Package no.priv.garshol.duke.utils

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

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
    DefaultOptionBuilder obuilder = new DefaultOptionBuilder();
    ArgumentBuilder abuilder = new ArgumentBuilder();
    GroupBuilder gbuilder = new GroupBuilder();

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

    Option outputOpt = obuilder.withLongName("output").withRequired(true).withArgument(
        abuilder.withName("output").withMinimum(1).withMaximum(1).create()).withDescription("The output file")
        .withShortName("o").create();

    Option fieldOpt = obuilder.withLongName("field").withRequired(true).withArgument(
        abuilder.withName("field").withMinimum(1).withMaximum(1).create()).withDescription(
        "The 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 in the index containing the index.  If null, then the Lucene internal doc "
            + "id is used which is prone to error if the underlying index changes").create();

    Option dictOutOpt = obuilder.withLongName("dictOut").withRequired(true).withArgument(
        abuilder.withName("dictOut").withMinimum(1).withMaximum(1).create()).withDescription(
        "The output of the dictionary").withShortName("t").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("w").create();

    Option delimiterOpt = obuilder.withLongName("delimiter").withRequired(false).withArgument(
        abuilder.withName("delimiter").withMinimum(1).withMaximum(1).create()).withDescription(
        "The delimiter for outputting the dictionary").withShortName("l").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 double 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 maxOpt = obuilder.withLongName("max").withRequired(false).withArgument(
        abuilder.withName("max").withMinimum(1).withMaximum(1).create()).withDescription(
        "The maximum number of vectors to output.  If not specified, then it will loop over all docs")
        .withShortName("m").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.").withShortName("x").create();

    Option maxPercentErrorDocsOpt = obuilder.withLongName("maxPercentErrorDocs").withRequired(false).withArgument(
        abuilder.withName("maxPercentErrorDocs").withMinimum(1).withMaximum(1).create()).withDescription(
        "The max percentage of docs that can have a null term vector. These are noise document and can occur if the " +
            "analyzer used strips out all terms in the target field. This percentage is expressed as a value between 0 and 1. " +
            "The default is 0.").withShortName("err").create();

    Option helpOpt = obuilder.withLongName("help").withDescription("Print out help").withShortName("h")
        .create();

    Group group = gbuilder.withName("Options").withOption(inputOpt).withOption(idFieldOpt).withOption(
        outputOpt).withOption(delimiterOpt).withOption(helpOpt).withOption(fieldOpt).withOption(maxOpt)
        .withOption(dictOutOpt).withOption(powerOpt).withOption(maxDFPercentOpt)
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
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
  public static void main(String[] args) throws IOException, InvalidDatastoreException {
    DefaultOptionBuilder obuilder = new DefaultOptionBuilder();
    ArgumentBuilder abuilder = new ArgumentBuilder();
    GroupBuilder gbuilder = new GroupBuilder();
   
    Option pathOpt = obuilder.withLongName("model").withRequired(true).withArgument(
      abuilder.withName("model").withMinimum(1).withMaximum(1).create()).withDescription(
      "The path on HDFS as defined by the -source parameter").withShortName("m")
        .create();
   
    Option dirOpt = obuilder.withLongName("testDir").withRequired(true).withArgument(
      abuilder.withName("testDir").withMinimum(1).withMaximum(1).create()).withDescription(
      "The directory where test documents resides in").withShortName("d").create();
   
    Option helpOpt = DefaultOptionCreator.helpOption();
   
    Option encodingOpt = obuilder.withLongName("encoding").withArgument(
      abuilder.withName("encoding").withMinimum(1).withMaximum(1).create()).withDescription(
      "The file encoding.  Defaults to UTF-8").withShortName("e").create();
   
    Option defaultCatOpt = obuilder.withLongName("defaultCat").withArgument(
      abuilder.withName("defaultCat").withMinimum(1).withMaximum(1).create()).withDescription(
      "The default category Default Value: unknown").withShortName("default").create();
   
    Option gramSizeOpt = obuilder.withLongName("gramSize").withRequired(false).withArgument(
      abuilder.withName("gramSize").withMinimum(1).withMaximum(1).create()).withDescription(
      "Size of the n-gram. Default Value: 1").withShortName("ng").create();
   
    Option alphaOpt = obuilder.withLongName("alpha").withRequired(false).withArgument(
      abuilder.withName("a").withMinimum(1).withMaximum(1).create()).withDescription(
      "Smoothing parameter Default Value: 1.0").withShortName("a").create();
   
    Option verboseOutputOpt = obuilder.withLongName("verbose").withRequired(false).withDescription(
      "Output which values were correctly and incorrectly classified").withShortName("v").create();
   
