UNLOZE/projects-jenz
11
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

removed levenhstein callable implementation, simplified sentence fetching from DB, moved from unloze db to a small vps db, instead of iterating 1 in updatematrix is 25 now, updated sentiment analyzing, also reduced get time of results to 5 seconds, a bunch of trivial things also got changed

Browse Source
This commit is contained in:
jenzur 2019-03-29 12:34:40 +01:00
parent 296be21753
commit 9e68cbb283
7 changed files with 457 additions and 450 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
ArtificialAutism/src/main/java/DataLayer/DBCPDataSource.java
View File

@ -20,9 +20,9 @@ public class DBCPDataSource {
static { static {
try { try {
ds.setDriver(new com.mysql.cj.jdbc.Driver()); ds.setDriver(new com.mysql.cj.jdbc.Driver());
ds.setUrl("jdbc:mysql://151.80.230.149:3306/ArtificialAutism?useLegacyDatetimeCode=false&serverTimezone=UTC"); ds.setUrl("jdbc:mysql://104.248.40.216:3306/ArtificialAutism?useLegacyDatetimeCode=false&serverTimezone=UTC");
ds.setUsername("ArtificialAutism"); ds.setUsername("root");
ds.setPassword("b423b54bwbfb1340438fn"); ds.setPassword("fb345972349fnsDW234/¤)#2");
ds.setMaxTotal(-1); ds.setMaxTotal(-1);
ds.setMinIdle(5); ds.setMinIdle(5);
ds.setMaxIdle(-1); ds.setMaxIdle(-1);

50
ArtificialAutism/src/main/java/DataLayer/DataMapper.java
View File

@ -140,41 +140,35 @@ public class DataMapper {
public static LinkedHashMap<String, LinkedHashMap<String, Double>> getAllRelationScores() { public static LinkedHashMap<String, LinkedHashMap<String, Double>> getAllRelationScores() {
int count = getSementicsDBRows(); int count = getSementicsDBRows();
int counter2 = 0;
int hardCapRetrieveCount = 500000;
LinkedHashMap<String, LinkedHashMap<String, Double>> LHMSMX = new LinkedHashMap(); LinkedHashMap<String, LinkedHashMap<String, Double>> LHMSMX = new LinkedHashMap();
while (count > counter2) { try (Connection l_cCon = DBCPDataSource.getConnection()) {
try (Connection l_cCon = DBCPDataSource.getConnection()) { l_cCon.setAutoCommit(false);
l_cCon.setAutoCommit(false); String l_sSQL = "SELECT * FROM `WordMatrix`";
String l_sSQL = "SELECT * FROM `WordMatrix` WHERE ID > " + counter2 + " AND ID < " + (counter2 + hardCapRetrieveCount); try (PreparedStatement l_pStatement = l_cCon.prepareStatement(l_sSQL, java.sql.ResultSet.TYPE_FORWARD_ONLY,
try (PreparedStatement l_pStatement = l_cCon.prepareStatement(l_sSQL, java.sql.ResultSet.TYPE_FORWARD_ONLY, java.sql.ResultSet.CONCUR_READ_ONLY)) {
java.sql.ResultSet.CONCUR_READ_ONLY)) { l_pStatement.setFetchSize(Integer.MIN_VALUE);
l_pStatement.setFetchSize(Integer.MIN_VALUE); try (ResultSet l_rsSearch = l_pStatement.executeQuery()) {
try (ResultSet l_rsSearch = l_pStatement.executeQuery()) { int i = 0;
int i = 0; LinkedHashMap<String, Double> LHMLocal = new LinkedHashMap();
LinkedHashMap<String, Double> LHMLocal = new LinkedHashMap(); while (l_rsSearch.next()) {
while (l_rsSearch.next() && i < hardCapRetrieveCount) { String str1 = l_rsSearch.getString(1);
String str1 = l_rsSearch.getString(1); String str2 = l_rsSearch.getString(2);
String str2 = l_rsSearch.getString(2); Double score = l_rsSearch.getDouble(3);
Double score = l_rsSearch.getDouble(3); LHMLocal.put(str2, score);
while (l_rsSearch.next() && str1.equals(l_rsSearch.getString(1))) {
str2 = l_rsSearch.getString(2);
score = l_rsSearch.getDouble(3);
LHMLocal.put(str2, score); LHMLocal.put(str2, score);
while (l_rsSearch.next() && i < hardCapRetrieveCount && str1.equals(l_rsSearch.getString(1))) {
str2 = l_rsSearch.getString(2);
score = l_rsSearch.getDouble(3);
LHMLocal.put(str2, score);
i++;
counter2++;
}
LHMSMX.put(str1, LHMLocal);
System.out.println("i: " + i + "\n" + "free memory: " + Runtime.getRuntime().freeMemory() + "\ncounter2: " + counter2 + "\n");
i++; i++;
counter2++;
} }
LHMSMX.put(str1, LHMLocal);
System.out.println("i: " + i + "\n" + "free memory: " + Runtime.getRuntime().freeMemory() + "\n");
i++;
} }
} }
} catch (SQLException ex) {
Logger.getLogger(DataMapper.class.getName()).log(Level.SEVERE, null, ex);
} }
} catch (SQLException ex) {
Logger.getLogger(DataMapper.class.getName()).log(Level.SEVERE, null, ex);
} }
return LHMSMX; return LHMSMX;
} }

