Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.
def test_fuzzy_finder(keywords, paper_id):
fp = Path("tests", "demo_data", "embase.csv")
as_data = ASReviewData.from_file(fp)
assert as_data.fuzzy_find(keywords)[0] == paper_id
def test_reader(test_file, n_lines, labels, ignore_col):
fp = Path("test", "demo_data", test_file)
as_data = ASReviewData.from_file(fp)
assert len(as_data) == n_lines
cols = ['title', 'abstract', 'authors', 'keywords']
cols = [col for col in cols if col not in ignore_col]
if labels is not None:
cols.append('final_included')
assert np.array_equal(as_data.labels, labels)
for col in cols:
values = as_data.get(col)
assert len(values) == n_lines
def test_features(feature_extraction, split_ta):
embedding_fp = os.path.join("test", "demo_data", "generic.vec")
data_fp = os.path.join("test", "demo_data", "generic.csv")
as_data = ASReviewData.from_file(data_fp)
texts = as_data.texts
if feature_extraction.startswith("embedding-"):
model = get_feature_model(feature_extraction, split_ta=split_ta,
embedding_fp=embedding_fp)
else:
model = get_feature_model(feature_extraction, split_ta=split_ta)
X = model.fit_transform(texts, titles=as_data.title,
abstracts=as_data.abstract)
assert X.shape[0] == len(as_data.title)
assert X.shape[1] > 0
assert isinstance(model.param, dict)
assert model.name == feature_extraction
def test_csv_write_data():
fp_in = Path("test", "demo_data", "generic_labels.csv")
fp_out = Path("test", "out_data", "generic_out.csv")
asr_data = ASReviewData.from_file(fp_in)
asr_data.to_csv(fp_out, labels=[0, 1, 0, 1, 0, 1])