File size: 7,610 Bytes
7885a28 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 |
import numpy as np
import pytest
from sklearn.experimental import enable_iterative_imputer # noqa
from sklearn.impute import IterativeImputer, KNNImputer, SimpleImputer
from sklearn.utils._testing import (
assert_allclose,
assert_allclose_dense_sparse,
assert_array_equal,
)
from sklearn.utils.fixes import CSR_CONTAINERS
def imputers():
return [IterativeImputer(tol=0.1), KNNImputer(), SimpleImputer()]
def sparse_imputers():
return [SimpleImputer()]
# ConvergenceWarning will be raised by the IterativeImputer
@pytest.mark.filterwarnings("ignore::sklearn.exceptions.ConvergenceWarning")
@pytest.mark.parametrize("imputer", imputers(), ids=lambda x: x.__class__.__name__)
def test_imputation_missing_value_in_test_array(imputer):
# [Non Regression Test for issue #13968] Missing value in test set should
# not throw an error and return a finite dataset
train = [[1], [2]]
test = [[3], [np.nan]]
imputer.set_params(add_indicator=True)
imputer.fit(train).transform(test)
# ConvergenceWarning will be raised by the IterativeImputer
@pytest.mark.filterwarnings("ignore::sklearn.exceptions.ConvergenceWarning")
@pytest.mark.parametrize("marker", [np.nan, -1, 0])
@pytest.mark.parametrize("imputer", imputers(), ids=lambda x: x.__class__.__name__)
def test_imputers_add_indicator(marker, imputer):
X = np.array(
[
[marker, 1, 5, marker, 1],
[2, marker, 1, marker, 2],
[6, 3, marker, marker, 3],
[1, 2, 9, marker, 4],
]
)
X_true_indicator = np.array(
[
[1.0, 0.0, 0.0, 1.0],
[0.0, 1.0, 0.0, 1.0],
[0.0, 0.0, 1.0, 1.0],
[0.0, 0.0, 0.0, 1.0],
]
)
imputer.set_params(missing_values=marker, add_indicator=True)
X_trans = imputer.fit_transform(X)
assert_allclose(X_trans[:, -4:], X_true_indicator)
assert_array_equal(imputer.indicator_.features_, np.array([0, 1, 2, 3]))
imputer.set_params(add_indicator=False)
X_trans_no_indicator = imputer.fit_transform(X)
assert_allclose(X_trans[:, :-4], X_trans_no_indicator)
# ConvergenceWarning will be raised by the IterativeImputer
@pytest.mark.filterwarnings("ignore::sklearn.exceptions.ConvergenceWarning")
@pytest.mark.parametrize("marker", [np.nan, -1])
@pytest.mark.parametrize(
"imputer", sparse_imputers(), ids=lambda x: x.__class__.__name__
)
@pytest.mark.parametrize("csr_container", CSR_CONTAINERS)
def test_imputers_add_indicator_sparse(imputer, marker, csr_container):
X = csr_container(
[
[marker, 1, 5, marker, 1],
[2, marker, 1, marker, 2],
[6, 3, marker, marker, 3],
[1, 2, 9, marker, 4],
]
)
X_true_indicator = csr_container(
[
[1.0, 0.0, 0.0, 1.0],
[0.0, 1.0, 0.0, 1.0],
[0.0, 0.0, 1.0, 1.0],
[0.0, 0.0, 0.0, 1.0],
]
)
imputer.set_params(missing_values=marker, add_indicator=True)
X_trans = imputer.fit_transform(X)
assert_allclose_dense_sparse(X_trans[:, -4:], X_true_indicator)
assert_array_equal(imputer.indicator_.features_, np.array([0, 1, 2, 3]))
imputer.set_params(add_indicator=False)
X_trans_no_indicator = imputer.fit_transform(X)
assert_allclose_dense_sparse(X_trans[:, :-4], X_trans_no_indicator)
# ConvergenceWarning will be raised by the IterativeImputer
@pytest.mark.filterwarnings("ignore::sklearn.exceptions.ConvergenceWarning")
@pytest.mark.parametrize("imputer", imputers(), ids=lambda x: x.__class__.__name__)
@pytest.mark.parametrize("add_indicator", [True, False])
def test_imputers_pandas_na_integer_array_support(imputer, add_indicator):
# Test pandas IntegerArray with pd.NA
pd = pytest.importorskip("pandas")
marker = np.nan
imputer = imputer.set_params(add_indicator=add_indicator, missing_values=marker)
X = np.array(
[
[marker, 1, 5, marker, 1],
[2, marker, 1, marker, 2],
[6, 3, marker, marker, 3],
[1, 2, 9, marker, 4],
]
)
# fit on numpy array
X_trans_expected = imputer.fit_transform(X)
# Creates dataframe with IntegerArrays with pd.NA
X_df = pd.DataFrame(X, dtype="Int16", columns=["a", "b", "c", "d", "e"])
# fit on pandas dataframe with IntegerArrays
X_trans = imputer.fit_transform(X_df)
assert_allclose(X_trans_expected, X_trans)
@pytest.mark.parametrize("imputer", imputers(), ids=lambda x: x.__class__.__name__)
@pytest.mark.parametrize("add_indicator", [True, False])
def test_imputers_feature_names_out_pandas(imputer, add_indicator):
"""Check feature names out for imputers."""
