arekit 0.24.0__py3-none-any.whl → 0.25.1__py3-none-any.whl

arekit/contrib/utils/pipelines/items/text/tokenizer.py

@@ -1,107 +0,0 @@
-import logging
-
-from arekit.common.context.token import Token
-from arekit.common.pipeline.context import PipelineContext
-from arekit.common.pipeline.items.base import BasePipelineItem
-from arekit.common.utils import split_by_whitespaces
-from arekit.contrib.utils.processing.text.tokens import Tokens
-
-logger = logging.getLogger(__name__)
-logger.setLevel(logging.INFO)
-
-
-class DefaultTextTokenizer(BasePipelineItem):
-    """ Default parser implementation.
-    """
-
-    def __init__(self, keep_tokens=True):
-        super(DefaultTextTokenizer, self).__init__()
-        self.__keep_tokens = keep_tokens
-
-    # region protected methods
-
-    def apply_core(self, input_data, pipeline_ctx):
-        assert(isinstance(pipeline_ctx, PipelineContext))
-        output_data = self.__process_parts(input_data)
-        if not self.__keep_tokens:
-            output_data = [word for word in output_data if not isinstance(word, Token)]
-        return output_data
-
-    # endregion
-
-    # region private static methods
-
-    def __process_parts(self, parts):
-        assert(isinstance(parts, list))
-
-        parsed = []
-        for part in parts:
-
-            if part is None:
-                continue
-
-            # Keep non str words as it is and try to parse str-based words.
-            processed = [part] if not isinstance(part, str) else \
-                self.__iter_processed_part(part=part)
-
-            parsed.extend(processed)
-
-        return parsed
-
-    def __iter_processed_part(self, part):
-        for word in split_by_whitespaces(part):
-            for term in self.__process_word(word):
-                yield term
-
-    def __process_word(self, word):
-        assert(isinstance(word, str))
-        return self.__split_tokens(word)
-
-    @staticmethod
-    def __split_tokens(term):
-        """
-        Splitting off tokens from parsed_doc ending, i.e. for example:
-            term: "сказать,-" -> "(term: "сказать", ["COMMA_TOKEN", "DASH_TOKEN"])
-        return: (unicode or None, list)
-            modified term and list of extracted tokens.
-        """
-
-        url = Tokens.try_create_url(term)
-        if url is not None:
-            return [url]
-
-        l = 0
-        words_and_tokens = []
-        while l < len(term):
-
-            # Token.
-            token = Tokens.try_create(term[l])
-            if token is not None:
-                if token.get_token_value() != Tokens.NEW_LINE:
-                    words_and_tokens.append(token)
-                l += 1
-
-            # Number.
-            elif str.isdigit(term[l]):
-                k = l + 1
-                while k < len(term) and str.isdigit(term[k]):
-                    k += 1
-                token = Tokens.try_create_number(term[l:k])
-                assert(token is not None)
-                words_and_tokens.append(token)
-                l = k
-
-            # Term.
-            else:
-                k = l + 1
-                while k < len(term):
-                    token = Tokens.try_create(term[k])
-                    if token is not None and token.get_token_value() != Tokens.DASH:
-                        break
-                    k += 1
-                words_and_tokens.append(term[l:k])
-                l = k
-
-        return words_and_tokens
-
-    # endregion

