def task(name):
if name == 'offenseval':
return of.Offenseval()
elif name == 'vua-format':
return vf.VuaFormat()
else:
raise ValueError("task name is unknown. You can add a custom task in 'tasks'")
def test_data_load():
task = vf.VuaFormat()
task.load(test_data_dir)
train_X, train_y, test_X, test_y = utils.get_instances(
task, split_train_dev=False)
assert len(train_X) == 199
assert len(test_X) == 99
def test_hate_speech():
task = vf.VuaFormat()
task.load(hate_speech_data_dir, ['testData.csv'])
train_X, train_y, test_X, test_y = utils.get_instances(
task, split_train_dev=True, proportion_train=0.1, proportion_dev=0.01)
pipe = pipelines.naive_bayes()
pipe.fit(train_X, train_y)
sys_y = pipe.predict(test_X)
assert len(sys_y) == len(test_y)
def test_trac2018():
task = vf.VuaFormat()
task.load(trac_data_dir, 'devData.csv')
train_X, train_y, test_X, test_y = utils.get_instances(
task, split_train_dev=True, proportion_train=0.1, proportion_dev=0.01)
pipe = pipelines.naive_bayes_counts()
pipe.fit(train_X, train_y)
sys_y = pipe.predict(test_X)
assert len(sys_y) == len(test_y)
def task(name):
if name == 'vua_format':
return vf.VuaFormat()
else:
raise ValueError(
"task name is unknown. You can add a custom task in 'tasks'")