def _make_single_prediction_shap_table(pipeline, input_features, top_k=3, training_data=None,
include_shap_values=False, output_format="text"):
"""Creates table summarizing the top_k positive and top_k negative contributing features to the prediction of a single datapoint.
Arguments:
pipeline (PipelineBase): Fitted pipeline whose predictions we want to explain with SHAP.
input_features (pd.DataFrame): Dataframe of features - needs to correspond to data the pipeline was fit on.
top_k (int): How many of the highest/lowest features to include in the table.
training_data (pd.DataFrame): Training data the pipeline was fit on.
This is required for non-tree estimators because we need a sample of training data for the KernelSHAP algorithm.
include_shap_values (bool): Whether the SHAP values should be included in an extra column in the output.
Default is False.
Returns:
str: Table
"""
pipeline_features = pipeline.compute_estimator_features(input_features)
shap_values = _compute_shap_values(pipeline, pipeline_features, training_data)
normalized_shap_values = _normalize_shap_values(shap_values)
class_names = None
if hasattr(pipeline, "classes_"):
class_names = pipeline.classes_
table_makers = {ProblemTypes.REGRESSION: _RegressionSHAPTable(),
ProblemTypes.BINARY: _BinarySHAPTable(class_names),
ProblemTypes.MULTICLASS: _MultiClassSHAPTable(class_names)}
table_maker_class = table_makers[pipeline.problem_type]
table_maker = table_maker_class.make_text if output_format == "text" else table_maker_class.make_dict
return table_maker(shap_values, normalized_shap_values, pipeline_features, top_k, include_shap_values)
def _make_single_prediction_shap_table(pipeline,
input_features,
y,
index_to_explain,
top_k=3,
include_shap_values=False,
output_format="text"):
"""Creates table summarizing the top_k_features positive and top_k_features negative contributing features to the prediction of a single datapoint.
Arguments:
pipeline (PipelineBase): Fitted pipeline whose predictions we want to explain with SHAP.
input_features (pd.DataFrame): Dataframe of features - needs to correspond to data the pipeline was fit on.
top_k (int): How many of the highest/lowest features to include in the table.
training_data (pd.DataFrame): Training data the pipeline was fit on.
This is required for non-tree estimators because we need a sample of training data for the KernelSHAP algorithm.
include_shap_values (bool): Whether the SHAP values should be included in an extra column in the output.
Default is False.
output_format (str): The desired format of the output. Can be "text", "dict", or "dataframe".
Returns:
str: Table
Raises:
ValueError: if requested index results in a NaN in the computed features.
"""
pipeline_features = pipeline.compute_estimator_features(input_features,
y).to_dataframe()
pipeline_features_row = pipeline_features.iloc[[index_to_explain]]
if pipeline_features_row.isna().any(axis=None):
raise ValueError(
f"Requested index ({index_to_explain}) produces NaN in features.")
shap_values = _compute_shap_values(
pipeline,
pipeline_features_row,
training_data=pipeline_features.dropna(axis=0))
normalized_shap_values = _normalize_shap_values(shap_values)
class_names = None
if hasattr(pipeline, "classes_"):
class_names = pipeline.classes_
table_makers = {
ProblemTypes.REGRESSION: _RegressionSHAPTable(),
ProblemTypes.BINARY: _BinarySHAPTable(class_names),
ProblemTypes.MULTICLASS: _MultiClassSHAPTable(class_names),
ProblemTypes.TIME_SERIES_REGRESSION: _RegressionSHAPTable(),
ProblemTypes.TIME_SERIES_BINARY: _BinarySHAPTable(class_names),
ProblemTypes.TIME_SERIES_MULTICLASS: _MultiClassSHAPTable(class_names)
}
table_maker_class = table_makers[pipeline.problem_type]
table_maker = {
"text": table_maker_class.make_text,
"dict": table_maker_class.make_dict,
"dataframe": table_maker_class.make_dataframe
}[output_format]
return table_maker(shap_values, normalized_shap_values,
pipeline_features_row, top_k, include_shap_values)
def test_normalize_values(values, answer):
normalized = _normalize_shap_values(values)
if isinstance(normalized, dict):
check_equal_dicts(normalized, answer)
else:
assert len(normalized) == len(answer)
for values, correct in zip(normalized, answer):
check_equal_dicts(values, correct)
def test_normalize_values(values, answer):
def check_equal_dicts(normalized, answer):
assert set(normalized.keys()) == set(answer)
for key in normalized:
np.testing.assert_almost_equal(normalized[key], answer[key], decimal=4)
normalized = _normalize_shap_values(values)
if isinstance(normalized, dict):
check_equal_dicts(normalized, answer)
else:
assert len(normalized) == len(answer)
for values, correct in zip(normalized, answer):
check_equal_dicts(values, correct)
def test_normalize_values_exceptions():
with pytest.raises(ValueError, match="^Unsupported data type for _normalize_shap_values"):
_normalize_shap_values(1)
