def generateInstanceFromSentence(self, sentence: Sentence, wordIndex: int) -> Instance:
word = sentence.getWord(wordIndex)
if isinstance(word, AnnotatedWord):
classLabel = NamedEntityType.getNamedEntityString(word.getNamedEntityType())
current = Instance(classLabel)
self.addAttributes(current, sentence, wordIndex)
return current
def generateInstanceFromSentence(self, sentence: Sentence,
wordIndex: int) -> Instance:
"""
Generates a single classification instance of the morphological disambiguation problem for the given word of the
given sentence. If the word does not have a morphological parse, the method throws InstanceNotGenerated.
PARAMETERS
----------
sentence : Sentence
Input sentence.
wordIndex : int
The index of the word in the sentence.
RETURNS
-------
Instance
Classification instance.
"""
word = sentence.getWord(wordIndex)
if isinstance(word, AnnotatedWord):
current = Instance(word.getParse().getTransitionList())
for i in range(self.windowSize):
if wordIndex - self.windowSize + i >= 0:
self.addAttributesForPreviousWords(
current, sentence, wordIndex - self.windowSize + i)
else:
self.addAttributesForEmptyWords(current, "<s>")
self.addAttributesForPreviousWords(current, sentence, wordIndex)
return current
def initWithFile(self, fileName: str):
"""
Constructor for generating a new DataSet from given File.
PARAMETERS
----------
fileName : str
File to generate DataSet from.
"""
self.__instances = InstanceList()
self.__definition = DataDefinition()
inputFile = open(fileName, 'r', encoding='utf8')
lines = inputFile.readlines()
i = 0
for line in lines:
attributes = line.split(",")
if i == 0:
for j in range(len(attributes) - 1):
try:
float(attributes[j])
self.__definition.addAttribute(
AttributeType.CONTINUOUS)
except:
self.__definition.addAttribute(AttributeType.DISCRETE)
else:
if len(attributes) != self.__definition.attributeCount() + 1:
continue
if ";" not in attributes[len(attributes) - 1]:
instance = Instance(attributes[len(attributes) - 1])
else:
labels = attributes[len(attributes) - 1].split(";")
instance = CompositeInstance(labels[0], None, labels)
for j in range(len(attributes) - 1):
if self.__definition.getAttributeType(
j) is AttributeType.CONTINUOUS:
instance.addAttribute(
ContinuousAttribute(float(attributes[j])))
elif self.__definition.getAttributeType(
j) is AttributeType.DISCRETE:
instance.addAttribute(DiscreteAttribute(attributes[j]))
if instance.attributeSize() == self.__definition.attributeCount():
self.__instances.add(instance)
i = i + 1
def generateInstanceFromSentence(self, sentence: Sentence, wordIndex: int) -> Instance:
"""
Generates a single classification instance of the Shallow Parse problem for the given word of the given
sentence. If the word has not been labeled with shallow parse tag yet, the method returns null.
PARAMETERS
----------
sentence : Sentence
Input sentence.
wordIndex : int
The index of the word in the sentence.
RETURNS
-------
Instance
Classification instance.
"""
word = sentence.getWord(wordIndex)
if isinstance(word, AnnotatedWord):
classLabel = word.getShallowParse()
current = Instance(classLabel)
self.addAttributes(current, sentence, wordIndex)
return current