def main_pairs(args):
"""Extract feature vectors for pairs of EDUs in the corpus."""
inputs = features.read_corpus_inputs(args)
stage = 'units' if args.parsing else 'discourse'
dialogues = list(mk_high_level_dialogues(inputs, stage))
# these paths should go away once we switch to a proper dumper
out_file = fp.join(args.output,
fp.basename(args.corpus) + '.relations.sparse')
instance_generator = lambda x: x.edu_pairs()
labels = frozenset(SUBORDINATING_RELATIONS + COORDINATING_RELATIONS)
# pylint: disable=invalid-name
# scikit-convention
feats = extract_pair_features(inputs, stage)
vzer = KeyGroupVectorizer()
if args.parsing or args.vocabulary:
vzer.vocabulary_ = load_vocabulary(args.vocabulary)
X_gen = vzer.transform(feats)
else:
X_gen = vzer.fit_transform(feats)
# pylint: enable=invalid-name
labtor = LabelVectorizer(instance_generator, labels, zero=args.parsing)
y_gen = labtor.transform(dialogues)
if not fp.exists(args.output):
os.makedirs(args.output)
dump_all(X_gen, y_gen, out_file, labtor.labelset_, dialogues,
instance_generator)
# dump vocabulary
vocab_file = out_file + '.vocab'
dump_vocabulary(vzer.vocabulary_, vocab_file)
def main_pairs(args):
"""Extract feature vectors for pairs of EDUs in the corpus."""
inputs = read_corpus_inputs(args)
stage = 'units' if args.parsing else 'discourse'
dialogues = list(mk_high_level_dialogues(inputs, stage))
instance_generator = lambda x: x.edu_pairs()
labels = frozenset(SUBORDINATING_RELATIONS +
COORDINATING_RELATIONS)
# pylint: disable=invalid-name
# X, y follow the naming convention in sklearn
feats = extract_pair_features(inputs, stage)
vzer = KeyGroupVectorizer()
if args.parsing or args.vocabulary:
vzer.vocabulary_ = load_vocabulary(args.vocabulary)
X_gen = vzer.transform(feats)
else:
X_gen = vzer.fit_transform(feats)
# pylint: enable=invalid-name
labtor = LabelVectorizer(instance_generator, labels,
zero=args.parsing)
y_gen = labtor.transform(dialogues)
# create directory structure
outdir = args.output
if not fp.exists(outdir):
os.makedirs(outdir)
corpus_name = fp.basename(args.corpus)
# these paths should go away once we switch to a proper dumper
out_file = fp.join(
outdir,
'{corpus_name}.relations.sparse'.format(
corpus_name=corpus_name))
dump_all(X_gen, y_gen, out_file, labtor.labelset_, dialogues,
instance_generator)
# dump vocabulary
vocab_file = fp.join(outdir,
'{corpus_name}.relations.sparse.vocab'.format(
corpus_name=corpus_name))
dump_vocabulary(vzer.vocabulary_, vocab_file)
def main_pairs(args):
"""
The usual main. Extract feature vectors from the corpus
"""
inputs = features.read_corpus_inputs(args)
stage = 'units' if args.parsing else 'discourse'
dialogues = list(mk_high_level_dialogues(inputs, stage))
# these paths should go away once we switch to a proper dumper
out_file = fp.join(args.output, fp.basename(args.corpus))
out_file += '.relations.sparse'
instance_generator = lambda x: x.edu_pairs()
labels = frozenset(SUBORDINATING_RELATIONS +
COORDINATING_RELATIONS)
# pylint: disable=invalid-name
# scikit-convention
feats = extract_pair_features(inputs, stage)
vzer = KeyGroupVectorizer()
if args.parsing or args.vocabulary:
vzer.vocabulary_ = load_vocabulary(args.vocabulary)
X_gen = vzer.transform(feats)
else:
X_gen = vzer.fit_transform(feats)
# pylint: enable=invalid-name
labtor = LabelVectorizer(instance_generator, labels,
zero=args.parsing)
y_gen = labtor.transform(dialogues)
if not fp.exists(args.output):
os.makedirs(args.output)
dump_all(X_gen,
y_gen,
out_file,
labtor.labelset_,
dialogues,
instance_generator)
# dump vocabulary
vocab_file = out_file + '.vocab'
dump_vocabulary(vzer.vocabulary_, vocab_file)
def main(args):
"main for feature extraction mode"
# retrieve parameters
feature_set = args.feature_set
live = args.parsing
# RST data
rst_reader = RstDtParser(args.corpus, args, coarse_rels=True)
rst_corpus = rst_reader.corpus
