def fit(self, durations, event_observed=None, timeline=None, entry=None,
label='NA_estimate', alpha=None, ci_labels=None, weights=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>
weights: n array, or pd.Series, of length n, 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, with new properties like 'cumulative_hazard_'.
"""
check_nans_or_infs(durations)
if event_observed is not None:
check_nans_or_infs(event_observed)
if weights is not None:
if (weights.astype(int) != weights).any():
warnings.warn("""It looks like your weights are not integers, possibly prospenity scores then?
It's important to know that the naive variance estimates of the coefficients are biased. Instead use Monte Carlo to
estimate the variances. See paper "Variance estimation when using inverse probability of treatment weighting (IPTW) with survival analysis"
or "Adjusted Kaplan-Meier estimator and log-rank test with inverse probability of treatment weighting for survival data."
""", RuntimeWarning)
v = _preprocess_inputs(durations, event_observed, timeline, entry, weights)
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 methods
self._estimation_method = "cumulative_hazard_"
self._estimate_name = "cumulative_hazard_"
self._predict_label = label
self._update_docstrings()
# plotting
self.plot_cumulative_hazard = self.plot
return self
def _check_values(self, df, events, start, stop):
# check_for_overlapping_intervals(df) # this is currently too slow for production.
check_nans_or_infs(df)
check_low_var(df)
check_complete_separation_low_variance(df, events, self.event_col)
check_for_numeric_dtypes_or_raise(df)
check_for_immediate_deaths(events, start, stop)
check_for_instantaneous_events(start, stop)
def _check_values(self, df, events, start, stop):
# check_for_overlapping_intervals(df) # this is currently too slow for production.
check_nans_or_infs(df)
check_low_var(df)
check_complete_separation_low_variance(df, events, self.event_col)
check_for_numeric_dtypes_or_raise(df)
check_for_immediate_deaths(events, start, stop)
check_for_instantaneous_events(start, stop)
def _check_values(df, stop_times_events):
# check_for_overlapping_intervals(df) # this is currenty too slow for production.
check_nans_or_infs(df)
check_low_var(df)
check_complete_separation_low_variance(df, stop_times_events['event'])
pass_for_numeric_dtypes_or_raise(df)
check_for_immediate_deaths(stop_times_events)
check_for_instantaneous_events(stop_times_events)
def fit(self, durations, event_observed=None, timeline=None, entry=None,
label='Exponential_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_' and 'lambda_'.
"""
check_nans_or_infs(durations)
if event_observed is not None:
check_nans_or_infs(event_observed)
self.durations = np.asarray(durations, dtype=float)
self.event_observed = np.asarray(event_observed, dtype=int) if event_observed is not None else np.ones_like(self.durations)
self.timeline = np.sort(np.asarray(timeline)) if timeline is not None else np.arange(int(self.durations.min()), int(self.durations.max()) + 1)
self._label = label
# estimation
D = self.event_observed.sum()
T = self.durations.sum()
self.lambda_ = D / T
self._lambda_variance_ = self.lambda_ / T
self._log_likelihood = np.log(self.lambda_) * D - self.lambda_ * T
self.survival_function_ = pd.DataFrame(np.exp(-self.lambda_ * self.timeline), columns=[self._label], index=self.timeline)
self.confidence_interval_ = self._bounds(alpha if alpha else self.alpha, ci_labels)
self.median_ = 1. / self.lambda_ * (np.log(2))
# estimation methods
self._estimate_name = "survival_function_"
self._predict_label = label
self._update_docstrings()
# plotting
self.plot_survival_function_ = self.plot
return self
def _preprocess_dataframe(self, df):
n, _ = df.shape
df = df.sort_values(by=self.duration_col)
# Extract time and event
T = df.pop(self.duration_col)
E = df.pop(
self.event_col) if (self.event_col is not None) else pd.Series(
np.ones(n), index=df.index, name="E")
W = (df.pop(self.weights_col) if (self.weights_col is not None) else
pd.Series(np.ones((n, )), index=df.index, name="weights"))
# check to make sure their weights are okay
if self.weights_col:
if (W.astype(int) != W).any():
warnings.warn(
"""It appears your weights are not integers, possibly propensity or sampling scores then?
It's important to know that the naive variance estimates of the coefficients are biased."
