def test_sf_doesnt_return_nans():
left = [6, 7, 8, 7, 5]
right = [7, 8, 10, 16, 20]
results = npmle(left, right)
npt.assert_allclose(results[1], [interval(7, 7), interval(8, 8)])
npt.assert_allclose(results[0], [0.5, 0.5])
sf = reconstruct_survival_function(*results, timeline=[6, 7, 8, 16, 20])
assert not np.isnan(sf.values).any()
def fit_interval_censoring(
self,
lower_bound,
upper_bound,
event_observed=None,
timeline=None,
label=None,
alpha=None,
ci_labels=None,
entry=None,
weights=None,
tol: float = 1e-5,
show_progress: bool = False,
**kwargs,
) -> "KaplanMeierFitter":
"""
Fit the model to a interval-censored dataset using non-parametric MLE. This estimator is
also called the Turnbull Estimator.
Currently, only closed interval are supported. However, it's easy to create open intervals by adding (or subtracting) a very small
value from the lower-bound (or upper bound). For example, the following turns closed intervals into open intervals.
>>> left, right = df['left'], df['right']
>>> KaplanMeierFitter().fit_interval_censoring(left + 0.00001, right - 0.00001)
Note
------
This is new and experimental, and many features are missing.
Parameters
----------
lower_bound: an array, list, pd.DataFrame or pd.Series
length n -- lower bound of observations
upper_bound: an array, list, pd.DataFrame or pd.Series
length n -- upper bound of observations
event_observed: an array, list, pd.DataFrame, or pd.Series, optional
True if the the death was observed, False if the event was lost (right-censored). This can be computed from
the lower_bound and upper_bound, and can be left blank.
timeline: an array, list, pd.DataFrame, or pd.Series, optional
return the best estimate at the values in timelines (positively increasing)
entry: an array, list, pd.DataFrame, or pd.Series, optional
relative time when a subject entered the study. This is useful for left-truncated (not left-censored) observations. If None, all members of the population
entered study when they were "born".
label: string, optional
a string to name the column of the estimate.
alpha: float, optional
the alpha value in the confidence intervals. Overrides the initializing alpha for this call to fit only.
ci_labels: tuple, optional
add custom column names to the generated confidence intervals as a length-2 list: [<lower-bound name>, <upper-bound name>]. Default: <label>_lower_<1-alpha/2>
weights: an array, list, pd.DataFrame, or pd.Series, optional
if providing a weighted dataset. For example, instead
of providing every subject as a single element of `durations` and `event_observed`, one could
weigh subject differently.
tol: float, optional
minimum difference in log likelihood changes for iterative algorithm.
show_progress: bool, optional
display information during fitting.
Returns
-------
self: KaplanMeierFitter
self with new properties like ``survival_function_``, ``plot()``, ``median_survival_time_``
"""
if entry is not None:
raise NotImplementedError("entry is not supported yet")
if weights is None:
weights = np.ones_like(upper_bound)
self.weights = np.asarray(weights)
self.upper_bound = np.atleast_1d(
pass_for_numeric_dtypes_or_raise_array(upper_bound))
self.lower_bound = np.atleast_1d(
pass_for_numeric_dtypes_or_raise_array(lower_bound))
check_nans_or_infs(self.lower_bound)
self.event_observed = self.lower_bound == self.upper_bound
self.timeline = coalesce(
timeline,
np.unique(np.concatenate((self.upper_bound, self.lower_bound))))
if (self.upper_bound < self.lower_bound).any():
raise ValueError(
"All upper_bound times must be greater than or equal to lower_bound times."
)
if event_observed is None:
event_observed = self.upper_bound == self.lower_bound
if ((self.lower_bound == self.upper_bound) != event_observed).any():
raise ValueError(
"For all rows, lower_bound == upper_bound if and only if event observed = 1 (uncensored). Likewise, lower_bound < upper_bound if and only if event observed = 0 (censored)"
)
self._label = coalesce(label, self._label, "NPMLE_estimate")
results = npmle(self.lower_bound,
self.upper_bound,
verbose=show_progress,
tol=tol,
weights=weights,
**kwargs)
self.survival_function_ = reconstruct_survival_function(
*results, self.timeline, label=self._label).loc[self.timeline]
self.cumulative_density_ = 1 - self.survival_function_
self._median = median_survival_times(self.survival_function_)
"""
self.confidence_interval_ = npmle_compute_confidence_intervals(self.lower_bound, self.upper_bound, self.survival_function_, self.alpha)
self.confidence_interval_survival_function_ = self.confidence_interval_
self.confidence_interval_cumulative_density_ = 1 - self.confidence_interval_
"""
# estimation methods
self._estimation_method = "survival_function_"
self._estimate_name = "survival_function_"
return self
def fit_interval_censoring(
self,
lower_bound,
upper_bound,
event_observed=None,
timeline=None,
label=None,
alpha=None,
ci_labels=None,
show_progress=False,
entry=None,
weights=None,
tol=1e-7,
) -> "KaplanMeierFitter":
"""
Fit the model to a interval-censored dataset using non-parametric MLE. This estimator is
also called the Turball Estimator.