# TODO: change educe.corpus.Reader.slurp*() so that they return an object
# which contains a *list* of FileIds and a *list* of annotations
# (see sklearn's Bunch)
# on creation of these lists, one can impose the list of names to be
# sorted so that the order in which docs are iterated is guaranteed
# to be always the same
# PTB data
ptb_parser = PtbParser(args.ptb)
# align EDUs with sentences, tokens and trees from PTB
def open_plus(doc):
"""Open and fully load a document
doc is an educe.corpus.FileId
"""
# create a DocumentPlus
doc = rst_reader.decode(doc)
# populate it with layers of info
# tokens
doc = ptb_parser.tokenize(doc)
# syn parses
doc = ptb_parser.parse(doc)
# disc segments
doc = rst_reader.segment(doc)
# disc parse
doc = rst_reader.parse(doc)
# pre-compute the relevant info for each EDU
doc = doc.align_with_doc_structure()
# logical order is align with tokens, then align with trees
# but aligning with trees first for the PTB enables
# to get proper sentence segmentation
doc = doc.align_with_trees()
doc = doc.align_with_tokens()
# dummy, fallback tokenization if there is no PTB gold or silver
doc = doc.align_with_raw_words()
return doc
# generate DocumentPluses
# TODO remove sorted() once educe.corpus.Reader is able
# to iterate over a stable (sorted) list of FileIds
docs = [open_plus(doc) for doc in sorted(rst_corpus)]
# instance generator
instance_generator = lambda doc: doc.all_edu_pairs()
# extract vectorized samples
if args.vocabulary is not None:
vocab = load_vocabulary(args.vocabulary)
vzer = DocumentCountVectorizer(instance_generator,
feature_set,
vocabulary=vocab)
X_gen = vzer.transform(docs)
else:
vzer = DocumentCountVectorizer(instance_generator,
feature_set,
min_df=5)
X_gen = vzer.fit_transform(docs)
# extract class label for each instance
if live:
y_gen = itertools.repeat(0)
elif args.labels is not None:
labelset = load_labels(args.labels)
labtor = DocumentLabelExtractor(instance_generator,
labelset=labelset)
labtor.fit(docs)
y_gen = labtor.transform(docs)
else:
labtor = DocumentLabelExtractor(instance_generator)
# y_gen = labtor.fit_transform(rst_corpus)
# fit then transform enables to get classes_ for the dump
labtor.fit(docs)
y_gen = labtor.transform(docs)
# dump instances to files
if not os.path.exists(args.output):
os.makedirs(args.output)
# data file
of_ext = '.sparse'
if live:
out_file = os.path.join(args.output, 'extracted-features' + of_ext)
else:
of_bn = os.path.join(args.output, os.path.basename(args.corpus))
out_file = '{}.relations{}'.format(of_bn, of_ext)
# dump
dump_all(X_gen, y_gen, out_file, labtor.labelset_, docs,
instance_generator)
# dump vocabulary
vocab_file = out_file + '.vocab'
dump_vocabulary(vzer.vocabulary_, vocab_file)
def main(args):
"main for feature extraction mode"
# retrieve parameters
feature_set = args.feature_set
live = args.parsing
# NEW lecsie features
lecsie_data_dir = args.lecsie_data_dir
# RST data
# fileX docs are currently not supported by CoreNLP
exclude_file_docs = args.corenlp_out_dir
rst_reader = RstDtParser(args.corpus, args,
coarse_rels=args.coarse,
fix_pseudo_rels=args.fix_pseudo_rels,
exclude_file_docs=exclude_file_docs)
rst_corpus = rst_reader.corpus
# TODO: change educe.corpus.Reader.slurp*() so that they return an object
# which contains a *list* of FileIds and a *list* of annotations
# (see sklearn's Bunch)
# on creation of these lists, one can impose the list of names to be
# sorted so that the order in which docs are iterated is guaranteed
# to be always the same
# syntactic preprocessing
if args.corenlp_out_dir:
# get the precise path to CoreNLP parses for the corpus currently used
# the folder layout of CoreNLP's output currently follows that of the
# corpus: RSTtrees-main-1.0/{TRAINING,TEST}, RSTtrees-double-1.0
# FIXME clean rewrite ; this could mean better modelling of the corpus
# subparts/versions, e.g. RST corpus have "version: 1.0", annotators
# "main" or "double"
# find the suffix of the path name that starts with RSTtrees-*
# FIXME find a cleaner way to do this ;
# should probably use pathlib, included in the standard lib
# for python >= 3.4
try:
