Package com.datasalt.pangool.examples.naivebayes.NaiveBayesGenerate

Examples of com.datasalt.pangool.examples.naivebayes.NaiveBayesGenerate.Category

58
59
60
61
62
63
64
65
66
67
68
      TupleFile.Reader reader = new TupleFile.Reader(fileSystem, conf, fileStatus.getPath());
      Tuple tuple = new Tuple(reader.getSchema());
      while(reader.next(tuple)) {
        // Read Tuple
        Integer count = (Integer) tuple.get("count");
        Category category = (Category) tuple.get("category");
        String word = tuple.get("word").toString();
        vocabulary.add(word);
        tokensPerCategory.put(category, MapUtils.getInteger(tokensPerCategory, category, 0) + count);
        wordCountPerCategory.get(category).put(word, count);
      }
View Full Code Here
77
78
79
80
81
82
83
84
85
86
87
   */
  public Category classify(String text) {
    StringTokenizer itr = new StringTokenizer(text);
    Map<Category, Double> scorePerCategory = new HashMap<Category, Double>();
    double bestScore = Double.NEGATIVE_INFINITY;
    Category bestCategory = null;
    while(itr.hasMoreTokens()) {
      String token = NaiveBayesGenerate.normalizeWord(itr.nextToken());
      for(Category category : Category.values()) {
        int count = MapUtils.getInteger(wordCountPerCategory.get(category), token, 0) + 1;
        double wordScore  = Math.log(count / (double) (tokensPerCategory.get(category) + V));
View Full Code Here
57
58
59
60
61
62
63
64
65
66
67
      TupleFile.Reader reader = new TupleFile.Reader(fileSystem, conf, fileStatus.getPath());
      Tuple tuple = new Tuple(reader.getSchema());
      while(reader.next(tuple)) {
        // Read Tuple
        Integer count = (Integer) tuple.get("count");
        Category category = (Category) tuple.get("category");
        String word = tuple.get("word").toString();
        vocabulary.add(word);
        tokensPerCategory.put(category, MapUtils.getInteger(tokensPerCategory, category, 0) + count);
        wordCountPerCategory.get(category).put(word, count);
      }
View Full Code Here
76
77
78
79
80
81
82
83
84
85
86
   */
  public Category classify(String text) {
    StringTokenizer itr = new StringTokenizer(text);
    Map<Category, Double> scorePerCategory = new HashMap<Category, Double>();
    double bestScore = Double.NEGATIVE_INFINITY;
    Category bestCategory = null;
    while(itr.hasMoreTokens()) {
      String token = NaiveBayesGenerate.normalizeWord(itr.nextToken());
      for(Category category : Category.values()) {
        int count = MapUtils.getInteger(wordCountPerCategory.get(category), token, 0) + 1;
        double wordScore  = Math.log(count / (double) (tokensPerCategory.get(category) + V));
View Full Code Here
58
59
60
61
62
63
64
65
66
67
68
      reader.initialize(fileStatus.getPath(), conf);
      while(reader.nextKeyValueNoSync()) {
        // Read Tuple
        ITuple tuple = reader.getCurrentKey();
        Integer count = (Integer) tuple.get("count");
        Category category = (Category) tuple.get("category");
        String word = tuple.get("word").toString();
        vocabulary.add(word);
        tokensPerCategory.put(category, MapUtils.getInteger(tokensPerCategory, category, 0) + count);
        wordCountPerCategory.get(category).put(word, count);
      }
View Full Code Here
77
78
79
80
81
82
83
84
85
86
87
   */
  public Category classify(String text) {
    StringTokenizer itr = new StringTokenizer(text);
    Map<Category, Double> scorePerCategory = new HashMap<Category, Double>();
    double bestScore = Double.NEGATIVE_INFINITY;
    Category bestCategory = null;
    while(itr.hasMoreTokens()) {
      String token = NaiveBayesGenerate.normalizeWord(itr.nextToken());
      for(Category category : Category.values()) {
        int count = MapUtils.getInteger(wordCountPerCategory.get(category), token, 0) + 1;
        double wordScore  = Math.log(count / (double) (tokensPerCategory.get(category) + V));
View Full Code Here
58
59
60
61
62
63
64
65
66
67
68
      TupleFile.Reader reader = new TupleFile.Reader(fileSystem, conf, fileStatus.getPath());
      Tuple tuple = new Tuple(reader.getSchema());
      while(reader.next(tuple)) {
        // Read Tuple
        Integer count = (Integer) tuple.get("count");
        Category category = (Category) tuple.get("category");
        String word = tuple.get("word").toString();
        vocabulary.add(word);
        tokensPerCategory.put(category, MapUtils.getInteger(tokensPerCategory, category, 0) + count);
        wordCountPerCategory.get(category).put(word, count);
      }
View Full Code Here
78
79
80
81
82
83
84
85
86
87
88
   */
  public Category classify(String text) {
    StringTokenizer itr = new StringTokenizer(text);
    Map<Category, Double> scorePerCategory = new HashMap<Category, Double>();
    double bestScore = Double.NEGATIVE_INFINITY;
    Category bestCategory = null;
    while(itr.hasMoreTokens()) {
      String token = NaiveBayesGenerate.normalizeWord(itr.nextToken());
      for(Category category : Category.values()) {
        int count = MapUtils.getInteger(wordCountPerCategory.get(category), token, 0) + 1;
        double wordScore  = Math.log(count / (double) (tokensPerCategory.get(category) + V));
View Full Code Here
58
59
60
61
62
63
64
65
66
67
68
      reader.initialize(fileStatus.getPath(), conf);
      while(reader.nextKeyValueNoSync()) {
        // Read Tuple
        ITuple tuple = reader.getCurrentKey();
        Integer count = (Integer) tuple.get("count");
        Category category = (Category) tuple.get("category");
        String word = tuple.get("word").toString();
        vocabulary.add(word);
        tokensPerCategory.put(category, MapUtils.getInteger(tokensPerCategory, category, 0) + count);
        wordCountPerCategory.get(category).put(word, count);
      }
View Full Code Here
77
78
79
80
81
82
83
84
85
86
87
   */
  public Category classify(String text) {
    StringTokenizer itr = new StringTokenizer(text);
    Map<Category, Double> scorePerCategory = new HashMap<Category, Double>();
    double bestScore = Double.NEGATIVE_INFINITY;
    Category bestCategory = null;
    while(itr.hasMoreTokens()) {
      String token = NaiveBayesGenerate.normalizeWord(itr.nextToken());
      for(Category category : Category.values()) {
        int count = MapUtils.getInteger(wordCountPerCategory.get(category), token, 0) + 1;
        double wordScore  = Math.log(count / (double) (tokensPerCategory.get(category) + V));
View Full Code Here
TOP

Related Classes of com.datasalt.pangool.examples.naivebayes.NaiveBayesGenerate.Category

  • com.datasalt.pangool.examples.naivebayes.NaiveBayesClassifier
    • 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.