def test_transform_datetime(self):
"""Test the ``GreaterThan.transform`` method passing a high column of type datetime.
If the columns are of type datetime, ``transform`` is expected
to convert the timedelta distance into numeric before applying
the +1 and logarithm.
Input:
- Table with values at a distance of exactly 1 second.
Output:
- Same table with the high column transformed into the logarithms
of the dinstance in nanoseconds + 1, which is np.log(1_000_000_001).
"""
# Setup
instance = GreaterThan(low='a', high='b', strict=True)
# Run
table_data = pd.DataFrame({
'a':
pd.to_datetime(['2020-01-01T00:00:00', '2020-01-02T00:00:00']),
'b':
pd.to_datetime(['2020-01-01T00:00:01', '2020-01-02T00:00:01']),
'c': [1, 2],
})
out = instance.transform(table_data)
# Assert
expected_out = pd.DataFrame({
'a':
pd.to_datetime(['2020-01-01T00:00:00', '2020-01-02T00:00:00']),
'b': [np.log(1_000_000_001),
np.log(1_000_000_001)],
'c': [1, 2],
})
def test_transform_float(self):
"""Test the ``GreaterThan.transform`` method passing a high column of type float.
The ``GreaterThan.transform`` method is expected to compute the distance
between the high and low columns and replace the high column with the
logarithm of the distance + 1.
Input:
- Table with two constrained columns at a constant distance of
exactly 3 and one additional dummy column.
Output:
- Same table with the high column transformed into the logarithms
of the distances + 1, which is np.log(4).
"""
# Setup
instance = GreaterThan(low='a', high='b', strict=True)
# Run
table_data = pd.DataFrame({
'a': [1, 2, 3],
'b': [4., 5., 6.],
'c': [7, 8, 9],
})
out = instance.transform(table_data)
# Assert
expected_out = pd.DataFrame({
'a': [1, 2, 3],
'b': [np.log(4)] * 3,
'c': [7, 8, 9],
})
pd.testing.assert_frame_equal(out, expected_out)
def test_transform(self):
"""Test the ``GreaterThan.transform`` method.
The ``GreaterThan.transform`` method is expected to:
- Transform the original table data.
Input:
- Table data (pandas.DataFrame)
Output:
- Table data transformed (pandas.DataFrame)
"""
# Setup
instance = GreaterThan(low='a', high='b', strict=True)
# Run
table_data = pd.DataFrame({
'a': [1, 2, 3],
'b': [4, 5, 6],
})
out = instance.transform(table_data)
# Assert
expected_out = pd.DataFrame({
'a': [1, 2, 3],
'b': [1.3862944, 1.3862944, 1.3862944]
})
pd.testing.assert_frame_equal(out, expected_out)
def test_transform_not_all_columns_provided(self):
"""Test the ``GreaterThan.transform`` method.
If some of the columns needed for the transform are missing, it will raise
a ``MissingConstraintColumnError``.
Input:
- Table data (pandas.DataFrame)
Output:
- Raises ``MissingConstraintColumnError``.
"""
# Setup
instance = GreaterThan(low='a', high='b', strict=True)
# Run/Assert
with pytest.raises(MissingConstraintColumnError):
instance.transform(pd.DataFrame({'a': ['a', 'b', 'c']}))