Package com.google.gxp.compiler.cli

Examples of com.google.gxp.compiler.cli.GxpcFlags$CommandLine

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
166
167
168
169
      encodingOpt).withOption(analyzerOpt).withOption(defaultCatOpt).withOption(gramSizeOpt).withOption(
      typeOpt).withOption(dataSourceOpt).create();
   
    Parser parser = new Parser();
    parser.setGroup(options);
    CommandLine cmdLine = parser.parse(args);
   
    int gramSize = 1;
    if (cmdLine.hasOption(gramSizeOpt)) {
      gramSize = Integer.parseInt((String) cmdLine.getValue(gramSizeOpt));
     
    }
   
    BayesParameters params = new BayesParameters(gramSize);
   
    String modelBasePath = (String) cmdLine.getValue(pathOpt);
   
    log.info("Loading model from: {}", params.print());
   
    Algorithm algorithm;
    Datastore datastore;
   
    String classifierType = (String) cmdLine.getValue(typeOpt);
   
    String dataSource = (String) cmdLine.getValue(dataSourceOpt);
    if (dataSource.equals("hdfs")) {
      if (classifierType.equalsIgnoreCase("bayes")) {
        log.info("Using Bayes Classifier");
        algorithm = new BayesAlgorithm();
        datastore = new InMemoryBayesDatastore(params);
      } else if (classifierType.equalsIgnoreCase("cbayes")) {
        log.info("Using Complementary Bayes Classifier");
        algorithm = new CBayesAlgorithm();
        datastore = new InMemoryBayesDatastore(params);
      } else {
        throw new IllegalArgumentException("Unrecognized classifier type: " + classifierType);
      }
     
    } else if (dataSource.equals("hbase")) {
      if (classifierType.equalsIgnoreCase("bayes")) {
        log.info("Using Bayes Classifier");
        algorithm = new BayesAlgorithm();
        datastore = new HBaseBayesDatastore(modelBasePath, params);
      } else if (classifierType.equalsIgnoreCase("cbayes")) {
        log.info("Using Complementary Bayes Classifier");
        algorithm = new CBayesAlgorithm();
        datastore = new HBaseBayesDatastore(modelBasePath, params);
      } else {
        throw new IllegalArgumentException("Unrecognized classifier type: " + classifierType);
      }
     
    } else {
      throw new IllegalArgumentException("Unrecognized dataSource type: " + dataSource);
    }
    ClassifierContext classifier = new ClassifierContext(algorithm, datastore);
    classifier.initialize();
    String defaultCat = "unknown";
    if (cmdLine.hasOption(defaultCatOpt)) {
      defaultCat = (String) cmdLine.getValue(defaultCatOpt);
    }
    File docPath = new File((String) cmdLine.getValue(classifyOpt));
    String encoding = "UTF-8";
    if (cmdLine.hasOption(encodingOpt)) {
      encoding = (String) cmdLine.getValue(encodingOpt);
    }
    Analyzer analyzer = null;
    if (cmdLine.hasOption(analyzerOpt)) {
      String className = (String) cmdLine.getValue(analyzerOpt);
      analyzer = Class.forName(className).asSubclass(Analyzer.class).newInstance();
    }
    if (analyzer == null) {
      analyzer = new StandardAnalyzer(Version.LUCENE_CURRENT);
    }
View Full Code Here
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
                                              .withOption(minEigenValOpt);
    Group group = gBuilder.create();

    Map<String,String> argMap = new HashMap<String,String>();

    CommandLine cmdLine;
    try {
      Parser parser = new Parser();
      parser.setGroup(group);
      cmdLine = parser.parse(args);
    } catch (OptionException e) {
      log.error(e.getMessage());
      CommandLineUtil.printHelp(group);
      return null;
    }
    if (cmdLine.hasOption(helpOpt)) {
      CommandLineUtil.printHelp(group);
      return argMap;
    }
    maybePut(argMap, cmdLine, eigenInputOpt, corpusInputOpt, helpOpt, outOpt, inMemOpt, errorOpt, minEigenValOpt);
    return argMap;
View Full Code Here
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
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
217
218
219
220
221
222
        .withOption(numReduceTasksOpt).withOption(maxNGramSizeOpt).withOption(overwriteOutput).withOption(
          helpOpt).withOption(sequentialAccessVectorOpt).create();
    try {
      Parser parser = new Parser();
      parser.setGroup(group);
      CommandLine cmdLine = parser.parse(args);
     
      if (cmdLine.hasOption(helpOpt)) {
        CommandLineUtil.printHelp(group);
        return;
      }
     