    Option typeOpt = obuilder.withLongName("classifierType").withRequired(false).withArgument(
      abuilder.withName("classifierType").withMinimum(1).withMaximum(1).create()).withDescription(
      "Type of classifier: bayes|cbayes. Default Value: bayes").withShortName("type").create();
   
    Option dataSourceOpt = obuilder.withLongName("dataSource").withRequired(false).withArgument(
      abuilder.withName("dataSource").withMinimum(1).withMaximum(1).create()).withDescription(
      "Location of model: hdfs").withShortName("source").create();
   
    Option methodOpt = obuilder.withLongName("method").withRequired(false).withArgument(
      abuilder.withName("method").withMinimum(1).withMaximum(1).create()).withDescription(
      "Method of Classification: sequential|mapreduce. Default Value: mapreduce").withShortName("method")
        .create();
   
    Option confusionMatrixOpt = obuilder.withLongName("confusionMatrix").withRequired(false).withArgument(
        abuilder.withName("confusionMatrix").withMinimum(1).withMaximum(1).create()).withDescription(
        "Export ConfusionMatrix as SequenceFile").withShortName("cm").create();
     
    Group group = gbuilder.withName("Options").withOption(defaultCatOpt).withOption(dirOpt).withOption(
      encodingOpt).withOption(gramSizeOpt).withOption(pathOpt).withOption(typeOpt).withOption(dataSourceOpt)
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
  public static void main(String[] args) throws Exception {
    DefaultOptionBuilder obuilder = new DefaultOptionBuilder();
    ArgumentBuilder abuilder = new ArgumentBuilder();
    GroupBuilder gbuilder = new GroupBuilder();
   
    Option helpOpt = DefaultOptionCreator.helpOption();
   
    Option inputDirOpt = DefaultOptionCreator.inputOption().create();
   
    Option outputOpt = DefaultOptionCreator.outputOption().create();
   
    Option gramSizeOpt = obuilder.withLongName("gramSize").withRequired(false).withArgument(
      abuilder.withName("gramSize").withMinimum(1).withMaximum(1).create()).withDescription(
      "Size of the n-gram. Default Value: 1 ").withShortName("ng").create();
   
    Option minDfOpt = obuilder.withLongName("minDf").withRequired(false).withArgument(
        abuilder.withName("minDf").withMinimum(1).withMaximum(1).create()).withDescription(
        "Minimum Term Document Frequency: 1 ").withShortName("mf").create();
   
    Option minSupportOpt = obuilder.withLongName("minSupport").withRequired(false).withArgument(
        abuilder.withName("minSupport").withMinimum(1).withMaximum(1).create()).withDescription(
        "Minimum Support (Term Frequency): 1 ").withShortName("ms").create();
   
    Option alphaOpt = obuilder.withLongName("alpha").withRequired(false).withArgument(
      abuilder.withName("a").withMinimum(1).withMaximum(1).create()).withDescription(
      "Smoothing parameter Default Value: 1.0").withShortName("a").create();
   
    Option typeOpt = obuilder.withLongName("classifierType").withRequired(false).withArgument(
      abuilder.withName("classifierType").withMinimum(1).withMaximum(1).create()).withDescription(
      "Type of classifier: bayes|cbayes. Default: bayes").withShortName("type").create();
   
    Option dataSourceOpt = obuilder.withLongName("dataSource").withRequired(false).withArgument(
      abuilder.withName("dataSource").withMinimum(1).withMaximum(1).create()).withDescription(
      "Location of model: hdfs. Default Value: hdfs").withShortName("source").create();
   
    Option skipCleanupOpt = obuilder.withLongName("skipCleanup").withRequired(false).withDescription(
        "Skip cleanup of feature extraction output").withShortName("sc").create();
   
    Group group = gbuilder.withName("Options").withOption(gramSizeOpt).withOption(helpOpt).withOption(
      inputDirOpt).withOption(outputOpt).withOption(typeOpt).withOption(dataSourceOpt).withOption(alphaOpt)
        .withOption(minDfOpt).withOption(minSupportOpt).withOption(skipCleanupOpt).create();
View Full Code Here
58
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
   
    DefaultOptionBuilder obuilder = new DefaultOptionBuilder();
    ArgumentBuilder abuilder = new ArgumentBuilder();
    GroupBuilder gbuilder = new GroupBuilder();
   
    Option pathOpt = obuilder.withLongName("path").withRequired(true).withArgument(
      abuilder.withName("path").withMinimum(1).withMaximum(1).create()).withDescription(
      "The local file system path").withShortName("m").create();
   
