def fit(self,
durations,
event_observed=None,
timeline=None,
entry=None,
label='NA-estimate',
alpha=None,
ci_labels=None):
"""
Parameters:
duration: an array, or pd.Series, of length n -- duration subject was observed for
timeline: return the best estimate at the values in timelines (postively increasing)
event_observed: an array, or pd.Series, of length n -- True if the the death was observed, False if the event
was lost (right-censored). Defaults all True if event_observed==None
entry: an array, or pd.Series, of length n -- relative time when a subject entered the study. This is
useful for left-truncated observations, i.e the birth event was not observed.
If None, defaults to all 0 (all birth events observed.)
label: a string to name the column of the estimate.
alpha: the alpha value in the confidence intervals. Overrides the initializing
alpha for this call to fit only.
ci_labels: add custom column names to the generated confidence intervals
as a length-2 list: [<lower-bound name>, <upper-bound name>]. Default: <label>_lower_<alpha>
Returns:
self, with new properties like 'cumulative_hazard_'.
"""
v = preprocess_inputs(durations, event_observed, timeline, entry)
self.durations, self.event_observed, self.timeline, self.entry, self.event_table = v
cumulative_hazard_, cumulative_sq_ = _additive_estimate(
self.event_table, self.timeline, self._additive_f,
self._variance_f, False)
# esimates
self.cumulative_hazard_ = pd.DataFrame(cumulative_hazard_,
columns=[label])
self.confidence_interval_ = self._bounds(
cumulative_sq_[:, None], alpha if alpha else self.alpha, ci_labels)
self._cumulative_sq = cumulative_sq_
# estimation functions
self.predict = _predict(self, "cumulative_hazard_", label)
self.subtract = _subtract(self, "cumulative_hazard_")
self.divide = _divide(self, "cumulative_hazard_")
# plotting
self.plot = plot_estimate(self, "cumulative_hazard_")
self.plot_cumulative_hazard = self.plot
self.plot_hazard = plot_estimate(self, 'hazard_')
return self
def fit(self, durations, event_observed=None, timeline=None, entry=None, label='KM-estimate',
alpha=None, left_censorship=False, ci_labels=None):
"""
Parameters:
duration: an array, or pd.Series, of length n -- duration subject was observed for
timeline: return the best estimate at the values in timelines (postively increasing)
event_observed: an array, or pd.Series, of length n -- True if the the death was observed, False if the event
was lost (right-censored). Defaults all True if event_observed==None
entry: an array, or pd.Series, of length n -- relative time when a subject entered the study. This is
useful for left-truncated observations, i.e the birth event was not observed.
If None, defaults to all 0 (all birth events observed.)
label: a string to name the column of the estimate.
alpha: the alpha value in the confidence intervals. Overrides the initializing
alpha for this call to fit only.
left_censorship: True if durations and event_observed refer to left censorship events. Default False
ci_labels: add custom column names to the generated confidence intervals
as a length-2 list: [<lower-bound name>, <upper-bound name>]. Default: <label>_lower_<alpha>
Returns:
self, with new properties like 'survival_function_'.
"""
# if the user is interested in left-censorship, we return the cumulative_density_, no survival_function_,
estimate_name = 'survival_function_' if not left_censorship else 'cumulative_density_'
v = preprocess_inputs(durations, event_observed, timeline, entry)
self.durations, self.event_observed, self.timeline, self.entry, self.event_table = v
self._label = label
self.alpha = alpha if alpha else self.alpha
log_survival_function, cumulative_sq_ = _additive_estimate(self.event_table, self.timeline,
self._additive_f, self._additive_var,
left_censorship)
if entry is not None:
# a serious problem with KM is that when the sample size is small and there are too few early
# truncation times, it may happen that is the number of patients at risk and the number of deaths is the same.
# we adjust for this using the Breslow-Fleming-Harrington estimator
n = self.event_table.shape[0]
net_population = (self.event_table['entrance'] - self.event_table['removed']).cumsum()
if net_population.iloc[:int(n / 2)].min() == 0:
ix = net_population.iloc[:int(n / 2)].argmin()
raise StatError("""There are too few early truncation times and too many events. S(t)==0 for all t>%.1f. Recommend BreslowFlemingHarringtonFitter.""" % ix)
# estimation
setattr(self, estimate_name, pd.DataFrame(np.exp(log_survival_function), columns=[self._label]))
self.__estimate = getattr(self, estimate_name)
self.confidence_interval_ = self._bounds(cumulative_sq_[:, None], ci_labels)
self.median_ = median_survival_times(self.__estimate)
# estimation methods
self.predict = _predict(self, estimate_name, label)
self.subtract = _subtract(self, estimate_name)
self.divide = _divide(self, estimate_name)
# plotting functions
self.plot = plot_estimate(self, estimate_name)
setattr(self, "plot_" + estimate_name, self.plot)
return self
def fit(self, durations, event_observed=None, timeline=None, entry=None, label='KM-estimate',
alpha=None, left_censorship=False, ci_labels=None):
"""
Parameters:
duration: an array, or pd.Series, of length n -- duration subject was observed for
timeline: return the best estimate at the values in timelines (postively increasing)
event_observed: an array, or pd.Series, of length n -- True if the the death was observed, False if the event
was lost (right-censored). Defaults all True if event_observed==None
entry: an array, or pd.Series, of length n -- relative time when a subject entered the study. This is
useful for left-truncated observations, i.e the birth event was not observed.
If None, defaults to all 0 (all birth events observed.)
label: a string to name the column of the estimate.
alpha: the alpha value in the confidence intervals. Overrides the initializing
alpha for this call to fit only.
left_censorship: True if durations and event_observed refer to left censorship events. Default False
ci_labels: add custom column names to the generated confidence intervals
as a length-2 list: [<lower-bound name>, <upper-bound name>]. Default: <label>_lower_<alpha>
Returns:
self, with new properties like 'survival_function_'.
"""
#if the user is interested in left-censorship, we return the cumulative_density_, no survival_function_,
estimate_name = 'survival_function_' if not left_censorship else 'cumulative_density_'
v = preprocess_inputs(durations, event_observed, timeline, entry)
self.durations, self.event_observed, self.timeline, self.entry, self.event_table = v
log_survival_function, cumulative_sq_ = _additive_estimate(self.event_table, self.timeline,
self._additive_f, self._additive_var,
left_censorship)
if entry is not None:
#a serious problem with KM is that when the sample size is small and there are too few early
# truncation times, it may happen that is the number of patients at risk and the number of deaths is the same.
# we adjust for this using the Breslow-Fleming-Harrington estimator
n = self.event_table.shape[0]
net_population = (self.event_table['entrance'] - self.event_table['removed']).cumsum()
if net_population.iloc[:int(n/2)].min() == 0:
ix = net_population.iloc[:int(n/2)].argmin()
raise StatError("""There are too few early truncation times and too many events. S(t)==0 for all t>%.1f. Recommend BFH estimator."""%ix)
# estimation
setattr(self, estimate_name, pd.DataFrame(np.exp(log_survival_function), columns=[label]))
self.__estimate = getattr(self,estimate_name)
self.confidence_interval_ = self._bounds(cumulative_sq_[:, None], alpha if alpha else self.alpha, ci_labels)
self.median_ = median_survival_times(self.__estimate)
# estimation methods
self.predict = _predict(self, estimate_name, label)
self.subtract = _subtract(self, estimate_name)
self.divide = _divide(self, estimate_name)
# plotting functions
self.plot = plot_estimate(self, estimate_name)
setattr(self, "plot_" + estimate_name, self.plot)
return self
def fit(self, durations, event_observed=None, timeline=None, entry=None,
label='NA-estimate', alpha=None, ci_labels=None):
"""
Parameters:
duration: an array, or pd.Series, of length n -- duration subject was observed for
timeline: return the best estimate at the values in timelines (postively increasing)
event_observed: an array, or pd.Series, of length n -- True if the the death was observed, False if the event
was lost (right-censored). Defaults all True if event_observed==None
entry: an array, or pd.Series, of length n -- relative time when a subject entered the study. This is
useful for left-truncated observations, i.e the birth event was not observed.
