stringtowordvector.java

来自「Weka」· Java 代码 · 共 1,638 行 · 第 1/4 页

  /**
   * Sets which attributes are to be processed.
   *
   * @param attributes an array containing indexes of attributes to process.
   * Since the array will typically come from a program, attributes are indexed
   * from 0.
   * @throws IllegalArgumentException if an invalid set of ranges
   * is supplied 
   */
  public void setAttributeIndicesArray(int[] attributes) {
    setAttributeIndices(Range.indicesToRangeList(attributes));
  }

  /**
   * Returns the tip text for this property
   *
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String invertSelectionTipText() {
    return "Set attribute selection mode. If false, only selected"
      + " attributes in the range will be worked on; if"
      + " true, only non-selected attributes will be processed.";
  }

  /**
   * Gets whether the supplied columns are to be processed or skipped
   *
   * @return true if the supplied columns will be kept
   */
  public boolean getInvertSelection() {
    return m_SelectedRange.getInvert();
  }

  /**
   * Sets whether selected columns should be processed or skipped.
   *
   * @param invert the new invert setting
   */
  public void setInvertSelection(boolean invert) {
    m_SelectedRange.setInvert(invert);
  }

  /**
   * Get the attribute name prefix.
   *
   * @return The current attribute name prefix.
   */
  public String getAttributeNamePrefix() {
    return m_Prefix;
  }
    
  /**
   * Set the attribute name prefix.
   *
   * @param newPrefix String to use as the attribute name prefix.
   */
  public void setAttributeNamePrefix(String newPrefix) {
    m_Prefix = newPrefix;
  }

  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String attributeNamePrefixTipText() {
      return "Prefix for the created attribute names. "+
             "(default: \"\")";
  }

  /**
   * Gets the number of words (per class if there is a class attribute
   * assigned) to attempt to keep.
   *
   * @return the target number of words in the output vector (per class if
   * assigned).
   */
  public int getWordsToKeep() {
    return m_WordsToKeep;
  }
  
  /**
   * Sets the number of words (per class if there is a class attribute
   * assigned) to attempt to keep.
   *
   * @param newWordsToKeep the target number of words in the output 
   * vector (per class if assigned).
   */
  public void setWordsToKeep(int newWordsToKeep) {
    m_WordsToKeep = newWordsToKeep;
  }
  
  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String wordsToKeepTipText() {
      return "The number of words (per class if there is a class attribute "+
             "assigned) to attempt to keep.";
  }

  /** Gets whether if the word frequencies should be transformed into
   *  log(1+fij) where fij is the frequency of word i in document(instance) j.
   *
   * @return true if word frequencies are to be transformed.
   */
  public boolean getTFTransform() {
      return this.m_TFTransform;
  }
  
  /** Sets whether if the word frequencies should be transformed into
   *  log(1+fij) where fij is the frequency of word i in document(instance) j.
   *
   * @param TFTransform true if word frequencies are to be transformed.
   */
  public void setTFTransform(boolean TFTransform) {
      this.m_TFTransform = TFTransform;
  }
  
  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String TFTransformTipText() {
      return "Sets whether if the word frequencies should be transformed into:\n "+
             "   log(1+fij) \n"+
             "       where fij is the frequency of word i in document (instance) j.";
  }
  
  /** Sets whether if the word frequencies in a document should be transformed
   * into: <br>
   * fij*log(num of Docs/num of Docs with word i) <br>
   *      where fij is the frequency of word i in document(instance) j.
   *
   * @return true if the word frequencies are to be transformed.
   */
  public boolean getIDFTransform() {
      return this.m_IDFTransform;
  }
  
  /** Sets whether if the word frequencies in a document should be transformed
   * into: <br>
   * fij*log(num of Docs/num of Docs with word i) <br>
   *      where fij is the frequency of word i in document(instance) j.
   *
   * @param IDFTransform true if the word frequecies are to be transformed
   */
  public void setIDFTransform(boolean IDFTransform) {
      this.m_IDFTransform = IDFTransform;
  }
  
  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String IDFTransformTipText() {
      return "Sets whether if the word frequencies in a document should be "+
             "transformed into: \n"+
             "   fij*log(num of Docs/num of Docs with word i) \n"+
             "      where fij is the frequency of word i in document (instance) j.";
  }

  
  /** Gets whether if the word frequencies for a document (instance) should
   *  be normalized or not.
   *
   * @return true if word frequencies are to be normalized.
   */
  public SelectedTag getNormalizeDocLength() {

    return new SelectedTag(m_filterType, TAGS_FILTER);
  }
  
  /** Sets whether if the word frequencies for a document (instance) should
   *  be normalized or not.
   *
   * @param newType the new type.
   */
  public void setNormalizeDocLength(SelectedTag newType) {
    
    if (newType.getTags() == TAGS_FILTER) {
      m_filterType = newType.getSelectedTag().getID();
    }
  }

  /**
   * Returns the tip text for this property
   *
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String normalizeDocLengthTipText() {
      return "Sets whether if the word frequencies for a document (instance) "+
             "should be normalized or not.";
  }
  
