Skip to content

Commit d66b56e

Browse files
imatiach-msftCloseChoicepre-commit-ci[bot]
authored
fix for missing objective error for LGBMRegressor (#1063)
* fix for missing objective error for LGBMRegressor * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * update test_tree to let tests pass --------- Co-authored-by: Tobias Pitters <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
1 parent 11af84a commit d66b56e

2 files changed

Lines changed: 169 additions & 1 deletion

File tree

‎shap/explainers/_tree.py‎

Lines changed: 4 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -578,7 +578,10 @@ def shap_values(
578578
assert not approximate, "approximate=True is not supported for LightGBM models!"
579579
phi = self.model.original_model.predict(X, num_iteration=tree_limit, pred_contrib=True)
580580
# Note: the data must be joined on the last axis
581-
if self.model.original_model.params["objective"] == "binary":
581+
if (
582+
"objective" in self.model.original_model.params
583+
and self.model.original_model.params["objective"] == "binary"
584+
):
582585
if not from_call:
583586
warnings.warn(
584587
"LightGBM binary classifier with TreeExplainer shap values output has changed to a list of ndarray"

‎tests/explainers/test_tree.py‎

Lines changed: 165 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -312,6 +312,171 @@ def create_binary_newsgroups_data():
312312
return newsgroups_train, newsgroups_test, class_names
313313

