def set_mydataset_instanceset(self, my_dataset, x_array, output, isTrain):
my_dataset.instanceSet = InstanceSet()
my_dataset.instanceSet.instanceSet = []
for i in range(0, len(x_array)):
newInstance = Instance()
line = ''
for j in x_array[i]:
if j is not None:
line = line + str(j) + ','
line = line + output[i]
newInstance.setThreeParameters(
line, isTrain, len(my_dataset.instanceSet.instanceSet))
my_dataset.instanceSet.instanceSet.append(newInstance)
def addInstance(self, inst):
i = 0
nVector = []
if self.instanceSet is not None:
nVector = [Instance() for x in range(len(self.instanceSet) + 1)]
for i in range(0, len(self.instanceSet)):
nVector[i] = self.instanceSet[i]
else:
nVector = Instance[1]
nVector[i] = inst
self.instanceSet = nVector
def removeInstance(self, instNum):
if instNum < 0 or instNum >= len(self.instanceSet):
return
aux = [Instance() for x in range(len(self.instanceSet) - 1)]
add = 0
for i in range(0, len(self.instanceSet)):
if instNum == i:
add = 1
else:
aux[i - add] = self.instanceSet[i]
# Copying the auxiliar to the instanceSet variable
self.instanceSet = aux
aux = None # avoiding memory leaks (not necessary in this case)
def read_set_from_data_row_array(self, data_raw_array, isTrain):
# print("Before try in read_set_from_data_row_array of InstanceSet")
try:
# Parsing the header of the DB.
errorLogger = FormatErrorKeeper()
# Declaring an instance parser
# to do The exception in init InstanceParserof InstanceParse is: can only concatenate str (not "WindowsPath") to str
instance_parser = InstanceParser.init_for_granularity_parser(data_raw_array, isTrain)
# Reading information in the header, i.e., @relation, @attribute, @inputs and @outputs
# print("data_raw_array size" + str(len(data_raw_array)))
self.parse_header_from_data_row_array(instance_parser, isTrain)
# print(" The number of output attributes is: " + str(Attributes.getOutputNumAttributes(Attributes)))
# The attributes statistics are init if we are in train mode.
# print("In readSet, isTrain is " + str(isTrain))
if isTrain and Attributes.getOutputNumAttributes(Attributes) == 1:
# print("Begin Attributes.initStatistics......")
Attributes.initStatistics(Attributes)
# A temporal vector is used to store the instances read.
# print("Reading the data in read_set_from_data_row_array")
tempSet = []
# print("begin instance_parser.getLines()...... ")
data_raw_array = self.data_rows
new_data_rows = []
number_of_rows= len(data_raw_array)
# print("********* There are : " + str(number_of_rows) + "In original Data rows ********* ")
# print("********* There are : " + str(len(new_data_rows)) + " In new Data rows ********* ")
for i in range(0, number_of_rows):
if len(new_data_rows) != 0:
# print("Data row: " + str(data_raw_array[i]))
newInstance = Instance()
# print("how many data already in the instanceSet: " + str(len(tempSet)))
newInstance.set_three_parameters_for_granularity_rules(data_raw_array[i], isTrain, len(tempSet))
tempSet.append(newInstance)
# The vector of instances is converted to an array of instances.
sizeInstance = len(tempSet)
# print(" Number of instances read: " + str(sizeInstance))
self.instanceSet = []
for i in range(0, sizeInstance):
self.instanceSet.append(tempSet[i])
# print("After converting all instances")
# System.out.println("The error logger has any error: "+errorLogger.getNumErrors());
if self.errorLogger.getNumErrors() > 0:
errorNumber = len(errorLogger.getAllErrors())
