Python model_selection.LeavePGroupsOut方法代码示例

# 需要导入模块: from sklearn import model_selection [as 别名]
# 或者: from sklearn.model_selection import LeavePGroupsOut [as 别名]
def test_2d_y():
    # smoke test for 2d y and multi-label
    n_samples = 30
    rng = np.random.RandomState(1)
    X = rng.randint(0, 3, size=(n_samples, 2))
    y = rng.randint(0, 3, size=(n_samples,))
    y_2d = y.reshape(-1, 1)
    y_multilabel = rng.randint(0, 2, size=(n_samples, 3))
    groups = rng.randint(0, 3, size=(n_samples,))
    splitters = [LeaveOneOut(), LeavePOut(p=2), KFold(), StratifiedKFold(),
                 RepeatedKFold(), RepeatedStratifiedKFold(),
                 ShuffleSplit(), StratifiedShuffleSplit(test_size=.5),
                 GroupShuffleSplit(), LeaveOneGroupOut(),
                 LeavePGroupsOut(n_groups=2), GroupKFold(), TimeSeriesSplit(),
                 PredefinedSplit(test_fold=groups)]
    for splitter in splitters:
        list(splitter.split(X, y, groups))
        list(splitter.split(X, y_2d, groups))
        try:
            list(splitter.split(X, y_multilabel, groups))
        except ValueError as e:
            allowed_target_types = ('binary', 'multiclass')
            msg = "Supported target types are: {}. Got 'multilabel".format(
                allowed_target_types)
            assert msg in str(e) 

# 需要导入模块: from sklearn import model_selection [as 别名]
# 或者: from sklearn.model_selection import LeavePGroupsOut [as 别名]
def test_leave_group_out_changing_groups():
    # Check that LeaveOneGroupOut and LeavePGroupsOut work normally if
    # the groups variable is changed before calling split
    groups = np.array([0, 1, 2, 1, 1, 2, 0, 0])
    X = np.ones(len(groups))
    groups_changing = np.array(groups, copy=True)
    lolo = LeaveOneGroupOut().split(X, groups=groups)
    lolo_changing = LeaveOneGroupOut().split(X, groups=groups)
    lplo = LeavePGroupsOut(n_groups=2).split(X, groups=groups)
    lplo_changing = LeavePGroupsOut(n_groups=2).split(X, groups=groups)
    groups_changing[:] = 0
    for llo, llo_changing in [(lolo, lolo_changing), (lplo, lplo_changing)]:
        for (train, test), (train_chan, test_chan) in zip(llo, llo_changing):
            assert_array_equal(train, train_chan)
            assert_array_equal(test, test_chan)

    # n_splits = no of 2 (p) group combinations of the unique groups = 3C2 = 3
    assert_equal(
        3, LeavePGroupsOut(n_groups=2).get_n_splits(X, y=X,
                                                    groups=groups))
    # n_splits = no of unique groups (C(uniq_lbls, 1) = n_unique_groups)
    assert_equal(3, LeaveOneGroupOut().get_n_splits(X, y=X,
                                                    groups=groups)) 

# 需要导入模块: from sklearn import model_selection [as 别名]
# 或者: from sklearn.model_selection import LeavePGroupsOut [as 别名]
def test_leave_one_p_group_out_error_on_fewer_number_of_groups():
    X = y = groups = np.ones(0)
    assert_raise_message(ValueError, "Found array with 0 sample(s)", next,
                         LeaveOneGroupOut().split(X, y, groups))
    X = y = groups = np.ones(1)
    msg = ("The groups parameter contains fewer than 2 unique groups ({}). "
           "LeaveOneGroupOut expects at least 2.").format(groups)
    assert_raise_message(ValueError, msg, next,
                         LeaveOneGroupOut().split(X, y, groups))
    X = y = groups = np.ones(1)
    msg = ("The groups parameter contains fewer than (or equal to) n_groups "
           "(3) numbers of unique groups ({}). LeavePGroupsOut expects "
           "that at least n_groups + 1 (4) unique groups "
           "be present").format(groups)
    assert_raise_message(ValueError, msg, next,
                         LeavePGroupsOut(n_groups=3).split(X, y, groups))
    X = y = groups = np.arange(3)
    msg = ("The groups parameter contains fewer than (or equal to) n_groups "
           "(3) numbers of unique groups ({}). LeavePGroupsOut expects "
           "that at least n_groups + 1 (4) unique groups "
           "be present").format(groups)
    assert_raise_message(ValueError, msg, next,
                         LeavePGroupsOut(n_groups=3).split(X, y, groups)) 

