def test_to_categorical_returns_correct_dataframe(categorical):
to_cat = ToCategorical()
result = to_cat.fit_transform(categorical)
expected_cols = [
'category_a_a1', 'category_a_a2', 'category_a_a3', 'category_b_b1',
'category_b_b2', 'category_b_b3'
]
assert isinstance(result, pd.DataFrame)
assert len(categorical) == len(result)
assert set(expected_cols) == set(result.columns)
for col in expected_cols:
assert pd.api.types.is_numeric_dtype(result[col])
def test_to_categorical_discards_unseen_values(categorical):
to_cat = ToCategorical()
to_cat.fit(categorical)
new_data = pd.DataFrame({
"category_a": ["a1", "a2", "ab1"],
"category_b": ["b1", "b2", "ab2"]
})
result = to_cat.transform(new_data)
expected_cols = [
'category_a_a1', 'category_a_a2', 'category_a_a3', 'category_b_b1',
'category_b_b2', 'category_b_b3'
]
assert isinstance(result, pd.DataFrame)
assert 0 == result.isna().sum().sum()
assert set(expected_cols) == set(result.columns)
def test_featureunion_returns_concatenated_df(categorical, numerical):
df = pd.concat([categorical, numerical], axis=1)
first_pipe = make_pipeline(Select(['category_a', 'category_b']),
ToCategorical())
union = DFFeatureUnion([('category', first_pipe),
('number', Select(['number_a', 'number_b']))])
transform_df = union.fit_transform(df)
assert isinstance(transform_df, pd.DataFrame)
assert 8 == len(transform_df.columns)
assert len(df) == len(transform_df)
def test_featureunion_returns_concatenated_df(self,
categorical: pd.DataFrame,
numerical: pd.DataFrame):
df = pd.concat([categorical, numerical], axis=1)
first_pipe = make_pipeline(Select(["category_a", "category_b"]),
ToCategorical())
union = DFFeatureUnion([("category", first_pipe),
("number", Select(["number_a", "number_b"]))])
transform_df = union.fit_transform(df)
assert isinstance(transform_df, pd.DataFrame)
assert 8 == len(transform_df.columns)
assert len(df) == len(transform_df)
"""
bed_type
========
What type of bed is available. Better bed should increase price
Type of bed
dtype: category
"""
from ml_tooling.transformers import Select, ToCategorical
from sklearn.pipeline import Pipeline
bed_type = Pipeline([("select", Select("bed_type")),
("categorical", ToCategorical())])
def test_works_without_args(self):
assert ToCategorical()
def test_to_categorical_works_gridsearch(self, train_iris_dataset):
grid = create_gridsearch(ToCategorical())
model = Model(grid)
result = model.score_estimator(train_iris_dataset)
assert isinstance(result, Result)
def test_to_categorical_works_in_cv(self, train_iris_dataset):
model = create_model(ToCategorical())
result = model.score_estimator(train_iris_dataset, cv=2)
assert isinstance(result, Result)