def test_multiple_operations_with_multiple_variables(df_vartypes):
transformer = RelativeFeatures(
variables=["Age", "Marks"],
reference=["Age", "Marks"],
func=["sub", "add"],
)
X = transformer.fit_transform(df_vartypes)
ref = pd.DataFrame.from_dict({
"Name": ["tom", "nick", "krish", "jack"],
"City": ["London", "Manchester", "Liverpool", "Bristol"],
"Age": [20, 21, 19, 18],
"Marks": [0.9, 0.8, 0.7, 0.6],
"dob":
pd.date_range("2020-02-24", periods=4, freq="T"),
"Age_sub_Age": [0, 0, 0, 0],
"Marks_sub_Age": [-19.1, -20.2, -18.3, -17.4],
"Age_sub_Marks": [19.1, 20.2, 18.3, 17.4],
"Marks_sub_Marks": [0.0, 0.0, 0.0, 0.0],
"Age_add_Age": [40, 42, 38, 36],
"Marks_add_Age": [20.9, 21.8, 19.7, 18.6],
"Age_add_Marks": [20.9, 21.8, 19.7, 18.6],
"Marks_add_Marks": [1.8, 1.6, 1.4, 1.2],
})
pd.testing.assert_frame_equal(X, ref)
transformer = RelativeFeatures(
variables=["Age", "Marks"],
reference=["Age", "Marks"],
func=["add", "sub"],
)
X = transformer.fit_transform(df_vartypes)
ref = pd.DataFrame.from_dict({
"Name": ["tom", "nick", "krish", "jack"],
"City": ["London", "Manchester", "Liverpool", "Bristol"],
"Age": [20, 21, 19, 18],
"Marks": [0.9, 0.8, 0.7, 0.6],
"dob":
pd.date_range("2020-02-24", periods=4, freq="T"),
"Age_add_Age": [40, 42, 38, 36],
"Marks_add_Age": [20.9, 21.8, 19.7, 18.6],
"Age_add_Marks": [20.9, 21.8, 19.7, 18.6],
"Marks_add_Marks": [1.8, 1.6, 1.4, 1.2],
"Age_sub_Age": [0, 0, 0, 0],
"Marks_sub_Age": [-19.1, -20.2, -18.3, -17.4],
"Age_sub_Marks": [19.1, 20.2, 18.3, 17.4],
"Marks_sub_Marks": [0.0, 0.0, 0.0, 0.0],
})
pd.testing.assert_frame_equal(X, ref)
def test_error_when_entered_variables_not_in_df(df_vartypes):
transformer = RelativeFeatures(
variables=["FeatOutsideDataset", "Age"],
reference=["Age", "Name"],
func=["sub"],
)
with pytest.raises(KeyError):
transformer.fit_transform(df_vartypes)
transformer = RelativeFeatures(
reference=["FeatOutsideDataset", "Age"],
variables=["Age", "Name"],
func=["sub"],
)
with pytest.raises(TypeError):
transformer.fit_transform(df_vartypes)
def test_error_when_variables_not_numeric(df_vartypes):
transformer = RelativeFeatures(
variables=["Name", "Age", "Marks"],
reference=["Age", "Name"],
func=["sub"],
)
with pytest.raises(TypeError):
transformer.fit_transform(df_vartypes)
transformer = RelativeFeatures(
reference=["Name", "Age", "Marks"],
variables=["Age", "Name"],
func=["sub"],
)
with pytest.raises(TypeError):
transformer.fit_transform(df_vartypes)
def test_when_df_cols_are_integers(df_vartypes):
df = df_vartypes.copy()
df.columns = [0, 1, 2, 3, 4]
transformer = RelativeFeatures(
variables=[2, 3],
reference=[2, 3],
func=["sub", "add"],
)
X = transformer.fit_transform(df)
ref = pd.DataFrame.from_dict({
0: ["tom", "nick", "krish", "jack"],
1: ["London", "Manchester", "Liverpool", "Bristol"],
2: [20, 21, 19, 18],
3: [0.9, 0.8, 0.7, 0.6],
4:
pd.date_range("2020-02-24", periods=4, freq="T"),
