Package dmt.tools

Examples of dmt.tools.CSVFileReader

31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
  {
   
    //run first the preProcessor
    (new CSVPreProcessor(inCSV, tmpFile)).run();
   
    CSVFileReader in = new CSVFileReader(tmpFile, ',');
    CSVFileWriter out = new CSVFileWriter(outCSV, ',');
   
    //adding headers
    out.writeFields(getHeaders());

      Vector<String> fields = in.readFields();
      int k=0;
     
      while(fields!=null)
      {
        //update the hashMap
        hashMap.put(fields.get(0)+fields.get(1), fields.get(2).equalsIgnoreCase("0") ? false : true);
       
        //preserve existing fields
       
        //compute the features
        Vector<Feature> features = Feature.getFeatures();
      for(int i=0; i < features.size(); i++)
      {
        Object[] values = features.get(i).getValues(fields, hashMap);
        for(int j = 0; j < values.length; j++)
        {
          try
          {
            fields.add(values[j].toString());
          }
          catch(NullPointerException exception)
          {
            fields.add("?");
          }
         
        }
      }
      fields.remove(3);
      //fields.set(3, new Integer(fields.get(3).length()).toString());
        out.writeFields(fields);
        fields = in.readFields();
        k++;
        //if(k>1000) break;
       
      }
 
      in.close();
      out.close();
     
      ElementTypeFeature.showElementTypes();
      NumberOfCharsStemmedFeature.printWords();
  }
View Full Code Here
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
    Vector<String> headers = new Vector<String>();
    headers.add("Euclidean");
    headers.add("Manhattan");
    out.writeFields(headers);

    CSVFileReader in1 = new CSVFileReader("csv_out.csv", ',');
    // skip the headers
    Vector<String> fields1 = in1.readFields();
    fields1 = in1.readFields();
    int count1 = 0;
    while (fields1 != null)
    {
      String id1 = fields1.get(0) + fields1.get(1);
      Object[] bagOfWordsTfIdf1 = fields1.subList(4, fields1.size())
          .toArray();
      TextInstance instance1 = new TextInstance(bagOfWordsTfIdf1, id1);
      CSVFileReader in2 = new CSVFileReader("csv_out.csv", ',');
      Vector<String> fields2 = in2.readFields();
      fields2 = in2.readFields();
      TextInstance instance2;
      Object[] bagOfWordsTfIdf2;
      int count2=0;
      while (fields2 != null)
      {     
        String id2 = fields2.get(0) + fields2.get(1);
        bagOfWordsTfIdf2 = fields2.subList(4, fields2.size()).toArray();
        instance2 = new TextInstance(bagOfWordsTfIdf2, id2);
        Vector<String> distances = new Vector<String>();
        double d1 = TextInstance.computeEuclideanDistance(
            instance1, instance2);
        distances.add(d1+"");
        distances.add(TextInstance.computeManhattanDistance(instance1, instance2)
            + "");
        out.writeFields(distances);
        fields2 = in2.readFields();
        count2++;
        if(count2==num_instances) break;
      }
      fields1 = in1.readFields();
      count1++;
View Full Code Here
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
    this.outCSV  = outCSV;
  }
 
  public void run() throws IOException
  {
    CSVFileReader in = new CSVFileReader(inCSV, ',');
    CSVFileWriter out = new CSVFileWriter(outCSV, ',');
   
      Vector<String> fields = in.readFields();
      int k=0;
     
      while(fields!=null)
      {
        //run the prefeatures
        Vector<PreFeature> preFeatures = PreFeature.getFeatures();
      for(int i=0; i < preFeatures.size(); i++)
      {
        preFeatures.get(i).run(fields);
      }
      out.writeFields(fields);
        fields = in.readFields();
        k++;
        //if(k>10) break;
       
      }
      in.close();
      out.close();
  }
View Full Code Here
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
  private double norm;
  public static Set<TextInstance> textInstancesSet = new HashSet<TextInstance>();

  public static void loadTextInstances() throws IOException
  {
    CSVFileReader in1 = new CSVFileReader("csv_out.csv", ',');
    // skip the headers
    Vector<String> fields1 = in1.readFields();
    fields1 = in1.readFields();
    int no_instances = 1000;
    int k = 0;
    while (fields1 != null)
    {
      String id = fields1.get(0) + fields1.get(1);
      Object[] bagOfWordsTfIdf1 = fields1.subList(4, fields1.size())
          .toArray();
      TextInstance instance1 = new TextInstance(bagOfWordsTfIdf1, id);
      // instance1.clearBagOfWordsTfIdf();
      textInstancesSet.add(instance1);
      fields1 = in1.readFields();
      k++;
      if (no_instances == k) break;
    }
  }
View Full Code Here
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
 
  public void run() throws IOException
  {
    loadBagOfWords();
   
