def use_classifier(data, cli, args):
cli = cli.format(cli, **args)
cls = from_commandline(cli, classname="weka.classifiers.Classifier")
cls.build_classifier(data)
evaluation = Evaluation(data)
evaluation.crossvalidate_model(cls, data, 10, Random(1))
return cls, evaluation
def test_from_and_to_commandline(self):
"""
Tests the from_commandline and to_commandline methods.
"""
cmdline = "weka.classifiers.trees.J48 -C 0.3 -M 4"
cls = classes.from_commandline(
cmdline=cmdline, classname="weka.classifiers.Classifier")
self.assertIsNotNone(cls)
self.assertEqual(cmdline, cls.to_commandline())
def use_classifier(data_filename, cli):
loader = Loader(classname="weka.core.converters.ArffLoader")
data = loader.load_file(data_filename)
data.class_is_last()
cls = from_commandline(cli, classname="weka.classifiers.Classifier")
cls.build_classifier(data)
evaluation = Evaluation(data)
evaluation.crossvalidate_model(cls, data, 10, Random(1))
return cls, evaluation
def test_from_and_to_commandline(self):
"""
Tests the from_commandline and to_commandline methods.
"""
cmdline = "weka.classifiers.trees.J48 -C 0.3 -M 4"
cls = classes.from_commandline(
cmdline=cmdline, classname="weka.classifiers.Classifier")
self.assertIsNotNone(cls)
self.assertEqual(cmdline, cls.to_commandline())
def convert(self):
"""
Performs the actual conversion.
:return: None if successful, otherwise errors message
:rtype: str
"""
cname = str(self.config["wrapper"])
self._output = classes.from_commandline(self._input, classname=cname)
return None
def convert(self):
"""
Performs the actual conversion.
:return: None if successful, otherwise errors message
:rtype: str
"""
cname = str(self.config["wrapper"])
self._output = classes.from_commandline(self._input, classname=cname)
return None
def setup(self):
"""
Initializes the experiment.
"""
# basic options
javabridge.call(
self.jobject, "setPropertyArray", "(Ljava/lang/Object;)V",
javabridge.get_env().make_object_array(0, javabridge.get_env().find_class("weka/classifiers/Classifier")))
javabridge.call(
self.jobject, "setUsePropertyIterator", "(Z)V", True)
javabridge.call(
self.jobject, "setRunLower", "(I)V", 1)
javabridge.call(
self.jobject, "setRunUpper", "(I)V", self.runs)
# setup result producer
rproducer, prop_path = self.configure_resultproducer()
javabridge.call(
self.jobject, "setResultProducer", "(Lweka/experiment/ResultProducer;)V", rproducer)
javabridge.call(
self.jobject, "setPropertyPath", "([Lweka/experiment/PropertyNode;)V", prop_path)
# classifiers
classifiers = javabridge.get_env().make_object_array(
len(self.classifiers), javabridge.get_env().find_class("weka/classifiers/Classifier"))
for i, classifier in enumerate(self.classifiers):
if type(classifier) is Classifier:
javabridge.get_env().set_object_array_element(
classifiers, i, classifier.jobject)
else:
javabridge.get_env().set_object_array_element(
classifiers, i, from_commandline(classifier).jobject)
javabridge.call(
self.jobject, "setPropertyArray", "(Ljava/lang/Object;)V",
classifiers)
# datasets
datasets = javabridge.make_instance("javax/swing/DefaultListModel", "()V")
for dataset in self.datasets:
f = javabridge.make_instance("java/io/File", "(Ljava/lang/String;)V", dataset)
javabridge.call(datasets, "addElement", "(Ljava/lang/Object;)V", f)
javabridge.call(
self.jobject, "setDatasets", "(Ljavax/swing/DefaultListModel;)V", datasets)
# output file
if str(self.result).lower().endswith(".arff"):
rlistener = javabridge.make_instance("weka/experiment/InstancesResultListener", "()V")
elif str(self.result).lower().endswith(".csv"):
rlistener = javabridge.make_instance("weka/experiment/CSVResultListener", "()V")
else:
raise Exception("Unhandled output format for results: " + self.result)
rfile = javabridge.make_instance("java/io/File", "(Ljava/lang/String;)V", self.result)
javabridge.call(
rlistener, "setOutputFile", "(Ljava/io/File;)V", rfile)
javabridge.call(
self.jobject, "setResultListener", "(Lweka/experiment/ResultListener;)V", rlistener)
def setup(self):
"""
Initializes the experiment.