""",
StatisticalWarning,
)
if (W <= 0).any():
raise ValueError(
"values in weight column %s must be positive." %
self.weights_col)
X = df.astype(float)
T = T.astype(float)
check_nans_or_infs(E)
E = E.astype(bool)
self._check_values(df, T, E)
if self.fit_intercept:
assert (
"_intercept" not in df.columns
), "_intercept is an internal lifelines column, please rename your column first."
X["_intercept"] = 1.0
return X, T, E, W
def _preprocess_dataframe(self, df):
n, _ = df.shape
df = df.sort_values(by=self.duration_col)
# Extract time and event
T = df.pop(self.duration_col)
E = df.pop(self.event_col) if (self.event_col is not None) else pd.Series(np.ones(n), index=df.index, name="E")
W = (
df.pop(self.weights_col)
if (self.weights_col is not None)
else pd.Series(np.ones((n,)), index=df.index, name="weights")
)
# check to make sure their weights are okay
if self.weights_col:
if (W.astype(int) != W).any():
warnings.warn(
"""It appears your weights are not integers, possibly propensity or sampling scores then?
It's important to know that the naive variance estimates of the coefficients are biased."
""",
StatisticalWarning,
)
if (W <= 0).any():
raise ValueError("values in weight column %s must be positive." % self.weights_col)
X = df.astype(float)
T = T.astype(float)
check_nans_or_infs(E)
E = E.astype(bool)
self._check_values(df, T, E)
if self.fit_intercept:
assert (
"_intercept" not in df.columns
), "_intercept is an internal lifelines column, please rename your column first."
X["_intercept"] = 1.0
return X, T, E, W
def _check_values(df, T, E):
pass_for_numeric_dtypes_or_raise(df)
check_nans_or_infs(T)
check_nans_or_infs(E)
check_nans_or_infs(df)
check_low_var(df)
check_complete_separation(df, E, T)
def _check_values(self, df, T, E, weights, entries):
check_for_numeric_dtypes_or_raise(df)
check_nans_or_infs(df)
check_nans_or_infs(T)
check_nans_or_infs(E)
check_positivity(T)
check_complete_separation(df, E, T, self.event_col)
if self.weights_col:
if (weights.astype(int) != weights).any() and not self.robust:
warnings.warn(
dedent(
"""It appears your weights are not integers, possibly propensity or sampling scores then?
It's important to know that the naive variance estimates of the coefficients are biased. Instead a) set `robust=True` in the call to `fit`, or b) use Monte Carlo to
estimate the variances. See paper "Variance estimation when using inverse probability of treatment weighting (IPTW) with survival analysis"""
),
StatisticalWarning,
)
if (weights <= 0).any():
raise ValueError(
"values in weight column %s must be positive." %
self.weights_col)
if self.entry_col:
count_invalid_rows = (entries > T).sum()
if count_invalid_rows:
warnings.warn(
"""There exist %d rows where entry > duration.""")
def _preprocess_dataframe(self, df):
n, _ = df.shape
df = df.sort_values(by=self.duration_col)
# Extract time and event
T = df.pop(self.duration_col)
E = df.pop(
self.event_col) if (self.event_col is not None) else pd.Series(
np.ones(n), index=df.index, name="E")
W = (df.pop(self.weights_col) if (self.weights_col is not None) else
pd.Series(np.ones((n, )), index=df.index, name="weights"))
# check to make sure their weights are okay
if self.weights_col:
if (W.astype(int) != W).any():
warnings.warn(
"""It appears your weights are not integers, possibly propensity or sampling scores then?
It's important to know that the naive variance estimates of the coefficients are biased."