166
ArtificialAutism/src/main/java/FunctionLayer/Datahandler.java
View File

@ -29,13 +29,11 @@ import java.io.StringReader;
import java.sql.SQLException; import java.sql.SQLException;
import java.util.ArrayList; import java.util.ArrayList;
import java.util.Collection; import java.util.Collection;
import java.util.Iterator;
import java.util.LinkedHashMap; import java.util.LinkedHashMap;
import java.util.List; import java.util.List;
import java.util.Map; import java.util.Map;
import java.util.Map.Entry; import java.util.Map.Entry;
import java.util.Properties; import java.util.Properties;
import java.util.Random;
import java.util.concurrent.Callable; import java.util.concurrent.Callable;
import java.util.concurrent.ConcurrentMap; import java.util.concurrent.ConcurrentMap;
import java.util.concurrent.CountDownLatch; import java.util.concurrent.CountDownLatch;
@ -56,6 +54,7 @@ public class Datahandler {
public static final long EXPIRE_TIME_IN_SECONDS = TimeUnit.SECONDS.convert(6, TimeUnit.MINUTES); public static final long EXPIRE_TIME_IN_SECONDS = TimeUnit.SECONDS.convert(6, TimeUnit.MINUTES);
public static final long EXPIRE_TIME_IN_SECONDS1 = TimeUnit.SECONDS.convert(10, TimeUnit.HOURS); public static final long EXPIRE_TIME_IN_SECONDS1 = TimeUnit.SECONDS.convert(10, TimeUnit.HOURS);
public static Datahandler instance = new Datahandler(); public static Datahandler instance = new Datahandler();
private static volatile Double minDistance;
private volatile boolean refreshMatrixFromDB; private volatile boolean refreshMatrixFromDB;
private static volatile int secondaryIterator = 0; private static volatile int secondaryIterator = 0;
private final ConcurrentMap<Integer, String> stringCache; private final ConcurrentMap<Integer, String> stringCache;
@ -66,6 +65,7 @@ public class Datahandler {
private final Stopwatch stopwatch; private final Stopwatch stopwatch;
private final Stopwatch stopwatch1; private final Stopwatch stopwatch1;
private ForkJoinPool executor; private ForkJoinPool executor;
private static String similar = "";
private static String shiftReduceParserPath = "edu/stanford/nlp/models/srparser/englishSR.ser.gz"; private static String shiftReduceParserPath = "edu/stanford/nlp/models/srparser/englishSR.ser.gz";
private static String sentimentModel = "edu/stanford/nlp/models/sentiment/sentiment.ser.gz"; private static String sentimentModel = "edu/stanford/nlp/models/sentiment/sentiment.ser.gz";
private static String lexParserEnglishRNN = "edu/stanford/nlp/models/lexparser/englishRNN.ser.gz"; private static String lexParserEnglishRNN = "edu/stanford/nlp/models/lexparser/englishRNN.ser.gz";
@ -278,6 +278,7 @@ public class Datahandler {
if (stringCache.values().size() > 10 && !refreshMatrixFromDB) { if (stringCache.values().size() > 10 && !refreshMatrixFromDB) {
ConcurrentMap<Integer, String> stringCachelocal = stringCache; ConcurrentMap<Integer, String> stringCachelocal = stringCache;
int selectUpdate = -1; int selectUpdate = -1;
int iteratorCap = 25;
LinkedHashMap<String, LinkedHashMap<String, Double>> LHMSMXLocal = lHMSMX; LinkedHashMap<String, LinkedHashMap<String, Double>> LHMSMXLocal = lHMSMX;
int ij2 = 0; int ij2 = 0;
for (String str : stringCachelocal.values()) { for (String str : stringCachelocal.values()) {
@ -290,67 +291,81 @@ public class Datahandler {
} }
if (selectUpdate == -1 || selectUpdate + 1 == stringCachelocal.size()) { if (selectUpdate == -1 || selectUpdate + 1 == stringCachelocal.size()) {
int valueSize = stringCachelocal.size(); int valueSize = stringCachelocal.size();
if (secondaryIterator + 1 >= valueSize) { if (secondaryIterator + iteratorCap >= valueSize) {
secondaryIterator = 0; secondaryIterator = 0;
} }
selectUpdate = secondaryIterator; selectUpdate = secondaryIterator;
secondaryIterator++; secondaryIterator += iteratorCap;
} }
final String getStringCacheStr = stringCachelocal.getOrDefault(selectUpdate, null); final ConcurrentMap<Integer, String> getStringCacheMap = new MapMaker().concurrencyLevel(2).makeMap();
ConcurrentMap<Integer, SimilarityMatrix> matrixUpdateList = new MapMaker().concurrencyLevel(2).makeMap(); for (int i = 0; i < iteratorCap; i++) {
getStringCacheMap.put(i, stringCachelocal.get(selectUpdate));
selectUpdate++;
}
ConcurrentMap<Integer, SimilarityMatrix> matrixUpdateMap = new MapMaker().concurrencyLevel(2).makeMap();
ConcurrentMap<Integer, Future<SimilarityMatrix>> futures = new MapMaker().concurrencyLevel(2).makeMap(); ConcurrentMap<Integer, Future<SimilarityMatrix>> futures = new MapMaker().concurrencyLevel(2).makeMap();
stringCachelocal.values().forEach((str1) -> { getStringCacheMap.values().forEach((getStringCacheStr) -> {
boolean present = false; stringCachelocal.values().forEach((str1) -> {
LinkedHashMap<String, Double> orDefault = lHMSMX.getOrDefault(getStringCacheStr, null); if (!getStringCacheStr.equals(str1)) {
if (orDefault != null) { boolean present = false;
Double orDefault1 = orDefault.getOrDefault(str1, null); LinkedHashMap<String, Double> orDefault = lHMSMX.getOrDefault(getStringCacheStr, null);
if (orDefault1 != null) { if (orDefault != null) {
present = true; Collection<String> strkeys = orDefault.keySet();
} for (String strkey : strkeys) {
} if (strkey.equals(str1)) {
if (!present) { present = true;
orDefault = lHMSMX.getOrDefault(str1, null); break;
if (orDefault != null) { }
Double orDefault1 = orDefault.getOrDefault(getStringCacheStr, null); }
if (orDefault1 != null) { }
present = true; if (!present) {
orDefault = lHMSMX.getOrDefault(str1, null);
if (orDefault != null) {
Collection<String> strkeys = orDefault.keySet();
for (String strkey : strkeys) {
if (strkey.equals(getStringCacheStr)) {
present = true;
break;
}
}
}
}
if (!present) {
LinkedHashMap<String, Double> orDefault1 = lHMSMX.getOrDefault(getStringCacheStr, null);
if (orDefault1 == null) {
orDefault1 = new LinkedHashMap<String, Double>();
}
orDefault1.put(str1, 0.0);
lHMSMX.put(getStringCacheStr, orDefault1);
SimilarityMatrix SMX = new SimilarityMatrix(getStringCacheStr, str1);
Callable<SimilarityMatrix> worker = new SentimentAnalyzerTest(getStringCacheStr, str1, SMX, jmweAnnotationCache.get(getStringCacheStr),
jmweAnnotationCache.get(str1), pipelineAnnotationCache.get(getStringCacheStr), pipelineAnnotationCache.get(str1),
pipelineSentimentAnnotationCache.get(getStringCacheStr), pipelineSentimentAnnotationCache.get(str1));
futures.put(futures.size() + 1, executor.submit(worker));
} }
} }
} });
if (!present) { System.out.println("finished worker assignment, futures size: " + futures.size() + "\n");
LinkedHashMap<String, Double> orDefault1 = lHMSMX.getOrDefault(getStringCacheStr, null); futures.values().parallelStream().forEach((future) -> {
if (orDefault1 == null) { SimilarityMatrix SMX = new SimilarityMatrix("", "");
orDefault1 = new LinkedHashMap<String, Double>(); try {
SMX = future.get(5, TimeUnit.SECONDS);
} catch (InterruptedException | ExecutionException | TimeoutException ex) {
Logger.getLogger(Datahandler.class.getName()).log(Level.SEVERE, null, ex);
SMX = null;
} }
orDefault1.put(str1, 0.0); if (SMX != null) {
lHMSMX.put(getStringCacheStr, orDefault1); LinkedHashMap<String, Double> getFuture = lHMSMX.getOrDefault(SMX.getPrimaryString(), null);
SimilarityMatrix SMX = new SimilarityMatrix(getStringCacheStr, str1); getFuture.put(SMX.getSecondaryString(), SMX.getDistance());
Callable<SimilarityMatrix> worker = new SentimentAnalyzerTest(getStringCacheStr, str1, SMX, jmweAnnotationCache.get(getStringCacheStr), lHMSMX.put(SMX.getPrimaryString(), getFuture);
jmweAnnotationCache.get(str1), pipelineAnnotationCache.get(getStringCacheStr), pipelineAnnotationCache.get(str1), matrixUpdateMap.put(matrixUpdateMap.size() + 1, SMX);
pipelineSentimentAnnotationCache.get(getStringCacheStr), pipelineSentimentAnnotationCache.get(str1)); }
futures.put(futures.size() + 1, executor.submit(worker)); });
}
});
System.out.println("finished worker assignment, futures size: " + futures.size() + "\n");
futures.values().parallelStream().forEach((future) -> {
SimilarityMatrix SMX = new SimilarityMatrix("", "");
try {
SMX = future.get(5, TimeUnit.SECONDS);
} catch (InterruptedException | ExecutionException | TimeoutException ex) {
Logger.getLogger(Datahandler.class.getName()).log(Level.SEVERE, null, ex);
SMX = null;
}
if (SMX != null) {
LinkedHashMap<String, Double> getFuture = lHMSMX.getOrDefault(SMX.getPrimaryString(), null);
getFuture.put(SMX.getSecondaryString(), SMX.getDistance());
lHMSMX.put(SMX.getPrimaryString(), getFuture);
matrixUpdateList.put(matrixUpdateList.size() + 1, SMX);
}
}); });
new Thread(() -> { new Thread(() -> {
try { try {
if (!matrixUpdateList.isEmpty()) { if (!matrixUpdateMap.isEmpty()) {
DataMapper.insertSementicMatrixes(matrixUpdateList); DataMapper.insertSementicMatrixes(matrixUpdateMap);
System.out.println("finished datamapper semetic insert"); System.out.println("finished datamapper semetic insert");
} }
} catch (CustomError ex) { } catch (CustomError ex) {
@ -359,7 +374,6 @@ public class Datahandler {
} }
}).start(); }).start();
} }
} }
public synchronized void checkIfUpdateStrings(boolean hlStatsMsg) throws CustomError { public synchronized void checkIfUpdateStrings(boolean hlStatsMsg) throws CustomError {
@ -398,7 +412,6 @@ public class Datahandler {
System.out.println("pre mostSimilarSTR \n"); System.out.println("pre mostSimilarSTR \n");
String mostSimilarSTR = mostSimilar(str, strArrs); String mostSimilarSTR = mostSimilar(str, strArrs);
if (mostSimilarSTR != null) { if (mostSimilarSTR != null) {
System.out.println("mostSimilarSTR; " + mostSimilarSTR + "\n");
LinkedHashMap<String, Double> orDefault = LHMSMXLocal.getOrDefault(mostSimilarSTR, null); LinkedHashMap<String, Double> orDefault = LHMSMXLocal.getOrDefault(mostSimilarSTR, null);
if (orDefault != null) { if (orDefault != null) {
for (Entry<String, Double> entrySet : orDefault.entrySet()) { for (Entry<String, Double> entrySet : orDefault.entrySet()) {
@ -452,7 +465,6 @@ public class Datahandler {
futureslocal.put(futureslocal.size() + 1, executor.submit(worker)); futureslocal.put(futureslocal.size() + 1, executor.submit(worker));
} }
}); });
int index = 0;
futureslocal.values().parallelStream().forEach((future) -> { futureslocal.values().parallelStream().forEach((future) -> {
SimilarityMatrix SMX = new SimilarityMatrix("", ""); SimilarityMatrix SMX = new SimilarityMatrix("", "");
try { try {
@ -464,15 +476,10 @@ public class Datahandler {
}); });
for (SimilarityMatrix SMX : futurereturn.values()) { for (SimilarityMatrix SMX : futurereturn.values()) {
double distance = SMX.getDistance(); double distance = SMX.getDistance();
/*
System.out.println("index: " + index + "\nfutures size: " + futureslocal.values().size() + "\nScore: " + SMX.getDistance() + "\nSecondary: "
+ SMX.getSecondaryString() + "\nPrimary: " + SMX.getPrimaryString() + "\n");
*/
if (distance > Score) { if (distance > Score) {
Score = distance; Score = distance;
SMXreturn = SMX; SMXreturn = SMX;
} }
index++;
} }
System.out.println("Reached end: secondary: " + SMXreturn.getSecondaryString() + "\nPrimarY: " + SMXreturn.getPrimaryString() System.out.println("Reached end: secondary: " + SMXreturn.getSecondaryString() + "\nPrimarY: " + SMXreturn.getPrimaryString()
+ "\nScore: " + SMXreturn.getDistance()); + "\nScore: " + SMXreturn.getDistance());
@ -480,30 +487,27 @@ public class Datahandler {
} }
public String mostSimilar(String toBeCompared, ConcurrentMap<Integer, String> concurrentStrings) { public String mostSimilar(String toBeCompared, ConcurrentMap<Integer, String> concurrentStrings) {
int minDistance = 7; similar = "";
String similar = ""; minDistance = 7.5;
List<Future<ConcurrentMap<String, Integer>>> futures = new ArrayList();
ConcurrentMap<String, Integer> futuresreturnvalues = new MapMaker().concurrencyLevel(2).makeMap();
concurrentStrings.values().parallelStream().forEach((str) -> { concurrentStrings.values().parallelStream().forEach((str) -> {
Callable<ConcurrentMap<String, Integer>> worker = new LevenshteinDistance(toBeCompared, str); LevenshteinDistance leven = new LevenshteinDistance(toBeCompared, str);
futures.add(executor.submit(worker)); double distance = leven.computeLevenshteinDistance();
}); if (distance < minDistance) {
futures.parallelStream().forEach((future) -> { minDistance = distance;
try { System.out.println("distance: " + distance + "\n");
ConcurrentMap<String, Integer> get = future.get(); similar = str;
get.entrySet().forEach((str) -> {
futuresreturnvalues.put(str.getKey(), str.getValue());
});
} catch (NullPointerException | InterruptedException | ExecutionException ex) {
System.out.println("failed future\nex: " + ex.getMessage() + "\n");
} }
}); });
for (Entry<String, Integer> entritr : futuresreturnvalues.entrySet()) { LinkedHashMap<String, Double> orDefault = lHMSMX.getOrDefault(similar, null);
int distance = entritr.getValue(); if (orDefault == null) {
if (distance < minDistance) { return null;
System.out.println("distance: " + distance + "\n"); }
minDistance = distance; Double maxDistance = 0.0;
similar = entritr.getKey(); for (Entry<String, Double> defaultEntry : orDefault.entrySet()) {
Double value = defaultEntry.getValue();
if (value > maxDistance) {
maxDistance = value;
similar = defaultEntry.getKey();
} }
} }
return similar; return similar;

