def __init__(self, model, data, link=IdentityLink(), **kwargs):
# convert incoming inputs to standardized iml objects
self.link = convert_to_link(link)
self.model = convert_to_model(model)
self.data = convert_to_data(data)
match_model_to_data(self.model, self.data)
# enforce our current input type limitations
assert isinstance(
self.data, DenseData
), "Shap explainer only supports the DenseData input currently."
assert not self.data.transposed, "Shap explainer does not support transposed DenseData currently."
# init our parameters
self.N = self.data.data.shape[0]
self.P = self.data.data.shape[1]
self.weights = kwargs.get("weights",
np.ones(self.N)) # TODO: Use these weights!
self.weights /= sum(self.weights)
assert len(
self.weights
) == self.N, "Provided 'weights' must match the number of representative data points {0}!".format(
self.N)
self.linkfv = np.vectorize(self.link.f)
self.nsamplesAdded = 0
self.nsamplesRun = 0
def __init__(self, model, data, link=IdentityLink(), **kwargs):
# convert incoming inputs to standardized iml objects
self.link = convert_to_link(link)
self.model = convert_to_model(model)
self.keep_index = kwargs.get("keep_index", False)
self.data = convert_to_data(data, keep_index=self.keep_index)
match_model_to_data(self.model, self.data)
# enforce our current input type limitations
assert isinstance(
self.data, DenseData
), "Shap explainer only supports the DenseData input currently."
assert not self.data.transposed, "Shap explainer does not support transposed DenseData currently."
# warn users about large background data sets
if len(self.data.weights) > 100:
log.warning(
"Using " + str(len(self.data.weights)) +
" background data samples could cause " +
"slower run times. Consider using shap.kmeans(data, K) to summarize the background "
+ "as K weighted samples.")
# init our parameters
self.N = self.data.data.shape[0]
self.P = self.data.data.shape[1]
self.linkfv = np.vectorize(self.link.f)
self.nsamplesAdded = 0
self.nsamplesRun = 0
def __init__(self, model, data, link=IdentityLink(), **kwargs):
# convert incoming inputs to standardized iml objects
self.link = convert_to_link(link)
self.model = convert_to_model(model)
self.keep_index = kwargs.get("keep_index", False)
self.keep_index_ordered = kwargs.get("keep_index_ordered", False)
self.data = convert_to_data(data, keep_index=self.keep_index)
match_model_to_data(self.model, self.data)
# enforce our current input type limitations
assert isinstance(
self.data, DenseData
), "Shap explainer only supports the DenseData input currently."
assert not self.data.transposed, "Shap explainer does not support transposed DenseData currently."
# warn users about large background data sets
if len(self.data.weights) > 100:
log.warning(
"Using " + str(len(self.data.weights)) +
" background data samples could cause " +
"slower run times. Consider using shap.kmeans(data, K) to summarize the background "
+ "as K weighted samples.")
# init our parameters
self.N = self.data.data.shape[0]
self.P = self.data.data.shape[1]
self.linkfv = np.vectorize(self.link.f)
self.nsamplesAdded = 0
self.nsamplesRun = 0
# find E_x[f(x)]
if self.keep_index:
model_null = self.model.f(self.data.convert_to_df())
else:
model_null = self.model.f(self.data.data)
if isinstance(model_null, (pd.DataFrame, pd.Series)):
model_null = np.squeeze(model_null.values)
self.fnull = np.sum((model_null.T * self.data.weights).T, 0)
self.expected_value = self.fnull
# see if we have a vector output
self.vector_out = True
if len(self.fnull.shape) == 0:
self.vector_out = False
self.fnull = np.array([self.fnull])
self.D = 1
else:
self.D = self.fnull.shape[0]
def __init__(self, model, data, link=IdentityLink(), **kwargs):
# convert incoming inputs to standardized iml objects
self.link = convert_to_link(link)
self.model = convert_to_model(model)
self.data = convert_to_data(data)
match_model_to_data(self.model, self.data)
# enforce our current input type limitations
assert isinstance(self.data, DenseData), "Shap explainer only supports the DenseData input currently."
assert not self.data.transposed, "Shap explainer does not support transposed DenseData currently."
# init our parameters
self.N = self.data.data.shape[0]
self.P = self.data.data.shape[1]
self.linkfv = np.vectorize(self.link.f)
self.nsamplesAdded = 0
self.nsamplesRun = 0