"2_sub_2": [0, 0, 0, 0],
"3_sub_2": [-19.1, -20.2, -18.3, -17.4],
"2_sub_3": [19.1, 20.2, 18.3, 17.4],
"3_sub_3": [0.0, 0.0, 0.0, 0.0],
"2_add_2": [40, 42, 38, 36],
"3_add_2": [20.9, 21.8, 19.7, 18.6],
"2_add_3": [20.9, 21.8, 19.7, 18.6],
"3_add_3": [1.8, 1.6, 1.4, 1.2],
})
pd.testing.assert_frame_equal(X, ref)
def test_when_missing_values_is_ignore(df_vartypes):
df_na = df_vartypes.copy()
df_na.loc[1, "Age"] = np.nan
transformer = RelativeFeatures(
variables=["Age", "Marks"],
reference=["Age", "Marks"],
func=["sub"],
missing_values="ignore",
)
X = transformer.fit_transform(df_na)
ref = pd.DataFrame.from_dict({
"Name": ["tom", "nick", "krish", "jack"],
"City": ["London", "Manchester", "Liverpool", "Bristol"],
"Age": [20, np.nan, 19, 18],
"Marks": [0.9, 0.8, 0.7, 0.6],
"dob":
pd.date_range("2020-02-24", periods=4, freq="T"),
"Age_sub_Age": [0, np.nan, 0, 0],
"Marks_sub_Age": [-19.1, np.nan, -18.3, -17.4],
"Age_sub_Marks": [19.1, np.nan, 18.3, 17.4],
"Marks_sub_Marks": [0.0, 0.0, 0.0, 0.0],
})
pd.testing.assert_frame_equal(X, ref)
def test_alternative_operation(df_vartypes):
# input df
df = df_vartypes.copy()
# Expected result
dft = df.copy()
dft["Age_truediv_Marks"] = dft["Age"].truediv(dft["Marks"])
dft["Age_floordiv_Marks"] = dft["Age"].floordiv(dft["Marks"])
dft["Age_mod_Marks"] = dft["Age"].mod(dft["Marks"])
dft["Age_pow_Marks"] = dft["Age"].pow(dft["Marks"])
transformer = RelativeFeatures(
variables=["Age"],
reference=["Marks"],
func=["truediv", "floordiv", "mod", "pow"],
)
X = transformer.fit_transform(df)
pd.testing.assert_frame_equal(X, dft)
def test_get_feature_names_out(_drop, df_vartypes):
transformer = RelativeFeatures(
variables=["Age", "Marks"],
reference=["Age", "Marks"],
func=["add", "sub"],
drop_original=_drop,
)
varnames = [
"Age_add_Age",
"Marks_add_Age",
"Age_add_Marks",
"Marks_add_Marks",
"Age_sub_Age",
"Marks_sub_Age",
"Age_sub_Marks",
"Marks_sub_Marks",
]
X = transformer.fit_transform(df_vartypes)
assert list(
X.columns) == transformer.get_feature_names_out(input_features=None)
assert list(
X.columns) == transformer.get_feature_names_out(input_features=False)
assert varnames == transformer.get_feature_names_out(input_features=True)
def test_classic_binary_operation(df_vartypes):
transformer = RelativeFeatures(
variables=["Age"],
reference=["Marks"],
func=["sub", "div", "add", "mul"],
)
X = transformer.fit_transform(df_vartypes)
ref = pd.DataFrame.from_dict({
"Name": ["tom", "nick", "krish", "jack"],
"City": ["London", "Manchester", "Liverpool", "Bristol"],
"Age": [20, 21, 19, 18],
"Marks": [0.9, 0.8, 0.7, 0.6],
"dob":
pd.date_range("2020-02-24", periods=4, freq="T"),
"Age_sub_Marks": [19.1, 20.2, 18.3, 17.4],
"Age_div_Marks": [22.22222222222222, 26.25, 27.142857142857146, 30.0],
"Age_add_Marks": [20.9, 21.8, 19.7, 18.6],
"Age_mul_Marks": [18.0, 16.8, 13.299999999999999, 10.799999999999999],
})
pd.testing.assert_frame_equal(X, ref)
