plotting¶
-
lifelines.plotting.
add_at_risk_counts
(*fitters, labels: Union[Iterable[T_co], bool, None] = None, rows_to_show=None, ypos=-0.6, xticks=None, ax=None, at_risk_count_from_start_of_period=False, **kwargs)¶ Add counts showing how many individuals were at risk, censored, and observed, at each time point in survival/hazard plots.
Tip: you probably want to call
plt.tight_layout()
afterwards.Parameters: - fitters – One or several fitters, for example KaplanMeierFitter, WeibullFitter, NelsonAalenFitter, etc…
- labels – provide labels for the fitters, default is to use the provided fitter label. Set to False for no labels.
- rows_to_show (list) – a sub-list of [‘At risk’, ‘Censored’, ‘Events’]. Default to show all.
- ypos – make more positive to move the table up.
- xticks (list) – specify the time periods (as a list) you want to evaluate the counts at.
- at_risk_count_from_start_of_period (bool, default False.) – By default, we use the at-risk count from the end of the period. This is what other packages, and KMunicate suggests, but the same issue keeps coming up with users. #1383, #1316 and discussion #1229. This makes the adjustment.
- ax – a matplotlib axes
Returns: The axes which was used.
Return type: ax
Examples
# First train some fitters and plot them fig = plt.figure() ax = plt.subplot(111) f1 = KaplanMeierFitter() f1.fit(data) f1.plot(ax=ax) f2 = KaplanMeierFitter() f2.fit(data) f2.plot(ax=ax) # These calls below are equivalent add_at_risk_counts(f1, f2) add_at_risk_counts(f1, f2, ax=ax, fig=fig) plt.tight_layout() # This overrides the labels add_at_risk_counts(f1, f2, labels=['fitter one', 'fitter two']) plt.tight_layout() # This hides the labels add_at_risk_counts(f1, f2, labels=False) plt.tight_layout() # Only show at-risk: add_at_risk_counts(f1, f2, rows_to_show=['At risk']) plt.tight_layout()
References
Morris TP, Jarvis CI, Cragg W, et al. Proposals on Kaplan–Meier plots in medical research and a survey of stakeholder views: KMunicate. BMJ Open 2019;9:e030215. doi:10.1136/bmjopen-2019-030215
-
lifelines.plotting.
plot_lifetimes
(durations, event_observed=None, entry=None, left_truncated=False, sort_by_duration=True, event_observed_color='#A60628', event_censored_color='#348ABD', ax=None, **kwargs)¶ Returns a lifetime plot, see examples: https://lifelines.readthedocs.io/en/latest/Survival%20Analysis%20intro.html#Censoring
Parameters: - durations ((n,) numpy array or pd.Series) – duration (relative to subject’s birth) the subject was alive for.
- event_observed ((n,) numpy array or pd.Series) – array of booleans: True if event observed, else False.
- entry ((n,) numpy array or pd.Series) – offsetting the births away from t=0. This could be from left-truncation, or delayed entry into study.
- left_truncated (boolean) – if entry is provided, and the data is left-truncated, this will display additional information in the plot to reflect this.
- sort_by_duration (boolean) – sort by the duration vector
- event_observed_color (str) – default: “#A60628”
- event_censored_color (str) – default: “#348ABD”
Returns: Return type: ax
Examples
from lifelines.datasets import load_waltons from lifelines.plotting import plot_lifetimes T, E = load_waltons()["T"], load_waltons()["E"] ax = plot_lifetimes(T.loc[:50], event_observed=E.loc[:50])
-
lifelines.plotting.
plot_interval_censored_lifetimes
(lower_bound, upper_bound, entry=None, left_truncated=False, sort_by_lower_bound=True, event_observed_color='#A60628', event_right_censored_color='#348ABD', ax=None, **kwargs)¶ Returns a lifetime plot for interval censored data.