# 需要导入模块: from sklearn import model_selection [as 别名]
# 或者: from sklearn.model_selection import LeavePGroupsOut [as 别名]
def test_cross_val_score_predict_groups():
    # Check if ValueError (when groups is None) propagates to cross_val_score
    # and cross_val_predict
    # And also check if groups is correctly passed to the cv object
    X, y = make_classification(n_samples=20, n_classes=2, random_state=0)

    clf = SVC(kernel="linear")

    group_cvs = [LeaveOneGroupOut(), LeavePGroupsOut(2), GroupKFold(),
                 GroupShuffleSplit()]
    for cv in group_cvs:
        assert_raise_message(ValueError,
                             "The 'groups' parameter should not be None.",
                             cross_val_score, estimator=clf, X=X, y=y, cv=cv)
        assert_raise_message(ValueError,
                             "The 'groups' parameter should not be None.",
                             cross_val_predict, estimator=clf, X=X, y=y, cv=cv) 

# 需要导入模块: from sklearn import model_selection [as 别名]
# 或者: from sklearn.model_selection import LeavePGroupsOut [as 别名]
def test_grid_search_groups():
    # Check if ValueError (when groups is None) propagates to GridSearchCV
    # And also check if groups is correctly passed to the cv object
    rng = np.random.RandomState(0)

    X, y = make_classification(n_samples=15, n_classes=2, random_state=0)
    groups = rng.randint(0, 3, 15)

    clf = LinearSVC(random_state=0)
    grid = {'C': [1]}

    group_cvs = [LeaveOneGroupOut(), LeavePGroupsOut(2), GroupKFold(),
                 GroupShuffleSplit()]
    for cv in group_cvs:
        gs = GridSearchCV(clf, grid, cv=cv)
        assert_raise_message(ValueError,
                             "The 'groups' parameter should not be None.",
                             gs.fit, X, y)
        gs.fit(X, y, groups=groups)

    non_group_cvs = [StratifiedKFold(), StratifiedShuffleSplit()]
    for cv in non_group_cvs:
        gs = GridSearchCV(clf, grid, cv=cv)
        # Should not raise an error
        gs.fit(X, y) 

# 需要导入模块: from sklearn import model_selection [as 别名]
# 或者: from sklearn.model_selection import LeavePGroupsOut [as 别名]
def test_objectmapper(self):
        df = pdml.ModelFrame([])

        # Splitter Classes
        self.assertIs(df.model_selection.KFold, ms.KFold)
        self.assertIs(df.model_selection.GroupKFold, ms.GroupKFold)
        self.assertIs(df.model_selection.StratifiedKFold, ms.StratifiedKFold)

        self.assertIs(df.model_selection.LeaveOneGroupOut, ms.LeaveOneGroupOut)
        self.assertIs(df.model_selection.LeavePGroupsOut, ms.LeavePGroupsOut)
        self.assertIs(df.model_selection.LeaveOneOut, ms.LeaveOneOut)
        self.assertIs(df.model_selection.LeavePOut, ms.LeavePOut)

        self.assertIs(df.model_selection.ShuffleSplit, ms.ShuffleSplit)
        self.assertIs(df.model_selection.GroupShuffleSplit,
                      ms.GroupShuffleSplit)
        # self.assertIs(df.model_selection.StratifiedShuffleSplit,
        #               ms.StratifiedShuffleSplit)
        self.assertIs(df.model_selection.PredefinedSplit, ms.PredefinedSplit)
        self.assertIs(df.model_selection.TimeSeriesSplit, ms.TimeSeriesSplit)

        # Splitter Functions

        # Hyper-parameter optimizers
        self.assertIs(df.model_selection.GridSearchCV, ms.GridSearchCV)
        self.assertIs(df.model_selection.RandomizedSearchCV, ms.RandomizedSearchCV)
        self.assertIs(df.model_selection.ParameterGrid, ms.ParameterGrid)
        self.assertIs(df.model_selection.ParameterSampler, ms.ParameterSampler)

        # Model validation 

# 需要导入模块: from sklearn import model_selection [as 别名]
# 或者: from sklearn.model_selection import LeavePGroupsOut [as 别名]
def test_objectmapper_abbr(self):
        df = pdml.ModelFrame([])

