Package org.encog.persist

Examples of org.encog.persist.EncogFileSection

329
330
331
332
333
334
335
336
337
338
339
   */
  public void load(final InputStream stream) {
    EncogReadHelper reader = null;

    try {
      EncogFileSection section = null;
      reader = new EncogReadHelper(stream);

      while ((section = reader.readNextSection()) != null) {
        processSubSection(section);
      }
View Full Code Here
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
   */
  @Override
  public Object read(final InputStream is) {

    final EncogReadHelper in = new EncogReadHelper(is);
    EncogFileSection section;
    final BasicMLDataSet samples = new BasicMLDataSet();
    Map<String, String> networkParams = null;
    PNNKernelType kernel = null;
    PNNOutputMode outmodel = null;
    int inputCount = 0;
    int outputCount = 0;
    double error = 0;
    double[] sigma = null;

    while ((section = in.readNextSection()) != null) {
      if (section.getSectionName().equals("PNN")
          && section.getSubSectionName().equals("PARAMS")) {
        networkParams = section.parseParams();
      }
      if (section.getSectionName().equals("PNN")
          && section.getSubSectionName().equals("NETWORK")) {
        final Map<String, String> params = section.parseParams();
        inputCount = EncogFileSection.parseInt(params,
            PersistConst.INPUT_COUNT);
        outputCount = EncogFileSection.parseInt(params,
            PersistConst.OUTPUT_COUNT);
        kernel = PersistBasicPNN.stringToKernel(params
            .get(PersistConst.KERNEL));
        outmodel = PersistBasicPNN.stringToOutputMode(params
            .get(PersistBasicPNN.PROPERTY_outputMode));
        error = EncogFileSection
            .parseDouble(params, PersistConst.ERROR);
        sigma = section.parseDoubleArray(params,
            PersistConst.SIGMA);
      }
      if (section.getSectionName().equals("PNN")
          && section.getSubSectionName().equals("SAMPLES")) {
        for (final String line : section.getLines()) {
          final List<String> cols = EncogFileSection
              .splitColumns(line);
          int index = 0;
          final MLData inputData = new BasicMLData(inputCount);
          for (int i = 0; i < inputCount; i++) {
View Full Code Here
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
   */
  @Override
  public Object read(final InputStream is) {
    final SOM result = new SOM();
    final EncogReadHelper in = new EncogReadHelper(is);
    EncogFileSection section;

    while ((section = in.readNextSection()) != null) {
      if (section.getSectionName().equals("SOM")
          && section.getSubSectionName().equals("PARAMS")) {
        final Map<String, String> params = section.parseParams();
        result.getProperties().putAll(params);
      }
      if (section.getSectionName().equals("SOM")
          && section.getSubSectionName().equals("NETWORK")) {
        final Map<String, String> params = section.parseParams();
        result.setWeights(EncogFileSection.parseMatrix(params,
            PersistConst.WEIGHTS));
      }
    }

View Full Code Here
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
115
116
117
118
119
120
121
122
123
124
125
126
127
128
  @Override
  public Object read(final InputStream is) {
    final BasicNetwork result = new BasicNetwork();
    final FlatNetwork flat = new FlatNetwork();
    final EncogReadHelper in = new EncogReadHelper(is);
    EncogFileSection section;

    while ((section = in.readNextSection()) != null) {
      if (section.getSectionName().equals("BASIC")
          && section.getSubSectionName().equals("PARAMS")) {
        final Map<String, String> params = section.parseParams();
        result.getProperties().putAll(params);
      }
      if (section.getSectionName().equals("BASIC")
          && section.getSubSectionName().equals("NETWORK")) {
        final Map<String, String> params = section.parseParams();