Note
------
This is new and experimental, and many feature are missing.
Parameters
----------
lower_bound: an array, list, pd.DataFrame or pd.Series
length n -- lower bound of observations
upper_bound: an array, list, pd.DataFrame or pd.Series
length n -- upper bound of observations
event_observed: an array, list, pd.DataFrame, or pd.Series, optional
True if the the death was observed, False if the event was lost (right-censored). This can be computed from
the lower_bound and upper_bound, and can be left blank.
timeline: an array, list, pd.DataFrame, or pd.Series, optional
return the best estimate at the values in timelines (positively increasing)
entry: an array, list, pd.DataFrame, or pd.Series, optional
relative time when a subject entered the study. This is useful for left-truncated (not left-censored) observations. If None, all members of the population
entered study when they were "born".
label: string, optional
a string to name the column of the estimate.
alpha: float, optional
the alpha value in the confidence intervals. Overrides the initializing alpha for this call to fit only.
ci_labels: tuple, optional
add custom column names to the generated confidence intervals as a length-2 list: [<lower-bound name>, <upper-bound name>]. Default: <label>_lower_<1-alpha/2>
weights: an array, list, pd.DataFrame, or pd.Series, optional
if providing a weighted dataset. For example, instead
of providing every subject as a single element of `durations` and `event_observed`, one could
weigh subject differently.
Returns
-------
self: KaplanMeierFitter
self with new properties like ``survival_function_``, ``plot()``, ``median_survival_time_``
"""
warnings.warn(
"This is new and experimental, many feature are missing and accuracy is not reliable",
UserWarning)
if entry is not None or weights is not None:
raise NotImplementedError("entry / weights is not supported yet")
self.weights = np.ones_like(upper_bound)
self.upper_bound = np.atleast_1d(
pass_for_numeric_dtypes_or_raise_array(upper_bound))
self.lower_bound = np.atleast_1d(
pass_for_numeric_dtypes_or_raise_array(lower_bound))
check_nans_or_infs(self.lower_bound)
self.event_observed = self.lower_bound == self.upper_bound
self.timeline = coalesce(
timeline,
np.unique(np.concatenate((self.upper_bound, self.lower_bound))))
if (self.upper_bound < self.lower_bound).any():
raise ValueError(
"All upper_bound times must be greater than or equal to lower_bound times."
)
if event_observed is None:
event_observed = self.upper_bound == self.lower_bound
if ((self.lower_bound == self.upper_bound) != event_observed).any():
raise ValueError(
"For all rows, lower_bound == upper_bound if and only if event observed = 1 (uncensored). Likewise, lower_bound < upper_bound if and only if event observed = 0 (censored)"
)
self._label = coalesce(label, self._label, "NPMLE_estimate")
probs, t_intervals = npmle(self.lower_bound,
self.upper_bound,
verbose=show_progress)
self.survival_function_ = reconstruct_survival_function(
probs, t_intervals, self.timeline,
label=self._label).loc[self.timeline]
self.cumulative_density_ = 1 - self.survival_function_
self._median = median_survival_times(self.survival_function_)
self.percentile = functools.partial(
qth_survival_time,
model_or_survival_function=self.survival_function_)
"""
self.confidence_interval_ = npmle_compute_confidence_intervals(self.lower_bound, self.upper_bound, self.survival_function_, self.alpha)
self.confidence_interval_survival_function_ = self.confidence_interval_
self.confidence_interval_cumulative_density_ = 1 - self.confidence_interval_
"""
# estimation methods
self._estimation_method = "survival_function_"
self._estimate_name = "survival_function_"
self._update_docstrings()
return self