def read_augmented_corpus(args, verbose=True):
"""
Read the unannotated stage of the augmented corpus
"""
aug_args = copy.copy(args)
aug_args.annotator = None
preselection = {'stage': ['unannotated']}
is_interesting = mk_is_interesting(aug_args, preselected=preselection)
reader = educe.stac.Reader(args.augmented)
anno_files = reader.filter(reader.files(), is_interesting)
return reader.slurp(anno_files, verbose)
def read_augmented_corpus(args, verbose=True):
"""
Read the unannotated stage of the augmented corpus
"""
aug_args = copy.copy(args)
aug_args.annotator = None
preselection = {'stage': ['unannotated']}
is_interesting = mk_is_interesting(aug_args,
preselected=preselection)
reader = educe.stac.Reader(args.augmented)
anno_files = reader.filter(reader.files(), is_interesting)
return reader.slurp(anno_files, verbose)
def _read_corpus_inputs(args):
"""
Read and filter the part of the corpus we want features for
"""
is_interesting = mk_is_interesting(args, preselected={"stage": ["units"]})
reader = educe.stac.Reader(args.corpus)
anno_files = reader.filter(reader.files(), is_interesting)
corpus = reader.slurp(anno_files, verbose=True)
postags = postag.read_tags(corpus, args.corpus)
parses = corenlp.read_results(corpus, args.corpus)
LEXICON.read(args.resources)
return FeatureInput(corpus=corpus,
postags=postags,
parses=parses,
lexicons=[LEXICON],
pdtb_lex=None,
verbnet_entries=None,
inquirer_lex=None)
def _read_corpus_inputs(args):
"""
Read and filter the part of the corpus we want features for
"""
is_interesting = mk_is_interesting(args,
preselected={"stage": ["units"]})
reader = educe.stac.Reader(args.corpus)
anno_files = reader.filter(reader.files(), is_interesting)
corpus = reader.slurp(anno_files, verbose=True)
postags = postag.read_tags(corpus, args.corpus)
parses = corenlp.read_results(corpus, args.corpus)
LEXICON.read(args.resources)
return FeatureInput(corpus=corpus,
postags=postags,
parses=parses,
lexicons=[LEXICON],
pdtb_lex=None,
verbnet_entries=None,
inquirer_lex=None)
# ---------------------------------------------------------------------
# args
# ---------------------------------------------------------------------
arg_parser = argparse.ArgumentParser(description='Dump EDU text' )
arg_parser.add_argument('idir', metavar='DIR',
help='Input directory'
)
educe_group = arg_parser.add_argument_group('corpus filtering arguments')
util.add_corpus_filters(educe_group, fields=[ 'doc' ])
args=arg_parser.parse_args()
args.subdoc = None
args.stage = 'unannotated'
args.annotator = None
is_interesting=util.mk_is_interesting(args)
# ---------------------------------------------------------------------
# main
# ---------------------------------------------------------------------
reader = educe.stac.Reader(args.idir)
anno_files = reader.filter(reader.files(), is_interesting)
trello = tr.TrelloApi(secrets.apikey, secrets.token)
board = trello.boards.get(board_id)
columns = trello.boards.get_list(board_id)
cards = trello.boards.get_card(board_id)
subdocs = collections.defaultdict(list)
for k in anno_files:
subdocs[k.doc].append(k.subdoc)
# # then visit in your web browser to approve
# # and paste in the resulting token
# ---------------------------------------------------------------------
# args
# ---------------------------------------------------------------------
arg_parser = argparse.ArgumentParser(description='Dump EDU text')
arg_parser.add_argument('idir', metavar='DIR', help='Input directory')
educe_group = arg_parser.add_argument_group('corpus filtering arguments')
util.add_corpus_filters(educe_group, fields=['doc'])
args = arg_parser.parse_args()
args.subdoc = None
args.stage = 'unannotated'
args.annotator = None
is_interesting = util.mk_is_interesting(args)
# ---------------------------------------------------------------------
# main
# ---------------------------------------------------------------------
reader = educe.stac.Reader(args.idir)
anno_files = reader.filter(reader.files(), is_interesting)
trello = tr.TrelloApi(secrets.apikey, secrets.token)
board = trello.boards.get(board_id)
columns = trello.boards.get_list(board_id)
cards = trello.boards.get_card(board_id)
subdocs = collections.defaultdict(list)
for k in anno_files:
subdocs[k.doc].append(k.subdoc)