25
ArtificialAutism/src/main/java/FunctionLayer/LevenshteinDistance.java
View File

@ -15,11 +15,9 @@ import java.util.concurrent.ConcurrentMap;
* *
* @author install1 * @author install1
*/ */
public class LevenshteinDistance implements Callable<ConcurrentMap<String, Integer>> { public class LevenshteinDistance {
private CharSequence lhs; private CharSequence lhs;
private CharSequence rhs; private CharSequence rhs;
private ConcurrentMap<String, Integer> distanceEntry = new MapMaker().concurrencyLevel(2).makeMap();
private static int minimum(int a, int b, int c) { private static int minimum(int a, int b, int c) {
return Math.min(Math.min(a, b), c); return Math.min(Math.min(a, b), c);
@ -48,25 +46,4 @@ public class LevenshteinDistance implements Callable<ConcurrentMap<String, Integ
} }
return distance[lhs.length()][rhs.length()]; return distance[lhs.length()][rhs.length()];
} }
@Override
public ConcurrentMap<String, Integer> call() {
int[][] distance = new int[lhs.length() + 1][rhs.length() + 1];
for (int i = 0; i <= lhs.length(); i++) {
distance[i][0] = i;
}
for (int j = 1; j <= rhs.length(); j++) {
distance[0][j] = j;
}
for (int i = 1; i <= lhs.length(); i++) {
for (int j = 1; j <= rhs.length(); j++) {
distance[i][j] = minimum(
distance[i - 1][j] + 1,
distance[i][j - 1] + 1,
distance[i - 1][j - 1] + ((lhs.charAt(i - 1) == rhs.charAt(j - 1)) ? 0 : 1));
}
}
distanceEntry.put(lhs.toString(), distance[lhs.length()][rhs.length()]);
return distanceEntry;
}
} }

4
ArtificialAutism/src/main/java/FunctionLayer/PipelineJMWESingleton.java
View File

@ -28,7 +28,6 @@ import java.io.File;
import java.io.IOException; import java.io.IOException;
import java.util.ArrayList; import java.util.ArrayList;
import java.util.Collection; import java.util.Collection;
import java.util.Date;
import java.util.List; import java.util.List;
import java.util.Properties; import java.util.Properties;
import java.util.concurrent.ConcurrentMap; import java.util.concurrent.ConcurrentMap;
@ -67,8 +66,7 @@ public class PipelineJMWESingleton {
} }
IMWEDetector detector = getDetector(index, detectorName); IMWEDetector detector = getDetector(index, detectorName);
ConcurrentMap<String, Annotation> returnAnnotations = new MapMaker().concurrencyLevel(2).makeMap(); ConcurrentMap<String, Annotation> returnAnnotations = new MapMaker().concurrencyLevel(2).makeMap();
Date startDate = new Date(); strvalues.forEach(str -> {
strvalues.parallelStream().forEach(str -> {
Annotation annoStr = new Annotation(str); Annotation annoStr = new Annotation(str);
returnAnnotations.put(str, annoStr); returnAnnotations.put(str, annoStr);
}); });

