def vote_classifier_train(dicrectory, nameOfDataSet, flag):
loader = Loader(classname="weka.core.converters.CSVLoader")
data = loader.load_file(dicrectory)
data.class_is_last()
meta = MultipleClassifiersCombiner(
classname="weka.classifiers.meta.Vote",
options=[
'-S', '1', '-B', 'weka.classifiers.trees.J48 -C 0.25 -M 2', '-B',
'weka.classifiers.trees.RandomTree -K 6 -M 1.0 -V 0.001 -S 1',
'-B',
'weka.classifiers.meta.Bagging -P 100 -S 1 -num-slots 1 -I 10 -W weka.classifiers.trees.REPTree -- '
'-M 2 -V 0.001 -N 3 -S 1 -L -1 -I 0.0', '-B',
'weka.classifiers.meta.AdaBoostM1 -P 100 -S 1 -I 10 -W weka.classifiers.trees.DecisionStump',
'-B',
'weka.classifiers.meta.Bagging -P 100 -S 1 -num-slots 1 -I 10 -W weka.classifiers.trees.REPTree -- '
'-M 2 -V 0.001 -N 3 -S 1 -L -1 -I 0.0', '-B',
'weka.classifiers.bayes.NaiveBayes ', '-R', 'AVG'
])
eval = Evaluation(data)
pout = PredictionOutput(
classname="weka.classifiers.evaluation.output.prediction.PlainText")
if flag:
eval.crossvalidate_model(meta, data, 10, Random(1), pout)
else:
eval.evaluate_train_test_split(meta, data, 80.0, Random(1), pout)
gc.collect()
print_and_save('Proposed model', flag, nameOfDataSet, eval)
def exposed_evaluate(self, X, d, task, i_model, i_evl):
data = np.reshape(eval(X), [d, -1], order='C')
if task == 'regression':
if i_model == 'LR':
data = converters.ndarray_to_instances(data, relation='tmp')
data.class_is_last()
model = Classifier(
classname='weka.classifiers.functions.LinearRegression')
evl = Evaluation(data)
evl.crossvalidate_model(model, data, 5, Random(0))
elif i_model == 'RF':
data = converters.ndarray_to_instances(data, relation='tmp')
data.class_is_last()
model = Classifier(
classname='weka.classifiers.trees.RandomForest')
evl = Evaluation(data)
evl.crossvalidate_model(model, data, 5, Random(0))
if i_evl == 'mae':
r_mae = evl.mean_absolute_error
return r_mae
elif i_evl == 'mse':
r_mae = evl.mean_square_error
return r_mse
elif i_evl == '1-rae':
r_one_minus_rae = 1 - evl.relative_absolute_error / 100
del evl, model, data
return r_one_minus_rae
elif task == 'classification':
le = LabelEncoder()
data[:, -1] = le.fit_transform(data[:, -1])
if i_model == 'RF':
dataRaw = converters.ndarray_to_instances(data, relation='tmp')
weka_filter = Filter(
classname=
"weka.filters.unsupervised.attribute.NumericToNominal",
options=["-R", "last"])
weka_filter.inputformat(dataRaw)
data = weka_filter.filter(dataRaw)
data.class_is_last()
model = Classifier(
classname='weka.classifiers.trees.RandomForest')
evl = Evaluation(data)
evl.crossvalidate_model(model, data, 5, Random(0))
elif i_model == 'LR':
model = LogisticRegression(multi_class='ovr')
elif i_model == 'SVM':
model = svm.SVC()
if i_evl == 'f_score':
fscore = evl.weighted_f_measure
del evl, model, data, dataRaw
if not (fscore >= 0.01 and fscore < 1.01):
fscore = 0.01
return fscore
def naive_bayse(dicrectory, nameOfDataSet, flag):
loader = Loader(classname="weka.core.converters.CSVLoader")
data = loader.load_file(dicrectory)
data.class_is_last()
cls = Classifier(classname='weka.classifiers.bayes.NaiveBayes')
eval = Evaluation(data)
pout = PredictionOutput(
classname="weka.classifiers.evaluation.output.prediction.PlainText")
if flag:
eval.crossvalidate_model(cls, data, 10, Random(1), pout)
else:
eval.evaluate_train_test_split(cls, data, 80.0, Random(1), pout)
print_and_save('Naive Bayes model', flag, nameOfDataSet, eval)
