Python jvm.start函数代码示例

def main():
    """
    Runs a datagenerator from the command-line. Calls JVM start/stop automatically.
    Use -h to see all options.
    """
    parser = argparse.ArgumentParser(
        description='Executes a data generator from the command-line. Calls JVM start/stop automatically.')
    parser.add_argument("-j", metavar="classpath", dest="classpath", help="additional classpath, jars/directories")
    parser.add_argument("-X", metavar="heap", dest="heap", help="max heap size for jvm, e.g., 512m")
    parser.add_argument("datagenerator", help="data generator classname, e.g., "
                                              + "weka.datagenerators.classifiers.classification.LED24")
    parser.add_argument("option", nargs=argparse.REMAINDER, help="additional data generator options")
    parsed = parser.parse_args()
    jars = []
    if parsed.classpath is not None:
        jars = parsed.classpath.split(os.pathsep)

    jvm.start(jars, max_heap_size=parsed.heap, packages=True)

    logger.debug("Commandline: " + join_options(sys.argv[1:]))

    try:
        generator = DataGenerator(classname=parsed.datagenerator)
        if len(parsed.option) > 0:
            generator.options = parsed.option
        DataGenerator.make_data(generator, parsed.option)
    except Exception, e:
        print(e)

def main():
    """
    Runs a associator from the command-line. Calls JVM start/stop automatically.
    Use -h to see all options.
    """

    parser = argparse.ArgumentParser(
        description='Executes an associator from the command-line. Calls JVM start/stop automatically.')
    parser.add_argument("-j", metavar="classpath", dest="classpath", help="additional classpath, jars/directories")
    parser.add_argument("-X", metavar="heap", dest="heap", help="max heap size for jvm, e.g., 512m")
    parser.add_argument("-t", metavar="train", dest="train", required=True, help="training set file")
    parser.add_argument("associator", help="associator classname, e.g., weka.associations.Apriori")
    parser.add_argument("option", nargs=argparse.REMAINDER, help="additional associator options")
    parsed = parser.parse_args()
    jars = []
    if parsed.classpath is not None:
        jars = parsed.classpath.split(os.pathsep)

    jvm.start(jars, max_heap_size=parsed.heap, packages=True)

    logger.debug("Commandline: " + join_options(sys.argv[1:]))

    try:
        associator = Associator(classname=parsed.associator)
        if len(parsed.option) > 0:
            associator.options = parsed.option
        loader = converters.loader_for_file(parsed.train)
        data = loader.load_file(parsed.train)
        associator.build_associations(data)
        print(str(associator))
    except Exception, e:
        print(e)

 def simpleKMeansTrain(self, dataf, options, mname, temp=True):
     '''
     :param data: -> data to be clustered
     :param options: -> SimpleKMeans options
                   N -> number of clusters
                   A -> Distance function to use (ex: default is "weka.core.EuclideanDistance -R first-last")
                   l -> maximum number of iterations default 500
           num-slots -> number of execution slots, 1 means no parallelism
                   S -> Random number seed (default 10)
           example => ["-N", "10", "-S", "10"]
     :return:
     '''
     try:
         jvm.start(max_heap_size=self.wHeap)
         data = self.loadData(dataf, temp=True)
         clusterer = Clusterer(classname="weka.clusterers.SimpleKMeans", options=options)
         clusterer.build_clusterer(data)
         print clusterer
         # cluster the data
         for inst in data:
             cl = clusterer.cluster_instance(inst)  # 0-based cluster index
             dist = clusterer.distribution_for_instance(inst)  # cluster membership distribution
             print("cluster=" + str(cl) + ", distribution=" + str(dist))
         self.saveModel(clusterer, 'skm', mname)
     except Exception, e:
         print(traceback.format_exc())

    def runclustermodel(self, model, method, dataf, temp=True):
        anomalies = []
        try:
            jvm.start(max_heap_size=self.wHeap)
            data = self.loadData(dataf, temp)
            cluster = self.loadClusterModel(model, method)
            clusterMembership = []
            print cluster.number_of_clusters
            for inst in data:
                try:
                    cl = cluster.cluster_instance(inst)
                except Exception as inst:
                    logger.error('[%s] : [ERROR] Mismatch model and data attributes',
                    datetime.fromtimestamp(time.time()).strftime('%Y-%m-%d %H:%M:%S'))

                dist = cluster.distribution_for_instance(inst)
                print ("cluster=" + str(cl) + ", distribution=" + str(dist))
                clusterMembership.append(cl)

