List of usage examples for weka.core Instance isMissing
public boolean isMissing(Attribute att);
From source file:classifier.CustomStringToWordVector.java
License:Open Source License
/** * determines the dictionary./*from ww w . j a va 2 s. c o m*/ */ private void determineDictionary() { if (forcedAttributes == null) { // initialize stopwords Stopwords stopwords = new Stopwords(); if (getUseStoplist()) { try { if (getStopwords().exists() && !getStopwords().isDirectory()) stopwords.read(getStopwords()); } catch (Exception e) { e.printStackTrace(); } } // Operate on a per-class basis if class attribute is set int classInd = getInputFormat().classIndex(); int values = 1; if (!m_doNotOperateOnPerClassBasis && (classInd != -1)) { values = getInputFormat().attribute(classInd).numValues(); } // TreeMap dictionaryArr [] = new TreeMap[values]; TreeMap[] dictionaryArr = new TreeMap[values]; for (int i = 0; i < values; i++) { dictionaryArr[i] = new TreeMap(); } // Make sure we know which fields to convert determineSelectedRange(); // Tokenize all training text into an orderedMap of "words". long pruneRate = Math.round((m_PeriodicPruningRate / 100.0) * getInputFormat().numInstances()); for (int i = 0; i < getInputFormat().numInstances(); i++) { Instance instance = getInputFormat().instance(i); int vInd = 0; if (!m_doNotOperateOnPerClassBasis && (classInd != -1)) { vInd = (int) instance.classValue(); } // Iterate through all relevant string attributes of the current // instance Hashtable h = new Hashtable(); for (int j = 0; j < instance.numAttributes(); j++) { if (m_SelectedRange.isInRange(j) && (instance.isMissing(j) == false)) { // Get tokenizer m_Tokenizer.tokenize(instance.stringValue(j)); // Iterate through tokens, perform stemming, and remove // stopwords // (if required) while (m_Tokenizer.hasMoreElements()) { String word = ((String) m_Tokenizer.nextElement()).intern(); if (this.m_lowerCaseTokens == true) word = word.toLowerCase(); word = m_Stemmer.stem(word); if (this.m_useStoplist == true) if (stopwords.is(word)) continue; if (!(h.contains(word))) h.put(word, new Integer(0)); Count count = (Count) dictionaryArr[vInd].get(word); if (count == null) { dictionaryArr[vInd].put(word, new Count(1)); } else { count.count++; } } } } // updating the docCount for the words that have occurred in // this // instance(document). Enumeration e = h.keys(); while (e.hasMoreElements()) { String word = (String) e.nextElement(); Count c = (Count) dictionaryArr[vInd].get(word); if (c != null) { c.docCount++; } else System.err.println("Warning: A word should definitely be in the " + "dictionary.Please check the code"); } if (pruneRate > 0) { if (i % pruneRate == 0 && i > 0) { for (int z = 0; z < values; z++) { Vector d = new Vector(1000); Iterator it = dictionaryArr[z].keySet().iterator(); while (it.hasNext()) { String word = (String) it.next(); Count count = (Count) dictionaryArr[z].get(word); if (count.count <= 1) { d.add(word); } } Iterator iter = d.iterator(); while (iter.hasNext()) { String word = (String) iter.next(); dictionaryArr[z].remove(word); } } } } } // Figure out the minimum required word frequency int totalsize = 0; int prune[] = new int[values]; for (int z = 0; z < values; z++) { totalsize += dictionaryArr[z].size(); int array[] = new int[dictionaryArr[z].size()]; int pos = 0; Iterator it = dictionaryArr[z].keySet().iterator(); while (it.hasNext()) { String word = (String) it.next(); Count count = (Count) dictionaryArr[z].get(word); array[pos] = count.count; pos++; } // sort the array sortArray(array); if (array.length < m_WordsToKeep) { // if there aren't enough words, set the threshold to // minFreq prune[z] = m_minTermFreq; } else { // otherwise set it to be at least minFreq prune[z] = Math.max(m_minTermFreq, array[array.length - m_WordsToKeep]); } } // Convert the dictionary into an attribute index // and create one attribute per word FastVector attributes = new FastVector(totalsize + getInputFormat().numAttributes()); // Add the non-converted attributes int classIndex = -1; for (int i = 0; i < getInputFormat().numAttributes(); i++) { if (!m_SelectedRange.isInRange(i)) { if (getInputFormat().classIndex() == i) { classIndex = attributes.size(); } attributes.addElement(getInputFormat().attribute(i).copy()); } } // Add the word vector attributes (eliminating duplicates // that occur in multiple classes) TreeMap newDictionary = new TreeMap(); int index = attributes.size(); for (int z = 0; z < values; z++) { Iterator it = dictionaryArr[z].keySet().iterator(); while (it.hasNext()) { String word = (String) it.next(); Count count = (Count) dictionaryArr[z].get(word); if (count.count >= prune[z]) { if (newDictionary.get(word) == null) { newDictionary.put(word, new Integer(index++)); attributes.addElement(new Attribute(m_Prefix + word)); } } } } // Compute document frequencies m_DocsCounts = new int[attributes.size()]; Iterator it = newDictionary.keySet().iterator(); while (it.hasNext()) { String word = (String) it.next(); int idx = ((Integer) newDictionary.get(word)).intValue(); int docsCount = 0; for (int j = 0; j < values; j++) { Count c = (Count) dictionaryArr[j].get(word); if (c != null) docsCount += c.docCount; } m_DocsCounts[idx] = docsCount; } // Trim vector and set instance variables attributes.trimToSize(); m_Dictionary = newDictionary; m_NumInstances = getInputFormat().numInstances(); // Set the filter's output format Instances outputFormat = new Instances(getInputFormat().relationName(), attributes, 0); outputFormat.setClassIndex(classIndex); setOutputFormat(outputFormat); } else { //m_Dictionary = newDictionary; determineSelectedRange(); m_NumInstances = getInputFormat().numInstances(); TreeMap newDictionary = new TreeMap(); for (int i = 2; i < forcedAttributes.size(); i++) { newDictionary.put(((Attribute) forcedAttributes.get(i)).name(), new Integer(i)); } m_Dictionary = newDictionary; // Set the filter's output format Instances outputFormat = new Instances(getInputFormat().relationName(), forcedAttributes, 0); outputFormat.setClassIndex(1); setOutputFormat(outputFormat); } }
From source file:classifier.CustomStringToWordVector.java
License:Open Source License
/** * Converts the instance w/o normalization. * /*w ww .java2 s.c o m*/ * @oaram instance the instance to convert * @param v * @return the conerted instance */ private int convertInstancewoDocNorm(Instance instance, FastVector v) { // Convert the instance into a sorted set of indexes TreeMap contained = new TreeMap(); // Copy all non-converted attributes from input to output int firstCopy = 0; for (int i = 0; i < getInputFormat().numAttributes(); i++) { if (!m_SelectedRange.isInRange(i)) { if (getInputFormat().attribute(i).type() != Attribute.STRING) { // Add simple nominal and numeric attributes directly if (instance.value(i) != 0.0) { contained.put(new Integer(firstCopy), new Double(instance.value(i))); } } else { if (instance.isMissing(i)) { contained.put(new Integer(firstCopy), new Double(Utils.missingValue())); } else { // If this is a string attribute, we have to first add // this value to the range of possible values, then add // its new internal index. if (outputFormatPeek().attribute(firstCopy).numValues() == 0) { // Note that the first string value in a // SparseInstance doesn't get printed. outputFormatPeek().attribute(firstCopy) .addStringValue("Hack to defeat SparseInstance bug"); } int newIndex = outputFormatPeek().attribute(firstCopy) .addStringValue(instance.stringValue(i)); contained.put(new Integer(firstCopy), new Double(newIndex)); } } firstCopy++; } } for (int j = 0; j < instance.numAttributes(); j++) { // if ((getInputFormat().attribute(j).type() == Attribute.STRING) if (m_SelectedRange.isInRange(j) && (instance.isMissing(j) == false)) { m_Tokenizer.tokenize(instance.stringValue(j)); while (m_Tokenizer.hasMoreElements()) { String word = (String) m_Tokenizer.nextElement(); if (this.m_lowerCaseTokens == true) word = word.toLowerCase(); word = m_Stemmer.stem(word); Integer index = (Integer) m_Dictionary.get(word); if (index != null) { if (m_OutputCounts) { // Separate if here rather than // two lines down to avoid // hashtable lookup Double count = (Double) contained.get(index); if (count != null) { contained.put(index, new Double(count.doubleValue() + 1.0)); } else { contained.put(index, new Double(1)); } } else { contained.put(index, new Double(1)); } } } } } // Doing TFTransform if (m_TFTransform == true) { Iterator it = contained.keySet().iterator(); for (int i = 0; it.hasNext(); i++) { Integer index = (Integer) it.next(); if (index.intValue() >= firstCopy) { double val = ((Double) contained.get(index)).doubleValue(); val = Math.log(val + 1); contained.put(index, new Double(val)); } } } // Doing IDFTransform if (m_IDFTransform == true) { Iterator it = contained.keySet().iterator(); for (int i = 0; it.hasNext(); i++) { Integer index = (Integer) it.next(); if (index.intValue() >= firstCopy) { double val = ((Double) contained.get(index)).doubleValue(); val = val * Math.log(m_NumInstances / (double) m_DocsCounts[index.intValue()]); contained.put(index, new Double(val)); } } } // Convert the set to structures needed to create a sparse instance. double[] values = new double[contained.size()]; int[] indices = new int[contained.size()]; Iterator it = contained.keySet().iterator(); for (int i = 0; it.hasNext(); i++) { Integer index = (Integer) it.next(); Double value = (Double) contained.get(index); values[i] = value.doubleValue(); indices[i] = index.intValue(); } Instance inst = new SparseInstance(instance.weight(), values, indices, outputFormatPeek().numAttributes()); inst.setDataset(outputFormatPeek()); v.addElement(inst); return firstCopy; }
From source file:clusterer.SimpleKMeansWithSilhouette.java
License:Open Source License