        # Splitter Classes
        self.assertIs(df.ms.KFold, ms.KFold)
        self.assertIs(df.ms.GroupKFold, ms.GroupKFold)
        self.assertIs(df.ms.StratifiedKFold, ms.StratifiedKFold)

        self.assertIs(df.ms.LeaveOneGroupOut, ms.LeaveOneGroupOut)
        self.assertIs(df.ms.LeavePGroupsOut, ms.LeavePGroupsOut)
        self.assertIs(df.ms.LeaveOneOut, ms.LeaveOneOut)
        self.assertIs(df.ms.LeavePOut, ms.LeavePOut)

        self.assertIs(df.ms.ShuffleSplit, ms.ShuffleSplit)
        self.assertIs(df.ms.GroupShuffleSplit,
                      ms.GroupShuffleSplit)
        # self.assertIs(df.ms.StratifiedShuffleSplit,
        #               ms.StratifiedShuffleSplit)
        self.assertIs(df.ms.PredefinedSplit, ms.PredefinedSplit)
        self.assertIs(df.ms.TimeSeriesSplit, ms.TimeSeriesSplit)

        # Splitter Functions

        # Hyper-parameter optimizers
        self.assertIs(df.ms.GridSearchCV, ms.GridSearchCV)
        self.assertIs(df.ms.RandomizedSearchCV, ms.RandomizedSearchCV)
        self.assertIs(df.ms.ParameterGrid, ms.ParameterGrid)
        self.assertIs(df.ms.ParameterSampler, ms.ParameterSampler)

        # Model validation 

# 需要导入模块: from sklearn import model_selection [as 别名]
# 或者: from sklearn.model_selection import LeavePGroupsOut [as 别名]
def split(self, X, y, groups):
        n_groups = self.get_n_splits(groups=groups)
        #print('n_groups', n_groups)
        lpgo = ms.LeavePGroupsOut(n_groups=n_groups-1)
        return lpgo.split(X, y, groups)

#class WithoutElement(BaseEstimator, TransformerMixin):
#    " Train the model without each element, then test on the rows with that element "
#    pass 

# 需要导入模块: from sklearn import model_selection [as 别名]
# 或者: from sklearn.model_selection import LeavePGroupsOut [as 别名]
def test_cross_validator_with_default_params():
    n_samples = 4
    n_unique_groups = 4
    n_splits = 2
    p = 2
    n_shuffle_splits = 10  # (the default value)

    X = np.array([[1, 2], [3, 4], [5, 6], [7, 8]])
    X_1d = np.array([1, 2, 3, 4])
    y = np.array([1, 1, 2, 2])
    groups = np.array([1, 2, 3, 4])
    loo = LeaveOneOut()
    lpo = LeavePOut(p)
    kf = KFold(n_splits)
    skf = StratifiedKFold(n_splits)
    lolo = LeaveOneGroupOut()
    lopo = LeavePGroupsOut(p)
    ss = ShuffleSplit(random_state=0)
    ps = PredefinedSplit([1, 1, 2, 2])  # n_splits = np of unique folds = 2

    loo_repr = "LeaveOneOut()"
    lpo_repr = "LeavePOut(p=2)"
    kf_repr = "KFold(n_splits=2, random_state=None, shuffle=False)"
    skf_repr = "StratifiedKFold(n_splits=2, random_state=None, shuffle=False)"
    lolo_repr = "LeaveOneGroupOut()"
    lopo_repr = "LeavePGroupsOut(n_groups=2)"
    ss_repr = ("ShuffleSplit(n_splits=10, random_state=0, "
               "test_size=None, train_size=None)")
    ps_repr = "PredefinedSplit(test_fold=array([1, 1, 2, 2]))"

    n_splits_expected = [n_samples, comb(n_samples, p), n_splits, n_splits,
                         n_unique_groups, comb(n_unique_groups, p),
                         n_shuffle_splits, 2]

    for i, (cv, cv_repr) in enumerate(zip(
            [loo, lpo, kf, skf, lolo, lopo, ss, ps],
            [loo_repr, lpo_repr, kf_repr, skf_repr, lolo_repr, lopo_repr,
             ss_repr, ps_repr])):
        # Test if get_n_splits works correctly
        assert_equal(n_splits_expected[i], cv.get_n_splits(X, y, groups))

        # Test if the cross-validator works as expected even if
        # the data is 1d
        np.testing.assert_equal(list(cv.split(X, y, groups)),
                                list(cv.split(X_1d, y, groups)))
        # Test that train, test indices returned are integers
        for train, test in cv.split(X, y, groups):
            assert_equal(np.asarray(train).dtype.kind, 'i')
            assert_equal(np.asarray(train).dtype.kind, 'i')

