def main():
"""
Just runs some example code.
"""
# load ARFF file
helper.print_title("Loading ARFF file")
loader = Loader(classname="weka.core.converters.ArffLoader")
data = loader.load_file(helper.get_data_dir() + os.sep + "iris.arff")
print(str(data))
# load CSV file
helper.print_title("Loading CSV file")
loader = Loader(classname="weka.core.converters.CSVLoader")
data = loader.load_file(helper.get_data_dir() + os.sep + "iris.csv")
print(str(data))
# load directory
# changes this to something sensible
text_dir = "/some/where"
if os.path.exists(text_dir) and os.path.isdir(text_dir):
helper.print_title("Loading directory: " + text_dir)
loader = TextDirectoryLoader(options=["-dir", text_dir, "-F", "-charset", "UTF-8"])
data = loader.load()
print(unicode(data))
def main():
"""
Just runs some example code.
"""
# load ARFF file
helper.print_title("Loading ARFF file")
loader = Loader(classname="weka.core.converters.ArffLoader")
data = loader.load_file(helper.get_data_dir() + os.sep + "iris.arff")
print(str(data))
# load CSV file
helper.print_title("Loading CSV file")
loader = Loader(classname="weka.core.converters.CSVLoader")
data = loader.load_file(helper.get_data_dir() + os.sep + "iris.csv")
print(str(data))
# load directory
# changes this to something sensible
text_dir = "/some/where"
if os.path.exists(text_dir) and os.path.isdir(text_dir):
helper.print_title("Loading directory: " + text_dir)
loader = TextDirectoryLoader(
options=["-dir", text_dir, "-F", "-charset", "UTF-8"])
data = loader.load()
print(unicode(data))
def main():
"""
Just runs some example code.
"""
# load a dataset
iris = helper.get_data_dir() + os.sep + "iris.arff"
helper.print_info("Loading dataset: " + iris)
loader = Loader("weka.core.converters.ArffLoader")
data = loader.load_file(iris)
# remove class attribute
helper.print_info("Removing class attribute")
remove = Filter(classname="weka.filters.unsupervised.attribute.Remove",
options=["-R", "last"])
remove.inputformat(data)
filtered = remove.filter(data)
# use MultiFilter
helper.print_info("Use MultiFilter")
remove = Filter(classname="weka.filters.unsupervised.attribute.Remove",
options=["-R", "first"])
std = Filter(classname="weka.filters.unsupervised.attribute.Standardize")
multi = MultiFilter()
multi.filters = [remove, std]
multi.inputformat(data)
filtered_multi = multi.filter(data)
# output datasets
helper.print_title("Input")
print(data)
helper.print_title("Output")
print(filtered)
helper.print_title("Output (MultiFilter)")
print(filtered_multi)
# load text dataset
text = helper.get_data_dir(
) + os.sep + "reutersTop10Randomized_1perc_shortened.arff"
helper.print_info("Loading dataset: " + text)
loader = Loader("weka.core.converters.ArffLoader")
data = loader.load_file(text)
data.class_is_last()
# apply StringToWordVector
stemmer = Stemmer(classname="weka.core.stemmers.IteratedLovinsStemmer")
stopwords = Stopwords(classname="weka.core.stopwords.Rainbow")
tokenizer = Tokenizer(classname="weka.core.tokenizers.WordTokenizer")
s2wv = StringToWordVector(options=["-W", "10", "-L", "-C"])
s2wv.stemmer = stemmer
s2wv.stopwords = stopwords
s2wv.tokenizer = tokenizer
s2wv.inputformat(data)
filtered = s2wv.filter(data)
helper.print_title("Input (StringToWordVector)")
print(data)
helper.print_title("Output (StringToWordVector)")
print(filtered)
def main(args):
"""
Loads a dataset, shuffles it, splits it into train/test set. Trains J48 with training set and
evaluates the built model on the test set.
:param args: the commandline arguments (optional, can be dataset filename)
:type args: list
"""
# load a dataset
if len(args) <= 1:
data_file = helper.get_data_dir() + os.sep + "vote.arff"
else:
data_file = args[1]
helper.print_info("Loading dataset: " + data_file)
loader = Loader(classname="weka.core.converters.ArffLoader")
data = loader.load_file(data_file)
data.class_is_last()
# generate train/test split of randomized data
train, test = data.train_test_split(66.0, Random(1))
# build classifier
cls = Classifier(classname="weka.classifiers.trees.J48")
cls.build_classifier(train)
print(cls)
# evaluate
evl = Evaluation(train)
evl.test_model(cls, test)
print(evl.summary())
def main():
"""
Just runs some example code.
"""
classifier = Classifier("weka.classifiers.trees.J48")
helper.print_title("Capabilities")
capabilities = classifier.capabilities
print(capabilities)
# 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()
data_capabilities = Capabilities.for_instances(iris_data)
print(data_capabilities)
print("classifier handles dataset: " + str(capabilities.supports(data_capabilities)))
# disable/enable
helper.print_title("Disable/Enable")
capability = Capability(member="UNARY_ATTRIBUTES")
capabilities.disable(capability)
capabilities.min_instances = 10
print("Removing: " + str(capability))
print(capabilities)
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")
full = loader.load_file(iris_file)
full.class_is_last()
# remove class attribute
data = Instances.copy_instances(full)
data.no_class()
data.delete_last_attribute()
# build a clusterer and output model
helper.print_title("Training SimpleKMeans clusterer")
clusterer = Clusterer(classname="weka.clusterers.SimpleKMeans", options=["-N", "3"])
clusterer.build_clusterer(data)
print("done")
# classes to clusters
evl = ClusterEvaluation()
evl.set_model(clusterer)
evl.test_model(full)
helper.print_title("Cluster results")
print(evl.cluster_results)
helper.print_title("Classes to clusters")
print(evl.classes_to_clusters)
def main(args):
"""
Trains a NaiveBayesUpdateable classifier incrementally on a dataset. The dataset can be supplied as parameter.
:param args: the commandline arguments
:type args: list
"""
# load a dataset
if len(args) <= 1:
data_file = helper.get_data_dir() + os.sep + "vote.arff"
else:
data_file = args[1]
helper.print_info("Loading dataset: " + data_file)
loader = Loader(classname="weka.core.converters.ArffLoader")
data = loader.load_file(data_file, incremental=True)
data.class_is_last()
# classifier
nb = Classifier(classname="weka.classifiers.bayes.NaiveBayesUpdateable")
nb.build_classifier(data)
# train incrementally
for inst in loader:
nb.update_classifier(inst)
print(nb)
def main(args):
"""
Trains a NaiveBayesUpdateable classifier incrementally on a dataset. The dataset can be supplied as parameter.
:param args: the commandline arguments
:type args: list
"""
# load a dataset
if len(args) <= 1:
data_file = helper.get_data_dir() + os.sep + "vote.arff"
else:
data_file = args[1]
helper.print_info("Loading dataset: " + data_file)
loader = Loader(classname="weka.core.converters.ArffLoader")
data = loader.load_file(data_file, incremental=True)
data.class_is_last()
# classifier
nb = Classifier(classname="weka.classifiers.bayes.NaiveBayesUpdateable")
nb.build_classifier(data)
# train incrementally
for inst in loader:
nb.update_classifier(inst)
print(nb)
def gridsearch():
"""
Applies GridSearch to a dataset. GridSearch package must be not be installed, as the monolithic weka.jar
already contains this package.
"""
helper.print_title("GridSearch")
# load a dataset
fname = helper.get_data_dir() + os.sep + "bolts.arff"
helper.print_info("Loading train: " + fname)
loader = Loader(classname="weka.core.converters.ArffLoader")
train = loader.load_file(fname)
train.class_is_last()
# classifier
grid = GridSearch(options=["-sample-size", "100.0", "-traversal", "ROW-WISE", "-num-slots", "1", "-S", "1"])
grid.evaluation = "CC"
grid.y = {"property": "kernel.gamma", "min": -3.0, "max": 3.0, "step": 1.0, "base": 10.0, "expression": "pow(BASE,I)"}
grid.x = {"property": "C", "min": -3.0, "max": 3.0, "step": 1.0, "base": 10.0, "expression": "pow(BASE,I)"}
cls = Classifier(
classname="weka.classifiers.functions.SMOreg",
options=["-K", "weka.classifiers.functions.supportVector.RBFKernel"])
grid.classifier = cls
grid.build_classifier(train)
print("Model:\n" + str(grid))
print("\nBest setup:\n" + grid.best.to_commandline())
def main(args):
"""
Loads a dataset, shuffles it, splits it into train/test set. Trains J48 with training set and
evaluates the built model on the test set.
