trnltk.morphology.contextless.parser.parser.ContextlessMorphologicalParser

Here are the examples of the python api trnltk.morphology.contextless.parser.parser.ContextlessMorphologicalParser taken from open source projects. By voting up you can indicate which examples are most useful and appropriate.

12 Examples 7

Example 1

Project: trnltk Source File: test_parser_brute_force_noun.py
    def setUp(self):
        logging.basicConfig(level=logging.INFO)
        parser_logger.setLevel(logging.INFO)
        suffix_applier_logger.setLevel(logging.INFO)

        suffix_graph = BasicSuffixGraph()
        suffix_graph.initialize()

        self.mock_brute_force_noun_root_finder = BruteForceNounRootFinder()

        self.parser = ContextlessMorphologicalParser(suffix_graph, None, [self.mock_brute_force_noun_root_finder])

Example 2

Project: trnltk Source File: test_parser_brute_force_noun.py
    def setUp(self):
        logging.basicConfig(level=logging.INFO)
        parser_logger.setLevel(logging.INFO)
        suffix_applier_logger.setLevel(logging.INFO)

        suffix_graph = BasicSuffixGraph()
        suffix_graph.initialize()

        self.mock_brute_force_noun_compound_root_finder = BruteForceCompoundNounRootFinder()

        self.parser = ContextlessMorphologicalParser(suffix_graph, None, [self.mock_brute_force_noun_compound_root_finder])

Example 3

Project: trnltk Source File: test_parser_brute_force_verb.py
    def setUp(self):
        logging.basicConfig(level=logging.INFO)
        parser_logger.setLevel(logging.INFO)
        suffix_applier_logger.setLevel(logging.INFO)

        suffix_graph = BasicSuffixGraph()
        suffix_graph.initialize()

        self.mock_brute_force_noun_root_finder = BruteForceVerbRootFinder()

        self.parser = ContextlessMorphologicalParser(suffix_graph, None, [self.mock_brute_force_noun_root_finder])

Example 4

Project: trnltk Source File: test_parser_with_copula_graph.py
    def setUp(self):
        logging.basicConfig(level=logging.INFO)
        parser_logger.setLevel(logging.INFO)
        suffix_applier_logger.setLevel(logging.INFO)

        self.cloned_root_map = copy(self._org_root_map)

        suffix_graph = CopulaSuffixGraph(BasicSuffixGraph())
        suffix_graph.initialize()
        predefined_paths = PredefinedPaths(self.cloned_root_map, suffix_graph)
        predefined_paths.create_predefined_paths()

        word_root_finder = WordRootFinder(self.cloned_root_map)

        self.parser = ContextlessMorphologicalParser(suffix_graph, predefined_paths,
            [word_root_finder])

Example 5

Project: trnltk Source File: test_parser_with_proper_noun_graph.py
    @classmethod
    def setUpClass(cls):
        super(ParserTestWithProperNouns, cls).setUpClass()
        cls.root_map = dict()

        suffix_graph = ProperNounSuffixGraph(BasicSuffixGraph())
        suffix_graph.initialize()

        proper_noun_from_apostrophe_root_finder = ProperNounFromApostropheRootFinder()
        proper_noun_without_apostrophe_root_finder = ProperNounWithoutApostropheRootFinder()

        cls.parser = ContextlessMorphologicalParser(suffix_graph, None,
            [proper_noun_from_apostrophe_root_finder, proper_noun_without_apostrophe_root_finder])

Example 6

Project: trnltk Source File: test_formatter.py
    def setUp(self):
        logging.basicConfig(level=logging.INFO)
        parser_logger.setLevel(logging.INFO)
        suffix_applier_logger.setLevel(logging.INFO)

        suffix_graph = BasicSuffixGraph()
        suffix_graph.initialize()

        word_root_finder = WordRootFinder(self.root_map)

        self.parser = ContextlessMorphologicalParser(suffix_graph, None, [word_root_finder])

Example 7

Project: trnltk Source File: test_contextlessdistributioncalculator.py
    @classmethod
    def setUpClass(cls):
        all_roots = []

        lexemes = LexiconLoader.load_from_file(os.path.join(os.path.dirname(__file__), '../../../../../resources/master_dictionary.txt'))
        for di in lexemes:
            all_roots.extend(RootGenerator.generate(di))

        root_map_generator = RootMapGenerator()
        cls.root_map = root_map_generator.generate(all_roots)

        suffix_graph = CopulaSuffixGraph(NumeralSuffixGraph(ProperNounSuffixGraph(BasicSuffixGraph())))
        suffix_graph.initialize()

