def get_attributes(self):
""" return attributes by tornado Attributes type
@return:
attributes: Attributes
"""
attributes = []
dim_index = 0
dataset_attributes = Dataset.get_attributes(self.dataset)
for attr in dataset_attributes:
for index in range(attr[1]):
attribute = Attribute()
attribute.set_name('{}_{}'.format(attr[0], index))
attribute.set_type(TornadoDic.NUMERIC_ATTRIBUTE)
attribute.set_possible_values([])
if self.split:
range_dim = self.configuration['split']['range'][
self.cur_data_slit][dim_index]
else:
range_dim = self.configuration['all']['range'][dim_index]
attribute.set_bounds_values(range_dim[0], range_dim[1])
if attr[0] != 'cast':
attributes.append(attribute)
dim_index += 1
return [0, 1], attributes
def construct_attribute(self):
for attr in [('warning_level', self.le, [0, 1, 2])]:
for index in range(attr[1]):
attribute = Attribute()
attribute.set_name('{}_{}'.format(attr[0], index))
attribute.set_type(TornadoDic.NOMINAL_ATTRIBUTE)
attribute.set_possible_values(attr[2])
self.attributes.append(attribute)
def construct_attribute():
nb_property = []
for attr in [('warning_level', 1, [1, 2, 3])]:
for index in range(attr[1]):
att = Attribute()
att.set_name('{}_{}'.format(attr[0], index))
att.set_type(TornadoDic.NOMINAL_ATTRIBUTE)
att.set_possible_values(attr[2])
nb_property.append(att)
return nb_property
def read(file_path):
labels = []
attributes = []
attributes_min_max = []
records = []
data_flag = False
reader = open(file_path, "r")
for line in reader:
if line.strip() == '':
continue
if line.startswith("@attribute") or line.startswith("@ATTRIBUTE"):
line = line.strip('\n\r\t')
line = line.split(' ')
attribute_name = line[1]
attribute_value_range = line[2]
attribute = Attribute()
attribute.set_name(attribute_name)
if attribute_value_range.lower() in ['numeric', 'real', 'integer']:
attribute_type = TornadoDic.NUMERIC_ATTRIBUTE
attribute_value_range = []
attributes_min_max.append([0, 0])
else:
attribute_type = TornadoDic.NOMINAL_ATTRIBUTE
attribute_value_range = attribute_value_range.strip('{}').replace("'", "")
attribute_value_range = attribute_value_range.split(',')
attributes_min_max.append([None, None])
attribute.set_type(attribute_type)
attribute.set_possible_values(attribute_value_range)
attributes.append(attribute)
elif line.startswith("@data") or line.startswith("@DATA"):
data_flag = True
labels = attributes[len(attributes) - 1].POSSIBLE_VALUES
attributes.pop(len(attributes) - 1)
continue
elif data_flag is True:
line = re.sub('\s+', '', line)
elements = line.split(',')
for i in range(0, len(elements) - 1):
if attributes[i].TYPE == TornadoDic.NUMERIC_ATTRIBUTE:
elements[i] = float(elements[i])
min_value = attributes_min_max[i][0]
max_value = attributes_min_max[i][1]
if elements[i] < min_value:
min_value = elements[i]
elif elements[i] > max_value:
max_value = elements[i]
attributes_min_max[i] = [min_value, max_value]
records.append(elements)
for i in range(0, len(attributes)):
if attributes[i].TYPE == TornadoDic.NUMERIC_ATTRIBUTE:
attributes[i].set_bounds_values(attributes_min_max[i][0], attributes_min_max[i][1])
return labels, attributes, records