:param args: the commandline arguments (optional, can be dataset filename)
:type args: list
"""
# load a dataset
if len(args) <= 1:
data_file = helper.get_data_dir() + os.sep + "vote.arff"
else:
data_file = args[1]
helper.print_info("Loading dataset: " + data_file)
loader = Loader(classname="weka.core.converters.ArffLoader")
data = loader.load_file(data_file)
data.class_is_last()
# generate train/test split of randomized data
train, test = data.train_test_split(66.0, Random(1))
# build classifier
cls = Classifier(classname="weka.classifiers.trees.J48")
cls.build_classifier(train)
print(cls)
# evaluate
evl = Evaluation(train)
evl.test_model(cls, test)
print(evl.summary())
def load_incremental():
"""
Loads a dataset incrementally.
"""
# setup the flow
helper.print_title("Load dataset (incremental)")
iris = helper.get_data_dir() + os.sep + "iris.arff"
flow = Flow(name="load dataset")
filesupplier = FileSupplier()
filesupplier.config["files"] = [iris]
flow.actors.append(filesupplier)
loaddataset = LoadDataset()
loaddataset.config["incremental"] = True
flow.actors.append(loaddataset)
console = Console()
flow.actors.append(console)
# run the flow
msg = flow.setup()
if msg is None:
msg = flow.execute()
if msg is not None:
print("Error executing flow:\n" + msg)
else:
print("Error setting up flow:\n" + msg)
flow.wrapup()
flow.cleanup()
def load_custom_loader():
"""
Loads a dataset using a custom loader.
"""
# setup the flow
helper.print_title("Load dataset (custom loader)")
iris = helper.get_data_dir() + os.sep + "iris.csv"
flow = Flow(name="load dataset")
filesupplier = FileSupplier()
filesupplier.config["files"] = [iris]
flow.actors.append(filesupplier)
loaddataset = LoadDataset()
loaddataset.config["incremental"] = False
loaddataset.config["use_custom_loader"] = True
loaddataset.config["custom_loader"] = Loader(classname="weka.core.converters.CSVLoader")
flow.actors.append(loaddataset)
console = Console()
flow.actors.append(console)
# run the flow
msg = flow.setup()
if msg is None:
msg = flow.execute()
if msg is not None:
print("Error executing flow:\n" + msg)
else:
print("Error setting up flow:\n" + msg)
flow.wrapup()
flow.cleanup()
def main():
"""
Just runs some example code.
"""
"""
Plots a dataset.
"""
# setup the flow
helper.print_title("Plot dataset")
iris = helper.get_data_dir() + os.sep + "iris.arff"
flow = Flow(name="plot dataset")
filesupplier = FileSupplier()
filesupplier.config["files"] = [iris]
flow.actors.append(filesupplier)
loaddataset = LoadDataset()
flow.actors.append(loaddataset)
branch = Branch()
flow.actors.append(branch)
seq = Sequence(name="matrix plot")
branch.actors.append(seq)
mplot = MatrixPlot()
mplot.config["percent"] = 50.0
mplot.config["wait"] = False
seq.actors.append(mplot)
seq = Sequence(name="line plot")
branch.actors.append(seq)
copy = Copy()
seq.actors.append(copy)
flter = Filter()
flter.config["setup"] = filters.Filter(
classname="weka.filters.unsupervised.attribute.Remove", options=["-R", "last"])
flter.config["keep_relationname"] = True
seq.actors.append(flter)
lplot = LinePlot()
lplot.config["percent"] = 50.0
lplot.config["wait"] = True
seq.actors.append(lplot)
# run the flow
msg = flow.setup()
if msg is None:
print("\n" + flow.tree + "\n")
msg = flow.execute()
if msg is not None:
print("Error executing flow:\n" + msg)
else:
print("Error setting up flow:\n" + msg)
flow.wrapup()
flow.cleanup()
def load_incremental():
"""
Loads a dataset incrementally.
"""
# setup the flow
helper.print_title("Load dataset (incremental)")
iris = helper.get_data_dir() + os.sep + "iris.arff"
flow = Flow(name="load dataset")
filesupplier = FileSupplier()
filesupplier.config["files"] = [iris]
flow.actors.append(filesupplier)
loaddataset = LoadDataset()
loaddataset.config["incremental"] = True
flow.actors.append(loaddataset)
console = Console()
flow.actors.append(console)
# run the flow
msg = flow.setup()
if msg is None:
msg = flow.execute()
if msg is not None:
print("Error executing flow:\n" + msg)
else:
print("Error setting up flow:\n" + msg)
flow.wrapup()
flow.cleanup()
def load_custom_loader():
"""
Loads a dataset using a custom loader.
"""
# setup the flow
helper.print_title("Load dataset (custom loader)")
iris = helper.get_data_dir() + os.sep + "iris.csv"
flow = Flow(name="load dataset")
filesupplier = FileSupplier()
filesupplier.config["files"] = [iris]
flow.actors.append(filesupplier)
loaddataset = LoadDataset()
loaddataset.config["incremental"] = False
loaddataset.config["use_custom_loader"] = True
loaddataset.config["custom_loader"] = Loader(
classname="weka.core.converters.CSVLoader")
flow.actors.append(loaddataset)
console = Console()
flow.actors.append(console)
# run the flow
msg = flow.setup()
if msg is None:
msg = flow.execute()
if msg is not None:
print("Error executing flow:\n" + msg)
else:
print("Error setting up flow:\n" + msg)
flow.wrapup()
flow.cleanup()
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")
data = loader.load_file(iris_file)
# remove class attribute
data.delete_last_attribute()
# build a clusterer and output model
helper.print_title("Training SimpleKMeans clusterer")
clusterer = Clusterer(classname="weka.clusterers.SimpleKMeans", options=["-N", "3"])
clusterer.build_clusterer(data)
print(clusterer)
# cluster data
helper.print_info("Clustering data")
for index, inst in enumerate(data):
cl = clusterer.cluster_instance(inst)
dist = clusterer.distribution_for_instance(inst)
print(str(index+1) + ": cluster=" + str(cl) + ", distribution=" + str(dist))
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")
full = loader.load_file(iris_file)
full.class_is_last()
# remove class attribute
data = Instances.copy_instances(full)
data.no_class()
data.delete_last_attribute()
# build a clusterer and output model
helper.print_title("Training SimpleKMeans clusterer")
clusterer = Clusterer(classname="weka.clusterers.SimpleKMeans",
options=["-N", "3"])
clusterer.build_clusterer(data)
print("done")
# classes to clusters
evl = ClusterEvaluation()
evl.set_model(clusterer)
evl.test_model(full)
helper.print_title("Cluster results")
print(evl.cluster_results)
helper.print_title("Classes to clusters")
print(evl.classes_to_clusters)
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()
# train classifier
classifier = Classifier("weka.classifiers.trees.J48")
classifier.build_classifier(iris_data)
# save and read object
helper.print_title("I/O: single object")
outfile = tempfile.gettempdir() + os.sep + "j48.model"
serialization.write(outfile, classifier)
model = Classifier(jobject=serialization.read(outfile))
print(model)
# save classifier and dataset header (multiple objects)
helper.print_title("I/O: single object")
serialization.write_all(outfile, [classifier, Instances.template_instances(iris_data)])
objects = serialization.read_all(outfile)
for i, obj in enumerate(objects):
helper.print_info("Object #" + str(i+1) + ":")
if javabridge.get_env().is_instance_of(obj, javabridge.get_env().find_class("weka/core/Instances")):
obj = Instances(jobject=obj)
elif javabridge.get_env().is_instance_of(obj, javabridge.get_env().find_class("weka/classifiers/Classifier")):
obj = Classifier(jobject=obj)
print(obj)
def main():
"""
Shows how to use the CostSensitiveClassifier.
"""
# load a dataset
data_file = helper.get_data_dir() + os.sep + "diabetes.arff"
helper.print_info("Loading dataset: " + data_file)
loader = Loader("weka.core.converters.ArffLoader")
data = loader.load_file(data_file)
data.class_is_last()
# classifier
classifier = SingleClassifierEnhancer(
classname="weka.classifiers.meta.CostSensitiveClassifier",
options=["-cost-matrix", "[0 1; 2 0]", "-S", "2"])
base = Classifier(classname="weka.classifiers.trees.J48", options=["-C", "0.3"])
classifier.classifier = base
folds = 10
evaluation = Evaluation(data)
evaluation.crossvalidate_model(classifier, data, folds, Random(1))
print("")
print("=== Setup ===")
print("Classifier: " + classifier.to_commandline())
print("Dataset: " + data.relationname)
print("")
print(evaluation.summary("=== " + str(folds) + " -fold Cross-Validation ==="))
def main():
"""
Shows how to use the CostSensitiveClassifier.