rel_idx = (args.corpus).index('RSTtrees-WSJ-')
except ValueError:
# if no part of the path starts with "RSTtrees", keep the
# entire path (no idea whether this is good)
relative_corpus_path = args.corpus
else:
relative_corpus_path = args.corpus[rel_idx:]
corenlp_out_dir = os.path.join(args.corenlp_out_dir,
relative_corpus_path)
csyn_parser = CoreNlpParser(corenlp_out_dir)
else:
# TODO improve switch between gold and predicted syntax
# PTB data
csyn_parser = PtbParser(args.ptb)
# FIXME
print('offline syntactic preprocessing: ready')
# align EDUs with sentences, tokens and trees from PTB
def open_plus(doc):
"""Open and fully load a document
doc is an educe.corpus.FileId
"""
# create a DocumentPlus
doc = rst_reader.decode(doc)
# populate it with layers of info
# tokens
doc = csyn_parser.tokenize(doc)
# syn parses
doc = csyn_parser.parse(doc)
# disc segments
doc = rst_reader.segment(doc)
# disc parse
doc = rst_reader.parse(doc)
# pre-compute the relevant info for each EDU
doc = doc.align_with_doc_structure()
# logical order is align with tokens, then align with trees
# but aligning with trees first for the PTB enables
# to get proper sentence segmentation
doc = doc.align_with_trees()
doc = doc.align_with_tokens()
# dummy, fallback tokenization if there is no PTB gold or silver
doc = doc.align_with_raw_words()
return doc
# generate DocumentPluses
# TODO remove sorted() once educe.corpus.Reader is able
# to iterate over a stable (sorted) list of FileIds
docs = [open_plus(doc) for doc in sorted(rst_corpus)]
# instance generator
instance_generator = lambda doc: doc.all_edu_pairs()
split_feat_space = 'dir_sent'
# extract vectorized samples
if args.vocabulary is not None:
vocab = load_vocabulary(args.vocabulary)
vzer = DocumentCountVectorizer(instance_generator,
feature_set,
lecsie_data_dir=lecsie_data_dir,
vocabulary=vocab,
split_feat_space=split_feat_space)
X_gen = vzer.transform(docs)
else:
vzer = DocumentCountVectorizer(instance_generator,
feature_set,
lecsie_data_dir=lecsie_data_dir,
min_df=5,
split_feat_space=split_feat_space)
X_gen = vzer.fit_transform(docs)
# extract class label for each instance
if live:
y_gen = itertools.repeat(0)
elif args.labels is not None:
labelset = load_labels(args.labels)
labtor = DocumentLabelExtractor(instance_generator,
labelset=labelset)
labtor.fit(docs)
y_gen = labtor.transform(docs)
else:
labtor = DocumentLabelExtractor(instance_generator)
# y_gen = labtor.fit_transform(rst_corpus)
# fit then transform enables to get classes_ for the dump
labtor.fit(docs)
y_gen = labtor.transform(docs)
# dump instances to files
if not os.path.exists(args.output):
os.makedirs(args.output)
# data file
of_ext = '.sparse'
if live:
out_file = os.path.join(args.output, 'extracted-features' + of_ext)
else:
of_bn = os.path.join(args.output, os.path.basename(args.corpus))
out_file = '{}.relations{}'.format(of_bn, of_ext)
# dump EDUs and features in svmlight format
dump_all(X_gen, y_gen, out_file, labtor.labelset_, docs,
instance_generator)
# dump vocabulary
vocab_file = out_file + '.vocab'
dump_vocabulary(vzer.vocabulary_, vocab_file)
def main(args):
"main for feature extraction mode"
# retrieve parameters
feature_set = args.feature_set
live = args.parsing
# NEW lecsie features
lecsie_data_dir = args.lecsie_data_dir
# RST data
# fileX docs are currently not supported by CoreNLP
exclude_file_docs = args.corenlp_out_dir
rst_reader = RstDtParser(args.corpus, args,
coarse_rels=args.coarse,
fix_pseudo_rels=args.fix_pseudo_rels,
exclude_file_docs=exclude_file_docs)
rst_corpus = rst_reader.corpus