gc.collect()
def Boost_J48(data, rnm):
data.class_is_last()
fc1 = FilteredClassifier()
fc1.classifier = Classifier(classname="weka.classifiers.trees.J48", options=["-C", "0.25", "-M", "2"])
fc1.filter = Filter(classname="weka.filters.unsupervised.attribute.Remove", options=["-R", "first"])
fc2 = SingleClassifierEnhancer(classname="weka.classifiers.meta.AdaBoostM1", options=["-P", "100", "-S", "1", "-I", "10"])
fc2.classifier = fc1
pred_output = PredictionOutput(classname="weka.classifiers.evaluation.output.prediction.CSV", options=["-p", "1"])
folds = 10
fc2.build_classifier(data)
evaluation = Evaluation(data)
evaluation.crossvalidate_model(fc2, data, folds, Random(1), pred_output)
f0 = open(rnm + '_Boost_J48_Tree.txt', 'w')
print >> f0, "Filename: ", rnm
print >> f0, '\n\n'
print >> f0, str(fc2)
f0.close()
f1 = open(rnm + '_Boost_J48_Prediction.txt', 'w')
print >> f1, 'Filename:', rnm
print >> f1, 'Prediction Summary:', (pred_output.buffer_content())
f1.close()
f2 = open(rnm + '_Boost_j48_Evaluation.txt', 'w')
print >> f2, 'Filename:', rnm
print >> f2, 'Evaluation Summary:', (evaluation.summary())
print >> f2, '\n\n\n'
print >> f2, (evaluation.class_details())
f2.close()
plot_roc(evaluation, class_index=[0,1], title=rnm, key_loc='best', outfile=rnm + '_Boost_J48_ROC.png', wait=False)
value_Boost_J48 = str(evaluation.percent_correct)
return value_Boost_J48
def RandomTree(data, rnm):
data.class_is_last()
fc = FilteredClassifier()
fc.classifier = Classifier(classname="weka.classifiers.trees.RandomTree", options=["-K", "0", "-M", "1.0", "-V", "0.001", "-S", "1"])
fc.filter = Filter(classname="weka.filters.unsupervised.attribute.Remove", options=["-R", "first"])
pred_output = PredictionOutput(classname="weka.classifiers.evaluation.output.prediction.CSV", options=["-p", "1"])
folds = 10
evl = Evaluation(data)
evl.crossvalidate_model(fc, data, folds, Random(1), pred_output)
fc.build_classifier(data)
f0 = open(rnm + '_RT_Tree.txt', 'w')
print >> f0, "Filename: ", rnm
print >> f0, '\n\n'
print >> f0, str(fc)
f0.close()
f1 = open(rnm + '_RT_Prediction.txt', 'w')
print >> f1, 'Filename:', rnm
print >> f1, 'Prediction Summary:', (pred_output.buffer_content())
f1.close()
f2 = open(rnm + '_RT_Evaluation.txt', 'w')
print >> f2, 'Filename:', rnm
print >> f2, 'Evaluation Summary:', (evl.summary())
print >> f2, '\n\n\n'
print >> f2, (evl.class_details())
f2.close()
plot_roc(evl, class_index=[0,1], title=rnm, key_loc='best', outfile=rnm+'_RT_ROC.png', wait=False)
value_RT = str(evl.percent_correct)
return value_RT
def runSMO(file, bound):
loader = Loader(classname="weka.core.converters.CSVLoader")
data = loader.load_file(file)
data.class_is_first()
remove = Filter(classname="weka.filters.unsupervised.attribute.Remove",
options=["-R", bound])
cls = KernelClassifier(
classname="weka.classifiers.functions.SMO",
options=["-C", "1.0", "-L", "0.001", "-P", "1.0E-12", "-N", "0"])
kernel = Kernel(
classname="weka.classifiers.functions.supportVector.PolyKernel",
options=["-C", "250007", "-E", "1.0"])
cls.kernel = kernel
pout = PredictionOutput(
classname="weka.classifiers.evaluation.output.prediction.PlainText")
remove.inputformat(data)
filtered = remove.filter(data)
evl = Evaluation(filtered)
evl.crossvalidate_model(cls, filtered, 10, Random(1), pout)
#print(pout.buffer_content())
print(evl.percent_correct)
