Python impute.IterativeImputer类代码示例

def test_iterative_imputer_additive_matrix():
    rng = np.random.RandomState(0)
    n = 100
    d = 10
    A = rng.randn(n, d)
    B = rng.randn(n, d)
    X_filled = np.zeros(A.shape)
    for i in range(d):
        for j in range(d):
            X_filled[:, (i+j) % d] += (A[:, i] + B[:, j]) / 2
    # a quarter is randomly missing
    nan_mask = rng.rand(n, d) < 0.25
    X_missing = X_filled.copy()
    X_missing[nan_mask] = np.nan

    # split up data
    n = n // 2
    X_train = X_missing[:n]
    X_test_filled = X_filled[n:]
    X_test = X_missing[n:]

    imputer = IterativeImputer(max_iter=10,
                               verbose=1,
                               random_state=rng).fit(X_train)
    X_test_est = imputer.transform(X_test)
    assert_allclose(X_test_filled, X_test_est, rtol=1e-3, atol=0.01)

def test_iterative_imputer_imputation_order(imputation_order):
    rng = np.random.RandomState(0)
    n = 100
    d = 10
    max_iter = 2
    X = sparse_random_matrix(n, d, density=0.10, random_state=rng).toarray()
    X[:, 0] = 1  # this column should not be discarded by IterativeImputer

    imputer = IterativeImputer(missing_values=0,
                               max_iter=max_iter,
                               n_nearest_features=5,
                               sample_posterior=False,
                               min_value=0,
                               max_value=1,
                               verbose=1,
                               imputation_order=imputation_order,
                               random_state=rng)
    imputer.fit_transform(X)
    ordered_idx = [i.feat_idx for i in imputer.imputation_sequence_]

    assert (len(ordered_idx) // imputer.n_iter_ ==
            imputer.n_features_with_missing_)

    if imputation_order == 'roman':
        assert np.all(ordered_idx[:d-1] == np.arange(1, d))
    elif imputation_order == 'arabic':
        assert np.all(ordered_idx[:d-1] == np.arange(d-1, 0, -1))
    elif imputation_order == 'random':
        ordered_idx_round_1 = ordered_idx[:d-1]
        ordered_idx_round_2 = ordered_idx[d-1:]
        assert ordered_idx_round_1 != ordered_idx_round_2
    elif 'ending' in imputation_order:
        assert len(ordered_idx) == max_iter * (d - 1)

def test_iterative_imputer_all_missing():
    n = 100
    d = 3
    X = np.zeros((n, d))
    imputer = IterativeImputer(missing_values=0, max_iter=1)
    X_imputed = imputer.fit_transform(X)
    assert_allclose(X_imputed, imputer.initial_imputer_.transform(X))

def test_iterative_imputer_truncated_normal_posterior():
    #  test that the values that are imputed using `sample_posterior=True`
    #  with boundaries (`min_value` and `max_value` are not None) are drawn
    #  from a distribution that looks gaussian via the Kolmogorov Smirnov test.
    #  note that starting from the wrong random seed will make this test fail
    #  because random sampling doesn't occur at all when the imputation
    #  is outside of the (min_value, max_value) range
    pytest.importorskip("scipy", minversion="0.17.0")
    rng = np.random.RandomState(42)

    X = rng.normal(size=(5, 5))
    X[0][0] = np.nan

    imputer = IterativeImputer(min_value=0,
                               max_value=0.5,
                               sample_posterior=True,
                               random_state=rng)

    imputer.fit_transform(X)
    # generate multiple imputations for the single missing value
    imputations = np.array([imputer.transform(X)[0][0] for _ in range(100)])

    assert all(imputations >= 0)
    assert all(imputations <= 0.5)

    mu, sigma = imputations.mean(), imputations.std()
    ks_statistic, p_value = kstest((imputations - mu) / sigma, 'norm')
    if sigma == 0:
        sigma += 1e-12
    ks_statistic, p_value = kstest((imputations - mu) / sigma, 'norm')
    # we want to fail to reject null hypothesis
    # null hypothesis: distributions are the same
    assert ks_statistic < 0.2 or p_value > 0.1, \
        "The posterior does appear to be normal"

