def _calc_a_file(self, files_to_compare, debug):
assert(isinstance(files_to_compare, FilesToCompare))
# Reading test answers.
test_opins = OpinionCollection.from_file(
files_to_compare.test_filepath,
self.synonyms_filepath,
stemmer=self.stemmer)
# Reading etalon answers.
etalon_opins = OpinionCollection.from_file(
files_to_compare.etalon_filepath,
self.synonyms_filepath,
stemmer=self.stemmer)
if debug:
print "{} <-> {}, {}".format(
files_to_compare.test_filepath,
files_to_compare.etalon_filepath,
files_to_compare.index)
# Comparing test and etalon results.
results = self._check(etalon_opins, test_opins)
# Save result comparison into file.
# TODO. remove path declaration from here.
comparison_file = "{}/art{}.comp.txt".format(
self.user_answers, str(files_to_compare.index))
if debug:
print "Save comparison file: {}".format(comparison_file)
results.to_csv(comparison_file)
return self._calcPrecisionAndRecall(results)
def to_opinion_collections(self, news_indices, synonyms):
# O(N^2)
assert (isinstance(news_indices, list))
assert (isinstance(synonyms, SynonymsCollection))
result = []
for news_ID in news_indices:
result_opinions = OpinionCollection(None, synonyms)
for r in self.relations:
assert (isinstance(r, ExtractedRelation))
if r.text_position.news_ID != news_ID:
continue
if r.label == NeutralLabel(): # ignore neutral labels
continue
o = r.create_opinion()
if not result_opinions.has_opinion_by_synonyms(o):
result_opinions.add_opinion(o)
result.append((news_ID, result_opinions))
return result
def predict(self, dest_data_type=DataType.Test):
self.relation_collections[dest_data_type].reset_labels()
for index, relation_groups in enumerate(
self.relation_collections[dest_data_type].
iter_by_linked_relations_groups(self.Settings.BatchSize)):
batch = Batch(relation_groups, self.Settings.GroupSize)
feed_dict = self.create_feed_dict(batch, dest_data_type)
result = self.sess.run([self.network.Labels], feed_dict=feed_dict)
uint_labels = result[0]
for group_index, group in enumerate(batch.iter_groups):
for relation in group:
assert (isinstance(relation, ExtractedRelation))
self.relation_collections[dest_data_type].apply_label(
label=Label.from_uint(int(uint_labels[group_index])),
relation_id=relation.relation_id)
for news_ID in self.io.get_data_indices(dest_data_type):
collection = OpinionCollection(None, self.synonyms,
self.Settings.Stemmer)
self.relation_collections[dest_data_type].fill_opinion_collection(
collection,
news_ID,
lambda labels: labels[0],
debug_check_collection=False)
collection.save(
self.io.get_opinion_output_filepath(
news_ID, self.io.get_model_root(dest_data_type)))
return self._evaluate(dest_data_type, self.Settings.Stemmer)
def read_opinions(filepath,
synonyms,
custom_opin_ends_iter=None,
read_sentiment=True,
skip_non_added=True):
assert (isinstance(synonyms, SynonymsCollection))
assert (callable(custom_opin_ends_iter) or custom_opin_ends_iter is None)
assert (isinstance(read_sentiment, bool))
assert (isinstance(skip_non_added, bool))
opinions = OpinionCollection(opinions=[], synonyms=synonyms)
it = __iter_opinion_end_values(filepath, read_sentiment) if custom_opin_ends_iter is None \
else custom_opin_ends_iter(read_sentiment)
for left_value, right_value, sentiment in tqdm(it, "Reading opinions:"):
o = Opinion(value_left=left_value,
value_right=right_value,
sentiment=Label.from_int(sentiment))
add_result = opinions.try_add_opinion(o)
msg = "Warning: opinion '{}->{}' was skipped!".format(
o.value_left, o.value_right)
if add_result is False:
if not skip_non_added:
raise Exception(msg)
else:
print(msg)
return opinions
def _process_into_collections(self, indices, data_type):
"""
Processing all parameters into collections.
