def test_aggregations_with_strings(df_vartypes):
transformer = MathFeatures(
variables=["Age", "Marks"],
func=["sum", "prod", "mean", "std", "max", "min"])
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"),
"sum_Age_Marks": [20.9, 21.8, 19.7, 18.6],
"prod_Age_Marks": [18.0, 16.8, 13.299999999999999, 10.799999999999999],
"mean_Age_Marks": [10.45, 10.9, 9.85, 9.3],
"std_Age_Marks": [
13.505739520663058,
14.28355697996826,
12.94005409571382,
12.303657992645928,
],
"max_Age_Marks": [20.0, 21.0, 19.0, 18.0],
"min_Age_Marks": [0.9, 0.8, 0.7, 0.6],
})
# transform params
pd.testing.assert_frame_equal(X, ref)
def test_get_feature_names_out(_varnames, _drop, df_vartypes):
# set up transformer
transformer = MathFeatures(
variables=["Age", "Marks"],
func=["sum", "mean"],
new_variables_names=_varnames,
drop_original=_drop,
)
# fit transformer
X = transformer.fit_transform(df_vartypes)
# assert functionality
assert list(
X.columns) == transformer.get_feature_names_out(input_features=None)
assert list(
X.columns) == transformer.get_feature_names_out(input_features=False)
if _varnames is not None:
assert _varnames == transformer.get_feature_names_out(
input_features=True)
else:
assert ["sum_Age_Marks", "mean_Age_Marks"
] == transformer.get_feature_names_out(input_features=True)
def test_no_error_when_null_values_in_variable(df_vartypes):
df_na = df_vartypes.copy()
df_na.loc[1, "Age"] = np.nan
transformer = MathFeatures(
variables=["Age", "Marks"],
func=["sum", "mean"],
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"),
"sum_Age_Marks": [20.9, 0.8, 19.7, 18.6],
"mean_Age_Marks": [10.45, 0.8, 9.85, 9.3],
})
# transform params
pd.testing.assert_frame_equal(X, ref)
def test_variable_names_when_df_cols_are_integers(df_numeric_columns):
transformer = MathFeatures(
variables=[2, 3], func=["sum", "prod", "mean", "std", "max", "min"])
X = transformer.fit_transform(df_numeric_columns)
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"),
"sum_2_3": [20.9, 21.8, 19.7, 18.6],
"prod_2_3": [18.0, 16.8, 13.299999999999999, 10.799999999999999],
"mean_2_3": [10.45, 10.9, 9.85, 9.3],
"std_2_3": [
13.505739520663058,
14.28355697996826,
12.94005409571382,
12.303657992645928,
],
"max_2_3": [20.0, 21.0, 19.0, 18.0],
"min_2_3": [0.9, 0.8, 0.7, 0.6],
})
pd.testing.assert_frame_equal(X, ref)
def test_one_mathematical_operation(df_vartypes):
transformer = MathFeatures(variables=["Age", "Marks"], func="sum")
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"),
"sum_Age_Marks": [20.9, 21.8, 19.7, 18.6],
})
pd.testing.assert_frame_equal(X, ref)
transformer = MathFeatures(variables=["Age", "Marks"], func=["sum"])
X = transformer.fit_transform(df_vartypes)
pd.testing.assert_frame_equal(X, ref)
def test_drop_original_variables(df_vartypes):
transformer = MathFeatures(
variables=["Age", "Marks"],
func=["sum", "mean"],
drop_original=True,
)
X = transformer.fit_transform(df_vartypes)
ref = pd.DataFrame.from_dict({
"Name": ["tom", "nick", "krish", "jack"],
"City": ["London", "Manchester", "Liverpool", "Bristol"],
"dob":
pd.date_range("2020-02-24", periods=4, freq="T"),
"sum_Age_Marks": [20.9, 21.8, 19.7, 18.6],
"mean_Age_Marks": [10.45, 10.9, 9.85, 9.3],
})
pd.testing.assert_frame_equal(X, ref)