/** * Move the centroid to it's new coordinates. Generate the centroid * coordinates based on it's members (objects assigned to the cluster of the * centroid) and the distance function being used. * // w w w . j a v a2s . co m * @param centroidIndex index of the centroid which the coordinates will be * computed * @param members the objects that are assigned to the cluster of this * centroid * @param updateClusterInfo if the method is supposed to update the m_Cluster * arrays * @param addToCentroidInstances true if the method is to add the computed * coordinates to the Instances holding the centroids * @return the centroid coordinates */ protected double[] moveCentroid(int centroidIndex, Instances members, boolean updateClusterInfo, boolean addToCentroidInstances) { double[] vals = new double[members.numAttributes()]; double[][] nominalDists = new double[members.numAttributes()][]; double[] weightMissing = new double[members.numAttributes()]; double[] weightNonMissing = new double[members.numAttributes()]; // Quickly calculate some relevant statistics for (int j = 0; j < members.numAttributes(); j++) { if (members.attribute(j).isNominal()) { nominalDists[j] = new double[members.attribute(j).numValues()]; } } for (Instance inst : members) { for (int j = 0; j < members.numAttributes(); j++) { if (inst.isMissing(j)) { weightMissing[j] += inst.weight(); } else { weightNonMissing[j] += inst.weight(); if (members.attribute(j).isNumeric()) { vals[j] += inst.weight() * inst.value(j); // Will be overwritten in Manhattan case } else { nominalDists[j][(int) inst.value(j)] += inst.weight(); } } } } for (int j = 0; j < members.numAttributes(); j++) { if (members.attribute(j).isNumeric()) { if (weightNonMissing[j] > 0) { vals[j] /= weightNonMissing[j]; } else { vals[j] = Utils.missingValue(); } } else { double max = -Double.MAX_VALUE; double maxIndex = -1; for (int i = 0; i < nominalDists[j].length; i++) { if (nominalDists[j][i] > max) { max = nominalDists[j][i]; maxIndex = i; } if (max < weightMissing[j]) { vals[j] = Utils.missingValue(); } else { vals[j] = maxIndex; } } } } if (m_DistanceFunction instanceof ManhattanDistance) { // Need to replace means by medians Instances sortedMembers = null; int middle = (members.numInstances() - 1) / 2; boolean dataIsEven = ((members.numInstances() % 2) == 0); if (m_PreserveOrder) { sortedMembers = members; } else { sortedMembers = new Instances(members); } for (int j = 0; j < members.numAttributes(); j++) { if ((weightNonMissing[j] > 0) && members.attribute(j).isNumeric()) { // singleton special case if (members.numInstances() == 1) { vals[j] = members.instance(0).value(j); } else { vals[j] = sortedMembers.kthSmallestValue(j, middle + 1); if (dataIsEven) { vals[j] = (vals[j] + sortedMembers.kthSmallestValue(j, middle + 2)) / 2; } } } } } if (updateClusterInfo) { for (int j = 0; j < members.numAttributes(); j++) { m_ClusterMissingCounts[centroidIndex][j] = weightMissing[j]; m_ClusterNominalCounts[centroidIndex][j] = nominalDists[j]; } } if (addToCentroidInstances) { m_ClusterCentroids.add(new DenseInstance(1.0, vals)); } return vals; }
From source file:cn.edu.xjtu.dbmine.source.NaiveBayes.java
License:Open Source License
/** * Generates the classifier./*from ww w. j ava 2 s .c o m*/ * * @param instances set of instances serving as training data * @exception Exception if the classifier has not been generated * successfully */ public void buildClassifier(Instances instances) throws Exception { // can classifier handle the data? getCapabilities().testWithFail(instances); // remove instances with missing class instances = new Instances(instances); instances.deleteWithMissingClass(); m_NumClasses = instances.numClasses(); // Copy the instances m_Instances = new Instances(instances); // Discretize instances if required if (m_UseDiscretization) { m_Disc = new weka.filters.supervised.attribute.Discretize(); m_Disc.setInputFormat(m_Instances); m_Instances = weka.filters.Filter.useFilter(m_Instances, m_Disc); } else { m_Disc = null; } // Reserve space for the distributions m_Distributions = new Estimator[m_Instances.numAttributes() - 1][m_Instances.numClasses()]; m_ClassDistribution = new DiscreteEstimator(m_Instances.numClasses(), true); int attIndex = 0; Enumeration enu = m_Instances.enumerateAttributes(); while (enu.hasMoreElements()) { Attribute attribute = (Attribute) enu.nextElement(); // If the attribute is numeric, determine the estimator // numeric precision from differences between adjacent values double numPrecision = DEFAULT_NUM_PRECISION; if (attribute.type() == Attribute.NUMERIC) { m_Instances.sort(attribute); if ((m_Instances.numInstances() > 0) && !m_Instances.instance(0).isMissing(attribute)) { double lastVal = m_Instances.instance(0).value(attribute); double currentVal, deltaSum = 0; int distinct = 0; for (int i = 1; i < m_Instances.numInstances(); i++) { Instance currentInst = m_Instances.instance(i); if (currentInst.isMissing(attribute)) { break; } currentVal = currentInst.value(attribute); if (currentVal != lastVal) { deltaSum += currentVal - lastVal; lastVal = currentVal; distinct++; } } if (distinct > 0) { numPrecision = deltaSum / distinct; } } } for (int j = 0; j < m_Instances.numClasses(); j++) { switch (attribute.type()) { case Attribute.NUMERIC: if (m_UseKernelEstimator) { m_Distributions[attIndex][j] = new KernelEstimator(numPrecision); } else { m_Distributions[attIndex][j] = new NormalEstimator(numPrecision); } break; case Attribute.NOMINAL: m_Distributions[attIndex][j] = new DiscreteEstimator(attribute.numValues(), true); break; default: throw new Exception("Attribute type unknown to NaiveBayes"); } } attIndex++; } // Compute counts Enumeration enumInsts = m_Instances.enumerateInstances(); while (enumInsts.hasMoreElements()) { Instance instance = (Instance) enumInsts.nextElement(); updateClassifier(instance); } // Save space m_Instances = new Instances(m_Instances, 0); }
From source file:cn.edu.xjtu.dbmine.source.NaiveBayes.java
License:Open Source License
/** * Updates the classifier with the given instance. * * @param instance the new training instance to include in the model * @exception Exception if the instance could not be incorporated in * the model.//from w w w .ja v a2 s . c o m */ public void updateClassifier(Instance instance) throws Exception { if (!instance.classIsMissing()) { Enumeration enumAtts = m_Instances.enumerateAttributes(); int attIndex = 0; while (enumAtts.hasMoreElements()) { Attribute attribute = (Attribute) enumAtts.nextElement(); if (!instance.isMissing(attribute)) { m_Distributions[attIndex][(int) instance.classValue()].addValue(instance.value(attribute), instance.weight()); } attIndex++; } m_ClassDistribution.addValue(instance.classValue(), instance.weight()); } }
From source file:cn.edu.xjtu.dbmine.source.NaiveBayes.java
License:Open Source License
/** * Calculates the class membership probabilities for the given test * instance.//from w ww.ja v a2 s . c om * * @param instance the instance to be classified * @return predicted class probability distribution * @exception Exception if there is a problem generating the prediction */ public double[] distributionForInstance(Instance instance) throws Exception { if (m_UseDiscretization) { m_Disc.input(instance); instance = m_Disc.output(); } double[] probs = new double[m_NumClasses]; for (int j = 0; j < m_NumClasses; j++) { probs[j] = m_ClassDistribution.getProbability(j); } Enumeration enumAtts = instance.enumerateAttributes(); int attIndex = 0; while (enumAtts.hasMoreElements()) { Attribute attribute = (Attribute) enumAtts.nextElement(); if (!instance.isMissing(attribute)) { double temp, max = 0; for (int j = 0; j < m_NumClasses; j++) { temp = Math.max(1e-75, Math.pow(m_Distributions[attIndex][j].getProbability(instance.value(attribute)), m_Instances.attribute(attIndex).weight())); probs[j] *= temp; if (probs[j] > max) { max = probs[j]; } if (Double.isNaN(probs[j])) { throw new Exception("NaN returned from estimator for attribute " + attribute.name() + ":\n" + m_Distributions[attIndex][j].toString()); } } if ((max > 0) && (max < 1e-75)) { // Danger of probability underflow for (int j = 0; j < m_NumClasses; j++) { probs[j] *= 1e75; } } } attIndex++; } // Display probabilities Utils.normalize(probs); return probs; }
From source file:cn.edu.xjtu.dbmine.StringToWordVector.java
License:Open Source License
/** * determines the dictionary./*from w w w . ja v a 2s. co m*/ */ private void determineDictionary() { // initialize stopwords Stopwords stopwords = new Stopwords(); if (getUseStoplist()) { try { if (getStopwords().exists() && !getStopwords().isDirectory()) stopwords.read(getStopwords()); } catch (Exception e) { e.printStackTrace(); } } // Operate on a per-class basis if class attribute is set int classInd = getInputFormat().classIndex(); int values = 1; if (!m_doNotOperateOnPerClassBasis && (classInd != -1)) { values = getInputFormat().attribute(classInd).numValues(); // System.out.println("number of class:"+getInputFormat().numClasses()+" "+getInputFormat().attribute(classInd).value(0)); } // TreeMap dictionaryArr [] = new TreeMap[values]; TreeMap[] dictionaryArr = new TreeMap[values]; for (int i = 0; i < values; i++) { dictionaryArr[i] = new TreeMap(); } // Make sure we know which fields to convert determineSelectedRange(); // Tokenize all training text into an orderedMap of "words". long pruneRate = Math.round((m_PeriodicPruningRate / 100.0) * getInputFormat().numInstances()); for (int i = 0; i < getInputFormat().numInstances(); i++) { Instance instance = getInputFormat().instance(i); int vInd = 0; if (!m_doNotOperateOnPerClassBasis && (classInd != -1)) { vInd = (int) instance.classValue(); } // Iterate through all relevant string attributes of the current // instance Hashtable h = new Hashtable(); for (int j = 0; j < instance.numAttributes(); j++) { if (m_SelectedRange.isInRange(j) && (instance.isMissing(j) == false)) { // Get tokenizer m_Tokenizer.tokenize(instance.stringValue(j)); // Iterate through tokens, perform stemming, and remove // stopwords // (if required) while (m_Tokenizer.hasMoreElements()) { String word = ((String) m_Tokenizer.nextElement()).intern(); if (this.m_lowerCaseTokens == true) word = word.toLowerCase(); word = m_Stemmer.stem(word); if (this.m_useStoplist == true) if (stopwords.is(word)) continue; if (!