"""
# basic options
javabridge.call(
self.jobject, "setPropertyArray", "(Ljava/lang/Object;)V",
javabridge.get_env().make_object_array(0, javabridge.get_env().find_class("weka/classifiers/Classifier")))
javabridge.call(
self.jobject, "setUsePropertyIterator", "(Z)V", True)
javabridge.call(
self.jobject, "setRunLower", "(I)V", 1)
javabridge.call(
self.jobject, "setRunUpper", "(I)V", self.runs)
# setup result producer
rproducer, prop_path = self.configure_resultproducer()
javabridge.call(
self.jobject, "setResultProducer", "(Lweka/experiment/ResultProducer;)V", rproducer)
javabridge.call(
self.jobject, "setPropertyPath", "([Lweka/experiment/PropertyNode;)V", prop_path)
# classifiers
classifiers = javabridge.get_env().make_object_array(
len(self.classifiers), javabridge.get_env().find_class("weka/classifiers/Classifier"))
for i, classifier in enumerate(self.classifiers):
if type(classifier) is Classifier:
javabridge.get_env().set_object_array_element(
classifiers, i, classifier.jobject)
else:
javabridge.get_env().set_object_array_element(
classifiers, i, from_commandline(classifier).jobject)
javabridge.call(
self.jobject, "setPropertyArray", "(Ljava/lang/Object;)V",
classifiers)
# datasets
datasets = javabridge.make_instance("javax/swing/DefaultListModel", "()V")
for dataset in self.datasets:
f = javabridge.make_instance("java/io/File", "(Ljava/lang/String;)V", dataset)
javabridge.call(datasets, "addElement", "(Ljava/lang/Object;)V", f)
javabridge.call(
self.jobject, "setDatasets", "(Ljavax/swing/DefaultListModel;)V", datasets)
# output file
if str(self.result).lower().endswith(".arff"):
rlistener = javabridge.make_instance("weka/experiment/InstancesResultListener", "()V")
elif str(self.result).lower().endswith(".csv"):
rlistener = javabridge.make_instance("weka/experiment/CSVResultListener", "()V")
else:
raise Exception("Unhandled output format for results: " + self.result)
rfile = javabridge.make_instance("java/io/File", "(Ljava/lang/String;)V", self.result)
javabridge.call(
rlistener, "setOutputFile", "(Ljava/io/File;)V", rfile)
javabridge.call(
self.jobject, "setResultListener", "(Lweka/experiment/ResultListener;)V", rlistener)
def make_copy(cls, generator):
"""
Creates a copy of the generator.
:param generator: the generator to copy
:type generator: DataGenerator
:return: the copy of the generator
:rtype: DataGenerator
"""
return from_commandline(
to_commandline(generator), classname=classes.get_classname(DataGenerator()))
def from_config(self, k, v):
"""
Hook method that allows converting values from the dictionary
:param k: the key in the dictionary
:type k: str
:param v: the value
:type v: object
:return: the potentially parsed value
:rtype: object
"""
if k == "setup":
return from_commandline(v, classname=to_commandline(datagen.DataGenerator()))
return super(DataGenerator, self).from_config(k, v)
def from_config(self, k, v):
"""
Hook method that allows converting values from the dictionary.
:param k: the key in the dictionary
:type k: str
:param v: the value
:type v: object
:return: the potentially parsed value
:rtype: object
"""
if k == "setup":
return from_commandline(v, classname=to_commandline(datagen.DataGenerator()))
return super(DataGenerator, self).from_config(k, v)
def train(option, sym, num):
# load dataset given the symbol
path = os.path.join('HistSet', 'histSet_%s.arff' % sym)
loader = Loader("weka.core.converters.ArffLoader")
dataset = loader.load_file(path)
dataset.class_is_last() # set the last attribute as class attribute
# load testset
# testset = loader.load_file(os.path.join('HistSet', 'testSet_LTC.arff'))
# testset.class_is_last()
# define classifier
cmd = {
'DecisionTable':
'weka.classifiers.rules.DecisionTable -X 1 -S "weka.attributeSelection.BestFirst -D 1 -N 5"',
'SMOreg':
'weka.classifiers.functions.SMOreg -C 1.0 -N 0 -I "weka.classifiers.functions.supportVector.RegSMOImproved -L 0.001 -W 1 -P 1.0E-12 -T 0.001 -V" -K "weka.classifiers.functions.supportVector.PolyKernel -C 250007 -E 1.0"',
'LinearRegression':
'weka.classifiers.functions.LinearRegression -S 0 -R 1.0E-8',
'GaussianProcesses':
'weka.classifiers.functions.GaussianProcesses -L 1.0 -N 0 -K "weka.classifiers.functions.supportVector.RBFKernel -C 250007 -G 1.0"',
}
cls = from_commandline(cmd[option],
classname='weka.classifiers.Classifier')
cls.build_classifier(dataset)
# begin evaluating
evaluation = Evaluation(dataset)
# evaluation.evaluate_train_test_split(cls, dataset, 90, Random(1)) # evaluate by splitting train/test set
evl = evaluation.test_model(cls, dataset) # evaluate on test set
print('predictions (' + str(len(evl)) + '): ')
for i in range(num):
print(evl[i - num], end=' ')
# print(evaluation.summary())
return evl[-num:]
def main():
"""
Just runs some example code.
