fix tests

CHANGELOG.md

@@ -8,6 +8,7 @@
    - removed the time-varying component from `AalenAdditiveFitter`. This will return in a future release.
    - new `print_summary`
    - `weights_col` is added
+   - `nn_cumulative_hazard` is removed (may add back)
 
 
 #### 0.16.3

lifelines/fitters/aalen_additive_fitter.py

@@ -8,13 +8,14 @@
 import pandas as pd
 from numpy.linalg import LinAlgError
 from scipy import stats
+from scipy.integrate import trapz
 
 from lifelines.fitters import BaseFitter
 from lifelines.utils import (
     _get_index,
     inv_normal_cdf,
     epanechnikov_kernel,
-    ridge_regression_plus as lr,
+    ridge_regression as lr,
     qth_survival_times,
     pass_for_numeric_dtypes_or_raise,
     concordance_index,
@@ -216,9 +217,7 @@ def _fit_model_to_data_batch(self, X, T, E, weights, show_progress):
             exits = T == t
             deaths = exits & E
             try:
-                R = lr(X, W * deaths, c1=self.coef_penalizer, c2=self.smoothing_penalizer, offset=v, ix=deaths)
-                V = R[:, :-1]
-                v = R[:, -1]
+                v, V = lr(X, W * deaths, c1=self.coef_penalizer, c2=self.smoothing_penalizer, offset=v, ix=deaths)
             except LinAlgError:
                 warnings.warn(
                     "Linear regression error at index=%d, time=%.3f. Try increasing the coef_penalizer value." % (i, t),

lifelines/utils/__init__.py

@@ -693,7 +693,7 @@ def significance_codes_as_text():
     return "Signif. codes: " + " ".join(["%s '%s'" % (p, significance_code(p)) for p in p_values]) + " 1"
 
 
-def ridge_regression_plus(X, Y, c1=0.0, c2=0.0, offset=None, ix=None):
+def ridge_regression(X, Y, c1=0.0, c2=0.0, offset=None, ix=None):
     """
     Also known as Tikhonov regularization. This solves the minimization problem:
 
@@ -732,7 +732,8 @@ def ridge_regression_plus(X, Y, c1=0.0, c2=0.0, offset=None, ix=None):
         M = np.c_[X.T[:, ix], b]
     else:
         M = np.c_[X.T, b]
-    return solve(A, M, assume_a="pos", check_finite=False)
+    R = solve(A, M, assume_a="pos", check_finite=False)
+    return R[:, -1], R[:, :-1]
 
 
 def _smart_search(minimizing_function, n, *args):

tests/test_estimation.py

@@ -2503,7 +2503,7 @@ def test_cumulative_hazards_versus_R(self, aaf, regression_dataset):
         regression_dataset["E"] = 1
 
         aaf.fit(regression_dataset, "T", "E")
-        actual = aaf.cumulative_hazards_.loc[regression_dataset["T"].max()]
+        actual = aaf.cumulative_hazards_.iloc[-1]
         npt.assert_allclose(actual["baseline"], 2.1675130235, rtol=1e-06)
         npt.assert_allclose(actual["var1"], 0.6820086125, rtol=1e-06)
         npt.assert_allclose(actual["var2"], -0.0776583514, rtol=1e-06)