Parameters: - lower_bound ((n,) numpy array or pd.Series) – the start of the period the subject experienced the event in.
- upper_bound ((n,) numpy array or pd.Series) – the end of the period the subject experienced the event in. If the value is equal to the corresponding value in lower_bound, then the individual’s event was observed (not censored).
- entry ((n,) numpy array or pd.Series) – offsetting the births away from t=0. This could be from left-truncation, or delayed entry into study.
- left_truncated (boolean) – if entry is provided, and the data is left-truncated, this will display additional information in the plot to reflect this.
- sort_by_lower_bound (boolean) – sort by the lower_bound vector
- event_observed_color (str) – default: “#A60628”
- event_right_censored_color (str) – default: “#348ABD” applies to any individual with an upper bound of infinity.
Returns: Return type: ax
Examples
import pandas as pd import numpy as np from lifelines.plotting import plot_interval_censored_lifetimes df = pd.DataFrame({'lb':[20,15,30, 10, 20, 30], 'ub':[25, 15, np.infty, 20, 20, np.infty]}) ax = plot_interval_censored_lifetimes(lower_bound=df['lb'], upper_bound=df['ub'])
-
lifelines.plotting.
qq_plot
(model, ax=None, scatter_color='k', **plot_kwargs)¶ Produces a quantile-quantile plot of the empirical CDF against the fitted parametric CDF. Large deviances away from the line y=x can invalidate a model (though we expect some natural deviance in the tails).
Parameters: - model (obj) – A fitted lifelines univariate parametric model, like
WeibullFitter
- plot_kwargs – kwargs for the plot.
Returns: The axes which was used.
Return type: ax
Examples
from lifelines import * from lifelines.plotting import qq_plot from lifelines.datasets import load_rossi df = load_rossi() wf = WeibullFitter().fit(df['week'], df['arrest']) qq_plot(wf)
Notes
The interval censoring case uses the mean between the upper and lower bounds.
- model (obj) – A fitted lifelines univariate parametric model, like
-
lifelines.plotting.
cdf_plot
(model, timeline=None, ax=None, **plot_kwargs)¶ This plot compares the empirical CDF (derived by KaplanMeier) vs the model CDF.
Parameters: - model (lifelines univariate model)
- timeline (iterable)
- ax (matplotlib axis)
-
lifelines.plotting.
rmst_plot
(model, model2=None, t=inf, ax=None, text_position=None, **plot_kwargs)¶ This functions plots the survival function of the model plus it’s area-under-the-curve (AUC) up until the point
t
. The AUC is known as the restricted mean survival time (RMST).To compare the difference between two models’ survival curves, you can supply an additional model in
model2
.Parameters: - model (lifelines.UnivariateFitter)
- model2 (lifelines.UnivariateFitter, optional) – used to compute the delta RMST of two models
- t (float) – the upper bound of the expectation
- ax (axis)
- text_position (tuple) – move the text position of the RMST.
Examples
from lifelines.utils import restricted_mean_survival_time from lifelines.datasets import load_waltons from lifelines.plotting import rmst_plot df = load_waltons() ix = df['group'] == 'miR-137' T, E = df['T'], df['E'] time_limit = 50 kmf_exp = KaplanMeierFitter().fit(T[ix], E[ix], label='exp') kmf_con = KaplanMeierFitter().fit(T[~ix], E[~ix], label='control') ax = plt.subplot(311) rmst_plot(kmf_exp, t=time_limit, ax=ax) ax = plt.subplot(312) rmst_plot(kmf_con, t=time_limit, ax=ax) ax = plt.subplot(313) rmst_plot(kmf_exp, model2=kmf_con, t=time_limit, ax=ax)
-
lifelines.plotting.
loglogs_plot
(cls, loc=None, iloc=None, show_censors=False, censor_styles=None, ax=None, **kwargs)¶ Specifies a plot of the log(-log(SV)) versus log(time) where SV is the estimated survival function.