"""
# load a dataset
iris_file = helper.get_data_dir() + os.sep + "iris.arff"
helper.print_info("Loading dataset: " + iris_file)
loader = Loader("weka.core.converters.ArffLoader")
iris_data = loader.load_file(iris_file)
iris_data.class_is_last()
# classifier help
helper.print_title("Creating help string")
classifier = Classifier(classname="weka.classifiers.trees.J48")
print(classifier.to_help())
# partial classname
helper.print_title("Creating classifier from partial classname")
clsname = ".J48"
classifier = Classifier(classname=clsname)
print(clsname + " --> " + classifier.classname)
# classifier from commandline
helper.print_title("Creating SMO from command-line string")
cmdline = 'weka.classifiers.functions.SMO -K "weka.classifiers.functions.supportVector.NormalizedPolyKernel -E 3.0"'
classifier = from_commandline(cmdline,
classname="weka.classifiers.Classifier")
classifier.build_classifier(iris_data)
print("input: " + cmdline)
print("output: " + classifier.to_commandline())
print("model:\n" + str(classifier))
# kernel classifier
helper.print_title("Creating SMO as KernelClassifier")
kernel = Kernel(
classname="weka.classifiers.functions.supportVector.RBFKernel",
options=["-G", "0.001"])
classifier = KernelClassifier(classname="weka.classifiers.functions.SMO",
options=["-M"])
classifier.kernel = kernel
classifier.build_classifier(iris_data)
print("classifier: " + classifier.to_commandline())
print("model:\n" + str(classifier))
# build a classifier and output model
helper.print_title("Training J48 classifier on iris")
classifier = Classifier(classname="weka.classifiers.trees.J48")
# Instead of using 'options=["-C", "0.3"]' in the constructor, we can also set the "confidenceFactor"
# property of the J48 classifier itself. However, being of type float rather than double, we need
# to convert it to the correct type first using the double_to_float function:
classifier.set_property("confidenceFactor", types.double_to_float(0.3))
classifier.build_classifier(iris_data)
print(classifier)
print(classifier.graph)
print(classifier.to_source("MyJ48"))
plot_graph.plot_dot_graph(classifier.graph)
# evaluate model on test set
helper.print_title("Evaluating J48 classifier on iris")
evaluation = Evaluation(iris_data)
evl = evaluation.test_model(classifier, iris_data)
print(evl)
print(evaluation.summary())
# evaluate model on train/test split
helper.print_title("Evaluating J48 classifier on iris (random split 66%)")
classifier = Classifier(classname="weka.classifiers.trees.J48",
options=["-C", "0.3"])
evaluation = Evaluation(iris_data)
evaluation.evaluate_train_test_split(classifier, iris_data, 66.0,
Random(1))
print(evaluation.summary())
# load a dataset incrementally and build classifier incrementally
helper.print_title("Build classifier incrementally on iris")
helper.print_info("Loading dataset: " + iris_file)
loader = Loader("weka.core.converters.ArffLoader")
iris_inc = loader.load_file(iris_file, incremental=True)
iris_inc.class_is_last()
classifier = Classifier(
classname="weka.classifiers.bayes.NaiveBayesUpdateable")
classifier.build_classifier(iris_inc)
for inst in loader:
classifier.update_classifier(inst)
print(classifier)
# construct meta-classifiers
helper.print_title("Meta classifiers")
# generic FilteredClassifier instantiation
print("generic FilteredClassifier instantiation")
meta = SingleClassifierEnhancer(
classname="weka.classifiers.meta.FilteredClassifier")
meta.classifier = Classifier(
classname="weka.classifiers.functions.LinearRegression")
flter = Filter("weka.filters.unsupervised.attribute.Remove")
flter.options = ["-R", "first"]
meta.set_property("filter", flter.jobject)
print(meta.to_commandline())
# direct FilteredClassifier instantiation
print("direct FilteredClassifier instantiation")
meta = FilteredClassifier()
meta.classifier = Classifier(
classname="weka.classifiers.functions.LinearRegression")
flter = Filter("weka.filters.unsupervised.attribute.Remove")
flter.options = ["-R", "first"]
meta.filter = flter
