def test_cleanutil_removecolumns(self):
int_missing_data = [[1, 0, 0], [0, None, None], [None, None, None]]
columns = ["col1", "col2", "col3"]
data = pd.DataFrame(int_missing_data, columns=columns)
clean = Data(x_train=data,
test_split_percentage=0.5,
split=False,
report_name="test")
clean.drop_column_missing_threshold(0.5)
validate = clean.x_train.columns.tolist()
self.assertListEqual(validate, ["col1"])
def test_report_cleaning_technique(self):
int_missing_data = np.array([(1, 0, 0), (0, None, None),
(None, None, None)])
columns = ["col1", "col2", "col3"]
data = pd.DataFrame(int_missing_data, columns=columns)
clean = Data(x_train=data,
test_split_percentage=0.5,
split=False,
report_name="test")
clean.drop_column_missing_threshold(0.5)
with open(clean.report.filename) as f:
content = f.read()
validate = "col2" in content and "col3" in content
os.remove(clean.report.filename)
self.assertTrue(validate)