"""
# load a dataset
data_file = helper.get_data_dir() + os.sep + "diabetes.arff"
helper.print_info("Loading dataset: " + data_file)
loader = Loader("weka.core.converters.ArffLoader")
data = loader.load_file(data_file)
data.class_is_last()
# classifier
classifier = SingleClassifierEnhancer(
classname="weka.classifiers.meta.CostSensitiveClassifier",
options=["-cost-matrix", "[0 1; 2 0]", "-S", "2"])
base = Classifier(classname="weka.classifiers.trees.J48",
options=["-C", "0.3"])
classifier.classifier = base
folds = 10
evaluation = Evaluation(data)
evaluation.crossvalidate_model(classifier, data, folds, Random(1))
print("")
print("=== Setup ===")
print("Classifier: " + classifier.to_commandline())
print("Dataset: " + data.relationname)
print("")
print(
evaluation.summary("=== " + str(folds) +
" -fold Cross-Validation ==="))
def main(args):
"""
Trains Apriori on the specified dataset (uses vote UCI dataset if no dataset specified).
:param args: the commandline arguments
:type args: list
"""
# load a dataset
if len(args) <= 1:
data_file = helper.get_data_dir() + os.sep + "vote.arff"
else:
data_file = args[1]
helper.print_info("Loading dataset: " + data_file)
loader = Loader("weka.core.converters.ArffLoader")
data = loader.load_file(data_file)
data.class_is_last()
# build Apriori, using last attribute as class attribute
apriori = Associator(classname="weka.associations.Apriori", options=["-c", "-1"])
apriori.build_associations(data)
print(str(apriori))
# iterate association rules (low-level)
helper.print_info("Rules (low-level)")
# make the underlying rules list object iterable in Python
rules = javabridge.iterate_collection(apriori.jwrapper.getAssociationRules().getRules().o)
for i, r in enumerate(rules):
# wrap the Java object to make its methods accessible
rule = JWrapper(r)
print(str(i+1) + ". " + str(rule))
# output some details on rule
print(" - consequence support: " + str(rule.getConsequenceSupport()))
print(" - premise support: " + str(rule.getPremiseSupport()))
print(" - total support: " + str(rule.getTotalSupport()))
print(" - total transactions: " + str(rule.getTotalTransactions()))
# iterate association rules (high-level)
helper.print_info("Rules (high-level)")
print("can produce rules? " + str(apriori.can_produce_rules()))
print("rule metric names: " + str(apriori.rule_metric_names))
rules = apriori.association_rules()
if rules is not None:
print("producer: " + rules.producer)
print("# rules: " + str(len(rules)))
for i, rule in enumerate(rules):
print(str(i+1) + ". " + str(rule))
# output some details on rule
print(" - consequence support: " + str(rule.consequence_support))
print(" - consequence: " + str(rule.consequence))
print(" - premise support: " + str(rule.premise_support))
print(" - premise: " + str(rule.premise))
print(" - total support: " + str(rule.total_support))
print(" - total transactions: " + str(rule.total_transactions))
print(" - metric names: " + str(rule.metric_names))
print(" - metric values: " + str(rule.metric_values))
print(" - metric value 'Confidence': " + str(rule.metric_value('Confidence')))
print(" - primary metric name: " + str(rule.primary_metric_name))
print(" - primary metric value: " + str(rule.primary_metric_value))
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")
data = loader.load_file(iris_file)
# remove class attribute
data.delete_last_attribute()
# build a clusterer and output model
helper.print_title("Training SimpleKMeans clusterer")
clusterer = Clusterer(classname="weka.clusterers.SimpleKMeans", options=["-N", "3"])
clusterer.build_clusterer(data)
print(clusterer)
helper.print_info("Evaluating on data")
evaluation = ClusterEvaluation()
evaluation.set_model(clusterer)
evaluation.test_model(data)
print("# clusters: " + str(evaluation.num_clusters))
print("log likelihood: " + str(evaluation.log_likelihood))
print("cluster assignments:\n" + str(evaluation.cluster_assignments))
plc.plot_cluster_assignments(evaluation, data, inst_no=True)
# using a filtered clusterer
helper.print_title("Filtered clusterer")
loader = Loader("weka.core.converters.ArffLoader")
data = loader.load_file(iris_file)
clusterer = Clusterer(classname="weka.clusterers.SimpleKMeans", options=["-N", "3"])
remove = Filter(classname="weka.filters.unsupervised.attribute.Remove", options=["-R", "last"])
fclusterer = FilteredClusterer()
fclusterer.clusterer = clusterer
fclusterer.filter = remove
fclusterer.build_clusterer(data)
print(fclusterer)
# load a dataset incrementally and build clusterer incrementally
helper.print_title("Incremental clusterer")
loader = Loader("weka.core.converters.ArffLoader")
iris_inc = loader.load_file(iris_file, incremental=True)
clusterer = Clusterer("weka.clusterers.Cobweb")
remove = Filter(classname="weka.filters.unsupervised.attribute.Remove", options=["-R", "last"])
remove.inputformat(iris_inc)
iris_filtered = remove.outputformat()
clusterer.build_clusterer(iris_filtered)
for inst in loader:
remove.input(inst)
inst_filtered = remove.output()
clusterer.update_clusterer(inst_filtered)
clusterer.update_finished()
print(clusterer.to_commandline())
print(clusterer)
print(clusterer.graph)
plg.plot_dot_graph(clusterer.graph)
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")
data = loader.load_file(iris_file)
# remove class attribute
data.delete_last_attribute()
# build a clusterer and output model
helper.print_title("Training SimpleKMeans clusterer")
clusterer = Clusterer(classname="weka.clusterers.SimpleKMeans", options=["-N", "3"])
clusterer.build_clusterer(data)
print(clusterer)
helper.print_info("Evaluating on data")
evaluation = ClusterEvaluation()
evaluation.set_model(clusterer)
evaluation.test_model(data)
print("# clusters: " + str(evaluation.num_clusters))
print("log likelihood: " + str(evaluation.log_likelihood))
print("cluster assignments:\n" + str(evaluation.cluster_assignments))
plc.plot_cluster_assignments(evaluation, data, inst_no=True)
# using a filtered clusterer
helper.print_title("Filtered clusterer")
loader = Loader("weka.core.converters.ArffLoader")
data = loader.load_file(iris_file)
clusterer = Clusterer(classname="weka.clusterers.SimpleKMeans", options=["-N", "3"])
remove = Filter(classname="weka.filters.unsupervised.attribute.Remove", options=["-R", "last"])
fclusterer = FilteredClusterer()
fclusterer.clusterer = clusterer
fclusterer.filter = remove
fclusterer.build_clusterer(data)
print(fclusterer)
# load a dataset incrementally and build clusterer incrementally
helper.print_title("Incremental clusterer")
loader = Loader("weka.core.converters.ArffLoader")
iris_inc = loader.load_file(iris_file, incremental=True)
clusterer = Clusterer("weka.clusterers.Cobweb")
remove = Filter(classname="weka.filters.unsupervised.attribute.Remove", options=["-R", "last"])
remove.inputformat(iris_inc)
iris_filtered = remove.outputformat()
clusterer.build_clusterer(iris_filtered)
for inst in loader:
remove.input(inst)
inst_filtered = remove.output()
clusterer.update_clusterer(inst_filtered)
clusterer.update_finished()
print(clusterer.to_commandline())
print(clusterer)
print(clusterer.graph)
plg.plot_dot_graph(clusterer.graph)
def incremental():
"""
Just runs some example code.
"""
"""
Loads/filters a dataset incrementally.
"""
# setup the flow
helper.print_title("Filter datasets (incrementally)")
iris = helper.get_data_dir() + os.sep + "iris.arff"
anneal = helper.get_data_dir() + os.sep + "anneal.arff"
flow = Flow(name="filter datasets (incrementally)")
filesupplier = FileSupplier()
filesupplier.config["files"] = [iris, anneal]
flow.actors.append(filesupplier)
loaddataset = LoadDataset()
loaddataset.config["incremental"] = True
flow.actors.append(loaddataset)
flter = Filter()
flter.config["setup"] = filters.Filter(
classname="weka.filters.unsupervised.attribute.Remove",
options=["-R", "1"])
flter.config["keep_relationname"] = True
flow.actors.append(flter)
console = Console()
flow.actors.append(console)
# run the flow
msg = flow.setup()
if msg is None:
print("\n" + flow.tree + "\n")
msg = flow.execute()
if msg is not None:
print("Error executing flow:\n" + msg)
else:
print("Error setting up flow:\n" + msg)
flow.wrapup()
flow.cleanup()
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()
# train classifier
classifier = Classifier("weka.classifiers.trees.J48")
classifier.build_classifier(iris_data)
# save and read object
helper.print_title("I/O: model (using serialization module)")
outfile = tempfile.gettempdir() + os.sep + "j48.model"
serialization.write(outfile, classifier)
model = Classifier(jobject=serialization.read(outfile))
print(model)
# save classifier and dataset header (multiple objects)
helper.print_title("I/O: model and header (using serialization module)")
serialization.write_all(
outfile,
[classifier, Instances.template_instances(iris_data)])
objects = serialization.read_all(outfile)
for i, obj in enumerate(objects):
helper.print_info("Object #" + str(i + 1) + ":")
if javabridge.get_env().is_instance_of(
obj,
javabridge.get_env().find_class("weka/core/Instances")):
obj = Instances(jobject=obj)
elif javabridge.get_env().is_instance_of(
obj,
javabridge.get_env().find_class(
"weka/classifiers/Classifier")):
obj = Classifier(jobject=obj)
print(obj)
# save and read object
helper.print_title("I/O: just model (using Classifier class)")
outfile = tempfile.gettempdir() + os.sep + "j48.model"
classifier.serialize(outfile)
model, _ = Classifier.deserialize(outfile)
print(model)
# save classifier and dataset header (multiple objects)
helper.print_title("I/O: model and header (using Classifier class)")
classifier.serialize(outfile, header=iris_data)
model, header = Classifier.deserialize(outfile)
print(model)
if header is not None:
print(header)
def incremental():
"""
Just runs some example code.