arekit/contrib/utils/pipelines/items/text/translator.py

@@ -1,135 +0,0 @@
-from arekit.common.data.input.providers.const import IDLE_MODE
-from arekit.common.pipeline.conts import PARENT_CTX
-from arekit.common.entities.base import Entity
-from arekit.common.pipeline.context import PipelineContext
-from arekit.common.pipeline.items.base import BasePipelineItem
-
-
-class MLTextTranslatorPipelineItem(BasePipelineItem):
-    """ Machine learning based translator pipeline item.
-    """
-
-    def __init__(self, batch_translate_model, do_translate_entity=True):
-        """ Model, which is based on translation of the text,
-            represented as a list of words.
-        """
-        self.__do_translate_entity = do_translate_entity
-        self.__translate = batch_translate_model
-
-    def fast_most_accurate_approach(self, input_data, entity_placeholder_template="<entityTag={}/>"):
-        """ This approach assumes that the translation won't corrupt the original
-            meta-annotation for entities and objects mentioned in text.
-        """
-
-        def __optionally_register(prts):
-            if len(prts) > 0:
-                content.append(" ".join(prts))
-            parts_to_join.clear()
-
-        content = []
-        origin_entities = []
-        parts_to_join = []
-
-        for part in input_data:
-            if isinstance(part, str) and part.strip():
-                parts_to_join.append(part)
-            elif isinstance(part, Entity):
-                entity_index = len(origin_entities)
-                parts_to_join.append(entity_placeholder_template.format(entity_index))
-                # Register entities information for further restoration.
-                origin_entities.append(part)
-
-        # Register original text with masked named entities.
-        __optionally_register(parts_to_join)
-        # Register all named entities in order of their appearance in text.
-        content.extend([e.Value for e in origin_entities])
-
-        # Compose text parts.
-        translated_parts = self.__translate(content)
-
-        if len(translated_parts) == 0:
-            return None
-
-        # Take the original text.
-        text = translated_parts[0]
-        for entity_index in range(len(origin_entities)):
-            if entity_placeholder_template.format(entity_index) not in text:
-                return None
-
-        # Enumerate entities.
-        from_ind = 0
-        text_parts = []
-        for entity_index, translated_value in enumerate(translated_parts[1:]):
-            entity_placeholder_instance = entity_placeholder_template.format(entity_index)
-            # Cropping text part.
-            to_ind = text.index(entity_placeholder_instance)
-
-            if self.__do_translate_entity:
-                origin_entities[entity_index].set_display_value(translated_value.strip())
-
-            # Register entities.
-            text_parts.append(text[from_ind:to_ind])
-            text_parts.append(origin_entities[entity_index])
-            # Update from index.
-            from_ind = to_ind + len(entity_placeholder_instance)
-
-        # Consider the remaining part.
-        text_parts.append(text[from_ind:])
-        return text_parts
-
-    def default_pre_part_splitting_approach(self, input_data):
-        """ This is the original strategy, based on the manually cropped named entities
-            before the actual translation call.
-        """
-
-        def __optionally_register(prts):
-            if len(prts) > 0:
-                content.append(" ".join(prts))
-            parts_to_join.clear()
-
-        content = []
-        origin_entities = []
-        origin_entity_ind = []
-        parts_to_join = []
-
-        for _, part in enumerate(input_data):
-            if isinstance(part, str) and part.strip():
-                parts_to_join.append(part)
-            elif isinstance(part, Entity):
-                # Register first the prior parts were merged.
-                __optionally_register(parts_to_join)
-                # Register entities information for further restoration.
-                origin_entity_ind.append(len(content))
-                origin_entities.append(part)
-                content.append(part.Value)
-
-        __optionally_register(parts_to_join)
-
-        # Compose text parts.
-        translated_parts = self.__translate(content)
-
-        for entity_ind, entity_part_ind in enumerate(origin_entity_ind):
-            entity = origin_entities[entity_ind]
-            if self.__do_translate_entity:
-                entity.set_display_value(translated_parts[entity_part_ind].strip())
-            translated_parts[entity_part_ind] = entity
-
-        return translated_parts
-
-    def apply_core(self, input_data, pipeline_ctx):
-        assert(isinstance(pipeline_ctx, PipelineContext))
-        assert(isinstance(input_data, list))
-
-        # Check the pipeline state whether is an idle mode or not.
-        parent_ctx = pipeline_ctx.provide(PARENT_CTX)
-        idle_mode = parent_ctx.provide(IDLE_MODE)
-
-        # When pipeline utilized only for the assessing the expected amount
-        # of rows (common case of idle_mode), there is no need to perform
-        # translation.
-        if idle_mode:
-            return
-
-        fast_accurate = self.fast_most_accurate_approach(input_data)
-        return self.default_pre_part_splitting_approach(input_data) \
-            if fast_accurate is None else fast_accurate

