Package dmt.tools

Examples of dmt.tools.CSVFileWriter

87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
        }

        line = reader.readLine();
      }

      CSVFileWriter out = new CSVFileWriter("output/" + clustersCount
          + "clusterCentersMarina.csv", ',');
      out.writeFields(headers);
      for (int i = 0; i < clustersCount; i++)
      {
        Vector<String> fields = clusterCenters.get(i);
        fields.add(0, "Cluster" + i);
        out.writeFields(fields);
      }
      out.close();

    }
  }
View Full Code Here
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
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
        .hierarchicalCluster(TextInstance.textInstancesSet);
    int k = 30;
    Set<Set<TextInstance>> clResponsePartition = completeLinkDendrogram
        .partitionK(k);
    Object[] clusters = clResponsePartition.toArray();
    CSVFileWriter out = new CSVFileWriter("completeLinkClustersCSV.csv",
        ',');
    Vector<String> header = new Vector<String>();
    header.add("Cluster label");
    out.writeFields(header);
    Object[] textInstancesArray = TextInstance.textInstancesSet.toArray();
    for (int i = 0; i < textInstancesArray.length; i++)
    {
      for (int j = 0; j < clusters.length; j++)
      {
        if (((Set<TextInstance>) clusters[j])
            .contains(textInstancesArray[i]))
        {
          Vector<String> clusterLabel = new Vector<String>();
          clusterLabel.add((j + 1) + "");
          out.writeFields(clusterLabel);
        }
      }
    }
    out.close();

    HierarchicalClusterer<TextInstance> slClusterer = new SingleLinkClusterer<TextInstance>(
        TextInstance.EUCLIDEAN_DISTANCE);
    Dendrogram<TextInstance> singleLinkDendrogram = slClusterer
        .hierarchicalCluster(TextInstance.textInstancesSet);
    Set<Set<TextInstance>> slResponsePartition = singleLinkDendrogram
        .partitionK(k);
    clusters = slResponsePartition.toArray();
    out = new CSVFileWriter("singleLinkClustersCSV.csv", ',');
    out.writeFields(header);
    for (int i = 0; i < textInstancesArray.length; i++)
    {
      for (int j = 0; j < clusters.length; j++)
      {
        if (((Set<TextInstance>) clusters[j])
            .contains(textInstancesArray[i]))
        {
          Vector<String> clusterLabel = new Vector<String>();
          clusterLabel.add((j + 1) + "");
          out.writeFields(clusterLabel);
        }
      }
    }
    out.close();

  }
View Full Code Here
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
    }
    ClusterAnalysis jca = new ClusterAnalysis(5, 100, dataPoints);
    jca.startAnalysis();

    Vector<Vector<DataPoint>> clusters = jca.getClusterOutput();
    CSVFileWriter out = new CSVFileWriter("kMeansClustersCSV.csv",
        ',');
    Vector<String> header = new Vector<String>();
    header.add("Document ID");
    header.add("XPath");
    header.add("Cluster label");
    out.writeFields(header);
    for (int i = 0; i < clusters.size(); i++)
    {
      for (int j = 0; j < clusters.get(i).size(); j++)
      {
        DataPoint point = clusters.get(i).get(j);
        String documentId = point.getId().substring(0, point.getId().indexOf("/"));
        String XPath = point.getId().substring(point.getId().indexOf("/"), point.getId().length());
        Vector<String> fields = new Vector<String>();
        fields.add(documentId);
        fields.add(XPath);
        fields.add(i+"");
        out.writeFields(fields);
      }
    }
    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
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
15
16
17
18
19
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
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
   */
  public static void main(String[] args) throws IOException
  {
    int num_instances = 200;
    int countNonNull=0;
    CSVFileWriter out = new CSVFileWriter("clusteringDistancesCSV.csv", ',');
    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++;
      if(count1==num_instances) break;
    }
    out.close();
    System.out.println(countNonNull);
   
  }
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
  }
 
  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
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
    }
  }
 
  private void listBagOfWords() throws IOException
  {
    CSVFileWriter out = new CSVFileWriter(outCSV, ',');
    Object[] keys = stemWords.keySet().toArray();
   
    for(int i=0; i< keys.length; i++)
    {
      Vector<String> fields = new Vector<String>();
      fields.add(keys[i].toString());
      fields.add(stemWords.get(keys[i]).toString());
      fields.add(stemWordsTotal.get(keys[i]).toString());
      out.writeFields(fields);
    }
    out.close();
  }
View Full Code Here
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
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
        .hierarchicalCluster(TextInstance.textInstancesSet);
    int k = 30;
    Set<Set<TextInstance>> clResponsePartition = completeLinkDendrogram
        .partitionK(k);
    Object[] clusters = clResponsePartition.toArray();
    CSVFileWriter out = new CSVFileWriter("completeLinkClustersCSV.csv",
        ',');
    Vector<String> header = new Vector<String>();
    header.add("Cluster label");
    out.writeFields(header);
    Object[] textInstancesArray = TextInstance.textInstancesSet.toArray();
    for (int i = 0; i < textInstancesArray.length; i++)
    {
      for (int j = 0; j < clusters.length; j++)
      {
        if (((Set<TextInstance>) clusters[j])
            .contains(textInstancesArray[i]))
        {
          Vector<String> clusterLabel = new Vector<String>();
          clusterLabel.add((j + 1) + "");
          out.writeFields(clusterLabel);
        }
      }
    }
    out.close();

    HierarchicalClusterer<TextInstance> slClusterer = new SingleLinkClusterer<TextInstance>(
        TextInstance.EUCLIDEAN_DISTANCE);
    Dendrogram<TextInstance> singleLinkDendrogram = slClusterer
        .hierarchicalCluster(TextInstance.textInstancesSet);
    Set<Set<TextInstance>> slResponsePartition = singleLinkDendrogram
        .partitionK(k);
    clusters = slResponsePartition.toArray();
    out = new CSVFileWriter("singleLinkClustersCSV.csv", ',');
    out.writeFields(header);
    for (int i = 0; i < textInstancesArray.length; i++)
    {
      for (int j = 0; j < clusters.length; j++)
      {
        if (((Set<TextInstance>) clusters[j])
            .contains(textInstancesArray[i]))
        {
          Vector<String> clusterLabel = new Vector<String>();
          clusterLabel.add((j + 1) + "");
          out.writeFields(clusterLabel);
        }
      }
    }
    out.close();

  }
View Full Code Here
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
      }
   
    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
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
TOP

Related Classes of dmt.tools.CSVFileWriter

  • dmt.clustering.ClusterCentersProcessor
  • dmt.clustering.ClusteringProcessor
  • dmt.clustering.DistancesProcessor
  • dmt.clustering.HierarchicalClusteringProcessor
  • dmt.clustering.KMeansClusteringProcessor
  • dmt.features.definitions.ElementTypeFeature
  • dmt.features.definitions.NumberOfCharsStemmedFeature
  • 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.