"""
"""
Loads/filters a dataset incrementally.
"""
# setup the flow
helper.print_title("Filter datasets (incrementally)")
iris = helper.get_data_dir() + os.sep + "iris.arff"
anneal = helper.get_data_dir() + os.sep + "anneal.arff"
flow = Flow(name="filter datasets (incrementally)")
filesupplier = FileSupplier()
filesupplier.config["files"] = [iris, anneal]
flow.actors.append(filesupplier)
loaddataset = LoadDataset()
loaddataset.config["incremental"] = True
flow.actors.append(loaddataset)
flter = Filter()
flter.config["setup"] = filters.Filter(
classname="weka.filters.unsupervised.attribute.Remove", options=["-R", "1"])
flter.config["keep_relationname"] = True
flow.actors.append(flter)
console = Console()
flow.actors.append(console)
# run the flow
msg = flow.setup()
if msg is None:
print("\n" + flow.tree + "\n")
msg = flow.execute()
if msg is not None:
print("Error executing flow:\n" + msg)
else:
print("Error setting up flow:\n" + msg)
flow.wrapup()
flow.cleanup()
def main():
"""
Just runs some example code.
"""
# setup the flow
flow = Flow(name="list files")
listfiles = ListFiles()
listfiles.config["dir"] = str(helper.get_data_dir())
listfiles.config["list_files"] = True
listfiles.config["list_dirs"] = False
listfiles.config["recursive"] = False
listfiles.config["regexp"] = ".*.arff"
flow.actors.append(listfiles)
tee = Tee()
flow.actors.append(tee)
convert = Convert()
convert.config["setup"] = conversion.PassThrough()
tee.actors.append(convert)
console = Console()
console.config["prefix"] = "Match: "
tee.actors.append(console)
load = LoadDataset()
load.config["use_custom_loader"] = True
flow.actors.append(load)
cross = CrossValidate()
cross.config["setup"] = Classifier(classname="weka.classifiers.trees.J48",
options=["-C", "0.3"])
flow.actors.append(cross)
summary = EvaluationSummary()
summary.config["matrix"] = True
flow.actors.append(summary)
# print flow
flow.setup()
print("\n" + flow.tree + "\n")
# save the flow
fname = tempfile.gettempdir() + os.sep + "simpleflow.json"
Flow.save(flow, fname)
# load flow
fl2 = Flow.load(fname)
# output flow
fl2.setup()
print("\n" + fl2.tree + "\n")
def arffInput(self):
# load a dataset
iris_file = helper.get_data_dir(
) + os.sep + "/Users/rezakhoshkangini/Documents/Drexel_Documents/Work/Mat-Code/NewCSV/BindedData/Section0.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())
def main():
"""
Just runs some example code.
"""
# setup the flow
flow = Flow(name="list files")
listfiles = ListFiles()
listfiles.config["dir"] = str(helper.get_data_dir())
listfiles.config["list_files"] = True
listfiles.config["list_dirs"] = False
listfiles.config["recursive"] = False
listfiles.config["regexp"] = ".*.arff"
flow.actors.append(listfiles)
tee = Tee()
flow.actors.append(tee)
convert = Convert()
convert.config["setup"] = conversion.PassThrough()
tee.actors.append(convert)
console = Console()
console.config["prefix"] = "Match: "
tee.actors.append(console)
load = LoadDataset()
load.config["use_custom_loader"] = True
flow.actors.append(load)
cross = CrossValidate()
cross.config["setup"] = Classifier(classname="weka.classifiers.trees.J48", options=["-C", "0.3"])
flow.actors.append(cross)
summary = EvaluationSummary()
summary.config["matrix"] = True
flow.actors.append(summary)
# print flow
flow.setup()
print("\n" + flow.tree + "\n")
# save the flow
fname = tempfile.gettempdir() + os.sep + "simpleflow.json"
Flow.save(flow, fname)
# load flow
fl2 = Flow.load(fname)
# output flow
fl2.setup()
print("\n" + fl2.tree + "\n")
def main(args):
"""
Loads a dataset, shuffles it, splits it into train/test set. Trains J48 with training set and
evaluates the built model on the test set.
The predictions get recorded in two different ways:
1. in-memory via the test_model method
2. directly to file (more memory efficient), but a separate run of making predictions
:param args: the commandline arguments (optional, can be dataset filename)
:type args: list
"""
# load a dataset
if len(args) <= 1:
data_file = helper.get_data_dir() + os.sep + "vote.arff"
else:
data_file = args[1]
helper.print_info("Loading dataset: " + data_file)
loader = Loader(classname="weka.core.converters.ArffLoader")
data = loader.load_file(data_file)
data.class_is_last()
# generate train/test split of randomized data
train, test = data.train_test_split(66.0, Random(1))
# build classifier
cls = Classifier(classname="weka.classifiers.trees.J48")
cls.build_classifier(train)
print(cls)
# evaluate and record predictions in memory
helper.print_title("recording predictions in-memory")
output = PredictionOutput(
classname="weka.classifiers.evaluation.output.prediction.CSV",
options=["-distribution"])
evl = Evaluation(train)
evl.test_model(cls, test, output=output)
print(evl.summary())
helper.print_info("Predictions:")
print(output.buffer_content())
# record/output predictions separately
helper.print_title("recording/outputting predictions separately")
outputfile = helper.get_tmp_dir() + "/j48_vote.csv"
output = PredictionOutput(
classname="weka.classifiers.evaluation.output.prediction.CSV",
options=["-distribution", "-suppress", "-file", outputfile])
output.header = test
output.print_all(cls, test)
helper.print_info("Predictions stored in:" + outputfile)
# by using "-suppress" we don't store the output in memory, the following statement won't output anything
print(output.buffer_content())
def main():
"""
Just runs some example code.
"""
# load a dataset
vote_file = helper.get_data_dir() + os.sep + "vote.arff"
helper.print_info("Loading dataset: " + vote_file)
loader = Loader("weka.core.converters.ArffLoader")
vote_data = loader.load_file(vote_file)
vote_data.class_is_last()
# train and output associator
associator = Associator(classname="weka.associations.Apriori", options=["-N", "9", "-I"])
associator.build_associations(vote_data)
print(associator)
def main():
"""
Just runs some example code.
"""
"""
Loads/filters a dataset incrementally and saves it to a new file.
"""
# setup the flow
helper.print_title("Load/filter/save dataset (incrementally)")
iris = helper.get_data_dir() + os.sep + "iris.arff"
flow = Flow(name="Load/filter/save dataset (incrementally)")
filesupplier = FileSupplier()
filesupplier.config["files"] = [iris]
flow.actors.append(filesupplier)
loaddataset = LoadDataset()
loaddataset.config["incremental"] = True
flow.actors.append(loaddataset)
flter = Filter()
flter.config["setup"] = filters.Filter(
classname="weka.filters.unsupervised.attribute.Remove",
options=["-R", "last"])
flow.actors.append(flter)
rename = RenameRelation()
rename.config["name"] = "iris-reduced"
flow.actors.append(rename)
dumper = InstanceDumper()
dumper.config["output"] = tempfile.gettempdir() + os.sep + "out.arff"
flow.actors.append(dumper)
# run the flow
msg = flow.setup()
if msg is None:
print("\n" + flow.tree + "\n")
msg = flow.execute()
if msg is not None:
print("Error executing flow:\n" + msg)
else:
print("Error setting up flow:\n" + msg)
flow.wrapup()
flow.cleanup()
def main():
"""
Just runs some example code.
"""
# load a dataset
bodyfat_file = helper.get_data_dir() + os.sep + "bodyfat.arff"
helper.print_info("Loading dataset: " + bodyfat_file)
loader = Loader("weka.core.converters.ArffLoader")
bodyfat_data = loader.load_file(bodyfat_file)
bodyfat_data.class_is_last()
# classifier help
helper.print_title("Creating help string")
classifier = Classifier(classname="weka.classifiers.trees.M5P")
classifier.build_classifier(bodyfat_data)
print(classifier)
def main():
"""
Just runs some example code.
