def test_brier_coxph():
X, y = load_gbsg2()
X.loc[:, "tgrade"] = X.loc[:, "tgrade"].map(len).astype(int)
Xt = OneHotEncoder().fit_transform(X)
est = CoxPHSurvivalAnalysis(ties="efron").fit(Xt, y)
survs = est.predict_survival_function(Xt)
preds = [fn(1825) for fn in survs]
_, score = brier_score(y, y, preds, 1825)
assert round(abs(score[0] - 0.208817407492645), 5) == 0
estimator = CoxPHSurvivalAnalysis()
estimator.fit(data_x_numeric, data_y)
pd.Series(estimator.coef_, index=data_x_numeric.columns)
x_new = pd.DataFrame.from_dict({
1: [65, 0, 0, 1, 60, 1, 0, 1],
2: [65, 0, 0, 1, 60, 1, 0, 0],
3: [65, 0, 1, 0, 60, 1, 0, 0],
4: [65, 0, 1, 0, 60, 1, 0, 1]},
columns=data_x_numeric.columns, orient='index')
x_new
import numpy as np
pred_surv = estimator.predict_survival_function(x_new)
time_points = np.arange(1, 1000)
for i, surv_func in enumerate(pred_surv):
plt.step(time_points, surv_func(time_points), where="post",
label="Sample %d" % (i + 1))
plt.ylabel("est. probability of survival $\hat{S}(t)$")
plt.xlabel("time $t$")
plt.legend(loc="best")
from sksurv.metrics import concordance_index_censored
prediction = estimator.predict(data_x_numeric)
result = concordance_index_censored(data_y["Status"], data_y["Survival_in_days"], prediction)
result[0]