        flat.setBeginTraining(EncogFileSection.parseInt(params,
            BasicNetwork.TAG_BEGIN_TRAINING));
        flat.setConnectionLimit(EncogFileSection.parseDouble(params,
            BasicNetwork.TAG_CONNECTION_LIMIT));
        flat.setContextTargetOffset(EncogFileSection.parseIntArray(
            params, BasicNetwork.TAG_CONTEXT_TARGET_OFFSET));
        flat.setContextTargetSize(EncogFileSection.parseIntArray(
            params, BasicNetwork.TAG_CONTEXT_TARGET_SIZE));
        flat.setEndTraining(EncogFileSection.parseInt(params,
            BasicNetwork.TAG_END_TRAINING));
        flat.setHasContext(EncogFileSection.parseBoolean(params,
            BasicNetwork.TAG_HAS_CONTEXT));
        flat.setInputCount(EncogFileSection.parseInt(params,
            PersistConst.INPUT_COUNT));
        flat.setLayerCounts(EncogFileSection.parseIntArray(params,
            BasicNetwork.TAG_LAYER_COUNTS));
        flat.setLayerFeedCounts(EncogFileSection.parseIntArray(params,
            BasicNetwork.TAG_LAYER_FEED_COUNTS));
        flat.setLayerContextCount(EncogFileSection.parseIntArray(
            params, BasicNetwork.TAG_LAYER_CONTEXT_COUNT));
        flat.setLayerIndex(EncogFileSection.parseIntArray(params,
            BasicNetwork.TAG_LAYER_INDEX));
        flat.setLayerOutput(section.parseDoubleArray(params,
            PersistConst.OUTPUT));
        flat.setLayerSums(new double[flat.getLayerOutput().length]);
        flat.setOutputCount(EncogFileSection.parseInt(params,
            PersistConst.OUTPUT_COUNT));
        flat.setWeightIndex(EncogFileSection.parseIntArray(params,
            BasicNetwork.TAG_WEIGHT_INDEX));
        flat.setWeights(section.parseDoubleArray(params,
            PersistConst.WEIGHTS));
        flat.setBiasActivation(section.parseDoubleArray(
            params, BasicNetwork.TAG_BIAS_ACTIVATION));
      } else if (section.getSectionName().equals("BASIC")
          && section.getSubSectionName().equals("ACTIVATION")) {
        int index = 0;

        flat.setActivationFunctions(new ActivationFunction[flat
            .getLayerCounts().length]);

        for (final String line : section.getLines()) {
          ActivationFunction af = null;
          final List<String> cols = EncogFileSection
              .splitColumns(line);
         
          // if this is a class name with a path, then do not default to inside of the Encog package.
View Full Code Here
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
   */
  @Override
  public Object read(final InputStream is) {
    final HopfieldNetwork result = new HopfieldNetwork();
    final EncogReadHelper in = new EncogReadHelper(is);
    EncogFileSection section;

    while ((section = in.readNextSection()) != null) {
      if (section.getSectionName().equals("HOPFIELD")
          && section.getSubSectionName().equals("PARAMS")) {
        final Map<String, String> params = section.parseParams();
        result.getProperties().putAll(params);
      }
      if (section.getSectionName().equals("HOPFIELD")
          && section.getSubSectionName().equals("NETWORK")) {
        final Map<String, String> params = section.parseParams();
        result.setWeights(section.parseDoubleArray(params,
            PersistConst.WEIGHTS));
        result.setCurrentState(section.parseDoubleArray(params,
            PersistConst.OUTPUT));
        result.setNeuronCount(EncogFileSection.parseInt(params,
            PersistConst.NEURON_COUNT));
      }
    }
View Full Code Here
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
   */
  @Override
  public Object read(final InputStream is) {
    final BoltzmannMachine result = new BoltzmannMachine();
    final EncogReadHelper in = new EncogReadHelper(is);
    EncogFileSection section;

    while ((section = in.readNextSection()) != null) {
      if (section.getSectionName().equals("BOLTZMANN")
          && section.getSubSectionName().equals("PARAMS")) {
        final Map<String, String> params = section.parseParams();
        result.getProperties().putAll(params);
      }
      if (section.getSectionName().equals("BOLTZMANN")
          && section.getSubSectionName().equals("NETWORK")) {
        final Map<String, String> params = section.parseParams();
        result.setWeights(NumberList.fromList(CSVFormat.EG_FORMAT,
            params.get(PersistConst.WEIGHTS)));
        result.setCurrentState(NumberList.fromList(CSVFormat.EG_FORMAT,
            params.get(PersistConst.OUTPUT)));
        result.setNeuronCount(EncogFileSection.parseInt(params,
View Full Code Here
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
    final NEATPopulation result = new NEATPopulation();
    final NEATInnovationList innovationList = new NEATInnovationList();
    innovationList.setPopulation(result);
    result.setInnovations(innovationList);
    final EncogReadHelper in = new EncogReadHelper(is);
    EncogFileSection section;

