List of usage examples for org.apache.mahout.vectorizer.encoders FeatureVectorEncoder setTraceDictionary
public void setTraceDictionary(Map<String, Set<Integer>> traceDictionary)
From source file:chapter4.src.logistic.CsvRecordFactoryPredict.java
License:Apache License
/** * Processes the first line of a file (which should contain the variable names). The target and * predictor column numbers are set from the names on this line. * * @param line Header line for the file. *///from w ww.j av a 2 s . c om public void firstLine(String line) { // read variable names, build map of name -> column final Map<String, Integer> vars = Maps.newHashMap(); variableNames = parseCsvLine(line); int column = 0; for (String var : variableNames) { vars.put(var, column++); } // record target column and establish dictionary for decoding target target = vars.get(targetName); // record id column if (idName != null) { id = vars.get(idName); } // create list of predictor column numbers predictors = Lists.newArrayList(Collections2.transform(typeMap.keySet(), new Function<String, Integer>() { public Integer apply(String from) { Integer r = vars.get(from); Preconditions.checkArgument(r != null, "Can't find variable %s, only know about %s", from, vars); return r; } })); if (includeBiasTerm) { predictors.add(-1); } Collections.sort(predictors); // and map from column number to type encoder for each column that is a predictor predictorEncoders = Maps.newHashMap(); for (Integer predictor : predictors) { String name; Class<? extends FeatureVectorEncoder> c; if (predictor == -1) { name = INTERCEPT_TERM; c = ConstantValueEncoder.class; } else { name = variableNames.get(predictor); c = TYPE_DICTIONARY.get(typeMap.get(name)); } try { Preconditions.checkArgument(c != null, "Invalid type of variable %s, wanted one of %s", typeMap.get(name), TYPE_DICTIONARY.keySet()); Constructor<? extends FeatureVectorEncoder> constructor = c.getConstructor(String.class); Preconditions.checkArgument(constructor != null, "Can't find correct constructor for %s", typeMap.get(name)); FeatureVectorEncoder encoder = constructor.newInstance(name); predictorEncoders.put(predictor, encoder); encoder.setTraceDictionary(traceDictionary); } catch (InstantiationException e) { throw new IllegalStateException(CANNOT_CONSTRUCT_CONVERTER, e); } catch (IllegalAccessException e) { throw new IllegalStateException(CANNOT_CONSTRUCT_CONVERTER, e); } catch (InvocationTargetException e) { throw new IllegalStateException(CANNOT_CONSTRUCT_CONVERTER, e); } catch (NoSuchMethodException e) { throw new IllegalStateException(CANNOT_CONSTRUCT_CONVERTER, e); } } }
From source file:chapter4.src.logistic.CsvRecordFactoryPredict.java
License:Apache License
public void firstLine(String line, String targetName) { // read variable names, build map of name -> column final Map<String, Integer> vars = Maps.newHashMap(); variableNames = parseCsvLine(line);/* ww w.ja v a 2s. c o m*/ int column = 0; for (String var : variableNames) { vars.put(var, column++); } // record target column and establish dictionary for decoding target target = vars.size() + 1; // record id column if (idName != null) { id = vars.get(idName); } // create list of predictor column numbers predictors = Lists.newArrayList(Collections2.transform(typeMap.keySet(), new Function<String, Integer>() { public Integer apply(String from) { Integer r = vars.get(from); Preconditions.checkArgument(r != null, "Can't find variable %s, only know about %s", from, vars); return r; } })); if (includeBiasTerm) { predictors.add(-1); } Collections.sort(predictors); // and map from column number to type encoder for each column that is a predictor predictorEncoders = Maps.newHashMap(); for (Integer predictor : predictors) { String name; Class<? extends FeatureVectorEncoder> c; if (predictor == -1) { name = INTERCEPT_TERM; c = ConstantValueEncoder.class; } else { name = variableNames.get(predictor); c = TYPE_DICTIONARY.get(typeMap.get(name)); } try { Preconditions.checkArgument(c != null, "Invalid type of