def load_integer_features(self, data):
"""Gives each POS tag in data a number."""
integer_features = []
pos_feature = np.array([])
for txt in data.textfiles:
if self.annotations == "union":
txt.compute_union_relations()
elif self.annotations == "intersected":
txt.compute_intersection_relations()
for rel in txt.relations:
f = Feature(rel)
# Build arrays of integers with which we can fit the encoder
# Standardize because f.get_pos_$x() doesn't have to be of length self.number_tags_per_feature/2
standardized_pos_target = self.standardize_sub_pos_feature(f.get_pos_target())
standardized_pos_source = self.standardize_sub_pos_feature(f.get_pos_source())
# Concatenate the two plain POS tag arrays from target and source event
pos_feature = np.concatenate((standardized_pos_target, standardized_pos_source))
# Transform this array into the corresponding array of integers
integer_feature = self.pos_tags_to_integers(pos_feature)
integer_features.append(integer_feature)
return integer_features
def load_integer_features(self, data):
"""Gives each POS tag in data a number."""
integer_features = []
pos_feature = np.array([])
for txt in data.textfiles:
if self.annotations == "union":
txt.compute_union_relations()
elif self.annotations == "intersected":
txt.compute_intersection_relations()
for rel in txt.relations:
f = Feature(rel)
# Build arrays of integers with which we can fit the encoder
# Standardize because f.get_pos_$x() doesn't have to be of length self.number_tags_per_feature/2
standardized_pos_target = self.standardize_sub_pos_feature(
f.get_pos_target())
standardized_pos_source = self.standardize_sub_pos_feature(
f.get_pos_source())
# Concatenate the two plain POS tag arrays from target and source event
pos_feature = np.concatenate(
(standardized_pos_target, standardized_pos_source))
# Transform this array into the corresponding array of integers
integer_feature = self.pos_tags_to_integers(pos_feature)
integer_features.append(integer_feature)
return integer_features
def load_pos_tags(self, data):
"""Loads all POS tags used in the pos_surrounding area around an event."""
pos_tags = np.array([])
for txt in data.textfiles:
if self.annotations == "union":
txt.compute_union_relations()
elif self.annotations == "intersected":
txt.compute_intersection_relations()
for rel in txt.relations:
f = Feature(rel)
# Collect all pos tags from the data
pos_tags = np.concatenate((pos_tags, f.get_pos_target()))
pos_tags = np.concatenate((pos_tags, f.get_pos_source()))
pos_tags = np.unique(pos_tags)
# Append a blank tag which will be used for filling up features which don't have enough elements
pos_tags = np.append(pos_tags, 'BL')
return pos_tags
def load_pos_tags(self, data):
"""Loads all POS tags used in the pos_surrounding area around an event."""
pos_tags = np.array([])
for txt in data.textfiles:
if self.annotations == "union":
txt.compute_union_relations()
elif self.annotations == "intersected":
txt.compute_intersection_relations()
for rel in txt.relations:
f = Feature(rel)
# Collect all pos tags from the data
pos_tags = np.concatenate((pos_tags, f.get_pos_target()))
pos_tags = np.concatenate((pos_tags, f.get_pos_source()))
pos_tags = np.unique(pos_tags)
# Append a blank tag which will be used for filling up features which don't have enough elements
pos_tags = np.append(pos_tags, 'BL')
return pos_tags
def parse_Features(data, new=False, annotations="union", features=["pos", "stem", "aspect", "tense", "distance", "similarity", "polarity", "modality"], distance=False):
"""Extracts the features out of the dataset and returns a list of features with the corresponding classes.
Args:
data (list): The parsed data from fables-100-temporal-dependency.xml.
new (bool): With new=True a new calculation of Pos() and Stem() can be enforced. Otherwise it will be loaded from a file.
annotations (str): Looking on all relations ("union") or at all relations in common between the annotators ("intersected").
features (list): Determines which features should be activated. Possible values: "pos", "stem", "aspect", "tense", "distance", "similarity", "polarity", "modality".
distance (bool): If set to True parse_Features() will return distance information for the data (needed for evaluation)
"""
# Only compute pos and stem if new flag is set
if "pos" in features or "stem" in features:
if new or not os.path.isfile("set.p"):
pos = Pos(data, 6, annotations)
stem = Stem(data, annotations)
pickle.dump((pos, stem), open("save.p", "wb"))
else:
pos, stem = pickle.load(open("save.p", "rb"))
if distance:
distance_diff = []
X = []
y = np.array([], dtype=int)
for txt in data.textfiles:
# Union or intersected relations?
if annotations == "union":
txt.compute_union_relations()
elif annotations == "intersected":
txt.compute_intersection_relations()
for rel in txt.relations:
f = Feature(rel)
feature = []
# Make polarity feature
if "polarity" in features:
feature = np.concatenate((feature, [f.get_polarity()]))
# Make distance feature
if "distance" in features:
feature = np.concatenate((feature, f.get_distance()))
# Make POS feature
if "pos" in features:
pos_feature = pos.transform(f.get_pos_target(), f.get_pos_source())
pos_feature = pos_feature.toarray()[0]
feature = np.concatenate((feature, pos_feature))
# Make Stem feature
if "stem" in features:
stem_feature = stem.transform(f.get_stem_source(), f.get_stem_target())
stem_feature = stem_feature[0]
feature = np.concatenate((feature, stem_feature))
# Make similarity feature
if "similarity" in features:
feature = np.concatenate((feature, [f.get_similarity_of_words()]))
# Make modality feature
if "modality" in features:
feature = np.concatenate((feature, [f.get_modality()]))
# Make aspect feature
if "aspect" in features:
feature = np.concatenate((feature, f.get_aspect()))
# Make tense feature
if "tense" in features:
feature = np.concatenate((feature, f.get_tense()))
# Append feature to X
X.append(feature)
y = np.append(y, [f.get_class()])
# Append distance information if needed
if distance:
distance_diff.append(f.get_distance_diff())
if distance:
return (X, y, distance_diff)
else:
return (X, y)