arekit/contrib/utils/pipelines/sources/nerel/doc_provider.py

@@ -1,27 +0,0 @@
-from arekit.common.data.doc_provider import DocumentProvider
-from arekit.contrib.source.nerel.reader import NerelDocReader
-from arekit.contrib.source.nerel.versions import NerelVersions
-
-
-class NERELDocProvider(DocumentProvider):
-    """ A Russian dataset with nested named entities, relations, events and linked entities.
-        https://github.com/nerel-ds/NEREL
-    """
-
-    def __init__(self, filename_by_id, version):
-        """ filename_ids: dict
-                Dictionary of {id: filename}, where
-                    - id: int
-                    - filename: str
-            version: NerelVersions
-                Specify the appropriate version of teh NEREL collection.
-        """
-        assert(isinstance(filename_by_id, dict))
-        assert(isinstance(version, NerelVersions))
-        super(NERELDocProvider, self).__init__()
-        self.__filename_by_id = filename_by_id
-        self.__version = version
-        self.__doc_reader = NerelDocReader(version)
-
-    def by_id(self, doc_id):
-        return self.__doc_reader.read_document(doc_id=doc_id, filename=self.__filename_by_id[doc_id])

arekit/contrib/utils/pipelines/sources/nerel/extract_text_relations.py

@@ -1,65 +0,0 @@
-from arekit.common.data.doc_provider import DocumentProvider
-from arekit.common.experiment.data_type import DataType
-from arekit.contrib.source.nerel.io_utils import NerelIOUtils
-from arekit.contrib.source.nerel.versions import NerelVersions
-from arekit.contrib.utils.pipelines.sources.nerel.doc_provider import NERELDocProvider
-from arekit.contrib.utils.pipelines.sources.nerel.labels_fmt import NerelAnyLabelFormatter
-from arekit.contrib.utils.pipelines.text_opinion.annot.predefined import PredefinedTextOpinionAnnotator
-from arekit.contrib.utils.pipelines.text_opinion.extraction import text_opinion_extraction_pipeline
-from arekit.contrib.utils.pipelines.text_opinion.filters.distance_based import DistanceLimitedTextOpinionFilter
-
-
-def create_text_relation_extraction_pipeline(nerel_version,
-                                             text_parser,
-                                             label_formatter=NerelAnyLabelFormatter(),
-                                             terms_per_context=50,
-                                             doc_ops=None,
-                                             docs_limit=None,
-                                             custom_text_opinion_filters=None):
-    assert(isinstance(nerel_version, NerelVersions))
-    assert(isinstance(doc_ops, DocumentProvider) or doc_ops is None)
-    assert(isinstance(custom_text_opinion_filters, list) or custom_text_opinion_filters is None)
-
-    data_folding = None
-
-    if doc_ops is None:
-        # Default Initialization.
-        filenames_by_ids, data_folding = NerelIOUtils.read_dataset_split(version=nerel_version,
-                                                                         docs_limit=docs_limit)
-        doc_ops = NERELDocProvider(filename_by_id=filenames_by_ids, version=nerel_version)
-
-    # Default text opinion filters.
-    text_opinion_filters = [
-        DistanceLimitedTextOpinionFilter(terms_per_context)
-    ]
-
-    # Append with the custom filters afterwards.
-    if custom_text_opinion_filters is not None:
-        text_opinion_filters += custom_text_opinion_filters
-
-    predefined_annot = PredefinedTextOpinionAnnotator(doc_ops, label_formatter)
-
-    pipelines = {
-        DataType.Train: text_opinion_extraction_pipeline(text_parser=text_parser,
-                                                         get_doc_by_id_func=doc_ops.by_id,
-                                                         annotators=[predefined_annot],
-                                                         entity_index_func=lambda brat_entity: brat_entity.ID,
-                                                         text_opinion_filters=text_opinion_filters),
-        DataType.Test: text_opinion_extraction_pipeline(text_parser=text_parser,
-                                                        get_doc_by_id_func=doc_ops.by_id,
-                                                        annotators=[predefined_annot],
-                                                        entity_index_func=lambda brat_entity: brat_entity.ID,
-                                                        text_opinion_filters=text_opinion_filters),
-        DataType.Dev: text_opinion_extraction_pipeline(text_parser=text_parser,
-                                                       get_doc_by_id_func=doc_ops.by_id,
-                                                       annotators=[predefined_annot],
-                                                       entity_index_func=lambda brat_entity: brat_entity.ID,
-                                                       text_opinion_filters=text_opinion_filters),
-    }
-
-    # In the case when we setup a default data-folding.
-    # There is a need to provide it, due to the needs in further.
-    if data_folding is not None:
-        return pipelines, data_folding
-
-    return pipelines