655
ArtificialAutism/src/main/java/FunctionLayer/StanfordParser/SentimentAnalyzerTest.java
View File

@ -38,6 +38,7 @@ import java.io.StringReader;
import java.util.ArrayList; import java.util.ArrayList;
import java.util.Collection; import java.util.Collection;
import java.util.List; import java.util.List;
import java.util.OptionalDouble;
import java.util.Set; import java.util.Set;
import java.util.concurrent.Callable; import java.util.concurrent.Callable;
import java.util.concurrent.ConcurrentMap; import java.util.concurrent.ConcurrentMap;
@ -95,344 +96,378 @@ public class SentimentAnalyzerTest implements Callable<SimilarityMatrix> {
Double score = -100.0; Double score = -100.0;
try { try {
List<List<TaggedWord>> taggedwordlist1 = new ArrayList(); List<List<TaggedWord>> taggedwordlist1 = new ArrayList();
List<List<TaggedWord>> taggedwordlist2 = new ArrayList(); List<List<TaggedWord>> taggedwordlist2 = new ArrayList();
DocumentPreprocessor tokenizer = new DocumentPreprocessor(new StringReader(str1)); DocumentPreprocessor tokenizer = new DocumentPreprocessor(new StringReader(str1));
//noneDelete //noneDelete
TokenizerFactory<CoreLabel> ptbTokenizerFactory TokenizerFactory<CoreLabel> ptbTokenizerFactory
= PTBTokenizer.factory(new CoreLabelTokenFactory(), "untokenizable=firstDelete"); = PTBTokenizer.factory(new CoreLabelTokenFactory(), "untokenizable=firstDelete");
tokenizer.setTokenizerFactory(ptbTokenizerFactory); tokenizer.setTokenizerFactory(ptbTokenizerFactory);
for (List<HasWord> sentence : tokenizer) { for (List<HasWord> sentence : tokenizer) {
taggedwordlist1.add(model.apply(tagger.tagSentence(sentence)).taggedYield()); taggedwordlist1.add(model.apply(tagger.tagSentence(sentence)).taggedYield());
} }
tokenizer = new DocumentPreprocessor(new StringReader(str)); tokenizer = new DocumentPreprocessor(new StringReader(str));
tokenizer.setTokenizerFactory(ptbTokenizerFactory); tokenizer.setTokenizerFactory(ptbTokenizerFactory);
for (List<HasWord> sentence : tokenizer) { for (List<HasWord> sentence : tokenizer) {
taggedwordlist2.add(model.apply(tagger.tagSentence(sentence)).taggedYield()); taggedwordlist2.add(model.apply(tagger.tagSentence(sentence)).taggedYield());
} }
int counter = 0; int counter = 0;
int counter1 = 0; int counter1 = 0;
counter = taggedwordlist2.stream().map((taggedlist2) -> taggedlist2.size()).reduce(counter, Integer::sum); counter = taggedwordlist2.stream().map((taggedlist2) -> taggedlist2.size()).reduce(counter, Integer::sum);
counter1 = taggedwordlist1.stream().map((taggedlist1) -> taggedlist1.size()).reduce(counter1, Integer::sum); counter1 = taggedwordlist1.stream().map((taggedlist1) -> taggedlist1.size()).reduce(counter1, Integer::sum);
int overValue = counter >= counter1 ? counter - counter1 : counter1 - counter; int overValue = counter >= counter1 ? counter - counter1 : counter1 - counter;
overValue *= 16; overValue *= 32;
score -= overValue; score -= overValue;
ConcurrentMap<Integer, String> tgwlistIndex = new MapMaker().concurrencyLevel(2).makeMap(); ConcurrentMap<Integer, String> tgwlistIndex = new MapMaker().concurrencyLevel(2).makeMap();
taggedwordlist1.forEach((TGWList) -> { taggedwordlist1.forEach((TGWList) -> {
TGWList.forEach((TaggedWord) -> { TGWList.forEach((TaggedWord) -> {
if (!tgwlistIndex.values().contains(TaggedWord.tag()) && !TaggedWord.tag().equals(":")) { if (!tgwlistIndex.values().contains(TaggedWord.tag()) && !TaggedWord.tag().equals(":")) {
tgwlistIndex.put(tgwlistIndex.size() + 1, TaggedWord.tag()); tgwlistIndex.put(tgwlistIndex.size() + 1, TaggedWord.tag());
}
});
});
taggedwordlist1.clear();
AtomicInteger runCount = new AtomicInteger(0);
taggedwordlist2.forEach((TGWList) -> {
TGWList.forEach((TaggedWord) -> {
if (tgwlistIndex.values().contains(TaggedWord.tag())) {
tgwlistIndex.values().remove(TaggedWord.tag());
runCount.getAndIncrement();
}
});
});
tgwlistIndex.clear();
taggedwordlist2.clear();
score += runCount.get() * 64;
ConcurrentMap<Integer, Tree> sentenceConstituencyParseList = new MapMaker().concurrencyLevel(2).makeMap();
try {
for (CoreMap sentence : pipelineAnnotation1.get(CoreAnnotations.SentencesAnnotation.class)) {
Tree sentenceConstituencyParse = sentence.get(TreeCoreAnnotations.TreeAnnotation.class);
sentenceConstituencyParseList.put(sentenceConstituencyParseList.size(), sentenceConstituencyParse);
} }
for (CoreMap sentence : pipelineAnnotation2.get(CoreAnnotations.SentencesAnnotation.class)) { });
Tree sentenceConstituencyParse = sentence.get(TreeCoreAnnotations.TreeAnnotation.class); });
GrammaticalStructure gs = gsf.newGrammaticalStructure(sentenceConstituencyParse); AtomicInteger runCount = new AtomicInteger(0);
Collection<TypedDependency> allTypedDependencies = gs.allTypedDependencies(); taggedwordlist2.forEach((TGWList) -> {
ConcurrentMap<Integer, String> filerTreeContent = new MapMaker().concurrencyLevel(2).makeMap(); TGWList.forEach((TaggedWord) -> {
for (Tree sentenceConstituencyParse1 : sentenceConstituencyParseList.values()) { if (tgwlistIndex.values().contains(TaggedWord.tag())) {
Set<Constituent> inT1notT2 = Tdiff.markDiff(sentenceConstituencyParse, sentenceConstituencyParse1); tgwlistIndex.values().remove(TaggedWord.tag());
Set<Constituent> inT2notT1 = Tdiff.markDiff(sentenceConstituencyParse1, sentenceConstituencyParse); runCount.getAndIncrement();
ConcurrentMap<Integer, String> constiLabels = new MapMaker().concurrencyLevel(2).makeMap();
for (Constituent consti : inT1notT2) {
for (Constituent consti1 : inT2notT1) {
if (consti.value().equals(consti1.value()) && !constiLabels.values().contains(consti.value())) {
score += 64;
constiLabels.put(constiLabels.size(), consti.value());
}
}
}
GrammaticalStructure gs1 = gsf.newGrammaticalStructure(sentenceConstituencyParse1);
Collection<TypedDependency> allTypedDependencies1 = gs1.allTypedDependencies();
for (TypedDependency TDY1 : allTypedDependencies1) {
IndexedWord dep = TDY1.dep();
IndexedWord gov = TDY1.gov();
GrammaticalRelation grammaticalRelation = gs.getGrammaticalRelation(gov, dep);
if (grammaticalRelation.isApplicable(sentenceConstituencyParse)) {
score += 900;
}
GrammaticalRelation reln = TDY1.reln();
if (reln.isApplicable(sentenceConstituencyParse)) {
score += 256;
}
}
for (TypedDependency TDY : allTypedDependencies) {
IndexedWord dep = TDY.dep();
IndexedWord gov = TDY.gov();
GrammaticalRelation grammaticalRelation = gs1.getGrammaticalRelation(gov, dep);
if (grammaticalRelation.isApplicable(sentenceConstituencyParse)) {
score += 900;
}
GrammaticalRelation reln = TDY.reln();
if (reln.isApplicable(sentenceConstituencyParse1)) {
score += 256;
}
}