      String inputDir = (String) cmdLine.getValue(inputDirOpt);
      String outputDir = (String) cmdLine.getValue(outputDirOpt);
     
      int chunkSize = 100;
      if (cmdLine.hasOption(chunkSizeOpt)) {
        chunkSize = Integer.parseInt((String) cmdLine.getValue(chunkSizeOpt));
      }
      int minSupport = 2;
      if (cmdLine.hasOption(minSupportOpt)) {
        String minSupportString = (String) cmdLine.getValue(minSupportOpt);
        minSupport = Integer.parseInt(minSupportString);
      }
     
      int maxNGramSize = 1;
     
      if (cmdLine.hasOption(maxNGramSizeOpt)) {
        try {
          maxNGramSize = Integer.parseInt(cmdLine.getValue(maxNGramSizeOpt).toString());
        } catch (NumberFormatException ex) {
          log.warn("Could not parse ngram size option");
        }
      }
      log.info("Maximum n-gram size is: {}", maxNGramSize);
     
      if (cmdLine.hasOption(overwriteOutput)) {
        HadoopUtil.overwriteOutput(outputDir);
      }
     
      float minLLRValue = LLRReducer.DEFAULT_MIN_LLR;
      if (cmdLine.hasOption(minLLROpt)) {
        minLLRValue = Float.parseFloat(cmdLine.getValue(minLLROpt).toString());
      }
      log.info("Minimum LLR value: {}", minLLRValue);
     
      int reduceTasks = 1;
      if (cmdLine.hasOption(numReduceTasksOpt)) {
        reduceTasks = Integer.parseInt(cmdLine.getValue(numReduceTasksOpt).toString());
      }
      log.info("Pass1 reduce tasks: {}", reduceTasks);
     
      Class<? extends Analyzer> analyzerClass = StandardAnalyzer.class;
      if (cmdLine.hasOption(analyzerNameOpt)) {
        String className = cmdLine.getValue(analyzerNameOpt).toString();
        analyzerClass = (Class<? extends Analyzer>) Class.forName(className);
        // try instantiating it, b/c there isn't any point in setting it if
        // you can't instantiate it
        analyzerClass.newInstance();
      }
     
      boolean processIdf;
     
      if (cmdLine.hasOption(weightOpt)) {
        String wString = cmdLine.getValue(weightOpt).toString();
        if (wString.equalsIgnoreCase("tf")) {
          processIdf = false;
        } else if (wString.equalsIgnoreCase("tfidf")) {
          processIdf = true;
        } else {
          throw new OptionException(weightOpt);
        }
      } else {
        processIdf = true;
      }
     
      int minDf = 1;
      if (cmdLine.hasOption(minDFOpt)) {
        minDf = Integer.parseInt(cmdLine.getValue(minDFOpt).toString());
      }
      int maxDFPercent = 99;
      if (cmdLine.hasOption(maxDFPercentOpt)) {
        maxDFPercent = Integer.parseInt(cmdLine.getValue(maxDFPercentOpt).toString());
      }
     
      float norm = PartialVectorMerger.NO_NORMALIZING;
      if (cmdLine.hasOption(powerOpt)) {
        String power = cmdLine.getValue(powerOpt).toString();
        if (power.equals("INF")) {
          norm = Float.POSITIVE_INFINITY;
        } else {
          norm = Float.parseFloat(power);
        }
      }
      HadoopUtil.overwriteOutput(outputDir);
      String tokenizedPath = outputDir + DocumentProcessor.TOKENIZED_DOCUMENT_OUTPUT_FOLDER;
      DocumentProcessor.tokenizeDocuments(inputDir, analyzerClass, tokenizedPath);
     
      boolean sequentialAccessOutput = false;
      if (cmdLine.hasOption(sequentialAccessVectorOpt)) {
        sequentialAccessOutput = true;
      }
     
      DictionaryVectorizer.createTermFrequencyVectors(tokenizedPath, outputDir, minSupport, maxNGramSize,
        minLLRValue, reduceTasks, chunkSize, sequentialAccessOutput);
View Full Code Here
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
      gBuilder = gBuilder.withOption(opt);
    }
   
    Group group = gBuilder.create();
   
    CommandLine cmdLine;
    try {
      Parser parser = new Parser();
      parser.setGroup(group);
      cmdLine = parser.parse(args);
    } catch (OptionException e) {
      log.error(e.getMessage());
      CommandLineUtil.printHelp(group);
      return null;
    }
   
    if (cmdLine.hasOption(helpOpt)) {
      CommandLineUtil.printHelp(group);
      return null;
    }
   
    Map<String,String> result = new HashMap<String,String>();
View Full Code Here
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
        .create();
    try {
      Parser parser = new Parser();
     
      parser.setGroup(group);
      CommandLine cmdLine = parser.parse(args);
      if (cmdLine.hasOption(helpOpt)) {
        CommandLineUtil.printHelp(group);
        return;
      }
     
