def test_imputation_error_invalid_strategy(strategy):
X = np.ones((3, 5))
X[0, 0] = np.nan
with pytest.raises(ValueError, match=str(strategy)):
imputer = SimpleImputer(strategy=strategy)
imputer.fit_transform(X)
def test_imputation_deletion_warning(strategy):
X = np.ones((3, 5))
X[:, 0] = np.nan
with pytest.warns(UserWarning, match="Deleting"):
imputer = SimpleImputer(strategy=strategy, verbose=True)
imputer.fit_transform(X)
def test_imputation_mean_median_error_invalid_type(strategy, dtype):
X = np.array([["a", "b", 3],
[4, "e", 6],
["g", "h", 9]], dtype=dtype)
msg = "non-numeric data:\ncould not convert string to float: '"
with pytest.raises(ValueError, match=msg):
imputer = SimpleImputer(strategy=strategy)
imputer.fit_transform(X)
def test_imputation_constant_error_invalid_type(X_data, missing_value):
# Verify that exceptions are raised on invalid fill_value type
X = np.full((3, 5), X_data, dtype=float)
X[0, 0] = missing_value
with pytest.raises(ValueError, match="imputing numerical"):
imputer = SimpleImputer(missing_values=missing_value,
strategy="constant",
fill_value="x")
imputer.fit_transform(X)
def test_imputation_mean_median_error_invalid_type_list_pandas(strategy, type):
X = [["a", "b", 3],
[4, "e", 6],
["g", "h", 9]]
if type == 'dataframe':
pd = pytest.importorskip("pandas")
X = pd.DataFrame(X)
msg = "non-numeric data:\ncould not convert string to float: '"
with pytest.raises(ValueError, match=msg):
imputer = SimpleImputer(strategy=strategy)
imputer.fit_transform(X)
def test_imputation_shape(strategy):
# Verify the shapes of the imputed matrix for different strategies.
X = np.random.randn(10, 2)
X[::2] = np.nan
imputer = SimpleImputer(strategy=strategy)
X_imputed = imputer.fit_transform(sparse.csr_matrix(X))
assert X_imputed.shape == (10, 2)
X_imputed = imputer.fit_transform(X)
assert X_imputed.shape == (10, 2)
iterative_imputer = IterativeImputer(initial_strategy=strategy)
X_imputed = iterative_imputer.fit_transform(X)
assert X_imputed.shape == (10, 2)
def test_simple_imputation_add_indicator_sparse_matrix(arr_type):
X_sparse = arr_type([
[np.nan, 1, 5],
[2, np.nan, 1],
[6, 3, np.nan],
[1, 2, 9]
])
X_true = np.array([
[3., 1., 5., 1., 0., 0.],
[2., 2., 1., 0., 1., 0.],
[6., 3., 5., 0., 0., 1.],
[1., 2., 9., 0., 0., 0.],
])
imputer = SimpleImputer(missing_values=np.nan, add_indicator=True)
X_trans = imputer.fit_transform(X_sparse)
assert sparse.issparse(X_trans)
assert X_trans.shape == X_true.shape
assert_allclose(X_trans.toarray(), X_true)
def test_imputation_constant_object(marker):
# Test imputation using the constant strategy on objects
X = np.array([
[marker, "a", "b", marker],
["c", marker, "d", marker],
["e", "f", marker, marker],
["g", "h", "i", marker]
], dtype=object)
X_true = np.array([
["missing", "a", "b", "missing"],
["c", "missing", "d", "missing"],
["e", "f", "missing", "missing"],
["g", "h", "i", "missing"]
], dtype=object)
imputer = SimpleImputer(missing_values=marker, strategy="constant",
fill_value="missing")
X_trans = imputer.fit_transform(X)
assert_array_equal(X_trans, X_true)
def test_imputation_constant_integer():
# Test imputation using the constant strategy on integers
X = np.array([
[-1, 2, 3, -1],
[4, -1, 5, -1],
[6, 7, -1, -1],
[8, 9, 0, -1]
])
X_true = np.array([
[0, 2, 3, 0],
[4, 0, 5, 0],
[6, 7, 0, 0],
[8, 9, 0, 0]
])
imputer = SimpleImputer(missing_values=-1, strategy="constant",
fill_value=0)
X_trans = imputer.fit_transform(X)
assert_array_equal(X_trans, X_true)
def test_imputation_constant_pandas(dtype):
# Test imputation using the constant strategy on pandas df
pd = pytest.importorskip("pandas")
f = io.StringIO("Cat1,Cat2,Cat3,Cat4\n"
",i,x,\n"
"a,,y,\n"
"a,j,,\n"
"b,j,x,")
df = pd.read_csv(f, dtype=dtype)
X_true = np.array([
["missing_value", "i", "x", "missing_value"],
["a", "missing_value", "y", "missing_value"],
["a", "j", "missing_value", "missing_value"],
["b", "j", "x", "missing_value"]
], dtype=object)
imputer = SimpleImputer(strategy="constant")
X_trans = imputer.fit_transform(df)
assert_array_equal(X_trans, X_true)
def test_imputation_constant_float(array_constructor):
# Test imputation using the constant strategy on floats
X = np.array([
[np.nan, 1.1, 0, np.nan],
[1.2, np.nan, 1.3, np.nan],
[0, 0, np.nan, np.nan],
[1.4, 1.5, 0, np.nan]
])
X_true = np.array([
[-1, 1.1, 0, -1],
[1.2, -1, 1.3, -1],
[0, 0, -1, -1],
[1.4, 1.5, 0, -1]
])
X = array_constructor(X)
X_true = array_constructor(X_true)
imputer = SimpleImputer(strategy="constant", fill_value=-1)
X_trans = imputer.fit_transform(X)
assert_allclose_dense_sparse(X_trans, X_true)