def test_coxph_plot_covariate_groups_with_nonnumeric_strata(self, block):
df = load_rossi()
df["strata"] = np.random.choice(["A", "B"], size=df.shape[0])
cp = CoxPHFitter()
cp.fit(df, "week", "arrest", strata="strata")
cp.plot_covariate_groups("age", [10, 50, 80])
self.plt.title("test_coxph_plot_covariate_groups_with_single_strata")
self.plt.show(block=block)
def test_weibull_aft_plot_partial_effects_on_outcome(self, block):
df = load_rossi()
aft = WeibullAFTFitter()
aft.fit(df, "week", "arrest")
aft.plot_partial_effects_on_outcome("age", [10, 50, 80])
self.plt.tight_layout()
self.plt.title("test_weibull_aft_plot_partial_effects_on_outcome")
self.plt.show(block=block)
def test_coxph_plot_covariate_groups_with_multiple_variables_and_strata(self, block):
df = load_rossi()
df["strata"] = np.random.choice(["A", "B"], size=df.shape[0])
cp = CoxPHFitter()
cp.fit(df, "week", "arrest", strata="strata")
cp.plot_covariate_groups(["age", "prio"], [[10, 0], [50, 10], [80, 90]])
self.plt.title("test_coxph_plot_covariate_groups_with_multiple_variables_and_strata")
self.plt.show(block=block)
def test_weibull_aft_plot_covariate_groups(self, block):
df = load_rossi()
aft = WeibullAFTFitter()
aft.fit(df, "week", "arrest")
aft.plot_covariate_groups("age", [10, 50, 80])
self.plt.tight_layout()
self.plt.title("test_weibull_aft_plot_covariate_groups")
self.plt.show(block=block)
def test_coxph_plot_partial_effects_on_outcome_with_strata(self, block):
df = load_rossi()
cp = CoxPHFitter()
cp.fit(df, "week", "arrest", strata=["paro", "fin"])
cp.plot_partial_effects_on_outcome("age", [10, 50, 80])
self.plt.title(
"test_coxph_plot_partial_effects_on_outcome_with_strata")
self.plt.show(block=block)
def test_weibull_aft_plot_covariate_groups_with_multiple_columns(self, block):
df = load_rossi()
aft = WeibullAFTFitter()
aft.fit(df, "week", "arrest")
aft.plot_covariate_groups(["age", "prio"], [[10, 0], [50, 10], [80, 50]])
self.plt.tight_layout()
self.plt.title("test_weibull_aft_plot_covariate_groups_with_multiple_columns")
self.plt.show(block=block)
def test_using_a_custom_timeline_in_static_fitting(self):
rossi = load_rossi()
aaf = AalenAdditiveFitter()
timeline = np.arange(10)
aaf.fit(rossi, event_col='week', duration_col='arrest', timeline=timeline)
npt.assert_array_equal(aaf.hazards_.index.values, timeline)
npt.assert_array_equal(aaf.cumulative_hazards_.index.values, timeline)
npt.assert_array_equal(aaf.variance_.index.values, timeline)
npt.assert_array_equal(aaf.timeline, timeline)
def test_using_a_custom_timeline_in_static_fitting(self):
rossi = load_rossi()
aaf = AalenAdditiveFitter()
timeline = np.arange(10)
aaf.fit(rossi, event_col='week', duration_col='arrest', timeline=timeline)
npt.assert_array_equal(aaf.hazards_.index.values, timeline)
npt.assert_array_equal(aaf.cumulative_hazards_.index.values, timeline)
npt.assert_array_equal(aaf.variance_.index.values, timeline)
npt.assert_array_equal(aaf.timeline, timeline)
def test_coxph_plot_covariate_groups_with_multiple_variables(self, block):
df = load_rossi()
cp = CoxPHFitter()
cp.fit(df, "week", "arrest")
cp.plot_covariate_groups(["age", "prio"],
[[10, 0], [50, 10], [80, 90]])
self.plt.title(
"test_coxph_plot_covariate_groups_with_multiple_variables")
self.plt.show(block=block)
def test_aft_plot_partial_effects_on_outcome_with_categorical(self, block):
df = load_rossi()
df["cat"] = np.random.choice(["a", "b", "c"], size=df.shape[0])
aft = WeibullAFTFitter()