# print("There has been " + str(errorNumber) + "errors in the Dataset format.")
for k in range(0, errorLogger.getNumErrors()):
errorLogger.getError(k).printErrorInfo()
# print("There has been " + errorLogger.getAllErrors().size() + " errors in the Dataset format",
# errorLogger.getAllErrors());
# print("Finishing the statistics: (isTrain)" + str(isTrain) + ", (# out attributes)" + str(Attributes.getOutputNumAttributes(Attributes)))
# # If being on a train dataset, the statistics are finished
if isTrain and Attributes.getOutputNumAttributes(Attributes) == 1:
Attributes.finishStatistics(Attributes)
# # close the stream
instance_parser.close()
# print("File LOADED CORRECTLY!!")
except Exception as e:
print("Unexpected error in readSet of InstanceSet class :" + str(e))
def readSet(self, fileName, isTrain,file_path):
print("Before try in readSet of InstanceSet, fileName is :" + str(fileName) + ".")
print("Opening the file in readSet of InstanceSet: " + str(fileName) + ".")
try:
# Parsing the header of the DB.
errorLogger = FormatErrorKeeper()
self.data_folder = file_path
self.file_to_open = self.data_folder + "\\dataset\\" + fileName
# Declaring an instance parser
print("In readSet,file_to_open is:" + str(self.file_to_open))
# to do The exception in init InstanceParserof InstanceParse is: can only concatenate str (not "WindowsPath") to str
instance_parser = InstanceParser(self.file_to_open, isTrain)
# Reading information in the header, i.e., @relation, @attribute, @inputs and @outputs
print("In readSet finished read file " + str(self.file_to_open))
self.parseHeader(instance_parser, isTrain)
print(" The number of output attributes is: " + str(Attributes.getOutputNumAttributes(Attributes)))
# The attributes statistics are init if we are in train mode.
print("In readSet, isTrain is " + str(isTrain))
if isTrain and Attributes.getOutputNumAttributes(Attributes) == 1:
print("Begin Attributes.initStatistics......")
Attributes.initStatistics(Attributes)
# A temporal vector is used to store the instances read.
print("Reading the data")
tempSet = []
print("begin instance_parser.getLines()...... ")
lines = self.data_lines
new_data_lines = []
print("********* There are : " + str(len(lines)) + "In original Data lines ********* ")
for line in lines:
if ("@relation" not in line) and ("@attribute" not in line) and ("@inputs" not in line) and (
"@outputs" not in line) and ("@data" not in line):
new_data_lines.append(line)
# print("********* There are : " + str(len(new_data_lines)) + " In new Data lines ********* ")
for line in new_data_lines:
if new_data_lines is not None:
print("Data line: " + str(line))
newInstance = Instance()
# print("how many data already in the instanceSet: " + str(len(tempSet)))
newInstance.setThreeParameters(line, isTrain, len(tempSet))
tempSet.append(newInstance)
# The vector of instances is converted to an array of instances.
sizeInstance = len(tempSet)
# print(" Number of instances read: " + str(sizeInstance))
self.instanceSet = []
for i in range(0, sizeInstance):
self.instanceSet.append(tempSet[i])
# print("After converting all instances")
# System.out.println("The error logger has any error: "+errorLogger.getNumErrors());
if self.errorLogger.getNumErrors() > 0:
errorNumber = len(errorLogger.getAllErrors())
# print("There has been " + str(errorNumber) + "errors in the Dataset format.")
for k in range(0, errorLogger.getNumErrors()):
errorLogger.getError(k).printErrorInfo()
# print("There has been " + errorLogger.getAllErrors().size() + " errors in the Dataset format",
# errorLogger.getAllErrors());
# print("Finishing the statistics: (isTrain)" + str(isTrain) + ", (# out attributes)" + str(Attributes.getOutputNumAttributes(Attributes)))
# # If being on a train dataset, the statistics are finished
if isTrain and Attributes.getOutputNumAttributes(Attributes) == 1:
Attributes.finishStatistics(Attributes)
# # close the stream
instance_parser.close()
# print("File LOADED CORRECTLY!!")
except Exception as e:
print("Unexpected error in readSet of InstanceSet class :" + str(e))