Package org.apache.mahout.classifier

Examples of org.apache.mahout.classifier.ConfusionMatrix

21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
        symbols.add(pieces[0]);
      }
      line = in.readLine();
    }

    ConfusionMatrix x2 = new ConfusionMatrix(symbols, "unknown");

    in = new BufferedReader(new FileReader(inputFile));
    line = in.readLine();
    while (line != null) {
      String[] pieces = line.split(",");        
      String trueValue = pieces[0];
      String estimatedValue = pieces[1];
      x2.addInstance(trueValue, estimatedValue);     
      line = in.readLine();
    }
    System.out.printf("%s\n\n", x2.toString());
  }
View Full Code Here
81
82
83
84
85
86
87
88
   
    client.setConf(conf);
    JobClient.runJob(conf);
   
    Path outputFiles = new Path(outPath.toString() + "/part*");
    ConfusionMatrix matrix = readResult(dfs, outputFiles, conf, params);
    log.info("{}", matrix.summarize());
  }
View Full Code Here
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
        confusionMatrix.put(correctLabel, rowMatrix);
       
      }
    }
   
    ConfusionMatrix matrix = new ConfusionMatrix(confusionMatrix.keySet(), defaultLabel);
    for (Map.Entry<String,Map<String,Integer>> correctLabelSet : confusionMatrix.entrySet()) {
      Map<String,Integer> rowMatrix = correctLabelSet.getValue();
      for (Map.Entry<String,Integer> classifiedLabelSet : rowMatrix.entrySet()) {
        matrix.addInstance(correctLabelSet.getKey(), classifiedLabelSet.getKey());
        matrix.putCount(correctLabelSet.getKey(), classifiedLabelSet.getKey(), classifiedLabelSet.getValue());
      }
    }
    return matrix;
   
  }
View Full Code Here
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
            // log.info("{} {}", correctLabel, classifiedLabel);
           
          }
          lineNum++;
        }
        ConfusionMatrix matrix = resultAnalyzer.getConfusionMatrix();
        log.info("{}", matrix);
        BayesClassifierDriver.confusionMatrixSeqFileExport(params, matrix);

        log.info("ConfusionMatrix: {}", matrix.toString());
          
        log.info("Classified instances from {}", file.getName());
        if (verbose) {
          log.info("Performance stats {}", operationStats.toString());
        }
View Full Code Here
85
86
87
88
89
90
91
92
93
94
95
   
    client.setConf(conf);
    JobClient.runJob(conf);
   
    Path outputFiles = new Path(outPath, "part*");
    ConfusionMatrix matrix = readResult(outputFiles, conf, params);
    log.info("{}", matrix);
    if (params.get("confusionMatrix") != null) {
      confusionMatrixSeqFileExport(params, matrix);
    }
   
View Full Code Here
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
      Integer count = Double.valueOf(value.get()).intValue();
      rowMatrix.put(classifiedLabel, count);
      confusionMatrix.put(correctLabel, rowMatrix);
    }

    ConfusionMatrix matrix = new ConfusionMatrix(confusionMatrix.keySet(), defaultLabel);
    for (Map.Entry<String,Map<String,Integer>> correctLabelSet : confusionMatrix.entrySet()) {
      Map<String,Integer> rowMatrix = correctLabelSet.getValue();
      for (Map.Entry<String,Integer> classifiedLabelSet : rowMatrix.entrySet()) {
        matrix.addInstance(correctLabelSet.getKey(), classifiedLabelSet.getKey());
        matrix.putCount(correctLabelSet.getKey(), classifiedLabelSet.getKey(), classifiedLabelSet.getValue());
      }
    }
    return matrix;
  }
View Full Code Here
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
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
      if (lmp.getTargetCategories().size() <=2 ) {
        collector = new Auc();
      }
     
      OnlineSummarizer slh = new OnlineSummarizer();
      ConfusionMatrix cm = new ConfusionMatrix(lmp.getTargetCategories(), defaultCategory);

      State<Wrapper, CrossFoldLearner> best = lr.getBest();
      if (best == null) {
        output.printf("%s\n",
            "AdaptiveLogisticRegression has not be trained probably.");
        return;
      }
      CrossFoldLearner learner = best.getPayload().getLearner();

      BufferedReader in = TrainLogistic.open(inputFile);
      String line = in.readLine();
      csv.firstLine(line);
      line = in.readLine();
      if (showScores) {
        output.printf(Locale.ENGLISH, "\"%s\", \"%s\", \"%s\", \"%s\"\n",
            "target", "model-output", "log-likelihood", "average-likelihood");
      }
      while (line != null) {
        Vector v = new SequentialAccessSparseVector(lmp.getNumFeatures());
        //TODO: How to avoid extra target values not shown in the training process.
        int target = csv.processLine(line, v);
        double likelihood = learner.logLikelihood(target, v);
        double score = learner.classifyFull(v).maxValue();
       
        slh.add(likelihood);
        cm.addInstance(csv.getTargetString(line), csv.getTargetLabel(target));       
       
        if (showScores) {
          output.printf(Locale.ENGLISH, "%8d, %.12f, %.13f, %.13f\n", target,
              score, learner.logLikelihood(target, v), slh.getMean());
        }
        if (collector != null) {
          collector.add(target, score);
        }
        line = in.readLine();
      }
     