returns:
NewsWordsCollection and RelationCollection
"""
def find_feature_vector_for_opinion(opinion_vector_collections, opinion):
assert(isinstance(opinion_vector_collections, list))
for collection in opinion_vector_collections:
assert(isinstance(collection, OpinionVectorCollection))
if not collection.has_opinion(opinion):
continue
return collection.find_by_opinion(opinion)
return None
assert(isinstance(indices, list))
erc = ExtractedRelationsCollection()
ntc = NewsTermsCollection()
for news_index in indices:
assert(isinstance(news_index, int))
entity_filepath = self.io.get_entity_filepath(news_index)
news_filepath = self.io.get_news_filepath(news_index)
opin_filepath = self.io.get_opinion_input_filepath(news_index)
neutral_filepath = self.io.get_neutral_filepath(news_index, data_type)
news = News.from_file(news_filepath,
EntityCollection.from_file(entity_filepath, self.Settings.Stemmer),
stemmer=self.Settings.Stemmer)
opinions_collections = [OpinionCollection.from_file(neutral_filepath,
self.io.get_synonyms_collection_filepath(),
self.Settings.Stemmer)]
if data_type == DataType.Train:
opinions_collections.append(OpinionCollection.from_file(opin_filepath,
self.io.get_synonyms_collection_filepath(),
self.Settings.Stemmer))
news_terms = NewsTerms.create_from_news(news_index, news, keep_tokens=self.Settings.KeepTokens)
for relations, opinion in self._extract_relations(opinions_collections, news, news_terms):
feature_vector = find_feature_vector_for_opinion(self.get_opinion_vector_collection(news_index, data_type),
opinion)
erc.add_news_relations(relations,
opinion,
news_terms,
news_index,
feature_vector)
ntc.add_news_terms(news_terms)
return ntc, erc
def __read_collection(self, io, data_type, settings):
assert(isinstance(io, RuSentRelNetworkIO))
assert(isinstance(data_type, unicode))
assert(isinstance(settings, CommonModelSettings))
erc = ExtractedRelationsCollection()
ntc = NewsTermsCollection()
entities_list = []
missed_relations_total = 0
for news_index in io.get_data_indices(data_type):
assert(isinstance(news_index, int))
entity_filepath = io.get_entity_filepath(news_index)
news_filepath = io.get_news_filepath(news_index)
opin_filepath = io.get_etalon_doc_opins_filepath(news_index)
neutral_filepath = io.get_neutral_filepath(news_index, data_type)
entities = EntityCollection.from_file(entity_filepath, settings.Stemmer, self.__synonyms)
news = News.from_file(news_filepath, entities)
opinions_collections = [OpinionCollection.from_file(neutral_filepath, self.__synonyms)]
if data_type == DataType.Train:
opinions_collections.append(OpinionCollection.from_file(opin_filepath, self.__synonyms))
news_terms = NewsTerms.create_from_news(news_index, news, keep_tokens=settings.KeepTokens)
news_terms_helper = NewsTermsHelper(news_terms)
if DebugKeys.NewsTermsStatisticShow:
news_terms_helper.debug_statistics()
if DebugKeys.NewsTermsShow:
news_terms_helper.debug_show_terms()
for relations, opinion, opinions in self.__extract_relations(opinions_collections, news, news_terms):
reversed = ContextModelInitHelper.__find_or_create_reversed_opinion(opinion, opinions_collections)
missed = erc.add_news_relations(relations=relations,
label=self.__labels_helper.create_label_from_opinions(forward=opinion, backward=reversed),
news_terms=news_terms,
news_index=news_index,
check_relation_is_correct=lambda r: Sample.check_ability_to_create_sample(
window_size=settings.TermsPerContext,
relation=r))
missed_relations_total += missed
ntc.add_news_terms(news_terms)
entities_list.append(entities)
return ntc, erc, entities_list, missed_relations_total
def __clone_with_different_label(self, opinions, label):
assert(isinstance(opinions, OpinionCollection))
assert(isinstance(label, Label))
ro = OpinionCollection(opinions=[],
synonyms=self.Synonyms)
for o in opinions:
assert(isinstance(o, Opinion))
no = Opinion(value_left=o.value_left,
value_right=o.value_right,
sentiment=label)
ro.add_opinion(no)
return ro
def calc_a_file(self, files_to_compare, debug):
assert (isinstance(files_to_compare, FilesToCompare))
# Reading test answers.
test_opins = OpinionCollection.from_file(
filepath=files_to_compare.TestFilepath, synonyms=self.__synonyms)
# Reading etalon answers.
etalon_opins = OpinionCollection.from_file(
filepath=files_to_compare.EtalonFilepath, synonyms=self.__synonyms)
if debug:
print "{} <-> {}, {}".format(files_to_compare.TestFilepath,
files_to_compare.EtalonFilepath,
files_to_compare.index)
return test_opins, etalon_opins
def __save_etalon(self, relation_collection_helper):
assert (isinstance(relation_collection_helper,
ExtractedRelationsCollectionHelper))
relation_collection_helper.save_into_opinion_collections(
create_opinion_collection=lambda: OpinionCollection(
opinions=None, synonyms=self.ReadOnlySynonymsCollection),
create_filepath_by_news_id=lambda news_id: self.IO.
