Package no.priv.garshol.duke.utils

Examples of no.priv.garshol.duke.utils.CommandLineParser$Option

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
  public static void main(String[] args) throws Exception {
    DefaultOptionBuilder obuilder = new DefaultOptionBuilder();
    ArgumentBuilder abuilder = new ArgumentBuilder();
    GroupBuilder gbuilder = new GroupBuilder();

    Option inputOpt = DefaultOptionCreator.inputOption().create();

    Option outputDirOpt = DefaultOptionCreator.outputOption().create();

    Option chunkSizeOpt = obuilder.withLongName("chunkSize").withArgument(
            abuilder.withName("chunkSize").withMinimum(1).withMaximum(1).create()).withDescription(
            "The chunkSize in MegaBytes. Defaults to 64").withShortName("chunk").create();

    Option keyPrefixOpt = obuilder.withLongName("keyPrefix").withArgument(
            abuilder.withName("keyPrefix").withMinimum(1).withMaximum(1).create()).withDescription(
            "The prefix to be prepended to the key").withShortName("prefix").create();
    Option charsetOpt = obuilder.withLongName("charset").withRequired(true).withArgument(
            abuilder.withName("charset").withMinimum(1).withMaximum(1).create()).withDescription(
            "The name of the character encoding of the input files").withShortName("c").create();
    Option subjectOpt = obuilder.withLongName("subject").withRequired(false).
            withDescription("Include the Mail subject as part of the text.  Default is false").withShortName("s").create();
    Option toOpt = obuilder.withLongName("to").withRequired(false).
            withDescription("Include the to field in the text.  Default is false").withShortName("to").create();
    Option fromOpt = obuilder.withLongName("from").withRequired(false).
            withDescription("Include the from field in the text.  Default is false").withShortName("from").create();
    Option refsOpt = obuilder.withLongName("references").withRequired(false).
            withDescription("Include the references field in the text.  Default is false").withShortName("refs").create();
    Option bodyOpt = obuilder.withLongName("body").withRequired(false).
            withDescription("Include the body in the output.  Default is false").withShortName("b").create();
    Option quotedOpt = obuilder.withLongName("stripQuoted").withRequired(false).
            withDescription("Strip (remove) quoted email text in the body.  Default is false").withShortName("q").create();
    Option quotedRegexOpt = obuilder.withLongName("quotedRegex").withRequired(false).withArgument(abuilder.withName("regex").withMinimum(1).withMaximum(1).create())
            .withDescription("Specify the regex that identifies quoted text.  Default is to look for > or | at the beginning of the line.").withShortName("q").create();
    Option separatorOpt = obuilder.withLongName("separator").withRequired(false).withArgument(
            abuilder.withName("separator").withMinimum(1).withMaximum(1).create()).
            withDescription("The separator to use between metadata items (to, from, etc.).  Default is \\n").withShortName("sep").create();

    Option bodySeparatorOpt = obuilder.withLongName("bodySeparator").withRequired(false).withArgument(
            abuilder.withName("bodySeparator").withMinimum(1).withMaximum(1).create()).
            withDescription("The separator to use between lines in the body.  Default is \\n.  Useful to change if you wish to have the message be on one line").withShortName("bodySep").create();
    Option helpOpt = DefaultOptionCreator.helpOption();

    Group group = gbuilder.withName("Options").withOption(keyPrefixOpt).withOption(chunkSizeOpt).withOption(
            charsetOpt).withOption(outputDirOpt).withOption(helpOpt).withOption(inputOpt).withOption(subjectOpt).withOption(toOpt)
            .withOption(fromOpt).withOption(bodyOpt).withOption(quotedOpt).withOption(refsOpt).withOption(bodySeparatorOpt)
            .withOption(quotedRegexOpt)
View Full Code Here
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
  public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
    DefaultOptionBuilder obuilder = new DefaultOptionBuilder();
    ArgumentBuilder abuilder = new ArgumentBuilder();
    GroupBuilder gbuilder = new GroupBuilder();
   
    Option inputOpt = DefaultOptionCreator.inputOption().withRequired(false).create();
    Option outputOpt = DefaultOptionCreator.outputOption().withRequired(false).create();
    Option vectorOpt = obuilder.withLongName("vector").withRequired(false).withArgument(
      abuilder.withName("v").withMinimum(1).withMaximum(1).create()).withDescription(
      "The vector implementation to use.").withShortName("v").create();
   