314314

315+
def create_random_forest_vectorizer():
316+
from sklearn.base import TransformerMixin
317+
from sklearn.ensemble import RandomForestClassifier
318+
from sklearn.feature_extraction.text import CountVectorizer
319+
from sklearn.pipeline import Pipeline
320+
321+
vectorizer = CountVectorizer(lowercase=False, min_df=0.0, binary=True)
322+
323+
class DenseTransformer(TransformerMixin):
324+
def fit(self, X, y=None, **fit_params):
325+
return self
326+
327+
def transform(self, X, y=None, **fit_params):
328+
return X.toarray()
329+
330+
rf = RandomForestClassifier(n_estimators=500, random_state=777)
331+
return Pipeline([("vectorizer", vectorizer), ("to_dense", DenseTransformer()), ("rf", rf)])
332+
333+
334+
def test_sklearn_random_forest_newsgroups():
335+
import shap
336+
# from sklearn.ensemble import RandomForestClassifier
337+
338+
# note: this test used to fail in native TreeExplainer code due to memory corruption
339+
newsgroups_train, newsgroups_test, _ = create_binary_newsgroups_data()
340+
pipeline = create_random_forest_vectorizer()
341+
pipeline.fit(newsgroups_train.data, newsgroups_train.target)
342+
rf = pipeline.named_steps["rf"]
343+
vectorizer = pipeline.named_steps["vectorizer"]
344+
densifier = pipeline.named_steps["to_dense"]
345+
346+
dense_bg = densifier.transform(vectorizer.transform(newsgroups_test.data[0:20]))
347+
348+
test_row = newsgroups_test.data[83:84]
349+
explainer = shap.TreeExplainer(rf, dense_bg, feature_perturbation="interventional")
350+
vec_row = vectorizer.transform(test_row)
351+
dense_row = densifier.transform(vec_row)
352+
explainer.shap_values(dense_row)
353+
354+
355+
def test_sklearn_decision_tree_multiclass():
356+
import numpy as np
357+
from sklearn.tree import DecisionTreeClassifier
358+
359+
import shap
360+
361+
X, y = shap.datasets.iris()
362+
y[y == 2] = 1
363+
model = DecisionTreeClassifier(max_depth=None, min_samples_split=2, random_state=0)
364+
model.fit(X, y)
365+
366+
explainer = shap.TreeExplainer(model)
367+
shap_values = explainer.shap_values(X)
368+
assert np.abs(shap_values[0][0, 0] - 0.05) < 1e-1
369+
assert np.abs(shap_values[1][0, 0] + 0.05) < 1e-1
370+
371+
372+
def _common_lightgbm_regressor_test(create_model):
373+
import numpy as np
374+
375+
import shap
376+
377+
# train lightgbm model on california housing price regression dataset
378+
X, y = shap.datasets.california()
379+
model = create_model()
380+
model.fit(X, y)
381+
382+
# explain the model's predictions using SHAP values
383+
ex = shap.TreeExplainer(model)
384+
shap_values = ex.shap_values(X)
385+
386+
predicted = model.predict(X, raw_score=True)
387+
388+
assert np.abs(shap_values.sum(1) + ex.expected_value - predicted).max() < 1e-4, (
389+
"SHAP values don't sum to model output!"
390+
)
391+
392+
393+
def test_lightgbm():
394+
lightgbm = pytest.importorskip("lightgbm")
395+
396+
def create_model():
397+
return lightgbm.sklearn.LGBMRegressor(categorical_feature=[8])
398+
399+
_common_lightgbm_regressor_test(create_model)
400+
401+
402+
def test_lightgbm_mse_regressor():
403+
lightgbm = pytest.importorskip("lightgbm")
404+
405+
# train the lightgbm model on a dataset with MSE objective
406+
def create_model():
407+
return lightgbm.sklearn.LGBMRegressor(categorical_feature=[8], objective="mean_squared_error")
408+
409+
_common_lightgbm_regressor_test(create_model)
410+
411+
412+
def _common_lightgbm_nonsklearn_api(dataset, params, validation):
413+
import lightgbm
414+
from sklearn.model_selection import train_test_split
415+
416+
import shap
417+
418+
# train the lightgbm model using non-sklearn API with binary classification dataset
419+
X_train, X_test, y_train, y_test = train_test_split(*dataset, test_size=0.2, random_state=0)
420+
lgb_train = lightgbm.Dataset(X_train, y_train)
421+
lgb_test = lightgbm.Dataset(X_test, y_test, reference=lgb_train)
422+
423+
booster = lightgbm.train(params, lgb_train, valid_sets=[lgb_train, lgb_test])
424+
# explain the model's predictions using SHAP values
425+
ex = shap.TreeExplainer(booster)
426+
shap_values = ex.shap_values(X_test)
427+
428+
predicted = booster.predict(X_test, raw_score=True)
429+
430+
validation(shap_values, ex.expected_value, predicted)
431+
432+
433+
def test_lightgbm_nonsklearn_api_binary():
434+
import numpy as np
435+
436+
import shap
437+
438+
# train the lightgbm model using non-sklearn API with binary classification dataset
439+
params = {
440+
"objective": "binary",
441+
"num_threads": 4,
442+
"n_estimators": 8000,
443+
"early_stopping_round": 50,
444+
"metric": ["binary_error"],
445+
"random_state": 7,
446+
"verbose": 1,
447+
}
448+
449+
def validation(shap_values, expected_value, predicted):
450+
assert np.abs(shap_values.sum(1) + expected_value - predicted).max() < 1e-4, (
451+
"SHAP values don't sum to model output!"
452+
)
453+
454+
_common_lightgbm_nonsklearn_api(dataset=shap.datasets.iris(), params=params, validation=validation)
455+
456+
457+
def test_lightgbm_nonsklearn_api_regressor():
458+
import numpy as np
459+
460+
import shap
461+
462+
# train the lightgbm model using non-sklearn API with regression dataset
463+
params = {
464+
"num_threads": 4,
465+
"n_estimators": 8000,
466+
"early_stopping_round": 50,
467+
"metric": ["rmse"],
468+
"random_state": 7,
469+
"verbose": 1,
470+
}
471+
472+
def validation(shap_values, expected_value, predicted):
473+
assert np.abs(shap_values.sum(1) + expected_value - predicted).max() < 1e-4, (
474+
"SHAP values don't sum to model output!"
475+
)
476+
477+
_common_lightgbm_nonsklearn_api(dataset=shap.datasets.adult(), params=params, validation=validation)
478+
479+
315480
def test_gpboost():
316481
gpboost = pytest.importorskip("gpboost")
317482
# train gpboost model

0 commit comments

Comments
 (0)