void Args::printHelp()

in src/utils/args.cpp [255:313]

• 59 lines of code
• 1 McCabe index (conditional complexity)

void Args::printHelp() {
  cout << "\n"
       << "\"starspace train ...\"  or \"starspace test ...\"\n\n"
       << "The following arguments are mandatory for train: \n"
       << "  -trainFile       training file path\n"
       << "  -model           output model file path\n\n"
       << "The following arguments are mandatory for test: \n"
       << "  -testFile        test file path\n"
       << "  -model           model file path\n\n"
       << "The following arguments for the dictionary are optional:\n"
       << "  -minCount        minimal number of word occurences [" << minCount << "]\n"
       << "  -minCountLabel   minimal number of label occurences [" << minCountLabel << "]\n"
       << "  -ngrams          max length of word ngram [" << ngrams << "]\n"
       << "  -bucket          number of buckets [" << bucket << "]\n"
       << "  -label           labels prefix [" << label << "]\n"
       << "\nThe following arguments for training are optional:\n"
       << "  -initModel       if not empty, it loads a previously trained model in -initModel and carry on training.\n"
       << "  -trainMode       takes value in [0, 1, 2, 3, 4, 5], see Training Mode Section. [" << trainMode << "]\n"
       << "  -fileFormat      currently support 'fastText' and 'labelDoc', see File Format Section. [" << fileFormat << "]\n"
       << "  -validationFile  validation file path\n"
       << "  -validationPatience    number of iterations of validation where does not improve before we stop training [" << validationPatience << "]\n"
       << "  -saveEveryEpoch  save intermediate models after each epoch [" << saveEveryEpoch << "]\n"
       << "  -saveTempModel   save intermediate models after each epoch with an unique name including epoch number [" << saveTempModel << "]\n"
       << "  -lr              learning rate [" << lr << "]\n"
       << "  -dim             size of embedding vectors [" << dim << "]\n"
       << "  -epoch           number of epochs [" << epoch << "]\n"
       << "  -maxTrainTime    max train time (secs) [" << maxTrainTime << "]\n"
       << "  -negSearchLimit  number of negatives sampled [" << negSearchLimit << "]\n"
       << "  -maxNegSamples   max number of negatives in a batch update [" << maxNegSamples << "]\n"
       << "  -loss            loss function {hinge, softmax} [hinge]\n"
       << "  -margin          margin parameter in hinge loss. It's only effective if hinge loss is used. [" << margin << "]\n"
       << "  -similarity      takes value in [cosine, dot]. Whether to use cosine or dot product as similarity function in  hinge loss.\n"
       << "                   It's only effective if hinge loss is used. [" << similarity << "]\n"
       << "  -adagrad         whether to use adagrad in training [" << adagrad << "]\n"
       << "  -shareEmb        whether to use the same embedding matrix for LHS and RHS. [" << shareEmb << "]\n"
       << "  -ws              only used in trainMode 5, the size of the context window for word level training. [" << ws << "]\n"
       << "  -dropoutLHS      dropout probability for LHS features. [" << dropoutLHS << "]\n"
       << "  -dropoutRHS      dropout probability for RHS features. [" << dropoutRHS << "]\n"
       << "  -initRandSd      initial values of embeddings are randomly generated from normal distribution with mean=0, standard deviation=initRandSd. [" << initRandSd << "]\n"
       << "  -trainWord       whether to train word level together with other tasks (for multi-tasking). [" << trainWord << "]\n"
       << "  -wordWeight      if trainWord is true, wordWeight specifies example weight for word level training examples. [" << wordWeight << "]\n"
       << "  -batchSize       size of mini batch in training. [" << batchSize << "]\n"
       << "\nThe following arguments for test are optional:\n"
       << "  -basedoc         file path for a set of labels to compare against true label. It is required when -fileFormat='labelDoc'.\n"
       << "                   In the case -fileFormat='fastText' and -basedoc is not provided, we compare true label with all other labels in the dictionary.\n"
       << "  -predictionFile  file path for save predictions. If not empty, top K predictions for each example will be saved.\n"
       << "  -K               if -predictionFile is not empty, top K predictions for each example will be saved.\n"
       << "  -excludeLHS      exclude elements in the LHS from predictions\n"
       <<  "\nThe following arguments are optional:\n"
       << "  -normalizeText   whether to run basic text preprocess for input files [" << normalizeText << "]\n"
       << "  -useWeight       whether input file contains weights [" << useWeight << "]\n"
       << "  -weightSep       separator for word and weights [" << weightSep << "]\n"
       << "  -verbose         verbosity level [" << verbose << "]\n"
       << "  -debug           whether it's in debug mode [" << debug << "]\n"
       << "  -thread          number of threads [" << thread << "]\n"
       << "  -compressFile    whether to load a compressed file [" << compressFile << "]\n"
       << "  -numGzFile       number of compressed file to load [" << numGzFile << "]\n"
       << std::endl;
}