    Option classifyOpt = obuilder.withLongName("classify").withRequired(true).withArgument(
      abuilder.withName("classify").withMinimum(1).withMaximum(1).create()).withDescription(
      "The doc to classify").withShortName("").create();
   
    Option encodingOpt = obuilder.withLongName("encoding").withRequired(true).withArgument(
      abuilder.withName("encoding").withMinimum(1).withMaximum(1).create()).withDescription(
      "The file encoding.  Default: UTF-8").withShortName("e").create();
   
    Option analyzerOpt = obuilder.withLongName("analyzer").withRequired(true).withArgument(
      abuilder.withName("analyzer").withMinimum(1).withMaximum(1).create()).withDescription(
      "The Analyzer to use").withShortName("a").create();
   
    Option defaultCatOpt = obuilder.withLongName("defaultCat").withRequired(true).withArgument(
      abuilder.withName("defaultCat").withMinimum(1).withMaximum(1).create()).withDescription(
      "The default category").withShortName("d").create();
   
    Option gramSizeOpt = obuilder.withLongName("gramSize").withRequired(true).withArgument(
      abuilder.withName("gramSize").withMinimum(1).withMaximum(1).create()).withDescription(
      "Size of the n-gram").withShortName("ng").create();
   
    Option typeOpt = obuilder.withLongName("classifierType").withRequired(true).withArgument(
      abuilder.withName("classifierType").withMinimum(1).withMaximum(1).create()).withDescription(
      "Type of classifier").withShortName("type").create();
   
    Option dataSourceOpt = obuilder.withLongName("dataSource").withRequired(true).withArgument(
      abuilder.withName("dataSource").withMinimum(1).withMaximum(1).create()).withDescription(
      "Location of model: hdfs").withShortName("source").create();
   
    Group options = gbuilder.withName("Options").withOption(pathOpt).withOption(classifyOpt).withOption(
      encodingOpt).withOption(analyzerOpt).withOption(defaultCatOpt).withOption(gramSizeOpt).withOption(
View Full Code Here
53
54
55
56
57
58
59
60
61
62
63
64
65
   *           any exception thrown at job execution.
   * */
  public static void execute(String[] args, BayesJob job) throws IOException {
    GroupBuilder gbuilder = new GroupBuilder();
   
    Option inputOpt = DefaultOptionCreator.inputOption().create();
    Option outputOpt = DefaultOptionCreator.outputOption().create();
    Option helpOpt = DefaultOptionCreator.helpOption();
   
    Group group = gbuilder.withName("Options").withOption(inputOpt).withOption(outputOpt).withOption(helpOpt)
        .create();
   
    try {
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
  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 outputOpt = DefaultOptionCreator.outputOption().create();
   
    Option labelOpt = obuilder.withLongName("label").withRequired(true).withArgument(
      abuilder.withName("label").withMinimum(1).withMaximum(1).create()).withDescription("The label of the file")
        .withShortName("l").create();
   
    Option analyzerOpt = obuilder.withLongName("analyzer").withArgument(
      abuilder.withName("analyzer").withMinimum(1).withMaximum(1).create()).withDescription(
      "The fully qualified class name of the analyzer to use. "
          + "Must have a no-arg constructor.  Default is the StandardAnalyzer").withShortName("a").create();
   
    Option charsetOpt = obuilder.withLongName("charset").withArgument(
      abuilder.withName("charset").withMinimum(1).withMaximum(1).create()).withDescription(
      "The character encoding of the input file").withShortName("c").create();
   
    Option collapseOpt = obuilder.withLongName("collapse").withRequired(true).withArgument(
      abuilder.withName("collapse").withMinimum(1).withMaximum(1).create()).withDescription(
      "Collapse a whole directory to a single file, one doc per line").withShortName("p").create();
   
    Option helpOpt = DefaultOptionCreator.helpOption();
    Group group = gbuilder.withName("Options").withOption(inputOpt).withOption(outputOpt).withOption(labelOpt)
        .withOption(analyzerOpt).withOption(charsetOpt).withOption(collapseOpt).withOption(helpOpt).create();
    try {
      Parser parser = new Parser();
      parser.setGroup(group);
View Full Code Here
52
53
54
55
56
57
58
59
60
61
62
63
64
  }