    Option helpOpt = DefaultOptionCreator.helpOption();
   
    Group group = gbuilder.withName("Options").withOption(inputOpt).withOption(outputOpt).withOption(
      vectorOpt).withOption(helpOpt).create();

    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
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
  public int run(String[] args) throws Exception {
    DefaultOptionBuilder obuilder = new DefaultOptionBuilder();
    ArgumentBuilder abuilder = new ArgumentBuilder();
    GroupBuilder gbuilder = new GroupBuilder();
   
    Option inputDirOpt = DefaultOptionCreator.inputOption().create();
   
    Option outputDirOpt = DefaultOptionCreator.outputOption().create();
   
    Option minSupportOpt = obuilder.withLongName("minSupport").withArgument(
      abuilder.withName("minSupport").withMinimum(1).withMaximum(1).create()).withDescription(
      "(Optional) Minimum Support. Default Value: 2").withShortName("s").create();
   
    Option analyzerNameOpt = obuilder.withLongName("analyzerName").withArgument(
      abuilder.withName("analyzerName").withMinimum(1).withMaximum(1).create()).withDescription(
      "The class name of the analyzer").withShortName("a").create();
   
    Option chunkSizeOpt = obuilder.withLongName("chunkSize").withArgument(
      abuilder.withName("chunkSize").withMinimum(1).withMaximum(1).create()).withDescription(
      "The chunkSize in MegaBytes. 100-10000 MB").withShortName("chunk").create();
   
    Option weightOpt = obuilder.withLongName("weight").withRequired(false).withArgument(
      abuilder.withName("weight").withMinimum(1).withMaximum(1).create()).withDescription(
      "The kind of weight to use. Currently TF or TFIDF").withShortName("wt").create();
   
    Option minDFOpt = obuilder.withLongName("minDF").withRequired(false).withArgument(
      abuilder.withName("minDF").withMinimum(1).withMaximum(1).create()).withDescription(
      "The minimum document frequency.  Default is 1").withShortName("md").create();

    Option maxDFPercentOpt = obuilder.withLongName("maxDFPercent").withRequired(false).withArgument(
      abuilder.withName("maxDFPercent").withMinimum(1).withMaximum(1).create()).withDescription(
      "The max percentage of docs for the DF.  Can be used to remove really high frequency terms."
          + " Expressed as an integer between 0 and 100. Default is 99.  If maxDFSigma is also set, it will override this value.").withShortName("x").create();

    Option maxDFSigmaOpt = obuilder.withLongName("maxDFSigma").withRequired(false).withArgument(
      abuilder.withName("maxDFSigma").withMinimum(1).withMaximum(1).create()).withDescription(
      "What portion of the tf (tf-idf) vectors to be used, expressed in times the standard deviation (sigma) of the document frequencies of these vectors." +
              "  Can be used to remove really high frequency terms."
          + " Expressed as a double value. Good value to be specified is 3.0. In case the value is less then 0 no vectors " +
              "will be filtered out. Default is -1.0.  Overrides maxDFPercent").withShortName("xs").create();
   
    Option minLLROpt = obuilder.withLongName("minLLR").withRequired(false).withArgument(
      abuilder.withName("minLLR").withMinimum(1).withMaximum(1).create()).withDescription(
      "(Optional)The minimum Log Likelihood Ratio(Float)  Default is " + LLRReducer.DEFAULT_MIN_LLR)
        .withShortName("ml").create();
   
    Option numReduceTasksOpt = obuilder.withLongName("numReducers").withArgument(
      abuilder.withName("numReducers").withMinimum(1).withMaximum(1).create()).withDescription(
      "(Optional) Number of reduce tasks. Default Value: 1").withShortName("nr").create();
   
    Option powerOpt = obuilder.withLongName("norm").withRequired(false).withArgument(
      abuilder.withName("norm").withMinimum(1).withMaximum(1).create()).withDescription(
      "The norm to use, expressed as either a float or \"INF\" if you want to use the Infinite norm.  "
          + "Must be greater or equal to 0.  The default is not to normalize").withShortName("n").create();
   