"""
# load a dataset
vote_file = helper.get_data_dir() + os.sep + "vote.arff"
helper.print_info("Loading dataset: " + vote_file)
loader = Loader("weka.core.converters.ArffLoader")
vote_data = loader.load_file(vote_file)
vote_data.class_is_last()
# train and output associator
associator = Associator(classname="weka.associations.Apriori",
options=["-N", "9", "-I"])
associator.build_associations(vote_data)
print(associator)
def main():
"""
Just runs some example code.
"""
"""
Loads/filters a dataset incrementally and saves it to a new file.
"""
# setup the flow
helper.print_title("Load/filter/save dataset (incrementally)")
iris = helper.get_data_dir() + os.sep + "iris.arff"
flow = Flow(name="Load/filter/save dataset (incrementally)")
filesupplier = FileSupplier()
filesupplier.config["files"] = [iris]
flow.actors.append(filesupplier)
loaddataset = LoadDataset()
loaddataset.config["incremental"] = True
flow.actors.append(loaddataset)
flter = Filter()
flter.config["setup"] = filters.Filter(
classname="weka.filters.unsupervised.attribute.Remove", options=["-R", "last"])
flow.actors.append(flter)
rename = RenameRelation()
rename.config["name"] = "iris-reduced"
flow.actors.append(rename)
dumper = InstanceDumper()
dumper.config["output"] = tempfile.gettempdir() + os.sep + "out.arff"
flow.actors.append(dumper)
# run the flow
msg = flow.setup()
if msg is None:
print("\n" + flow.tree + "\n")
msg = flow.execute()
if msg is not None:
print("Error executing flow:\n" + msg)
else:
print("Error setting up flow:\n" + msg)
flow.wrapup()
flow.cleanup()
def main():
"""
Just runs some example code.
"""
# load a dataset
bodyfat_file = helper.get_data_dir() + os.sep + "bodyfat.arff"
helper.print_info("Loading dataset: " + bodyfat_file)
loader = Loader("weka.core.converters.ArffLoader")
bodyfat_data = loader.load_file(bodyfat_file)
bodyfat_data.class_is_last()
# classifier help
helper.print_title("Creating help string")
classifier = Classifier(classname="weka.classifiers.trees.M5P")
classifier.build_classifier(bodyfat_data)
print(classifier)
def main():
"""
Just runs some example code.
"""
# setup the flow
helper.print_title("build and save clusterer")
iris = helper.get_data_dir() + os.sep + "iris_no_class.arff"
flow = Flow(name="build and save clusterer")
filesupplier = FileSupplier()
filesupplier.config["files"] = [iris]
flow.actors.append(filesupplier)
loaddataset = LoadDataset()
flow.actors.append(loaddataset)
train = Train()
train.config["setup"] = Clusterer(classname="weka.clusterers.SimpleKMeans")
flow.actors.append(train)
pick = ContainerValuePicker()
pick.config["value"] = "Model"
flow.actors.append(pick)
console = Console()
pick.actors.append(console)
writer = ModelWriter()
writer.config["output"] = str(
tempfile.gettempdir()) + os.sep + "simplekmeans.model"
flow.actors.append(writer)
# run the flow
msg = flow.setup()
if msg is None:
print("\n" + flow.tree + "\n")
msg = flow.execute()
if msg is not None:
print("Error executing flow:\n" + msg)
else:
print("Error setting up flow:\n" + msg)
flow.wrapup()
flow.cleanup()
def main():
"""
Just runs some example code.
"""
# setup the flow
helper.print_title("build and save clusterer")
iris = helper.get_data_dir() + os.sep + "iris_no_class.arff"
flow = Flow(name="build and save clusterer")
filesupplier = FileSupplier()
filesupplier.config["files"] = [iris]
flow.actors.append(filesupplier)
loaddataset = LoadDataset()
flow.actors.append(loaddataset)
train = Train()
train.config["setup"] = Clusterer(classname="weka.clusterers.SimpleKMeans")
flow.actors.append(train)
pick = ContainerValuePicker()
pick.config["value"] = "Model"
flow.actors.append(pick)
console = Console()
pick.actors.append(console)
writer = ModelWriter()
writer.config["output"] = str(tempfile.gettempdir()) + os.sep + "simplekmeans.model"
flow.actors.append(writer)
# run the flow
msg = flow.setup()
if msg is None:
print("\n" + flow.tree + "\n")
msg = flow.execute()
if msg is not None:
print("Error executing flow:\n" + msg)
else:
print("Error setting up flow:\n" + msg)
flow.wrapup()
flow.cleanup()
def main():
"""
Just runs some example code.
"""
# setup the flow
helper.print_title("Cross-validate clusterer")
iris = helper.get_data_dir() + os.sep + "iris.arff"
flow = Flow(name="cross-validate clusterer")
filesupplier = FileSupplier()
filesupplier.config["files"] = [iris]
flow.actors.append(filesupplier)
loaddataset = LoadDataset()
flow.actors.append(loaddataset)
flter = Filter()
flter.name = "Remove class"
flter.config["filter"] = filters.Filter(
classname="weka.filters.unsupervised.attribute.Remove",
options=["-R", "last"])
flow.actors.append(flter)
cv = CrossValidate()
cv.config["setup"] = Clusterer(classname="weka.clusterers.EM")
flow.actors.append(cv)
console = Console()
console.config["prefix"] = "Loglikelihood: "
flow.actors.append(console)
# run the flow
msg = flow.setup()
if msg is None:
print("\n" + flow.tree + "\n")
msg = flow.execute()
if msg is not None:
print("Error executing flow:\n" + msg)
else:
print("Error setting up flow:\n" + msg)
flow.wrapup()
flow.cleanup()
def main():
"""
Just runs some example code.
"""
# load a dataset
anneal_file = helper.get_data_dir() + os.sep + "anneal.arff"
helper.print_info("Loading dataset: " + anneal_file)
loader = Loader("weka.core.converters.ArffLoader")
anneal_data = loader.load_file(anneal_file)
anneal_data.class_is_last()
# perform attribute selection
helper.print_title("Attribute selection")
search = ASSearch(classname="weka.attributeSelection.BestFirst",
options=["-D", "1", "-N", "5"])
evaluation = ASEvaluation(
classname="weka.attributeSelection.CfsSubsetEval",
options=["-P", "1", "-E", "1"])
attsel = AttributeSelection()
attsel.search(search)
attsel.evaluator(evaluation)
attsel.select_attributes(anneal_data)
print("# attributes: " + str(attsel.number_attributes_selected))
print("attributes (as numpy array): " + str(attsel.selected_attributes))
print("attributes (as list): " + str(list(attsel.selected_attributes)))
print("result string:\n" + attsel.results_string)
# perform ranking
helper.print_title("Attribute ranking (2-fold CV)")
search = ASSearch(classname="weka.attributeSelection.Ranker",
options=["-N", "-1"])
evaluation = ASEvaluation("weka.attributeSelection.InfoGainAttributeEval")
attsel = AttributeSelection()
attsel.ranking(True)
attsel.folds(2)
attsel.crossvalidation(True)
attsel.seed(42)
attsel.search(search)
attsel.evaluator(evaluation)
attsel.select_attributes(anneal_data)
print("ranked attributes:\n" + str(attsel.ranked_attributes))
print("result string:\n" + attsel.results_string)
def main():
"""
Just runs some example code.
"""
# setup the flow
helper.print_title("Cross-validate clusterer")
iris = helper.get_data_dir() + os.sep + "iris.arff"
flow = Flow(name="cross-validate clusterer")
filesupplier = FileSupplier()
filesupplier.config["files"] = [iris]
flow.actors.append(filesupplier)
loaddataset = LoadDataset()
flow.actors.append(loaddataset)
flter = Filter()
flter.name = "Remove class"
flter.config["filter"] = filters.Filter(
classname="weka.filters.unsupervised.attribute.Remove", options=["-R", "last"])
flow.actors.append(flter)
cv = CrossValidate()
cv.config["setup"] = Clusterer(classname="weka.clusterers.EM")
flow.actors.append(cv)
console = Console()
console.config["prefix"] = "Loglikelihood: "
flow.actors.append(console)
# run the flow
msg = flow.setup()
if msg is None:
print("\n" + flow.tree + "\n")
msg = flow.execute()
if msg is not None:
print("Error executing flow:\n" + msg)
else:
print("Error setting up flow:\n" + msg)
flow.wrapup()
flow.cleanup()
def main(args):
"""
Performs attribute selection on the specified dataset (uses vote UCI dataset if no dataset specified). Last
attribute is assumed to be the class attribute. Used: CfsSubsetEval, GreedyStepwise, J48
:param args: the commandline arguments
:type args: list
"""
# load a dataset
if len(args) <= 1:
data_file = helper.get_data_dir() + os.sep + "vote.arff"
else:
data_file = args[1]
helper.print_info("Loading dataset: " + data_file)
loader = Loader(classname="weka.core.converters.ArffLoader")
data = loader.load_file(data_file)
data.class_is_last()
use_classifier(data)
use_filter(data)
use_low_level(data)
def main(args):
"""
Performs attribute selection on the specified dataset (uses vote UCI dataset if no dataset specified). Last
attribute is assumed to be the class attribute. Used: CfsSubsetEval, GreedyStepwise, J48
:param args: the commandline arguments
:type args: list
"""
# load a dataset
if len(args) <= 1:
data_file = helper.get_data_dir() + os.sep + "vote.arff"
else:
data_file = args[1]
helper.print_info("Loading dataset: " + data_file)
loader = Loader(classname="weka.core.converters.ArffLoader")
data = loader.load_file(data_file)
data.class_is_last()
use_classifier(data)
use_filter(data)
use_low_level(data)
def main(args):
"""
Trains Apriori on the specified dataset (uses vote UCI dataset if no dataset specified).