    CSVFileReader in = new CSVFileReader(inCSV, ',');

      Vector<String> fields = in.readFields();
     
      while(fields!=null)
      { 
        //generate here the id of the element
        fields.set(0, fields.get(0) + fields.get(1));
       
        String text = fields.get(3).toLowerCase();
       
        loadStopWords();
      SnowballStemmer stemmer = new org.tartarus.snowball.ext.englishStemmer();
     
      for(int i=0; i < stopWords.size(); i++)
      {
        text = text.replaceAll("[\\s]"+stopWords.get(i)+"[\\s]", " ");
      }
     
      Pattern p = Pattern.compile("[^a-zA-Z]+");
      String [] words = p.split(text);
      text = "";
      for(int i=0; i < words.length; i++)
      {
        if(words[i].length() < 3)
        {
          continue;
        }
       
        stemmer.setCurrent(words[i]);
        stemmer.stem();
        String stemmed = stemmer.getCurrent();
       
        if(!loadedWords.contains(stemmed))
        {
          continue;
        }
       
        if(stemWordsTotal.containsKey(stemmed))
        {
          stemWordsTotal.put(stemmed, stemWordsTotal.get(stemmed) + 1);
        }
        else
        {
          stemWordsTotal.put(stemmed, 1);
        }
       
        if(text.indexOf(stemmed) >= 0)
        {
          continue;
        }
       
        if(documentsWords.containsKey(stemmed))
        {
          if(documentsWords.get(stemmed).indexOf(fields.get(0)) < 0)
          {
            documentsWords.put(stemmed, documentsWords.get(stemmed) + " " + fields.get(0));
            stemWords.put(stemmed, stemWords.get(stemmed) + 1);
          }
        }
        else
        {
          stemWords.put(stemmed, 1);
          documentsWords.put(stemmed, fields.get(0));
        }
      }
       
        fields = in.readFields();
      }
 
      in.close();
     
      listBagOfWords();
  }
View Full Code Here
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
  }
 
  private void loadBagOfWords() throws IOException
  {
    loadedWords = new Vector<String>();
    CSVFileReader in = new CSVFileReader(inBagOfWords, ',');

      Vector<String> fields = in.readFields();
     
      while(fields!=null)
      {
        loadedWords.add(fields.get(0));
        fields = in.readFields();
      }
 
      in.close();
  }
View Full Code Here
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
    if(stopWords != null)
    {
      return;
    }
   
    CSVFileReader in;
    try
    {
      in = new CSVFileReader("datasets/common-english-words-with-contractions.txt", ',');
      stopWords = in.readFields();
      in.close();
    } catch (IOException e)
    {
      e.printStackTrace();
    }
  }
View Full Code Here
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
  }
 
  public void run() throws IOException
  {
    Vector<String> fields;
    CSVFileReader clusters1In = new CSVFileReader(clusters1,',');
    fields = clusters1In.readFields();
    fields = clusters1In.readFields();
    while(fields!=null)
      {
      hashMap1.put(fields.get(0)+fields.get(1), fields.get(2).substring(7));
      fields = clusters1In.readFields();
      }
   
    clusters1In.close();
   
    CSVFileReader clusters2In = new CSVFileReader(clutsers2,',');
    fields = clusters2In.readFields();
    fields = clusters2In.readFields();
    while(fields!=null)
      {
      hashMap2.put(fields.get(0)+fields.get(1), fields.get(2).substring(7));
      fields = clusters2In.readFields();
      }
   
    clusters2In.close();
   
    CSVFileReader in = new CSVFileReader(inCSV, ',');
    CSVFileWriter out = new CSVFileWriter(outCSV, ',');
   
