def start_search(file_name, type):
	start = time.clock() # time Preprocessing
	tile_set, characteristic, nmrClass = read_file(file_name)
	calculate_char_heuristic(tile_set, characteristic) # do before you add the place holder tiles
	tile_set = generate_placeholders(tile_set, characteristic, nmrClass) # gets place holder tiles
	# kill jvm that was started after calling read file
	# the jvm is used for the machine learning filtering 
	# so that weka can be run
	jvm.stop() 
	calculate_order_heuristic(tile_set)

	# add up heuristic from all tiles and make starting node
	heuristic_val = 0
	for tile in tile_set:
		heuristic_val += tile.heuristic_cost
		# print tile.heuristic_order_cost,
		# print tile.get_tile()
	root = Node(tile_set, [], heuristic_val, characteristic,0,0, heuristic=heuristic_val) # makes start state for search

	end = time.clock() # time Preprocessing
	print "Preprocessing Time:  " + str(end-start)
	
	# picks algorithm
	if (int(type) == 0): # uniform cost search
		best_solution, node_count = aStar([root])
		output_soultion(best_solution, node_count)
	elif (int(type) == 1): # puzzle building
		best_solution = puzzle_building_search([root]) 

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 as e:
        print(e)
    finally:
        jvm.stop()

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 as e:
        print(e)
    finally:
        jvm.stop()

def stop():
    """
    Stop a weka connection.

    May be called multiple times, but note that a new connection
    cannot be started after calling this.
    """
    if MODULE_SUPPORTED:
        jvm.stop()

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 start_search(file_name, type):
	tile_set, characteristic, nmrClass = read_file(file_name) # gets data from file
	tile_set = generate_placeholders(tile_set, characteristic, nmrClass) # gets place holder tiles
	jvm.stop()
	root = Node(tile_set, [], 0.0, characteristic,0,0) # makes start state for search

	# picks algorithm
	if (int(type) == 0): # uniform cost search
		best_solution, node_count = uniform_cost([root])
		output_soultion(best_solution, node_count)
	elif (int(type) == 1): # puzzle building
		best_solution = puzzle_building_search([root])

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 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 playback_speed_checker(inputFile, dirRef):
    
    TRAINING_ARFF = 'dataset_playback.arff'
    inputRef = ""

    # Start JVM
    jvm.start()
    jvm.start(system_cp=True, packages=True)
    jvm.start(max_heap_size="512m")
    
    # Find reference file
    for file in os.listdir(dirRef):
        if str(file).find(str(os.path.basename(inputFile))) != -1:
            inputRef = os.path.join(dirRef, file)
            break

    # Calculation distance
    (result, distance) = dtw_checker(inputFile, inputRef)

    # Loading data
    loader = Loader(classname="weka.core.converters.ArffLoader")    
    data = loader.load_file(TRAINING_ARFF)
    data.class_is_last()                    # set class attribute

    # Train the classifier
    #cls = Classifier(classname="weka.classifiers.functions.SMO")
    cls = Classifier(classname="weka.classifiers.trees.J48", options = ["-C", "0.3", "-M", "10"])
    cls.build_classifier(data)

    # Classify instance
    speed_instance = Instance.create_instance(numpy.ndarray(distance), classname='weka.core.DenseInstance', weight=1.0)
    speed_instance.dataset = data
    
    # Classify instance
    speed_flag = cls.classify_instance(speed_instance)
    
    if (distance == 0):
        speed_class = 'nominal'
    else:
        if speed_flag == 0: speed_class = 'down_speed'
        if speed_flag == 0: speed_class = 'up_speed'
        
#    print os.path.basename(inputFile) + ' --- ' + speed_class
    
    # Stop JVM
    jvm.stop()    

    print "SPEED IS: " + speed_class

    return speed_class

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 riaa_checker(inputFile):
    
    TRAINING_ARFF = 'C:\Users\ASUS\Desktop\IGNASI\SMC\Workspace\dataset_riaa.arff'

    # Start JVM
    jvm.start()
    jvm.start(system_cp=True, packages=True)
    jvm.start(max_heap_size="512m")

    # Calculation of bark bands information
    (absolute_bark, relative_bark, bark_ratios) = compute_bark_spectrum(inputFile)