aft.fit(df, "week", "arrest", formula="cat + age + fin")
aft.plot_partial_effects_on_outcome("cat", values=["a", "b", "c"])
self.plt.title(
"test_aft_plot_partial_effects_on_outcome_with_categorical")
self.plt.show(block=block)
def test_coxph_plot_partial_effects_on_outcome_with_cumulative_hazard(
self, block):
df = load_rossi()
cp = CoxPHFitter()
cp.fit(df, "week", "arrest")
cp.plot_partial_effects_on_outcome("age", [10, 50, 80],
y="cumulative_hazard")
self.plt.title("test_coxph_plot_partial_effects_on_outcome")
self.plt.show(block=block)
def test_survival_probability_calibration_on_out_of_sample_data(
self, block):
rossi = load_rossi()
rossi = rossi.sample(frac=1.0)
cph = CoxPHFitter().fit(rossi.loc[:300], "week", "arrest")
survival_probability_calibration(cph, rossi.loc[300:], 25)
self.plt.title(
"test_survival_probability_calibration_on_out_of_sample_data")
self.plt.show(block=block)
def get_rossi_dataset():
from lifelines.datasets import load_rossi
df = load_rossi()
T_train = df.pop("week").values
E_train = df.pop("arrest").values
X_train = df.values
return X_train, T_train, E_train
def test_spline_coxph_plot_partial_effects_on_outcome_with_strata(
self, block):
df = load_rossi()
cp = CoxPHFitter(baseline_estimation_method="spline",
n_baseline_knots=2)
cp.fit(df, "week", "arrest", strata=["wexp"])
cp.plot_partial_effects_on_outcome("age", [10, 50, 80])
self.plt.title(
"test_spline_coxph_plot_partial_effects_on_outcome_with_strata")
self.plt.show(block=block)
def test_right_censorship_cdf_plots(self, block):
df = load_rossi()
fig, axes = self.plt.subplots(2, 2, figsize=(9, 5))
axes = axes.reshape(4)
for i, model in enumerate([WeibullFitter(), LogNormalFitter(), LogLogisticFitter(), ExponentialFitter()]):
model.fit(df["week"], df["arrest"])
ax = cdf_plot(model, ax=axes[i])
assert ax is not None
self.plt.suptitle("test_right_censorship_cdf_plots")
self.plt.show(block=block)
def test_input_column_order_is_equal_to_output_hazards_order(self):
rossi = load_rossi()
aaf = AalenAdditiveFitter()
expected = ['fin', 'age', 'race', 'wexp', 'mar', 'paro', 'prio']
aaf.fit(rossi, event_col='week', duration_col='arrest')
assert list(aaf.cumulative_hazards_.columns.drop('baseline')) == expected
aaf = AalenAdditiveFitter(fit_intercept=False)
expected = ['fin', 'age', 'race', 'wexp', 'mar', 'paro', 'prio']
aaf.fit(rossi, event_col='week', duration_col='arrest')
assert list(aaf.cumulative_hazards_.columns) == expected
def test_input_column_order_is_equal_to_output_hazards_order(self):
rossi = load_rossi()
aaf = AalenAdditiveFitter()
expected = ['fin', 'age', 'race', 'wexp', 'mar', 'paro', 'prio']
aaf.fit(rossi, event_col='week', duration_col='arrest')
assert list(aaf.cumulative_hazards_.columns.drop('baseline')) == expected
aaf = AalenAdditiveFitter(fit_intercept=False)
expected = ['fin', 'age', 'race', 'wexp', 'mar', 'paro', 'prio']
aaf.fit(rossi, event_col='week', duration_col='arrest')
assert list(aaf.cumulative_hazards_.columns) == expected
def test_penalizer_reduces_norm_of_hazards(self):
from numpy.linalg import norm
rossi = load_rossi()
aaf_without_penalizer = AalenAdditiveFitter(coef_penalizer=0., smoothing_penalizer=0.)
assert aaf_without_penalizer.coef_penalizer == aaf_without_penalizer.smoothing_penalizer == 0.0
aaf_without_penalizer.fit(rossi, event_col='week', duration_col='arrest')
aaf_with_penalizer = AalenAdditiveFitter(coef_penalizer=10., smoothing_penalizer=10.)
