Python POSContextSequenceFeatureExtractor Examples

Example #1

    def __init__(self,
                 context_window_size=4,
                 prime_feature_length=4,
                 add_prime_feature=False,
                 ngram_value=2):
        # get hold of suitable feature extractor
        # k_param: pass 4 tokens as context window length:

        self.feature_extractor = POSContextSequenceFeatureExtractor(
            k_param=context_window_size,
            prime_feature_length=prime_feature_length,
            add_prime_feature=add_prime_feature)

        self.lexicalized_fe = LexicalizedNgramsFeatureExtractor(ngram_value)

Example #2

File: lexicalized_feature_extraction_flow_mapper.py Project: kperisetla/glossextractionengine

    def __init__(self, context_window_size=4, prime_feature_length=4, add_prime_feature = False, ngram_value=2):
        # get hold of suitable feature extractor
        # k_param: pass 4 tokens as context window length:

        self.feature_extractor = POSContextSequenceFeatureExtractor(k_param=context_window_size,prime_feature_length=prime_feature_length, add_prime_feature=add_prime_feature)

        self.lexicalized_fe = LexicalizedNgramsFeatureExtractor(ngram_value)

Example #3

class LexicalizedFeatureExtractionFlowMapper:
    def __init__(self,
                 context_window_size=4,
                 prime_feature_length=4,
                 add_prime_feature=False,
                 ngram_value=2):
        # get hold of suitable feature extractor
        # k_param: pass 4 tokens as context window length:

        self.feature_extractor = POSContextSequenceFeatureExtractor(
            k_param=context_window_size,
            prime_feature_length=prime_feature_length,
            add_prime_feature=add_prime_feature)

        self.lexicalized_fe = LexicalizedNgramsFeatureExtractor(ngram_value)

    def process(self, line):
        try:
            feature_dict, category, word = self.feature_extractor.extract_features(
                line)
            lex_feature_dict, lex_cat, lex_word = self.lexicalized_fe.extract_features(
                line)

            # updating the feature dict with lexicalized features as well
            feature_dict.update(lex_feature_dict)

            if not feature_dict is None:
                print word, "\t", category, "\t", feature_dict
        except Exception as ex:
            print >> sys.stderr, ex.message
            pass

Example #4

File: kartik_fe_map.py Project: kperisetla/glossextractionengine

class FeatureExtractionFlowMapper:
    def __init__(self):
        # get hold of suitable feature extractor
        # k_param: pass 4 tokens as context window length:
        self.feature_extractor = POSContextSequenceFeatureExtractor(k_param=4)

    def process(self, line):
        feature_dict,category,word = self.feature_extractor.extract_features(line)
        if not feature_dict is None:
            print word,"\t",category,"\t",feature_dict

Example #5

File: kartik_fe_map.py Project: anetschka/glossextractionengine

class FeatureExtractionFlowMapper:
    def __init__(self):
        # get hold of suitable feature extractor
        # k_param: pass 4 tokens as context window length:
        self.feature_extractor = POSContextSequenceFeatureExtractor(k_param=4)

    def process(self, line):
        feature_dict, category, word = self.feature_extractor.extract_features(
            line)
        if not feature_dict is None:
            print word, "\t", category, "\t", feature_dict

Example #6

File: cross_validation_feature_extraction_flow_mapper.py Project: anetschka/glossextractionengine

class CrossValidationFeatureExtractionFlowMapper:
    def __init__(self, context_window_size=4, prime_feature_length=4, add_prime_feature_val = False):
        # get hold of suitable feature extractor
        # k_param: pass 4 tokens as context window length:

        self.feature_extractor = POSContextSequenceFeatureExtractor(k_param=context_window_size,prime_feature_length=prime_feature_length, add_prime_feature=add_prime_feature_val)

    def process(self, line):
        try:
            feature_dict,category,word = self.feature_extractor.extract_features(line)
            if not feature_dict is None:
                print word,"\t",category,"\t",feature_dict
        except Exception as ex:
            print >>sys.stderr,ex.message
            pass

Example #7

File: lexicalized_feature_extraction_flow_mapper.py Project: kperisetla/glossextractionengine

class LexicalizedFeatureExtractionFlowMapper:
    def __init__(self, context_window_size=4, prime_feature_length=4, add_prime_feature = False, ngram_value=2):
        # get hold of suitable feature extractor
        # k_param: pass 4 tokens as context window length:

        self.feature_extractor = POSContextSequenceFeatureExtractor(k_param=context_window_size,prime_feature_length=prime_feature_length, add_prime_feature=add_prime_feature)

        self.lexicalized_fe = LexicalizedNgramsFeatureExtractor(ngram_value)

    def process(self, line):
        try:
            feature_dict,category,word = self.feature_extractor.extract_features(line)
            lex_feature_dict, lex_cat, lex_word = self.lexicalized_fe.extract_features(line)

            # updating the feature dict with lexicalized features as well
            feature_dict.update(lex_feature_dict)

            if not feature_dict is None:
                print word,"\t",category,"\t",feature_dict
        except Exception as ex:
            print >>sys.stderr,ex.message
            pass

Example #8

File: kartik_fe_map.py Project: anetschka/glossextractionengine

 def __init__(self):
     # get hold of suitable feature extractor
     # k_param: pass 4 tokens as context window length:
     self.feature_extractor = POSContextSequenceFeatureExtractor(k_param=4)

Example #9

File: kartik_fe_map.py Project: kperisetla/glossextractionengine

 def __init__(self):
     # get hold of suitable feature extractor
     # k_param: pass 4 tokens as context window length:
     self.feature_extractor = POSContextSequenceFeatureExtractor(k_param=4)

Example #10

File: cross_validation_feature_extraction_flow_mapper.py Project: anetschka/glossextractionengine

    def __init__(self, context_window_size=4, prime_feature_length=4, add_prime_feature_val = False):
        # get hold of suitable feature extractor
        # k_param: pass 4 tokens as context window length:

        self.feature_extractor = POSContextSequenceFeatureExtractor(k_param=context_window_size,prime_feature_length=prime_feature_length, add_prime_feature=add_prime_feature_val)