""",
StatisticalWarning,
)
if (W <= 0).any():
raise ValueError(
"values in weight column %s must be positive." %
self.weights_col)
self.regressors = utils.CovariateParameterMappings(
{"beta_": self.formula}, df, force_intercept=self.fit_intercept)
X = self.regressors.transform_df(df)["beta_"]
T = T.astype(float)
check_nans_or_infs(E)
E = E.astype(bool)
self._check_values(df, T, E)
return X, T, E, W
def _check_values(self, df, T, E, event_col):
check_for_numeric_dtypes_or_raise(df)
check_nans_or_infs(T)
check_nans_or_infs(E)
check_nans_or_infs(df)
check_complete_separation(df, E, T, event_col)
if self.fit_intercept:
check_low_var(df)
def fit(
self,
durations,
event_observed=None,
timeline=None,
label="Weibull_estimate",
alpha=None,
ci_labels=None,
show_progress=False,
): # pylint: disable=too-many-arguments
"""
Parameters
----------
durations: an array, or pd.Series
length n, duration subject was observed for
event_observed: numpy array or pd.Series, optional
length n, True if the the death was observed, False if the event
was lost (right-censored). Defaults all True if event_observed==None
timeline: list, optional
return the estimate at the values in timeline (postively increasing)
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: list, optional
add custom column names to the generated confidence intervals
as a length-2 list: [<lower-bound name>, <upper-bound name>]. Default: <label>_lower_<alpha>
show_progress: boolean, optional
since this is an iterative fitting algorithm, switching this to True will display some iteration details.
Returns
-------
self : WeibullFitter
self with new properties like ``cumulative_hazard_``, ``survival_function_``, ``lambda_``, and ``rho_``.
"""
check_nans_or_infs(durations)
if event_observed is not None:
check_nans_or_infs(event_observed)
self.durations = np.asarray(durations, dtype=float)
# check for negative or 0 durations - these are not allowed in a weibull model.
if np.any(self.durations <= 0):
raise ValueError(
"This model does not allow for non-positive durations. Suggestion: add a small positive value to zero elements."
)
self.event_observed = (
np.asarray(event_observed, dtype=int) if event_observed is not None else np.ones_like(self.durations)
)
if timeline is not None:
self.timeline = np.sort(np.asarray(timeline))
else:
self.timeline = np.linspace(self.durations.min(), self.durations.max(), self.durations.shape[0])
self._label = label
alpha = alpha if alpha is not None else self.alpha
# estimation
(self.lambda_, self.rho_), self._hessian_ = self._newton_rhaphson(
self.durations, self.event_observed, show_progress=show_progress
)
self._log_likelihood = -_negative_log_likelihood((self.lambda_, self.rho_), self.durations, self.event_observed)
self.variance_matrix_ = inv(self._hessian_)
self.survival_function_ = self.survival_function_at_times(self.timeline).to_frame(name=self._label)
self.hazard_ = self.hazard_at_times(self.timeline).to_frame(self._label)
self.cumulative_hazard_ = self.cumulative_hazard_at_times(self.timeline).to_frame(self._label)
self.confidence_interval_ = self._bounds(alpha, ci_labels)
self.median_ = 1.0 / self.lambda_ * (np.log(2)) ** (1.0 / self.rho_)
# estimation methods
self._estimate_name = "cumulative_hazard_"
self._predict_label = label
self._update_docstrings()
# plotting - Cumulative hazard takes priority.
self.plot_cumulative_hazard = self.plot
return self
def fit(self,
durations,
event_observed=None,
timeline=None,
label="LogNormal_estimate",
alpha=0.95,
ci_labels=None): # pylint: disable=too-many-arguments
"""
Parameters
----------
durations: iterable
an array, or pd.Series, of length n -- duration subject was observed for
event_observed: iterable, optional
an array, list, 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
timeline: iterable, optional
return the best estimate at the values in timelines (postively increasing)
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: list, optional
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 : LogNormalFitter
self, with new properties like 'survival_function_', 'sigma_' and 'mu_'.
"""
check_nans_or_infs(durations)
if event_observed is not None:
check_nans_or_infs(event_observed)
self.durations = np.asarray(durations, dtype=float)
self.event_observed = (np.asarray(event_observed, dtype=int)
if event_observed is not None else np.ones_like(
self.durations))
# check for negative or 0 durations - these are not allowed in a weibull model.
if np.any(self.durations <= 0):
raise ValueError(
"This model does not allow for non-positive durations. Suggestion: add a small positive value to zero elements."
