def import_dataset_from_arff(arff, class_index=None):
'''Imports Dataset From an ARFF Textual Format
:param arff: the data in ARFF textual format
:param classIndex: the index of the class attribute
:return: a dataset (Bunch)
'''
if not jp.isThreadAttachedToJVM():
jp.attachThreadToJVM()
tmp = common.TemporaryFile(suffix='.arff')
tmp.writeString(arff)
source = jp.JClass('weka.core.converters.ConverterUtils$DataSource')(
tmp.name)
instances = source.getDataSet()
if class_index is None:
print 'Warning: class is set to the last attribute!'
class_index = instances.numAttributes() - 1
elif class_index == -1:
class_index = instances.numAttributes() - 1
instances.setClassIndex(class_index)
return convert_weka_instances_to_bunch(instances)
def weka_local_arff_to_weka_instances(input_dict):
'''
Reads a dataset into a format suitable for WEKA methods
'''
if not jp.isThreadAttachedToJVM():
jp.attachThreadToJVM()
tmp = common.TemporaryFile(suffix='.arff')
tmp.writeString(input_dict['arff'])
try:
class_index = int(input_dict['class_index'])
except:
class_index = None
source = jp.JClass('weka.core.converters.ConverterUtils$DataSource')(
tmp.name)
instances = source.getDataSet()
if class_index is None:
print 'Warning: class is set to the last attribute!'
class_index = instances.numAttributes() - 1
elif class_index == -1:
class_index = instances.numAttributes() - 1
instances.setClassIndex(class_index)
return {'instances': common.serialize_weka_object(instances)}
def apply_mapped_classifier_get_instances(weka_classifier, original_data,
data):
'''An advanced version of the Apply Classifier method.
Addresses incompatible training and test data, and returns a dataset with predictions.
:param weka_classifier: WekaClassifier object
:param original_data: original training instances, bunch
:param data: test instances, bunch
:return: Dataset (Bunch) object with predictions and a textual report from the InputMappedClassifier class
'''
if not jp.isThreadAttachedToJVM():
jp.attachThreadToJVM()
try:
classifier = common.deserialize_weka_object(
weka_classifier.sclassifier)
except:
raise Exception(
"Only WEKA classifiers/models supported. Please provide a valid WEKA learner."
)
original_training_instances = ut.convert_bunch_to_weka_instances(
original_data)
instances = ut.convert_bunch_to_weka_instances(data)
# serialize classifier with original instances to a file once again for the Mapped classifier
tfile = common.TemporaryFile(flags='wb+')
s = jp.JClass('weka.core.SerializationHelper')
s.writeAll(tfile.name, [classifier, original_training_instances])
# construct a MappedClassifier
mapped_classifier = jp.JClass(
'weka.classifiers.misc.InputMappedClassifier')()
mapped_classifier.setIgnoreCaseForNames(True)
mapped_classifier.setTrim(True)
# mapped_classifier.setSuppressMappingReport(True)
# mc.setModelHeader(original_training_instances)
mapped_classifier.setModelPath(tfile.name)
predictions = []
try:
for instance in instances:
label = int(mapped_classifier.classifyInstance(instance))
predictions.append(label)
data["targetPredicted"] = predictions
except:
raise Exception(
"Classifier not built. Please use the Build Classifier widget first."
)
report = mapped_classifier.toString()
if MAPPING_REPORT_START in report:
report = report[report.index(MAPPING_REPORT_START):]
return data, report
def weka_local_apply_mapped_classifier_get_instances(input_dict):
if not jp.isThreadAttachedToJVM():
jp.attachThreadToJVM()
MAPPING_REPORT_START = 'Attribute mappings:'
classifier = common.deserialize_weka_object(input_dict['classifier'])
original_training_instances = common.deserialize_weka_object(
input_dict['original_training_instances'])
instances = common.deserialize_weka_object(input_dict['instances'])
# serialize classifier with original instances to a file once again for the Mapped classifier
tfile = common.TemporaryFile(flags='wb+')
s = jp.JClass('weka.core.SerializationHelper')
s.writeAll(tfile.name, [classifier, original_training_instances])
# construct a MappedClassifier
mappedClassifier = jp.JClass(
'weka.classifiers.misc.InputMappedClassifier')()
mappedClassifier.setIgnoreCaseForNames(True)
mappedClassifier.setTrim(True)
#mappedClassifier.setSuppressMappingReport(True)
#mc.setModelHeader(original_training_instances)
mappedClassifier.setModelPath(tfile.name)
# use the mapped classifier on new data
classIndex = instances.classIndex()
if classIndex == -1:
raise ValueError('Class not set!')
classAttribute = instances.classAttribute()
for instance in instances:
label = int(mappedClassifier.classifyInstance(instance))
instance.setClassValue(classAttribute.value(label))
report = mappedClassifier.toString()
if MAPPING_REPORT_START in report:
report = report[report.index(MAPPING_REPORT_START):]
return {
'mapping_report': report,
'instances': common.serialize_weka_object(instances)
}