AtomicInteger runCount1 = new AtomicInteger(0);
sentenceConstituencyParse.taggedLabeledYield().forEach((LBW) -> {
sentenceConstituencyParse1.taggedLabeledYield().stream().filter((LBW1) -> (LBW.lemma().equals(LBW1.lemma())
&& !filerTreeContent.values().contains(LBW.lemma()))).map((_item) -> {
filerTreeContent.put(filerTreeContent.size() + 1, LBW.lemma());
return _item;
}).forEachOrdered((_item) -> {
runCount1.getAndIncrement();
});
});
score += runCount1.get() * 1500;
}
} }
} catch (Exception ex) { });
System.out.println("pipelineAnnotation stacktrace: " + ex.getLocalizedMessage() + "\n"); });
score += runCount.get() * 64;
ConcurrentMap<Integer, Tree> sentenceConstituencyParseList = new MapMaker().concurrencyLevel(2).makeMap();
try {
for (CoreMap sentence : pipelineAnnotation1.get(CoreAnnotations.SentencesAnnotation.class)) {
Tree sentenceConstituencyParse = sentence.get(TreeCoreAnnotations.TreeAnnotation.class);
sentenceConstituencyParseList.put(sentenceConstituencyParseList.size(), sentenceConstituencyParse);
} }
sentenceConstituencyParseList.clear(); for (CoreMap sentence : pipelineAnnotation2.get(CoreAnnotations.SentencesAnnotation.class)) {
ConcurrentMap<Integer, SimpleMatrix> simpleSMXlist = new MapMaker().concurrencyLevel(2).makeMap(); int constiRelationsize = 0;
ConcurrentMap<Integer, SimpleMatrix> simpleSMXlistVector = new MapMaker().concurrencyLevel(2).makeMap(); Tree sentenceConstituencyParse = sentence.get(TreeCoreAnnotations.TreeAnnotation.class);
ConcurrentMap<Integer, Integer> sentiment1 = new MapMaker().concurrencyLevel(2).makeMap(); GrammaticalStructure gs = gsf.newGrammaticalStructure(sentenceConstituencyParse);
ConcurrentMap<Integer, Integer> sentiment2 = new MapMaker().concurrencyLevel(2).makeMap(); Collection<TypedDependency> allTypedDependencies = gs.allTypedDependencies();
for (CoreMap sentence : pipelineAnnotation1Sentiment.get(CoreAnnotations.SentencesAnnotation.class)) { ConcurrentMap<Integer, String> filerTreeContent = new MapMaker().concurrencyLevel(2).makeMap();
Tree tree = sentence.get(SentimentCoreAnnotations.SentimentAnnotatedTree.class); for (Tree sentenceConstituencyParse1 : sentenceConstituencyParseList.values()) {
sentiment1.put(sentiment1.size(), RNNCoreAnnotations.getPredictedClass(tree)); Set<Constituent> constinuent1 = Tdiff.markDiff(sentenceConstituencyParse, sentenceConstituencyParse1);
SimpleMatrix predictions = RNNCoreAnnotations.getPredictions(tree); Set<Constituent> constinuent2 = Tdiff.markDiff(sentenceConstituencyParse1, sentenceConstituencyParse);
SimpleMatrix nodeVector = RNNCoreAnnotations.getNodeVector(tree); ConcurrentMap<Integer, String> constiLabels = new MapMaker().concurrencyLevel(2).makeMap();
simpleSMXlist.put(simpleSMXlist.size(), predictions); for (Constituent consti : constinuent1) {
simpleSMXlistVector.put(simpleSMXlistVector.size() + 1, nodeVector); for (Constituent consti1 : constinuent2) {
} if (consti.value().equals(consti1.value()) && !constiLabels.values().contains(consti.value())) {
for (CoreMap sentence : pipelineAnnotation2Sentiment.get(CoreAnnotations.SentencesAnnotation.class)) { constiLabels.put(constiLabels.size(), consti.value());
Tree tree = sentence.get(SentimentCoreAnnotations.SentimentAnnotatedTree.class); constiRelationsize++;
sentiment2.put(sentiment2.size() + 1, RNNCoreAnnotations.getPredictedClass(tree)); }
SimpleMatrix predictions = RNNCoreAnnotations.getPredictions(tree); }
SimpleMatrix nodeVector = RNNCoreAnnotations.getNodeVector(tree);
score = simpleSMXlist.values().stream().map((simpleSMX) -> predictions.dot(simpleSMX) * 100).map((dot) -> dot > 50 ? dot - 50 : 50 - dot).map((subtracter) -> {
subtracter *= 25;
return subtracter;
}).map((subtracter) -> subtracter).reduce(score, (accumulator, _item) -> accumulator - _item);
for (SimpleMatrix simpleSMX : simpleSMXlistVector.values()) {
double dot = nodeVector.dot(simpleSMX);
double elementSum = nodeVector.kron(simpleSMX).elementSum();
elementSum = Math.round(elementSum * 100.0) / 100.0;
if (dot < 0.1) {
score += 256;
} }
if (elementSum < 0.1 && elementSum > 0.0) { int constituents1 = constinuent1.size() - constiRelationsize;
score += 1300; int constituents2 = constinuent2.size() - constiRelationsize;
} else if (elementSum > 0.1 && elementSum < 1.0) { if (constituents1 > 0 && constituents2 > 0) {
score -= 1100; score -= (constituents1 + constituents2) * 200;
} else { } else {
score -= 1424; score += constiRelationsize * 200;
} }
GrammaticalStructure gs1 = gsf.newGrammaticalStructure(sentenceConstituencyParse1);
Collection<TypedDependency> allTypedDependencies1 = gs1.allTypedDependencies();
for (TypedDependency TDY1 : allTypedDependencies1) {
IndexedWord dep = TDY1.dep();
IndexedWord gov = TDY1.gov();
GrammaticalRelation grammaticalRelation = gs.getGrammaticalRelation(gov, dep);
if (grammaticalRelation.isApplicable(sentenceConstituencyParse)) {
score += 1900;
}
GrammaticalRelation reln = TDY1.reln();
if (reln.isApplicable(sentenceConstituencyParse)) {
score += 525;
}
}
for (TypedDependency TDY : allTypedDependencies) {
IndexedWord dep = TDY.dep();
IndexedWord gov = TDY.gov();
GrammaticalRelation grammaticalRelation = gs1.getGrammaticalRelation(gov, dep);
if (grammaticalRelation.isApplicable(sentenceConstituencyParse)) {
score += 900;
}
GrammaticalRelation reln = TDY.reln();
if (reln.isApplicable(sentenceConstituencyParse1)) {
score += 525;
}
}
AtomicInteger runCount1 = new AtomicInteger(0);
sentenceConstituencyParse.taggedLabeledYield().forEach((LBW) -> {
sentenceConstituencyParse1.taggedLabeledYield().stream().filter((LBW1) -> (LBW.lemma().equals(LBW1.lemma())
&& !filerTreeContent.values().contains(LBW.lemma()))).map((_item) -> {
filerTreeContent.put(filerTreeContent.size() + 1, LBW.lemma());
return _item;
}).forEachOrdered((_item) -> {
runCount1.getAndIncrement();
});
});
score += runCount1.get() * 1500;
} }
} }
score -= (sentiment1.size() > sentiment2.size() ? sentiment1.size() - sentiment2.size() : sentiment2.size() - sentiment1.size()) * 500; } catch (Exception ex) {
DocumentReaderAndWriter<CoreLabel> readerAndWriter = classifier.makePlainTextReaderAndWriter(); System.out.println("pipelineAnnotation stacktrace: " + ex.getLocalizedMessage() + "\n");
List classifyRaw1 = classifier.classifyRaw(str, readerAndWriter); }
List classifyRaw2 = classifier.classifyRaw(str1, readerAndWriter); sentenceConstituencyParseList.clear();
score -= (classifyRaw1.size() > classifyRaw2.size() ? classifyRaw1.size() - classifyRaw2.size() : classifyRaw2.size() - classifyRaw1.size()) * 200; ConcurrentMap<Integer, SimpleMatrix> simpleSMXlist = new MapMaker().concurrencyLevel(2).makeMap();