variable %s, wanted one of %s", typeMap.get(name), TYPE_DICTIONARY.keySet()); Constructor<? extends FeatureVectorEncoder> constructor = c.getConstructor(String.class); Preconditions.checkArgument(constructor != null, "Can't find correct constructor for %s", typeMap.get(name)); FeatureVectorEncoder encoder = constructor.newInstance(name); predictorEncoders.put(predictor, encoder); encoder.setTraceDictionary(traceDictionary); } catch (InstantiationException e) { throw new IllegalStateException(CANNOT_CONSTRUCT_CONVERTER, e); } catch (IllegalAccessException e) { throw new IllegalStateException(CANNOT_CONSTRUCT_CONVERTER, e); } catch (InvocationTargetException e) { throw new IllegalStateException(CANNOT_CONSTRUCT_CONVERTER, e); } catch (NoSuchMethodException e) { throw new IllegalStateException(CANNOT_CONSTRUCT_CONVERTER, e); } } }
From source file:com.cloudera.knittingboar.records.CSVBasedDatasetRecordFactory.java
License:Apache License
/** * Processes the first line of a file (which should contain the variable * names). The target and predictor column numbers are set from the names on * this line./* www. ja v a 2 s . c o m*/ * * @param line * Header line for the file. */ public void firstLine(String line) { // System.out.println("> firstline: " + line); // read variable names, build map of name -> column final Map<String, Integer> vars = Maps.newHashMap(); variableNames = Lists.newArrayList(COMMA.split(line)); int column = 0; for (String var : variableNames) { vars.put(var, column++); } // record target column and establish dictionary for decoding target target = vars.get(targetName); // record id column if (idName != null) { id = vars.get(idName); } // create list of predictor column numbers predictors = Lists.newArrayList(Collections2.transform(typeMap.keySet(), new Function<String, Integer>() { @Override public Integer apply(String from) { Integer r = vars.get(from); Preconditions.checkArgument(r != null, "Can't find variable %s, only know about %s", from, vars); return r; } })); if (includeBiasTerm) { predictors.add(-1); } Collections.sort(predictors); // and map from column number to type encoder for each column that is a // predictor predictorEncoders = Maps.newHashMap(); for (Integer predictor : predictors) { String name; Class<? extends FeatureVectorEncoder> c; if (predictor == -1) { name = INTERCEPT_TERM; c = ConstantValueEncoder.class; } else { name = variableNames.get(predictor); c = TYPE_DICTIONARY.get(typeMap.get(name)); } try { Preconditions.checkArgument(c != null, "Invalid type of variable %s, wanted one of %s", typeMap.get(name), TYPE_DICTIONARY.keySet()); Constructor<? extends FeatureVectorEncoder> constructor = c.getConstructor(String.class); Preconditions.checkArgument(constructor != null, "Can't find correct constructor for %s", typeMap.get(name)); FeatureVectorEncoder encoder = constructor.newInstance(name); predictorEncoders.put(predictor, encoder); encoder.setTraceDictionary(traceDictionary); } catch (InstantiationException e) { throw new IllegalStateException(CANNOT_CONSTRUCT_CONVERTER, e); } catch (IllegalAccessException e) { throw new IllegalStateException(CANNOT_CONSTRUCT_CONVERTER, e); } catch (InvocationTargetException e) { throw new IllegalStateException(CANNOT_CONSTRUCT_CONVERTER, e); } catch (NoSuchMethodException e) { throw new IllegalStateException(CANNOT_CONSTRUCT_CONVERTER, e); } } }
From source file:com.cloudera.knittingboar.records.Test20NewsgroupsBookParsing.java
License:Apache License