arekit/contrib/utils/pipelines/sources/nerel/labels_fmt.py

@@ -1,60 +0,0 @@
-from arekit.common.labels.str_fmt import StringLabelsFormatter
-from arekit.contrib.source.nerel import labels
-
-
-class NerelAnyLabelFormatter(StringLabelsFormatter):
-
-    def __init__(self):
-
-        stol = {
-            "OPINION_BELONGS_TO": labels.OpinionBelongsTo,
-            "OPINION_RELATES_TO": labels.OpinionRelatesTo,
-            "NEG_EFFECT_FROM": labels.NegEffectFrom,
-            "POS_EFFECT_FROM": labels.PosEffectFrom,
-            "NEG_STATE_FROM": labels.NegStateFrom,
-            "POS_STATE_FROM": labels.PosStateFrom,
-            "NEGATIVE_TO": labels.NegativeTo,
-            "POSITIVE_TO": labels.PositiveTo,
-            "STATE_BELONGS_TO": labels.STATE_BELONGS_TO,
-            "POS_AUTHOR_FROM": labels.PosAuthorFrom,
-            "NEG_AUTHOR_FROM": labels.NegAuthorFrom,
-            "ALTERNATIVE_NAME": labels.ALTERNATIVE_NAME,
-            "ORIGINS_FROM": labels.ORIGINS_FROM,
-            "START_TIME": labels.START_TIME,
-            "OWNER_OF": labels.OWNER_OF,
-            "SUBEVENT_OF": labels.SUBEVENT_OF,
-            "PARENT_OF": labels.PARENT_OF,
-            "SUBORDINATE_OF": labels.SUBORDINATE_OF,
-            "PART_OF": labels.PART_OF,
-            "TAKES_PLACE_IN": labels.TAKES_PLACE_IN,
-            "PARTICIPANT_IN": labels.PARTICIPANT_IN,
-            "WORKPLACE": labels.WORKPLACE,
-            "PENALIZED_AS": labels.PENALIZED_AS,
-            "WORKS_AS": labels.WORKS_AS,
-            "PLACE_OF_DEATH": labels.PLACE_OF_DEATH,
-            "PLACE_OF_BIRTH": labels.PLACE_OF_BIRTH,
-            "HAS_CAUSE": labels.HAS_CAUSE,
-            "AWARDED_WITH": labels.AWARDED_WITH,
-            "CAUSE_OF_DEATH": labels.CAUSE_OF_DEATH,
-            "CONVICTED_OF": labels.CONVICTED_OF,
-            "DATE_DEFUNCT_IN": labels.DATE_DEFUNCT_IN,
-            "DATE_FOUNDED_IN": labels.DATE_FOUNDED_IN,
-            "DATE_OF_BIRTH": labels.DATE_OF_BIRTH,
-            "DATE_OF_CREATION": labels.DATE_OF_CREATION,
-            "DATE_OF_DEATH": labels.DATE_OF_DEATH,
-            "END_TIME": labels.END_TIME,
-            "EXPENDITURE": labels.EXPENDITURE,
-            "FOUNDED_BY": labels.FOUNDED_BY,
-            "KNOWS": labels.KNOWS,
-            "RELATIVE": labels.RELATIVE,
-            "LOCATED_IN": labels.LOCATED_IN,
-            "RELIGION_OF": labels.RELIGION_OF,
-            "MEDICAL_CONDITION": labels.MEDICAL_CONDITION,
-            "SCHOOLS_ATTENDED": labels.SCHOOLS_ATTENDED,
-            "MEMBER_OF": labels.MEMBER_OF,
-            "SIBLING": labels.SIBLING,
-            "ORGANIZES": labels.ORGANIZES,
-            "SPOUSE": labels.SPOUSE
-        }
-
-        super(NerelAnyLabelFormatter, self).__init__(stol=stol)

arekit/contrib/utils/pipelines/sources/nerel_bio/doc_provider.py

@@ -1,29 +0,0 @@
-from arekit.common.data.doc_provider import DocumentProvider
-from arekit.contrib.source.nerelbio.reader import NerelBioDocReader
-from arekit.contrib.source.nerelbio.versions import NerelBioVersions
-
-
-class NERELBioDocProvider(DocumentProvider):
-    """ NEREL-BIO extends the general domain dataset NEREL.
-        NEREL-BIO annotation scheme covers both general and biomedical
-        domains making it suitable for domain transfer experiments.
-        https://github.com/nerel-ds/NEREL-BIO
-    """
-
-    def __init__(self, filename_by_id, version):
-        """ filename_ids: dict
-                Dictionary of {id: filename}, where
-                    - id: int
-                    - filename: str
-            version: NerelBioVersions
-                Specify the appropriate version of the NEREL-BIO collection.
-        """
-        assert(isinstance(filename_by_id, dict))
-        assert(isinstance(version, NerelBioVersions))
-        super(NERELBioDocProvider, self).__init__()
-        self.__filename_by_id = filename_by_id
-        self.__version = version
-        self.__doc_reader = NerelBioDocReader(version)
-
-    def by_id(self, doc_id):
-        return self.__doc_reader.read_document(doc_id=doc_id, filename=self.__filename_by_id[doc_id])