)
if timeline is not None:
self.timeline = np.sort(np.asarray(timeline))
else:
self.timeline = np.linspace(self.durations.min(),
self.durations.max(),
self.durations.shape[0])
self._label = label
(self.mu_, self.sigma_
), self._log_likelihood, self.variance_matrix_ = self._fit_model(
self.durations, self.event_observed)
self.survival_function_ = self.survival_function_at_times(
self.timeline).to_frame(name=self._label)
self.hazard_ = self.hazard_at_times(
self.timeline).to_frame(name=self._label)
self.cumulative_hazard_ = self.cumulative_hazard_at_times(
self.timeline).to_frame(name=self._label)
self.median_ = np.exp(self.mu_)
self.confidence_interval_ = self._bounds(alpha, ci_labels)
# estimation methods
self._estimate_name = "cumulative_hazard_"
self._predict_label = label
self._update_docstrings()
# plotting - Cumulative hazard takes priority.
self.plot_cumulative_hazard = self.plot
return self
def _check_values(self, array):
check_nans_or_infs(array)
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 _check_values(self, array):
check_nans_or_infs(array)
def _check_values(self, X, T, E):
check_for_numeric_dtypes_or_raise(X)
check_nans_or_infs(T)
check_nans_or_infs(X)
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
def fit(
self,
durations,
event_observed=None,
timeline=None,
entry=None,
label="KM_estimate",
alpha=None,
left_censorship=False,
ci_labels=None,
weights=None,
): # pylint: disable=too-many-arguments,too-many-locals
"""
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 (not left-censored) observations. If None, all members of the population
were born at time 0.
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>
weights: n array, or pd.Series, of length n, 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_'.
"""
check_nans_or_infs(durations)
if event_observed is not None:
check_nans_or_infs(event_observed)
if weights is not None:
if (weights.astype(int) != weights).any():
warnings.warn(
"""It looks like your weights are not integers, possibly prospenity scores then?
It's important to know that the naive variance estimates of the coefficients are biased. Instead use Monte Carlo to
estimate the variances. See paper "Variance estimation when using inverse probability of treatment weighting (IPTW) with survival analysis"
or "Adjusted Kaplan-Meier estimator and log-rank test with inverse probability of treatment weighting for survival data."
""",
StatisticalWarning,
)
# 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,
weights)
self.durations, self.event_observed, self.timeline, self.entry, self.event_table = v
self._label = label
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)].idxmin()
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],
alpha, ci_labels)
self.median_ = median_survival_times(self.__estimate,
left_censorship=left_censorship)
# estimation methods
self._estimation_method = estimate_name
self._estimate_name = estimate_name
self._predict_label = label
self._update_docstrings()
# plotting functions
setattr(self, "plot_" + estimate_name, self.plot)
return self
def fit(self,
durations,
event_observed=None,
timeline=None,
entry=None,
label='Weibull_estimate',
alpha=None,
ci_labels=None,
show_progress=False):
"""
Parameters:
duration: an array, or pd.Series, of length n -- duration subject was observed for
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
timeline: return the estimate at the values in timeline (postively increasing)
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>
show_progress: since this is an iterative fitting algorithm, switching this to True will display some iteration details.
Returns:
self, with new properties like `cumulative_hazard_', 'survival_function_', 'lambda_' and 'rho_'.
"""
check_nans_or_infs(durations)
if event_observed is not None:
check_nans_or_infs(event_observed)
self.durations = np.asarray(durations, dtype=float)
# check for negative or 0 durations - these are not allowed in a weibull model.
if np.any(self.durations <= 0):
raise ValueError(
'This model does not allow for non-positive durations. Suggestion: add a small positive value to zero elements.'
)
self.event_observed = np.asarray(
event_observed,
dtype=int) if event_observed is not None else np.ones_like(
self.durations)
if timeline is not None:
self.timeline = np.sort(np.asarray(timeline))
else:
self.timeline = np.linspace(self.durations.min(),
self.durations.max(),
self.durations.shape[0])
self._label = label
alpha = alpha if alpha is not None else self.alpha
# estimation
(self.lambda_, self.rho_), self._hessian_ = self._newton_rhaphson(
self.durations, self.event_observed, show_progress=show_progress)
self._log_likelihood = -_negative_log_likelihood(
(self.lambda_, self.rho_), self.durations, self.event_observed)
self.variance_matrix_ = -inv(self._hessian_)
self.survival_function_ = pd.DataFrame(self.survival_function_at_times(
self.timeline),
columns=[self._label],
index=self.timeline)
self.hazard_ = pd.DataFrame(self.hazard_at_times(self.timeline),
columns=[self._label],
index=self.timeline)
self.cumulative_hazard_ = pd.DataFrame(self.cumulative_hazard_at_times(
self.timeline),
columns=[self._label],
index=self.timeline)
self.confidence_interval_ = self._bounds(alpha, ci_labels)
self.median_ = 1. / self.lambda_ * (np.log(2))**(1. / self.rho_)
# estimation methods
self._estimate_name = "cumulative_hazard_"
self._predict_label = label
self._update_docstrings()