print(meta.to_commandline())
# generic Vote
print("generic Vote instantiation")
meta = MultipleClassifiersCombiner(classname="weka.classifiers.meta.Vote")
classifiers = [
Classifier(classname="weka.classifiers.functions.SMO"),
Classifier(classname="weka.classifiers.trees.J48")
]
meta.classifiers = classifiers
print(meta.to_commandline())
# cross-validate nominal classifier
helper.print_title("Cross-validating NaiveBayes on diabetes")
diabetes_file = helper.get_data_dir() + os.sep + "diabetes.arff"
helper.print_info("Loading dataset: " + diabetes_file)
loader = Loader("weka.core.converters.ArffLoader")
diabetes_data = loader.load_file(diabetes_file)
diabetes_data.class_is_last()
classifier = Classifier(classname="weka.classifiers.bayes.NaiveBayes")
pred_output = PredictionOutput(
classname="weka.classifiers.evaluation.output.prediction.PlainText",
options=["-distribution"])
evaluation = Evaluation(diabetes_data)
evaluation.crossvalidate_model(classifier,
diabetes_data,
10,
Random(42),
output=pred_output)
print(evaluation.summary())
print(evaluation.class_details())
print(evaluation.matrix())
print("areaUnderPRC/0: " + str(evaluation.area_under_prc(0)))
print("weightedAreaUnderPRC: " + str(evaluation.weighted_area_under_prc))
print("areaUnderROC/1: " + str(evaluation.area_under_roc(1)))
print("weightedAreaUnderROC: " + str(evaluation.weighted_area_under_roc))
print("avgCost: " + str(evaluation.avg_cost))
print("totalCost: " + str(evaluation.total_cost))
print("confusionMatrix: " + str(evaluation.confusion_matrix))
print("correct: " + str(evaluation.correct))
print("pctCorrect: " + str(evaluation.percent_correct))
print("incorrect: " + str(evaluation.incorrect))
print("pctIncorrect: " + str(evaluation.percent_incorrect))
print("unclassified: " + str(evaluation.unclassified))
print("pctUnclassified: " + str(evaluation.percent_unclassified))
print("coverageOfTestCasesByPredictedRegions: " +
str(evaluation.coverage_of_test_cases_by_predicted_regions))
print("sizeOfPredictedRegions: " +
str(evaluation.size_of_predicted_regions))
print("falseNegativeRate: " + str(evaluation.false_negative_rate(1)))
print("weightedFalseNegativeRate: " +
str(evaluation.weighted_false_negative_rate))
print("numFalseNegatives: " + str(evaluation.num_false_negatives(1)))
print("trueNegativeRate: " + str(evaluation.true_negative_rate(1)))
print("weightedTrueNegativeRate: " +
str(evaluation.weighted_true_negative_rate))
print("numTrueNegatives: " + str(evaluation.num_true_negatives(1)))
print("falsePositiveRate: " + str(evaluation.false_positive_rate(1)))
print("weightedFalsePositiveRate: " +
str(evaluation.weighted_false_positive_rate))
print("numFalsePositives: " + str(evaluation.num_false_positives(1)))
print("truePositiveRate: " + str(evaluation.true_positive_rate(1)))
print("weightedTruePositiveRate: " +
str(evaluation.weighted_true_positive_rate))
print("numTruePositives: " + str(evaluation.num_true_positives(1)))
print("fMeasure: " + str(evaluation.f_measure(1)))
print("weightedFMeasure: " + str(evaluation.weighted_f_measure))
print("unweightedMacroFmeasure: " +
str(evaluation.unweighted_macro_f_measure))
print("unweightedMicroFmeasure: " +
str(evaluation.unweighted_micro_f_measure))
print("precision: " + str(evaluation.precision(1)))
print("weightedPrecision: " + str(evaluation.weighted_precision))
print("recall: " + str(evaluation.recall(1)))
print("weightedRecall: " + str(evaluation.weighted_recall))
print("kappa: " + str(evaluation.kappa))
print("KBInformation: " + str(evaluation.kb_information))
print("KBMeanInformation: " + str(evaluation.kb_mean_information))
print("KBRelativeInformation: " + str(evaluation.kb_relative_information))
print("SFEntropyGain: " + str(evaluation.sf_entropy_gain))
print("SFMeanEntropyGain: " + str(evaluation.sf_mean_entropy_gain))
print("SFMeanPriorEntropy: " + str(evaluation.sf_mean_prior_entropy))
print("SFMeanSchemeEntropy: " + str(evaluation.sf_mean_scheme_entropy))
print("matthewsCorrelationCoefficient: " +