public void test20NewsgroupsFileScan() throws IOException { // p.270 ----- metrics to track lucene's parsing mechanics, progress, performance of OLR ------------ double averageLL = 0.0; double averageCorrect = 0.0; double averageLineCount = 0.0; int k = 0;// w w w .ja va 2 s . co m double step = 0.0; int[] bumps = new int[] { 1, 2, 5 }; double lineCount = 0; Splitter onColon = Splitter.on(":").trimResults(); // last line on p.269 Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_31); File base = new File("/Users/jpatterson/Downloads/datasets/20news-bydate/20-debug/"); overallCounts = HashMultiset.create(); // p.269 --------------------------------------------------------- Map<String, Set<Integer>> traceDictionary = new TreeMap<String, Set<Integer>>(); // encodes the text content in both the subject and the body of the email FeatureVectorEncoder encoder = new StaticWordValueEncoder("body"); encoder.setProbes(2); encoder.setTraceDictionary(traceDictionary); // provides a constant offset that the model can use to encode the average frequency // of each class FeatureVectorEncoder bias = new ConstantValueEncoder("Intercept"); bias.setTraceDictionary(traceDictionary); // used to encode the number of lines in a message FeatureVectorEncoder lines = new ConstantValueEncoder("Lines"); lines.setTraceDictionary(traceDictionary); Dictionary newsGroups = new Dictionary(); // bottom of p.269 ------------------------------ // because OLR expects to get integer class IDs for the target variable during training // we need a dictionary to convert the target variable (the newsgroup name) // to an integer, which is the newsGroup object List<File> files = new ArrayList<File>(); for (File newsgroup : base.listFiles()) { newsGroups.intern(newsgroup.getName()); System.out.println(">> " + newsgroup.getName()); files.addAll(Arrays.asList(newsgroup.listFiles())); } // mix up the files, helps training in OLR Collections.shuffle(files); System.out.printf("%d training files\n", files.size()); // ----- p.270 ------------ "reading and tokenzing the data" --------- for (File file : files) { BufferedReader reader = new BufferedReader(new FileReader(file)); // identify newsgroup ---------------- // convert newsgroup name to unique id // ----------------------------------- String ng = file.getParentFile().getName(); int actual = newsGroups.intern(ng); Multiset<String> words = ConcurrentHashMultiset.create(); // check for line count header ------- String line = reader.readLine(); while (line != null && line.length() > 0) { // if this is a line that has a line count, let's pull that value out ------ if (line.startsWith("Lines:")) { String count = Iterables.get(onColon.split(line), 1); try { lineCount = Integer.parseInt(count); averageLineCount += (lineCount - averageLineCount) / Math.min(k + 1, 1000); } catch (NumberFormatException e) { // if anything goes wrong in parse: just use the avg count lineCount = averageLineCount; } } // which header words to actually count boolean countHeader = (line.startsWith("From:") || line.startsWith("Subject:") || line.startsWith("Keywords:") || line.startsWith("Summary:")); // we're still looking at the header at this point // loop through the lines in the file, while the line starts with: " " do { // get a reader for this specific string ------ StringReader in = new StringReader(line); // ---- count words in header --------- if (countHeader) { //System.out.println( "#### countHeader ################*************" ); countWords(analyzer, words, in); } // iterate to the next string ---- line = reader.readLine(); } while (line.startsWith(" ")); //System.out.println("[break]"); } // now we're done with the header //System.out.println("[break-header]"); // -------- count words in body ---------- countWords(analyzer, words, reader); reader.close(); /* for (String word : words.elementSet()) { //encoder.addToVector(word, Math.log(1 + words.count(word)), v); System.out.println( "> " + word + ", " + words.count(word) ); } */ } }
From source file:com.cloudera.knittingboar.records.TwentyNewsgroupsRecordFactory.java
License:Apache License