:param args: the commandline arguments
:type args: list
"""
# load a dataset
if len(args) <= 1:
data_file = helper.get_data_dir() + os.sep + "vote.arff"
else:
data_file = args[1]
helper.print_info("Loading dataset: " + data_file)
loader = Loader("weka.core.converters.ArffLoader")
data = loader.load_file(data_file)
data.class_is_last()
# build Apriori, using last attribute as class attribute
apriori = Associator(classname="weka.associations.Apriori",
options=["-c", "-1"])
apriori.build_associations(data)
print(str(apriori))
def main():
"""
Just runs some example code.
"""
# load a dataset
anneal_file = helper.get_data_dir() + os.sep + "anneal.arff"
helper.print_info("Loading dataset: " + anneal_file)
loader = Loader("weka.core.converters.ArffLoader")
anneal_data = loader.load_file(anneal_file)
anneal_data.class_is_last()
# perform attribute selection
helper.print_title("Attribute selection")
search = ASSearch(classname="weka.attributeSelection.BestFirst", options=["-D", "1", "-N", "5"])
evaluation = ASEvaluation(classname="weka.attributeSelection.CfsSubsetEval", options=["-P", "1", "-E", "1"])
attsel = AttributeSelection()
attsel.search(search)
attsel.evaluator(evaluation)
attsel.select_attributes(anneal_data)
print("# attributes: " + str(attsel.number_attributes_selected))
print("attributes: " + str(attsel.selected_attributes))
print("result string:\n" + attsel.results_string)
# perform ranking
helper.print_title("Attribute ranking (2-fold CV)")
search = ASSearch(classname="weka.attributeSelection.Ranker", options=["-N", "-1"])
evaluation = ASEvaluation("weka.attributeSelection.InfoGainAttributeEval")
attsel = AttributeSelection()
attsel.ranking(True)
attsel.folds(2)
attsel.crossvalidation(True)
attsel.seed(42)
attsel.search(search)
attsel.evaluator(evaluation)
attsel.select_attributes(anneal_data)
print("ranked attributes:\n" + str(attsel.ranked_attributes))
print("result string:\n" + attsel.results_string)
def multisearch():
"""
Applies MultiSearch to a dataset. "multisearch-weka-package" package must be installed.
"""
helper.print_title("MultiSearch")
# load a dataset
fname = helper.get_data_dir() + os.sep + "bolts.arff"
helper.print_info("Loading train: " + fname)
loader = Loader(classname="weka.core.converters.ArffLoader")
train = loader.load_file(fname)
train.class_is_last()
# classifier
multi = MultiSearch(options=[
"-sample-size", "100.0", "-initial-folds", "2", "-subsequent-folds",
"2", "-num-slots", "1", "-S", "1"
])
multi.evaluation = "CC"
mparam = MathParameter()
mparam.prop = "classifier.kernel.gamma"
mparam.minimum = -3.0
mparam.maximum = 3.0
mparam.step = 1.0
mparam.base = 10.0
mparam.expression = "pow(BASE,I)"
lparam = ListParameter()
lparam.prop = "classifier.C"
lparam.values = ["-2.0", "-1.0", "0.0", "1.0", "2.0"]
multi.parameters = [mparam, lparam]
cls = Classifier(
classname="weka.classifiers.functions.SMOreg",
options=["-K", "weka.classifiers.functions.supportVector.RBFKernel"])
multi.classifier = cls
multi.build_classifier(train)
print("Model:\n" + str(multi))
print("\nBest setup:\n" + multi.best.to_commandline())
def multisearch():
"""
Applies MultiSearch to a dataset. "multisearch-weka-package" package must be installed.
"""
helper.print_title("MultiSearch")
# load a dataset
fname = helper.get_data_dir() + os.sep + "bolts.arff"
helper.print_info("Loading train: " + fname)
loader = Loader(classname="weka.core.converters.ArffLoader")
train = loader.load_file(fname)
train.class_is_last()
# classifier
multi = MultiSearch(
options=["-sample-size", "100.0", "-initial-folds", "2", "-subsequent-folds", "2",
"-num-slots", "1", "-S", "1"])
multi.evaluation = "CC"
mparam = MathParameter()
mparam.prop = "classifier.kernel.gamma"
mparam.minimum = -3.0
mparam.maximum = 3.0
mparam.step = 1.0
mparam.base = 10.0
mparam.expression = "pow(BASE,I)"
lparam = ListParameter()
lparam.prop = "classifier.C"
lparam.values = ["-2.0", "-1.0", "0.0", "1.0", "2.0"]
multi.parameters = [mparam, lparam]
cls = Classifier(
classname="weka.classifiers.functions.SMOreg",
options=["-K", "weka.classifiers.functions.supportVector.RBFKernel"])
multi.classifier = cls
multi.build_classifier(train)
print("Model:\n" + str(multi))
print("\nBest setup:\n" + multi.best.to_commandline())
def main():
"""
Just runs some example code.
"""
"""
Displays a dataset as matrixplot.
"""
# setup the flow
helper.print_title("Matrix plot")
iris = helper.get_data_dir() + os.sep + "iris.arff"
flow = Flow(name="matrix plot")
filesupplier = FileSupplier()
filesupplier.config["files"] = [iris]
flow.actors.append(filesupplier)
loaddataset = LoadDataset()
flow.actors.append(loaddataset)
plot = MatrixPlot()
plot.config["percent"] = 50.0
flow.actors.append(plot)
# run the flow
msg = flow.setup()
if msg is None:
print("\n" + flow.tree + "\n")
msg = flow.execute()
if msg is not None:
print("Error executing flow:\n" + msg)
else:
print("Error setting up flow:\n" + msg)
flow.wrapup()
flow.cleanup()
def main():
"""
Just runs some example code.
"""
"""
Displays a dataset as matrixplot.
"""
# setup the flow
helper.print_title("Matrix plot")
iris = helper.get_data_dir() + os.sep + "iris.arff"
flow = Flow(name="matrix plot")
filesupplier = FileSupplier()
filesupplier.config["files"] = [iris]
flow.actors.append(filesupplier)
loaddataset = LoadDataset()
flow.actors.append(loaddataset)
plot = MatrixPlot()
plot.config["percent"] = 50.0
flow.actors.append(plot)
# run the flow
msg = flow.setup()
if msg is None:
print("\n" + flow.tree + "\n")
msg = flow.execute()
if msg is not None:
print("Error executing flow:\n" + msg)
else:
print("Error setting up flow:\n" + msg)
flow.wrapup()
flow.cleanup()
def main():
"""
Just runs some example code.
