def filter_data(self, data):
print("Filtering Data..\n")
flter = Filter(
classname="weka.filters.supervised.attribute.AttributeSelection")
aseval = ASEvaluation(
classname="weka.attributeSelection.CfsSubsetEval",
options=["-P", "1", "-E", "1"])
assearch = ASSearch(classname="weka.attributeSelection.BestFirst",
options=["-D", "1", "-N", "5"])
flter.set_property("evaluator", aseval.jobject)
flter.set_property("search", assearch.jobject)
flter.inputformat(data)
filtered = flter.filter(data)
return filtered
def use_filter(data):
"""
Uses the AttributeSelection filter for attribute selection.
:param data: the dataset to use
:type data: Instances
"""
print("\n2. Filter")
flter = Filter(classname="weka.filters.supervised.attribute.AttributeSelection")
aseval = ASEvaluation(classname="weka.attributeSelection.CfsSubsetEval")
assearch = ASSearch(classname="weka.attributeSelection.GreedyStepwise", options=["-B"])
flter.set_property("evaluator", aseval.jobject)
flter.set_property("search", assearch.jobject)
flter.inputformat(data)
filtered = flter.filter(data)
print(str(filtered))
def use_filter(data):
"""
Uses the AttributeSelection filter for attribute selection.
:param data: the dataset to use
:type data: Instances
"""
print("\n2. Filter")
flter = Filter(classname="weka.filters.supervised.attribute.AttributeSelection")
aseval = ASEvaluation(classname="weka.attributeSelection.CfsSubsetEval")
assearch = ASSearch(classname="weka.attributeSelection.GreedyStepwise", options=["-B"])
flter.set_property("evaluator", aseval.jobject)
flter.set_property("search", assearch.jobject)
flter.inputformat(data)
filtered = flter.filter(data)
print(str(filtered))
def classification(data, train, test, num_clases):
baseClassifiers_list = [
"weka.classifiers.bayes.NaiveBayes",
"weka.classifiers.functions.MultilayerPerceptron",
"weka.classifiers.functions.SMO", "weka.classifiers.lazy.IBk",
"weka.classifiers.lazy.KStar", "weka.classifiers.meta.AdaBoostM1",
"weka.classifiers.meta.Bagging", "weka.classifiers.meta.LogitBoost",
"weka.classifiers.trees.J48", "weka.classifiers.trees.DecisionStump",
"weka.classifiers.trees.LMT", "weka.classifiers.trees.RandomForest",
"weka.classifiers.trees.REPTree", "weka.classifiers.rules.PART",
"weka.classifiers.rules.JRip", "weka.classifiers.functions.Logistic",
"weka.classifiers.meta.ClassificationViaRegression",
"weka.classifiers.bayes.BayesNet"
]
results_train = pd.DataFrame()
results_test = pd.DataFrame()
cost_matrix_list = [
"[]", "[0]", "[0.0 1.0; 1.0 0.0]",
"[0.0 1.0 2.0; 1.0 0.0 1.0; 2.0 1.0 0.0]",
"[0.0 1.0 2.0 3.0; 1.0 0.0 1.0 2.0; 2.0 1.0 0.0 1.0; 3.0 2.0 1.0 0.0]",
"[0.0 1.0 2.0 3.0 4.0; 1.0 0.0 1.0 2.0 3.0; 2.0 1.0 0.0 1.0 2.0; 3.0 2.0 1.0 0.0 1.0; 4.0 3.0 2.0 1.0 0.0]",
"[0.0 1.0 2.0 3.0 4.0 5.0; 1.0 0.0 1.0 2.0 3.0 4.0; 2.0 1.0 0.0 1.0 2.0 3.0; 3.0 2.0 1.0 0.0 1.0 2.0; 4.0 3.0 2.0 1.0 0.0 1.0; 5.0 4.0 3.0 2.0 1.0 0.0]",
"[0.0 1.0 2.0 3.0 4.0 5.0 6.0; 1.0 0.0 1.0 2.0 3.0 4.0 5.0; 2.0 1.0 0.0 1.0 2.0 3.0 4.0; 3.0 2.0 1.0 0.0 1.0 2.0 3.0; 4.0 3.0 2.0 1.0 0.0 1.0 2.0; 5.0 4.0 3.0 2.0 1.0 0.0 1.0; 6.0 5.0 4.0 3.0 2.0 1.0 0.0]",
