def get_sentences(number, class_id, annotations="intersected"):
"""Returns number sentences which have the relation type class_id.
Useful if you need to get an overview over sentences with a certain temporal relation.
"""
data = parse_XML("fables-100-temporal-dependency.xml", "McIntyreLapata09Resources/fables")
i=0
go_to_next_textfile = False
for txt in data.textfiles:
go_to_next_textfile = False
if annotations == "union":
txt.compute_union_relations()
elif annotations == "intersected":
txt.compute_intersection_relations()
for rel in txt.relations:
f = Feature(rel)
if f.get_class() == class_id and go_to_next_textfile == False:
# Stop if number relations are reached
if i >= number:
break
i += 1
if rel.target.sentence == rel.source.sentence:
print "---------------"
print "Source event: " +rel.source.content
print "Target event: " +rel.target.content
print rel.target.sentence
print
print "Source Surrounding: " + rel.source.surrounding
print "Target Surrounding: " + rel.target.surrounding
else:
print "---------------"
print "Source event: " +rel.source.content
print "Whole sentence " +rel.source.sentence
print "Surrounding" + rel.source.surrounding
print
print "Target event: " +rel.target.content
print "Whole sentence: " + rel.target.sentence
print "Surrounding: " + rel.target.surrounding
tense_source = f.get_tense_source()
tense_target = f.get_tense_target()
if tense_source == 0:
print "Estimated tense for source event: None"
elif tense_source == 1:
print "Estimated tense for source event: Present"
elif tense_source == 2:
print "Estimated tense for source event: Past"
elif tense_source == 3:
print "Estimated tense for source event: Future"
if tense_target == 0:
print "Estimated tense for target event: None"
elif tense_target == 1:
print "Estimated tense for target event: Present"
elif tense_target == 2:
print "Estimated tense for target event: Past"
elif tense_target == 3:
print "Estimated tense for target event: Future"
aspect_source = f.get_aspect_source()
aspect_target = f.get_aspect_target()
if aspect_source == 0:
print "Estimated aspect for source event: None"
elif aspect_source == 1:
print "Estimated aspect for source event: Progressive"
elif aspect_source == 2:
print "Estimated aspect for source event: Perfect"
elif aspect_source == 3:
print "Estimated aspect for source event: Perfect Progressive"
if aspect_target == 0:
print "Estimated aspect for target event: None"
elif aspect_target == 1:
print "Estimated aspect for target event: Progressive"
elif aspect_target == 2:
print "Estimated aspect for target event: Perfect"
elif aspect_target == 3:
print "Estimated aspect for target event: Perfect Progressive"
print "Distance between events: " + str(f.get_distance())
print "---------------"
print
# Get next sentence from the next text
go_to_next_textfile = True
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)
def get_sentences(number, class_id, annotations="intersected"):
"""Returns number sentences which have the relation type class_id.
Useful if you need to get an overview over sentences with a certain temporal relation.
"""
data = parse_XML("fables-100-temporal-dependency.xml",
"McIntyreLapata09Resources/fables")
i = 0
go_to_next_textfile = False
for txt in data.textfiles:
go_to_next_textfile = False
if annotations == "union":
txt.compute_union_relations()
elif annotations == "intersected":
txt.compute_intersection_relations()
for rel in txt.relations:
f = Feature(rel)
if f.get_class() == class_id and go_to_next_textfile == False:
# Stop if number relations are reached
if i >= number:
break
i += 1
if rel.target.sentence == rel.source.sentence:
print "---------------"
print "Source event: " + rel.source.content
print "Target event: " + rel.target.content
print rel.target.sentence
print
print "Source Surrounding: " + rel.source.surrounding
print "Target Surrounding: " + rel.target.surrounding
else:
print "---------------"
print "Source event: " + rel.source.content
print "Whole sentence " + rel.source.sentence
print "Surrounding" + rel.source.surrounding
print
print "Target event: " + rel.target.content
print "Whole sentence: " + rel.target.sentence
print "Surrounding: " + rel.target.surrounding
tense_source = f.get_tense_source()
tense_target = f.get_tense_target()
if tense_source == 0:
print "Estimated tense for source event: None"
elif tense_source == 1:
print "Estimated tense for source event: Present"
elif tense_source == 2:
print "Estimated tense for source event: Past"
elif tense_source == 3:
print "Estimated tense for source event: Future"
if tense_target == 0:
print "Estimated tense for target event: None"
elif tense_target == 1:
print "Estimated tense for target event: Present"
elif tense_target == 2:
print "Estimated tense for target event: Past"
elif tense_target == 3:
print "Estimated tense for target event: Future"
aspect_source = f.get_aspect_source()
aspect_target = f.get_aspect_target()
if aspect_source == 0:
print "Estimated aspect for source event: None"
elif aspect_source == 1:
print "Estimated aspect for source event: Progressive"
elif aspect_source == 2:
print "Estimated aspect for source event: Perfect"
elif aspect_source == 3:
print "Estimated aspect for source event: Perfect Progressive"
if aspect_target == 0:
print "Estimated aspect for target event: None"
elif aspect_target == 1:
print "Estimated aspect for target event: Progressive"
elif aspect_target == 2:
print "Estimated aspect for target event: Perfect"
elif aspect_target == 3:
print "Estimated aspect for target event: Perfect Progressive"
print "Distance between events: " + str(f.get_distance())
print "---------------"
print
# Get next sentence from the next text
go_to_next_textfile = True