#print(evl.summary())
result = evl.class_details()
print(result)
return result
def create_model(input_file, output_file):
# Load data
data = converters.load_any_file(input_file)
data.class_is_last() # set class attribute
# filter data
print_title("Filtering Data")
discretize = Filter(
classname="weka.filters.unsupervised.attribute.Discretize",
options=["-B", "10", "-M", "-1.0", "-R", "first-last"])
discretize.inputformat(
data) # let the filter know about the type of data to filter
filtered_data = discretize.filter(data)
print("Done! (believe it or not)")
print_title("Build Classifier")
classifier = Classifier(classname="weka.classifiers.trees.RandomForest",
options=["-I", "100", "-K", "0", "-S", "1"])
classifier.build_classifier(filtered_data)
print("Done! (believe it or not)")
serialization.write_all(output_file, [classifier, discretize])
print("Model and filter saved to ", output_file)
evaluation = Evaluation(data) # initialize with priors
evaluation.crossvalidate_model(classifier, filtered_data, 10,
Random(42)) # 10-fold CV
print(evaluation.summary())
print("pctCorrect: " + str(evaluation.percent_correct))
print("incorrect: " + str(evaluation.incorrect))
def train_and_eval_weka_classifier(clf, train, valid, n_instances):
total_train_inst = train.num_instances
percentage = (n_instances * 100) / total_train_inst
if percentage == 100:
opt = train
else:
opt, residual = train.train_test_split(percentage, Random(1))
# opt, residual = train.train_test_split(percentage, Random(1))
print('total_train_inst: ', total_train_inst, '| percentage: ',
percentage, '| used_inst: ', opt.num_instances)
clf.build_classifier(opt)
evl = Evaluation(opt)
evl.test_model(clf, valid)
# evl.crossvalidate_model(clf, opt, 10, Random(1))
acc = evl.percent_correct
auc = evl.weighted_area_under_roc
err = evl.error_rate
log = evl.sf_mean_scheme_entropy
print(
"# validating | loss: {:.2}, accuracy: {:.4}, AUC: {:.2}, error: {:.2}"
.format(log, acc, auc, err))
return {'loss': log, 'accuracy': acc, 'auc': auc, 'err': err}
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 naiveBayes(data):
classifier = Classifier(classname="weka.classifiers.bayes.NaiveBayes", options=["-D"])
nfolds=13
rnd = Random(0)
evaluation = Evaluation(data)
evaluation.crossvalidate_model(classifier, data,
nfolds, rnd)
print(" Naive Bayes Cross-validation information")
print(evaluation.summary())
print("precision: " + str(evaluation.precision(1)))
print("recall: " + str(evaluation.recall(1)))
print("F-measure: " + str(evaluation.f_measure(1)))
print("==confusion matrix==")
print(" a b")
print(evaluation.confusion_matrix)
print
#write to file
f = open("naiveeval.txt", "w")
f.write(evaluation.summary())
f.write("\n")
f.write("==confusion matrix==\n")
f.write(" a b\n")
for item in evaluation.confusion_matrix:
f.write("%s\n" % item)
f.close()
#plot roc graph
plcls.plot_roc(evaluation, title="Naive Bayes ROC", outfile="NBROC", wait=True)
return evaluation.percent_correct
def run():
jvm.start()
load_csv = Loader("weka.core.converters.CSVLoader")
data_csv = load_csv.load_file(
"/Users/imeiliasantoso/web_graduate_project4/predict_page/predict_data.csv"
)
saver = Saver("weka.core.converters.ArffSaver")
saver.save_file(
data_csv,
"/Users/imeiliasantoso/web_graduate_project4/predict_page/predict_data.arff"
)
load_arff = Loader("weka.core.converters.ArffLoader")
data_arff = load_arff.load_file(