"""
print(helper.get_data_dir())
# cross-validation + classification
helper.print_title("Experiment: Cross-validation + classification")
datasets = [
helper.get_data_dir() + os.sep + "iris.arff",
helper.get_data_dir() + os.sep + "anneal.arff"
]
classifiers = [
Classifier("weka.classifiers.rules.ZeroR"),
Classifier("weka.classifiers.trees.J48")
]
outfile = tempfile.gettempdir() + os.sep + "results-cv.arff"
exp = SimpleCrossValidationExperiment(classification=True,
runs=10,
folds=10,
datasets=datasets,
classifiers=classifiers,
result=outfile)
exp.setup()
exp.run()
# evaluate
loader = converters.loader_for_file(outfile)
data = loader.load_file(outfile)
matrix = ResultMatrix("weka.experiment.ResultMatrixPlainText")
tester = Tester("weka.experiment.PairedCorrectedTTester")
tester.resultmatrix = matrix
comparison_col = data.attribute_by_name("Percent_correct").index
tester.instances = data
print(tester.header(comparison_col))
print(tester.multi_resultset_full(0, comparison_col))
# random split + regression
helper.print_title("Experiment: Random split + regression")
datasets = [
helper.get_data_dir() + os.sep + "bolts.arff",
helper.get_data_dir() + os.sep + "bodyfat.arff"
]
classifiers = [
Classifier("weka.classifiers.rules.ZeroR"),
Classifier("weka.classifiers.functions.LinearRegression")
]
outfile = tempfile.gettempdir() + os.sep + "results-rs.arff"
exp = SimpleRandomSplitExperiment(classification=False,
runs=10,
percentage=66.6,
preserve_order=False,
datasets=datasets,
classifiers=classifiers,
result=outfile)
exp.setup()
exp.run()
# evaluate
loader = converters.loader_for_file(outfile)
data = loader.load_file(outfile)
matrix = ResultMatrix("weka.experiment.ResultMatrixPlainText")
tester = Tester("weka.experiment.PairedCorrectedTTester")
tester.resultmatrix = matrix
comparison_col = data.attribute_by_name("Correlation_coefficient").index
tester.instances = data
print(tester.header(comparison_col))
print(tester.multi_resultset_full(0, comparison_col))
# plot
plot_exp.plot_experiment(matrix,
title="Random split",
measure="Correlation coefficient",
wait=True)
def main():
"""
Just runs some example code.
"""
# setup the flow
helper.print_title("cluster data")
iris = helper.get_data_dir() + os.sep + "iris_no_class.arff"
clsfile = str(tempfile.gettempdir()) + os.sep + "simplekmeans.model"
flow = Flow(name="cluster data")
start = Start()
flow.actors.append(start)
build_save = Trigger()
build_save.name = "build and save clusterer"
flow.actors.append(build_save)
filesupplier = FileSupplier()
filesupplier.config["files"] = [iris]
build_save.actors.append(filesupplier)
loaddataset = LoadDataset()
build_save.actors.append(loaddataset)
ssv = SetStorageValue()
ssv.config["storage_name"] = "data"
build_save.actors.append(ssv)
train = Train()
train.config["setup"] = Clusterer(classname="weka.clusterers.SimpleKMeans")
build_save.actors.append(train)
ssv = SetStorageValue()
ssv.config["storage_name"] = "model"
build_save.actors.append(ssv)
pick = ContainerValuePicker()
pick.config["value"] = "Model"
build_save.actors.append(pick)
console = Console()
console.config["prefix"] = "built: "
pick.actors.append(console)
writer = ModelWriter()
writer.config["output"] = clsfile
build_save.actors.append(writer)
pred_serialized = Trigger()
pred_serialized.name = "make predictions (serialized model)"
flow.actors.append(pred_serialized)
filesupplier = FileSupplier()
filesupplier.config["files"] = [iris]
pred_serialized.actors.append(filesupplier)
loaddataset = LoadDataset()
loaddataset.config["incremental"] = True
pred_serialized.actors.append(loaddataset)
predict = Predict()
predict.config["model"] = clsfile
pred_serialized.actors.append(predict)
console = Console()
console.config["prefix"] = "serialized: "
pred_serialized.actors.append(console)
pred_storage = Trigger()
pred_storage.name = "make predictions (model from storage)"
flow.actors.append(pred_storage)
filesupplier = FileSupplier()
filesupplier.config["files"] = [iris]
pred_storage.actors.append(filesupplier)
loaddataset = LoadDataset()
loaddataset.config["incremental"] = True
pred_storage.actors.append(loaddataset)
predict = Predict()
predict.config["storage_name"] = "model"
pred_storage.actors.append(predict)
console = Console()
console.config["prefix"] = "storage: "
pred_storage.actors.append(console)
# run the flow
msg = flow.setup()
if msg is None:
print("\n" + flow.tree + "\n")
msg = flow.execute()
if msg is not None:
print("Error executing flow:\n" + msg)
else:
print("Error setting up flow:\n" + msg)
flow.wrapup()
flow.cleanup()
def main():
"""
Just runs some example code.
"""
# setup the flow
helper.print_title("build and evaluate classifier")
iris = helper.get_data_dir() + os.sep + "iris.arff"
flow = Flow(name="build and evaluate classifier")
start = Start()
flow.actors.append(start)
build_save = Trigger()
build_save.name = "build and store classifier"
flow.actors.append(build_save)
filesupplier = FileSupplier()
filesupplier.config["files"] = [iris]
build_save.actors.append(filesupplier)
loaddataset = LoadDataset()
build_save.actors.append(loaddataset)
select = ClassSelector()
select.config["index"] = "last"
build_save.actors.append(select)
ssv = SetStorageValue()
ssv.config["storage_name"] = "data"
build_save.actors.append(ssv)
train = Train()
train.config["setup"] = Classifier(classname="weka.classifiers.trees.J48")
build_save.actors.append(train)
pick = ContainerValuePicker()
pick.config["value"] = "Model"
build_save.actors.append(pick)
ssv = SetStorageValue()
ssv.config["storage_name"] = "model"
pick.actors.append(ssv)
evaluate = Trigger()
evaluate.name = "evaluate classifier"
flow.actors.append(evaluate)
gsv = GetStorageValue()
gsv.config["storage_name"] = "data"
evaluate.actors.append(gsv)
evl = Evaluate()
evl.config["storage_name"] = "model"
evaluate.actors.append(evl)
summary = EvaluationSummary()
summary.config["matrix"] = True
evaluate.actors.append(summary)
console = Console()
evaluate.actors.append(console)
# run the flow
msg = flow.setup()
if msg is None:
print("\n" + flow.tree + "\n")
msg = flow.execute()
if msg is not None:
print("Error executing flow:\n" + msg)
else:
print("Error setting up flow:\n" + msg)
flow.wrapup()
flow.cleanup()
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()
helper.print_title("Iris dataset")
print(iris_data)
helper.print_title("Iris dataset (incrementally output)")
for i in iris_data:
print(i)
helper.print_title("Iris summary")
print(Instances.summary(iris_data))
helper.print_title("Iris attributes")
for a in iris_data.attributes():
print(a)
helper.print_title("Instance at #0")
print(iris_data.get_instance(0))
print(iris_data.get_instance(0).values)
print("Attribute stats (first):\n" + str(iris_data.attribute_stats(0)))
print("total count (first attribute):\n" + str(iris_data.attribute_stats(0).total_count))
print("numeric stats (first attribute):\n" + str(iris_data.attribute_stats(0).numeric_stats))
print("nominal counts (last attribute):\n"
+ str(iris_data.attribute_stats(iris_data.num_attributes - 1).nominal_counts))
helper.print_title("Instance values at #0")
for v in iris_data.get_instance(0):
print(v)
# append datasets
helper.print_title("append datasets")
data1 = Instances.copy_instances(iris_data, 0, 2)
data2 = Instances.copy_instances(iris_data, 2, 2)
print("Dataset #1:\n" + str(data1))
print("Dataset #2:\n" + str(data2))
msg = data1.equal_headers(data2)
print("#1 == #2 ? " + "yes" if msg is None else msg)
combined = Instances.append_instances(data1, data2)
print("Combined:\n" + str(combined))
# merge datasets
helper.print_title("merge datasets")
data1 = Instances.copy_instances(iris_data, 0, 2)
data1.class_index = -1
data1.delete_attribute(1)
data1.delete_first_attribute()
data2 = Instances.copy_instances(iris_data, 0, 2)
data2.class_index = -1
data2.delete_attribute(4)
data2.delete_attribute(3)
data2.delete_attribute(2)
print("Dataset #1:\n" + str(data1))
print("Dataset #2:\n" + str(data2))
msg = data1.equal_headers(data2)
print("#1 == #2 ? " + ("yes" if msg is None else msg))
combined = Instances.merge_instances(data2, data1)
print("Combined:\n" + str(combined))
# load dataset incrementally
iris_file = helper.get_data_dir() + os.sep + "iris.arff"
helper.print_info("Loading dataset incrementally: " + iris_file)
loader = Loader("weka.core.converters.ArffLoader")
iris_data = loader.load_file(iris_file, incremental=True)
iris_data.class_is_last()
helper.print_title("Iris dataset")
print(iris_data)
for inst in loader:
print(inst)
# create attributes
helper.print_title("Creating attributes")
num_att = Attribute.create_numeric("num")
print("numeric: " + str(num_att))
date_att = Attribute.create_date("dat", "yyyy-MM-dd")
