def _check_statistics(X, X_true, strategy, statistics, missing_values):
"""Utility function for testing imputation for a given strategy.
Test with dense and sparse arrays
Check that:
- the statistics (mean, median, mode) are correct
- the missing values are imputed correctly"""
err_msg = "Parameters: strategy = %s, missing_values = %s, " \
"sparse = {0}" % (strategy, missing_values)
assert_ae = assert_array_equal
if X.dtype.kind == 'f' or X_true.dtype.kind == 'f':
assert_ae = assert_array_almost_equal
# Normal matrix
imputer = SimpleImputer(missing_values, strategy=strategy)
X_trans = imputer.fit(X).transform(X.copy())
assert_ae(imputer.statistics_, statistics, err_msg=err_msg.format(False))
assert_ae(X_trans, X_true, err_msg=err_msg.format(False))
# Sparse matrix
imputer = SimpleImputer(missing_values, strategy=strategy)
imputer.fit(sparse.csc_matrix(X))
X_trans = imputer.transform(sparse.csc_matrix(X.copy()))
if sparse.issparse(X_trans):
X_trans = X_trans.toarray()
assert_ae(imputer.statistics_, statistics, err_msg=err_msg.format(True))
assert_ae(X_trans, X_true, err_msg=err_msg.format(True))
def test_imputation_error_sparse_0(strategy):
# check that error are raised when missing_values = 0 and input is sparse
X = np.ones((3, 5))
X[0] = 0
X = sparse.csc_matrix(X)
imputer = SimpleImputer(strategy=strategy, missing_values=0)
with pytest.raises(ValueError, match="Provide a dense array"):
imputer.fit(X)
imputer.fit(X.toarray())
with pytest.raises(ValueError, match="Provide a dense array"):
imputer.transform(X)
def test_imputation_const_mostf_error_invalid_types(strategy, dtype):
# Test imputation on non-numeric data using "most_frequent" and "constant"
# strategy
X = np.array([
[np.nan, np.nan, "a", "f"],
[np.nan, "c", np.nan, "d"],
[np.nan, "b", "d", np.nan],
[np.nan, "c", "d", "h"],
],
dtype=dtype)
err_msg = "SimpleImputer does not support data"
with pytest.raises(ValueError, match=err_msg):
imputer = SimpleImputer(strategy=strategy)
imputer.fit(X).transform(X)
def test_imputation_copy():
# Test imputation with copy
X_orig = sparse_random_matrix(5, 5, density=0.75, random_state=0)
# copy=True, dense => copy
X = X_orig.copy().toarray()
imputer = SimpleImputer(missing_values=0, strategy="mean", copy=True)
Xt = imputer.fit(X).transform(X)
Xt[0, 0] = -1
assert not np.all(X == Xt)
# copy=True, sparse csr => copy
X = X_orig.copy()
imputer = SimpleImputer(missing_values=X.data[0],
strategy="mean",
copy=True)
Xt = imputer.fit(X).transform(X)
Xt.data[0] = -1
assert not np.all(X.data == Xt.data)
# copy=False, dense => no copy
X = X_orig.copy().toarray()
imputer = SimpleImputer(missing_values=0, strategy="mean", copy=False)
Xt = imputer.fit(X).transform(X)
Xt[0, 0] = -1
assert_array_almost_equal(X, Xt)
# copy=False, sparse csc => no copy
X = X_orig.copy().tocsc()
imputer = SimpleImputer(missing_values=X.data[0],
strategy="mean",
copy=False)
Xt = imputer.fit(X).transform(X)
Xt.data[0] = -1
assert_array_almost_equal(X.data, Xt.data)
# copy=False, sparse csr => copy
X = X_orig.copy()
imputer = SimpleImputer(missing_values=X.data[0],
strategy="mean",
copy=False)
Xt = imputer.fit(X).transform(X)
Xt.data[0] = -1
assert not np.all(X.data == Xt.data)
def test_imputation_most_frequent_objects(marker):
# Test imputation using the most-frequent strategy.
X = np.array([
[marker, marker, "a", "f"],
[marker, "c", marker, "d"],
[marker, "b", "d", marker],
[marker, "c", "d", "h"],
],
dtype=object)
X_true = np.array([
["c", "a", "f"],
["c", "d", "d"],
["b", "d", "d"],
["c", "d", "h"],
],
dtype=object)
imputer = SimpleImputer(missing_values=marker, strategy="most_frequent")
X_trans = imputer.fit(X).transform(X)
assert_array_equal(X_trans, X_true)