    Option logNormalizeOpt = obuilder.withLongName("logNormalize").withRequired(false)
    .withDescription(
      "(Optional) Whether output vectors should be logNormalize. If set true else false")
    .withShortName("lnorm").create();
   
    Option maxNGramSizeOpt = obuilder.withLongName("maxNGramSize").withRequired(false).withArgument(
      abuilder.withName("ngramSize").withMinimum(1).withMaximum(1).create())
        .withDescription(
          "(Optional) The maximum size of ngrams to create"
              + " (2 = bigrams, 3 = trigrams, etc) Default Value:1").withShortName("ng").create();
   
    Option sequentialAccessVectorOpt = obuilder.withLongName("sequentialAccessVector").withRequired(false)
        .withDescription(
          "(Optional) Whether output vectors should be SequentialAccessVectors. If set true else false")
        .withShortName("seq").create();
   
    Option namedVectorOpt = obuilder.withLongName("namedVector").withRequired(false)
    .withDescription(
      "(Optional) Whether output vectors should be NamedVectors. If set true else false")
    .withShortName("nv").create();
   
    Option overwriteOutput = obuilder.withLongName("overwrite").withRequired(false).withDescription(
      "If set, overwrite the output directory").withShortName("ow").create();
    Option helpOpt = obuilder.withLongName("help").withDescription("Print out help").withShortName("h")
        .create();
   
    Group group = gbuilder.withName("Options").withOption(minSupportOpt).withOption(analyzerNameOpt)
        .withOption(chunkSizeOpt).withOption(outputDirOpt).withOption(inputDirOpt).withOption(minDFOpt)
        .withOption(maxDFSigmaOpt).withOption(maxDFPercentOpt).withOption(weightOpt).withOption(powerOpt).withOption(minLLROpt)
View Full Code Here
285
286
287
288
289
290
291
292
293
294
295
   *
   *
   */
  public Map<String, String> parseArguments(String[] args) throws IOException {

    Option helpOpt = addOption(DefaultOptionCreator.helpOption());
    addOption("tempDir", null, "Intermediate output directory", "temp");
    addOption("startPhase", null, "First phase to run", "0");
    addOption("endPhase", null, "Last phase to run", String.valueOf(Integer.MAX_VALUE));

    GroupBuilder gBuilder = new GroupBuilder().withName("Job-Specific Options:");
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
   
    DefaultOptionBuilder obuilder = new DefaultOptionBuilder();
    ArgumentBuilder abuilder = new ArgumentBuilder();
    GroupBuilder gbuilder = new GroupBuilder();
   
    Option dataOpt = obuilder.withLongName("data").withShortName("d").withRequired(true)
        .withArgument(abuilder.withName("path").withMinimum(1).withMaximum(1).create())
        .withDescription("Data path").create();
   
    Option datasetOpt = obuilder.withLongName("dataset").withShortName("ds").withRequired(true)
        .withArgument(abuilder.withName("dataset").withMinimum(1).withMaximum(1).create())
        .withDescription("Dataset path").create();
   
    Option selectionOpt = obuilder.withLongName("selection").withShortName("sl").withRequired(false)
        .withArgument(abuilder.withName("m").withMinimum(1).withMaximum(1).create())
        .withDescription("Optional, Number of variables to select randomly at each tree-node.\n" +
        "For classification problem, the default is square root of the number of explanatory variables.\n" +
        "For regression problem, the default is 1/3 of the number of explanatory variables.").create();

    Option noCompleteOpt = obuilder.withLongName("no-complete").withShortName("nc").withRequired(false)
        .withDescription("Optional, The tree is not complemented").create();

    Option minSplitOpt = obuilder.withLongName("minsplit").withShortName("ms").withRequired(false)
        .withArgument(abuilder.withName("minsplit").withMinimum(1).withMaximum(1).create())
        .withDescription("Optional, The tree-node is not divided, if the branching data size is " +
        "smaller than this value.\nThe default is 2.").create();

    Option minPropOpt = obuilder.withLongName("minprop").withShortName("mp").withRequired(false)
        .withArgument(abuilder.withName("minprop").withMinimum(1).withMaximum(1).create())
        .withDescription("Optional, The tree-node is not divided, if the proportion of the " +
        "variance of branching data is smaller than this value.\n" +
        "In the case of a regression problem, this value is used. " +
        "The default is 1/1000(0.001).").create();