      String classifierType = (String) cmdLine.getValue(typeOpt);
      String dataSourceType = (String) cmdLine.getValue(dataSourceOpt);
     
      BayesParameters params = new BayesParameters(Integer.parseInt((String) cmdLine.getValue(gramSizeOpt)));
     
      String alphaI = "1.0";
      if (cmdLine.hasOption(alphaOpt)) {
        alphaI = (String) cmdLine.getValue(alphaOpt);
      }
     
      params.set("alpha_i", alphaI);
     
      if (dataSourceType.equals("hbase")) {
        params.set("dataSource", "hbase");
      } else {
        params.set("dataSource", "hdfs");
      }
     
      if (classifierType.equalsIgnoreCase("bayes")) {
        log.info("Training Bayes Classifier");
        trainNaiveBayes((String) cmdLine.getValue(inputDirOpt), (String) cmdLine
            .getValue(outputOpt), params);
       
      } else if (classifierType.equalsIgnoreCase("cbayes")) {
        log.info("Training Complementary Bayes Classifier");
        // setup the HDFS and copy the files there, then run the trainer
        trainCNaiveBayes((String) cmdLine.getValue(inputDirOpt), (String) cmdLine
            .getValue(outputOpt), params);
      }
    } catch (OptionException e) {
      log.error("Error while parsing options", e);
      CommandLineUtil.printHelp(group);
View Full Code Here
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
166
167
168
        .withOption(helpOpt).withOption(methodOpt).withOption(verboseOutputOpt).withOption(alphaOpt).create();
   
    try {
      Parser parser = new Parser();
      parser.setGroup(group);
      CommandLine cmdLine = parser.parse(args);
     
      if (cmdLine.hasOption(helpOpt)) {
        CommandLineUtil.printHelp(group);
        return;
      }
     
      int gramSize = 1;
      if (cmdLine.hasOption(gramSizeOpt)) {
        gramSize = Integer.parseInt((String) cmdLine.getValue(gramSizeOpt));
       
      }
      BayesParameters params = new BayesParameters(gramSize);
     
      String modelBasePath = (String) cmdLine.getValue(pathOpt);
     
      String classifierType = (String) cmdLine.getValue(typeOpt);
      String dataSource = (String) cmdLine.getValue(dataSourceOpt);
     
      String defaultCat = "unknown";
      if (cmdLine.hasOption(defaultCatOpt)) {
        defaultCat = (String) cmdLine.getValue(defaultCatOpt);
      }
     
      String encoding = "UTF-8";
      if (cmdLine.hasOption(encodingOpt)) {
        encoding = (String) cmdLine.getValue(encodingOpt);
      }
     
      String alphaI = "1.0";
      if (cmdLine.hasOption(alphaOpt)) {
        alphaI = (String) cmdLine.getValue(alphaOpt);
      }
     
      boolean verbose = cmdLine.hasOption(verboseOutputOpt);
     
      String testDirPath = (String) cmdLine.getValue(dirOpt);
     
      String classificationMethod = "sequential";
      if (cmdLine.hasOption(methodOpt)) {
        classificationMethod = (String) cmdLine.getValue(methodOpt);
      }
     
      params.set("verbose", Boolean.toString(verbose));
      params.set("basePath", modelBasePath);
      params.set("classifierType", classifierType);
View Full Code Here
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
        .create();
   
    try {
      Parser parser = new Parser();
      parser.setGroup(group);
      CommandLine cmdLine = parser.parse(args);
     
      if (cmdLine.hasOption(helpOpt)) {
        CommandLineUtil.printHelp(group);
        return;
      }
     
      String input = cmdLine.getValue(inputOpt).toString();
      String output = cmdLine.getValue(outputOpt).toString();
      String measureClass = SquaredEuclideanDistanceMeasure.class.getName();
      if (cmdLine.hasOption(measureClassOpt)) {
        measureClass = cmdLine.getValue(measureClassOpt).toString();
      }
     
      // Class<? extends Vector> vectorClass = cmdLine.hasOption(vectorClassOpt) == false ?
      // RandomAccessSparseVector.class
      // : (Class<? extends Vector>) Class.forName(cmdLine.getValue(vectorClassOpt).toString());
      double t1 = Double.parseDouble(cmdLine.getValue(t1Opt).toString());
      double t2 = Double.parseDouble(cmdLine.getValue(t2Opt).toString());
     
      runJob(input, output, measureClass, t1, t2);
    } catch (OptionException e) {
      log.error("Exception", e);
      CommandLineUtil.printHelp(group);
View Full Code Here
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
          mOpt).withOption(topicsOpt).withOption(helpOpt).withOption(numRedOpt).create();
   
    try {
      Parser parser = new Parser();
      parser.setGroup(group);
      CommandLine cmdLine = parser.parse(args);
      if (cmdLine.hasOption(helpOpt)) {
        CommandLineUtil.printHelp(group);
        return;
      }
     