"/Users/imeiliasantoso/web_graduate_project4/predict_page/predict_data.arff"
)
data_arff.class_is_last()
global j48
J48_class = Classifier(classname="weka.classifiers.trees.J48",
options=["-C", "0.25", "-M", "2"])
J48_class.build_classifier(data_arff)
evaluationj48 = Evaluation(data_arff)
evaluationj48.crossvalidate_model(J48_class, data_arff, 10, Random(100))
j48 = str(evaluationj48.percent_correct)
jvm.stop()
return j48
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 experiment_file_random(path_features, path_folder_save_results, options,
classifier, fold, random, name):
print("start weka")
cls = Classifier(classname=classifier,
options=weka.core.classes.split_options(options))
d_results = {
'percent_correct': [],
'percent_incorrect': [],
'confusion_matrix': []
}
data = converters.load_any_file(path_features)
data.class_is_last()
pout = PredictionOutput(
classname="weka.classifiers.evaluation.output.prediction.CSV")
evl = Evaluation(data)
evl.crossvalidate_model(cls, data, fold, Random(random), pout)
d_results['percent_correct'].append(evl.percent_correct)
d_results['percent_incorrect'].append(evl.percent_incorrect)
d_results['confusion_matrix'].append(
evl.matrix()) # Generates the confusion matrix.
d_results = pd.DataFrame(data=d_results)
d_results.to_csv(path_folder_save_results + '/' + str(name) + '.csv',
index=False)
save = pout.buffer_content()
with open(
path_folder_save_results + '/' + 'prediction/' + str(name) +
'.csv', 'w') as f:
f.write(save)
def splitTrainSet(data,m_numLabledData=10) :
total = data.num_instances
labeled_amount = int(m_numLabledData * total / 100)
unlabeled_amount = total - labeled_amount
rand = Random(1)
data.randomize(rand)
labledDataSet = Instances.create_instances(data.relationname,data.attributes(),labeled_amount)
UnlabledDataSet = Instances.create_instances(data.relationname,data.attributes(),unlabeled_amount)
for i in range(labeled_amount) :
labledDataSet.add_instance(data.get_instance(i))
labledDataSet.randomize(rand)
for i in range(unlabeled_amount) :
UnlabledDataSet.add_instance(data.get_instance(labeled_amount + i))
# labledDataSet.randomize(rand)
labledDataSet.class_is_last()
# UnlabledDataSet.randomize(rand)
UnlabledDataSet.class_is_last()
return labledDataSet,UnlabledDataSet
def evaluation(self, classifier, trainingData, testingData=None):
trainingData.set_class_index(trainingData.num_attributes() - 1)
if testingData == None:
evaluation = Evaluation(trainingData)
# initialize with priors
evaluation.crossvalidate_model(classifier, trainingData, 10,
Random(42)) # 10-fold CV
return evaluation
else:
print "testing data exists"
if testingData.num_attributes() == trainingData.num_attributes():
testingData.set_class_index(testingData.num_attributes() - 1)
evaluation = Evaluation(trainingData)
classifier.build_classifier(trainingData)
evaluation.test_model(classifier, testingData)
#for attribute in trainingData.attributes():
# print "train:" + str(attribute)
#for attribute in testingData.attributes():
# print "test:" + str(attribute)
return evaluation
else:
print "testing Data doesn't have same attribute with training data"
for attribute in trainingData.attributes():
print "train:" + str(attribute)
for attribute in testingData.attributes():
print "test:" + str(attribute)
def test_generate_thresholdcurve_data(self):
"""
Tests the generate_thresholdcurve_data method.