    Option seedOpt = obuilder.withLongName("seed").withShortName("sd").withRequired(false)
        .withArgument(abuilder.withName("seed").withMinimum(1).withMaximum(1).create())
        .withDescription("Optional, seed value used to initialise the Random number generator").create();
   
    Option partialOpt = obuilder.withLongName("partial").withShortName("p").withRequired(false)
        .withDescription("Optional, use the Partial Data implementation").create();
   
    Option nbtreesOpt = obuilder.withLongName("nbtrees").withShortName("t").withRequired(true)
        .withArgument(abuilder.withName("nbtrees").withMinimum(1).withMaximum(1).create())
        .withDescription("Number of trees to grow").create();
   
    Option outputOpt = obuilder.withLongName("output").withShortName("o").withRequired(true)
        .withArgument(abuilder.withName("path").withMinimum(1).withMaximum(1).create())
        .withDescription("Output path, will contain the Decision Forest").create();

    Option helpOpt = obuilder.withLongName("help").withShortName("h")
        .withDescription("Print out help").create();
   
    Group group = gbuilder.withName("Options").withOption(dataOpt).withOption(datasetOpt)
        .withOption(selectionOpt).withOption(noCompleteOpt).withOption(minSplitOpt)
        .withOption(minPropOpt).withOption(seedOpt).withOption(partialOpt).withOption(nbtreesOpt)
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
  public static void main(String[] args) throws Exception {
    DefaultOptionBuilder obuilder = new DefaultOptionBuilder();
    ArgumentBuilder abuilder = new ArgumentBuilder();
    GroupBuilder gbuilder = new GroupBuilder();

    Option seqOpt = obuilder.withLongName("seqFile").withRequired(false).withArgument(
            abuilder.withName("seqFile").withMinimum(1).withMaximum(1).create()).withDescription(
            "The Sequence File containing the Vectors").withShortName("s").create();
    Option vectorAsKeyOpt = obuilder.withLongName("useKey").withRequired(false).withDescription(
            "If the Key is a vector, then dump that instead").withShortName("u").create();
    Option printKeyOpt = obuilder.withLongName("printKey").withRequired(false).withDescription(
            "Print out the key as well, delimited by a tab (or the value if useKey is true)").withShortName("p")
            .create();
    Option outputOpt = obuilder.withLongName("output").withRequired(false).withArgument(
        abuilder.withName("output").withMinimum(1).withMaximum(1).create()).withDescription(
            "The output file.  If not specified, dumps to the console").withShortName("o").create();
    Option dictOpt = obuilder.withLongName("dictionary").withRequired(false).withArgument(
        abuilder.withName("dictionary").withMinimum(1).withMaximum(1).create()).withDescription(
            "The dictionary file. ").withShortName("d").create();
    Option dictTypeOpt = obuilder.withLongName("dictionaryType").withRequired(false).withArgument(
            abuilder.withName("dictionaryType").withMinimum(1).withMaximum(1).create()).withDescription(
            "The dictionary file type (text|sequencefile)").withShortName("dt").create();
    Option csvOpt = obuilder.withLongName("csv").withRequired(false).withDescription(
            "Output the Vector as CSV.  Otherwise it substitutes in the terms for vector cell entries")
            .withShortName("c").create();
    Option namesAsCommentsOpt = obuilder.withLongName("namesAsComments").withRequired(false).withDescription(
            "If using CSV output, optionally add a comment line for each NamedVector (if the vector is one) printing out the name")
            .withShortName("n").create();
    Option sortVectorsOpt = obuilder.withLongName("sortVectors").withRequired(false).withDescription(
            "Sort output key/value pairs of the vector entries in abs magnitude descending order")
            .withShortName("sort").create();
    Option sizeOpt = obuilder.withLongName("sizeOnly").withRequired(false).
            withDescription("Dump only the size of the vector").withShortName("sz").create();
    Option numItemsOpt = obuilder.withLongName("numItems").withRequired(false).withArgument(
        abuilder.withName("n").withMinimum(1).withMaximum(1).create()).
            withDescription("Output at most <n> vecors").withShortName("n").create();
    Option numIndexesPerVectorOpt = obuilder.withLongName("vectorSize").withShortName("vs")
        .withRequired(false).withArgument(abuilder.withName("vs").withMinimum(1)
                                              .withMaximum(1).create())
        .withDescription("Truncate vectors to <vs> length when dumping (most useful when in"
                             + " conjunction with -sort").create();
    Option filtersOpt = obuilder.withLongName("filter").withRequired(false).withArgument(
            abuilder.withName("filter").withMinimum(1).withMaximum(100).create()).
            withDescription("Only dump out those vectors whose name matches the filter." +
            "  Multiple items may be specified by repeating the argument.").withShortName("fi").create();
    Option helpOpt = obuilder.withLongName("help").withDescription("Print out help").withShortName("h")
            .create();