If None, defaults to all 0 (all birth events observed.)
label: a string to name the column of the estimate.
alpha: the alpha value in the confidence intervals. Overrides the initializing
alpha for this call to fit only.
ci_labels: add custom column names to the generated confidence intervals
as a length-2 list: [<lower-bound name>, <upper-bound name>]. Default: <label>_lower_<alpha>
Returns:
self, with new properties like 'cumulative_hazard_'.
"""
v = preprocess_inputs(durations, event_observed, timeline, entry)
self.durations, self.event_observed, self.timeline, self.entry, self.event_table = v
cumulative_hazard_, cumulative_sq_ = _additive_estimate(self.event_table, self.timeline,
self._additive_f, self._variance_f, False)
# esimates
self._label = label
self.cumulative_hazard_ = pd.DataFrame(cumulative_hazard_, columns=[self._label])
self.confidence_interval_ = self._bounds(cumulative_sq_[:, None], alpha if alpha else self.alpha, ci_labels)
self._cumulative_sq = cumulative_sq_
# estimation functions
self.predict = _predict(self, "cumulative_hazard_", self._label)
self.subtract = _subtract(self, "cumulative_hazard_")
self.divide = _divide(self, "cumulative_hazard_")
# plotting
self.plot = plot_estimate(self, "cumulative_hazard_")
self.plot_cumulative_hazard = self.plot
self.plot_hazard = plot_estimate(self, 'hazard_')
return self
def fit(self, durations, censorship=None, timeline=None, entry=None, label='KM-estimate', alpha=None):
"""
Parameters:
duration: an array, or pd.Series, of length n -- duration subject was observed for
timeline: return the best estimate at the values in timelines (postively increasing)
censorship: an array, or pd.Series, of length n -- True if the the death was observed, False if the event
was lost (right-censored). Defaults all True if censorship==None
entry: an array, or pd.Series, of length n -- relative time when a subject entered the study. This is
useful for left-truncated observations, i.e the birth event was not observed.
If None, defaults to all 0 (all birth events observed.)
label: a string to name the column of the estimate.
alpha: the alpha value in the confidence intervals. Overrides the initializing
alpha for this call to fit only.
Returns:
self, with new properties like 'survival_function_'.
"""
v = preprocess_inputs(durations, censorship, timeline, entry)
self.durations, self.censorship, self.timeline, self.entry, self.event_table = v
log_survival_function, cumulative_sq_ = _additive_estimate(
self.event_table, self.timeline,
self._additive_f, self._additive_var)
if entry is not None:
# a serious problem with KM is that when the sample size is small and there are too few early
# truncation times, it may happen that is the number of patients at risk and the number of deaths is the same.
# we adjust for this using the Breslow-Fleming-Harrington estimator
n = self.event_table.shape[0]
net_population = (
self.event_table['entrance'] - self.event_table['removed']).cumsum()
if net_population.iloc[:int(n / 2)].min() == 0:
ix = net_population.iloc[:int(n / 2)].argmin()
raise StatError(
"""There are too few early truncation times and too many events. S(t)==0 for all t>%.1f. Recommend BFH estimator.""" % ix)
# estimation
self.survival_function_ = pd.DataFrame(
np.exp(log_survival_function), columns=[label])
self.confidence_interval_ = self._bounds(
cumulative_sq_[:, None], alpha if alpha else self.alpha)
self.median_ = median_survival_times(self.survival_function_)
# estimation methods
self.predict = _predict(self, "survival_function_", label)
self.subtract = _subtract(self, "survival_function_")
self.divide = _divide(self, "survival_function_")
# plotting functions
self.plot = plot_estimate(self, "survival_function_")
self.plot_survival_function = self.plot
return self
def fit(self,
durations,
event_observed=None,
timeline=None,
entry=None,
label='BFH-estimate',
alpha=None,
ci_labels=None):
"""
Parameters:
duration: an array, or pd.Series, of length n -- duration subject was observed for
timeline: return the best estimate at the values in timelines (postively increasing)
event_observed: an array, or pd.Series, of length n -- True if the the death was observed, False if the event
was lost (right-censored). Defaults all True if event_observed==None
entry: an array, or pd.Series, of length n -- relative time when a subject entered the study. This is
useful for left-truncated observations, i.e the birth event was not observed.
