def test_train_and_test_dataset():
with tempfile.TemporaryDirectory() as temp_dir:
# Test both the normal cahce_dir and the given cache dir
for data_dir in [None, Path(temp_dir, 'twitter data')]:
train_data = wang_2017_election_twitter_train(data_dir)
test_data = wang_2017_election_twitter_test(data_dir)
assert len(train_data) > len(test_data)
combined_data = TargetTextCollection.combine(train_data, test_data)
assert 11899 == combined_data.number_targets()
train_count += 1
percentage_train_targets = (train_count / len(train_targets)) * 100
print(
f'Percentage of targets that have been predicted that are in train: {percentage_train_targets}'
)
test_count = 0
for test_target in test_targets:
if test_target in pred_targets:
test_count += 1
percentage_test_targets = (test_count / len(test_targets)) * 100
print(
f'Percentage of targets that have been predicted that are in test: {percentage_test_targets}'
)
train_test = TargetTextCollection.combine(train_data, test_data)
train_test_in_count = 0
train_test_out_count = 0
train_test_targets = train_test.target_count(lower=True)
for train_test_target in train_test_targets:
if train_test_target in pred_targets:
train_test_in_count += 1
else:
train_test_out_count += 1
print(
f'Number of new predicted targets that are in the whole gold datasets: '
f'{train_test_in_count} compared to that are not: {train_test_out_count}'
)
train_and_pred = TargetTextCollection.combine(train_data, all_targets)
train_and_pred_targets = set(