    Group group = gbuilder.withName("Options").withOption(seqOpt).withOption(outputOpt)
                          .withOption(dictTypeOpt).withOption(dictOpt).withOption(csvOpt)
                          .withOption(vectorAsKeyOpt).withOption(printKeyOpt).withOption(sortVectorsOpt)
View Full Code Here
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
  public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
    DefaultOptionBuilder obuilder = new DefaultOptionBuilder();
    ArgumentBuilder abuilder = new ArgumentBuilder();
    GroupBuilder gbuilder = new GroupBuilder();

    Option inputOpt = DefaultOptionCreator.inputOption().create();

    Option labelOpt = obuilder.withLongName("label").withRequired(true).withShortName("l")
        .withArgument(abuilder.withName("index").withMinimum(1).withMaximum(1).create())
        .withDescription("label's index.").create();

    Option thresholdOpt = obuilder.withLongName("threshold").withRequired(false).withShortName("t").withArgument(
        abuilder.withName("threshold").withMinimum(1).withMaximum(1).create()).withDescription(
        "Condition activation threshold, default = 0.5.").create();

    Option crosspntsOpt = obuilder.withLongName("crosspnts").withRequired(false).withShortName("cp").withArgument(
        abuilder.withName("points").withMinimum(1).withMaximum(1).create()).withDescription(
        "Number of crossover points to use, default = 1.").create();

    Option mutrateOpt = obuilder.withLongName("mutrate").withRequired(true).withShortName("m").withArgument(
        abuilder.withName("true").withMinimum(1).withMaximum(1).create())
        .withDescription("Mutation rate (float).").create();

    Option mutrangeOpt = obuilder.withLongName("mutrange").withRequired(false).withShortName("mr").withArgument(
        abuilder.withName("range").withMinimum(1).withMaximum(1).create())
        .withDescription("Mutation range, default = 0.1 (10%).").create();

    Option mutprecOpt = obuilder.withLongName("mutprec").withRequired(false).withShortName("mp").withArgument(
        abuilder.withName("precision").withMinimum(1).withMaximum(1).create())
        .withDescription("Mutation precision, default = 2.").create();

    Option popsizeOpt = obuilder.withLongName("popsize").withRequired(true).withShortName("p").withArgument(
        abuilder.withName("size").withMinimum(1).withMaximum(1).create()).withDescription("Population size.").create();

    Option gencntOpt = obuilder.withLongName("gencnt").withRequired(true).withShortName("g").withArgument(
        abuilder.withName("count").withMinimum(1).withMaximum(1).create())
        .withDescription("Generations count.").create();

    Option helpOpt = DefaultOptionCreator.helpOption();

    Group group = gbuilder.withName("Options").withOption(inputOpt).withOption(helpOpt).withOption(labelOpt)
        .withOption(thresholdOpt).withOption(crosspntsOpt).withOption(mutrateOpt).withOption(mutrangeOpt)
        .withOption(mutprecOpt).withOption(popsizeOpt).withOption(gencntOpt).create();
View Full Code Here
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
  public static int main2(String[] args, Configuration conf) throws Exception {
    DefaultOptionBuilder obuilder = new DefaultOptionBuilder();
    ArgumentBuilder abuilder = new ArgumentBuilder();
    GroupBuilder gbuilder = new GroupBuilder();

    Option helpOpt = DefaultOptionCreator.helpOption();

    Option inputDirOpt = obuilder.withLongName("input").withRequired(true).withArgument(
      abuilder.withName("input").withMinimum(1).withMaximum(1).create()).withDescription(
      "The Directory on HDFS containing the collapsed, properly formatted files having "
          + "one doc per line").withShortName("i").create();