    while ((section = in.readNextSection()) != null) {
      if (section.getSectionName().equals("NEAT-POPULATION")
          && section.getSubSectionName().equals("INNOVATIONS")) {
        for (final String line : section.getLines()) {
          final List<String> cols = EncogFileSection
              .splitColumns(line);
          final NEATInnovation innovation = new NEATInnovation();
          final int innovationID = Integer.parseInt(cols.get(1));
          innovation.setInnovationID(innovationID);
          innovation.setNeuronID(Integer.parseInt(cols.get(2)));
          result.getInnovations().getInnovations()
              .put(cols.get(0), innovation);
          nextInnovationID = Math.max(nextInnovationID,
              innovationID + 1);
        }
      } else if (section.getSectionName().equals("NEAT-POPULATION")
          && section.getSubSectionName().equals("SPECIES")) {
        NEATGenome lastGenome = null;
        BasicSpecies lastSpecies = null;

        for (final String line : section.getLines()) {
          final List<String> cols = EncogFileSection
              .splitColumns(line);

          if (cols.get(0).equalsIgnoreCase("s")) {
            lastSpecies = new BasicSpecies();
            lastSpecies.setPopulation(result);
            lastSpecies.setAge(Integer.parseInt(cols.get(1)));
            lastSpecies.setBestScore(CSVFormat.EG_FORMAT.parse(cols
                .get(2)));
            lastSpecies.setGensNoImprovement(Integer.parseInt(cols
                .get(3)));
            result.getSpecies().add(lastSpecies);
          } else if (cols.get(0).equalsIgnoreCase("g")) {
            final boolean isLeader = lastGenome == null;
            lastGenome = new NEATGenome();
            lastGenome.setInputCount(result.getInputCount());
            lastGenome.setOutputCount(result.getOutputCount());
            lastGenome.setSpecies(lastSpecies);
            lastGenome.setAdjustedScore(CSVFormat.EG_FORMAT
                .parse(cols.get(1)));
            lastGenome.setScore(CSVFormat.EG_FORMAT.parse(cols
                .get(2)));
            lastGenome.setBirthGeneration(Integer.parseInt(cols
                .get(3)));
            lastSpecies.add(lastGenome);
            if (isLeader) {
              lastSpecies.setLeader(lastGenome);
            }
          } else if (cols.get(0).equalsIgnoreCase("n")) {
            final NEATNeuronGene neuronGene = new NEATNeuronGene();
            final int geneID = Integer.parseInt(cols.get(1));
            neuronGene.setId(geneID);

            final ActivationFunction af = EncogFileSection
                .parseActivationFunction(cols.get(2));
            neuronGene.setActivationFunction(af);

            neuronGene.setNeuronType(PersistNEATPopulation
                .stringToNeuronType(cols.get(3)));
            neuronGene
                .setInnovationId(Integer.parseInt(cols.get(4)));
            lastGenome.getNeuronsChromosome().add(neuronGene);
            nextGeneID = Math.max(geneID + 1, nextGeneID);
          } else if (cols.get(0).equalsIgnoreCase("l")) {
            final NEATLinkGene linkGene = new NEATLinkGene();
            linkGene.setId(Integer.parseInt(cols.get(1)));
            linkGene.setEnabled(Integer.parseInt(cols.get(2)) > 0);
            linkGene.setFromNeuronID(Integer.parseInt(cols.get(3)));
            linkGene.setToNeuronID(Integer.parseInt(cols.get(4)));
            linkGene.setWeight(CSVFormat.EG_FORMAT.parse(cols
                .get(5)));
            linkGene.setInnovationId(Integer.parseInt(cols.get(6)));
            lastGenome.getLinksChromosome().add(linkGene);
          }
        }