If None, defaults to all 0 (all birth events observed.)
label: a string to name the column of the estimate.
alpha: the alpha value in the confidence intervals. Overrides the initializing
alpha for this call to fit only.
ci_labels: add custom column names to the generated confidence intervals
as a length-2 list: [<lower-bound name>, <upper-bound name>]. Default: <label>_lower_<alpha>
Returns:
self, with new properties like 'survival_function_'.
"""
naf = NelsonAalenFitter(self.alpha)
naf.fit(durations,
event_observed=event_observed,
timeline=timeline,
label=label,
entry=entry,
ci_labels=ci_labels)
self.durations, self.event_observed, self.timeline, self.entry, self.event_table = \
naf.durations, naf.event_observed, naf.timeline, naf.entry, naf.event_table
# estimation
self.survival_function_ = np.exp(-naf.cumulative_hazard_)
self.confidence_interval_ = np.exp(-naf.confidence_interval_)
self.median_ = median_survival_times(self.survival_function_)
# estimation methods
self.predict = _predict(self, "survival_function_", label)
self.subtract = _subtract(self, "survival_function_")
self.divide = _divide(self, "survival_function_")
# plotting functions
self.plot = plot_estimate(self, "survival_function_")
self.plot_survival_function = self.plot
return self
def fit(self, durations, censorship=None, timeline=None, entry=None, label="BFH-estimate", alpha=None):
"""
Parameters:
duration: an array, or pd.Series, of length n -- duration subject was observed for
timeline: return the best estimate at the values in timelines (postively increasing)
censorship: an array, or pd.Series, of length n -- True if the the death was observed, False if the event
was lost (right-censored). Defaults all True if censorship==None
entry: an array, or pd.Series, of length n -- relative time when a subject entered the study. This is
useful for left-truncated observations, i.e the birth event was not observed.
If None, defaults to all 0 (all birth events observed.)
label: a string to name the column of the estimate.
alpha: the alpha value in the confidence intervals. Overrides the initializing
alpha for this call to fit only.
Returns:
self, with new properties like 'survival_function_'.
"""
naf = NelsonAalenFitter(self.alpha)
naf.fit(durations, censorship=censorship, timeline=timeline, label=label, entry=entry)
self.durations, self.censorship, self.timeline, self.entry, self.event_table = (
naf.durations,
naf.censorship,
naf.timeline,
naf.entry,
naf.event_table,
)
# estimation
self.survival_function_ = np.exp(-naf.cumulative_hazard_)
self.confidence_interval_ = np.exp(-naf.confidence_interval_)
self.median_ = median_survival_times(self.survival_function_)
# estimation methods
self.predict = _predict(self, "survival_function_", label)
self.subtract = _subtract(self, "survival_function_")
self.divide = _divide(self, "survival_function_")
# plotting functions
self.plot = plot_estimate(self, "survival_function_")
self.plot_survival_function = self.plot
return self
def _plot_estimate(self, *args):
return plot_estimate(self, *args)
def _plot_estimate(self, *args):
return plot_estimate(self, *args)
def plot(self, *args, **kwargs):
return plot_estimate(self, *args, **kwargs)