def test_iterative_imputer_verbose():
    rng = np.random.RandomState(0)

    n = 100
    d = 3
    X = sparse_random_matrix(n, d, density=0.10, random_state=rng).toarray()
    imputer = IterativeImputer(missing_values=0, max_iter=1, verbose=1)
    imputer.fit(X)
    imputer.transform(X)
    imputer = IterativeImputer(missing_values=0, max_iter=1, verbose=2)
    imputer.fit(X)
    imputer.transform(X)

def test_iterative_imputer_no_missing():
    rng = np.random.RandomState(0)
    X = rng.rand(100, 100)
    X[:, 0] = np.nan
    m1 = IterativeImputer(max_iter=10, random_state=rng)
    m2 = IterativeImputer(max_iter=10, random_state=rng)
    pred1 = m1.fit(X).transform(X)
    pred2 = m2.fit_transform(X)
    # should exclude the first column entirely
    assert_allclose(X[:, 1:], pred1)
    # fit and fit_transform should both be identical
    assert_allclose(pred1, pred2)

def test_iterative_imputer_rank_one():
    rng = np.random.RandomState(0)
    d = 100
    A = rng.rand(d, 1)
    B = rng.rand(1, d)
    X = np.dot(A, B)
    nan_mask = rng.rand(d, d) < 0.5
    X_missing = X.copy()
    X_missing[nan_mask] = np.nan

    imputer = IterativeImputer(max_iter=5,
                               verbose=1,
                               random_state=rng)
    X_filled = imputer.fit_transform(X_missing)
    assert_allclose(X_filled, X, atol=0.01)

def test_imputation_shape():
    # Verify the shapes of the imputed matrix for different strategies.
    X = np.random.randn(10, 2)
    X[::2] = np.nan

    for strategy in ['mean', 'median', 'most_frequent', "constant"]:
        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_iterative_imputer_clip():
    rng = np.random.RandomState(0)
    n = 100
    d = 10
    X = sparse_random_matrix(n, d, density=0.10,
                             random_state=rng).toarray()

    imputer = IterativeImputer(missing_values=0,
                               max_iter=1,
                               min_value=0.1,
                               max_value=0.2,
                               random_state=rng)

    Xt = imputer.fit_transform(X)
    assert_allclose(np.min(Xt[X == 0]), 0.1)
    assert_allclose(np.max(Xt[X == 0]), 0.2)
    assert_allclose(Xt[X != 0], X[X != 0])

def test_iterative_imputer_early_stopping():
    rng = np.random.RandomState(0)
    n = 50
    d = 5
    A = rng.rand(n, 1)
    B = rng.rand(1, d)
    X = np.dot(A, B)
    nan_mask = rng.rand(n, d) < 0.5
    X_missing = X.copy()
    X_missing[nan_mask] = np.nan

    imputer = IterativeImputer(max_iter=100,
                               tol=1e-3,
                               sample_posterior=False,
                               verbose=1,
                               random_state=rng)
    X_filled_100 = imputer.fit_transform(X_missing)
    assert len(imputer.imputation_sequence_) == d * imputer.n_iter_

    imputer = IterativeImputer(max_iter=imputer.n_iter_,
                               sample_posterior=False,
                               verbose=1,
                               random_state=rng)
    X_filled_early = imputer.fit_transform(X_missing)
    assert_allclose(X_filled_100, X_filled_early, atol=1e-7)

    imputer = IterativeImputer(max_iter=100,
                               tol=0,
                               sample_posterior=False,
                               verbose=1,
                               random_state=rng)
    imputer.fit(X_missing)
    assert imputer.n_iter_ == imputer.max_iter

def test_iterative_imputer_clip_truncnorm():
    rng = np.random.RandomState(0)
    n = 100
    d = 10
    X = sparse_random_matrix(n, d, density=0.10, random_state=rng).toarray()
    X[:, 0] = 1