arekit/contrib/utils/pipelines/sources/nerel_bio/extrat_text_relations.py

@@ -1,64 +0,0 @@
-from arekit.common.data.doc_provider import DocumentProvider
-from arekit.common.experiment.data_type import DataType
-from arekit.contrib.source.nerelbio.io_utils import NerelBioIOUtils
-from arekit.contrib.source.nerelbio.versions import NerelBioVersions
-from arekit.contrib.utils.pipelines.sources.nerel_bio.doc_provider import NERELBioDocProvider
-from arekit.contrib.utils.pipelines.sources.nerel_bio.labels_fmt import NerelBioAnyLabelFormatter
-from arekit.contrib.utils.pipelines.text_opinion.annot.predefined import PredefinedTextOpinionAnnotator
-from arekit.contrib.utils.pipelines.text_opinion.extraction import text_opinion_extraction_pipeline
-from arekit.contrib.utils.pipelines.text_opinion.filters.distance_based import DistanceLimitedTextOpinionFilter
-
-
-def create_text_relation_extraction_pipeline(nerel_bio_version,
-                                             text_parser,
-                                             label_formatter=NerelBioAnyLabelFormatter(),
-                                             terms_per_context=50,
-                                             doc_ops=None,
-                                             docs_limit=None,
-                                             custom_text_opinion_filters=None):
-    assert(isinstance(nerel_bio_version, NerelBioVersions))
-    assert(isinstance(doc_ops, DocumentProvider) or doc_ops is None)
-    assert(isinstance(custom_text_opinion_filters, list) or custom_text_opinion_filters is None)
-
-    data_folding = None
-
-    if doc_ops is None:
-        # Default Initialization.
-        filenames_by_ids, data_folding = NerelBioIOUtils.read_dataset_split(version=nerel_bio_version,
-                                                                            docs_limit=docs_limit)
-        doc_ops = NERELBioDocProvider(filename_by_id=filenames_by_ids, version=nerel_bio_version)
-
-    text_opinion_filters = [
-        DistanceLimitedTextOpinionFilter(terms_per_context)
-    ]
-
-    # Append with the custom filters afterwards.
-    if custom_text_opinion_filters is not None:
-        text_opinion_filters += custom_text_opinion_filters
-
-    predefined_annot = PredefinedTextOpinionAnnotator(doc_ops, label_formatter)
-
-    pipelines = {
-        DataType.Train: text_opinion_extraction_pipeline(text_parser=text_parser,
-                                                         get_doc_by_id_func=doc_ops.by_id,
-                                                         annotators=[predefined_annot],
-                                                         entity_index_func=lambda brat_entity: brat_entity.ID,
-                                                         text_opinion_filters=text_opinion_filters),
-        DataType.Test: text_opinion_extraction_pipeline(text_parser=text_parser,
-                                                        get_doc_by_id_func=doc_ops.by_id,
-                                                        annotators=[predefined_annot],
-                                                        entity_index_func=lambda brat_entity: brat_entity.ID,
-                                                        text_opinion_filters=text_opinion_filters),
-        DataType.Dev: text_opinion_extraction_pipeline(text_parser=text_parser,
-                                                       get_doc_by_id_func=doc_ops.by_id,
-                                                       annotators=[predefined_annot],
-                                                       entity_index_func=lambda brat_entity: brat_entity.ID,
-                                                       text_opinion_filters=text_opinion_filters),
-    }
-
-    # In the case when we setup a default data-folding.
-    # There is a need to provide it, due to the needs in further.
-    if data_folding is not None:
-        return pipelines, data_folding
-
-    return pipelines