"""
loader = converters.Loader(classname="weka.core.converters.ArffLoader")
data = loader.load_file(self.datafile("diabetes.arff"))
data.class_is_last()
remove = filters.Filter(
classname="weka.filters.unsupervised.attribute.Remove",
options=["-R", "1-3"])
cls = classifiers.Classifier(
classname="weka.classifiers.bayes.NaiveBayes")
fc = classifiers.FilteredClassifier()
fc.filter = remove
fc.classifier = cls
evl = classifiers.Evaluation(data)
evl.crossvalidate_model(cls, data, 10, Random(1))
data = plot.generate_thresholdcurve_data(evl, 0)
self.assertEqual(13,
data.num_attributes,
msg="number of attributes differs")
self.assertEqual(769, data.num_instances, msg="number of rows differs")
attname = "True Positives"
self.assertIsNotNone(data.attribute_by_name(attname),
msg="Failed to locate attribute: " + attname)
attname = "False Positive Rate"
self.assertIsNotNone(data.attribute_by_name(attname),
msg="Failed to locate attribute: " + attname)
attname = "Lift"
self.assertIsNotNone(data.attribute_by_name(attname),
msg="Failed to locate attribute: " + attname)
def naivebay_classifier_weka(data):
classifier = Classifier("weka.classifiers.bayes.NaiveBayes")
evaluation = Evaluation(data)
evaluation.crossvalidate_model(classifier, data, 10, Random(42))
print(evaluation.summary())
print(evaluation.confusion_matrix)
return classifier
def runCV(this, arffFile, classifier, folds):
loader = Loader(classname="weka.core.converters.ArffLoader")
data = loader.load_file(arffFile)
data.class_is_last()
classes = [str(code) for code in data.class_attribute.values]
header = ["Accuracy"]
for name in classes:
header += [name + " TP", name + " FP", name + " AUC ROC"]
values = []
cls = Classifier(classname=classifier)
evl = Evaluation(data)
evl.crossvalidate_model(cls, data, folds, Random(1))
values.append(evl.percent_correct)
for name in classes:
index = classes.index(name)
values += [
evl.true_positive_rate(index) * 100,
evl.false_positive_rate(index) * 100,
evl.area_under_roc(index)
]
this.values = values
this.header = header
def main():
try:
jvm.start()
loader = Loader(classname="weka.core.converters.CSVLoader")
data = loader.load_file("./data/adult.csv")
data.class_is_last() # set class attribute
# randomize data
folds = k
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)
NaiveBayes(rand_data, folds, seed, data)
DecisionTree(rand_data, folds, seed, data)
except Exception as e:
raise e
finally:
jvm.stop()
def split_train_test_valid(self):
try:
self.data = self.return_data()
total_inst = self.data.num_instances
train_, self.test = self.data.train_test_split(80.0, Random(1))
self.train, self.valid = train_.train_test_split(75.0, Random(1))
print('total_inst: ', total_inst, '| train_inst: ',
self.train.num_instances, '| valid_inst: ',
self.valid.num_instances, '| test_inst: ',
self.test.num_instances)
except Exception:
pass
return self.train, self.valid, self.test
def main():
dataset = sys.argv[1]
#load a dataset
loader = Loader("weka.core.converters.ArffLoader")
data = loader.load_file("./data/" + dataset + ".arff")
data.class_is_last()
num_classes = data.class_attribute.num_values
os.mkdir('resultados_' + sys.argv[1])
for random_cv in range(10): #10 CV
# generate train/test split of randomized data
train, test = data.train_test_split(75.0, Random(random_cv))
results_train, results_test = classification(data, train, test,
num_classes)
# results_test = classification(test, num_classes)
#Write results in Excel format
train_name = "./resultados_" + sys.argv[1] + "/resultados_" + sys.argv[
1] + "_" + "E" + np.str(random_cv) + ".csv"
test_name = "./resultados_" + sys.argv[1] + "/resultados_" + sys.argv[
1] + "_" + "T" + np.str(random_cv) + ".csv"
results_train.to_csv(train_name)
results_test.to_csv(test_name)
def fitness(toeval : Individual):
cls = Classifier(classname="weka.classifiers.functions.MultilayerPerceptron", options=toeval.settings())
fc = FilteredClassifier()
fc.filter = remove