  /** Gets whether if the tokens are to be downcased or not.
   *
   * @return true if the tokens are to be downcased.
   */
  public boolean getLowerCaseTokens() {
      return this.m_lowerCaseTokens;
  }
  
  /** Sets whether if the tokens are to be downcased or not. (Doesn't affect
   * non-alphabetic characters in tokens).
   *
   * @param downCaseTokens should be true if only lower case tokens are 
   * to be formed.
   */
  public void setLowerCaseTokens(boolean downCaseTokens) {
      this.m_lowerCaseTokens = downCaseTokens;
  }

  /**
   * Returns the tip text for this property.
   *
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String doNotOperateOnPerClassBasisTipText() {
      return "If this is set, the maximum number of words and the "
	+ "minimum term frequency is not enforced on a per-class "
	+ "basis but based on the documents in all the classes "
	+  "(even if a class attribute is set).";
  }

  /**
   * Get the DoNotOperateOnPerClassBasis value.
   * @return the DoNotOperateOnPerClassBasis value.
   */
  public boolean getDoNotOperateOnPerClassBasis() {
    return m_doNotOperateOnPerClassBasis;
  }

  /**
   * Set the DoNotOperateOnPerClassBasis value.
   * @param newDoNotOperateOnPerClassBasis The new DoNotOperateOnPerClassBasis value.
   */
  public void setDoNotOperateOnPerClassBasis(boolean newDoNotOperateOnPerClassBasis) {
    this.m_doNotOperateOnPerClassBasis = newDoNotOperateOnPerClassBasis;
  }

  /**
   * Returns the tip text for this property.
   *
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String minTermFreqTipText() {
      return "Sets the minimum term frequency. This is enforced "
	+ "on a per-class basis.";
  }

  /**
   * Get the MinTermFreq value.
   * @return the MinTermFreq value.
   */
  public int getMinTermFreq() {
    return m_minTermFreq;
  }

  /**
   * Set the MinTermFreq value.
   * @param newMinTermFreq The new MinTermFreq value.
   */
  public void setMinTermFreq(int newMinTermFreq) {
    this.m_minTermFreq = newMinTermFreq;
  }
  
  /**
   * Returns the tip text for this property.
   *
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String lowerCaseTokensTipText() {
      return "If set then all the word tokens are converted to lower case "+
             "before being added to the dictionary.";
  }

  /** Gets whether if the words on the stoplist are to be ignored (The stoplist
   *  is in weka.core.StopWords).
   *
   * @return true if the words on the stoplist are to be ignored.
   */
  public boolean getUseStoplist() {
      return m_useStoplist;
  }  
  
  /** Sets whether if the words that are on a stoplist are to be ignored (The
   * stop list is in weka.core.StopWords).
   *
   * @param useStoplist true if the tokens that are on a stoplist are to be 
   * ignored.
   */
  public void setUseStoplist(boolean useStoplist) {
      m_useStoplist = useStoplist;
  }  
  
  /**
   * Returns the tip text for this property.
   *
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String useStoplistTipText() {
      return "Ignores all the words that are on the stoplist, if set to true.";
  } 

  /**
   * the stemming algorithm to use, null means no stemming at all (i.e., the
   * NullStemmer is used)
   *
   * @param value     the configured stemming algorithm, or null
   * @see             NullStemmer
   */
  public void setStemmer(Stemmer value) {
    if (value != null)
      m_Stemmer = value;
    else
      m_Stemmer = new NullStemmer();
  }

  /**
   * Returns the current stemming algorithm, null if none is used.
   *
   * @return          the current stemming algorithm, null if none set
   */
  public Stemmer getStemmer() {
    return m_Stemmer;
  }

  /**
   * Returns the tip text for this property.
   *
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String stemmerTipText() {
    return "The stemming algorithm to use on the words.";
  }

  /**
   * sets the file containing the stopwords, null or a directory unset the
   * stopwords. If the file exists, it automatically turns on the flag to
   * use the stoplist.
   *
   * @param value     the file containing the stopwords
   */
  public void setStopwords(File value) {
    if (value == null)
      value = new File(System.getProperty("user.dir"));

    m_Stopwords = value;
    if (value.exists() && value.isFile())
      setUseStoplist(true);
  }

  /**
   * returns the file used for obtaining the stopwords, if the file represents
   * a directory then the default ones are used.
   *
   * @return          the file containing the stopwords
   */
  public File getStopwords() {
    return m_Stopwords;
  }

  /**
   * Returns the tip text for this property.
   *
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String stopwordsTipText() {
    return "The file containing the stopwords (if this is a directory then the default ones are used).";
  }
  
  /**
   * the tokenizer algorithm to use
   *
   * @param value     the configured tokenizing algorithm
   */
  public void setTokenizer(Tokenizer value) {
    m_Tokenizer = value;
  }

  /**
   * Returns the current tokenizer algorithm.
   *
   * @return          the current tokenizer algorithm
   */
  public Tokenizer getTokenizer() {
    return m_Tokenizer;
  }

  /**
   * Returns the tip text for this property.
   *
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String tokenizerTipText() {
    return "The tokenizing algorithm to use on the strings.";