(h.contains(word))) h.put(word, new Integer(0)); Count count = (Count) dictionaryArr[vInd].get(word); if (count == null) { dictionaryArr[vInd].put(word, new Count(1)); } else { count.count++; } } } } // updating the docCount for the words that have occurred in this // instance(document). Enumeration e = h.keys(); while (e.hasMoreElements()) { String word = (String) e.nextElement(); Count c = (Count) dictionaryArr[vInd].get(word); if (c != null) { c.docCount++; // c.doclist.add(vInd); } else System.err.println( "Warning: A word should definitely be in the " + "dictionary.Please check the code"); } if (pruneRate > 0) { if (i % pruneRate == 0 && i > 0) { for (int z = 0; z < values; z++) { Vector d = new Vector(1000); Iterator it = dictionaryArr[z].keySet().iterator(); while (it.hasNext()) { String word = (String) it.next(); Count count = (Count) dictionaryArr[z].get(word); if (count.count <= 1) { d.add(word); } } Iterator iter = d.iterator(); while (iter.hasNext()) { String word = (String) iter.next(); dictionaryArr[z].remove(word); } } } } } // Figure out the minimum required word frequency int totalsize = 0; int prune[] = new int[values]; for (int z = 0; z < values; z++) { totalsize += dictionaryArr[z].size(); int array[] = new int[dictionaryArr[z].size()]; int pos = 0; Iterator it = dictionaryArr[z].keySet().iterator(); while (it.hasNext()) { String word = (String) it.next(); Count count = (Count) dictionaryArr[z].get(word); array[pos] = count.count; pos++; } // sort the array sortArray(array); if (array.length < m_WordsToKeep) { // if there aren't enough words, set the threshold to // minFreq prune[z] = m_minTermFreq; } else { // otherwise set it to be at least minFreq prune[z] = Math.max(m_minTermFreq, array[array.length - m_WordsToKeep]); } } // Convert the dictionary into an attribute index // and create one attribute per word FastVector attributes = new FastVector(totalsize + getInputFormat().numAttributes()); // Add the non-converted attributes int classIndex = -1; for (int i = 0; i < getInputFormat().numAttributes(); i++) { if (!m_SelectedRange.isInRange(i)) { if (getInputFormat().classIndex() == i) { classIndex = attributes.size(); } attributes.addElement(getInputFormat().attribute(i).copy()); } } // Add the word vector attributes (eliminating duplicates // that occur in multiple classes) TreeMap newDictionary = new TreeMap(); int index = attributes.size(); for (int z = 0; z < values; z++) { Iterator it = dictionaryArr[z].keySet().iterator(); while (it.hasNext()) { String word = (String) it.next(); Count count = (Count) dictionaryArr[z].get(word); if (count.count >= prune[z]) { if (newDictionary.get(word) == null) { newDictionary.put(word, new Integer(index++)); attributes.addElement(new Attribute(m_Prefix + word)); } } } } // Compute document frequencies m_DocsCounts = new int[attributes.size()]; Iterator it = newDictionary.keySet().iterator(); while (it.hasNext()) { String word = (String) it.next(); int idx = ((Integer) newDictionary.get(word)).intValue(); int docsCount = 0; for (int j = 0; j < values; j++) { Count c = (Count) dictionaryArr[j].get(word); if (c != null) docsCount += c.docCount; /* * if(!ctd.containsKey(j)){ Map<Integer,Integer> ma = new * HashMap<Integer,Integer>(); ctd.put(j, ma); } */ // if(ctd.get(j)==null) // ctd.get(j).put(idx, c); // int tt = ctd.get(j).get(idx); /* * for(int kk = 0;kk<c.doclist.size();kk++) { * //if(getInputFormat * ().instance(c.doclist.get(kk)).value(idx)>0) * ctd.get(j).put(idx, tt++); } */} m_DocsCounts[idx] = docsCount; } // Trim vector and set instance variables attributes.trimToSize(); m_Dictionary = newDictionary; m_NumInstances = getInputFormat().numInstances(); // Set the filter's output format Instances outputFormat = new Instances(getInputFormat().relationName(), attributes, 0); outputFormat.setClassIndex(classIndex); setOutputFormat(outputFormat); }
From source file:cn.edu.xjtu.dbmine.StringToWordVector.java
License:Open Source License
