def _generate_leaf_node_predictions(self, data: xgb.DMatrix) -> np.ndarray:
"""Method to generate leaf node predictions from the xgboost model.
Method calls xgb.Booster.predict with pred_leaf = True and
ntree_limit = model's best_iteration + 1.
If the output of predict is not a 2d matrix the output is shaped to
be 2d.
Parameters
----------
data : xgb.DMatrix
Data to generate predictions on.
"""
check_type(data, [xgb.DMatrix], "data")
# matrix of (nsample, ntrees) with each record giving
# the leaf node of each sample in each tree
leaf_node_predictions = self.model.predict(
data=data,
pred_leaf=True,
ntree_limit=self.model.best_iteration + 1)
# if the input data is a single column reshape the output to
# be 2d array rather than 1d
if len(leaf_node_predictions.shape) == 1:
leaf_node_predictions = leaf_node_predictions.reshape(
(data.num_row(), 1))
return leaf_node_predictions
def xgbooster_predict_proba(booster: xgb.Booster,
d_x: xgb.DMatrix) -> np.ndarray:
""" Simulate the `predict_proba` interface from sklearn
This function will only work as expected if `booster` has been
training using the `binary:logistic` loss.
Parameters
----------
booster : xgboost.Booster
The trained booster
d_x : xgboost.DMatrix
The dataset
Returns
-------
y_proba_pred : numpy.ndarray
The probabilistic predictions. The shape of the array
is (n_row, 2).
"""
y_score = booster.predict(d_x)
y_false = 1 - y_score
size = (d_x.num_row(), 2)
y_probas_pred = np.zeros(size)
y_probas_pred[:, 0] = y_false
y_probas_pred[:, 1] = y_score
return y_probas_pred
def dmatrix_to_numpy(dmatrix: xgb.DMatrix) -> np.ndarray:
"""Convert DMatrix to 2d numpy array
Parameters
----------
dmatrix : xgb.DMatrix
DMatrix to convert
Returns
-------
np.ndarray
2d numpy array with the corresponding DMatrix feature values
Raises
------
InvalidInput
Input is not a valid DMatrix
"""
if not isinstance(dmatrix, xgb.DMatrix):
raise InvalidInput("Type error: input parameter is not DMatrix")
stream_parser = DMatrixStreamParserV0_80 if version.parse(xgb.__version__) < version.parse('1.0.0') \
else DMatrixStreamParserV1_0_0
# We set delete=False to avoid permissions error. This way, file can be accessed
# by XGBoost without being deleted while handle is closed
try:
with tempfile.NamedTemporaryFile(delete=False) as fp:
dmatrix.save_binary(fp.name)
result = stream_parser(fp, dmatrix.num_row(),
dmatrix.num_col()).parse()
finally:
# We can safely remove the temp file now, parsing process finished
with suppress(OSError):
os.remove(fp.name)
return result