    //adding headers
      fields = in.readFields();
      fields.add("ClusterVictor");
      fields.add("ClusterMarina");
      String toc = fields.get(2);
      fields.remove(2);
      fields.add(toc);
      out.writeFields(fields);
      fields = in.readFields();
      int k=0;
     
      while(fields!=null)
      {
        if(hashMap1.containsKey(fields.get(0)+fields.get(1)))
        {
          fields.add(hashMap1.get(fields.get(0)+fields.get(1)));
        }
        else
        {
          fields.add(""+no_clusters1);
        }
        if(hashMap2.containsKey(fields.get(0)+fields.get(1)))
        {
          fields.add(hashMap2.get(fields.get(0)+fields.get(1)));
        }
        else
        {
          fields.add(""+no_clusters2);
        }
       
        toc = fields.get(2);
        fields.remove(2);
        fields.add(toc);
       
        out.writeFields(fields);
        fields = in.readFields();
        k++;
       
      }
 
      in.close();
      out.close();
  }
View Full Code Here
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
  {
   
    //run first the preProcessor
    (new CSVPreProcessor(inCSV, tmpFile)).run();
   
    CSVFileReader in = new CSVFileReader(tmpFile, ',');
    CSVFileWriter out = new CSVFileWriter(outCSV, ',');
   
    //adding headers
    out.writeFields(getHeaders());

      Vector<String> fields = in.readFields();
      int k=0;
     
      while(fields!=null)
      {
        //update the hashMap
        hashMap.put(fields.get(0)+fields.get(1), fields.get(2).equalsIgnoreCase("0") ? false : true);
       
        //preserve existing fields
       
        //compute the features
        Feature bagOfWordsFeature = new MostFrequentWordsFeature();
      Object[] values = bagOfWordsFeature.getValues(fields, hashMap);
      for(int j = 0; j < values.length; j++)
      {
        try
        {
          fields.add(values[j].toString());
        }
        catch(NullPointerException exception)
        {
          fields.add("?");
        }
      }
      fields.remove(3);
      //fields.set(3, new Integer(fields.get(3).length()).toString());
        out.writeFields(fields);
        fields = in.readFields();
        k++;
        //if(k>10) break;
       
      }
 
      in.close();
      out.close();
     
      ElementTypeFeature.showElementTypes();
      NumberOfCharsStemmedFeature.printWords();
  }
View Full Code Here
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
  }
 
  public void run() throws IOException
  {
   
    CSVFileReader in = new CSVFileReader(inCSV, ',');
    CSVFileWriter out = new CSVFileWriter(outCSV, ',');

      Vector<String> fields = in.readFields();
      int k=0;
     
      while(fields!=null)
      {
        fields.remove(0);
        fields.remove(0);
        fields.remove(0);
        if (k == 0)
        {
          out.writeFields(fields);
          for(int i=0; i < NO_CLUSTERS; i++)
          {
            clusters.add(new Vector<Double>(fields.size()));
            for(int j=0;  j < fields.size(); j++)
            {
              clusters.get(i).add(0.0);
            }
          }
        }
        else
        {
         
          int cluster = Integer.parseInt(fields.get(fields.size()-1).substring(7));
         
          if(cluster >= NO_CLUSTERS || cluster < 0)
          {
            continue;
          }
         
          clusters.get(cluster).set(fields.size()-1, clusters.get(cluster).get(fields.size()-1) + 1);
         
          for(int i=0; i < fields.size()-1; i++)
          {
            Double word = Double.parseDouble(fields.get(i));
            clusters.get(cluster).set(i, clusters.get(cluster).get(i) + word);
          }
        }
       
        fields = in.readFields();
        k++;
        //if(k>1000) break;
       
      }
     
      for(int i=0; i < NO_CLUSTERS; i++)
      {
        Vector<String> newFields = new Vector<String>();
        Double noInstances = clusters.get(i).get(clusters.get(i).size()-1);
        for(int j=0; j < clusters.get(i).size() - 1; j++)
        {
         
          newFields.add((new Double(
              clusters.get(i).get(j) / noInstances
          )).toString());
        }
        newFields.add((new Double(i)).toString());
        out.writeFields(newFields);
      }
 
      in.close();
      out.close();
     
  }
View Full Code Here
TOP

Related Classes of dmt.tools.CSVFileReader

  • dmt.clustering.DistancesProcessor
  • dmt.clustering.TextInstance
  • dmt.features.definitions.ElementTypeFeature
  • dmt.features.definitions.MostFrequentWordsFeature
  • dmt.features.definitions.NumberOfCharsStemmedFeature
  • dmt.features.definitions.NumberOfWordsAfterFeature
  • dmt.features.definitions.NumberOfWordsStemmedFeature
  • dmt.processors.BagOfWordsProcessor
  • dmt.processors.BuildListOfWordsProcessor
  • dmt.processors.CollectClustersProcessor
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.