aaf_with_penalizer.fit(rossi, event_col='week', duration_col='arrest')
assert norm(aaf_with_penalizer.cumulative_hazards_) <= norm(aaf_without_penalizer.cumulative_hazards_)
def test_penalizer_reduces_norm_of_hazards(self):
from numpy.linalg import norm
rossi = load_rossi()
aaf_without_penalizer = AalenAdditiveFitter(coef_penalizer=0., smoothing_penalizer=0.)
assert aaf_without_penalizer.coef_penalizer == aaf_without_penalizer.smoothing_penalizer == 0.0
aaf_without_penalizer.fit(rossi, event_col='week', duration_col='arrest')
aaf_with_penalizer = AalenAdditiveFitter(coef_penalizer=10., smoothing_penalizer=10.)
aaf_with_penalizer.fit(rossi, event_col='week', duration_col='arrest')
assert norm(aaf_with_penalizer.cumulative_hazards_) <= norm(aaf_without_penalizer.cumulative_hazards_)
def test_coxph_plot_partial_effects_on_outcome_with_multiple_variables(
self, block):
df = load_rossi()
cp = CoxPHFitter()
cp.fit(df, "week", "arrest")
cp.plot_partial_effects_on_outcome(["age", "prio"],
[[10, 0], [50, 10], [80, 90]])
self.plt.title(
"test_coxph_plot_partial_effects_on_outcome_with_multiple_variables"
)
self.plt.show(block=block)
def test_penalized_output_against_R(self):
# R code:
#
# rossi <- read.csv('.../lifelines/datasets/rossi.csv')
# mod.allison <- coxph(Surv(week, arrest) ~ ridge(fin, age, race, wexp, mar, paro, prio,
# theta=1.0, scale=FALSE), data=rossi)
# cat(round(mod.allison$coefficients, 4), sep=", ")
expected = np.array([[-0.3641, -0.0580, 0.2894, -0.1496, -0.3837, -0.0822, 0.0913]])
df = load_rossi()
cf = CoxPHFitter(normalize=False, penalizer=1.0)
cf.fit(df, duration_col='week', event_col='arrest')
npt.assert_array_almost_equal(cf.hazards_.values, expected, decimal=3)
def test_penalized_output_against_R(self):
# R code:
#
# rossi <- read.csv('.../lifelines/datasets/rossi.csv')
# mod.allison <- coxph(Surv(week, arrest) ~ ridge(fin, age, race, wexp, mar, paro, prio,
# theta=1.0, scale=FALSE), data=rossi)
# cat(round(mod.allison$coefficients, 4), sep=", ")
expected = np.array([[-0.3641, -0.0580, 0.2894, -0.1496, -0.3837, -0.0822, 0.0913]])
df = load_rossi()
cf = CoxPHFitter(normalize=False, penalizer=1.0)
cf.fit(df, duration_col='week', event_col='arrest')
npt.assert_array_almost_equal(cf.hazards_.values, expected, decimal=3)
def test_to_episodic_format_with_long_time_gap_is_identical(self):
rossi = load_rossi()
rossi["id"] = np.arange(rossi.shape[0])
long_rossi = utils.to_episodic_format(rossi, duration_col="week", event_col="arrest", id_col="id", time_gaps=1000.0)
# using astype(int) would fail on Windows because int32 and int64 are used as dtype
long_rossi["week"] = long_rossi["stop"].astype(rossi["week"].dtype)
del long_rossi["start"]
del long_rossi["stop"]
assert_frame_equal(long_rossi, rossi, check_like=True)
def test_output_against_R(self):
# from http://cran.r-project.org/doc/contrib/Fox-Companion/appendix-cox-regression.pdf
# Link is now broken, but this is the code:
#
# rossi <- read.csv('.../lifelines/datasets/rossi.csv')
# mod.allison <- coxph(Surv(week, arrest) ~ fin + age + race + wexp + mar + paro + prio,
# data=rossi)
# cat(round(mod.allison$coefficients, 4), sep=", ")
expected = np.array([[-0.3794, -0.0574, 0.3139, -0.1498, -0.4337, -0.0849, 0.0915]])
df = load_rossi()
cf = CoxPHFitter(normalize=False)
cf.fit(df, duration_col='week', event_col='arrest')
npt.assert_array_almost_equal(cf.hazards_.values, expected, decimal=3)
def test_cox_concordance():
""" test based on lifelines doc example from lifelines.readthedocs.io
