Python converters.Loader类代码示例

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.
    """

    # 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)

class Classifier():

    def __init__(self):
        jvm.start(class_path=['/vol/customopt/machine-learning/src/weka/weka-3-6-8/weka.jar'])
        self.loader = Loader(classname="weka.core.converters.ArffLoader")
        
    def train(self,classifier,trainfile):
        if classifier == "ripper":
            self.cls = classifiers.Classifier(classname="weka.classifiers.rules.JRip",options=["-P", "false","-E","false","O","5"])
        data = self.loader.load_file(trainfile)
        data.set_class_index(data.num_attributes() - 1)
        self.cls.build_classifier(data)
        return(self.cls.__str__())

    def test(self,testfile):
        predictions = []
        testdata = self.loader.load_file(testfile, incremental=True)
        testdata.set_class_index(testdata.num_attributes() - 1)
        while True:
            inst = self.loader.next_instance(testdata)
            if inst is None:
                break
            predictions.append([self.cls.classify_instance(inst)," ".join([str(round(x,2)) for x in self.cls.distribution_for_instance(inst)])])
        return predictions

    def stop(self):
        jvm.stop()

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 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 initData(self, arrfFile):
     loader = Loader(classname="weka.core.converters.ArffLoader")
     print self.dataDir + '/' + arrfFile
     self.data = loader.load_file(self.dataDir + '/' + arrfFile)
     self.data.class_is_last()
     
     print 'Carregando arquivo ' + self.dataDir + '/' + arrfFile

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():
    """
    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():
    """
    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 a J48 classifier on a training set and outputs the predicted class and class distribution alongside the
    actual class from a test set. Class attribute is assumed to be the last attribute.
    :param args: the commandline arguments (train and test datasets)
    :type args: list
    """

    # load a dataset
    helper.print_info("Loading train: " + args[1])
    loader = Loader(classname="weka.core.converters.ArffLoader")
    train = loader.load_file(args[1])
    train.class_index = train.num_attributes - 1
    helper.print_info("Loading test: " + args[2])
    test = loader.load_file(args[2])
    test.class_is_last()

    # classifier
    cls = Classifier(classname="weka.classifiers.trees.J48")
    cls.build_classifier(train)

    # output predictions
    print("# - actual - predicted - error - distribution")
    for index, inst in enumerate(test):
        pred = cls.classify_instance(inst)
        dist = cls.distribution_for_instance(inst)
        print(
            "%d - %s - %s - %s  - %s" %
            (index+1,
             inst.get_string_value(inst.class_index),
             inst.class_attribute.value(int(pred)),
             "yes" if pred != inst.get_value(inst.class_index) else "no",
             str(dist.tolist())))

 def _load_data(self, dfile, index = None):
     loader = Loader(classname = 'weka.core.converters.CSVLoader')
     data = loader.load_file(dfile = dfile)
     if index == None:
         data.set_class_index(data.num_attributes() - 1)
     else:
         data.set_class_index(index)
     return 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))

    # 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 train(self):
     filename = "train.arff"
     self.write_arff(filename, "train", 0, self.input_x, self.input_y)
     loader = Loader(classname="weka.core.converters.ArffLoader")
     data = loader.load_file(filename)
     data.class_is_last()
     self.cls = Classifier(classname="weka.classifiers.meta.Bagging", options=["-S", "5"])
     self.cls.build_classifier(data)
     os.remove(filename)

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