        # Test if the repr works without any errors
        assert_equal(cv_repr, repr(cv))

    # ValueError for get_n_splits methods
    msg = "The 'X' parameter should not be None."
    assert_raise_message(ValueError, msg,
                         loo.get_n_splits, None, y, groups)
    assert_raise_message(ValueError, msg,
                         lpo.get_n_splits, None, y, groups) 

# 需要导入模块: from sklearn import model_selection [as 别名]
# 或者: from sklearn.model_selection import LeavePGroupsOut [as 别名]
def test_leave_one_p_group_out():
    logo = LeaveOneGroupOut()
    lpgo_1 = LeavePGroupsOut(n_groups=1)
    lpgo_2 = LeavePGroupsOut(n_groups=2)

    # Make sure the repr works
    assert_equal(repr(logo), 'LeaveOneGroupOut()')
    assert_equal(repr(lpgo_1), 'LeavePGroupsOut(n_groups=1)')
    assert_equal(repr(lpgo_2), 'LeavePGroupsOut(n_groups=2)')
    assert_equal(repr(LeavePGroupsOut(n_groups=3)),
                 'LeavePGroupsOut(n_groups=3)')

    for j, (cv, p_groups_out) in enumerate(((logo, 1), (lpgo_1, 1),
                                            (lpgo_2, 2))):
        for i, groups_i in enumerate(test_groups):
            n_groups = len(np.unique(groups_i))
            n_splits = (n_groups if p_groups_out == 1
                        else n_groups * (n_groups - 1) / 2)
            X = y = np.ones(len(groups_i))

            # Test that the length is correct
            assert_equal(cv.get_n_splits(X, y, groups=groups_i), n_splits)

            groups_arr = np.asarray(groups_i)

            # Split using the original list / array / list of string groups_i
            for train, test in cv.split(X, y, groups=groups_i):
                # First test: no train group is in the test set and vice versa
                assert_array_equal(np.intersect1d(groups_arr[train],
                                                  groups_arr[test]).tolist(),
                                   [])

                # Second test: train and test add up to all the data
                assert_equal(len(train) + len(test), len(groups_i))

                # Third test:
                # The number of groups in test must be equal to p_groups_out
                assert np.unique(groups_arr[test]).shape[0], p_groups_out

    # check get_n_splits() with dummy parameters
    assert_equal(logo.get_n_splits(None, None, ['a', 'b', 'c', 'b', 'c']), 3)
    assert_equal(logo.get_n_splits(groups=[1.0, 1.1, 1.0, 1.2]), 3)
    assert_equal(lpgo_2.get_n_splits(None, None, np.arange(4)), 6)
    assert_equal(lpgo_1.get_n_splits(groups=np.arange(4)), 4)

    # raise ValueError if a `groups` parameter is illegal
    with assert_raises(ValueError):
        logo.get_n_splits(None, None, [0.0, np.nan, 0.0])
    with assert_raises(ValueError):
        lpgo_2.get_n_splits(None, None, [0.0, np.inf, 0.0])

    msg = "The 'groups' parameter should not be None."
    assert_raise_message(ValueError, msg,
                         logo.get_n_splits, None, None, None)
    assert_raise_message(ValueError, msg,
                         lpgo_1.get_n_splits, None, None, None) 

# 需要导入模块: from sklearn import model_selection [as 别名]
# 或者: from sklearn.model_selection import LeavePGroupsOut [as 别名]
def test_cross_validator_with_default_params():
    n_samples = 4
    n_unique_groups = 4
    n_splits = 2
    p = 2
    n_shuffle_splits = 10  # (the default value)

    X = np.array([[1, 2], [3, 4], [5, 6], [7, 8]])
    X_1d = np.array([1, 2, 3, 4])
    y = np.array([1, 1, 2, 2])
    groups = np.array([1, 2, 3, 4])
    loo = LeaveOneOut()
    lpo = LeavePOut(p)
    kf = KFold(n_splits)
    skf = StratifiedKFold(n_splits)
    lolo = LeaveOneGroupOut()
    lopo = LeavePGroupsOut(p)
    ss = ShuffleSplit(random_state=0)
    ps = PredefinedSplit([1, 1, 2, 2])  # n_splits = np of unique folds = 2

    loo_repr = "LeaveOneOut()"
    lpo_repr = "LeavePOut(p=2)"
    kf_repr = "KFold(n_splits=2, random_state=None, shuffle=False)"
    skf_repr = "StratifiedKFold(n_splits=2, random_state=None, shuffle=False)"
    lolo_repr = "LeaveOneGroupOut()"
    lopo_repr = "LeavePGroupsOut(n_groups=2)"
    ss_repr = ("ShuffleSplit(n_splits=10, random_state=0, "
               "test_size='default',\n       train_size=None)")
    ps_repr = "PredefinedSplit(test_fold=array([1, 1, 2, 2]))"

