def test_user_enters_variables_and_max_value_imputation(df_na):
imputer = EndTailImputer(imputation_method="max",
tail="right",
fold=2,
variables=["Age", "Marks"])
imputer.fit(df_na)
assert imputer.imputer_dict_ == {"Age": 82.0, "Marks": 1.8}
def test_user_enters_variables_and_iqr_imputation_on_left_tail(df_na):
# test case 5: IQR + left tail
imputer = EndTailImputer(imputation_method="iqr",
tail="left",
fold=1.5,
variables=["Age", "Marks"])
imputer.fit(df_na)
assert imputer.imputer_dict_ == {"Age": -6.5, "Marks": 0.36249999999999993}
def test_automatically_select_variables_and_gaussian_imputation_on_left_tail(
df_na):
imputer = EndTailImputer(imputation_method="gaussian", tail="left", fold=3)
imputer.fit(df_na)
assert imputer.imputer_dict_ == {
"Age": -1.520509756212462,
"Marks": 0.04224051634034898,
}
def test_automatically_select_variables_and_gaussian_imputation_on_left_tail(
df_na):
imputer = EndTailImputer(imputation_method="gaussian", tail="left", fold=3)
imputer.fit(df_na)
imputer.imputer_dict_ = {
key: round(value, 3)
for (key, value) in imputer.imputer_dict_.items()
}
assert imputer.imputer_dict_ == {
"Age": -1.521,
"Marks": 0.042,
}