Package edu.msu.cme.rdp.classifier.train

Examples of edu.msu.cme.rdp.classifier.train.LineageSequence

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
        LineageSequenceParser parser = new LineageSequenceParser(in);
        boolean next = parser.hasNext();
        assertTrue(next);
        // test the first sequence
        LineageSequence pSeq = parser.next();
        String name = "X53199";
        assertEquals(name.toUpperCase(), pSeq.getSeqName());
        assertEquals("AZOSPIRILLUM_GROUP", (String) pSeq.getAncestors().get(4));
        assertEquals("PROTEOBACTERIA", (String) pSeq.getAncestors().get(2));
        assertEquals("GAEA", (String) pSeq.getAncestors().get(0));

        //test the last sequence
        parser.next();
        pSeq = parser.next();
        name = "AB002485";
        assertEquals(name.toUpperCase(), pSeq.getSeqName());
        assertEquals("M.RRR_SUBGROUP", (String) pSeq.getAncestors().get(5));
        assertEquals("TTTT_GROUP", (String) pSeq.getAncestors().get(4));
        assertEquals("BELTA_SUBDIVISION", (String) pSeq.getAncestors().get(3));
        assertEquals("GAEA", (String) pSeq.getAncestors().get(0));
        String sequence = "AAAAUAtttAGUCCCCCCCCUG";

        assertEquals(sequence, pSeq.getSeqString());
        assertTrue(!parser.hasNext());
    }
View Full Code Here
42
43
44
45
46
47
48
49
50
51
52
        File in = new File(System.class.getResource("/test/classifier/testTrainingSet.fasta").getFile());

        LineageSequenceParser parser = new LineageSequenceParser(in);
        // test the first sequence
        LineageSequence pSeq = parser.next();
        c1.initWordOccurrence(pSeq, wordPriorArr, true);

        pSeq = parser.next();
        c1.initWordOccurrence(pSeq, wordPriorArr, true);
View Full Code Here
100
101
102
103
104
105
106
107
108
109
110
        HierarchyTree c2 = new HierarchyTree("child2", root, c2Taxon);
        File in = new File(System.class.getResource("/test/classifier/testTrainingSet.fasta").getFile());

        LineageSequenceParser parser = new LineageSequenceParser(in);
        // test the first sequence
        LineageSequence pSeq = parser.next();
        c1.initWordOccurrence(pSeq, wordPriorArr, true);

        pSeq = parser.next();
        c1.initWordOccurrence(pSeq, wordPriorArr, true);
View Full Code Here
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
        ArrayList<HierarchyTree> nodeList = new ArrayList(nodeMap.values());
       
        // test the first sequence
        File queryReader = new File(System.class.getResource("/test/classifier/testNBClassifierSet.fasta").getFile());       
        parser = new LineageSequenceParser(queryReader);
        LineageSequence pSeq = parser.next();
        GoodWordIterator iterator = new GoodWordIterator(pSeq.getSeqString());
        NBClassifier classifier = new NBClassifier(factory, iterator.getWordArr(), nodeList, useSeed, min_bootstrap_words);

        assertEquals(pSeq.getSeqName(), "XG1_child1");       
        ValidationClassificationResult result = classifier.assignClass();
        assertEquals("G1", ((HierarchyTree) result.getBestClass()).getName());
        assertTrue(0.1 > result.getPosteriorProb());


        pSeq = parser.next();
        // test the 3rd getSequence()
        pSeq = parser.next();
        assertEquals(pSeq.getSeqName(), "XG2_child1");
        iterator = new GoodWordIterator(pSeq.getSeqString());
        classifier = new NBClassifier(factory, iterator.getWordArr(), nodeList, useSeed, min_bootstrap_words);
        result = classifier.assignClass();
        assertEquals("G2", ((HierarchyTree) result.getBestClass()).getName());
        assertTrue(0.2 > result.getPosteriorProb());


        pSeq = parser.next();
        // test the 5th getSequence()
        pSeq = parser.next();
        assertEquals(pSeq.getSeqName(), "XPh2G6_child1");
        iterator = new GoodWordIterator(pSeq.getSeqString());
        classifier = new NBClassifier(factory, iterator.getWordArr(), nodeList, useSeed, min_bootstrap_words);
        result = classifier.assignClass();
        assertEquals("G1", ((HierarchyTree) result.getBestClass()).getName());
        assertTrue(0.2 > result.getPosteriorProb());

        //test the 8th sequence in G7, it is the same as the 9th sequence in G8
        // the classifier should randomly choose a genus (either G7 or G8) because the score will be tie
        parser.next();
        parser.next();
        pSeq = parser.next();
        assertEquals(pSeq.getSeqName(), "XPh2G7_child1");
        iterator = new GoodWordIterator(pSeq.getSeqString());
        int G7_count = 0;
        int G8_count = 0;
        for ( int run = 0; run < DecisionMaker.NUM_OF_RUNS; run++){
            classifier = new NBClassifier(factory, iterator.getWordArr(), nodeList, useSeed, min_bootstrap_words);
            result = classifier.assignClass();
View Full Code Here
TOP

Related Classes of edu.msu.cme.rdp.classifier.train.LineageSequence

  • edu.msu.cme.rdp.classifier.train.validation.crossvalidate.CrossValidate
  • edu.msu.cme.rdp.classifier.train.validation.crossvalidate.RdmSelectTaxon
  • edu.msu.cme.rdp.classifier.train.validation.distance.CompareTrainingSets
  • edu.msu.cme.rdp.classifier.train.validation.distance.PairwiseSeqDistance
  • edu.msu.cme.rdp.classifier.train.validation.distance.TaxaSimilarityMain
  • edu.msu.cme.rdp.classifier.train.validation.HierarchyTreeTest
  • edu.msu.cme.rdp.classifier.train.validation.leaveoneout.LeaveOneOutTester
  • edu.msu.cme.rdp.classifier.train.validation.movingwindow.WindowTester
  • edu.msu.cme.rdp.classifier.train.validation.NBClassifierTest
  • edu.msu.cme.rdp.classifier.train.validation.SequenceParserTest
    • 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.