        predefined_paths = PredefinedPaths(cls.root_map, suffix_graph)
        predefined_paths.create_predefined_paths()

        word_root_finder = WordRootFinder(cls.root_map)
        digit_numeral_root_finder = DigitNumeralRootFinder()
        text_numeral_root_finder = TextNumeralRootFinder(cls.root_map)
        proper_noun_from_apostrophe_root_finder = ProperNounFromApostropheRootFinder()
        proper_noun_without_apostrophe_root_finder = ProperNounWithoutApostropheRootFinder()

        cls.contextless_parser = ContextlessMorphologicalParser(suffix_graph, predefined_paths,
            [word_root_finder, digit_numeral_root_finder, text_numeral_root_finder,
             proper_noun_from_apostrophe_root_finder, proper_noun_without_apostrophe_root_finder])

        mongodb_connection = pymongo.Connection(host='127.0.0.1')
        collection_map = {
            1: mongodb_connection['trnltk']['wordUnigrams{}'.format(cls.parseset_index)]
        }

        database_index_builder = DatabaseIndexBuilder(collection_map)
        target_form_given_context_counter = TargetFormGivenContextCounter(collection_map)
        smoother = CachedContextlessDistributionSmoother()
        smoother.initialize()

        cls.calculator = ContextlessDistributionCalculator(database_index_builder, target_form_given_context_counter, smoother)
        cls.calculator.build_indexes()

Example 8

Project: trnltk Source File: test_calculator.py
    @classmethod
    def setUpClass(cls):
        super(_LikelihoodCalculatorTest, cls).setUpClass()
        all_roots = []

        lexemes = LexiconLoader.load_from_file(os.path.join(os.path.dirname(__file__), '../../../../../resources/master_dictionary.txt'))
        for di in lexemes:
            all_roots.extend(RootGenerator.generate(di))

        root_map_generator = RootMapGenerator()
        cls.root_map = root_map_generator.generate(all_roots)

        suffix_graph = CopulaSuffixGraph(NumeralSuffixGraph(ProperNounSuffixGraph(BasicSuffixGraph())))
        suffix_graph.initialize()

        predefined_paths = PredefinedPaths(cls.root_map, suffix_graph)
        predefined_paths.create_predefined_paths()

        word_root_finder = WordRootFinder(cls.root_map)
        digit_numeral_root_finder = DigitNumeralRootFinder()
        text_numeral_root_finder = TextNumeralRootFinder(cls.root_map)
        proper_noun_from_apostrophe_root_finder = ProperNounFromApostropheRootFinder()
        proper_noun_without_apostrophe_root_finder = ProperNounWithoutApostropheRootFinder()

        cls.contextless_parser = ContextlessMorphologicalParser(suffix_graph, predefined_paths,
            [word_root_finder, digit_numeral_root_finder, text_numeral_root_finder,
             proper_noun_from_apostrophe_root_finder, proper_noun_without_apostrophe_root_finder])

        cls.mongodb_connection = pymongo.Connection(host='127.0.0.1')
        cls.collection_map = {
            1: cls.mongodb_connection['trnltk']['wordUnigrams999'],
            2: cls.mongodb_connection['trnltk']['wordBigrams999'],
            3: cls.mongodb_connection['trnltk']['wordTrigrams999']
        }

        cls.generator = None

Example 9

Project: trnltk Source File: playground.py
def initialize():
    all_roots = []
    lexemes = LexiconLoader.load_from_file(os.path.join(os.path.dirname(__file__), '../resources/master_dictionary.txt'))
    for di in lexemes:
        all_roots.extend(CircuemflexConvertingRootGenerator.generate(di))

    root_map_generator = RootMapGenerator()
    root_map = root_map_generator.generate(all_roots)

    suffix_graph = CopulaSuffixGraph(NumeralSuffixGraph(ProperNounSuffixGraph(BasicSuffixGraph())))
    suffix_graph.initialize()

    predefined_paths = PredefinedPaths(root_map, suffix_graph)
    predefined_paths.create_predefined_paths()

    word_root_finder = WordRootFinder(root_map)
    text_numeral_root_finder = TextNumeralRootFinder(root_map)
    digit_numeral_root_finder = DigitNumeralRootFinder()
    proper_noun_from_apostrophe_root_finder = ProperNounFromApostropheRootFinder()
    proper_noun_without_apostrophe_root_finder = ProperNounWithoutApostropheRootFinder()

    global contextless_parser
    contextless_parser = ContextlessMorphologicalParser(suffix_graph, predefined_paths,
        [word_root_finder, text_numeral_root_finder, digit_numeral_root_finder,
         proper_noun_from_apostrophe_root_finder, proper_noun_without_apostrophe_root_finder])