    # Loading data
    loader = Loader(classname="weka.core.converters.ArffLoader")    
    data = loader.load_file(TRAINING_ARFF)
    data.class_is_last()                    # set class attribute

    # Train the classifier
    cls = Classifier(classname="weka.classifiers.functions.SMO")
    #cls = Classifier(classname="weka.classifiers.trees.J48", options = ["-C", "0.3", "-M", "10"])
    cls.build_classifier(data)

    # Classify instance
    bark_instance = Instance.create_instance(bark_ratios, classname='weka.core.DenseInstance', weight=1.0)
    bark_instance.dataset = data
    
    # Classify instance
    riaa_flag = cls.classify_instance(bark_instance)
    
    if riaa_flag == 0:
        riaa_class = 'riaa_ok'
    else:
        riaa_class = 'riaa_ko'
        
#    print os.path.basename(inputFile) + ' --- ' + riaa_class
    
    # Stop JVM
    jvm.stop()   

    print "RIAA FILTERING?: " + riaa_class

    return riaa_class

def batch_riaa_checking(inputDir):

    # Start JVM
    jvm.start()
    jvm.start(system_cp=True, packages=True)
    jvm.start(max_heap_size="512m")

    riaa_ok = 0
    riaa_ko = 0

    for file in os.listdir(inputDir):
        if file.endswith(".wav"):
            riaa_flag = riaa_checker(os.path.join(inputDir, file))
            if (riaa_flag == 'riaa_ko'): riaa_ko+=1
            if (riaa_flag == 'riaa_ok'): riaa_ok+=1
    
    # Stop JVM
    jvm.stop()      
    
    return (riaa_ko, riaa_ok)

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

#.........这里部分代码省略.........

                meta = addict.Dict()
                meta.search    = comb.Search.NAME
                meta.evaluator = comb.Evaluator.NAME
                meta.features  = [tran.attribute(index).name for index in attr.selected_attributes]

                feat.append(meta)

                for i, stage in enumerate(self.stages):
                    if stage.code == 'ats':
                        search    = stage.value.search.name
                        evaluator = stage.value.evaluator.name

                        if search == comb.Search.NAME and evaluator == comb.Evaluator.NAME:
                            self.stages[i].status = Pipeline.COMPLETE

        models = [ ]
        for model in para.MODEL:
            if model.USE:
                summary         = addict.Dict()

                self.logs.append('Modelling {model}'.format(model = model.LABEL))

                summary.label   = model.LABEL
                summary.name    = model.NAME
                summary.options = assign_if_none(model.OPTIONS, [ ])

                for i, stage in enumerate(self.stages):
                    if stage.code == 'lrn' and stage.value.name == model.NAME:
                        self.stages[i].status = Pipeline.RUNNING

                for i, instance in enumerate(data):
                    iclass = list(range(instance.num_classes))
                
                options    = assign_if_none(model.OPTIONS, [ ])
                classifier = Classifier(classname = 'weka.classifiers.{classname}'.format(classname = model.NAME), options = options)
                classifier.build_classifier(tran)
        
                serializer.write(os.path.join(head, '{name}.{classname}.model'.format(
                        name = name,
                    classname = model.NAME
                )), classifier)

                self.logs.append('Testing model {model}'.format(model = model.LABEL))

                evaluation       = Evaluation(tran)
                evaluation.test_model(classifier, test)

                summary.summary  = evaluation.summary()

                frame  = pd.DataFrame(data = evaluation.confusion_matrix)
                axes   = sns.heatmap(frame, cbar = False, annot = True)
                b64str = get_b64_plot(axes)
                
                summary.confusion_matrix = addict.Dict({
                    'value': evaluation.confusion_matrix.tolist(),
                     'plot': b64str
                })

                self.logs.append('Plotting Learning Curve for {model}'.format(model = model.LABEL))

                buffer = io.BytesIO()
                plot_classifier_errors(evaluation.predictions, tran, test, outfile = buffer, wait = False)
                b64str = buffer_to_b64(buffer)