fc.classifier = cls
evl = Evaluation(data)
evl.crossvalidate_model(fc, data, 10, Random(1))
return evl.percent_correct
def f_smote():
jvm.start()
train_data, test_data = b_i_impute_data()
train_data = train_data[:10000]
y_train = train_data["class"]
x_train = train_data.drop("class", axis=1)
sm = SMOTE(ratio="minority")
x_train_sm, y_train_sm = sm.fit_sample(x_train, y_train)
x_train_sm_df = pd.DataFrame(x_train_sm, columns=x_train.columns)
y_train_sm_df = pd.DataFrame(y_train_sm, columns=["class"])
train_data_sm_df = pd.concat([y_train_sm_df, x_train_sm_df], axis=1)
print_f("smote train data shape", train_data_sm_df.shape)
train_data_sm_df.to_csv("./train_data_sm.csv", index=False)
train_data_sm = converters.load_any_file("train_data_sm.csv")
train_data_sm.class_is_first()
test_data = converters.load_any_file("test_data.csv")
test_data.class_is_first()
print_f("1")
cls = Classifier(classname="weka.classifiers.trees.LMT")
print_f("bulding classifier")
cls.build_classifier(train_data_sm)
print_f("Evaluating")
evl = Evaluation(train_data_sm)
evl.crossvalidate_model(cls, train_data_sm, 5, Random(1))
print_f("Train Accuracy:", evl.percent_correct)
print_f("Train summary")
print_f(evl.summary())
print_f("Train class details")
print_f(evl.class_details())
print_f("Train confusion matrix")
print_f(evl.confusion_matrix)
plcls.plot_roc(evl,
class_index=[0, 1],
wait=True,
outfile="./plots/2_f_smote_10k.png")
plt.suptitle("Train ROC Curve", fontsize=20, y=0.95)
evl = Evaluation(test_data)
print_f("testing model")
evl.test_model(cls, test_data)
print_f("Test Accuracy:", evl.percent_correct)
print_f("Test summary")
print_f(evl.summary())
print_f(" Testclass details")
print_f(evl.class_details())
print_f("Testconfusion matrix")
print_f(evl.confusion_matrix)
plcls.plot_roc(evl, class_index=[0, 1], wait=True)
plt.suptitle("Test ROC Curve", fontsize=20, y=0.95)
savefig("./plots/f_test_roc_curve.png")
def run_bayesNet(file):
# Get filename from Pathlib object
filename = file.parts[-1]
dir = file.parents[0]
print("Running BayesNet on %s" % filename)
if not filename.endswith(".arff"):
print("%s not ARFF file." % filename)
return
# Removes '.arff' from filename
filename_base = filename[:-5]
# Load data with class as first attr
data = load_Arff_file(file)
data.class_is_first()
# Use BayesNet and set options
cls = Classifier(classname="weka.classifiers.bayes.BayesNet",
options=[
"-D", "-Q",
"weka.classifiers.bayes.net.search.local.TAN", "--",
"-P", "1", "-S", "BAYES", "-E",
"weka.classifiers.bayes.net.estimate.SimpleEstimator",
"--", "-A", "0.5"
])
# Predictions stored in pout
pout = PredictionOutput(
classname="weka.classifiers.evaluation.output.prediction.PlainText")
# Evaluate data
evaluation = Evaluation(data)
evaluation.crossvalidate_model(cls, data, 10, Random(1), output=pout)
print(evaluation.summary())
print(evaluation.class_details())
print(evaluation.confusion_matrix)
# Generate grid for ROC
# plcls.plot_roc(evaluation, class_index=[0,1], wait=True)
# mk dirs for output
dir = dir / "bayesNet_results"
dir.mkdir(parents=True, exist_ok=True)
# Save summary, class details and confusion matrix to file
result_output = filename_base + "_bayesNet_eval_results_TAN.txt"
output_eval(evaluation, dir / result_output)
# Save the predicited results to file
prediction_output = filename_base + "_bayesNet_pred_results_TAN.txt"
output_pred(pout, dir / prediction_output)
print("BayesNet complete")
def get_weka_training_data(self):
percentage_of_train_set = 100 - self.test_size * 100
loader = Loader(classname="weka.core.converters.CSVLoader")
dataset = loader.load_file(os.path.join(constants.BASE_DIR, constants.BREAST_CANCER_FILE_NAME))
dataset.class_is_last()
train_set, test_set = dataset.train_test_split(percentage_of_train_set, Random(1))
return {
'train_set': train_set,
'test_set': test_set,
'labels': dataset.class_attribute.values
}
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.