/** * Converts the instance w/o normalization. * //from www . j av a 2 s.c om * @oaram instance the instance to convert * @param v * @return the conerted instance */ private int convertInstancewoDocNorm(Instance instance, FastVector v) { // Convert the instance into a sorted set of indexes TreeMap contained = new TreeMap(); // Copy all non-converted attributes from input to output int firstCopy = 0; for (int i = 0; i < getInputFormat().numAttributes(); i++) { if (!m_SelectedRange.isInRange(i)) { if (getInputFormat().attribute(i).type() != Attribute.STRING) { // Add simple nominal and numeric attributes directly if (instance.value(i) != 0.0) { contained.put(new Integer(firstCopy), new Double(instance.value(i))); } } else { if (instance.isMissing(i)) { contained.put(new Integer(firstCopy), new Double(Instance.missingValue())); } else { // If this is a string attribute, we have to first add // this value to the range of possible values, then add // its new internal index. if (outputFormatPeek().attribute(firstCopy).numValues() == 0) { // Note that the first string value in a // SparseInstance doesn't get printed. outputFormatPeek().attribute(firstCopy) .addStringValue("Hack to defeat SparseInstance bug"); } int newIndex = outputFormatPeek().attribute(firstCopy) .addStringValue(instance.stringValue(i)); contained.put(new Integer(firstCopy), new Double(newIndex)); } } firstCopy++; } } for (int j = 0; j < instance.numAttributes(); j++) { // if ((getInputFormat().attribute(j).type() == Attribute.STRING) if (m_SelectedRange.isInRange(j) && (instance.isMissing(j) == false)) { m_Tokenizer.tokenize(instance.stringValue(j)); while (m_Tokenizer.hasMoreElements()) { String word = (String) m_Tokenizer.nextElement(); if (this.m_lowerCaseTokens == true) word = word.toLowerCase(); word = m_Stemmer.stem(word); Integer index = (Integer) m_Dictionary.get(word); if (index != null) { if (m_OutputCounts) { // Separate if here rather than // two lines down to avoid // hashtable lookup Double count = (Double) contained.get(index); if (count != null) { contained.put(index, new Double(count.doubleValue() + 1.0)); } else { contained.put(index, new Double(1)); } } else { contained.put(index, new Double(1)); } } } } } // Doing TFTransform if (m_TFTransform == true) { Iterator it = contained.keySet().iterator(); for (int i = 0; it.hasNext(); i++) { Integer index = (Integer) it.next(); if (index.intValue() >= firstCopy) { double val = ((Double) contained.get(index)).doubleValue(); val = Math.log(val + 1); contained.put(index, new Double(val)); Tfcontained.put(index, new Double(val)); ; } } } // Doing IDFTransform if (m_IDFTransform == true) { Iterator it = contained.keySet().iterator(); for (int i = 0; it.hasNext(); i++) { Integer index = (Integer) it.next(); if (index.intValue() >= firstCopy) { double val = ((Double) contained.get(index)).doubleValue(); val = val * Math.log(m_NumInstances / ((double) m_DocsCounts[index.intValue()] + 0.01)); contained.put(index, new Double(val)); } } } // Convert the set to structures needed to create a sparse instance. double[] values = new double[contained.size()]; int[] indices = new int[contained.size()]; Iterator it = contained.keySet().iterator(); for (int i = 0; it.hasNext(); i++) { Integer index = (Integer) it.next(); Double value = (Double) contained.get(index); values[i] = value.doubleValue(); indices[i] = index.intValue(); } Instance inst = new SparseInstance(instance.weight(), values, indices, outputFormatPeek().numAttributes()); inst.setDataset(outputFormatPeek()); v.addElement(inst); return firstCopy; }
From source file:com.entopix.maui.filters.MauiFilter.java
License:Open Source License
/** * Converts an instance./* w w w. j av a2 s . c om*/ */ private FastVector convertInstance(Instance instance, boolean training) { FastVector vector = new FastVector(); String fileName = instance.stringValue(fileNameAtt); if (debugMode) { log.info("-- Converting instance for document " + fileName); } // Get the key phrases for the document HashMap<String, Counter> hashKeyphrases = null; if (!instance.isMissing(keyphrasesAtt)) { String keyphrases = instance.stringValue(keyphrasesAtt); hashKeyphrases = getGivenKeyphrases(keyphrases); } // Get the document text String documentText = instance.stringValue(documentAtt); // Compute the candidate topics HashMap<String, Candidate> candidateList; if (allCandidates != null && allCandidates.containsKey(instance)) { candidateList = allCandidates.get(instance); } else { candidateList = getCandidates(documentText); } if (debugMode) { log.info(candidateList.size() + " candidates "); } // Set indices for key attributes int tfidfAttIndex = documentAtt + 2; int distAttIndex = documentAtt + 3; int probsAttIndex = documentAtt + numFeatures; int countPos = 0; int countNeg = 0; // Go through the phrases and convert them into instances for (Candidate candidate : candidateList.values()) { if (candidate.getFrequency() < minOccurFrequency) { continue; } String name = candidate.getName(); String orig = candidate.getBestFullForm(); if (!vocabularyName.equals("none")) { orig = candidate.getTitle(); } double[] vals = computeFeatureValues(candidate, training, hashKeyphrases, candidateList); Instance inst = new Instance(instance.weight(), vals); inst.setDataset(classifierData); double[] probs = null; try { // Get probability of a phrase being key phrase probs = classifier.distributionForInstance(inst); } catch (Exception e) { log.error("Exception while getting probability for candidate " + candidate.getName()); continue; } double prob = probs[0]; if (nominalClassValue) { prob = probs[1]; } // Compute attribute values for final