# plotting - Cumulative hazard takes priority.
self.plot_cumulative_hazard = self.plot
return self
def _check_values(self, X, T, E):
pass_for_numeric_dtypes_or_raise(X)
check_nans_or_infs(T)
check_nans_or_infs(E)
check_nans_or_infs(X)
def fit(
self, durations, event_observed=None, timeline=None, label="Exponential_estimate", alpha=None, ci_labels=None
): # pylint: disable=too-many-arguments
"""
Parameters
----------
durations: iterable
an array, or pd.Series, of length n -- duration subject was observed for
event_observed: iterable, optional
an array, list, 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
timeline: iterable, optional
return the best estimate at the values in timelines (postively increasing)
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: list, optional
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 : ExponentialFitter
self, with new properties like 'survival_function_', 'cumulative_hazard_', and 'lambda_'.
"""
check_nans_or_infs(durations)
if event_observed is not None:
check_nans_or_infs(event_observed)
self.durations = np.asarray(durations, dtype=float)
self.event_observed = (
np.asarray(event_observed, dtype=int) if event_observed is not None else np.ones_like(self.durations)
)
if timeline is not None:
self.timeline = np.sort(np.asarray(timeline))
else:
self.timeline = np.linspace(self.durations.min(), self.durations.max(), self.durations.shape[0])
self._label = label
# estimation
D = self.event_observed.sum()
T = self.durations.sum()
self.lambda_ = D / T
self._lambda_variance_ = self.lambda_ / T
self._log_likelihood = np.log(self.lambda_) * D - self.lambda_ * T
self.survival_function_ = self.survival_function_at_times(self.timeline).to_frame(self._label)
self.cumulative_hazard_ = self.cumulative_hazard_at_times(self.timeline).to_frame(self._label)
self.hazard_ = self.hazard_at_times(self.timeline).to_frame(self._label)
self.confidence_interval_ = self._bounds(alpha if alpha else self.alpha, ci_labels)
self.median_ = 1.0 / self.lambda_ * (np.log(2))
# estimation methods
self._estimate_name = "cumulative_hazard_"
self._predict_label = label
self._update_docstrings()
# plotting
self.plot_cumulative_hazards_ = self.plot
return self
def _fit(
self,
log_likelihood_function,
df,
Ts,
regressors,
event_col=None,
show_progress=False,
timeline=None,
weights_col=None,
robust=False,
initial_point=None,
entry_col=None,
):
self._time_fit_was_called = datetime.utcnow().strftime(
"%Y-%m-%d %H:%M:%S") + " UTC"
self.weights_col = weights_col
self.entry_col = entry_col
self.event_col = event_col
self._n_examples = df.shape[0]
self.timeline = timeline
self.robust = robust
self.regressors = regressors # TODO name
E = (pass_for_numeric_dtypes_or_raise_array(df.pop(self.event_col)) if
(self.event_col is not None) else pd.Series(np.ones(
self._n_examples, dtype=bool),
index=df.index,
name="E"))
weights = (pass_for_numeric_dtypes_or_raise_array(
df.pop(self.weights_col)).astype(float) if
(self.weights_col is not None) else pd.Series(
np.ones(self._n_examples, dtype=float),
index=df.index,
name="weights"))
entries = (pass_for_numeric_dtypes_or_raise_array(
df.pop(entry_col)).astype(float) if (entry_col is not None) else
pd.Series(np.zeros(self._n_examples, dtype=float),
index=df.index,
name="entry"))
check_nans_or_infs(E)
E = E.astype(bool)
self.event_observed = E.copy()
self.entry = entries.copy()
self.weights = weights.copy()
df = df.astype(float)
self._check_values(df, coalesce(Ts[1], Ts[0]), E, weights, entries)
check_for_numeric_dtypes_or_raise(df)
check_nans_or_infs(df)
_norm_std = df.std(0)
_norm_std[_norm_std < 1e-8] = 1.0
df_normalized = normalize(df, 0, _norm_std)
Xs = self._create_Xs_dict(df_normalized)
self._LOOKUP_SLICE = self._create_slicer(Xs)
_index = pd.MultiIndex.from_tuples(
sum(([(name, col) for col in columns]
for name, columns in regressors.items()), []))
self._norm_std = pd.Series(
[_norm_std.loc[variable_name] for _, variable_name in _index],
index=_index)
_params, self._log_likelihood, self._hessian_ = self._fit_model(
log_likelihood_function,
Ts,
Xs,
