autism

2019-03-02 15:10:46 +01:00
parent fc01f7fb43
commit 57bbd5d55e
62 changed files with 2233 additions and 0 deletions
@@ -0,0 +1,73 @@
+package FunctionLayer.misc;
+
+import edu.stanford.nlp.ling.HasWord;
+import edu.stanford.nlp.ling.IndexedWord;
+import edu.stanford.nlp.ling.TaggedWord;
+import edu.stanford.nlp.ling.Word;
+import edu.stanford.nlp.parser.lexparser.LexicalizedParser;
+import edu.stanford.nlp.process.DocumentPreprocessor;
+import edu.stanford.nlp.process.Tokenizer;
+import edu.stanford.nlp.trees.GrammaticalStructure;
+import edu.stanford.nlp.trees.GrammaticalStructureFactory;
+import edu.stanford.nlp.trees.Tree;
+import edu.stanford.nlp.trees.TreebankLanguagePack;
+import edu.stanford.nlp.trees.TypedDependency;
+import java.io.StringReader;
+import java.util.ArrayList;
+import java.util.List;
+
+/*
+ * To change this license header, choose License Headers in Project Properties.
+ * To change this template file, choose Tools | Templates
+ * and open the template in the editor.
+ */
+/**
+ *
+ * @author install1
+ */
+public class SentimentAnalyzerTest {
+
+    public static SentimentAnalyzerTest instance = new SentimentAnalyzerTest();
+    public static String grammar = "edu/stanford/nlp/models/lexparser/englishPCFG.ser.gz";
+    public static String[] options = {"-maxLength", "80", "-retainTmpSubcategories"};
+
+    public static LexicalizedParser initiateLexicalizedParser() {
+        LexicalizedParser lp = LexicalizedParser.loadModel(grammar, options);
+        return lp;
+    }
+
+    public static TreebankLanguagePack initiateTreebankLanguagePack(LexicalizedParser lp) {
+        TreebankLanguagePack tlp = lp.getOp().langpack();
+        return tlp;
+    }
+
+    public double sentimentanalyzing(String str, String str1, double sreturn, LexicalizedParser lp, TreebankLanguagePack tlp) {
+        Iterable<List<? extends HasWord>> sentences;
+        Tokenizer<? extends HasWord> toke
+                = tlp.getTokenizerFactory().getTokenizer(new StringReader(str));
+        List<? extends HasWord> sentence = toke.tokenize();
+        String[] sent3 = {str1};
+        String[] tag3 = {"PRP", "MD", "VB", "PRP", "."}; // Parser gets second "can" wrong without help
+        List<TaggedWord> sentence2 = new ArrayList<>();
+        for (int i = 0; i < sent3.length; i++) {
+            sentence2.add(new TaggedWord(sent3[i], tag3[i]));
+        }
+        //parse.pennPrint();
+        List<List<? extends HasWord>> tmp
+                = new ArrayList<>();
+        tmp.add(sentence2);
+        tmp.add(sentence);
+        sentences = tmp;
+        for (List<? extends HasWord> sentence1 : sentences) {
+            Tree parse1 = lp.parse(sentence1);
+            GrammaticalStructureFactory gsf = tlp.grammaticalStructureFactory();
+            GrammaticalStructure gs = gsf.newGrammaticalStructure(parse1);
+            double score = parse1.score();
+            if (score > sreturn) {
+                //System.out.println("\n score : " + score + "\n");
+                sreturn = score;
+            }
+        }
+        return sreturn;
+    }
+}
@@ -0,0 +1,66 @@
+/*
+ * To change this license header, choose License Headers in Project Properties.
+ * To change this template file, choose Tools | Templates
+ * and open the template in the editor.
