Python IterativeImputer.transform方法代码示例

# 需要导入模块: from sklearn.impute import IterativeImputer [as 别名]
# 或者: from sklearn.impute.IterativeImputer import transform [as 别名]
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)

# 需要导入模块: from sklearn.impute import IterativeImputer [as 别名]
# 或者: from sklearn.impute.IterativeImputer import transform [as 别名]
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)

# 需要导入模块: from sklearn.impute import IterativeImputer [as 别名]
# 或者: from sklearn.impute.IterativeImputer import transform [as 别名]
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"

# 需要导入模块: from sklearn.impute import IterativeImputer [as 别名]
# 或者: from sklearn.impute.IterativeImputer import transform [as 别名]
def test_iterative_imputer_transform_stochasticity():
    pytest.importorskip("scipy", minversion="0.17.0")
    rng1 = np.random.RandomState(0)
    rng2 = np.random.RandomState(1)
    n = 100
    d = 10
    X = sparse_random_matrix(n, d, density=0.10,
                             random_state=rng1).toarray()

    # when sample_posterior=True, two transforms shouldn't be equal
    imputer = IterativeImputer(missing_values=0,
                               max_iter=1,
                               sample_posterior=True,
                               random_state=rng1)
    imputer.fit(X)

    X_fitted_1 = imputer.transform(X)
    X_fitted_2 = imputer.transform(X)

    # sufficient to assert that the means are not the same
    assert np.mean(X_fitted_1) != pytest.approx(np.mean(X_fitted_2))

    # when sample_posterior=False, and n_nearest_features=None
    # and imputation_order is not random
    # the two transforms should be identical even if rng are different
    imputer1 = IterativeImputer(missing_values=0,
                                max_iter=1,
                                sample_posterior=False,
                                n_nearest_features=None,
                                imputation_order='ascending',
                                random_state=rng1)

    imputer2 = IterativeImputer(missing_values=0,
                                max_iter=1,
                                sample_posterior=False,
                                n_nearest_features=None,
                                imputation_order='ascending',
                                random_state=rng2)
    imputer1.fit(X)
    imputer2.fit(X)

    X_fitted_1a = imputer1.transform(X)
    X_fitted_1b = imputer1.transform(X)
    X_fitted_2 = imputer2.transform(X)

    assert_allclose(X_fitted_1a, X_fitted_1b)
    assert_allclose(X_fitted_1a, X_fitted_2)

# 需要导入模块: from sklearn.impute import IterativeImputer [as 别名]
# 或者: from sklearn.impute.IterativeImputer import transform [as 别名]
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))

# 需要导入模块: from sklearn.impute import IterativeImputer [as 别名]
# 或者: from sklearn.impute.IterativeImputer import transform [as 别名]
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])

# 需要导入模块: from sklearn.impute import IterativeImputer [as 别名]
# 或者: from sklearn.impute.IterativeImputer import transform [as 别名]
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)