def test_explain_catboost_catboost(boston_train):
xs, ys, feature_names = boston_train
catb = CatBoost().fit(xs, ys)
res = explain_weights(catb)
for expl in format_as_all(res, catb):
assert '12' in expl
res = explain_weights(catb, feature_names=feature_names)
for expl in format_as_all(res, catb):
assert 'LSTAT' in expl
def test_explain_xgboost_regressor(boston_train):
xs, ys, feature_names = boston_train
reg = XGBRegressor()
reg.fit(xs, ys)
res = explain_weights(reg)
for expl in format_as_all(res, reg):
assert 'f12' in expl
res = explain_weights(reg, feature_names=feature_names)
for expl in format_as_all(res, reg):
assert 'LSTAT' in expl
def test_explain_xgboost_booster(boston_train):
xs, ys, feature_names = boston_train
booster = xgboost.train(
params={'objective': 'reg:linear', 'silent': True},
dtrain=xgboost.DMatrix(xs, label=ys),
)
res = explain_weights(booster)
for expl in format_as_all(res, booster):
assert 'f12' in expl
res = explain_weights(booster, feature_names=feature_names)
for expl in format_as_all(res, booster):
assert 'LSTAT' in expl
def test_explain_weights_feature_names_pandas(boston_train):
pd = pytest.importorskip('pandas')
X, y, feature_names = boston_train
df = pd.DataFrame(X, columns=feature_names)
reg = XGBRegressor().fit(df, y)
# it shoud pick up feature names from DataFrame columns
res = explain_weights(reg)
for expl in format_as_all(res, reg):
assert 'PTRATIO' in expl
# it is possible to override DataFrame feature names
numeric_feature_names = ["zz%s" % idx for idx in range(len(feature_names))]
res = explain_weights(reg, feature_names=numeric_feature_names)
for expl in format_as_all(res, reg):
assert 'zz12' in expl
def explain_weights_pipeline(estimator, feature_names=None, **kwargs):
last_estimator = estimator.steps[-1][1]
transform_pipeline = Pipeline(estimator.steps[:-1])
if 'vec' in kwargs:
feature_names = get_feature_names(feature_names, vec=kwargs.pop('vec'))
feature_names = transform_feature_names(transform_pipeline, feature_names)
out = explain_weights(last_estimator,
feature_names=feature_names,
**kwargs)
out.estimator = repr(estimator)
return out
def test_explain_catboost_catboost_wrong_importance_type(
iris_train, importance_type):
x, y, feature_names, target = iris_train
train = Pool(x, y)
catb = CatBoostClassifier(iterations=10,
learning_rate=1,
depth=2,
loss_function='MultiClass')
catb.fit(train)
with pytest.raises(ValueError):
res = explain_weights(catb,
importance_type=importance_type,
pool=train)
def test_explain_catboost_classifier(iris_train, importance_type):
x, y, feature_names, target = iris_train
train = Pool(x, y)
catb = CatBoostClassifier(iterations=10,
learning_rate=1,
depth=2,
loss_function='MultiClass')
catb.fit(train)
res = explain_weights(catb, importance_type=importance_type, pool=train)
for expl in format_as_all(res, catb):
assert '3' in expl
res = explain_weights(catb,
feature_names=feature_names,
importance_type=importance_type,
pool=train)
for expl in format_as_all(res, catb):
assert 'petal width (cm)' in expl
if (importance_type == 'LossFunctionChange'):
with pytest.raises(ValueError):
res = explain_weights(catb,
feature_names=feature_names,
importance_type=importance_type,
pool=[x, y])