# TODO: change educe.corpus.Reader.slurp*() so that they return an object
# which contains a *list* of FileIds and a *list* of annotations
# (see sklearn's Bunch)
# on creation of these lists, one can impose the list of names to be
# sorted so that the order in which docs are iterated is guaranteed
# to be always the same
# syntactic preprocessing
if args.corenlp_out_dir:
# get the precise path to CoreNLP parses for the corpus currently used
# the folder layout of CoreNLP's output currently follows that of the
# corpus: RSTtrees-main-1.0/{TRAINING,TEST}, RSTtrees-double-1.0
# FIXME clean rewrite ; this could mean better modelling of the corpus
# subparts/versions, e.g. RST corpus have "version: 1.0", annotators
# "main" or "double"
# find the suffix of the path name that starts with RSTtrees-*
# FIXME find a cleaner way to do this ;
# should probably use pathlib, included in the standard lib
# for python >= 3.4
try:
rel_idx = (args.corpus).index('RSTtrees-WSJ-')
except ValueError:
# if no part of the path starts with "RSTtrees", keep the
# entire path (no idea whether this is good)
relative_corpus_path = args.corpus
else:
relative_corpus_path = args.corpus[rel_idx:]
corenlp_out_dir = os.path.join(args.corenlp_out_dir,
relative_corpus_path)
csyn_parser = CoreNlpParser(corenlp_out_dir)
else:
# TODO improve switch between gold and predicted syntax
# PTB data
csyn_parser = PtbParser(args.ptb)
# FIXME
print('offline syntactic preprocessing: ready')
# align EDUs with sentences, tokens and trees from PTB
def open_plus(doc):
"""Open and fully load a document
doc is an educe.corpus.FileId
"""
# create a DocumentPlus
doc = rst_reader.decode(doc)
# populate it with layers of info
# tokens
doc = csyn_parser.tokenize(doc)
# syn parses
doc = csyn_parser.parse(doc)
# disc segments
doc = rst_reader.segment(doc)
# disc parse
doc = rst_reader.parse(doc)
# pre-compute the relevant info for each EDU
doc = doc.align_with_doc_structure()
# logical order is align with tokens, then align with trees
# but aligning with trees first for the PTB enables
# to get proper sentence segmentation
doc = doc.align_with_trees()
doc = doc.align_with_tokens()
# dummy, fallback tokenization if there is no PTB gold or silver
doc = doc.align_with_raw_words()
return doc
# generate DocumentPluses
# TODO remove sorted() once educe.corpus.Reader is able
# to iterate over a stable (sorted) list of FileIds
docs = [open_plus(doc) for doc in sorted(rst_corpus)]
# instance generator
instance_generator = lambda doc: doc.all_edu_pairs()
split_feat_space = 'dir_sent'
# extract vectorized samples
if args.vocabulary is not None:
vocab = load_vocabulary(args.vocabulary)
vzer = DocumentCountVectorizer(instance_generator,
feature_set,
lecsie_data_dir=lecsie_data_dir,
vocabulary=vocab,
split_feat_space=split_feat_space)
X_gen = vzer.transform(docs)
else:
vzer = DocumentCountVectorizer(instance_generator,
feature_set,
lecsie_data_dir=lecsie_data_dir,
min_df=5,
split_feat_space=split_feat_space)
X_gen = vzer.fit_transform(docs)
# extract class label for each instance
if live:
y_gen = itertools.repeat(0)
elif args.labels is not None:
labelset = load_labels(args.labels)
labtor = DocumentLabelExtractor(instance_generator,
labelset=labelset)
labtor.fit(docs)
y_gen = labtor.transform(docs)
else:
labtor = DocumentLabelExtractor(instance_generator)
# y_gen = labtor.fit_transform(rst_corpus)
# fit then transform enables to get classes_ for the dump
labtor.fit(docs)
y_gen = labtor.transform(docs)
# dump instances to files
if not os.path.exists(args.output):
os.makedirs(args.output)
# data file
of_ext = '.sparse'
if live:
out_file = os.path.join(args.output, 'extracted-features' + of_ext)
else:
of_bn = os.path.join(args.output, os.path.basename(args.corpus))
out_file = '{}.relations{}'.format(of_bn, of_ext)
# dump EDUs and features in svmlight format
dump_all(X_gen, y_gen, out_file, labtor.labelset_, docs,
instance_generator)
# dump vocabulary
vocab_file = out_file + '.vocab'
dump_vocabulary(vzer.vocabulary_, vocab_file)