      } else if (section.getSectionName().equals("NEAT-POPULATION")
          && section.getSubSectionName().equals("CONFIG")) {
        final Map<String, String> params = section.parseParams();

        final String afStr = params
            .get(NEATPopulation.PROPERTY_NEAT_ACTIVATION);

        if (afStr.equalsIgnoreCase(PersistNEATPopulation.TYPE_CPPN)) {
View Full Code Here
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
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
  public Object read(final InputStream is) {
    final RBFNetwork result = new RBFNetwork();
    final FlatNetworkRBF flat = (FlatNetworkRBF) result.getFlat();

    final EncogReadHelper in = new EncogReadHelper(is);
    EncogFileSection section;

    while ((section = in.readNextSection()) != null) {
      if (section.getSectionName().equals("RBF-NETWORK")
          && section.getSubSectionName().equals("PARAMS")) {
        final Map<String, String> params = section.parseParams();
        result.getProperties().putAll(params);
      }
      if (section.getSectionName().equals("RBF-NETWORK")
          && section.getSubSectionName().equals("NETWORK")) {
        final Map<String, String> params = section.parseParams();

        flat.setBeginTraining(EncogFileSection.parseInt(params,
            BasicNetwork.TAG_BEGIN_TRAINING));
        flat.setConnectionLimit(EncogFileSection.parseDouble(params,
            BasicNetwork.TAG_CONNECTION_LIMIT));
        flat.setContextTargetOffset(EncogFileSection.parseIntArray(
            params, BasicNetwork.TAG_CONTEXT_TARGET_OFFSET));
        flat.setContextTargetSize(EncogFileSection.parseIntArray(
            params, BasicNetwork.TAG_CONTEXT_TARGET_SIZE));
        flat.setEndTraining(EncogFileSection.parseInt(params,
            BasicNetwork.TAG_END_TRAINING));
        flat.setHasContext(EncogFileSection.parseBoolean(params,
            BasicNetwork.TAG_HAS_CONTEXT));
        flat.setInputCount(EncogFileSection.parseInt(params,
            PersistConst.INPUT_COUNT));
        flat.setLayerCounts(EncogFileSection.parseIntArray(params,
            BasicNetwork.TAG_LAYER_COUNTS));
        flat.setLayerFeedCounts(EncogFileSection.parseIntArray(params,
            BasicNetwork.TAG_LAYER_FEED_COUNTS));
        flat.setLayerContextCount(EncogFileSection.parseIntArray(
            params, BasicNetwork.TAG_LAYER_CONTEXT_COUNT));
        flat.setLayerIndex(EncogFileSection.parseIntArray(params,
            BasicNetwork.TAG_LAYER_INDEX));
        flat.setLayerOutput(section.parseDoubleArray(params,
            PersistConst.OUTPUT));
        flat.setLayerSums(new double[flat.getLayerOutput().length]);
        flat.setOutputCount(EncogFileSection.parseInt(params,
            PersistConst.OUTPUT_COUNT));
        flat.setWeightIndex(EncogFileSection.parseIntArray(params,
            BasicNetwork.TAG_WEIGHT_INDEX));
        flat.setWeights(section.parseDoubleArray(params,
            PersistConst.WEIGHTS));
        flat.setBiasActivation(section.parseDoubleArray(
            params, BasicNetwork.TAG_BIAS_ACTIVATION));
      } else if (section.getSectionName().equals("RBF-NETWORK")
          && section.getSubSectionName().equals("ACTIVATION")) {
        int index = 0;

        flat.setActivationFunctions(new ActivationFunction[flat
            .getLayerCounts().length]);

        for (final String line : section.getLines()) {
          ActivationFunction af = null;
          final List<String> cols = EncogFileSection
              .splitColumns(line);
          final String name = "org.encog.engine.network.activation."
              + cols.get(0);
          try {
            final Class<?> clazz = Class.forName(name);
            af = (ActivationFunction) clazz.newInstance();
          } catch (final ClassNotFoundException e) {
            throw new PersistError(e);
          } catch (final InstantiationException e) {
            throw new PersistError(e);
          } catch (final IllegalAccessException e) {
            throw new PersistError(e);
          }