int mainSentiment1 = 0; ConcurrentMap<Integer, SimpleMatrix> simpleSMXlistVector = new MapMaker().concurrencyLevel(2).makeMap();
int longest1 = 0; ConcurrentMap<Integer, Integer> sentiment1 = new MapMaker().concurrencyLevel(2).makeMap();
int mainSentiment2 = 0; ConcurrentMap<Integer, Integer> sentiment2 = new MapMaker().concurrencyLevel(2).makeMap();
int longest2 = 0; for (CoreMap sentence : pipelineAnnotation1Sentiment.get(CoreAnnotations.SentencesAnnotation.class)) {
for (CoreMap sentence : pipelineAnnotation1Sentiment.get(CoreAnnotations.SentencesAnnotation.class)) { Tree tree = sentence.get(SentimentCoreAnnotations.SentimentAnnotatedTree.class);
Tree tree = sentence.get(SentimentCoreAnnotations.SentimentAnnotatedTree.class); sentiment1.put(sentiment1.size(), RNNCoreAnnotations.getPredictedClass(tree));
int sentiment = RNNCoreAnnotations.getPredictedClass(tree); SimpleMatrix predictions = RNNCoreAnnotations.getPredictions(tree);
String partText = sentence.toString(); SimpleMatrix nodeVector = RNNCoreAnnotations.getNodeVector(tree);
SimpleMatrix predictions = RNNCoreAnnotations.getPredictions(tree); simpleSMXlist.put(simpleSMXlist.size(), predictions);
if (partText.length() > longest1) { simpleSMXlistVector.put(simpleSMXlistVector.size() + 1, nodeVector);
mainSentiment1 = sentiment; }
longest1 = partText.length(); ConcurrentMap<Integer, Double> elementSumCounter = new MapMaker().concurrencyLevel(2).makeMap();
ConcurrentMap<Integer, Double> dotMap = new MapMaker().concurrencyLevel(2).makeMap();
for (CoreMap sentence : pipelineAnnotation2Sentiment.get(CoreAnnotations.SentencesAnnotation.class)) {
Tree tree = sentence.get(SentimentCoreAnnotations.SentimentAnnotatedTree.class);
sentiment2.put(sentiment2.size() + 1, RNNCoreAnnotations.getPredictedClass(tree));
SimpleMatrix predictions = RNNCoreAnnotations.getPredictions(tree);
SimpleMatrix nodeVector = RNNCoreAnnotations.getNodeVector(tree);
score += simpleSMXlist.values().stream().map((simpleSMX) -> predictions.dot(simpleSMX) * 100).map((dot) -> dot > 50 ? dot - 50 : dot > 0 ? 50 - dot : 50).map((subtracter) -> {
subtracter *= 25; //25
return subtracter;
}).map((subtracter) -> subtracter).reduce(score, (accumulator, _item) -> accumulator + _item);
for (SimpleMatrix simpleSMX : simpleSMXlistVector.values()) {
double dot = nodeVector.dot(simpleSMX);
double elementSum = nodeVector.kron(simpleSMX).elementSum();
elementSum = Math.round(elementSum * 100.0) / 100.0;
elementSumCounter.put(elementSumCounter.size() + 1, elementSum);
dotMap.put(dotMap.size() + 1, dot);
if (dot < 0.1) {
score += 256;
} }
} if (dot > 0.50) {
for (CoreMap sentence : pipelineAnnotation2Sentiment.get(CoreAnnotations.SentencesAnnotation.class)) { score -= 2400;
Tree tree = sentence.get(SentimentCoreAnnotations.SentimentAnnotatedTree.class);
int sentiment = RNNCoreAnnotations.getPredictedClass(tree);
SimpleMatrix predictions = RNNCoreAnnotations.getPredictions(tree);
String partText = sentence.toString();
if (partText.length() > longest2) {
mainSentiment2 = sentiment;
longest2 = partText.length();
} }
} if (elementSum < 0.01 && elementSum > 0.00) {
if (longest1 != longest2) { score += 1300;
long deffLongest = longest1 > longest2 ? longest1 : longest2; } else if (elementSum > 0.1 && elementSum < 1.0) {
long deffshorter = longest1 < longest2 ? longest1 : longest2; score += 1100;
if (deffLongest >= (deffshorter * 2) - 1 && deffLongest - deffshorter <= 45) {
score += (deffLongest - deffshorter) * 200;
} else if (mainSentiment1 != mainSentiment2 && deffLongest - deffshorter > 20 && deffLongest - deffshorter < 45) {
score += (deffLongest - deffshorter) * 200;
} else { } else {
score -= (deffLongest - deffshorter) * 50; score -= elementSum * 1424;
} }
} }
int tokensCounter1 = 0; }
int tokensCounter2 = 0; if (dotMap.values().size() > 1) {
int anotatorcounter1 = 0; OptionalDouble minvalueDots = dotMap.values().stream().mapToDouble(Double::doubleValue).min();
int anotatorcounter2 = 0; OptionalDouble maxvalueDots = dotMap.values().stream().mapToDouble(Double::doubleValue).max();
int inflectedCounterPositive1 = 0; if (maxvalueDots.getAsDouble() - minvalueDots.getAsDouble() < 0.05) {
int inflectedCounterPositive2 = 0; score += 3500;
int inflectedCounterNegative = 0;
int MarkedContinuousCounter1 = 0;
int MarkedContinuousCounter2 = 0;
int UnmarkedPatternCounter = 0;
ConcurrentMap<Integer, String> ITokenMapTag1 = new MapMaker().concurrencyLevel(2).makeMap();
ConcurrentMap<Integer, String> ITokenMapTag2 = new MapMaker().concurrencyLevel(2).makeMap();
ConcurrentMap<Integer, String> strTokenStems1 = new MapMaker().concurrencyLevel(2).makeMap();
ConcurrentMap<Integer, String> strTokenStems2 = new MapMaker().concurrencyLevel(2).makeMap();
ConcurrentMap<Integer, String> strTokenForm1 = new MapMaker().concurrencyLevel(2).makeMap();
ConcurrentMap<Integer, String> strTokenForm2 = new MapMaker().concurrencyLevel(2).makeMap();
ConcurrentMap<Integer, String> strTokenGetEntry1 = new MapMaker().concurrencyLevel(2).makeMap();
ConcurrentMap<Integer, String> strTokenGetEntry2 = new MapMaker().concurrencyLevel(2).makeMap();
ConcurrentMap<Integer, String> strTokenGetiPart1 = new MapMaker().concurrencyLevel(2).makeMap();
ConcurrentMap<Integer, String> strTokenGetiPart2 = new MapMaker().concurrencyLevel(2).makeMap();
ConcurrentMap<Integer, String> strTokenEntryPOS1 = new MapMaker().concurrencyLevel(2).makeMap();
ConcurrentMap<Integer, String> strTokenEntryPOS2 = new MapMaker().concurrencyLevel(2).makeMap();
try {
List<CoreMap> sentences = jmweStrAnnotation1.get(CoreAnnotations.SentencesAnnotation.class);
for (CoreMap sentence : sentences) {
for (IMWE<IToken> token : sentence.get(JMWEAnnotation.class)) {
if (token.isInflected()) {
inflectedCounterPositive1++;
} else {
inflectedCounterNegative++;
}
strTokenForm1.put(strTokenForm1.size() + 1, token.getForm());
strTokenGetEntry1.put(strTokenGetEntry1.size() + 1, token.getEntry().toString().substring(token.getEntry().toString().length() - 1));
Collection<IMWEDesc.IPart> values = token.getPartMap().values();
IMWEDesc entry = token.getEntry();
MarkedContinuousCounter1 += entry.getMarkedContinuous();
UnmarkedPatternCounter += entry.getUnmarkedPattern();
for (IMWEDesc.IPart iPart : values) {
strTokenGetiPart1.put(strTokenGetiPart1.size() + 1, iPart.getForm());
}
for (String strPostPrefix : entry.getPOS().getPrefixes()) {
strTokenEntryPOS1.put(strTokenEntryPOS1.size() + 1, strPostPrefix);
}
for (IToken tokens : token.getTokens()) {
ITokenMapTag1.put(ITokenMapTag1.size() + 1, tokens.getTag());
for (String strtoken : tokens.getStems()) {
strTokenStems1.put(strTokenStems1.size() + 1, strtoken);
}
}