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

    Option inputOpt = DefaultOptionCreator.inputOption().withRequired(false).create();
    Option outputOpt = DefaultOptionCreator.outputOption().withRequired(false).create();
    Option helpOpt = DefaultOptionCreator.helpOption();
    Group group = gbuilder.withName("Options").withOption(inputOpt).withOption(outputOpt).withOption(helpOpt).create();

    try {
      Parser parser = new Parser();
      parser.setGroup(group);
View Full Code Here
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
  }

  boolean parseArgs(String[] args) {
    DefaultOptionBuilder builder = new DefaultOptionBuilder();

    Option help = builder.withLongName("help").withDescription("print this list").create();

    ArgumentBuilder argumentBuilder = new ArgumentBuilder();
    Option inputFileOption = builder.withLongName("input")
            .withRequired(true)
            .withArgument(argumentBuilder.withName("input").withMaximum(1).create())
            .withDescription("where to get training data")
            .create();

    Option modelFileOption = builder.withLongName("model")
            .withRequired(true)
            .withArgument(argumentBuilder.withName("model").withMaximum(1).create())
            .withDescription("where to get a model")
            .create();
View Full Code Here
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
 
  public static void main(String[] args) throws Exception {
    DefaultOptionBuilder obuilder = new DefaultOptionBuilder();
    ArgumentBuilder abuilder = new ArgumentBuilder();
    GroupBuilder gbuilder = new GroupBuilder();
    Option helpOpt = DefaultOptionCreator.helpOption();
   
    Option parentOpt = obuilder.withLongName("parent").withRequired(true).withArgument(
      abuilder.withName("parent").withMinimum(1).withMaximum(1).create()).withDescription(
      "Parent dir containing the newsgroups").withShortName("p").create();
   
    Option outputDirOpt = obuilder.withLongName("outputDir").withRequired(true).withArgument(
      abuilder.withName("outputDir").withMinimum(1).withMaximum(1).create()).withDescription(
      "The output directory").withShortName("o").create();
   
    Option analyzerNameOpt = obuilder.withLongName("analyzerName").withRequired(true).withArgument(
      abuilder.withName("analyzerName").withMinimum(1).withMaximum(1).create()).withDescription(
      "The class name of the analyzer").withShortName("a").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();
   
    Group group = gbuilder.withName("Options").withOption(analyzerNameOpt).withOption(charsetOpt).withOption(
      outputDirOpt).withOption(parentOpt).withOption(helpOpt).create();
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
  public static void main(String[] args) throws IOException {
    DefaultOptionBuilder obuilder = new DefaultOptionBuilder();
    ArgumentBuilder abuilder = new ArgumentBuilder();
    GroupBuilder gbuilder = new GroupBuilder();
   
    Option dumpFileOpt = obuilder.withLongName("dumpFile").withRequired(true).withArgument(
      abuilder.withName("dumpFile").withMinimum(1).withMaximum(1).create()).withDescription(
      "The path to the wikipedia dump file (.bz2 or uncompressed)").withShortName("d").create();
   
    Option outputDirOpt = obuilder.withLongName("outputDir").withRequired(true).withArgument(
      abuilder.withName("outputDir").withMinimum(1).withMaximum(1).create()).withDescription(
      "The output directory to place the splits in:\n"
          + "local files:\n\t/var/data/wikipedia-xml-chunks or\n\tfile:///var/data/wikipedia-xml-chunks\n"
          + "Hadoop DFS:\n\thdfs://wikipedia-xml-chunks\n"
          + "AWS S3 (blocks):\n\ts3://bucket-name/wikipedia-xml-chunks\n"
          + "AWS S3 (native files):\n\ts3n://bucket-name/wikipedia-xml-chunks\n")

    .withShortName("o").create();
   
    Option s3IdOpt = obuilder.withLongName("s3ID").withRequired(false).withArgument(
      abuilder.withName("s3Id").withMinimum(1).withMaximum(1).create()).withDescription("Amazon S3 ID key")
        .withShortName("i").create();
    Option s3SecretOpt = obuilder.withLongName("s3Secret").withRequired(false).withArgument(
      abuilder.withName("s3Secret").withMinimum(1).withMaximum(1).create()).withDescription(
      "Amazon S3 secret key").withShortName("s").create();
   
    Option chunkSizeOpt = obuilder.withLongName("chunkSize").withRequired(true).withArgument(
      abuilder.withName("chunkSize").withMinimum(1).withMaximum(1).create()).withDescription(
      "The Size of the chunk, in megabytes").withShortName("c").create();
    Option numChunksOpt = obuilder
        .withLongName("numChunks")
        .withRequired(false)
        .withArgument(abuilder.withName("numChunks").withMinimum(1).withMaximum(1).create())
        .withDescription(
          "The maximum number of chunks to create.  If specified, program will only create a subset of the chunks")
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.