      output.printf(Locale.ENGLISH,"\nLog-likelihood:");
      output.printf(Locale.ENGLISH, "Min=%.2f, Max=%.2f, Mean=%.2f, Median=%.2f\n",
          slh.getMin(), slh.getMax(), slh.getMean(), slh.getMedian());

      if (collector != null) {       
        output.printf(Locale.ENGLISH, "\nAUC = %.2f\n", collector.auc());       
      }
     
      if (showConfusion) {
        output.printf(Locale.ENGLISH, "\n%s\n\n", cm.toString());
       
        if (collector != null){
          Matrix m = collector.entropy();
          output.printf(Locale.ENGLISH,
              "Entropy Matrix: [[%.1f, %.1f], [%.1f, %.1f]]\n", m.get(0, 0),
View Full Code Here
80
81
82
83
84
85
86
87
    client.setConf(conf);
    JobClient.runJob(conf);
   
    Path outputFiles = new Path(outPath, "part*");
    FileSystem dfs = FileSystem.get(outPath.toUri(), conf);   
    ConfusionMatrix matrix = readResult(dfs, outputFiles, conf, params);
    log.info("{}", matrix.summarize());
  }
View Full Code Here
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
        confusionMatrix.put(correctLabel, rowMatrix);
       
      }
    }
   
    ConfusionMatrix matrix = new ConfusionMatrix(confusionMatrix.keySet(), defaultLabel);
    for (Map.Entry<String,Map<String,Integer>> correctLabelSet : confusionMatrix.entrySet()) {
      Map<String,Integer> rowMatrix = correctLabelSet.getValue();
      for (Map.Entry<String,Integer> classifiedLabelSet : rowMatrix.entrySet()) {
        matrix.addInstance(correctLabelSet.getKey(), classifiedLabelSet.getKey());
        matrix.putCount(correctLabelSet.getKey(), classifiedLabelSet.getKey(), classifiedLabelSet.getValue());
      }
    }
    return matrix;
   
  }
View Full Code Here
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
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
      if (lmp.getTargetCategories().size() <= 2) {
        collector = new Auc();
      }

      OnlineSummarizer slh = new OnlineSummarizer();
      ConfusionMatrix cm = new ConfusionMatrix(lmp.getTargetCategories(), defaultCategory);

      State<Wrapper, CrossFoldLearner> best = lr.getBest();
      if (best == null) {
        output.println("AdaptiveLogisticRegression has not be trained probably.");
        return;
      }
      CrossFoldLearner learner = best.getPayload().getLearner();

      BufferedReader in = TrainLogistic.open(inputFile);
      String line = in.readLine();
      csv.firstLine(line);
      line = in.readLine();
      if (showScores) {
        output.println("\"target\", \"model-output\", \"log-likelihood\", \"average-likelihood\"");
      }
      while (line != null) {
        Vector v = new SequentialAccessSparseVector(lmp.getNumFeatures());
        //TODO: How to avoid extra target values not shown in the training process.
        int target = csv.processLine(line, v);
        double likelihood = learner.logLikelihood(target, v);
        double score = learner.classifyFull(v).maxValue();

        slh.add(likelihood);
        cm.addInstance(csv.getTargetString(line), csv.getTargetLabel(target));       

        if (showScores) {
          output.printf(Locale.ENGLISH, "%8d, %.12f, %.13f, %.13f%n", target,
              score, learner.logLikelihood(target, v), slh.getMean());
        }
        if (collector != null) {
          collector.add(target, score);
        }
        line = in.readLine();
      }

      output.printf(Locale.ENGLISH,"\nLog-likelihood:");
      output.printf(Locale.ENGLISH, "Min=%.2f, Max=%.2f, Mean=%.2f, Median=%.2f%n",
          slh.getMin(), slh.getMax(), slh.getMean(), slh.getMedian());

      if (collector != null) {       
        output.printf(Locale.ENGLISH, "%nAUC = %.2f%n", collector.auc());
      }

      if (showConfusion) {
        output.printf(Locale.ENGLISH, "%n%s%n%n", cm.toString());

        if (collector != null) {
          Matrix m = collector.entropy();
          output.printf(Locale.ENGLISH,
              "Entropy Matrix: [[%.1f, %.1f], [%.1f, %.1f]]%n", m.get(0, 0),
View Full Code Here
TOP

Related Classes of org.apache.mahout.classifier.ConfusionMatrix

  • mia.classifier.ch15.ConfusionMatrixExample
  • org.apache.commons.math3.stat.descriptive.moment.Mean
  • org.apache.mahout.cf.taste.impl.common.FullRunningAverageAndStdDev
  • org.apache.mahout.cf.taste.impl.common.RunningAverageAndStdDev
  • org.apache.mahout.classifier.bayes.mapreduce.bayes.BayesClassifierDriver
  • org.apache.mahout.classifier.bayes.TestClassifier
  • org.apache.mahout.classifier.sgd.ValidateAdaptiveLogistic
  • org.apache.mahout.math.DenseMatrix
  • org.apache.mahout.math.Matrix
    • 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.