arekit/contrib/utils/pipelines/sources/nerel_bio/labels_fmt.py

@@ -1,79 +0,0 @@
-from arekit.common.labels.str_fmt import StringLabelsFormatter
-from arekit.contrib.source.nerelbio import labels
-
-
-class NerelBioAnyLabelFormatter(StringLabelsFormatter):
-
-    def __init__(self):
-
-        stol = {
-            "ABBREVIATION": labels.ABBREVIATION,
-            "ALTERNATIVE_NAME": labels.ALTERNATIVE_NAME,
-            "KNOWS": labels.KNOWS,
-            "AGE_IS": labels.AGE_IS,
-            "AGE_DIED_AT": labels.AGE_DIED_AT,
-            "AWARDED_WITH": labels.AWARDED_WITH,
-            "PLACE_OF_BIRTH": labels.PLACE_OF_BIRTH,
-            "DATE_DEFUNCT_IN": labels.DATE_DEFUNCT_IN,
-            "DATE_FOUNDED_IN": labels.DATE_FOUNDED_IN,
-            "DATE_OF_BIRTH": labels.DATE_OF_BIRTH,
-            "DATE_OF_CREATION": labels.DATE_OF_CREATION,
-            "DATE_OF_DEATH": labels.DATE_OF_DEATH,
-            "POINT_IN_TIME": labels.POINT_IN_TIME,
-            "PLACE_OF_DEATH": labels.PLACE_OF_DEATH,
-            "FOUNDED_BY": labels.FOUNDED_BY,
-            "HEADQUARTERED_IN": labels.HEADQUARTERED_IN,
-            "IDEOLOGY_OF": labels.IDEOLOGY_OF,
-            "SPOUSE": labels.SPOUSE,
-            "MEMBER_OF": labels.MEMBER_OF,
-            "ORGANIZES": labels.ORGANIZES,
-            "OWNER_OF": labels.OWNER_OF,
-            "PARENT_OF": labels.PARENT_OF,
-            "PARTICIPANT_IN": labels.PARTICIPANT_IN,
-            "PLACE_RESIDES_IN": labels.PLACE_RESIDES_IN,
-            "PRICE_OF": labels.PRICE_OF,
-            "PRODUCES": labels.PRODUCES,
-            "RELATIVE": labels.RELATIVE,
-            "RELIGION_OF": labels.RELIGION_OF,
-            "SCHOOLS_ATTENDED": labels.SCHOOLS_ATTENDED,
-            "SIBLING": labels.SIBLING,
-            "SUBEVENT_OF": labels.SUBEVENT_OF,
-            "SUBORDINATE_OF": labels.SUBORDINATE_OF,
-            "TAKES_PLACE_IN": labels.TAKES_PLACE_IN,
-            "WORKPLACE": labels.WORKPLACE,
-            "WORKS_AS": labels.WORKS_AS,
-            "CONVICTED_OF": labels.CONVICTED_OF,
-            "PENALIZED_AS": labels.PENALIZED_AS,
-            "START_TIME": labels.START_TIME,
-            "END_TIME": labels.END_TIME,
-            "EXPENDITURE": labels.EXPENDITURE,
-            "AGENT": labels.AGENT,
-            "INANIMATE_INVOLVED": labels.INANIMATE_INVOLVED,
-            "INCOME": labels.INCOME,
-            "SUBCLASS_OF": labels.SUBCLASS_OF,
-            "PART_OF": labels.PART_OF,
-            "LOCATED_IN": labels.LOCATED_IN,
-            "TREATED_USING": labels.TREATED_USING,
-            "ORIGINS_FROM": labels.ORIGINS_FROM,
-            "TO_DETECT_OR_STUDY": labels.TO_DETECT_OR_STUDY,
-            "AFFECTS": labels.AFFECTS,
-            "HAS_CAUSE": labels.HAS_CAUSE,
-            "APPLIED_TO": labels.APPLIED_TO,
-            "USED_IN": labels.USED_IN,
-            "ASSOCIATED_WITH": labels.ASSOCIATED_WITH,
-            "HAS_ADMINISTRATION_ROUTE": labels.HAS_ADMINISTRATION_ROUTE,
-            "HAS_STRENGTH": labels.HAS_STRENGTH,
-            "DURATION_OF": labels.DURATION_OF,
-            "VALUE_IS": labels.VALUE_IS,
-            "PHYSIOLOGY_OF": labels.PHYSIOLOGY_OF,
-            "PROCEDURE_PERFORMED": labels.PROCEDURE_PERFORMED,
-            "MENTAL_PROCESS_OF": labels.MENTAL_PROCESS_OF,
-            "MEDICAL_CONDITION": labels.MEDICAL_CONDITION,
-            "DOSE_IS": labels.DOSE_IS,
-            "FINDING_OF": labels.FINDING_OF,
-            "CAUSE_OF_DEATH": labels.CAUSE_OF_DEATH,
-            "CONSUME": labels.CONSUME,
-        }
-
-        super(NerelBioAnyLabelFormatter, self).__init__(stol=stol)
-