+ */
+package FunctionLayer.misc;
+
+import DataLayer.DataMapper;
+import FunctionLayer.CustomError;
+import FunctionLayer.SimilarityMatrix;
+import static FunctionLayer.MYSQLDatahandler.EXPIRE_TIME_IN_SECONDS;
+import com.google.common.base.Stopwatch;
+import com.google.common.collect.ArrayListMultimap;
+import com.google.common.collect.MapMaker;
+import com.google.common.collect.Multimap;
+import java.io.IOException;
+import java.sql.SQLException;
+import java.util.LinkedHashMap;
+import java.util.List;
+import java.util.Map;
+import java.util.concurrent.ConcurrentMap;
+import java.util.concurrent.TimeUnit;
+
+/**
+ *
+ * @author install1
+ */
+public class SentimentSimilarityCacheObsolete {
+
+    public static final long EXPIRE_TIME_IN_SECONDS = TimeUnit.SECONDS.convert(5, TimeUnit.HOURS);
+    private static ConcurrentMap<String, List<SimilarityMatrix>> SimilarityMatrixCache;
+    private static Stopwatch stopwatch;
+
+    public SentimentSimilarityCacheObsolete(ConcurrentMap<Integer, String> StringCache, Stopwatch stopwatch) {
+        this.stopwatch = Stopwatch.createUnstarted();
+        this.SimilarityMatrixCache = new MapMaker().concurrencyLevel(2).makeMap();
+    }
+
+    public void clearConCurrentMaps() {
+        SimilarityMatrixCache.clear();
+    }
+
+    private Multimap<String, SimilarityMatrix> getCache() throws SQLException, IOException, CustomError {
+        List<SimilarityMatrix> matrixlist;
+        matrixlist = DataMapper.getAllSementicMatrixes();
+        Multimap<String, SimilarityMatrix> LHM =  ArrayListMultimap.create();
+        for (int i = 0; i < matrixlist.size(); i++) {
+            LHM.put(matrixlist.get(i).getPrimaryString(), matrixlist.get(i));
+        }
+        return LHM;
+    }
+
+    public static String getResponseStr(String strreturn) {
+        String str = "";
+        if (stopwatch.elapsed(TimeUnit.SECONDS) >= EXPIRE_TIME_IN_SECONDS || !stopwatch.isRunning()) {
+
+            if (!stopwatch.isRunning()) {
+                stopwatch.start();
+            } else {
+                stopwatch.reset();
+            }
+        }
+        return str;
+    }
+
+}
@@ -0,0 +1,152 @@
+/*
+ * To change this license header, choose License Headers in Project Properties.
+ * To change this template file, choose Tools | Templates
+ * and open the template in the editor.
+https://github.com/DonatoMeoli/WS4J
+ */
+package FunctionLayer.misc;
+
+import edu.cmu.lti.jawjaw.pobj.POS;
+import edu.cmu.lti.lexical_db.ILexicalDatabase;
+import edu.cmu.lti.lexical_db.NictWordNet;
+import edu.cmu.lti.lexical_db.data.Concept;
+import edu.cmu.lti.ws4j.Relatedness;
+import edu.cmu.lti.ws4j.RelatednessCalculator;
+import edu.cmu.lti.ws4j.impl.HirstStOnge;
+import edu.cmu.lti.ws4j.impl.JiangConrath;
+import edu.cmu.lti.ws4j.impl.LeacockChodorow;
+import edu.cmu.lti.ws4j.impl.Lesk;
+import edu.cmu.lti.ws4j.impl.Lin;
+import edu.cmu.lti.ws4j.impl.Path;
+import edu.cmu.lti.ws4j.impl.Resnik;
+import edu.cmu.lti.ws4j.impl.WuPalmer;
+
+/**
+ *
+ * @author install1
+ * https://www.programcreek.com/java-api-examples/?api=edu.cmu.lti.ws4j.RelatednessCalculator
+ * https://stackoverflow.com/questions/36300485/how-to-resolve-the-difference-between-the-values-attained-in-the-web-api-and-the
+ */
+public class WordNetSimalarityObsolete {
+
+    private static ILexicalDatabase db = new NictWordNet();
+    private static RelatednessCalculator rc1 = new WuPalmer(db);
+    private static RelatednessCalculator rc2 = new Resnik(db);
+    private static RelatednessCalculator rc3 = new JiangConrath(db);
+    private static RelatednessCalculator rc4 = new Lin(db);
+    private static RelatednessCalculator rc5 = new LeacockChodorow(db);
+    private static RelatednessCalculator rc6 = new Path(db);
+    private static RelatednessCalculator rc7 = new Lesk(db);
+    private static RelatednessCalculator rc8 = new HirstStOnge(db);
+
+    public static double SentenceMatcherSimilarityMatrix(String[] words1, String[] words2, double maxScore) {
+        {
+            double[][] s1 = getSimilarityMatrix(words1, words2, rc1);
+            for (int i = 0; i < words1.length; i++) {
+                for (int j = 0; j < words2.length; j++) {
+                    if (s1[i][j] < maxScore && s1[i][j] > 0.0) {
+                        System.out.print(s1[i][j] + "\t");