get_etalon_doc_opins_filepath(news_id),
label_calculation_mode=LabelCalculationMode.FIRST_APPEARED)
def __extract_sentence_opinion_refs(text_objects_collection, title_opinions, synonyms):
assert(isinstance(text_objects_collection, TextObjectsCollection))
opinion_list = []
opinion_refs = []
added_opinions = OpinionCollection(opinions=None, synonyms=synonyms)
TextProcessor.__setup_tags(text_objects_collection=text_objects_collection,
synonyms=synonyms)
for l_obj in text_objects_collection:
for r_obj in text_objects_collection:
if l_obj.CollectionInd == r_obj.CollectionInd:
continue
opinion = Opinion(value_left=l_obj.get_value(),
value_right=r_obj.get_value(),
sentiment=NeutralLabel())
is_title_already_has_opinion = title_opinions.has_synonymous_opinion(opinion)
is_already_added = added_opinions.has_synonymous_opinion(opinion)
is_appropriate = is_title_already_has_opinion and not is_already_added
if not is_appropriate:
continue
opinion = title_opinions.get_synonymous_opinion(opinion)
o = RefOpinion(left_index=l_obj.CollectionInd,
right_index=r_obj.CollectionInd,
sentiment=opinion.sentiment)
opinion_refs.append(o)
opinion_list.append(opinion)
add_result = added_opinions.try_add_opinion(opinion)
assert(add_result)
return opinion_refs, opinion_list
def create_test_opinions(test_collections, labels, synonyms_filepath, stemmer):
assert (isinstance(test_collections, list))
assert (isinstance(labels, np.ndarray))
assert (isinstance(stemmer, Stemmer))
label_index = 0
opinion_collection_list = []
synonyms = SynonymsCollection.from_file(synonyms_filepath, stemmer=stemmer)
for c in test_collections:
opinions = OpinionCollection(None, synonyms, stemmer)
for opinion_vector in c:
l = Label.from_int(int(labels[label_index]))
opinion_vector.set_label(l)
o = opinions.create_opinion(opinion_vector.value_left,
opinion_vector.value_right,
opinion_vector.label)
if not opinions.has_opinion_by_synonyms(o) and not isinstance(
l, NeutralLabel):
opinions.add_opinion(o)
elif not isinstance(l, NeutralLabel):
print "Failed for o={}".format(o.to_unicode().encode('utf-8'))
label_index += 1
opinion_collection_list.append(opinions)
return opinion_collection_list
def _process_into_collections(self, indices, entity_indices,
word_embedding, window_size_in_words,
is_train_collection):
assert (isinstance(indices, list))
assert (isinstance(word_embedding, Embedding))
assert (isinstance(is_train_collection, bool))
rc = ExtractedRelationsCollection()
nwc = NewsWordsCollection(entity_indices, word_embedding)
for n in indices:
assert (type(n) == int)
entity_filepath = self.io.get_entity_filepath(n)
news_filepath = self.io.get_news_filepath(n)
opin_filepath = self.io.get_opinion_input_filepath(n)
neutral_filepath = self.io.get_neutral_filepath(
n, is_train_collection)
news = News.from_file(news_filepath,
EntityCollection.from_file(entity_filepath))
opinions_collections = [
OpinionCollection.from_file(neutral_filepath,
self.synonyms_filepath)
]
if is_train_collection:
opinions_collections.append(
OpinionCollection.from_file(opin_filepath,
self.synonyms_filepath))
news_words = NewsWords(n, news)
news_descriptor = self.create_news_descriptor(
n, news, news_words, opinions_collections, is_train_collection)
rc.add_news_relations(news_descriptor, self.synonyms,
window_size_in_words, is_train_collection)
nwc.add_news(news_words)
return nwc, rc
def get_method_statistic(files_to_compare_list, synonyms_filepath, stemmer):
"""
Calculate statistic based on result files
files_to_compare_list: list
list of FilesToCompare objects
synonyms_filepath: str
stemmer: Stemmer
"""
assert(isinstance(stemmer, Stemmer))
columns = ["t_all", "t_pos", "t_neg", "e_all", "e_pos", "e_neg"]
