def test_passing_in_a_single_transform_returns_new_pipeline(self):
transform = OneHotVectorizer() << 'c0'
transform.fit(train_df)
combined_pipeline = Pipeline.combine_models(transform,
contains_predictor=False)
result = combined_pipeline.transform(test_df)
self.assertEqual(len(result), 3)
self.assertEqual(len(result.columns), 4)
self.assertTrue(result.columns[0].startswith('c0.'))
self.assertTrue(result.columns[1].startswith('c0.'))
self.assertTrue(isinstance(combined_pipeline, Pipeline))
def test_combine_transform_and_transform(self):
transform_1 = RangeFilter(min=0.0, max=4.5) << 'c2'
df = transform_1.fit_transform(train_df)
transform_2 = OneHotVectorizer() << 'c0'
transform_2.fit(df)
df = transform_1.transform(test_df)
result_1 = transform_2.transform(df)
combined_pipeline = Pipeline.combine_models(transform_1,
transform_2,
contains_predictor=False)
result_2 = combined_pipeline.transform(test_df)
self.assertTrue(result_1.equals(result_2))
def test_sparse_vector_column_combined_with_single_value_columns(self):
train_data = {'c0': [0, 1, 0, 3], 'c1': ['a', 'b', 'a', 'b']}
train_df = pd.DataFrame(train_data).astype({'c0': np.float32})
xf = OneHotVectorizer(columns={'c1': 'c1'})
xf.fit(train_df)
expected_result = xf.transform(train_df)
self.assertTrue(type(expected_result) == pd.DataFrame)
result = xf.transform(train_df, as_csr=True)
self.assertEqual(result.nnz, 6)
self.assertTrue(type(result) == csr_matrix)
result = pd.DataFrame(result.todense(), columns=['c0', 'c1.a', 'c1.b'])
self.assertTrue(result.equals(expected_result))
def test_sparse_vector_column(self):
train_data = {'c0': ['a', 'b', 'a', 'b'], 'c1': ['c', 'd', 'd', 'c']}
train_df = pd.DataFrame(train_data)
xf = OneHotVectorizer(columns={'c0': 'c0', 'c1': 'c1'})
xf.fit(train_df)
expected_result = xf.transform(train_df)
self.assertTrue(type(expected_result) == pd.DataFrame)
result = xf.transform(train_df, as_csr=True)
self.assertEqual(result.nnz, 8)
self.assertTrue(type(result) == csr_matrix)
result = pd.DataFrame(result.todense(),
columns=['c0.a', 'c0.b', 'c1.c', 'c1.d'])
self.assertTrue(result.equals(expected_result))
def test_fit_transform(self):
# data input (as a FileDataStream)
path = get_dataset('infert').as_filepath()
data = FileDataStream.read_csv(path)
# transform usage
xf = OneHotVectorizer(
columns={
'edu': 'education',
'in': 'induced',
'sp': 'spontaneous'})
# fit and transform
res1 = xf.fit_transform(data)
res2 = xf.fit(data).transform(data)
assert_frame_equal(res1, res2)
def test_syntax4_passing(self):
df, X, y = self.get_simple_df()
vec = OneHotVectorizer() << {'edu1': ['education']}
vec.fit(X)
res = vec.transform(X)
assert res.shape == (5, 5)