+                        System.out.println("WuPalmer");
+                        maxScore = s1[i][j];
+                    }
+                }
+            }
+        }
+        {
+            double[][] s2 = getSimilarityMatrix(words1, words2, rc2);
+            for (int i = 0; i < words1.length; i++) {
+                for (int j = 0; j < words2.length; j++) {
+                    if (s2[i][j] < maxScore && s2[i][j] > 0.0) {
+                        System.out.println("Resnik");
+                        System.out.print(s2[i][j] + "\t");
+                        maxScore = s2[i][j];
+                    }
+                }
+            }
+        }
+        {
+            double[][] s2 = getSimilarityMatrix(words1, words2, rc3);
+            for (int i = 0; i < words1.length; i++) {
+                for (int j = 0; j < words2.length; j++) {
+                    if (s2[i][j] < maxScore && s2[i][j] > 0.0) {
+                        System.out.println("JiangConrath");
+                        System.out.print(s2[i][j] + "\t");
+                        maxScore = s2[i][j];
+                    }
+                }
+            }
+        }
+        {
+            double[][] s2 = getSimilarityMatrix(words1, words2, rc4);
+            for (int i = 0; i < words1.length; i++) {
+                for (int j = 0; j < words2.length; j++) {
+                    if (s2[i][j] < maxScore && s2[i][j] > 0.0) {
+                        System.out.println("Lin");
+                        System.out.print(s2[i][j] + "\t");
+                        maxScore = s2[i][j];
+                    }
+                }
+            }
+        }
+        {
+            double[][] s2 = getSimilarityMatrix(words1, words2, rc5);
+            for (int i = 0; i < words1.length; i++) {
+                for (int j = 0; j < words2.length; j++) {
+                    if (s2[i][j] < maxScore && s2[i][j] > 0.0) {
+                        System.out.print(s2[i][j] + "\t");
+                        System.out.println("LeacockChodrow");
+                        maxScore = s2[i][j];
+                    }
+                }
+            }
+        }
+        {
+            double[][] s2 = getSimilarityMatrix(words1, words2, rc6);
+            for (int i = 0; i < words1.length; i++) {
+                for (int j = 0; j < words2.length; j++) {
+                    if (s2[i][j] < maxScore && s2[i][j] > 0.0) {
+                        System.out.println("Path");
+                        System.out.print(s2[i][j] + "\t");
+                        maxScore = s2[i][j];
+                    }
+                }
+            }
+        }
+        {
+            double[][] s2 = getSimilarityMatrix(words1, words2, rc7);
+            for (int i = 0; i < words1.length; i++) {
+                for (int j = 0; j < words2.length; j++) {
+                    if (s2[i][j] < maxScore && s2[i][j] > 0.0) {
+                        System.out.println("Lesk");
+                        System.out.print(s2[i][j] + "\t");
+                        maxScore = s2[i][j];
+                    }
+                }
+            }
+        }
+        {
+            double[][] s2 = getSimilarityMatrix(words1, words2, rc8);
+            for (int i = 0; i < words1.length; i++) {
+                for (int j = 0; j < words2.length; j++) {
+                    if (s2[i][j] < maxScore && s2[i][j] > 0.0) {
+                        System.out.println("HirstStOnge");
+                        System.out.print(s2[i][j] + "\t");
+                        maxScore = s2[i][j];
+                    }
+                }
+            }
+        }
+        return maxScore;
+    }
+
+    public static double[][] getSimilarityMatrix(String[] words1, String[] words2, RelatednessCalculator rc) {
+        double[][] result = new double[words1.length][words2.length];
+        for (int i = 0; i < words1.length; i++) {
+            for (int j = 0; j < words2.length; j++) {
+                double score = rc.calcRelatednessOfWords(words1[i], words2[j]);
+                result[i][j] = score;
+            }
+        }
+        return result;
+    }
+}
@@ -0,0 +1,74 @@
+/*
+ * To change this license header, choose License Headers in Project Properties.
+ * To change this template file, choose Tools | Templates
+ * and open the template in the editor.