str(evaluation.matthews_correlation_coefficient(1)))
print("weightedMatthewsCorrelation: " +
str(evaluation.weighted_matthews_correlation))
print("class priors: " + str(evaluation.class_priors))
print("numInstances: " + str(evaluation.num_instances))
print("meanAbsoluteError: " + str(evaluation.mean_absolute_error))
print("meanPriorAbsoluteError: " +
str(evaluation.mean_prior_absolute_error))
print("relativeAbsoluteError: " + str(evaluation.relative_absolute_error))
print("rootMeanSquaredError: " + str(evaluation.root_mean_squared_error))
print("rootMeanPriorSquaredError: " +
str(evaluation.root_mean_prior_squared_error))
print("rootRelativeSquaredError: " +
str(evaluation.root_relative_squared_error))
print("prediction output:\n" + str(pred_output))
plot_cls.plot_roc(evaluation,
title="ROC diabetes",
class_index=range(
0, diabetes_data.class_attribute.num_values),
wait=False)
plot_cls.plot_prc(evaluation,
title="PRC diabetes",
class_index=range(
0, diabetes_data.class_attribute.num_values),
wait=False)
# train 2nd classifier on diabetes dataset
classifier2 = Classifier(classname="weka.classifiers.trees.RandomForest")
evaluation2 = Evaluation(diabetes_data)
evaluation2.crossvalidate_model(classifier2, diabetes_data, 10, Random(42))
plot_cls.plot_rocs({
"NB": evaluation,
"RF": evaluation2
},
title="ROC diabetes",
class_index=0,
wait=False)
plot_cls.plot_prcs({
"NB": evaluation,
"RF": evaluation2
},
title="PRC diabetes",
class_index=0,
wait=False)
# load a numeric dataset
bolts_file = helper.get_data_dir() + os.sep + "bolts.arff"
helper.print_info("Loading dataset: " + bolts_file)
loader = Loader("weka.core.converters.ArffLoader")
bolts_data = loader.load_file(bolts_file)
bolts_data.class_is_last()
# build a classifier and output model
helper.print_title("Training LinearRegression on bolts")
classifier = Classifier(
classname="weka.classifiers.functions.LinearRegression",
options=["-S", "1", "-C"])
classifier.build_classifier(bolts_data)
print(classifier)
# cross-validate numeric classifier
helper.print_title("Cross-validating LinearRegression on bolts")
classifier = Classifier(
classname="weka.classifiers.functions.LinearRegression",
options=["-S", "1", "-C"])
evaluation = Evaluation(bolts_data)
evaluation.crossvalidate_model(classifier, bolts_data, 10, Random(42))
print(evaluation.summary())
print("correlationCoefficient: " + str(evaluation.correlation_coefficient))
print("errorRate: " + str(evaluation.error_rate))
helper.print_title("Header - bolts")
print(str(evaluation.header))
helper.print_title("Predictions on bolts")
for index, pred in enumerate(evaluation.predictions):
print(
str(index + 1) + ": " + str(pred) + " -> error=" + str(pred.error))
plot_cls.plot_classifier_errors(evaluation.predictions, wait=False)
# train 2nd classifier and show errors in same plot
classifier2 = Classifier(classname="weka.classifiers.functions.SMOreg")
evaluation2 = Evaluation(bolts_data)
evaluation2.crossvalidate_model(classifier2, bolts_data, 10, Random(42))
plot_cls.plot_classifier_errors(
{
"LR": evaluation.predictions,
"SMOreg": evaluation2.predictions
},
wait=False)
# learning curve
cls = [
Classifier(classname="weka.classifiers.trees.J48"),
Classifier(classname="weka.classifiers.bayes.NaiveBayesUpdateable")
]
plot_cls.plot_learning_curve(cls,
diabetes_data,
increments=0.05,
label_template="[#] !",
metric="percent_correct",
wait=True)
# access classifier's Java API
labor_file = helper.get_data_dir() + os.sep + "labor.arff"
helper.print_info("Loading dataset: " + labor_file)
loader = Loader("weka.core.converters.ArffLoader")
labor_data = loader.load_file(labor_file)
labor_data.class_is_last()
helper.print_title("Using JRip's Java API to access rules")
jrip = Classifier(classname="weka.classifiers.rules.JRip")
jrip.build_classifier(labor_data)
rset = jrip.jwrapper.getRuleset()
for i in xrange(rset.size()):
r = rset.get(i)
print(str(r.toString(labor_data.class_attribute.jobject)))
def main():
"""
Just runs some example code.