arekit/contrib/utils/pipelines/sources/ruattitudes/doc_provider.py

@@ -1,56 +0,0 @@
-from arekit.common.utils import progress_bar_iter
-from arekit.contrib.source.ruattitudes.collection import RuAttitudesCollection
-from arekit.contrib.source.ruattitudes.io_utils import RuAttitudesVersions
-from arekit.contrib.source.ruattitudes.doc import RuAttitudesDocument
-from arekit.contrib.source.ruattitudes.doc_brat import RuAttitudesDocumentsConverter
-from arekit.contrib.utils.data.doc_provider.dict_based import DictionaryBasedDocumentProvider
-
-
-class RuAttitudesDocumentProvider(DictionaryBasedDocumentProvider):
-
-    def __init__(self, version, keep_doc_ids_only, doc_id_func, limit):
-        d = self.read_ruattitudes_to_brat_in_memory(version=version,
-                                                    keep_doc_ids_only=keep_doc_ids_only,
-                                                    doc_id_func=doc_id_func,
-                                                    limit=limit)
-        super(RuAttitudesDocumentProvider, self).__init__(d)
-
-    @staticmethod
-    def read_ruattitudes_to_brat_in_memory(version, keep_doc_ids_only, doc_id_func, limit=None):
-        """ Performs reading of RuAttitude formatted documents and
-            selection according to 'doc_ids_set' parameter.
-        """
-        assert (isinstance(version, RuAttitudesVersions))
-        assert (isinstance(keep_doc_ids_only, bool))
-        assert (callable(doc_id_func))
-
-        it = RuAttitudesCollection.iter_docs(version=version,
-                                             get_doc_index_func=doc_id_func,
-                                             return_inds_only=keep_doc_ids_only)
-
-        it_formatted_and_logged = progress_bar_iter(
-            iterable=RuAttitudesDocumentProvider.__iter_id_with_doc(
-                docs_it=it, keep_doc_ids_only=keep_doc_ids_only),
-            desc="Loading RuAttitudes Collection [{}]".format("doc ids only" if keep_doc_ids_only else "fully"),
-            unit='docs')
-
-        d = {}
-        docs_read = 0
-        for doc_id, doc in it_formatted_and_logged:
-            assert(isinstance(doc, RuAttitudesDocument) or doc is None)
-            d[doc_id] = RuAttitudesDocumentsConverter.to_brat_doc(doc) if doc is not None else None
-            docs_read += 1
-            if limit is not None and docs_read >= limit:
-                break
-
-        return d
-
-    @staticmethod
-    def __iter_id_with_doc(docs_it, keep_doc_ids_only):
-        if keep_doc_ids_only:
-            for doc_id in docs_it:
-                yield doc_id, None
-        else:
-            for doc in docs_it:
-                assert (isinstance(doc, RuAttitudesDocument))
-                yield doc.ID, doc

arekit/contrib/utils/pipelines/sources/ruattitudes/entity_filter.py

@@ -1,20 +0,0 @@
-from arekit.common.entities.types import OpinionEntityType
-from arekit.contrib.utils.entities.filter import EntityFilter
-
-
-class RuAttitudesEntityFilter(EntityFilter):
-    """ This is a task-specific filter, which is applicable of entity types proposed
-        by the OntoNotesV5 resource: https://catalog.ldc.upenn.edu/LDC2013T19
-        We consider only a short list related to the sentiment attitude extraction task.
-    """
-
-    supported = ["GPE", "PERSON", "LOCAL", "GEO", "ORG"]
-
-    def is_ignored(self, entity, e_type):
-
-        if e_type == OpinionEntityType.Subject:
-            return entity.Type not in RuAttitudesEntityFilter.supported
-        if e_type == OpinionEntityType.Object:
-            return entity.Type not in RuAttitudesEntityFilter.supported
-        else:
-            return True