pd = pytest.importorskip("pandas")
marker = np.nan
imputer = imputer.set_params(add_indicator=add_indicator, missing_values=marker)
X = np.array(
[
[marker, 1, 5, 3, marker, 1],
[2, marker, 1, 4, marker, 2],
[6, 3, 7, marker, marker, 3],
[1, 2, 9, 8, marker, 4],
]
)
X_df = pd.DataFrame(X, columns=["a", "b", "c", "d", "e", "f"])
imputer.fit(X_df)
names = imputer.get_feature_names_out()
if add_indicator:
expected_names = [
"a",
"b",
"c",
"d",
"f",
"missingindicator_a",
"missingindicator_b",
"missingindicator_d",
"missingindicator_e",
]
assert_array_equal(expected_names, names)
else:
expected_names = ["a", "b", "c", "d", "f"]
assert_array_equal(expected_names, names)
@pytest.mark.parametrize("keep_empty_features", [True, False])
@pytest.mark.parametrize("imputer", imputers(), ids=lambda x: x.__class__.__name__)
def test_keep_empty_features(imputer, keep_empty_features):
"""Check that the imputer keeps features with only missing values."""
X = np.array([[np.nan, 1], [np.nan, 2], [np.nan, 3]])
imputer = imputer.set_params(
add_indicator=False, keep_empty_features=keep_empty_features
)
for method in ["fit_transform", "transform"]:
X_imputed = getattr(imputer, method)(X)
if keep_empty_features:
assert X_imputed.shape == X.shape
else:
assert X_imputed.shape == (X.shape[0], X.shape[1] - 1)
@pytest.mark.parametrize("imputer", imputers(), ids=lambda x: x.__class__.__name__)
@pytest.mark.parametrize("missing_value_test", [np.nan, 1])
def test_imputation_adds_missing_indicator_if_add_indicator_is_true(
imputer, missing_value_test
):
"""Check that missing indicator always exists when add_indicator=True.
Non-regression test for gh-26590.
"""
X_train = np.array([[0, np.nan], [1, 2]])
# Test data where missing_value_test variable can be set to np.nan or 1.
X_test = np.array([[0, missing_value_test], [1, 2]])
imputer.set_params(add_indicator=True)
imputer.fit(X_train)
X_test_imputed_with_indicator = imputer.transform(X_test)
assert X_test_imputed_with_indicator.shape == (2, 3)
imputer.set_params(add_indicator=False)
imputer.fit(X_train)
X_test_imputed_without_indicator = imputer.transform(X_test)
assert X_test_imputed_without_indicator.shape == (2, 2)
assert_allclose(
X_test_imputed_with_indicator[:, :-1], X_test_imputed_without_indicator
)
if np.isnan(missing_value_test):
expected_missing_indicator = [1, 0]
else:
expected_missing_indicator = [0, 0]
assert_allclose(X_test_imputed_with_indicator[:, -1], expected_missing_indicator)
|