"""
# load a dataset
iris_file = helper.get_data_dir() + os.sep + "iris.arff"
helper.print_info("Loading dataset: " + iris_file)
loader = Loader("weka.core.converters.ArffLoader")
iris_data = loader.load_file(iris_file)
iris_data.class_is_last()
# classifier help
helper.print_title("Creating help string")
classifier = Classifier(classname="weka.classifiers.trees.J48")
print(classifier.to_help())
# partial classname
helper.print_title("Creating classifier from partial classname")
clsname = ".J48"
classifier = Classifier(classname=clsname)
print(clsname + " --> " + classifier.classname)
# classifier from commandline
helper.print_title("Creating SMO from command-line string")
cmdline = 'weka.classifiers.functions.SMO -K "weka.classifiers.functions.supportVector.NormalizedPolyKernel -E 3.0"'
classifier = from_commandline(cmdline, classname="weka.classifiers.Classifier")
classifier.build_classifier(iris_data)
print("input: " + cmdline)
print("output: " + classifier.to_commandline())
print("model:\n" + str(classifier))
# kernel classifier
helper.print_title("Creating SMO as KernelClassifier")
kernel = Kernel(classname="weka.classifiers.functions.supportVector.RBFKernel", options=["-G", "0.001"])
classifier = KernelClassifier(classname="weka.classifiers.functions.SMO", options=["-M"])
classifier.kernel = kernel
classifier.build_classifier(iris_data)
print("classifier: " + classifier.to_commandline())
print("model:\n" + str(classifier))
# build a classifier and output model
helper.print_title("Training J48 classifier on iris")
classifier = Classifier(classname="weka.classifiers.trees.J48")
# Instead of using 'options=["-C", "0.3"]' in the constructor, we can also set the "confidenceFactor"
# property of the J48 classifier itself. However, being of type float rather than double, we need
# to convert it to the correct type first using the double_to_float function:
classifier.set_property("confidenceFactor", typeconv.double_to_float(0.3))
classifier.build_classifier(iris_data)
print(classifier)
print(classifier.graph)
print(classifier.to_source("MyJ48"))
plot_graph.plot_dot_graph(classifier.graph)
# evaluate model on test set
helper.print_title("Evaluating J48 classifier on iris")
evaluation = Evaluation(iris_data)
evl = evaluation.test_model(classifier, iris_data)
print(evl)
print(evaluation.summary())
# evaluate model on train/test split
helper.print_title("Evaluating J48 classifier on iris (random split 66%)")
classifier = Classifier(classname="weka.classifiers.trees.J48", options=["-C", "0.3"])
evaluation = Evaluation(iris_data)
evaluation.evaluate_train_test_split(classifier, iris_data, 66.0, Random(1))
print(evaluation.summary())
# load a dataset incrementally and build classifier incrementally
helper.print_title("Build classifier incrementally on iris")
helper.print_info("Loading dataset: " + iris_file)
loader = Loader("weka.core.converters.ArffLoader")
iris_inc = loader.load_file(iris_file, incremental=True)
iris_inc.class_is_last()
classifier = Classifier(classname="weka.classifiers.bayes.NaiveBayesUpdateable")
classifier.build_classifier(iris_inc)
for inst in loader:
classifier.update_classifier(inst)
print(classifier)
# construct meta-classifiers
helper.print_title("Meta classifiers")
# generic FilteredClassifier instantiation
print("generic FilteredClassifier instantiation")
meta = SingleClassifierEnhancer(classname="weka.classifiers.meta.FilteredClassifier")
meta.classifier = Classifier(classname="weka.classifiers.functions.LinearRegression")
flter = Filter("weka.filters.unsupervised.attribute.Remove")
flter.options = ["-R", "first"]
meta.set_property("filter", flter.jobject)
print(meta.to_commandline())
# direct FilteredClassifier instantiation
print("direct FilteredClassifier instantiation")
meta = FilteredClassifier()
meta.classifier = Classifier(classname="weka.classifiers.functions.LinearRegression")
flter = Filter("weka.filters.unsupervised.attribute.Remove")
flter.options = ["-R", "first"]
meta.filter = flter
print(meta.to_commandline())
# generic Vote
print("generic Vote instantiation")
meta = MultipleClassifiersCombiner(classname="weka.classifiers.meta.Vote")
classifiers = [
Classifier(classname="weka.classifiers.functions.SMO"),
Classifier(classname="weka.classifiers.trees.J48")
]
meta.classifiers = classifiers