            # print data.attribute_by_name('key')
            # print data.num_instances
            # print data.get_instance(3)

            pa = self.calcThreashold(dict(Counter(clusterMembership)), 21)
            if pa == 0:
                logger.warning('[%s] : [WARN] Most instances are computed as anomalies, possible error encountered!',
                    datetime.fromtimestamp(time.time()).strftime('%Y-%m-%d %H:%M:%S'),)
                print "Most instances are computed as anomalies, possible error encountered!"
            else:
                for a in pa:
                    # print data.get_instance(a).get_value(0)  #todo always set key as first atribute
                    anomalies.append(data.get_instance(a).get_value(0))
                print "Detected using %s anomalies at timestamp(s) %s" % (model, str(anomalies))
        except Exception, e:
            print(traceback.format_exc())

def read_file(file_name):
	tile_set_list = []
	characteristic = []
	jvm.start()
	nmrClass = Classifier(jobject=serialization.read("models/lmt_3sd.model"))
	with open(file_name) as f: # opens file

		# reads in characteristic protein sequence and coverts it to expected chemical shift values
		tile_characteristic = f.readline()
		characteristic = re.findall(r'\b[A-Za-z]{3,4}\b', tile_characteristic)
		characteristic = letters_to_numbers(characteristic)

		for line in f: # reads in NMR Data
			#reads each line and grabs numbers and na data
			#file format "a b c d"
			a, b, c, d = re.findall(r'\b\d+\.\d*\b|\bna\b', line)
			# Dealing with missing data
			if (a == "na"):
				a = -1
			if (b == "na"):
				b = -1
			if (c == "na"):
				c = -1
			if (d == "na"):
				d = -1
			# adds a new Tile to tile_set_list
			if (not (a==-1 and b==-1 and c==-1 and d==-1)):
				tile_set_list.append(Tile(a, b, c, d, nmrClass)) 
	return tile_set_list, characteristic, nmrClass

def main():
    """
    Runs a clusterer from the command-line. Calls JVM start/stop automatically.
    Use -h to see all options.
    """
    parser = argparse.ArgumentParser(
        description='Performs clustering from the command-line. Calls JVM start/stop automatically.')
    parser.add_argument("-j", metavar="classpath", dest="classpath", help="additional classpath, jars/directories")
    parser.add_argument("-X", metavar="heap", dest="heap", help="max heap size for jvm, e.g., 512m")
    parser.add_argument("-t", metavar="train", dest="train", required=True, help="training set file")
    parser.add_argument("-T", metavar="test", dest="test", help="test set file")
    parser.add_argument("-d", metavar="outmodel", dest="outmodel", help="model output file name")
    parser.add_argument("-l", metavar="inmodel", dest="inmodel", help="model input file name")
    parser.add_argument("-p", metavar="attributes", dest="attributes", help="attribute range")
    parser.add_argument("-x", metavar="num folds", dest="numfolds", help="number of folds")
    parser.add_argument("-s", metavar="seed", dest="seed", help="seed value for randomization")
    parser.add_argument("-c", metavar="class index", dest="classindex", help="1-based class attribute index")
    parser.add_argument("-g", metavar="graph", dest="graph", help="graph output file (if supported)")
    parser.add_argument("clusterer", help="clusterer classname, e.g., weka.clusterers.SimpleKMeans")
    parser.add_argument("option", nargs=argparse.REMAINDER, help="additional clusterer options")
    parsed = parser.parse_args()
    jars = []
    if parsed.classpath is not None:
        jars = parsed.classpath.split(os.pathsep)
    params = []
    if parsed.train is not None:
        params.extend(["-t", parsed.train])
    if parsed.test is not None:
        params.extend(["-T", parsed.test])
    if parsed.outmodel is not None:
        params.extend(["-d", parsed.outmodel])
    if parsed.inmodel is not None:
        params.extend(["-l", parsed.inmodel])
    if parsed.attributes is not None:
        params.extend(["-p", parsed.attributes])
    if parsed.numfolds is not None:
        params.extend(["-x", parsed.numfolds])
    if parsed.seed is not None:
        params.extend(["-s", parsed.seed])
    if parsed.classindex is not None:
        params.extend(["-c", parsed.classindex])
    if parsed.graph is not None:
        params.extend(["-g", parsed.graph])

    jvm.start(jars, max_heap_size=parsed.heap, packages=True)

    logger.debug("Commandline: " + join_options(sys.argv[1:]))

    try:
        clusterer = Clusterer(classname=parsed.clusterer)
        if len(parsed.option) > 0:
            clusterer.options = parsed.option
        print(ClusterEvaluation.evaluate_clusterer(clusterer, params))
    except Exception as e:
        print(e)
    finally:
        jvm.stop()

def generate_folds(dataset_path, output_folder, n_folds=10, random_state=None):
    """
    Given a dataset df, generate n_folds for it and store them in <output_folder>/<dataset_name>.

