Visualization and prediction with Weibull model

Survival Analysis in Python

Shae Wang

Senior Data Scientist

.plot()

Returns a plot of the coefficients and their ranges from the 95% confidence intervals.

aft.plot()
plt.show()

Sample plot:

sample_covariate_plot

Returns a plot comparing the baseline survival curve versus what happens when covariates are varied over values.

aft.plot_partial_effects_on_outcome(covariates, values)
plt.show()

sample_partial_effects_plot

.plot_partial_effects_on_outcome()

covariates (string or list): covariate(s) in the original dataset that we wish to vary.
values (1d or 2d iterable): values we wish the covariate to take on.
Baseline survival curve: predicted survival curve at all average values in the original dataset.

aft.plot_partial_effects_on_outcome(
  covariates='var', 
  values=[0, 3, 6, 9, 12, 15]
)
plt.show()

partial effects plot for weibull model

Hard-code values:

aft.plot_partial_effects_on_outcome(
  covariates='a', 
  values=[0, 3, 6]
)

Use a range function:

aft.plot_partial_effects_on_outcome(
  covariates='a', 
  values=np.arange(10)
)

Multiple covariates:

aft.plot_partial_effects_on_outcome(
  covariates=['a','b'], 
  values=[[1,2],[1,3],[2,3]]
)

Custom formula:
- Necessary transformations (interactions, one-hot encoding, etc.) will be made internally and automatically.

DataFrame example: mortgage_df

id	house	principal	interest	property_tax	credit score	duration	paid_off
1	1	1275	0.035	0.019	780	25	0
2	0	756	0.028	0.020	695	17	1
3	0	968	0.029	0.017	810	5	0
...	...	...	...	...	...	...	...
1000	1	1505	0.041	0.023	750	30	1

aft.plot_partial_effects_on_outcome(
    covariates='credit score',
    values=np.arange(700, 860, 30)
)
plt.show()

partial effects plot for mortgage_df

Predict survival functions of individuals based on covariate values.

.predict_survival_function()

Arguments:

X (np array or DataFrame): covariates. If a DataFrame, columns can be in any order.

Predict median survival durations of individuals based on covariate values.

.predict_median()

Arguments:

df (np array or DataFrame): covariates. If a DataFrame, columns can be in any order.

Predict survival function or median survival duration conditional after current duration.

Example:

aft.predict_median(new_subject)

4.0

aft.predict_median(new_subject, conditional_after=[2])

2.0

Survival Analysis in Python