> comparedMap;
    private BiPredicate<String, String> valueMatcher;

    @Before
    public void initMaps() {
        goldMap = new HashMap<>();
        goldMap.put("ORGANIZATION", Arrays.asList("Fulton Tax Commissioner", "Grady Hospital", "Fulton Health Department"));
        goldMap.put("LOCATION", Arrays.asList("Bellwood", "Alpharetta"));

        comparedMap = new HashMap<>();
        comparedMap.put("ORGANIZATION", Arrays.asList("Atlanta Police Department", "Fulton Tax Commissioner", "Fulton Health Department"));
        comparedMap.put("LOCATION", Arrays.asList("Alpharetta"));
        comparedMap.put("PERSON", Arrays.asList("Bellwood", "Grady Hospital"));

        valueMatcher = String::equalsIgnoreCase;
    }

    @Test
    public void test() {
        MapComparison<String, String> comparison = new MapComparison<>(goldMap, comparedMap, valueMatcher);

        System.out.println(comparison.formatMatchedCounters());
    }
}

has the result of:

ORGANIZATION:
truePositiveCount=2
falsePositiveCount=1
falseNegativeCount=1

LOCATION:
truePositiveCount=1
falsePositiveCount=0
falseNegativeCount=1

PERSON:
truePositiveCount=0
falsePositiveCount=2
falseNegativeCount=0

Note, that I don't know how you want to compare similar values (e.g. "Fulton Tax Commissioner" vs "Fulton Tax Commissioner s"), so I decided to put that decision in the signature (in this case a BiPredicate as parameter).

For example, the String comparison could be implemented using the Levenshtein distance:

valueMatcher = (s1, s2) -> StringUtils.getLevenshteinDistance(s1, s2) < 5;

Answer 3

I came up with a simplified version. This is the output that I get:

Organization:
    False Positive: Atlanta Police Department
    True Positive: Fulton Tax Commissioner
    True Positive: Fulton Health Department
    False Negative: Grady Hospital

Person:
    False Positive: Bellwood
    False Positive: Grady Hospital

Location:
    True Positive: Alpharetta
    False Negative: Bellwood

[2, 1, 1, 0, 0, 2, 1, 1, 0]

---

Here is the code that I created:

---

public class MapCompare {

    public static boolean listContains(List<String> annotationList, String value) {
        if(annotationList.contains(value)) {
            // 100% Match
            return true;
        }
        for(String s: annotationList) {
            if (s.contains(value) || value.contains(s)) {
                // Partial Match
                return true;
            }
        }
        return false;
    }

    public static List<Integer> compareLists(List<String> annotationList, List<String> rageList){
        List<Integer> compareResults = new ArrayList<Integer>();
        if(annotationList == null || rageList == null) return Arrays.asList(0, 0, 0);
        Integer truePositiveCount = 0;
        Integer falseNegativeCount = 0;
        Integer falsePositiveCount = 0;

        for(String r: rageList) {
            if(listContains(annotationList, r)) {
                System.out.println("\tTrue Positive: " + r);
                truePositiveCount ++;
            } else {
                System.out.println("\tFalse Positive: " + r);
                falsePositiveCount ++;
            }
        }

        for(String s: annotationList) {
            if(listContains(rageList, s) == false){
                System.out.println("\tFalse Negative: " + s);
                falseNegativeCount ++;
            }
        }

        compareResults.add(truePositiveCount);
        compareResults.add(falseNegativeCount);
        compareResults.add(falsePositiveCount);

        System.out.println();

        return compareResults;
    }

    private static List<Integer> compareMaps(LinkedHashMap<String, List<String>> annotationMap, LinkedHashMap<String, List<String>> rageMap) {
        List<Integer> compareResults = new ArrayList<Integer>();
        System.out.println("Organization:");
        compareResults.addAll(compareLists(annotationMap.get("ORGANIZATION"), rageMap.get("ORGANIZATION")));
        System.out.println("Person:");
        compareResults.addAll(compareLists(annotationMap.get("PERSON"), rageMap.get("PERSON")));
        System.out.println("Location:");
        compareResults.addAll(compareLists(annotationMap.get("LOCATION"), rageMap.get("LOCATION")));
        System.out.println(compareResults);
        return compareResults;
    }

    public static void main(String[] args) {
        LinkedHashMap<String, List<String>> Map1 = new LinkedHashMap<>();
        List<String> m1l1 = Arrays.asList("Fulton Tax Commissioner's Office", "Grady Hospital", "Fulton Health Department");
        List<String> m1l2 = Arrays.asList("Bellwood", "Alpharetta");
        List<String> m1l3 = Arrays.asList();
        Map1.put("ORGANIZATION", m1l1);
        Map1.put("LOCATION", m1l2);
        Map1.put("PERSON", m1l3);

        LinkedHashMap<String, List<String>> Map2 = new LinkedHashMap<>();
        List<String> m2l1 = Arrays.asList("Atlanta Police Department", "Fulton Tax Commissioner", "Fulton Health Department");
        List<String> m2l2 = Arrays.asList("Alpharetta");
        List<String> m2l3 = Arrays.asList("Bellwood", "Grady Hospital");

        Map2.put("ORGANIZATION", m2l1);
        Map2.put("LOCATION", m2l2);
        Map2.put("PERSON", m2l3);

        compareMaps(Map1, Map2);

    }

}

---

Hope this helps!