    :type dataset_path: str
    :param dataset_path: Path to dataset with .arff file extension (i.e my_dataset.arff)
    :type output_folder: str
    :param output_folder: Path to store both index file with folds and fold files.
    :type n_folds: int
    :param n_folds: Optional - Number of folds to split the dataset into. Defaults to 10.
    :type random_state: int
    :param random_state: Optional - Seed to use in the splitting process. Defaults to None (no seed).
    """

    import warnings
    warnings.filterwarnings('error')

    dataset_name = dataset_path.split('/')[-1].split('.')[0]

    af = load_arff(dataset_path)
    df = load_dataframe(af)

    skf = StratifiedKFold(n_splits=n_folds, shuffle=True, random_state=random_state)
    fold_iter = skf.split(df[df.columns[:-1]], df[df.columns[-1]])

    fold_index = dict()

    jvm.start()

    csv_loader = Loader(classname="weka.core.converters.CSVLoader")
    arff_saver = Saver(classname='weka.core.converters.ArffSaver')

    for i, (arg_rest, arg_test) in enumerate(fold_iter):
        fold_index[i] = list(arg_test)

        _temp_path = 'temp_%s_%d.csv' % (dataset_name, i)

        fold_data = df.loc[arg_test]  # type: pd.DataFrame
        fold_data.to_csv(_temp_path, sep=',', index=False)

        java_arff_dataset = csv_loader.load_file(_temp_path)
        java_arff_dataset.relationname = af['relation']
        java_arff_dataset.class_is_last()
        arff_saver.save_file(java_arff_dataset, os.path.join(output_folder, '%s_fold_%d.arff' % (dataset_name, i)))

        os.remove(_temp_path)

    json.dump(
        fold_index, open(os.path.join(output_folder, dataset_name + '.json'), 'w'), indent=2
    )

    jvm.stop()
    warnings.filterwarnings('default')

def run(arff_path, model_out):
    jvm.start()
    loader = Loader(classname = "weka.core.converters.ArffLoader")
    data = loader.load_file(arff_path)
    data.class_is_last()
    cls = Logistic()
    cls.build_classifier(data)
    cls.save_model(model_out)
    coefficients = cls.coefficients
    for coeff in coefficients:
        print str(coeff)

    return coefficients

def start(*args, **kwargs):
    """
    Open a weka connection.

    May be called multiple times, but not after calling stop().

    Arguments:

        *args, **kwargs: Any additional arguments to pass to
          jvm.start().
    """
    if MODULE_SUPPORTED:
        jvm.start(*args, **kwargs)

def assign_classify(file_location, output="classified.out", model="naivebayes.model"):
    data = read_csv_file(file_location)
    jvm.start()
    # load clusters
    obj = serialization.read(model)
    classifier = Classifier(jobject=obj)
    # create file with cluster group
    with open(output, 'w') as cluster_file:
        for index, attrs in enumerate(data):
            inst = Instance.create_instance(attrs[1:])
            pred = classifier.classify_instance(inst)
            print(str(index + 1) + ": label index=" + str(pred))
    jvm.stop()

def predict(attributes):
    jvm.start()
    file_path = print_to_file(attributes)
    # load the saved model
    objects = serialization.read_all("/Users/hosyvietanh/Desktop/data_mining/trained_model.model")
    classifier = Classifier(jobject=objects[0])
    loader = Loader(classname="weka.core.converters.ArffLoader")
    data = loader.load_file(file_path)
    data.class_is_last()
    for index, inst in enumerate(data):
        pred = classifier.classify_instance(inst)
        dist = classifier.distribution_for_instance(inst)
        return int(pred)
    jvm.stop()

def query_instance(attributes, model="out.model"):
    """
        get the cluster for defined attributes
        :params attributes: array or list
        :returns: cluster id
    """
    jvm.start()
    # create instance
    inst = Instance(attributes)
    # load model
    obj = serialization.read(model)
    # load cluster and get the cluster_id
    cluster = Clusterer(jobject=obj)
    cluster_id = cluster.cluster_instance(inst)
    jvm.stop()
    return cluster_id

