Did I find the right examples for you? yes no      Crawl my project      Python Jobs

All Samples(7)  |  Call(4)  |  Derive(0)  |  Import(3)

src/s/t/streamcorpus_pipeline-0.5.23.dev1/streamcorpus_pipeline/_tokenizer.py   streamcorpus_pipeline(Download)
from sortedcollection import SortedCollection
import streamcorpus
from streamcorpus import Token, Sentence, EntityType, Chunk, Offset, OffsetType, Gender, MentionType, Attribute, AttributeType
from streamcorpus_pipeline.stages import IncrementalTransform
from streamcorpus_pipeline._taggers import TaggerBatchTransform
        for sent_start, sent_end, sent_str in self._sentences(stream_item.body.clean_visible):
            assert isinstance(sent_str, unicode)
            sent = Sentence()
            sentence_pos = 0
            for start, end in self.word_tokenizer.span_tokenize(sent_str):

src/s/t/streamcorpus_pipeline-0.5.23.dev1/streamcorpus_pipeline/_lingpipe.py   streamcorpus_pipeline(Download)
from nltk.tokenize import WhitespaceTokenizer
 
from streamcorpus import Token, Sentence, EntityType, Chunk, Offset, \
    OffsetType, Gender, MentionType, Attribute, AttributeType
from streamcorpus_pipeline.stages import Configured
                while more_sentence_remains:
                    ## always a sentence
                    sent = Sentence()
 
                    ## this "node" came from for loop above, and it's

src/s/t/streamcorpus_pipeline-0.5.23.dev1/streamcorpus_pipeline/_upgrade_streamcorpus_v0_3_0.py   streamcorpus_pipeline(Download)
        si3.body.sentences['lingpipe'] = []
        for sentence_id, sentence in enumerate(si.body.sentences.get('lingpipe', [])):
            new_sent = streamcorpus.Sentence()
            si3.body.sentences['lingpipe'].append(new_sent)
 

src/s/t/streamcorpus_pipeline-0.5.23.dev1/streamcorpus_pipeline/tests/test_taggers.py   streamcorpus_pipeline(Download)
from __future__ import absolute_import
import pytest
from streamcorpus import Chunk, make_stream_item, add_annotation, \
    Sentence, Token, Annotator, Target, Rating
 
    target_id = 'test_target'
    si.body.sentences[tagger_id] = [
        Sentence(tokens=[
                Token(token='This'),
                Token(token='-LRB-big-RRB- dog'),