print(meta.to_commandline())
# cross-validate nominal classifier
helper.print_title("Cross-validating NaiveBayes on diabetes")
diabetes_file = helper.get_data_dir() + os.sep + "diabetes.arff"
helper.print_info("Loading dataset: " + diabetes_file)
loader = Loader("weka.core.converters.ArffLoader")
diabetes_data = loader.load_file(diabetes_file)
diabetes_data.class_is_last()
classifier = Classifier(classname="weka.classifiers.bayes.NaiveBayes")
pred_output = PredictionOutput(
classname="weka.classifiers.evaluation.output.prediction.PlainText", options=["-distribution"])
evaluation = Evaluation(diabetes_data)
evaluation.crossvalidate_model(classifier, diabetes_data, 10, Random(42), output=pred_output)
print(evaluation.summary())
print(evaluation.class_details())
print(evaluation.matrix())
print("areaUnderPRC/0: " + str(evaluation.area_under_prc(0)))
print("weightedAreaUnderPRC: " + str(evaluation.weighted_area_under_prc))
print("areaUnderROC/1: " + str(evaluation.area_under_roc(1)))
print("weightedAreaUnderROC: " + str(evaluation.weighted_area_under_roc))
print("avgCost: " + str(evaluation.avg_cost))
print("totalCost: " + str(evaluation.total_cost))
print("confusionMatrix: " + str(evaluation.confusion_matrix))
print("correct: " + str(evaluation.correct))
print("pctCorrect: " + str(evaluation.percent_correct))
print("incorrect: " + str(evaluation.incorrect))
print("pctIncorrect: " + str(evaluation.percent_incorrect))
print("unclassified: " + str(evaluation.unclassified))
print("pctUnclassified: " + str(evaluation.percent_unclassified))
print("coverageOfTestCasesByPredictedRegions: " + str(evaluation.coverage_of_test_cases_by_predicted_regions))
print("sizeOfPredictedRegions: " + str(evaluation.size_of_predicted_regions))
print("falseNegativeRate: " + str(evaluation.false_negative_rate(1)))
print("weightedFalseNegativeRate: " + str(evaluation.weighted_false_negative_rate))
print("numFalseNegatives: " + str(evaluation.num_false_negatives(1)))
print("trueNegativeRate: " + str(evaluation.true_negative_rate(1)))
print("weightedTrueNegativeRate: " + str(evaluation.weighted_true_negative_rate))
print("numTrueNegatives: " + str(evaluation.num_true_negatives(1)))
print("falsePositiveRate: " + str(evaluation.false_positive_rate(1)))
print("weightedFalsePositiveRate: " + str(evaluation.weighted_false_positive_rate))
print("numFalsePositives: " + str(evaluation.num_false_positives(1)))
print("truePositiveRate: " + str(evaluation.true_positive_rate(1)))
print("weightedTruePositiveRate: " + str(evaluation.weighted_true_positive_rate))
print("numTruePositives: " + str(evaluation.num_true_positives(1)))
print("fMeasure: " + str(evaluation.f_measure(1)))
print("weightedFMeasure: " + str(evaluation.weighted_f_measure))
print("unweightedMacroFmeasure: " + str(evaluation.unweighted_macro_f_measure))
print("unweightedMicroFmeasure: " + str(evaluation.unweighted_micro_f_measure))
print("precision: " + str(evaluation.precision(1)))
print("weightedPrecision: " + str(evaluation.weighted_precision))
print("recall: " + str(evaluation.recall(1)))
print("weightedRecall: " + str(evaluation.weighted_recall))
print("kappa: " + str(evaluation.kappa))
print("KBInformation: " + str(evaluation.kb_information))
print("KBMeanInformation: " + str(evaluation.kb_mean_information))
print("KBRelativeInformation: " + str(evaluation.kb_relative_information))
print("SFEntropyGain: " + str(evaluation.sf_entropy_gain))
print("SFMeanEntropyGain: " + str(evaluation.sf_mean_entropy_gain))
print("SFMeanPriorEntropy: " + str(evaluation.sf_mean_prior_entropy))
print("SFMeanSchemeEntropy: " + str(evaluation.sf_mean_scheme_entropy))
print("matthewsCorrelationCoefficient: " + str(evaluation.matthews_correlation_coefficient(1)))
print("weightedMatthewsCorrelation: " + str(evaluation.weighted_matthews_correlation))
print("class priors: " + str(evaluation.class_priors))
print("numInstances: " + str(evaluation.num_instances))
print("meanAbsoluteError: " + str(evaluation.mean_absolute_error))
print("meanPriorAbsoluteError: " + str(evaluation.mean_prior_absolute_error))
print("relativeAbsoluteError: " + str(evaluation.relative_absolute_error))
print("rootMeanSquaredError: " + str(evaluation.root_mean_squared_error))
print("rootMeanPriorSquaredError: " + str(evaluation.root_mean_prior_squared_error))