instance double[] newInst = new double[instance.numAttributes() + numFeatures + 2]; int pos = 0; for (int i = 1; i < instance.numAttributes(); i++) { if (i == documentAtt) { // output of values for a given phrase: // 0 Add phrase int index = outputFormatPeek().attribute(pos).addStringValue(name); newInst[pos++] = index; // 1 Add original version if (orig != null) { index = outputFormatPeek().attribute(pos).addStringValue(orig); } else { index = outputFormatPeek().attribute(pos).addStringValue(name); } // 2 newInst[pos++] = index; // Add features newInst[pos++] = inst.value(tfIndex); // 3 newInst[pos++] = inst.value(idfIndex); // 4 newInst[pos++] = inst.value(tfidfIndex); // 5 newInst[pos++] = inst.value(firstOccurIndex); // 6 newInst[pos++] = inst.value(lastOccurIndex); // 7 newInst[pos++] = inst.value(spreadOccurIndex); // 8 newInst[pos++] = inst.value(domainKeyphIndex); // 9 newInst[pos++] = inst.value(lengthIndex); // 10 newInst[pos++] = inst.value(generalityIndex); // 11 newInst[pos++] = inst.value(nodeDegreeIndex); // 12 newInst[pos++] = inst.value(invWikipFreqIndex); // 13 newInst[pos++] = inst.value(totalWikipKeyphrIndex); // 14 newInst[pos++] = inst.value(wikipGeneralityIndex); // 15 // Add probability probsAttIndex = pos; newInst[pos++] = prob; // 16 // Set rank to missing (computed below) newInst[pos++] = Instance.missingValue(); // 17 } else if (i == keyphrasesAtt) { newInst[pos++] = inst.classValue(); } else { newInst[pos++] = instance.value(i); } } Instance ins = new Instance(instance.weight(), newInst); ins.setDataset(outputFormatPeek()); vector.addElement(ins); if (inst.classValue() == 0) { countNeg++; } else { countPos++; } } if (debugMode) { log.info(countPos + " positive; " + countNeg + " negative instances"); } // Sort phrases according to their distance (stable sort) double[] vals = new double[vector.size()]; for (int i = 0; i < vals.length; i++) { vals[i] = ((Instance) vector.elementAt(i)).value(distAttIndex); } FastVector newVector = new FastVector(vector.size()); int[] sortedIndices = Utils.stableSort(vals); for (int i = 0; i < vals.length; i++) { newVector.addElement(vector.elementAt(sortedIndices[i])); } vector = newVector; // Sort phrases according to their tfxidf value (stable sort) for (int i = 0; i < vals.length; i++) { vals[i] = -((Instance) vector.elementAt(i)).value(tfidfAttIndex); } newVector = new FastVector(vector.size()); sortedIndices = Utils.stableSort(vals); for (int i = 0; i < vals.length; i++) { newVector.addElement(vector.elementAt(sortedIndices[i])); } vector = newVector; // Sort phrases according to their probability (stable sort) for (int i = 0; i < vals.length; i++) { vals[i] = 1 - ((Instance) vector.elementAt(i)).value(probsAttIndex); } newVector = new FastVector(vector.size()); sortedIndices = Utils.stableSort(vals); for (int i = 0; i < vals.length; i++) { newVector.addElement(vector.elementAt(sortedIndices[i])); } vector = newVector; // Compute rank of phrases. Check for subphrases that are ranked // lower than superphrases and assign probability -1 and set the // rank to Integer.MAX_VALUE int rank = 1; for (int i = 0; i < vals.length; i++) { Instance currentInstance = (Instance) vector.elementAt(i); // log.info(vals[i] + "\t" + currentInstance); // Short cut: if phrase very unlikely make rank very low and // continue if (Utils.grOrEq(vals[i], 1.0)) { currentInstance.setValue(probsAttIndex + 1, Integer.MAX_VALUE); continue; } // Otherwise look for super phrase starting with first phrase // in list that has same probability, TFxIDF value, and distance as // current phrase. We do this to catch all superphrases // that have same probability, TFxIDF value and distance as current // phrase. int startInd = i; while (startInd < vals.length) { Instance inst = (Instance) vector.elementAt(startInd); if ((inst.value(tfidfAttIndex) != currentInstance.value(tfidfAttIndex)) || (inst.value(probsAttIndex) != currentInstance.value(probsAttIndex)) || (inst.value(distAttIndex) != currentInstance.value(distAttIndex))) { break; } startInd++; } currentInstance.setValue(probsAttIndex + 1, rank++); } return vector; }
From source file:com.esda.util.StringToWordVector.java
License:Open Source License
/** * determines the dictionary.