    imputer = IterativeImputer(missing_values=0,
                               max_iter=2,
                               n_nearest_features=5,
                               sample_posterior=True,
                               min_value=0.1,
                               max_value=0.2,
                               verbose=1,
                               imputation_order='random',
                               random_state=rng)
    Xt = imputer.fit_transform(X)
    assert_allclose(np.min(Xt[X == 0]), 0.1)
    assert_allclose(np.max(Xt[X == 0]), 0.2)
    assert_allclose(Xt[X != 0], X[X != 0])

def test_iterative_imputer_missing_at_transform(strategy):
    rng = np.random.RandomState(0)
    n = 100
    d = 10
    X_train = rng.randint(low=0, high=3, size=(n, d))
    X_test = rng.randint(low=0, high=3, size=(n, d))

    X_train[:, 0] = 1  # definitely no missing values in 0th column
    X_test[0, 0] = 0  # definitely missing value in 0th column

    imputer = IterativeImputer(missing_values=0,
                               max_iter=1,
                               initial_strategy=strategy,
                               random_state=rng).fit(X_train)
    initial_imputer = SimpleImputer(missing_values=0,
                                    strategy=strategy).fit(X_train)

    # if there were no missing values at time of fit, then imputer will
    # only use the initial imputer for that feature at transform
    assert_allclose(imputer.transform(X_test)[:, 0],
                    initial_imputer.transform(X_test)[:, 0])

def test_iterative_imputer_transform_recovery(rank):
    rng = np.random.RandomState(0)
    n = 100
    d = 100
    A = rng.rand(n, rank)
    B = rng.rand(rank, d)
    X_filled = np.dot(A, B)
    nan_mask = rng.rand(n, d) < 0.5
    X_missing = X_filled.copy()
    X_missing[nan_mask] = np.nan

    # split up data in half
    n = n // 2
    X_train = X_missing[:n]
    X_test_filled = X_filled[n:]
    X_test = X_missing[n:]

    imputer = IterativeImputer(max_iter=10,
                               verbose=1,
                               random_state=rng).fit(X_train)
    X_test_est = imputer.transform(X_test)
    assert_allclose(X_test_filled, X_test_est, atol=0.1)

def test_iterative_imputer_estimators(estimator):
    rng = np.random.RandomState(0)

    n = 100
    d = 10
    X = sparse_random_matrix(n, d, density=0.10, random_state=rng).toarray()

    imputer = IterativeImputer(missing_values=0,
                               max_iter=1,
                               estimator=estimator,
                               random_state=rng)
    imputer.fit_transform(X)

    # check that types are correct for estimators
    hashes = []
    for triplet in imputer.imputation_sequence_:
        expected_type = (type(estimator) if estimator is not None
                         else type(BayesianRidge()))
        assert isinstance(triplet.estimator, expected_type)
        hashes.append(id(triplet.estimator))

    # check that each estimator is unique
    assert len(set(hashes)) == len(hashes)

def test_iterative_imputer_zero_iters():
    rng = np.random.RandomState(0)

    n = 100
    d = 10
    X = sparse_random_matrix(n, d, density=0.10, random_state=rng).toarray()
    missing_flag = X == 0
    X[missing_flag] = np.nan

    imputer = IterativeImputer(max_iter=0)
    X_imputed = imputer.fit_transform(X)
    # with max_iter=0, only initial imputation is performed
    assert_allclose(X_imputed, imputer.initial_imputer_.transform(X))

    # repeat but force n_iter_ to 0
    imputer = IterativeImputer(max_iter=5).fit(X)
    # transformed should not be equal to initial imputation
    assert not np.all(imputer.transform(X) ==
                      imputer.initial_imputer_.transform(X))

    imputer.n_iter_ = 0
    # now they should be equal as only initial imputation is done
    assert_allclose(imputer.transform(X),
                    imputer.initial_imputer_.transform(X))