Python helper.print_title函数代码示例

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.
    """
    # setup the flow
    helper.print_title("Generate dataset")

    flow = Flow(name="generate dataset")

    generator = DataGenerator()
    generator.config["setup"] = datagen.DataGenerator(classname="weka.datagenerators.classifiers.classification.Agrawal")
    flow.actors.append(generator)

    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 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():
    """
    Just runs some example code.
    """
    """
    Loads data from a database.
    """

    # setup the flow
    helper.print_title("Load from database")

    flow = Flow(name="load from database")

    loaddatabase = LoadDatabase()
    loaddatabase.config["db_url"] = "jdbc:mysql://HOSTNAME:3306/DBNAME"
    loaddatabase.config["user"] = "DBUSER"
    loaddatabase.config["password"] = "DBPW"
    loaddatabase.config["query"] = "select * from TABLE"
    flow.actors.append(loaddatabase)

    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")
    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.
    """

    helper.print_title("Generate data (Agrawal)")
    generator = DataGenerator(
        classname="weka.datagenerators.classifiers.classification.Agrawal",
        options=["-n", "10", "-r", "agrawal"])
    generator.dataset_format = generator.define_data_format()
    print(generator.dataset_format)
    if generator.single_mode_flag:
        for i in xrange(generator.num_examples_act):
            print(generator.generate_example())
    else:
        print(generator.generate_examples())

    helper.print_title("Generate data (BayesNet)")
    generator = DataGenerator(
        classname="weka.datagenerators.classifiers.classification.BayesNet",
        options=["-S", "2", "-n", "10", "-C", "10"])
    generator.dataset_format = generator.define_data_format()
    print(generator.dataset_format)
    if generator.single_mode_flag:
        for i in xrange(generator.num_examples_act):
            print(generator.generate_example())
    else:
        print(generator.generate_examples())

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 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 main():
    """
    Just runs some example code.
    """

    # setup the flow
    helper.print_title("Output actor help")

    cv = CrossValidate()
    cv.config["setup"] = Classifier(classname="weka.classifiers.trees.J48")
    cv.print_help()

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.
    """
    """
    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.
    """

    # 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()