df = pd.DataFrame(columns=columns)
for files_to_compare in files_to_compare_list:
assert(isinstance(files_to_compare, FilesToCompare))
test_opins = OpinionCollection.from_file(
files_to_compare.test_filepath, synonyms_filepath, stemmer=stemmer)
etalon_opins = OpinionCollection.from_file(
files_to_compare.etalon_filepath, synonyms_filepath, stemmer=stemmer)
df.loc[files_to_compare.index] = [
MethodStatistic.founded_opins(test_opins, etalon_opins),
MethodStatistic.founded_opins(test_opins, etalon_opins, PositiveLabel()),
MethodStatistic.founded_opins(test_opins, etalon_opins, NegativeLabel()),
len(etalon_opins),
len(list(etalon_opins.iter_sentiment(PositiveLabel()))),
len(list(etalon_opins.iter_sentiment(NegativeLabel())))]
df.loc['sum'] = [float(df[c].sum()) for c in columns]
df.loc['found'] = None
df.loc['found']['t_all'] = float(df.loc['sum']['t_all']) / df.loc['sum']['e_all']
df.loc['found']['t_pos'] = float(df.loc['sum']['t_pos']) / df.loc['sum']['e_pos']
df.loc['found']['t_neg'] = float(df.loc['sum']['t_neg']) / df.loc['sum']['e_neg']
return df
def process_news_content(self, news_info, title_opinions, synonyms):
""" news_id: assumes a unique name/key
Perform sentences parsing, excluding news title
"""
assert(isinstance(news_info, NewsInfo))
text_opinions = OpinionCollection(opinions=None, synonyms=synonyms)
cds = []
for index in range(news_info.sentences_count()):
_, parsed_sentence, s_objects, s_frames = self._process_sentence_core(news_info, s_ind=index)
s_opinion_refs, s_opinions_list = self.__extract_sentence_opinion_refs(
text_objects_collection=s_objects,
title_opinions=title_opinions,
synonyms=synonyms)
if len(s_opinion_refs) == 0:
continue
for opinion in s_opinions_list:
if not text_opinions.has_synonymous_opinion(opinion):
add_result = text_opinions.try_add_opinion(opinion)
assert(add_result)
cd = ContextDescriptor(
sentence_index=index,
parsed_text=parsed_sentence,
opinion_refs=s_opinion_refs,
objects_collection=s_objects,
text_frames=s_frames,
frames=self.Settings.Frames)
cds.append(cd)
return cds, text_opinions
def predict_core(self,
dest_data_type,
rc_labeling_callback):
assert(isinstance(dest_data_type, unicode))
assert(callable(rc_labeling_callback))
rc = self.get_relations_collection(dest_data_type)
rch = self.get_relations_collection_helper(dest_data_type)
assert(isinstance(rc, ExtractedRelationsCollection))
assert(isinstance(rch, ExtractedRelationsCollectionHelper))
rc.reset_labels()
assert(rc.check_all_relations_without_labels())
predict_log = rc_labeling_callback(rc, dest_data_type)
assert(rc.check_all_relations_has_labels())
rch.debug_labels_statistic()
rch.save_into_opinion_collections(
create_opinion_collection=lambda: OpinionCollection(opinions=None,
synonyms=self.ReadOnlySynonymsCollection),
create_filepath_by_news_id=lambda news_id: self.IO.get_model_doc_opins_filepath(doc_id=news_id,
data_type=dest_data_type),
label_calculation_mode=self.Settings.RelationLabelCalculationMode)
eval_result = self.get_eval_helper().evaluate_model(data_type=dest_data_type,
io=self.IO,
indices=rch.iter_unique_news_ids(),
synonyms=self.ReadOnlySynonymsCollection)
rc.reset_labels()
return eval_result, predict_log
def opinions_between_entities(E, diff, news, synonyms, sentiment_opins=None):
""" Relations that had the same difference
"""
def try_add_opinion(o, added, neutral_opins):
assert (isinstance(o, Opinion))
assert (isinstance(neutral_opins, OpinionCollection))
# Filter if there is a sentiment relation
if sentiment_opins is not None:
if sentiment_opins.has_opinion_by_synonyms(o):
return
if neutral_opins.has_opinion_by_synonyms(o):
return
added.add(o.create_value_id())
neutral_opins.add_opinion(o)
def is_ignored(entity):