E.values,
weights.values,
entries.values,
show_progress=show_progress,
initial_point=initial_point,
)
self.params_ = _params / self._norm_std
self.variance_matrix_ = self._compute_variance_matrix()
self.standard_errors_ = self._compute_standard_errors(
Ts, E.values, weights.values, entries.values, Xs)
self.confidence_intervals_ = self._compute_confidence_intervals()
self._predicted_median = self.predict_median(df)
def fit(
self,
durations,
event_observed=None,
timeline=None,
label=None,
alpha=None,
ci_labels=None,
show_progress=False,
entry=None,
): # pylint: disable=too-many-arguments
"""
Parameters
----------
durations: an array, or pd.Series
length n, duration subject was observed for
event_observed: numpy array or pd.Series, optional
length n, True if the the death was observed, False if the event was lost (right-censored). Defaults all True if event_observed==None
timeline: list, optional
return the estimate at the values in timeline (postively increasing)
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: list, optional
add custom column names to the generated confidence intervals as a length-2 list: [<lower-bound name>, <upper-bound name>]. Default: <label>_lower_<alpha>
show_progress: boolean, optional
since this is an iterative fitting algorithm, switching this to True will display some iteration details.
entry: an array, or pd.Series, of length n
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": time zero.
Returns
-------
self : WeibullFitter
self with new properties like ``cumulative_hazard_``, ``survival_function_``
"""
label = coalesce(
label,
self.__class__.__name__.replace("Fitter", "") + "_estimate")
check_nans_or_infs(durations)
if event_observed is not None:
check_nans_or_infs(event_observed)
self.durations = np.asarray(durations, dtype=float)
# check for negative or 0 durations - these are not allowed in a weibull model.
if np.any(self.durations <= 0):
raise ValueError(
"This model does not allow for non-positive durations. Suggestion: add a small positive value to zero elements."
)
if not self._KNOWN_MODEL:
self._check_cumulative_hazard_is_monotone_and_positive(
self.durations, self._initial_values)
self.event_observed = (np.asarray(event_observed, dtype=int)
if event_observed is not None else np.ones_like(
self.durations))
self.entry = np.asarray(entry) if entry is not None else np.zeros_like(
self.durations)
if timeline is not None:
self.timeline = np.sort(np.asarray(timeline))
else:
self.timeline = np.linspace(self.durations.min(),
self.durations.max(),
self.durations.shape[0])
self._label = label
self._ci_labels = ci_labels
self.alpha = coalesce(alpha, self.alpha)
# estimation
self._fitted_parameters_, self._log_likelihood, self._hessian_ = self._fit_model(
self.durations,
self.event_observed.astype(bool),
self.entry,
show_progress=show_progress)
if not self._KNOWN_MODEL:
self._check_cumulative_hazard_is_monotone_and_positive(
self.durations, self._fitted_parameters_)
for param_name, fitted_value in zip(self._fitted_parameter_names,
self._fitted_parameters_):
setattr(self, param_name, fitted_value)
try:
self.variance_matrix_ = inv(self._hessian_)
except np.linalg.LinAlgError:
self.variance_matrix_ = pinv(self._hessian_)
warning_text = dedent("""\
The hessian was not invertable. This could be a model problem:
1. Are two parameters in the model colinear / exchangeable?
2. Is the cumulative hazard always non-negative and always non-decreasing?
3. Are there cusps/ in the cumulative hazard?
We will instead approximate it using the psuedo-inverse.
It's advisable to not trust the variances reported, and to be suspicious of the
fitted parameters too. Perform plots of the cumulative hazard to help understand
the latter's bias.
""")
warnings.warn(warning_text, StatisticalWarning)
self._predict_label = label
self._update_docstrings()
self.survival_function_ = self.survival_function_at_times(
self.timeline).to_frame()
self.hazard_ = self.hazard_at_times(self.timeline).to_frame()
self.cumulative_hazard_ = self.cumulative_hazard_at_times(
self.timeline).to_frame()
return self