tokensCounter1++;
}
anotatorcounter1++;
}
sentences = jmweStrAnnotation2.get(CoreAnnotations.SentencesAnnotation.class);
for (CoreMap sentence : sentences) {
for (IMWE<IToken> token : sentence.get(JMWEAnnotation.class)) {
if (token.isInflected()) {
inflectedCounterPositive2++;
} else {
inflectedCounterNegative--;
}
strTokenForm2.put(strTokenForm2.size() + 1, token.getForm());
strTokenGetEntry2.put(strTokenGetEntry2.size() + 1, token.getEntry().toString().substring(token.getEntry().toString().length() - 1));
Collection<IMWEDesc.IPart> values = token.getPartMap().values();
IMWEDesc entry = token.getEntry();
MarkedContinuousCounter2 += entry.getMarkedContinuous();
UnmarkedPatternCounter += entry.getUnmarkedPattern();
for (IMWEDesc.IPart iPart : values) {
strTokenGetiPart2.put(strTokenGetiPart2.size() + 1, iPart.getForm());
}
for (String strPostPrefix : entry.getPOS().getPrefixes()) {
strTokenEntryPOS2.put(strTokenEntryPOS2.size() + 1, strPostPrefix);
}
for (IToken tokens : token.getTokens()) {
ITokenMapTag2.put(ITokenMapTag2.size() + 1, tokens.getTag());
for (String strtoken : tokens.getStems()) {
strTokenStems2.put(strTokenStems2.size() + 1, strtoken);
}
}
tokensCounter2++;
}
anotatorcounter2++;
}
} catch (Exception ex) {
System.out.println("SENTIMENT stacktrace: " + ex.getMessage() + "\n");
} }
for (String strTokenPos1 : strTokenEntryPOS1.values()) { }
for (String strTokenPos2 : strTokenEntryPOS2.values()) { if (elementSumCounter.values().size() > 1){
if (strTokenPos1.equals(strTokenPos2)) { OptionalDouble minvalueElements = elementSumCounter.values().stream().mapToDouble(Double::doubleValue).min();
score += 500; OptionalDouble maxvalueElements = elementSumCounter.values().stream().mapToDouble(Double::doubleValue).max();
if (maxvalueElements.getAsDouble() - minvalueElements.getAsDouble() < 0.05) {
score += 3500;
}
}
score -= (sentiment1.size() > sentiment2.size() ? sentiment1.size() - sentiment2.size() : sentiment2.size() - sentiment1.size()) * 500;
DocumentReaderAndWriter<CoreLabel> readerAndWriter = classifier.makePlainTextReaderAndWriter();
List classifyRaw1 = classifier.classifyRaw(str, readerAndWriter);
List classifyRaw2 = classifier.classifyRaw(str1, readerAndWriter);
score -= (classifyRaw1.size() > classifyRaw2.size() ? classifyRaw1.size() - classifyRaw2.size() : classifyRaw2.size() - classifyRaw1.size()) * 200;
int mainSentiment1 = 0;
int longest1 = 0;
int mainSentiment2 = 0;
int longest2 = 0;
for (CoreMap sentence : pipelineAnnotation1Sentiment.get(CoreAnnotations.SentencesAnnotation.class)) {
Tree tree = sentence.get(SentimentCoreAnnotations.SentimentAnnotatedTree.class);
int sentiment = RNNCoreAnnotations.getPredictedClass(tree);
String partText = sentence.toString();
SimpleMatrix predictions = RNNCoreAnnotations.getPredictions(tree);
if (partText.length() > longest1) {
mainSentiment1 = sentiment;
longest1 = partText.length();
}
}
for (CoreMap sentence : pipelineAnnotation2Sentiment.get(CoreAnnotations.SentencesAnnotation.class)) {
Tree tree = sentence.get(SentimentCoreAnnotations.SentimentAnnotatedTree.class);
int sentiment = RNNCoreAnnotations.getPredictedClass(tree);
SimpleMatrix predictions = RNNCoreAnnotations.getPredictions(tree);
String partText = sentence.toString();
if (partText.length() > longest2) {
mainSentiment2 = sentiment;
longest2 = partText.length();
}
}
if (longest1 != longest2) {
long deffLongest = longest1 > longest2 ? longest1 : longest2;
long deffshorter = longest1 < longest2 ? longest1 : longest2;
//deffLongest >= (deffshorter * 2)
if (deffLongest < (deffshorter * 2) - 1 && deffLongest - deffshorter <= 45) {
score += (deffLongest - deffshorter) * 120;
} else if (mainSentiment1 != mainSentiment2 && deffLongest - deffshorter > 20 && deffLongest - deffshorter < 45) {
score += (deffLongest - deffshorter) * 120;
} else if (deffLongest - deffshorter < 2) {
score += (deffLongest + deffshorter) * 40;
} else if (deffLongest - deffshorter <= 5){
score += 2500;
} else{
score -= (deffLongest - deffshorter) * 50;
}
}
int tokensCounter1 = 0;
int tokensCounter2 = 0;
int anotatorcounter1 = 0;
int anotatorcounter2 = 0;
int inflectedCounterPositive1 = 0;
int inflectedCounterPositive2 = 0;
int inflectedCounterNegative = 0;
int MarkedContinuousCounter1 = 0;
int MarkedContinuousCounter2 = 0;
int UnmarkedPatternCounter = 0;
ConcurrentMap<Integer, String> ITokenMapTag1 = new MapMaker().concurrencyLevel(2).makeMap();
ConcurrentMap<Integer, String> ITokenMapTag2 = new MapMaker().concurrencyLevel(2).makeMap();
ConcurrentMap<Integer, String> strTokenStems1 = new MapMaker().concurrencyLevel(2).makeMap();
ConcurrentMap<Integer, String> strTokenStems2 = new MapMaker().concurrencyLevel(2).makeMap();
ConcurrentMap<Integer, String> strTokenForm1 = new MapMaker().concurrencyLevel(2).makeMap();
ConcurrentMap<Integer, String> strTokenForm2 = new MapMaker().concurrencyLevel(2).makeMap();
ConcurrentMap<Integer, String> strTokenGetEntry1 = new MapMaker().concurrencyLevel(2).makeMap();
ConcurrentMap<Integer, String> strTokenGetEntry2 = new MapMaker().concurrencyLevel(2).makeMap();
ConcurrentMap<Integer, String> strTokenGetiPart1 = new MapMaker().concurrencyLevel(2).makeMap();
ConcurrentMap<Integer, String> strTokenGetiPart2 = new MapMaker().concurrencyLevel(2).makeMap();
ConcurrentMap<Integer, String> strTokenEntryPOS1 = new MapMaker().concurrencyLevel(2).makeMap();
ConcurrentMap<Integer, String> strTokenEntryPOS2 = new MapMaker().concurrencyLevel(2).makeMap();
try {
List<CoreMap> sentences = jmweStrAnnotation1.get(CoreAnnotations.SentencesAnnotation.class);
for (CoreMap sentence : sentences) {
for (IMWE<IToken> token : sentence.get(JMWEAnnotation.class)) {
if (token.isInflected()) {
inflectedCounterPositive1++;
} else {
inflectedCounterNegative++;
} }
strTokenForm1.put(strTokenForm1.size() + 1, token.getForm());
strTokenGetEntry1.put(strTokenGetEntry1.size() + 1, token.getEntry().toString().substring(token.getEntry().toString().length() - 1));
Collection<IMWEDesc.IPart> values = token.getPartMap().values();
IMWEDesc entry = token.getEntry();
MarkedContinuousCounter1 += entry.getMarkedContinuous();
UnmarkedPatternCounter += entry.getUnmarkedPattern();
for (IMWEDesc.IPart iPart : values) {
strTokenGetiPart1.put(strTokenGetiPart1.size() + 1, iPart.getForm());
}
for (String strPostPrefix : entry.getPOS().getPrefixes()) {
strTokenEntryPOS1.put(strTokenEntryPOS1.size() + 1, strPostPrefix);
}
for (IToken tokens : token.getTokens()) {
ITokenMapTag1.put(ITokenMapTag1.size() + 1, tokens.getTag());
for (String strtoken : tokens.getStems()) {
strTokenStems1.put(strTokenStems1.size() + 1, strtoken);
}
}
tokensCounter1++;
}