print("rootRelativeSquaredError: " + str(evaluation.root_relative_squared_error))
print("prediction output:\n" + str(pred_output))
plot_cls.plot_roc(
evaluation, title="ROC diabetes",
class_index=range(0, diabetes_data.class_attribute.num_values), wait=False)
plot_cls.plot_prc(
evaluation, title="PRC diabetes",
class_index=range(0, diabetes_data.class_attribute.num_values), wait=False)
# load a numeric dataset
bolts_file = helper.get_data_dir() + os.sep + "bolts.arff"
helper.print_info("Loading dataset: " + bolts_file)
loader = Loader("weka.core.converters.ArffLoader")
bolts_data = loader.load_file(bolts_file)
bolts_data.class_is_last()
# build a classifier and output model
helper.print_title("Training LinearRegression on bolts")
classifier = Classifier(classname="weka.classifiers.functions.LinearRegression", options=["-S", "1", "-C"])
classifier.build_classifier(bolts_data)
print(classifier)
# cross-validate numeric classifier
helper.print_title("Cross-validating LinearRegression on bolts")
classifier = Classifier(classname="weka.classifiers.functions.LinearRegression", options=["-S", "1", "-C"])
evaluation = Evaluation(bolts_data)
evaluation.crossvalidate_model(classifier, bolts_data, 10, Random(42))
print(evaluation.summary())
print("correlationCoefficient: " + str(evaluation.correlation_coefficient))
print("errorRate: " + str(evaluation.error_rate))
helper.print_title("Header - bolts")
print(str(evaluation.header))
helper.print_title("Predictions on bolts")
for index, pred in enumerate(evaluation.predictions):
print(str(index+1) + ": " + str(pred) + " -> error=" + str(pred.error))
plot_cls.plot_classifier_errors(evaluation.predictions, wait=False)
# learning curve
cls = [
Classifier(classname="weka.classifiers.trees.J48"),
Classifier(classname="weka.classifiers.bayes.NaiveBayesUpdateable")]
plot_cls.plot_learning_curve(
cls, diabetes_data, increments=0.05, label_template="[#] !", metric="percent_correct", wait=True)
# access classifier's Java API
labor_file = helper.get_data_dir() + os.sep + "labor.arff"
helper.print_info("Loading dataset: " + labor_file)
loader = Loader("weka.core.converters.ArffLoader")
labor_data = loader.load_file(labor_file)
labor_data.class_is_last()
helper.print_title("Using JRip's Java API to access rules")
jrip = Classifier(classname="weka.classifiers.rules.JRip")
jrip.build_classifier(labor_data)
rset = jrip.jwrapper.getRuleset()
for i in range(rset.size()):
r = rset.get(i)
print(str(r.toString(labor_data.class_attribute.jobject)))
# remove class attribute
print(f"Numeric to nominals")
remove = Filter(classname="weka.filters.unsupervised.attribute.NumericToNominal", options=["-R", "8,11,12,13,14,25"])
remove.inputformat(data)
filtered = remove.filter(data)
filtered.class_is_last()
print(f"[Done] Numeric to nominals")
attributes = (filtered.attribute_stats(filtered.num_attributes - 1))
num_class1 = (attributes.nominal_counts[0])
num_class2 = (attributes.nominal_counts[1])
input_config = f'weka.classifiers.trees.PBC4cip -S 1 -miner \"PRFramework.Core.SupervisedClassifiers.EmergingPatterns.Miners.RandomForestMinerWithoutFiltering -bagSizePercent 100 -numFeatures -1 -numTrees {numTrees} -builder \\\"PRFramework.Core.SupervisedClassifiers.DecisionTrees.Builder.DecisionTreeBuilder -distributionEvaluator \\\\\\\"PRFramework.Core.SupervisedClassifiers.DecisionTrees.DistributionEvaluators.Hellinger \\\\\\\" -maxDepth {maxDepth} \\\\\\\"-minimalObjByLeaf \\\\\\\" {minObjects} -minimalSplitGain 1.0E-30\\\"\"'
classifier = from_commandline(input_config, classname="weka.classifiers.Classifier")
print(">>> Building classifier...")
start_time_1 = time.time()
classifier.build_classifier(filtered)
print(f">>> [Done] Bulding classifier. Time: {(time.time() - start_time_1)} seconds ---")
print(">>> Serializing model...")
start_time_1 = time.time()
classifier.serialize(f"{path}/{file_name}.model")
print(f">>> [Done] Serializing model. Time: {(time.time() - start_time_1)} seconds ---")
print(">>> Generating big string...")
start_time_1 = time.time()
big_string = str(classifier).split("]")
print(f">>> [Done] Generating big string. Time: {(time.time() - start_time_1)} seconds ---")
def train_bayes(self, train_set):
self.model = from_commandline(self.cmdline,
classname="weka.classifiers.Classifier")
self.model.build_classifier(train_set)