                summary.learning_curve   = b64str

                buffer = io.BytesIO()
                plot_roc(evaluation, class_index = iclass, outfile = buffer, wait = False)
                b64str = buffer_to_b64(buffer)

                summary.roc_curve        = b64str

                buffer = io.BytesIO()
                plot_prc(evaluation, class_index = iclass, outfile = buffer, wait = False)
                b64str = buffer_to_b64(buffer)

                summary.prc_curve        = b64str

                if classifier.graph:
                    summary.graph = classifier.graph

                for i, instance in enumerate(test):
                    prediction = classifier.classify_instance(instance)

                for i, stage in enumerate(self.stages):
                    if stage.code == 'lrn' and stage.value.name == model.NAME:
                        self.stages[i].status = Pipeline.COMPLETE

                models.append(summary)

        self.gist.models = models

        JVM.stop()

        JSON.write(os.path.join(head, '{name}.cgist'.format(name = name)), self.gist)

        self.logs.append('Pipeline Complete')

        self.set_status(Pipeline.COMPLETE)

 def stop(self):
     jvm.stop()

def run_classifier(path, prot, sel, cols, prot_vals, beta):
        
    DIs = dict()
    jvm.start()

    for i in range(len(cols)-1):
        loader = Loader(classname="weka.core.converters.CSVLoader")
        data = loader.load_file(path)
    
        # remove selected attribute from the data
        # NOTE: options are ONE indexed, not ZERO indexed
        remove = Filter(classname="weka.filters.unsupervised.attribute.Remove", \
                        options=["-R", str(sel[2]+1)])
        remove.inputformat(data)
        data = remove.filter(data)

        # if running for only one attribue, remove all others (except protected)
        if i > 0:
            for j in range(1, prot[2]+1):
                if i != j:
                    remove = Filter(classname="weka.filters.unsupervised.attribute.Remove", \
                                    options=["-R", ("1" if i>j else "2")])
                    remove.inputformat(data)
                    data = remove.filter(data)

        # set prot attribute as Class attribute
        data.class_is_last()
        
        # run classifier
        cls = Classifier(classname="weka.classifiers.bayes.NaiveBayes")
        cls.build_classifier(data)
    
        # count the number of each combination
        pos_and_pred = float(0.0)
        pos_and_not_pred = float(0.0)
        neg_and_pred = float(0.0)
        neg_and_not_pred = float(0.0)
        for ind, inst in enumerate(data):
            if cls.classify_instance(inst):
                if prot_vals[ind] == prot[1]:
                    pos_and_pred += 1
                else:
                    neg_and_pred += 1
            else:
                if prot_vals[ind] == prot[1]:
                    pos_and_not_pred += 1
                else:
                    neg_and_not_pred += 1

        # calculate DI
        BER = ((pos_and_not_pred / (pos_and_pred + pos_and_not_pred)) + \
               (neg_and_pred / (neg_and_pred + neg_and_not_pred))) * 0.5
        if BER > 0.5:
            BER = 1 - BER
        DI = 1 - ((1 - 2 * BER) / (beta + 1 - 2 * BER))

        if i == 0: # consider changing this to a 'code word' instead of 'all'
            DIs["all"] = DI
        else:
            DIs[cols[i-1]] = DI

    jvm.stop()

    return DIs

#.........这里部分代码省略.........
                        remove = Filter(classname = "weka.filters.unsupervised.attribute.Remove", options = ["-R", str(fitur_hapus)])
                        remove.inputformat(data)
                        data_baru = remove.filter(data)
                        data_baru.class_is_last()
                    else:
                        data_baru = loader.load_file("hasil.arff")
                        data_baru.class_is_last()

                    filter = Filter(classname = "weka.filters.unsupervised.instance.Randomize", options = ["-S", str(int(time.time()))])
                    filter.inputformat(data_baru)
                    data_random = filter.filter(data_baru)
                    data_random.class_is_last()

                    if(pruning == 0):
                        classifier = Classifier(classname = "weka.classifiers.trees.J48", options = ["-U"])
                    else:
                        classifier = Classifier(classname = "weka.classifiers.trees.J48", options = ["-C", "0.25"])