    n_splits_expected = [n_samples, comb(n_samples, p), n_splits, n_splits,
                         n_unique_groups, comb(n_unique_groups, p),
                         n_shuffle_splits, 2]

    for i, (cv, cv_repr) in enumerate(zip(
            [loo, lpo, kf, skf, lolo, lopo, ss, ps],
            [loo_repr, lpo_repr, kf_repr, skf_repr, lolo_repr, lopo_repr,
             ss_repr, ps_repr])):
        # Test if get_n_splits works correctly
        assert_equal(n_splits_expected[i], cv.get_n_splits(X, y, groups))

        # Test if the cross-validator works as expected even if
        # the data is 1d
        np.testing.assert_equal(list(cv.split(X, y, groups)),
                                list(cv.split(X_1d, y, groups)))
        # Test that train, test indices returned are integers
        for train, test in cv.split(X, y, groups):
            assert_equal(np.asarray(train).dtype.kind, 'i')
            assert_equal(np.asarray(train).dtype.kind, 'i')

        # Test if the repr works without any errors
        assert_equal(cv_repr, repr(cv))

    # ValueError for get_n_splits methods
    msg = "The 'X' parameter should not be None."
    assert_raise_message(ValueError, msg,
                         loo.get_n_splits, None, y, groups)
    assert_raise_message(ValueError, msg,
                         lpo.get_n_splits, None, y, groups) 

# 需要导入模块: from sklearn import model_selection [as 别名]
# 或者: from sklearn.model_selection import LeavePGroupsOut [as 别名]
def test_leave_one_p_group_out():
    logo = LeaveOneGroupOut()
    lpgo_1 = LeavePGroupsOut(n_groups=1)
    lpgo_2 = LeavePGroupsOut(n_groups=2)

    # Make sure the repr works
    assert_equal(repr(logo), 'LeaveOneGroupOut()')
    assert_equal(repr(lpgo_1), 'LeavePGroupsOut(n_groups=1)')
    assert_equal(repr(lpgo_2), 'LeavePGroupsOut(n_groups=2)')
    assert_equal(repr(LeavePGroupsOut(n_groups=3)),
                 'LeavePGroupsOut(n_groups=3)')

    for j, (cv, p_groups_out) in enumerate(((logo, 1), (lpgo_1, 1),
                                            (lpgo_2, 2))):
        for i, groups_i in enumerate(test_groups):
            n_groups = len(np.unique(groups_i))
            n_splits = (n_groups if p_groups_out == 1
                        else n_groups * (n_groups - 1) / 2)
            X = y = np.ones(len(groups_i))

            # Test that the length is correct
            assert_equal(cv.get_n_splits(X, y, groups=groups_i), n_splits)

            groups_arr = np.asarray(groups_i)

            # Split using the original list / array / list of string groups_i
            for train, test in cv.split(X, y, groups=groups_i):
                # First test: no train group is in the test set and vice versa
                assert_array_equal(np.intersect1d(groups_arr[train],
                                                  groups_arr[test]).tolist(),
                                   [])

                # Second test: train and test add up to all the data
                assert_equal(len(train) + len(test), len(groups_i))

                # Third test:
                # The number of groups in test must be equal to p_groups_out
                assert_true(np.unique(groups_arr[test]).shape[0], p_groups_out)

    # check get_n_splits() with dummy parameters
    assert_equal(logo.get_n_splits(None, None, ['a', 'b', 'c', 'b', 'c']), 3)
    assert_equal(logo.get_n_splits(groups=[1.0, 1.1, 1.0, 1.2]), 3)
    assert_equal(lpgo_2.get_n_splits(None, None, np.arange(4)), 6)
    assert_equal(lpgo_1.get_n_splits(groups=np.arange(4)), 4)

    # raise ValueError if a `groups` parameter is illegal
    with assert_raises(ValueError):
        logo.get_n_splits(None, None, [0.0, np.nan, 0.0])
    with assert_raises(ValueError):
        lpgo_2.get_n_splits(None, None, [0.0, np.inf, 0.0])

    msg = "The 'groups' parameter should not be None."
    assert_raise_message(ValueError, msg,
                         logo.get_n_splits, None, None, None)
    assert_raise_message(ValueError, msg,
                         lpgo_1.get_n_splits, None, None, None)