    Option dictOpt = obuilder.withLongName("dictionary").withRequired(false).withArgument(
      abuilder.withName("dictionary").withMinimum(1).withMaximum(1).create()).withDescription(
      "The path to the term-dictionary format is ... ").withShortName("d").create();

    Option dfsOpt = obuilder.withLongName("dfs").withRequired(false).withArgument(
      abuilder.withName("dfs").withMinimum(1).withMaximum(1).create()).withDescription(
      "HDFS namenode URI").withShortName("dfs").create();

    Option numTopicsOpt = obuilder.withLongName("numTopics").withRequired(true).withArgument(abuilder
        .withName("numTopics").withMinimum(1).withMaximum(1)
        .create()).withDescription("Number of topics to learn").withShortName("top").create();

    Option outputTopicFileOpt = obuilder.withLongName("topicOutputFile").withRequired(true).withArgument(
        abuilder.withName("topicOutputFile").withMinimum(1).withMaximum(1).create())
        .withDescription("File to write out p(term | topic)").withShortName("to").create();

    Option outputDocFileOpt = obuilder.withLongName("docOutputFile").withRequired(true).withArgument(
        abuilder.withName("docOutputFile").withMinimum(1).withMaximum(1).create())
        .withDescription("File to write out p(topic | docid)").withShortName("do").create();

    Option alphaOpt = obuilder.withLongName("alpha").withRequired(false).withArgument(abuilder
        .withName("alpha").withMinimum(1).withMaximum(1).withDefault("0.1").create())
        .withDescription("Smoothing parameter for p(topic | document) prior").withShortName("a").create();

    Option etaOpt = obuilder.withLongName("eta").withRequired(false).withArgument(abuilder
        .withName("eta").withMinimum(1).withMaximum(1).withDefault("0.1").create())
        .withDescription("Smoothing parameter for p(term | topic)").withShortName("e").create();

    Option maxIterOpt = obuilder.withLongName("maxIterations").withRequired(false).withArgument(abuilder
        .withName("maxIterations").withMinimum(1).withMaximum(1).withDefault(10).create())
        .withDescription("Maximum number of training passes").withShortName("m").create();

    Option modelCorpusFractionOption = obuilder.withLongName("modelCorpusFraction")
        .withRequired(false).withArgument(abuilder.withName("modelCorpusFraction").withMinimum(1)
        .withMaximum(1).withDefault(0.0).create()).withShortName("mcf")
        .withDescription("For online updates, initial value of |model|/|corpus|").create();

    Option burnInOpt = obuilder.withLongName("burnInIterations").withRequired(false).withArgument(abuilder
        .withName("burnInIterations").withMinimum(1).withMaximum(1).withDefault(5).create())
        .withDescription("Minimum number of iterations").withShortName("b").create();

    Option convergenceOpt = obuilder.withLongName("convergence").withRequired(false).withArgument(abuilder
        .withName("convergence").withMinimum(1).withMaximum(1).withDefault("0.0").create())
        .withDescription("Fractional rate of perplexity to consider convergence").withShortName("c").create();

    Option reInferDocTopicsOpt = obuilder.withLongName("reInferDocTopics").withRequired(false)
        .withArgument(abuilder.withName("reInferDocTopics").withMinimum(1).withMaximum(1)
        .withDefault("no").create())
        .withDescription("re-infer p(topic | doc) : [no | randstart | continue]")
        .withShortName("rdt").create();

    Option numTrainThreadsOpt = obuilder.withLongName("numTrainThreads").withRequired(false)
        .withArgument(abuilder.withName("numTrainThreads").withMinimum(1).withMaximum(1)
        .withDefault("1").create())
        .withDescription("number of threads to train with")
        .withShortName("ntt").create();

    Option numUpdateThreadsOpt = obuilder.withLongName("numUpdateThreads").withRequired(false)
        .withArgument(abuilder.withName("numUpdateThreads").withMinimum(1).withMaximum(1)
        .withDefault("1").create())
        .withDescription("number of threads to update the model with")
        .withShortName("nut").create();