The predictions get recorded in two different ways:
1. in-memory via the test_model method
2. directly to file (more memory efficient), but a separate run of making predictions
: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 and record predictions in memory
helper.print_title("recording predictions in-memory")
output = PredictionOutput(
classname="weka.classifiers.evaluation.output.prediction.CSV",
options=["-distribution"])
evl = Evaluation(train)
evl.test_model(cls, test, output=output)
print(evl.summary())
helper.print_info("Predictions:")
print(output.buffer_content())
# record/output predictions separately
helper.print_title("recording/outputting predictions separately")
outputfile = helper.get_tmp_dir() + "/j48_vote.csv"
output = PredictionOutput(
classname="weka.classifiers.evaluation.output.prediction.CSV",
options=["-distribution", "-suppress", "-file", outputfile])
output.header = test
output.print_all(cls, test)
helper.print_info("Predictions stored in:" + outputfile)
# by using "-suppress" we don't store the output in memory, the following statement won't output anything
print(output.buffer_content())
def main():
"""
Just runs some example code.
"""
# generic JavaObject stuff
helper.print_title("Generic stuff using weka.core.SystemInfo")
info = JavaObject(JavaObject.new_instance("weka.core.SystemInfo"))
jwrapper = info.jwrapper
print("toString() method:")
print(jwrapper.toString())
# random
helper.print_title("Random")
rnd = Random(1)
for i in xrange(10):
print(rnd.next_double())
for i in xrange(10):
print(rnd.next_int(100))
# single index
helper.print_title("SingleIndex")
si = SingleIndex(index="first")
upper = 10
si.upper(upper)
print(str(si) + " (upper=" + str(upper) + ")\n -> " + str(si.index()))
si.single_index = "3"
si.upper(upper)
print(str(si) + " (upper=" + str(upper) + ")\n -> " + str(si.index()))
si.single_index = "last"
si.upper(upper)
print(str(si) + " (upper=" + str(upper) + ")\n -> " + str(si.index()))
# range
helper.print_title("Range")
rng = Range(ranges="first")
upper = 10
invert = False
rng.upper(upper)
rng.invert = invert
print(str(rng.ranges) + " (upper=" + str(upper) + ", invert=" + str(invert) + ")\n -> " + str(rng.selection()))
rng.ranges = "3"
rng.upper(upper)
rng.invert = invert
print(str(rng.ranges) + " (upper=" + str(upper) + ", invert=" + str(invert) + ")\n -> " + str(rng.selection()))
rng.ranges = "last"
rng.upper(upper)
rng.invert = invert
print(str(rng.ranges) + " (upper=" + str(upper) + ", invert=" + str(invert) + ")\n -> " + str(rng.selection()))
rng.ranges = "first-last"
rng.upper(upper)
rng.invert = invert
print(str(rng.ranges) + " (upper=" + str(upper) + ", invert=" + str(invert) + ")\n -> " + str(rng.selection()))
rng.ranges = "3,4,7-last"
rng.upper(upper)
rng.invert = invert
print(str(rng.ranges) + " (upper=" + str(upper) + ", invert=" + str(invert) + ")\n -> " + str(rng.selection()))
rng.ranges = "3,4,7-last"
rng.upper(upper)
invert = True
rng.invert = invert
print(str(rng.ranges) + " (upper=" + str(upper) + ", invert=" + str(invert) + ")\n -> " + str(rng.selection()))
# tag
helper.print_title("Tag")
tag = Tag(ident=1, ident_str="one")
print("tag=" + str(tag) + ", ident=" + str(tag.ident) + ", readable=" + tag.readable)
tag.ident = 3
print("tag=" + str(tag) + ", ident=" + str(tag.ident) + ", readable=" + tag.readable)
tag = Tag(ident=2, ident_str="two", readable="2nd tag")
print("tag=" + str(tag) + ", ident=" + str(tag.ident) + ", readable=" + tag.readable)