anotatorcounter1++;
}
sentences = jmweStrAnnotation2.get(CoreAnnotations.SentencesAnnotation.class);
for (CoreMap sentence : sentences) {
for (IMWE<IToken> token : sentence.get(JMWEAnnotation.class)) {
if (token.isInflected()) {
inflectedCounterPositive2++;
} else {
inflectedCounterNegative--;
}
strTokenForm2.put(strTokenForm2.size() + 1, token.getForm());
strTokenGetEntry2.put(strTokenGetEntry2.size() + 1, token.getEntry().toString().substring(token.getEntry().toString().length() - 1));
Collection<IMWEDesc.IPart> values = token.getPartMap().values();
IMWEDesc entry = token.getEntry();
MarkedContinuousCounter2 += entry.getMarkedContinuous();
UnmarkedPatternCounter += entry.getUnmarkedPattern();
for (IMWEDesc.IPart iPart : values) {
strTokenGetiPart2.put(strTokenGetiPart2.size() + 1, iPart.getForm());
}
for (String strPostPrefix : entry.getPOS().getPrefixes()) {
strTokenEntryPOS2.put(strTokenEntryPOS2.size() + 1, strPostPrefix);
}
for (IToken tokens : token.getTokens()) {
ITokenMapTag2.put(ITokenMapTag2.size() + 1, tokens.getTag());
for (String strtoken : tokens.getStems()) {
strTokenStems2.put(strTokenStems2.size() + 1, strtoken);
}
}
tokensCounter2++;
}
anotatorcounter2++;
}
} catch (Exception ex) {
System.out.println("SENTIMENT stacktrace: " + ex.getMessage() + "\n");
}
for (String strTokenPos1 : strTokenEntryPOS1.values()) {
for (String strTokenPos2 : strTokenEntryPOS2.values()) {
if (strTokenPos1.equals(strTokenPos2)) {
score += 500;
} }
} }
}
if (UnmarkedPatternCounter > 0 && UnmarkedPatternCounter < 5) {
score += UnmarkedPatternCounter * 1600; score += UnmarkedPatternCounter * 1600;
if (MarkedContinuousCounter1 > 0 && MarkedContinuousCounter2 > 0) { }
score += MarkedContinuousCounter1 > MarkedContinuousCounter2 ? (MarkedContinuousCounter1 - MarkedContinuousCounter2) * 500 if (MarkedContinuousCounter1 > 0 && MarkedContinuousCounter2 > 0) {
: (MarkedContinuousCounter2 - MarkedContinuousCounter1) * 500; score += MarkedContinuousCounter1 > MarkedContinuousCounter2 ? (MarkedContinuousCounter1 - MarkedContinuousCounter2) * 500
} : (MarkedContinuousCounter2 - MarkedContinuousCounter1) * 500;
for (String strTokeniPart1 : strTokenGetiPart1.values()) { }
for (String strTokeniPart2 : strTokenGetiPart2.values()) { for (String strTokeniPart1 : strTokenGetiPart1.values()) {
if (strTokeniPart1.equals(strTokeniPart2)) { for (String strTokeniPart2 : strTokenGetiPart2.values()) {
score += 400; if (strTokeniPart1.equals(strTokeniPart2)) {
} score += 400;
} }
} }
for (String strTokenEntry1 : strTokenGetEntry1.values()) { }
for (String strTokenEntry2 : strTokenGetEntry2.values()) { for (String strTokenEntry1 : strTokenGetEntry1.values()) {
if (strTokenEntry1.equals(strTokenEntry2)) { for (String strTokenEntry2 : strTokenGetEntry2.values()) {
score += 2500; if (strTokenEntry1.equals(strTokenEntry2)) {
} score += 2500;
} }
} }
for (String strmapTag : ITokenMapTag1.values()) { }
for (String strmapTag1 : ITokenMapTag2.values()) { for (String strmapTag : ITokenMapTag1.values()) {
if (strmapTag.equals(strmapTag1)) { for (String strmapTag1 : ITokenMapTag2.values()) {
score += 1450; if (strmapTag.equals(strmapTag1)) {
} score += 1450;
} }
} }
for (String strTokenForm1itr1 : strTokenForm1.values()) { }
for (String strTokenForm1itr2 : strTokenForm2.values()) { for (String strTokenForm1itr1 : strTokenForm1.values()) {
if (strTokenForm1itr1.equals(strTokenForm1itr2)) { for (String strTokenForm1itr2 : strTokenForm2.values()) {
score += 2600; if (strTokenForm1itr1.equals(strTokenForm1itr2)) {
} else if (strTokenForm1itr1.contains(strTokenForm1itr2)) { score += 2600;
score += 500; } else if (strTokenForm1itr1.contains(strTokenForm1itr2)) {
} score += 500;
} }
} }
for (String strTokenStem : strTokenStems1.values()) { }
for (String strTokenStem1 : strTokenStems2.values()) { for (String strTokenStem : strTokenStems1.values()) {
if (strTokenStem.equals(strTokenStem1)) { for (String strTokenStem1 : strTokenStems2.values()) {
score += 1500; if (strTokenStem.equals(strTokenStem1)) {
} score += 1500;
} }
} }
if (inflectedCounterPositive1 + inflectedCounterPositive2 > inflectedCounterNegative && inflectedCounterNegative > 0) { }
score += (inflectedCounterPositive1 - inflectedCounterNegative) * 650; if (inflectedCounterPositive1 + inflectedCounterPositive2 > inflectedCounterNegative && inflectedCounterNegative > 0) {
} score += (inflectedCounterPositive1 - inflectedCounterNegative) * 650;
if (inflectedCounterPositive1 > 0 && inflectedCounterPositive2 > 0) { }
score += ((inflectedCounterPositive1 + inflectedCounterPositive2) - inflectedCounterNegative) * 550; if (inflectedCounterPositive1 > 0 && inflectedCounterPositive2 > 0) {
} score += ((inflectedCounterPositive1 + inflectedCounterPositive2) - inflectedCounterNegative) * 550;
if (anotatorcounter1 > 1 && anotatorcounter2 > 1) { }
score += (anotatorcounter1 + anotatorcounter2) * 400; if (anotatorcounter1 > 1 && anotatorcounter2 > 1) {
} score += (anotatorcounter1 + anotatorcounter2) * 400;
if (tokensCounter1 > 0 && tokensCounter2 > 0) { }
score += (tokensCounter1 + tokensCounter2) * 400; if (tokensCounter1 > 0 && tokensCounter2 > 0) {
} else { score += (tokensCounter1 + tokensCounter2) * 400;
score -= tokensCounter1 >= tokensCounter2 ? (tokensCounter1 - tokensCounter2) * 500 : (tokensCounter2 - tokensCounter1) * 500; } else {
} int elseint = tokensCounter1 >= tokensCounter2 ? (tokensCounter1 - tokensCounter2) * 500 : (tokensCounter2 - tokensCounter1) * 500;
LevenshteinDistance leven = new LevenshteinDistance(str, str1); score -= elseint;
double SentenceScoreDiff = leven.computeLevenshteinDistance(); }
SentenceScoreDiff *= 15; LevenshteinDistance leven = new LevenshteinDistance(str, str1);
score -= SentenceScoreDiff; double SentenceScoreDiff = leven.computeLevenshteinDistance();
SentenceScoreDiff *= 15;
score -= SentenceScoreDiff;
} catch (Exception ex) { } catch (Exception ex) {
System.out.println("SENTIMENT stacktrace Overall catch: " + ex.getMessage() + "\n"); System.out.println("SENTIMENT stacktrace Overall catch: " + ex.getMessage() + "\n");
} }

1
ArtificialAutism/src/main/java/PresentationLayer/DiscordHandler.java
View File

@ -21,7 +21,6 @@ import FunctionLayer.PipelineJMWESingleton;
import java.io.IOException; import java.io.IOException;
import java.sql.SQLException; import java.sql.SQLException;
import java.util.List; import java.util.List;
import java.util.concurrent.CountDownLatch;
import java.util.logging.Level; import java.util.logging.Level;
import java.util.logging.Logger; import java.util.logging.Logger;
import org.javacord.api.DiscordApi; import org.javacord.api.DiscordApi;