    Option verboseOpt = obuilder.withLongName("verbose").withRequired(false)
        .withArgument(abuilder.withName("verbose").withMinimum(1).withMaximum(1)
        .withDefault("false").create())
        .withDescription("print verbose information, like top-terms in each topic, during iteration")
        .withShortName("v").create();
View Full Code Here
205
206
207
208
209
210
211
212
213
214
215
216
217
  }

  public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
    GroupBuilder gbuilder = new GroupBuilder();

    Option inputOpt = DefaultOptionCreator.inputOption().create();

    Option helpOpt = DefaultOptionCreator.helpOption();

    Group group = gbuilder.withName("Options").withOption(inputOpt).withOption(helpOpt).create();

    Parser parser = new Parser();
    parser.setGroup(group);
View Full Code Here
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
    DefaultOptionBuilder obuilder = new DefaultOptionBuilder();
    ArgumentBuilder abuilder = new ArgumentBuilder();
    GroupBuilder gbuilder = new GroupBuilder();

    Option indexOpt = obuilder.withLongName("dir").withRequired(true).withArgument(
        abuilder.withName("dir").withMinimum(1).withMaximum(1).create())
        .withDescription("The Lucene index directory").withShortName("d").create();

    Option outputOpt = obuilder.withLongName("output").withRequired(false).withArgument(
        abuilder.withName("output").withMinimum(1).withMaximum(1).create()).withDescription(
        "The output file. If not specified, the result is printed on console.").withShortName("o").create();

    Option fieldOpt = obuilder.withLongName("field").withRequired(true).withArgument(
        abuilder.withName("field").withMinimum(1).withMaximum(1).create())
        .withDescription("The content field in the index").withShortName("f").create();

    Option idFieldOpt = obuilder.withLongName("idField").withRequired(false).withArgument(
        abuilder.withName("idField").withMinimum(1).withMaximum(1).create()).withDescription(
        "The field for the document ID in the index.  If null, then the Lucene internal doc "
            + "id is used which is prone to error if the underlying index changes").withShortName("i").create();

    Option seqOpt = obuilder.withLongName("seqFileDir").withRequired(true).withArgument(
        abuilder.withName("seqFileDir").withMinimum(1).withMaximum(1).create()).withDescription(
        "The directory containing Sequence Files for the Clusters").withShortName("s").create();

    Option pointsOpt = obuilder.withLongName("pointsDir").withRequired(true).withArgument(
        abuilder.withName("pointsDir").withMinimum(1).withMaximum(1).create()).withDescription(
        "The directory containing points sequence files mapping input vectors to their cluster.  ")
        .withShortName("p").create();
    Option minClusterSizeOpt = obuilder.withLongName("minClusterSize").withRequired(false).withArgument(
        abuilder.withName("minClusterSize").withMinimum(1).withMaximum(1).create()).withDescription(
        "The minimum number of points required in a cluster to print the labels for").withShortName("m").create();
    Option maxLabelsOpt = obuilder.withLongName("maxLabels").withRequired(false).withArgument(
        abuilder.withName("maxLabels").withMinimum(1).withMaximum(1).create()).withDescription(
        "The maximum number of labels to print per cluster").withShortName("x").create();
    Option helpOpt = DefaultOptionCreator.helpOption();

    Group group = gbuilder.withName("Options").withOption(indexOpt).withOption(idFieldOpt).withOption(outputOpt)
        .withOption(fieldOpt).withOption(seqOpt).withOption(pointsOpt).withOption(helpOpt)
        .withOption(maxLabelsOpt).withOption(minClusterSizeOpt).create();
View Full Code Here
TOP

Related Classes of no.priv.garshol.duke.utils.CommandLineParser$Option

  • com.digitalpebble.behemoth.mahout.SparseVectorsFromBehemoth
  • com.digitalpebble.behemoth.tika.TikaDriver
  • no.priv.garshol.duke.Duke
  • org.apache.commons.cli.CLI2Converter
  • org.apache.commons.cli2.commandline.PreferencesCommandLine
  • org.apache.commons.cli2.commandline.PropertiesCommandLine
  • org.apache.commons.cli2.option.GroupImpl
  • org.apache.hadoop.streaming.StreamJob
  • org.apache.mahout.benchmark.VectorBenchmarks
  • org.apache.mahout.cf.taste.example.TasteOptionParser
    • 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.