/** * Processes single line of input into: - target variable - Feature vector * //from w ww . j a va 2 s. c om * @throws Exception */ public int processLine(String line, Vector v) throws Exception { String[] parts = line.split(this.class_id_split_string); if (parts.length < 2) { throw new Exception("wtf: line not formed well."); } String newsgroup_name = parts[0]; String msg = parts[1]; // p.269 --------------------------------------------------------- Map<String, Set<Integer>> traceDictionary = new TreeMap<String, Set<Integer>>(); // encodes the text content in both the subject and the body of the email FeatureVectorEncoder encoder = new StaticWordValueEncoder("body"); encoder.setProbes(2); encoder.setTraceDictionary(traceDictionary); // provides a constant offset that the model can use to encode the average // frequency // of each class FeatureVectorEncoder bias = new ConstantValueEncoder("Intercept"); bias.setTraceDictionary(traceDictionary); int actual = newsGroups.intern(newsgroup_name); // newsGroups.values().contains(arg0) // System.out.println( "> newsgroup name: " + newsgroup_name ); // System.out.println( "> newsgroup id: " + actual ); Multiset<String> words = ConcurrentHashMultiset.create(); /* * // System.out.println("record: "); for ( int x = 1; x < parts.length; x++ * ) { //String s = ts.getAttribute(CharTermAttribute.class).toString(); // * System.out.print( " " + parts[x] ); String foo = parts[x].trim(); * System.out.print( " " + foo ); words.add( foo ); * * } // System.out.println("\nEOR"); System.out.println( "\nwords found: " + * (parts.length - 1) ); System.out.println( "words in set: " + words.size() * + ", " + words.toString() ); */ StringReader in = new StringReader(msg); countWords(analyzer, words, in); // ----- p.271 ----------- // Vector v = new RandomAccessSparseVector(FEATURES); // original value does nothing in a ContantValueEncoder bias.addToVector("", 1, v); // original value does nothing in a ContantValueEncoder // lines.addToVector("", lineCount / 30, v); // original value does nothing in a ContantValueEncoder // logLines.addToVector("", Math.log(lineCount + 1), v); // now scan through all the words and add them // System.out.println( "############### " + words.toArray().length); for (String word : words.elementSet()) { encoder.addToVector(word, Math.log(1 + words.count(word)), v); // System.out.print( words.count(word) + " " ); } // System.out.println("\nEOL\n"); return actual; }
From source file:com.cloudera.knittingboar.sgd.olr.TestBaseOLR_Train20Newsgroups.java
License:Apache License
public void testTrainNewsGroups() throws IOException { File base = new File("/Users/jpatterson/Downloads/datasets/20news-bydate/20news-bydate-train/"); overallCounts = HashMultiset.create(); long startTime = System.currentTimeMillis(); // p.269 --------------------------------------------------------- Map<String, Set<Integer>> traceDictionary = new TreeMap<String, Set<Integer>>(); // encodes the text content in both the subject and the body of the email FeatureVectorEncoder encoder = new StaticWordValueEncoder("body"); encoder.setProbes(2);/*from w w w .j a v a2s.com*/ encoder.setTraceDictionary(traceDictionary); // provides a constant offset that the model can use to encode the average frequency // of each class FeatureVectorEncoder bias = new ConstantValueEncoder("Intercept"); bias.setTraceDictionary(traceDictionary); // used to encode the number of lines in a message FeatureVectorEncoder lines = new ConstantValueEncoder("Lines"); lines.setTraceDictionary(traceDictionary); FeatureVectorEncoder logLines = new ConstantValueEncoder("LogLines"); logLines.setTraceDictionary(traceDictionary); Dictionary newsGroups = new Dictionary(); // matches the OLR setup on p.269 --------------- // stepOffset, decay, and alpha --- describe how the learning rate decreases // lambda: amount of regularization // learningRate: amount of initial learning rate OnlineLogisticRegression learningAlgorithm = new OnlineLogisticRegression(20, FEATURES, new L1()).alpha(1) .stepOffset(1000).decayExponent(0.9).lambda(3.0e-5).learningRate(20); // bottom of p.269 ------------------------------ // because OLR expects to get integer class IDs for the target variable during training // we need a dictionary to convert the target variable (the newsgroup name) // to an integer, which is the newsGroup object List<File> files = new ArrayList<File>(); for (File newsgroup : base.listFiles()) { newsGroups.intern(newsgroup.getName()); files.addAll(Arrays.asList(newsgroup.listFiles())); } // mix up the files, helps training in OLR Collections.shuffle(files); System.out.printf("%d training files\n", files.size()); // p.270 ----- metrics to track lucene's parsing mechanics, progress, performance of OLR ------------ double averageLL = 0.0; double averageCorrect = 0.0; double averageLineCount = 0.0; int k = 0; double step = 0.0; int[] bumps = new int[] { 1, 2, 5 }; double lineCount = 0; // last line on p.269 Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_31); Splitter onColon = Splitter.on(":").trimResults(); int input_file_count = 0; // ----- p.270 ------------ "reading and tokenzing the data" --------- for (File file : files) { BufferedReader reader = new BufferedReader(new FileReader(file)); input_file_count++; // identify newsgroup ---------------- // convert newsgroup name to unique id // ----------------------------------- String ng = file.getParentFile().getName(); int actual = newsGroups.intern(ng); Multiset<String> words = ConcurrentHashMultiset.create(); // check for line count header ------- String line = reader.readLine(); while (line != null && line.length() > 0) { // if this is a line that has a line count, let's pull that value out ------ if (line.startsWith("Lines:")) { String count = Iterables.get(onColon.split(line), 1); try { lineCount = Integer.parseInt(count); averageLineCount += (lineCount - averageLineCount) / Math.min(k + 1, 1000); } catch (NumberFormatException e) { // if anything goes wrong in parse: just use the avg count lineCount = averageLineCount; } } boolean countHeader = (line.startsWith("From:") || line.startsWith("Subject:") || line.startsWith("Keywords:") || line.startsWith("Summary:")); // loop through the lines in the file, while the line starts with: " " do { // get a reader for this specific string ------ StringReader in = new StringReader(line); // ---- count words in header --------- if (countHeader) { countWords(analyzer, words, in); } // iterate to the next string ---- line = reader.readLine(); } while (line.startsWith(" ")); } // while (lines in header) { // -------- count words in body ---------- countWords(analyzer, words, reader); reader.close(); // ----- p.271 ----------- Vector v = new RandomAccessSparseVector(FEATURES); // original value does nothing in a ContantValueEncoder bias.addToVector("", 1, v); // original value does nothing in a ContantValueEncoder lines.addToVector("", lineCount / 30, v); // original value does nothing in a ContantValueEncoder logLines.addToVector("", Math.log(lineCount + 1), v); // now scan through all the words and add them for (String word : words.elementSet()) { encoder.addToVector(word, Math.log(1 + words.count(word)), v); } //Utils.PrintVectorNonZero(v); // calc stats --------- double mu = Math.min(k + 1, 200); double ll = learningAlgorithm.logLikelihood(actual, v); averageLL = averageLL + (ll - averageLL) / mu; Vector p = new DenseVector(20); learningAlgorithm.classifyFull(p, v); int estimated = p.maxValueIndex(); int correct = (estimated == actual ? 1 : 0); averageCorrect = averageCorrect + (correct - averageCorrect) / mu; learningAlgorithm.train(actual, v); k++; int bump = bumps[(int) Math.floor(step) % bumps.length]; int scale = (int) Math.pow(10, Math.floor(step / bumps.length)); if (k % (bump * scale) == 0) { step += 0.25; System.out.printf("%10d %10.3f %10.3f %10.2f %s %s\n", k, ll, averageLL, averageCorrect * 100, ng, newsGroups.values().get(estimated)); } learningAlgorithm.close(); /* if (k>4) { break; } */ } Utils.PrintVectorSection(learningAlgorithm.getBeta().viewRow(0), 3); long endTime = System.currentTimeMillis(); //System.out.println("That took " + (endTime - startTime) + " milliseconds"); long duration = (endTime - startTime); System.out.println("Processed Input Files: " + input_file_count + ", time: " + duration + "ms"); ModelSerializer.writeBinary("/tmp/olr-news-group.model", learningAlgorithm); // learningAlgorithm.getBest().getPayload().getLearner().getModels().get(0)); }