+ */
+package FunctionLayer.misc;
+
+import edu.cmu.lti.lexical_db.ILexicalDatabase;
+import edu.cmu.lti.lexical_db.NictWordNet;
+import edu.cmu.lti.ws4j.RelatednessCalculator;
+import edu.cmu.lti.ws4j.impl.HirstStOnge;
+import edu.cmu.lti.ws4j.impl.JiangConrath;
+import edu.cmu.lti.ws4j.impl.LeacockChodorow;
+import edu.cmu.lti.ws4j.impl.Lesk;
+import edu.cmu.lti.ws4j.impl.Lin;
+import edu.cmu.lti.ws4j.impl.Path;
+import edu.cmu.lti.ws4j.impl.Resnik;
+import edu.cmu.lti.ws4j.impl.WuPalmer;
+import java.util.ArrayList;
+import java.util.List;
+
+/**
+ *
+ * @author install1
+ * http://ws4jdemo.appspot.com/?mode=s&s1=something+like+a+sentence&s2=should+not+be+like+the+first+one
+ */
+public class WordNetSimalarityTestObsolete {
+
+    private static ILexicalDatabase db = new NictWordNet();
+    private static RelatednessCalculator rc1 = new WuPalmer(db);
+    private static RelatednessCalculator rc2 = new Resnik(db);
+    private static RelatednessCalculator rc3 = new JiangConrath(db);
+    private static RelatednessCalculator rc4 = new Lin(db);
+    private static RelatednessCalculator rc5 = new LeacockChodorow(db);
+    private static RelatednessCalculator rc6 = new Path(db);
+    private static RelatednessCalculator rc7 = new Lesk(db);
+    private static RelatednessCalculator rc8 = new HirstStOnge(db);
+
+    public static double SentenceMatcherSimilarityMatrix(String[] words1, String[] words2, double maxScore) {
+        boolean initial = maxScore == 0.0;
+        List<RelatednessCalculator> RCList = new ArrayList();
+        RCList.add(rc1);
+        RCList.add(rc2);
+        RCList.add(rc3);
+        RCList.add(rc4);
+        RCList.add(rc5);
+        RCList.add(rc6);
+        RCList.add(rc7);
+        RCList.add(rc8);
+        for (int h = 0; h < RCList.size(); h++) {
+            double s1 = getSimilarityMatrix(words1, words2, RCList.get(h), maxScore, initial);
+            System.out.println("s1: " + String.format("%.0f", s1) + " \nmaxScore: " + maxScore);
+            if (s1 > 0.01 && (s1 < maxScore || initial)) {
+                maxScore = s1;
+            }
+        }
+        return maxScore;
+    }
+
+    public static double getSimilarityMatrix(String[] words1, String[] words2, RelatednessCalculator rc, double maxScore, boolean initial) {
+        double rtndouble = 0.01;
+        for (int i = 0; i < words1.length; i++) {
+            for (int j = 0; j < words2.length; j++) {
+                if (maxScore > rtndouble / words2.length || initial) {
+                    rtndouble += (rc.calcRelatednessOfWords(words1[i], words2[j]));
+                    //System.out.println("RelatednessCalculator: " + rc.toString());
+                } else {
+                    return rtndouble;
+                }
+            }
+        }
+        return rtndouble;
+    }
+}
@@ -0,0 +1,58 @@
+/*
+ * To change this license header, choose License Headers in Project Properties.
+ * To change this template file, choose Tools | Templates
+ * and open the template in the editor.
+ */
+package FunctionLayer.misc;
+
+/**
+ *
+ * @author install1
+ */
+public class notes {
+    /* 
+    
+        /*
+            ILexicalDatabase db = new NictWordNet();
+            RelatednessCalculator lesk = new Lesk(db);
+            POS posWord1 = POS.n;
+            POS posWord2 = POS.n;
+            double maxScore = 0;
+            WS4JConfiguration.getInstance().setMFS(true);
+            List<Concept> synsets1 = (List<Concept>) db.getAllConcepts(strreturn, posWord1.name());
+            for (int i = 0; i < allStringValuesPresent.size(); i++) {
+                List<Concept> synsets2 = (List<Concept>) db.getAllConcepts(allStringValuesPresent.get(i), posWord2.name());
+                for (Concept synset1 : synsets1) {
+                    for (Concept synset2 : synsets2) {
+                        Relatedness relatedness = lesk.calcRelatednessOfSynset(synset1, synset2);
+                        double score = relatedness.getScore();
+                        if (score > maxScore) {
+                            maxScore = score;
+                            index = i;
+                        }
+                    }
+                }
+
+            }
+             
+    private static RelatednessCalculator[] rcs;
+
+    static {
+        WS4JConfiguration.getInstance().setMemoryDB(false);
+        WS4JConfiguration.getInstance().setMFS(true);
+        ILexicalDatabase db = new MITWordNet();
+        rcs = new RelatednessCalculator[]{
+            new HirstStOnge(db), new LeacockChodorow(db), new Lesk(db), new WuPalmer(db),
+            new Resnik(db), new JiangConrath(db), new Lin(db), new Path(db)
+        };
+    }
+    https://github.com/DonatoMeoli/WS4J
+    https://www.programcreek.com/2014/01/calculate-words-similarity-using-wordnet-in-java/
+     */
+ /*
+ //available options of metrics
+ private static RelatednessCalculator[] rcs = { new HirstStOnge(db),
+   new LeacockChodorow(db), new Lesk(db), new WuPalmer(db),
+   new Resnik(db), new JiangConrath(db), new Lin(db), new Path(db) };
+     */
+}