def add_km_censor(self, steps='post'):
"""Add censoring estimates obtained by Kaplan-Meier on the test set
(durations, 1-events).
"""
km = utils.kaplan_meier(self.durations, 1 - self.events)
surv = pd.DataFrame(np.repeat(km.values.reshape(-1, 1),
len(self.durations),
axis=1),
index=km.index)
return self.add_censor_est(surv, steps)
def cuts_quantiles(durations, events, num, min_=0., dtype='float64'):
"""
If min_ = None, we will use durations.min() for the first cut.
"""
km = utils.kaplan_meier(durations, events)
surv_est, surv_durations = km.values, km.index.values
s_cuts = np.linspace(km.values.min(), km.values.max(), num)
cuts_idx = np.searchsorted(surv_est[::-1], s_cuts)[::-1]
cuts = surv_durations[::-1][cuts_idx]
cuts = np.unique(cuts)
if len(cuts) != num:
warnings.warn(
f"cuts are not unique, continue with {len(cuts)} cuts instead of {num}"
)
cuts[0] = durations.min() if min_ is None else min_
assert cuts[-1] == durations.max(), 'something wrong...'
return cuts.astype(dtype)
def calc_km(durations,events):
km = utils.kaplan_meier(durations, 1 - events)
return km