"[0.0 1.0 2.0 3.0 4.0 5.0 6.0 7.0; 1.0 0.0 1.0 2.0 3.0 4.0 5.0 6.0; 2.0 1.0 0.0 1.0 2.0 3.0 4.0 5.0; 3.0 2.0 1.0 0.0 1.0 2.0 3.0 4.0; 4.0 3.0 2.0 1.0 0.0 1.0 2.0 3.0; 5.0 4.0 3.0 2.0 1.0 0.0 1.0 2.0; 6.0 5.0 4.0 3.0 2.0 1.0 0.0 1.0; 7.0 6.0 5.0 4.0 3.0 2.0 1.0 0.0]",
"[0.0 1.0 2.0 3.0 4.0 5.0 6.0 7.0 8.0; 1.0 0.0 1.0 2.0 3.0 4.0 5.0 6.0 7.0; 2.0 1.0 0.0 1.0 2.0 3.0 4.0 5.0 6.0; 3.0 2.0 1.0 0.0 1.0 2.0 3.0 4.0 5.0; 4.0 3.0 2.0 1.0 0.0 1.0 2.0 3.0 4.0; 5.0 4.0 3.0 2.0 1.0 0.0 1.0 2.0 3.0; 6.0 5.0 4.0 3.0 2.0 1.0 0.0 1.0 2.0; 7.0 6.0 5.0 4.0 3.0 2.0 1.0 0.0 1.0; 8.0 7.0 6.0 5.0 4.0 3.0 2.0 1.0 0.0]",
"[0.0 1.0 2.0 3.0 4.0 5.0 6.0 7.0 8.0 9.0; 1.0 0.0 1.0 2.0 3.0 4.0 5.0 6.0 7.0 8.0; 2.0 1.0 0.0 1.0 2.0 3.0 4.0 5.0 6.0 7.0; 3.0 2.0 1.0 0.0 1.0 2.0 3.0 4.0 5.0 6.0; 4.0 3.0 2.0 1.0 0.0 1.0 2.0 3.0 4.0 5.0; 5.0 4.0 3.0 2.0 1.0 0.0 1.0 2.0 3.0 4.0; 6.0 5.0 4.0 3.0 2.0 1.0 0.0 1.0 2.0 3.0; 7.0 6.0 5.0 4.0 3.0 2.0 1.0 0.0 1.0 2.0; 8.0 7.0 6.0 5.0 4.0 3.0 2.0 1.0 0.0 1.0; 9.0 8.0 7.0 6.0 5.0 4.0 3.0 2.0 1.0 0.0]"
]
real_train = [] # the real label of the dataset
for i in range(train.num_instances):
real_train.append(
train.get_instance(i).values[(train.num_attributes - 1)])
results_train['real'] = real_train
real_test = [] # the real label of the dataset
for i in range(test.num_instances):
real_test.append(
test.get_instance(i).values[(test.num_attributes - 1)])
results_test['real'] = real_test
num = 0
for clas in baseClassifiers_list:
column = "p" + np.str(num)
#classifier
classifier = SingleClassifierEnhancer(
classname="weka.classifiers.meta.CostSensitiveClassifier",
options=[
"-cost-matrix", cost_matrix_list[num_clases], "-M", "-S", "1"
])
base = Classifier(classname=clas)
classifier.classifier = base
predicted_data_train = None
predicted_data_test = None
evaluation = Evaluation(data)
classifier.build_classifier(train)
#evaluation.test_model(classifier, train)
# add predictions
addcls = Filter(
classname="weka.filters.supervised.attribute.AddClassification",
options=["-classification"])
addcls.set_property("classifier", Classifier.make_copy(classifier))
addcls.inputformat(train)
#addcls.filter(train) # trains the classifier
pred_train = addcls.filter(train)
pred_test = addcls.filter(test)
if predicted_data_train is None:
predicted_data_train = Instances.template_instances(pred_train, 0)
for n in range(pred_train.num_instances):
predicted_data_train.add_instance(pred_train.get_instance(n))
if predicted_data_test is None:
predicted_data_test = Instances.template_instances(pred_test, 0)
for n in range(pred_test.num_instances):
predicted_data_test.add_instance(pred_test.get_instance(n))
preds_train = [
] #labels predicted for the classifer trained in the iteration
preds_test = []
for i in range(predicted_data_train.num_instances):
preds_train.append(
predicted_data_train.get_instance(i).values[(
predicted_data_train.num_attributes - 1)])
for i in range(predicted_data_test.num_instances):
preds_test.append(
predicted_data_test.get_instance(i).values[(
predicted_data_test.num_attributes - 1)])
results_train[column] = preds_train
results_test[column] = preds_test
num = num + 1
return results_train, results_test
def main():
"""
Just runs some example code.