# TODO. Move ignored entities into core.
return env.stemmer.lemmatize_to_str(entity.value) in IGNORED_ENTITIES
def get_entity_synonyms(entity):
return synonyms.get_synonyms_list(entity.value), \
synonyms.get_synonym_group_index(entity.value)
added = set()
c = OpinionCollection(opinions=None, synonyms=synonyms)
for i in range(E.shape[0]):
for j in range(E.shape[1]):
if E[i][j] != diff:
continue
e1 = news.entities.get_entity_by_index(i)
e2 = news.entities.get_entity_by_index(j)
if is_ignored(e1) or is_ignored(e2):
continue
if not synonyms.has_synonym(e1.value):
synonyms.add_synonym(e1.value)
if not synonyms.has_synonym(e2.value):
synonyms.add_synonym(e2.value)
sl1, g1 = get_entity_synonyms(e1)
sl2, g2 = get_entity_synonyms(e2)
r_left = sl1[0]
r_right = sl2[0]
# Filter the same groups
if g1 == g2:
"Entities '{}', and '{}' a part of the same synonym group".format(
r_left.encode('utf-8'), r_right.encode('utf-8'))
continue
try_add_opinion(Opinion(r_left, r_right, NeutralLabel()), added, c)
try_add_opinion(Opinion(r_right, r_left, NeutralLabel()), added, c)
return c
#
# Train
#
root = io_utils.train_root()
for n in io_utils.train_indices():
entity_filepath = root + "art{}.ann".format(n)
news_filepath = root + "art{}.txt".format(n)
opin_filepath = root + "art{}.opin.txt".format(n)
neutral_filepath = root + "art{}.neut.txt".format(n)
print neutral_filepath
entities = EntityCollection.from_file(entity_filepath)
news = News.from_file(news_filepath, entities)
opinions = OpinionCollection.from_file(opin_filepath,
io_utils.get_synonyms_filepath())
neutral_opins = make_neutrals(news, synonyms, opinions)
neutral_opins.save(neutral_filepath)
#
# Test
#
root = io_utils.test_root()
for n in io_utils.test_indices():
entity_filepath = path.join(root, "art{}.ann".format(n))
news_filepath = path.join(root, "art{}.txt".format(n))
neutral_filepath = path.join(root, "art{}.neut.txt".format(n))
print neutral_filepath
def predict(self, dest_data_type=DataType.Test):
def calculate_label(relation_labels):
assert(isinstance(relation_labels, list))
label = None
if self.Settings.RelationLabelCalculationMode == LabelCalculationMode.FIRST_APPEARED:
label = relation_labels[0]
if self.Settings.RelationLabelCalculationMode == LabelCalculationMode.AVERAGE:
label = Label.from_int(np.sign(sum([l.to_int() for l in relation_labels])))
if DebugKeys.PredictLabel:
print [l.to_int() for l in relation_labels]
print "Result: {}".format(label.to_int())
return label
assert(isinstance(dest_data_type, unicode))
self._relations_collections[dest_data_type].reset_labels()
prediction_collection = RelationPredictionResultCollection(len(self._relations_collections[dest_data_type]))
for bags_group in self.bags_collection[dest_data_type].iter_by_groups(self.Settings.BagsPerMinibatch):
minibatch = MiniBatch(bags_group)
feed_dict = self.create_feed_dict(minibatch, data_type=dest_data_type)
log_names, log_params = self.network.Log
result = self.sess.run([self.network.Labels, self.network.Output] + log_params, feed_dict=feed_dict)
uint_labels = result[0]
output = result[1]
if DebugKeys.PredictBatchDisplayLog:
self._display_log(log_names, result[2:])
# apply labels
sample_indices_count = 0
for sample_index, sample in enumerate(minibatch.iter_by_samples()):
label = Label.from_uint(int(uint_labels[sample_index]))
self._relations_collections[dest_data_type].apply_label(label, sample.RelationID)
prediction_collection.add(sample.RelationID, RelationPredictionResult(output[sample_index]))
sample_indices_count += 1
assert(sample_indices_count == len(uint_labels))
assert(self._relations_collections[dest_data_type].debug_check_all_relations_has_labels())
self._relations_collections[dest_data_type].debug_labels_statistic(dest_data_type)