Warning: doc example has multivariable result, here is one variable result """
rossi_dataset = load_rossi()
example = Survival(rossi_dataset, 'week',
'arrest').stratify('fin', ['no fin', 'fin'])
cox_model = example.cox_model_fitted
concordance_value = concordance_index(
cox_model.durations,
-cox_model.predict_partial_hazard(cox_model.data).values.ravel(),
cox_model.event_observed)
np.testing.assert_allclose(concordance_value, 0.545735287211, atol=0.005)
def test_to_episodic_format_with_long_time_gap_is_identical(self):
rossi = load_rossi()
rossi["id"] = np.arange(rossi.shape[0])
long_rossi = utils.to_episodic_format(
rossi, duration_col="week", event_col="arrest", id_col="id", time_gaps=1000.0
)
long_rossi["week"] = long_rossi["stop"].astype(int)
del long_rossi["start"]
del long_rossi["stop"]
assert_frame_equal(long_rossi, rossi, check_like=True)
def test_output_against_R(self):
# from http://cran.r-project.org/doc/contrib/Fox-Companion/appendix-cox-regression.pdf
# Link is now broken, but this is the code:
#
# rossi <- read.csv('.../lifelines/datasets/rossi.csv')
# mod.allison <- coxph(Surv(week, arrest) ~ fin + age + race + wexp + mar + paro + prio,
# data=rossi)
# cat(round(mod.allison$coefficients, 4), sep=", ")
expected = np.array([[-0.3794, -0.0574, 0.3139, -0.1498, -0.4337, -0.0849, 0.0915]])
df = load_rossi()
cf = CoxPHFitter(normalize=False)
cf.fit(df, duration_col='week', event_col='arrest')
npt.assert_array_almost_equal(cf.hazards_.values, expected, decimal=3)
def test_summary(self):
cp = CoxPHFitter()
df = load_rossi()
cp.fit(df, duration_col='week', event_col='arrest')
summDf = cp.summary
expectedColumns = ['coef',
'exp(coef)',
'se(coef)',
'z',
'p',
'lower 0.95',
'upper 0.95']
assert all([col in summDf.columns for col in expectedColumns])
def test_strata_against_r_output(self):
"""
> r = coxph(formula = Surv(week, arrest) ~ fin + age + strata(race,
paro, mar, wexp) + prio, data = rossi)
> r
> r$loglik
"""
df = load_rossi()
cp = CoxPHFitter(normalize=False)
cp.fit(df, 'week', 'arrest', strata=['race', 'paro', 'mar', 'wexp'], include_likelihood=True)
npt.assert_almost_equal(cp.summary['coef'].values, [-0.335, -0.059, 0.100], decimal=3)
assert abs(cp._log_likelihood - -436.9339) / 436.9339 < 0.01
def test_strata_against_r_output(self):
"""
> r = coxph(formula = Surv(week, arrest) ~ fin + age + strata(race,
paro, mar, wexp) + prio, data = rossi)
> r
> r$loglik
"""
df = load_rossi()
cp = CoxPHFitter(normalize=False)
cp.fit(df, 'week', 'arrest', strata=['race', 'paro', 'mar', 'wexp'], include_likelihood=True)
npt.assert_almost_equal(cp.summary['coef'].values, [-0.335, -0.059, 0.100], decimal=3)
assert abs(cp._log_likelihood - -436.9339) / 436.9339 < 0.01
def test_summary(self):
cp = CoxPHFitter()
df = load_rossi()
cp.fit(df, duration_col='week', event_col='arrest')
summDf = cp.summary
expectedColumns = ['coef',
'exp(coef)',
'se(coef)',
'z',
'p',
'lower 0.95',
'upper 0.95']
assert all([col in summDf.columns for col in expectedColumns])
def test_swapping_order_of_columns_in_a_df_is_okay(self):
rossi = load_rossi()
aaf = AalenAdditiveFitter()
aaf.fit(rossi, event_col='week', duration_col='arrest')
misorder = ['age', 'race', 'wexp', 'mar', 'paro', 'prio', 'fin']
natural_order = rossi.columns.drop(['week', 'arrest'])
deleted_order = rossi.columns - ['week', 'arrest']
assert_frame_equal(aaf.predict_median(rossi[natural_order]), aaf.predict_median(rossi[misorder]))
assert_frame_equal(aaf.predict_median(rossi[natural_order]), aaf.predict_median(rossi[deleted_order]))
aaf = AalenAdditiveFitter(fit_intercept=False)
