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 ---------- durations: an array, list, pd.DataFrame or pd.Series length n -- duration subject was observed for 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). Defaults all True if event_observed==None timeline: an array, list, pd.DataFrame, or pd.Series, optional return the best estimate at the values in timelines (postively 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. left_censorship: bool, optional (default=False) True if durations and event_observed refer to left censorship events. Default False 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`` """ self._check_values(durations) if event_observed is not None: self._check_values(event_observed) if weights is not None: if (weights.astype(int) != weights).any(): warnings.warn( """It looks like your weights are not integers, possibly propensity 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>%g. 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) self._cumulative_sq_ = cumulative_sq_ # estimation methods self._estimation_method = estimate_name self._estimate_name = estimate_name self._predict_label = label self._update_docstrings() 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, 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 (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, with new properties like 'survival_function_'. """ check_nans(durations) if event_observed is not None: check_nans(event_observed) # 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.predict = self._predict(estimate_name, label) self.subtract = self._subtract(estimate_name) self.divide = self._divide(estimate_name) # plotting functions self.plot = self._plot_estimate(estimate_name) setattr(self, "plot_" + estimate_name, self.plot) self.plot_loglogs = plot_loglogs(self) return self