                    evaluation = Evaluation(data_random)
                    if(persen_train == 0):
                        evaluation.evaluate_train_test_split(classifier, data_random, percentage = 40)
                    elif(persen_train == 1):
                        evaluation.evaluate_train_test_split(classifier, data_random, percentage = 50)
                    elif(persen_train == 2):
                        evaluation.evaluate_train_test_split(classifier, data_random, percentage = 60)
                    else:
                        evaluation.evaluate_train_test_split(classifier, data_random, percentage = 70)

                    f.write(str(count + 1) + str( ". " ) + str(evaluation.weighted_true_positive_rate) + str( " " ) + str(evaluation.weighted_recall) + str( " " ) + str(evaluation.weighted_precision) + str( " " ) + str(evaluation.weighted_f_measure) + str( " " ) + str(evaluation.weighted_area_under_roc) + "\n")
                    print count + 1, evaluation.weighted_true_positive_rate, evaluation.weighted_recall, evaluation.weighted_precision, evaluation.weighted_f_measure, evaluation.weighted_area_under_roc

                    list_akurasi.append(evaluation.weighted_true_positive_rate)
                    list_recall.append(evaluation.weighted_recall)
                    list_presisi.append(evaluation.weighted_precision)
                    list_fmeasure.append(evaluation.weighted_f_measure)
                    list_roc.append(evaluation.weighted_area_under_roc)

                    count += 1
                    time.sleep(1)

                list_akurasi.sort()
                list_recall.sort()
                list_presisi.sort()
                list_fmeasure.sort()
                list_roc.sort()

                f.write( ""  + "\n")
                f.write( "Rata-Rata"  + "\n")
                f.write( "Akurasi:" + str(sum(list_akurasi) / 100.0)  + "\n")
                f.write( "Recall:" + str(sum(list_recall) / 100.0)  + "\n")
                f.write( "Presisi:" + str(sum(list_presisi) / 100.0)  + "\n")
                f.write( "F-Measure:" + str(sum(list_fmeasure) / 100.0)  + "\n")
                f.write( "ROC:" + str(sum(list_roc) / 100.0)  + "\n")
                f.write( ""  + "\n")
                f.write( "Max"  + "\n")
                f.write( "Akurasi:" + str(list_akurasi[-1] ) + "\n")
                f.write( "Recall:" + str(list_recall[-1] ) + "\n")
                f.write( "Presisi:" + str(list_presisi[-1] ) + "\n")
                f.write( "F-Measure:" + str(list_fmeasure[-1] ) + "\n")
                f.write( "ROC:" + str(list_roc[-1] ) + "\n")
                f.write( ""  + "\n")
                f.write( "Min"  + "\n")
                f.write( "Akurasi:" + str(list_akurasi[0] ) + "\n")
                f.write( "Recall:" + str(list_recall[0] ) + "\n")
                f.write( "Presisi:" + str(list_presisi[0] ) + "\n")
                f.write( "F-Measure:" + str(list_fmeasure[0] ) + "\n")
                f.write( "ROC:" + str(list_roc[0] ) + "\n")
                f.write( ""  + "\n")

                print ""
                print "Rata-Rata"
                print "Akurasi:", sum(list_akurasi) / 100.0
                print "Recall:", sum(list_recall) / 100.0
                print "Presisi:", sum(list_presisi) / 100.0
                print "F-Measure:", sum(list_fmeasure) / 100.0
                print "ROC:", sum(list_roc) / 100.0
                print ""
                print "Max"
                print "Akurasi:", list_akurasi[-1]
                print "Recall:", list_recall[-1]
                print "Presisi:", list_presisi[-1]
                print "F-Measure:", list_fmeasure[-1]
                print "ROC:", list_roc[-1]
                print ""
                print "Min"
                print "Akurasi:", list_akurasi[0]
                print "Recall:", list_recall[0]
                print "Presisi:", list_presisi[0]
                print "F-Measure:", list_fmeasure[0]
                print "ROC:", list_roc[0]
                print ""

                f.close()
                fitur_hapus -= 1

            persen_train += 1

        pruning += 1

    jvm.stop()