def test_transform_numeric(self):
"""Test the ``transform`` on numeric input.
In this test ``transform`` should return a matrix
representing each item in the input as one-hot encodings.
Input:
- Series with numeric input
Output:
- one-hot encoding of the input
"""
# Setup
ohet = OneHotEncodingTransformer()
data = pd.Series([1, 2])
ohet.fit(data)
expected = np.array([
[1, 0],
[0, 1],
])
# Run
out = ohet.transform(data)
# Assert
assert not ohet.dummy_encoded
np.testing.assert_array_equal(out, expected)
def test_transform_unknown(self):
"""Test the ``transform`` with unknown data.
In this test ``transform`` should raise an error
due to the attempt of transforming data with previously
unseen categories.
Input:
- Series with unknown categorical values
"""
# Setup
ohet = OneHotEncodingTransformer()
data = pd.Series(['a'])
ohet.fit(data)
# Assert
with np.testing.assert_raises(ValueError):
ohet.transform(['b'])
def test_one_hot_numerical_nans():
"""Ensure OneHotEncodingTransformer works on numerical + nan only columns."""
data = pd.Series([1, 2, float('nan'), np.nan])
transformer = OneHotEncodingTransformer()
transformer.fit(data)
transformed = transformer.transform(data)
reverse = transformer.reverse_transform(transformed)
pd.testing.assert_series_equal(reverse, data)
def test_transform_single(self):
"""Test the ``transform`` on a single category.
In this test ``transform`` should return a column
filled with ones.
Input:
- Series with a single categorical value
Output:
- one-hot encoding of the input
"""
# Setup
ohet = OneHotEncodingTransformer()
data = pd.Series(['a', 'a', 'a'])
ohet.fit(data)
# Run
out = ohet.transform(data)
# Assert
expected = np.array([[1], [1], [1]])
np.testing.assert_array_equal(out, expected)
def test_transform_nans(self):
"""Test the ``transform`` with nans.
In this test ``transform`` should return an identity matrix
representing each item in the input as well as nans.
Input:
- Series with categorical values and nans
Output:
- one-hot encoding of the input
"""
# Setup
ohet = OneHotEncodingTransformer()
data = pd.Series(['a', 'b', None])
ohet.fit(data)
# Run
out = ohet.transform(data)
# Assert
expected = np.array([[1, 0, 0], [0, 1, 0], [0, 0, 1]])
np.testing.assert_array_equal(out, expected)