def predict(self, X, return_interval_probs=False):
"""
Predicts survival probabilities using the XGBoost + Weibull AFT stacking pipeline.
Args:
X (pd.DataFrame): Dataframe of features to be used as input for the
XGBoost model.
return_interval_probs (Bool): Boolean indicating if interval probabilities are
supposed to be returned. If False the cumulative survival is returned.
Default is False.
Returns:
pd.DataFrame: A dataframe of survival probabilities
for all times (columns), from a time_bins array, for all samples of X
(rows). If return_interval_probs is True, the interval probabilities are returned
instead of the cumulative survival probabilities.
"""
# converting to xgb format
d_matrix = xgb.DMatrix(X)
# getting leaves and extracting neighbors
risk = self.bst.predict(d_matrix)
weibull_score_df = pd.DataFrame({"risk": risk})
# predicting from logistic regression artifacts
preds_df = self.weibull_aft.predict_survival_function(
weibull_score_df, self.time_bins).T
if return_interval_probs:
preds_df = calculate_interval_failures(preds_df)
return preds_df
def predict(self, X, return_interval_probs=False):
"""
Predicts survival probabilities using the XGBoost + Logistic Regression pipeline.
Args:
X (pd.DataFrame): Dataframe of features to be used as input for the
XGBoost model.
return_interval_probs (Bool): Boolean indicating if interval probabilities are
supposed to be returned. If False the cumulative survival is returned.
Default is False.
Returns:
pd.DataFrame: A dataframe of survival probabilities
for all times (columns), from a time_bins array, for all samples of X
(rows). If return_interval_probs is True, the interval probabilities are returned
instead of the cumulative survival probabilities.
"""
# converting to xgb format
d_matrix = xgb.DMatrix(X)
# getting leaves and extracting neighbors
leaves = self.bst.predict(d_matrix, pred_leaf=True)
leaves_encoded = self.encoder.transform(leaves)
# predicting from logistic regression artifacts
preds_df = self._predict_from_lr_list(self.lr_estimators_,
leaves_encoded, self.time_bins)
if return_interval_probs:
preds_df = calculate_interval_failures(preds_df)
return preds_df
def predict(self, X, return_ci=False, return_interval_probs=False):
"""
Run samples through tree until terminal nodes. Predict the Kaplan-Meier
estimator associated to the leaf node each sample ended into.
Args:
X (pd.DataFrame): Data frame with samples to generate predictions
return_ci (Bool): Whether to return confidence intervals via the Exponential Greenwood formula
return_interval_probs (Bool): Boolean indicating if interval probabilities are
supposed to be returned. If False the cumulative survival is returned.
Returns:
preds_df (pd.DataFrame): A dataframe of survival probabilities
for all times (columns), from a time_bins array, for all samples of X
(rows). If return_interval_probs is True, the interval probabilities are returned
instead of the cumulative survival probabilities.
upper_ci (np.array): Upper confidence interval for the survival
probability values
lower_ci (np.array): Lower confidence interval for the survival
probability values
"""
# converting to xgb format
d_matrix = xgb.DMatrix(X)
# getting leaves and extracting neighbors
leaves = self.bst.predict(d_matrix,
pred_leaf=True,
iteration_range=(0, self.bst.best_iteration +
1))
# searching for kaplan meier curves in leaves
preds_df = self._train_survival.loc[leaves].reset_index(drop=True)
upper_ci = self._train_upper_ci.loc[leaves].reset_index(drop=True)
lower_ci = self._train_lower_ci.loc[leaves].reset_index(drop=True)
if return_ci and return_interval_probs:
raise ValueError(
"Confidence intervals for interval probabilities is not supported. Choose between return_ci and return_interval_probs."
)
if return_interval_probs:
preds_df = calculate_interval_failures(preds_df)
return preds_df
if return_ci:
return preds_df, upper_ci, lower_ci
return preds_df
def predict(
self,
X,
time_bins=None,
return_ci=False,
ci_width=0.683,
return_interval_probs=False,
):
"""
Make queries to nearest neighbor search index build on the transformed XGBoost space.
Compute a Kaplan-Meier estimator for each neighbor-set. Predict the KM estimators.
Args:
X (pd.DataFrame): Dataframe with samples to generate predictions
time_bins (np.array): Specified time windows to use when making survival predictions
return_ci (Bool): Whether to return confidence intervals via the Exponential Greenwood formula
ci_width (Float): Width of confidence interval
return_interval_probs (Bool): Boolean indicating if interval probabilities are
supposed to be returned. If False the cumulative survival is returned.
Returns:
(pd.DataFrame): A dataframe of survival probabilities
for all times (columns), from a time_bins array, for all samples of X
(rows). If return_interval_probs is True, the interval probabilities are returned
instead of the cumulative survival probabilities.
upper_ci (np.array): Upper confidence interval for the survival
probability values
lower_ci (np.array): Lower confidence interval for the survival
probability values
"""
# converting to xgb format
d_matrix = xgb.DMatrix(X)
# getting leaves and extracting neighbors
leaves = self.bst.predict(d_matrix, pred_leaf=True)
if self.radius:
assert self.radius > 0, "Radius must be positive"
neighs, _ = self.tree.query_radius(
leaves, r=self.radius, return_distance=True
)
number_of_neighbors = np.array([len(neigh) for neigh in neighs])
if np.argwhere(number_of_neighbors == 1).shape[0] > 0:
# If there is at least one sample without neighbors apart from itself
# a warning is raised suggesting a radius increase
warnings.warn(
"Warning: Some samples don't have neighbors apart from itself. Increase the radius",
RuntimeWarning,
)
else:
_, neighs = self.tree.query(leaves, k=self.n_neighbors)
# gathering times and events/censors for neighbor sets
T_neighs = self.T_train[neighs]
E_neighs = self.E_train[neighs]
# vectorized (very fast!) implementation of Kaplan Meier curves
if time_bins is None:
time_bins = self.time_bins
# calculating z-score from width
z = st.norm.ppf(0.5 + ci_width / 2)
preds_df, upper_ci, lower_ci = calculate_kaplan_vectorized(
T_neighs, E_neighs, time_bins, z
)
if return_ci and return_interval_probs:
raise ValueError(
"Confidence intervals for interval probabilities is not supported. Choose between return_ci and return_interval_probs."
)
if return_interval_probs:
preds_df = calculate_interval_failures(preds_df)
return preds_df
if return_ci:
return preds_df, upper_ci, lower_ci
return preds_df