# Compose Result
self._relations_collections[dest_data_type].save(
self.io.get_relations_filepath(data_type=dest_data_type,
epoch=self._last_fit_epoch_index))
prediction_collection.save(
self.io.get_relations_prediction_filepath(data_type=dest_data_type,
epoch=self._last_fit_epoch_index))
for news_ID in self.io.get_data_indices(dest_data_type):
collection = OpinionCollection(None, self.synonyms, self.settings.Stemmer)
self._relations_collections[dest_data_type].fill_opinion_collection(collection, news_ID, calculate_label)
collection.save(self.io.get_opinion_output_filepath(news_ID, self.io.get_model_root(dest_data_type)))
return self._evaluate(dest_data_type, self.Settings.Stemmer)
def _extract_opinions_from_title(self, title_terms, title_objects, title_frames, synonyms):
assert(isinstance(title_terms, list))
assert(isinstance(title_objects, TextObjectsCollection))
assert(isinstance(title_frames, TextFrameVariantsCollection))
assert(isinstance(synonyms, SynonymsCollection))
opinion_refs = []
title_opinions = OpinionCollection(opinions=None, synonyms=synonyms)
TextProcessor.__setup_tags(text_objects_collection=title_objects,
synonyms=synonyms)
for l_obj in title_objects:
for r_obj in title_objects:
l_bound = l_obj.get_bound()
r_bound = r_obj.get_bound()
if l_bound.TermIndex == r_bound.TermIndex:
continue
if l_bound.TermIndex >= r_bound.TermIndex:
continue
i = l_obj.CollectionInd
j = r_obj.CollectionInd
if not self.__check_auth_correctness(i=i, j=j, objects=title_objects):
continue
label = self.decide_label_of_pair_in_title_optional(
i=i, j=j,
title_objects=title_objects,
title_frames=title_frames)
if label is None:
# Considered by pair-base processor
continue
opinion = Opinion(value_left=l_obj.get_value(),
value_right=r_obj.get_value(),
sentiment=label)
self.__debug_opinions_created += 1
if self.__check_obj_preposition_in_title:
if self.__reject_by_russian_prepositions(l_obj=l_obj, r_obj=r_obj, title_terms=title_terms):
self.__debug_opinions_rejected_by_preps += 1
continue
if not self.__guarantee_synonyms_presence(synonyms=synonyms, obj_value=opinion.value_left):
self.__debug_opinions_with_missed_synonyms += 1
continue
if not self.__guarantee_synonyms_presence(synonyms=synonyms, obj_value=opinion.value_right):
self.__debug_opinions_with_missed_synonyms += 1
continue
lg_ind = synonyms.get_synonym_group_index(opinion.value_left)
rg_ind = synonyms.get_synonym_group_index(opinion.value_right)
if lg_ind == rg_ind:
self.__debug_opinions_looped += 1
continue
if not title_opinions.has_synonymous_opinion(opinion):
# OK, adding
self.__debug_opinions_total_extracted_from_titles += 1
add_result = title_opinions.try_add_opinion(opinion)
assert(add_result)
else:
self.__debug_opinions_title_synonymous_existed += 1
opinion_ref = RefOpinion(left_index=i, right_index=j, sentiment=opinion.sentiment)
opinion_refs.append(opinion_ref)
return opinion_refs, title_opinions
# Train collection
#
root = io_utils.train_root()
for n in io_utils.train_indices():
entity_filepath = root + "art{}.ann".format(n)
opin_filepath = root + "art{}.opin.txt".format(n)
neutral_filepath = root + "art{}.neut.txt".format(n)
news_filepath = root + "art{}.txt".format(n)
vector_output = root + "art{}.vectors.txt".format(n)
print vector_output
entities = EntityCollection.from_file(entity_filepath)
news = News.from_file(news_filepath, entities)
sentiment_opins = OpinionCollection.from_file(
opin_filepath, io_utils.get_synonyms_filepath())
neutral_opins = OpinionCollection.from_file(
neutral_filepath, io_utils.get_synonyms_filepath())
# filter_neutral(neutral_opins)
vectors = vectorize_opinions(
news, entities, [sentiment_opins, neutral_opins])
vectors.save(vector_output)
#
# Test collection
#
root = io_utils.test_root()
for n in io_utils.test_indices():