view release on metacpan or  search on metacpan

xgboost/tests/python/test_with_sklearn.py  view on Meta::CPAN

    from matplotlib.axes import Axes
    from graphviz import Digraph

    ax = xgb.plot_importance(classifier)
    assert isinstance(ax, Axes)
    assert ax.get_title() == 'Feature importance'
    assert ax.get_xlabel() == 'F score'
    assert ax.get_ylabel() == 'Features'
    assert len(ax.patches) == 4

    g = xgb.to_graphviz(classifier, num_trees=0)
    assert isinstance(g, Digraph)

    ax = xgb.plot_tree(classifier, num_trees=0)
    assert isinstance(ax, Axes)


def test_sklearn_nfolds_cv():
    tm._skip_if_no_sklearn()
    from sklearn.datasets import load_digits
    from sklearn.model_selection import StratifiedKFold

    digits = load_digits(3)
    X = digits['data']
    y = digits['target']
    dm = xgb.DMatrix(X, label=y)

    params = {
        'max_depth': 2,
        'eta': 1,
        'silent': 1,
        'objective':
        'multi:softprob',
        'num_class': 3
    }

    seed = 2016
    nfolds = 5
    skf = StratifiedKFold(n_splits=nfolds, shuffle=True, random_state=seed)

    cv1 = xgb.cv(params, dm, num_boost_round=10, nfold=nfolds, seed=seed)
    cv2 = xgb.cv(params, dm, num_boost_round=10, nfold=nfolds, folds=skf, seed=seed)
    cv3 = xgb.cv(params, dm, num_boost_round=10, nfold=nfolds, stratified=True, seed=seed)
    assert cv1.shape[0] == cv2.shape[0] and cv2.shape[0] == cv3.shape[0]
    assert cv2.iloc[-1, 0] == cv3.iloc[-1, 0]


def test_split_value_histograms():
    tm._skip_if_no_sklearn()
    from sklearn.datasets import load_digits

    digits_2class = load_digits(2)

    X = digits_2class['data']
    y = digits_2class['target']

    dm = xgb.DMatrix(X, label=y)
    params = {'max_depth': 6, 'eta': 0.01, 'silent': 1, 'objective': 'binary:logistic'}

    gbdt = xgb.train(params, dm, num_boost_round=10)
    assert gbdt.get_split_value_histogram("not_there", as_pandas=True).shape[0] == 0
    assert gbdt.get_split_value_histogram("not_there", as_pandas=False).shape[0] == 0
    assert gbdt.get_split_value_histogram("f28", bins=0).shape[0] == 1
    assert gbdt.get_split_value_histogram("f28", bins=1).shape[0] == 1
    assert gbdt.get_split_value_histogram("f28", bins=2).shape[0] == 2
    assert gbdt.get_split_value_histogram("f28", bins=5).shape[0] == 2
    assert gbdt.get_split_value_histogram("f28", bins=None).shape[0] == 2


def test_sklearn_random_state():
    tm._skip_if_no_sklearn()

    clf = xgb.XGBClassifier(random_state=402)
    assert clf.get_xgb_params()['seed'] == 402

    clf = xgb.XGBClassifier(seed=401)
    assert clf.get_xgb_params()['seed'] == 401


def test_seed_deprecation():
    tm._skip_if_no_sklearn()
    warnings.simplefilter("always")
    with warnings.catch_warnings(record=True) as w:
        xgb.XGBClassifier(seed=1).get_xgb_params()
        assert w[0].category == DeprecationWarning


def test_sklearn_n_jobs():
    tm._skip_if_no_sklearn()

    clf = xgb.XGBClassifier(n_jobs=1)
    assert clf.get_xgb_params()['nthread'] == 1

    clf = xgb.XGBClassifier(nthread=2)
    assert clf.get_xgb_params()['nthread'] == 2


def test_nthread_deprecation():
    tm._skip_if_no_sklearn()
    warnings.simplefilter("always")
    with warnings.catch_warnings(record=True) as w:
        xgb.XGBClassifier(nthread=1).get_xgb_params()
        assert w[0].category == DeprecationWarning


def test_kwargs():
    tm._skip_if_no_sklearn()

    params = {'updater': 'grow_gpu', 'subsample': .5, 'n_jobs': -1}
    clf = xgb.XGBClassifier(n_estimators=1000, **params)
    assert clf.get_params()['updater'] == 'grow_gpu'
    assert clf.get_params()['subsample'] == .5
    assert clf.get_params()['n_estimators'] == 1000


@raises(TypeError)
def test_kwargs_error():
    tm._skip_if_no_sklearn()

    params = {'updater': 'grow_gpu', 'subsample': .5, 'n_jobs': -1}
    clf = xgb.XGBClassifier(n_jobs=1000, **params)
    assert isinstance(clf, xgb.XGBClassifier)