def main():
    """
    Runs attribute selection from the command-line. Calls JVM start/stop automatically.
    Use -h to see all options.
    """
    parser = argparse.ArgumentParser(
        description='Performs attribute selection from the command-line. Calls JVM start/stop automatically.')
    parser.add_argument("-j", metavar="classpath", dest="classpath", help="additional classpath, jars/directories")
    parser.add_argument("-X", metavar="heap", dest="heap", help="max heap size for jvm, e.g., 512m")
    parser.add_argument("-i", metavar="input", dest="input", required=True, help="input file")
    parser.add_argument("-c", metavar="class index", dest="classindex", help="1-based class attribute index")
    parser.add_argument("-s", metavar="search", dest="search", help="search method, classname and options")
    parser.add_argument("-x", metavar="num folds", dest="numfolds", help="number of folds")
    parser.add_argument("-n", metavar="seed", dest="seed", help="the seed value for randomization")
    parser.add_argument("evaluator", help="evaluator classname, e.g., weka.attributeSelection.CfsSubsetEval")
    parser.add_argument("option", nargs=argparse.REMAINDER, help="additional evaluator options")
    parsed = parser.parse_args()
    jars = []
    if parsed.classpath is not None:
        jars = parsed.classpath.split(os.pathsep)
    params = []
    if parsed.input is not None:
        params.extend(["-i", parsed.input])
    if parsed.classindex is not None:
        params.extend(["-c", parsed.classindex])
    if parsed.search is not None:
        params.extend(["-s", parsed.search])
    if parsed.numfolds is not None:
        params.extend(["-x", parsed.numfolds])
    if parsed.seed is not None:
        params.extend(["-n", parsed.seed])

    jvm.start(jars, max_heap_size=parsed.heap, packages=True)

    logger.debug("Commandline: " + join_options(sys.argv[1:]))

    try:
        evaluation = ASEvaluation(classname=parsed.evaluator)
        if len(parsed.option) > 0:
            evaluation.options = parsed.option
        print(AttributeSelection.attribute_selection(evaluation, params))
    except Exception as e:
        print(e)
    finally:
        jvm.stop()

 def dict2arff(self, fileIn, fileOut):
     '''
     :param fileIn: name of csv file
     :param fileOut: name of new arff file
     :return:
     '''
     dataIn = os.path.join(self.dataDir, fileIn)
     dataOut = os.path.join(self.dataDir, fileOut)
     logger.info('[%s] : [INFO] Starting conversion of %s to %s', datetime.fromtimestamp(time.time()).strftime('%Y-%m-%d %H:%M:%S'), dataIn, dataOut)
     try:
         jvm.start()
         convertCsvtoArff(dataIn, dataOut)
     except Exception as inst:
         pass
     finally:
         logger.error('[%s] : [ERROR] Exception occured while converting to arff with %s and %s', datetime.fromtimestamp(time.time()).strftime('%Y-%m-%d %H:%M:%S'), type(inst), inst.args)
         jvm.stop()
     logger.info('[%s] : [INFO] Finished conversion of %s to %s', datetime.fromtimestamp(time.time()).strftime('%Y-%m-%d %H:%M:%S'), dataIn, dataOut)

def classify(train, test, name="RF", tuning=False):
    jvm.start()

    if isinstance(train, list) and isinstance(test, list):
        train = weka_instance(train)
        trn_data = converters.load_any_file(train)
        test = weka_instance(test)
        tst_data = converters.load_any_file(test)

    elif os.path.isfile(train) and os.path.isfile(test):
        trn_data = converters.load_any_file(train)
        tst_data = converters.load_any_file(test)

    else:
        trn = csv_as_ndarray(train)
        tst = csv_as_ndarray(test)

        trn_data = converters.ndarray_to_instances(trn, relation="Train")
        tst_data = converters.ndarray_to_instances(tst, relation="Test")

    trn_data.class_is_last()
    tst_data.class_is_last()

    # t = time()
    if tuning:
        opt = tune(train)
    else:
        opt = default_opt
    # print("Time to tune: {} seconds".format(time() - t))

    cls = Classifier(classname=classifiers[name.lower()], options=opt)

    cls.build_classifier(trn_data)

    distr = [cls.distribution_for_instance(inst)[1] for inst in tst_data]
    preds = [cls.classify_instance(inst) for inst in tst_data]

    jvm.stop()

    return preds, distr