      String input = cmdLine.getValue(inputOpt).toString();
      String output = cmdLine.getValue(outputOpt).toString();
      String modelFactory = "org.apache.mahout.clustering.dirichlet.models.NormalModelDistribution";
      if (cmdLine.hasOption(modelOpt)) modelFactory = cmdLine.getValue(modelOpt).toString();
      String modelPrototype = "org.apache.mahout.math.RandomAccessSparseVector";
      if (cmdLine.hasOption(prototypeOpt)) modelPrototype = cmdLine.getValue(prototypeOpt).toString();
      int prototypeSize = Integer.parseInt(cmdLine.getValue(sizeOpt).toString());
      int numReducers = Integer.parseInt(cmdLine.getValue(numRedOpt).toString());
      int numModels = Integer.parseInt(cmdLine.getValue(topicsOpt).toString());
      int maxIterations = Integer.parseInt(cmdLine.getValue(maxIterOpt).toString());
      double alpha_0 = Double.parseDouble(cmdLine.getValue(mOpt).toString());
      runJob(input, output, modelFactory, modelPrototype, prototypeSize, numModels, maxIterations, alpha_0,
        numReducers);
    } catch (OptionException e) {
      log.error("Exception parsing command line: ", e);
      CommandLineUtil.printHelp(group);
View Full Code Here
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
        .withOption(helpOpt).create();
   
    try {
      Parser parser = new Parser();
      parser.setGroup(group);
      CommandLine cmdLine = parser.parse(args);
      if (cmdLine.hasOption(helpOpt)) {
        CommandLineUtil.printHelp(group);
        return;
      }
     
      String measureClass = SquaredEuclideanDistanceMeasure.class.getName();
      if (cmdLine.hasOption(measureClassOpt)) {
        measureClass = cmdLine.getValue(measureClassOpt).toString();
      }
      String output = cmdLine.getValue(outputOpt).toString();
      String canopies = cmdLine.getValue(canopiesOpt).toString();
      String points = cmdLine.getValue(pointsOpt).toString();
      // Class<? extends Vector> vectorClass = cmdLine.hasOption(vectorClassOpt) == false ?
      // RandomAccessSparseVector.class
      // : (Class<? extends Vector>) Class.forName(cmdLine.getValue(vectorClassOpt).toString());
      double t1 = Double.parseDouble(cmdLine.getValue(t1Opt).toString());
      double t2 = Double.parseDouble(cmdLine.getValue(t2Opt).toString());
     
      runJob(points, canopies, output, measureClass, t1, t2);
     
    } catch (OptionException e) {
      log.error("Exception", e);
View Full Code Here
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
        .create();
   
    try {
      Parser parser = new Parser();
      parser.setGroup(group);
      CommandLine cmdLine = parser.parse(args);
     
      if (cmdLine.hasOption(helpOpt)) {
        CommandLineUtil.printHelp(group);
        return;
      }
     
      String input = cmdLine.getValue(inputOpt).toString();
      String output = cmdLine.getValue(outputOpt).toString();
      String measureClass = SquaredEuclideanDistanceMeasure.class.getName();
      if (cmdLine.hasOption(measureClassOpt)) {
        measureClass = cmdLine.getValue(measureClassOpt).toString();
      }
     
      // Class<? extends Vector> vectorClass = cmdLine.hasOption(vectorClassOpt) == false ?
      // RandomAccessSparseVector.class
      // : (Class<? extends Vector>) Class.forName(cmdLine.getValue(vectorClassOpt).toString());
      double t1 = Double.parseDouble(cmdLine.getValue(t1Opt).toString());
      double t2 = Double.parseDouble(cmdLine.getValue(t2Opt).toString());
     
      runJob(input, output, measureClass, t1, t2);
     
    } catch (OptionException e) {
      log.error("Exception", e);
View Full Code Here
TOP

Related Classes of com.google.gxp.compiler.cli.GxpcFlags$CommandLine

  • com.digitalpebble.behemoth.mahout.SparseVectorsFromBehemoth
  • com.digitalpebble.behemoth.tika.TikaDriver
  • org.apache.commons.cli2.commandline.DefaultingCommandLine
  • org.apache.commons.cli2.commandline.Parser
  • org.apache.hadoop.mapred.pipes.Submitter
  • org.apache.hadoop.streaming.StreamJob
  • org.apache.jackrabbit.vault.util.console.AbstractApplication
  • org.apache.jackrabbit.vault.util.console.ExecutionContext
  • org.apache.jackrabbit.vault.util.console.Test
  • org.apache.mahout.benchmark.VectorBenchmarks
    • 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.