def test_non_numeric_errors(non_numeric_df):
# test col with all strings
X = non_numeric_df
# mean with all strings
strategies = {'A': {"impute_strategy": "mean"}}
with pytest.raises(ValueError,
match="Cannot use mean strategy with non-numeric data"):
transformer = PerColumnImputer(impute_strategies=strategies)
transformer.fit_transform(X)
with pytest.raises(ValueError,
match="Cannot use mean strategy with non-numeric data"):
transformer = PerColumnImputer(impute_strategies=strategies)
transformer.fit(X)
# median with all strings
strategies = {'B': {"impute_strategy": "median"}}
with pytest.raises(
ValueError,
match="Cannot use median strategy with non-numeric data"):
transformer = PerColumnImputer(impute_strategies=strategies)
transformer.fit_transform(X)
with pytest.raises(
ValueError,
match="Cannot use median strategy with non-numeric data"):
transformer = PerColumnImputer(impute_strategies=strategies)
transformer.fit(X)
def test_transform_drop_all_nan_columns():
X = pd.DataFrame({
"all_nan": [np.nan, np.nan, np.nan],
"some_nan": [np.nan, 1, 0],
"another_col": [0, 1, 2]
})
strategies = {
'all_nan': {
"impute_strategy": "most_frequent"
},
'some_nan': {
"impute_strategy": "most_frequent"
},
'another_col': {
"impute_strategy": "most_frequent"
}
}
transformer = PerColumnImputer(impute_strategies=strategies)
transformer.fit(X)
X_expected_arr = pd.DataFrame({
"some_nan": [0, 1, 0],
"another_col": [0, 1, 2]
})
assert_frame_equal(X_expected_arr,
transformer.transform(X),
check_dtype=False)
assert_frame_equal(
X,
pd.DataFrame({
"all_nan": [np.nan, np.nan, np.nan],
"some_nan": [np.nan, 1, 0],
"another_col": [0, 1, 2]
}))
def test_transform_drop_all_nan_columns_empty():
X = pd.DataFrame([[np.nan, np.nan, np.nan]])
strategies = {'0': {"impute_strategy": "most_frequent"}, }
transformer = PerColumnImputer(impute_strategies=strategies)
assert transformer.fit_transform(X).to_dataframe().empty
assert_frame_equal(X, pd.DataFrame([[np.nan, np.nan, np.nan]]))
strategies = {'0': {"impute_strategy": "most_frequent"}}
transformer = PerColumnImputer(impute_strategies=strategies)
transformer.fit(X)
assert transformer.transform(X).to_dataframe().empty
assert_frame_equal(X, pd.DataFrame([[np.nan, np.nan, np.nan]]))
def test_per_column_imputer_woodwork_custom_overrides_returned_by_components(X_df, has_nan):
y = pd.Series([1, 2, 1])
if has_nan:
X_df.iloc[len(X_df) - 1, 0] = np.nan
override_types = [Integer, Double, Categorical, NaturalLanguage, Boolean]
for logical_type in override_types:
try:
X = ww.DataTable(X_df, logical_types={0: logical_type})
except TypeError:
continue
imputer = PerColumnImputer()
imputer.fit(X, y)
transformed = imputer.transform(X, y)
assert isinstance(transformed, ww.DataTable)
assert transformed.logical_types == {0: logical_type}
def test_fit_transform():
X = pd.DataFrame([[2], [4], [6], [np.nan]])
X_expected = pd.DataFrame([[2], [4], [6], [4]])
X.columns = ['A']
X_expected.columns = ['A']
strategies = {'A': {"impute_strategy": "median"}}
transformer = PerColumnImputer(impute_strategies=strategies)
transformer.fit(X)
X_t = transformer.transform(X)
transformer = PerColumnImputer(impute_strategies=strategies)
X_fit_transform = transformer.fit_transform(X)
assert_frame_equal(X_t, X_fit_transform, check_dtype=False)