print("date: " + str(date_att))
nom_att = Attribute.create_nominal("nom", ["label1", "label2"])
print("nominal: " + str(nom_att))
# create dataset
helper.print_title("Create dataset")
dataset = Instances.create_instances("helloworld", [num_att, date_att, nom_att], 0)
print(str(dataset))
# create an instance
helper.print_title("Create and add instance")
values = [3.1415926, date_att.parse_date("2014-04-10"), 1.0]
inst = Instance.create_instance(values)
print("Instance #1:\n" + str(inst))
dataset.add_instance(inst)
values = [2.71828, date_att.parse_date("2014-08-09"), Instance.missing_value()]
inst = Instance.create_instance(values)
dataset.add_instance(inst)
print("Instance #2:\n" + str(inst))
inst.set_value(0, 4.0)
print("Instance #2 (updated):\n" + str(inst))
print("Dataset:\n" + str(dataset))
dataset.delete_with_missing(2)
print("Dataset (after delete of missing):\n" + str(dataset))
values = [(1, date_att.parse_date("2014-07-11"))]
inst = Instance.create_sparse_instance(values, 3, classname="weka.core.SparseInstance")
print("sparse Instance:\n" + str(inst))
dataset.add_instance(inst)
print("dataset with mixed dense/sparse instance objects:\n" + str(dataset))
# create dataset (lists)
helper.print_title("Create dataset from lists")
x = [[randint(1, 10) for _ in range(5)] for _ in range(10)]
y = [randint(0, 1) for _ in range(10)]
dataset2 = ds.create_instances_from_lists(x, y, "generated from lists")
print(dataset2)
x = [[randint(1, 10) for _ in range(5)] for _ in range(10)]
dataset2 = ds.create_instances_from_lists(x, name="generated from lists (no y)")
print(dataset2)
# create dataset (matrices)
helper.print_title("Create dataset from matrices")
x = np.random.randn(10, 5)
y = np.random.randn(10)
dataset3 = ds.create_instances_from_matrices(x, y, "generated from matrices")
print(dataset3)
x = np.random.randn(10, 5)
dataset3 = ds.create_instances_from_matrices(x, name="generated from matrices (no y)")
print(dataset3)
# create more sparse instances
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()
helper.print_title("Create sparse instances using template dataset")
sparse_data = Instances.template_instances(diabetes_data)
for i in range(diabetes_data.num_attributes - 1):
inst = Instance.create_sparse_instance(
[(i, float(i+1) / 10.0)], sparse_data.num_attributes, classname="weka.core.SparseInstance")
sparse_data.add_instance(inst)
print("sparse dataset:\n" + str(sparse_data))
# simple scatterplot of iris dataset: petalwidth x petallength
iris_data = loader.load_file(iris_file)
iris_data.class_is_last()
pld.scatter_plot(
iris_data, iris_data.attribute_by_name("petalwidth").index,
iris_data.attribute_by_name("petallength").index,
percent=50,
wait=False)
# line plot of iris dataset (without class attribute)
iris_data = loader.load_file(iris_file)
iris_data.class_is_last()
pld.line_plot(iris_data, atts=range(iris_data.num_attributes - 1), percent=50, title="Line plot iris", wait=False)
# matrix plot of iris dataset
iris_data = loader.load_file(iris_file)
iris_data.class_is_last()
pld.matrix_plot(iris_data, percent=50, title="Matrix plot iris", wait=True)
def main():
"""
Just runs some example code.
"""
# load a dataset
iris = helper.get_data_dir() + os.sep + "iris.arff"
helper.print_info("Loading dataset: " + iris)
loader = Loader("weka.core.converters.ArffLoader")
data = loader.load_file(iris)
# remove class attribute
helper.print_info("Removing class attribute")
remove = Filter(classname="weka.filters.unsupervised.attribute.Remove", options=["-R", "last"])
remove.inputformat(data)
filtered = remove.filter(data)
# use MultiFilter
helper.print_info("Use MultiFilter")
remove = Filter(classname="weka.filters.unsupervised.attribute.Remove", options=["-R", "first"])
std = Filter(classname="weka.filters.unsupervised.attribute.Standardize")
multi = MultiFilter()
multi.filters = [remove, std]
multi.inputformat(data)
filtered_multi = multi.filter(data)
# output datasets
helper.print_title("Input")
print(data)
helper.print_title("Output")
print(filtered)
helper.print_title("Output (MultiFilter)")
print(filtered_multi)
# load text dataset
text = helper.get_data_dir() + os.sep + "reutersTop10Randomized_1perc_shortened.arff"
helper.print_info("Loading dataset: " + text)
loader = Loader("weka.core.converters.ArffLoader")
data = loader.load_file(text)
data.class_is_last()
# apply StringToWordVector
stemmer = Stemmer(classname="weka.core.stemmers.IteratedLovinsStemmer")
stopwords = Stopwords(classname="weka.core.stopwords.Rainbow")
tokenizer = Tokenizer(classname="weka.core.tokenizers.WordTokenizer")
s2wv = StringToWordVector(options=["-W", "10", "-L", "-C"])
s2wv.stemmer = stemmer
s2wv.stopwords = stopwords
s2wv.tokenizer = tokenizer
s2wv.inputformat(data)
filtered = s2wv.filter(data)
helper.print_title("Input (StringToWordVector)")
print(data)
helper.print_title("Output (StringToWordVector)")
print(filtered)
# partial classname
helper.print_title("Creating filter from partial classname")
clsname = ".Standardize"
f = Filter(classname=clsname)
print(clsname + " --> " + f.classname)
# source code
helper.print_info("Generate source code")
bolts = helper.get_data_dir() + os.sep + "labor.arff"
helper.print_info("Loading dataset: " + bolts)
loader = Loader("weka.core.converters.ArffLoader")
data = loader.load_file(bolts)
replace = Filter(classname="weka.filters.unsupervised.attribute.ReplaceMissingValues")
replace.inputformat(data)
replace.filter(data)
print(replace.to_source("MyReplaceMissingValues", data))
def main():
"""
Just runs some example code.
"""
# setup the flow
helper.print_title("build and evaluate classifier")
iris = helper.get_data_dir() + os.sep + "iris.arff"
flow = Flow(name="build and evaluate classifier")
start = Start()
flow.actors.append(start)
build_save = Trigger()
build_save.name = "build and store classifier"
flow.actors.append(build_save)
filesupplier = FileSupplier()
filesupplier.config["files"] = [iris]
build_save.actors.append(filesupplier)
loaddataset = LoadDataset()
build_save.actors.append(loaddataset)
select = ClassSelector()
select.config["index"] = "last"
build_save.actors.append(select)
ssv = SetStorageValue()
ssv.config["storage_name"] = "data"
build_save.actors.append(ssv)
train = Train()
train.config["setup"] = Classifier(classname="weka.classifiers.trees.J48")
build_save.actors.append(train)
pick = ContainerValuePicker()
pick.config["value"] = "Model"
build_save.actors.append(pick)
ssv = SetStorageValue()
ssv.config["storage_name"] = "model"
pick.actors.append(ssv)
evaluate = Trigger()
evaluate.name = "evaluate classifier"
flow.actors.append(evaluate)
gsv = GetStorageValue()
gsv.config["storage_name"] = "data"
evaluate.actors.append(gsv)
evl = Evaluate()
evl.config["storage_name"] = "model"
evaluate.actors.append(evl)
summary = EvaluationSummary()
summary.config["matrix"] = True
evaluate.actors.append(summary)
console = Console()
evaluate.actors.append(console)
# run the flow
msg = flow.setup()
if msg is None:
print("\n" + flow.tree + "\n")
msg = flow.execute()
if msg is not None:
print("Error executing flow:\n" + msg)
else:
print("Error setting up flow:\n" + msg)
flow.wrapup()
flow.cleanup()
def main():
"""
Just runs some example code.
"""
# setup the flow
helper.print_title("Attribute selection")
iris = helper.get_data_dir() + os.sep + "iris.arff"
flow = Flow(name="attribute selection")
filesupplier = FileSupplier()
filesupplier.config["files"] = [iris]
flow.actors.append(filesupplier)
loaddataset = LoadDataset()
loaddataset.config["incremental"] = False
flow.actors.append(loaddataset)
attsel = AttributeSelection()
attsel.config["search"] = ASSearch(classname="weka.attributeSelection.BestFirst")
attsel.config["eval"] = ASEvaluation(classname="weka.attributeSelection.CfsSubsetEval")
flow.actors.append(attsel)
results = Tee()
results.name = "output results"
flow.actors.append(results)
picker = ContainerValuePicker()
picker.config["value"] = "Results"
picker.config["switch"] = True
results.actors.append(picker)
console = Console()
console.config["prefix"] = "Attribute selection results:"
results.actors.append(console)
reduced = Tee()
reduced.name = "reduced dataset"
flow.actors.append(reduced)
picker = ContainerValuePicker()
picker.config["value"] = "Reduced"
picker.config["switch"] = True
reduced.actors.append(picker)
console = Console()
console.config["prefix"] = "Reduced dataset:\n\n"
reduced.actors.append(console)
# run the flow
msg = flow.setup()
if msg is None:
print("\n" + flow.tree + "\n")
msg = flow.execute()
if msg is not None:
print("Error executing flow:\n" + msg)
else:
print("Error setting up flow:\n" + msg)
flow.wrapup()
flow.cleanup()