          for (int i = 0; i < af.getParamNames().length; i++) {
            af.setParam(i,
                CSVFormat.EG_FORMAT.parse(cols.get(i + 1)));
          }

          flat.getActivationFunctions()[index++] = af;
        }

      } else if (section.getSectionName().equals("RBF-NETWORK")
          && section.getSubSectionName().equals("RBF")) {
        int index = 0;

        final int hiddenCount = flat.getLayerCounts()[1];
        final int inputCount = flat.getLayerCounts()[2];

        flat.setRBF(new RadialBasisFunction[hiddenCount]);

        for (final String line : section.getLines()) {
          RadialBasisFunction rbf = null;
          final List<String> cols = EncogFileSection
              .splitColumns(line);
          final String name = "org.encog.mathutil.rbf." + cols.get(0);
          try {
View Full Code Here
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
   */
  @Override
  public Object read(final InputStream is) {
    final TrainingContinuation result = new TrainingContinuation();
    final EncogReadHelper in = new EncogReadHelper(is);
    EncogFileSection section;

    while ((section = in.readNextSection()) != null) {
      if (section.getSectionName().equals("CONT")
          && section.getSubSectionName().equals("PARAMS")) {
        final Map<String, String> params = section.parseParams();
        for (final String key : params.keySet()) {
          if (key.equalsIgnoreCase("type")) {
            result.setTrainingType(params.get(key));
          } else {
            final double[] list = section
                .parseDoubleArray(params, key);
            result.put(key, list);
          }
        }
      }
View Full Code Here
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
    Matrix transitionProbability = null;
    Map<String,String> properties = null;
    List<StateDistribution> distributions = new ArrayList<StateDistribution>();
   
    final EncogReadHelper in = new EncogReadHelper(is);
    EncogFileSection section;

    while ((section = in.readNextSection()) != null) {
      if (section.getSectionName().equals("HMM")
          && section.getSubSectionName().equals("PARAMS")) {
        properties = section.parseParams();
       
      }
      if (section.getSectionName().equals("HMM")
          && section.getSubSectionName().equals("CONFIG")) {
        final Map<String, String> params = section.parseParams();

        states = EncogFileSection.parseInt(params, HiddenMarkovModel.TAG_STATES);
       
        if( params.containsKey(HiddenMarkovModel.TAG_ITEMS) ) {
          items = EncogFileSection.parseIntArray(params, HiddenMarkovModel.TAG_ITEMS);
        }
        pi = section.parseDoubleArray(params,  HiddenMarkovModel.TAG_PI);
        transitionProbability = section.parseMatrix(params, HiddenMarkovModel.TAG_TRANSITION);
      } else if (section.getSectionName().equals("HMM")
          && section.getSubSectionName().startsWith("DISTRIBUTION-")) {
        final Map<String, String> params = section.parseParams();
        String t = params.get(HiddenMarkovModel.TAG_DIST_TYPE);
        if( "ContinousDistribution".equals(t) ) {
          double[] mean = section.parseDoubleArray(params, HiddenMarkovModel.TAG_MEAN);
          Matrix cova = section.parseMatrix(params, HiddenMarkovModel.TAG_COVARIANCE);
          ContinousDistribution dist = new ContinousDistribution(mean,cova.getData());
          distributions.add(dist);
        } else if( "DiscreteDistribution".equals(t) ) {
          Matrix prob = section.parseMatrix(params, HiddenMarkovModel.TAG_PROBABILITIES);
          DiscreteDistribution dist = new DiscreteDistribution(prob.getData());
          distributions.add(dist);
        }
      }
    }
View Full Code Here
TOP

Related Classes of org.encog.persist.EncogFileSection

  • org.encog.app.analyst.AnalystError
  • org.encog.app.analyst.script.ScriptLoad
  • org.encog.ca.universe.basic.PersistBasicUniverse
  • org.encog.engine.network.activation.ActivationFunction
  • org.encog.mathutil.matrices.Matrix
  • org.encog.ml.bayesian.PersistBayes
  • org.encog.ml.hmm.PersistHMM
  • org.encog.ml.prg.PersistPrgPopulation
  • org.encog.ml.svm.PersistSVM
  • org.encog.neural.art.PersistART1
    • 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.