// ww w. j av a2 s .c o m */ private void determineDictionary() { // initialize stopwords Stopwords stopwords = new Stopwords(); if (getUseStoplist()) { try { if (getStopwords().exists() && !getStopwords().isDirectory()) stopwords.read(getStopwords()); } catch (Exception e) { e.printStackTrace(); } } // Operate on a per-class basis if class attribute is set int classInd = getInputFormat().classIndex(); int values = 1; if (!m_doNotOperateOnPerClassBasis && (classInd != -1)) { values = getInputFormat().attribute(classInd).numValues(); } // TreeMap dictionaryArr [] = new TreeMap[values]; TreeMap[] dictionaryArr = new TreeMap[values]; for (int i = 0; i < values; i++) { dictionaryArr[i] = new TreeMap(); } // Make sure we know which fields to convert determineSelectedRange(); // Tokenize all training text into an orderedMap of "words". long pruneRate = Math.round((m_PeriodicPruningRate / 100.0) * getInputFormat().numInstances()); for (int i = 0; i < getInputFormat().numInstances(); i++) { Instance instance = getInputFormat().instance(i); int vInd = 0; if (!m_doNotOperateOnPerClassBasis && (classInd != -1)) { vInd = (int) instance.classValue(); } // Iterate through all relevant string attributes of the current // instance Hashtable h = new Hashtable(); for (int j = 0; j < instance.numAttributes(); j++) { if (m_SelectedRange.isInRange(j) && (instance.isMissing(j) == false)) { // Get tokenizer m_Tokenizer.tokenize(instance.stringValue(j)); // Iterate through tokens, perform stemming, and remove // stopwords // (if required) while (m_Tokenizer.hasMoreElements()) { String word = ((String) m_Tokenizer.nextElement()).intern(); if (this.m_lowerCaseTokens == true) word = word.toLowerCase(); String[] wordsArr = word.split(" "); StringBuilder stemmedStr = new StringBuilder(); for (String wordStr : wordsArr) { if (!this.m_useStoplist || !stopwords.is(wordStr)) { stemmedStr.append(m_Stemmer.stem(wordStr)); stemmedStr.append(" "); } } /*for (int icounter = 0; icounter < wordsArr.length; icounter++) { stemmedStr += m_Stemmer.stem(wordsArr[icounter]); if (icounter + 1 < wordsArr.length) stemmedStr += " "; }*/ word = stemmedStr.toString().trim(); if (!(h.containsKey(word))) h.put(word, new Integer(0)); Count count = (Count) dictionaryArr[vInd].get(word); if (count == null) { dictionaryArr[vInd].put(word, new Count(1)); } else { count.count++; } } } } // updating the docCount for the words that have occurred in this // instance(document). Enumeration e = h.keys(); while (e.hasMoreElements()) { String word = (String) e.nextElement(); Count c = (Count) dictionaryArr[vInd].get(word); if (c != null) { c.docCount++; } else System.err.println( "Warning: A word should definitely be in the " + "dictionary.Please check the code"); } if (pruneRate > 0) { if (i % pruneRate == 0 && i > 0) { for (int z = 0; z < values; z++) { Vector d = new Vector(1000); Iterator it = dictionaryArr[z].keySet().iterator(); while (it.hasNext()) { String word = (String) it.next(); Count count = (Count) dictionaryArr[z].get(word); if (count.count <= 1) { d.add(word); } } Iterator iter = d.iterator(); while (iter.hasNext()) { String word = (String) iter.next(); dictionaryArr[z].remove(word); } } } } } // Figure out the minimum required word frequency int totalsize = 0; int prune[] = new int[values]; for (int z = 0; z < values; z++) { totalsize += dictionaryArr[z].size(); int array[] = new int[dictionaryArr[z].size()]; int pos = 0; Iterator it = dictionaryArr[z].keySet().iterator(); while (it.hasNext()) { String word = (String) it.next(); Count count = (Count) dictionaryArr[z].get(word); array[pos] = count.count; pos++; } // sort the array sortArray(array); if (array.length < m_WordsToKeep) { // if there aren't enough words, set the threshold to // minFreq prune[z] = m_minTermFreq; } else { // otherwise set it to be at least minFreq prune[z] = Math.max(m_minTermFreq, array[array.length - m_WordsToKeep]); } } // Convert the dictionary into an attribute index // and create one attribute per word FastVector attributes = new FastVector(totalsize + getInputFormat().numAttributes()); // Add the non-converted attributes int classIndex = -1; for (int i = 0; i < getInputFormat().numAttributes(); i++) { if (!m_SelectedRange.isInRange(i)) { if (getInputFormat().classIndex() == i) { classIndex = attributes.size(); } attributes.addElement(getInputFormat().attribute(i).copy()); } } // Add the word vector attributes (eliminating duplicates // that occur in multiple classes) TreeMap newDictionary = new TreeMap(); int index = attributes.size(); for (int z = 0; z < values; z++) { Iterator it = dictionaryArr[z].keySet().iterator(); while (it.hasNext()) { String word = (String) it.next(); Count count = (Count) dictionaryArr[z].get(word); if (count.count >= prune[z]) { if (newDictionary.get(word) == null) { newDictionary.put(word, new Integer(index++)); attributes.addElement(new Attribute(m_Prefix + word)); } } } } // Compute document frequencies m_DocsCounts = new int[attributes.size()]; Iterator it = newDictionary.keySet().iterator(); while (it.hasNext()) { String word = (String) it.next(); int idx = ((Integer) newDictionary.get(word)).intValue(); int docsCount = 0; for (int j = 0; j < values; j++) { Count c = (Count) dictionaryArr[j].get(word); if (c != null) docsCount += c.docCount; } m_DocsCounts[idx] = docsCount; } // Trim vector and set instance variables attributes.trimToSize(); m_Dictionary = newDictionary; m_NumInstances = getInputFormat().numInstances(); // Set the filter's output format Instances outputFormat = new Instances(getInputFormat().relationName(), attributes, 0); outputFormat.setClassIndex(classIndex); setOutputFormat(outputFormat); }