def test_model(self, test_data, empty_solution, evaluate = False):
model_weka = None
if os.path.isfile(self.prediction_file):
print 'Model ' + self.name + ' already tested.'
elif not os.path.isfile(self.model_file):
print 'Impossible testing this model. It should be trained first.'
return
else:
print 'Starting to test_model model ' + self.name + '.'
model_weka = Classifier(jobject = serialization.read(self.model_file))
evaluation = Evaluation(data = test_data)
evaluation.test_model(classifier = model_weka, data = test_data)
predictions = evaluation.predictions()
rows = read_sheet(file_name = empty_solution)
solutions = []
for row in rows:
solution = [row['userid'], row['tweetid'], predictions.pop(0).predicted()]
solutions.append(solution)
write_the_solution_file(solutions, self.prediction_file)
print 'Model ' + self.name + ' tested.'
if evaluate == True:
if os.path.isfile(self.evaluation_file):
print 'Model ' + self.name + ' already evaluated.'
return
elif model_weka == None:
model_weka = Classifier(jobject = serialization.read(self.model_file))
evaluation = Evaluation(data = test_data)
evaluation.test_model(classifier = model_weka, data = test_data)
save_file(file_name = self.evaluation_file, content = evaluation.to_summary())
print 'Model ' + self.name + ' evaluated.'
print("\nLoading dataset: " + fname + "\n")
loader = Loader(classname="weka.core.converters.ArffLoader")
data = loader.load_file(fname)
data.set_class_index(data.num_attributes() - 1)
# plot
pld.scatter_plot(
data, data.get_attribute_by_name("petalwidth").get_index(),
data.get_attribute_by_name("petallength").get_index(),
wait=False)
# add classifier errors to dataset
addcls = Filter(
classname="weka.filters.supervised.attribute.AddClassification",
options=["-W", "weka.classifiers.trees.J48", "-classification", "-error"])
addcls.set_inputformat(data)
filtered = addcls.filter(data)
print(filtered)
# build J48
cls = Classifier(classname="weka.classifiers.trees.J48")
cls.build_classifier(data)
evl = Evaluation(data)
evl.test_model(cls, data)
# plot classifier errors
plc.plot_classifier_errors(evl.predictions(), wait=True)
jvm.stop()
jvm.start()
# load credit-g
fname = data_dir + os.sep + "credit-g.arff"
print("\nLoading dataset: " + fname + "\n")
loader = Loader(classname="weka.core.converters.ArffLoader")
data = loader.load_file(fname)
data.set_class_index(data.num_attributes() - 1)
# cross-validate NaiveBayes
classifier = "weka.classifiers.bayes.NaiveBayes"
print("\n--> " + classifier + "\n")
cls = Classifier(classname=classifier)
evl = Evaluation(data)
evl.crossvalidate_model(cls, data, 10, Random(1))
preds = classifiers.predictions_to_instances(data, evl.predictions())
preds.sort(preds.get_attribute_by_name("distribution-good").get_index())
print(evl.to_summary())
print(evl.to_matrix())
print(preds)
# cross-validate J48
classifier = "weka.classifiers.trees.J48"
print("\n--> " + classifier + "\n")
cls = Classifier(classname=classifier, options=["-M", "100"])
evl = Evaluation(data)
evl.crossvalidate_model(cls, data, 10, Random(1))
preds = classifiers.predictions_to_instances(data, evl.predictions())
preds.sort(preds.get_attribute_by_name("distribution-good").get_index())
print(evl.to_summary())
print(evl.to_matrix())