Example 10

Project: trnltk Source File: test_statistical_parser.py
    @classmethod
    def setUpClass(cls):
        super(StatisticalParserTest, cls).setUpClass()
        all_roots = []

        lexemes = LexiconLoader.load_from_file(os.path.join(os.path.dirname(__file__), '../../resources/master_dictionary.txt'))
        for di in lexemes:
            all_roots.extend(RootGenerator.generate(di))


        root_map_generator = RootMapGenerator()
        cls.root_map = root_map_generator.generate(all_roots)

        suffix_graph = CopulaSuffixGraph(NumeralSuffixGraph(BasicSuffixGraph()))
        suffix_graph.initialize()

        predefined_paths = PredefinedPaths(cls.root_map, suffix_graph)
        predefined_paths.create_predefined_paths()

        word_root_finder = WordRootFinder(cls.root_map)
        digit_numeral_root_finder = DigitNumeralRootFinder()
        text_numeral_root_finder = TextNumeralRootFinder(cls.root_map)
        proper_noun_from_apostrophe_root_finder = ProperNounFromApostropheRootFinder()
        proper_noun_without_apostrophe_root_finder = ProperNounWithoutApostropheRootFinder()

        contextless_parser = ContextlessMorphologicalParser(suffix_graph, predefined_paths,
            [word_root_finder, digit_numeral_root_finder, text_numeral_root_finder, proper_noun_from_apostrophe_root_finder, proper_noun_without_apostrophe_root_finder])

        parseset_index = "001"
        dom = parse(os.path.join(os.path.dirname(__file__), '../../testresources/parsesets/parseset{}.xml'.format(parseset_index)))
        parseset = ParseSetBinding.build(dom.getElementsByTagName("parseset")[0])
        parse_set_word_list = []
        for sentence in parseset.sentences:
            parse_set_word_list.extend(sentence.words)

        complete_word_concordance_index = CompleteWordConcordanceIndex(parse_set_word_list)

        cls.parser = StatisticalParser(contextless_parser, complete_word_concordance_index)

Example 11

Project: trnltk Source File: test_morphemecontainerstats.py
    @classmethod
    def setUpClass(cls):
        super(MorphemeContainerContextlessProbabilityGeneratorWithContainersTest, cls).setUpClass()
        all_roots = []

        lexicon_lines = u'''
            duvar
            tutku
            saç
            oğul [A:LastVowelDrop]
            demek [A:RootChange, Passive_In, Passive_InIl]
            bu [P:Det]
        '''.strip().splitlines()

        lexemes = LexiconLoader.load_from_lines(lexicon_lines)
        for di in lexemes:
            all_roots.extend(RootGenerator.generate(di))

        root_map_generator = RootMapGenerator()
        cls.root_map = root_map_generator.generate(all_roots)

        suffix_graph = BasicSuffixGraph()
        suffix_graph.initialize()

        word_root_finder = WordRootFinder(cls.root_map)

        cls.contextless_parser = ContextlessMorphologicalParser(suffix_graph, None,
            [word_root_finder])

Example 12

Project: trnltk Source File: test_transitiongenerator.py
    @classmethod
    def setUpClass(cls):
        super(TransitionGeneratorTest, cls).setUpClass()
        all_roots = []

        lexemes = LexiconLoader.load_from_file(os.path.join(os.path.dirname(__file__), '../../resources/master_dictionary.txt'))
        for di in lexemes:
            all_roots.extend(RootGenerator.generate(di))

        root_map_generator = RootMapGenerator()
        cls.root_map = root_map_generator.generate(all_roots)

        suffix_graph = CopulaSuffixGraph(NumeralSuffixGraph(ProperNounSuffixGraph(BasicSuffixGraph())))
        suffix_graph.initialize()

        predefined_paths = PredefinedPaths(cls.root_map, suffix_graph)
        predefined_paths.create_predefined_paths()

        word_root_finder = WordRootFinder(cls.root_map)
        digit_numeral_root_finder = DigitNumeralRootFinder()
        text_numeral_root_finder = TextNumeralRootFinder(cls.root_map)
        proper_noun_from_apostrophe_root_finder = ProperNounFromApostropheRootFinder()
        proper_noun_without_apostrophe_root_finder = ProperNounWithoutApostropheRootFinder()

        cls.parser = ContextlessMorphologicalParser(suffix_graph, predefined_paths,
            [word_root_finder, digit_numeral_root_finder, text_numeral_root_finder,
             proper_noun_from_apostrophe_root_finder, proper_noun_without_apostrophe_root_finder])

        cls.transition_generator = TransitionGenerator(cls.parser)