def test_dropcolumns_regex(self):
int_missing_data = [[1, 0, 0, 3], [0, 2, 3, 4], [0, 3, 4, 4],
[1, 2, 3, 6]]
columns = ["agent.hi", "agent.user_name", "agent.hello", "message"]
data = pd.DataFrame(int_missing_data, columns=columns)
clean = Data(
x_train=data,
x_test=None,
split=False,
target_field="",
report_name="test",
test_split_percentage=0.5,
)
clean.drop(regexp=r"agent*")
validate = clean.x_train.columns == ["message"]
self.assertTrue(validate)
def test_dropcolumns_complex(self):
int_missing_data = [[1, 0, 0, 3], [0, 2, 3, 4], [0, 3, 4, 4],
[1, 2, 3, 6]]
columns = ["col1", "col2", "col3", "py"]
data = pd.DataFrame(int_missing_data, columns=columns)
clean = Data(
x_train=data,
x_test=None,
split=True,
target_field="",
report_name="test",
test_split_percentage=0.5,
)
clean.drop("col1",
keep=["col2"],
regexp=r"col*",
reason="Columns were unimportant.")
validate = list(clean.x_train.columns) == ["col2", "py"] and list(
clean.x_test.columns) == ["col2", "py"]
self.assertTrue(validate)
def test_dropcolumns_keep(self):
int_missing_data = [[1, 0, 0], [0, 2, 3], [0, 3, 4], [1, 2, 3]]
columns = ["col1", "col2", "col3"]
data = pd.DataFrame(int_missing_data, columns=columns)
clean = Data(x_train=data,
report_name="test",
test_split_percentage=0.5)
clean_inst = clean.drop(keep=["col2"],
reason="Columns were unimportant.")
validate = (clean_inst.x_train.columns == ["col2"]
and clean_inst.x_test.columns == ["col2"]
and isinstance(clean_inst, Data))
self.assertTrue(validate)