"""
# load a dataset
data_file = helper.get_data_dir() + os.sep + "vote.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 = Classifier(classname="weka.classifiers.trees.J48")
# randomize data
folds = 10
seed = 1
rnd = Random(seed)
rand_data = Instances.copy_instances(data)
rand_data.randomize(rnd)
if rand_data.class_attribute.is_nominal:
rand_data.stratify(folds)
# perform cross-validation and add predictions
predicted_data = None
evaluation = Evaluation(rand_data)
for i in xrange(folds):
train = rand_data.train_cv(folds, i)
# the above code is used by the StratifiedRemoveFolds filter,
# the following code is used by the Explorer/Experimenter
# train = rand_data.train_cv(folds, i, rnd)
test = rand_data.test_cv(folds, i)
# build and evaluate classifier
cls = Classifier.make_copy(classifier)
cls.build_classifier(train)
evaluation.test_model(cls, test)
# add predictions
addcls = Filter(
classname="weka.filters.supervised.attribute.AddClassification",
options=["-classification", "-distribution", "-error"])
# setting the java object directory avoids issues with correct quoting in option array
addcls.set_property("classifier", Classifier.make_copy(classifier))
addcls.inputformat(train)
addcls.filter(train) # trains the classifier
pred = addcls.filter(test)
if predicted_data is None:
predicted_data = Instances.template_instances(pred, 0)
for n in xrange(pred.num_instances):
predicted_data.add_instance(pred.get_instance(n))
print("")
print("=== Setup ===")
print("Classifier: " + classifier.to_commandline())
print("Dataset: " + data.relationname)
print("Folds: " + str(folds))
print("Seed: " + str(seed))
print("")
print(evaluation.summary("=== " + str(folds) + " -fold Cross-Validation ==="))
print("")
print(predicted_data)
# the above code is used by the StratifiedRemoveFolds filter,
# the following code is used by the Explorer/Experimenter
# train = rand_data.train_cv(folds, i, rnd)
test = rand_data.test_cv(folds, i)
# build and evaluate classifier
cls = Classifier.make_copy(classifier)
cls.build_classifier(train)
evaluation.test_model(cls, test)
# add predictions
addcls = Filter(
classname="weka.filters.supervised.attribute.AddClassification",
options=["-classification", "-distribution", "-error"])
# setting the java object directory avoids issues with correct quoting in option array
addcls.set_property("classifier", Classifier.make_copy(classifier))
addcls.inputformat(train)
addcls.filter(train) # trains the classifier
pred = addcls.filter(test)
if predicted_data is None:
predicted_data = Instances.template_instances(pred, 0)
for n in xrange(pred.num_instances):
predicted_data.add_instance(pred.get_instance(n))
print("")
print("=== Setup ===")
print("Classifier: " + classifier.to_commandline())
print("Dataset: " + data.relationname)
print("Folds: " + str(folds))
print("Seed: " + str(seed))
print("")
