def test_error_if_input_df_contains_categories_not_present_in_fit_df(
df_enc, df_enc_rare):
# test case 3: when dataset to be transformed contains categories not present in
# training dataset
with pytest.warns(UserWarning):
encoder = CountFrequencyEncoder()
encoder.fit(df_enc)
encoder.transform(df_enc_rare)
def test_no_error_triggered_when_df_contains_unseen_categories_and_errors_is_encode(
df_enc, df_enc_rare
):
# dataset to be transformed contains categories not present in
# training dataset (unseen categories).
# check for no error and no warning when errors equals 'encode'
warnings.simplefilter("error")
encoder = CountFrequencyEncoder(errors="encode")
encoder.fit(df_enc)
with warnings.catch_warnings():
encoder.transform(df_enc_rare)
def test_warning_when_df_contains_unseen_categories(df_enc, df_enc_rare):
# dataset to be transformed contains categories not present in
# training dataset (unseen categories), errors set to ignore.
msg = "During the encoding, NaN values were introduced in the feature(s) var_A."
# check for warning when errors equals 'ignore'
encoder = CountFrequencyEncoder(errors="ignore")
encoder.fit(df_enc)
with pytest.warns(UserWarning) as record:
encoder.transform(df_enc_rare)
# check that only one warning was raised
assert len(record) == 1
# check that the message matches
assert record[0].message.args[0] == msg
def test_error_when_df_contains_unseen_categories(df_enc, df_enc_rare):
# dataset to be transformed contains categories not present in
# training dataset (unseen categories), errors set to raise.
msg = "During the encoding, NaN values were introduced in the feature(s) var_A."
encoder = CountFrequencyEncoder(errors="raise")
encoder.fit(df_enc)
# check for exception when errors equals 'raise'
with pytest.raises(ValueError) as record:
encoder.transform(df_enc_rare)
# check that the error message matches
assert str(record.value) == msg
# check for no error and no warning when errors equals 'encode'
with warnings.catch_warnings():
warnings.simplefilter("error")
encoder = CountFrequencyEncoder(errors="encode")
encoder.fit(df_enc)
encoder.transform(df_enc_rare)
def test_transform_raises_error_if_df_contains_na(df_enc, df_enc_na):
# test case 4: when dataset contains na, transform method
with pytest.raises(ValueError):
encoder = CountFrequencyEncoder()
encoder.fit(df_enc)
encoder.transform(df_enc_na)
def convertFromField36ToField40WithCountFrequencyEncoder(array):
dataFrame = pd.DataFrame(array[:, 44:49])
encoder = CountFrequencyEncoder(encoding_method='frequency')
encoder.fit(dataFrame)
encodedField36Field40 = encoder.transform(dataFrame)
array[:, 44:49] = encodedField36Field40
def test_fit_raises_error_if_df_contains_na(errors, df_enc_na):
# test case 4: when dataset contains na, fit method
encoder = CountFrequencyEncoder(errors=errors)
with pytest.raises(ValueError):
encoder.fit(df_enc_na)