aaf.fit(rossi, event_col='week', duration_col='arrest')
assert_frame_equal(aaf.predict_median(rossi[natural_order]), aaf.predict_median(rossi[misorder]))
assert_frame_equal(aaf.predict_median(rossi[natural_order]), aaf.predict_median(rossi[deleted_order]))
def test_swapping_order_of_columns_in_a_df_is_okay(self):
rossi = load_rossi()
aaf = AalenAdditiveFitter()
aaf.fit(rossi, event_col='week', duration_col='arrest')
misorder = ['age', 'race', 'wexp', 'mar', 'paro', 'prio', 'fin']
natural_order = rossi.columns.drop(['week', 'arrest'])
deleted_order = rossi.columns - ['week', 'arrest']
assert_frame_equal(aaf.predict_median(rossi[natural_order]), aaf.predict_median(rossi[misorder]))
assert_frame_equal(aaf.predict_median(rossi[natural_order]), aaf.predict_median(rossi[deleted_order]))
aaf = AalenAdditiveFitter(fit_intercept=False)
aaf.fit(rossi, event_col='week', duration_col='arrest')
assert_frame_equal(aaf.predict_median(rossi[natural_order]), aaf.predict_median(rossi[misorder]))
assert_frame_equal(aaf.predict_median(rossi[natural_order]), aaf.predict_median(rossi[deleted_order]))
def test_concordance_index_fast_is_same_as_slow():
size = 100
T = np.random.normal(size=size)
P = np.random.normal(size=size)
C = np.random.choice([0, 1], size=size)
Z = np.zeros_like(T)
# Hard to imagine these failing
assert slow_cindex(T, Z, C) == fast_cindex(T, Z, C)
assert slow_cindex(T, T, C) == fast_cindex(T, T, C)
# This is the real test though
assert slow_cindex(T, P, C) == fast_cindex(T, P, C)
cp = CoxPHFitter()
df = load_rossi()
cp.fit(df, duration_col='week', event_col='arrest')
T = cp.durations.values.ravel()
P = -cp.predict_partial_hazard(cp.data).values.ravel()
E = cp.event_observed.values.ravel()
assert slow_cindex(T, P, E) == fast_cindex(T, P, E)
def test_concordance_index_fast_is_same_as_slow():
size = 100
T = np.random.normal(size=size)
P = np.random.normal(size=size)
C = np.random.choice([0, 1], size=size)
Z = np.zeros_like(T)
# Hard to imagine these failing
assert slow_cindex(T, Z, C) == fast_cindex(T, Z, C)
assert slow_cindex(T, T, C) == fast_cindex(T, T, C)
# This is the real test though
assert slow_cindex(T, P, C) == fast_cindex(T, P, C)
cp = CoxPHFitter()
df = load_rossi()
cp.fit(df, duration_col='week', event_col='arrest')
T = cp.durations.values.ravel()
P = -cp.predict_partial_hazard(cp.data).values.ravel()
E = cp.event_observed.values.ravel()
assert slow_cindex(T, P, E) == fast_cindex(T, P, E)
def coxph_smoke():
rossi = load_rossi()
cph = CoxPHFitter()
cph.fit(rossi, duration_col='week', event_col='arrest')
cph.print_summary()
rossiH2O = h2o.H2OFrame(rossi)
cphH2O = H2OCoxProportionalHazardsEstimator(stop_column="week")
cphH2O.train(x=["age", "fin", "race", "wexp", "mar", "paro", "prio"], y="arrest", training_frame=rossiH2O)
assert cphH2O.model_id != ""
assert cphH2O.formula() == "Surv(week, arrest) ~ fin + age + race + wexp + mar + paro + prio", \
"Expected formula to be 'Surv(week, arrest) ~ fin + age + race + wexp + mar + paro + prio' but it was " + cphH2O.formula()
predH2O = cphH2O.predict(test_data=rossiH2O)
assert len(predH2O) == len(rossi)
metricsH2O = cphH2O.model_performance(rossiH2O)
py_concordance = concordance_for_lifelines(cph)
assert abs(py_concordance - metricsH2O.concordance()) < 0.001
def test_print_summary(self):
import sys
try:
from StringIO import StringIO
except:
from io import StringIO
saved_stdout = sys.stdout
try:
out = StringIO()
sys.stdout = out
cp = CoxPHFitter()
df = load_rossi()
cp.fit(df, duration_col='week', event_col='arrest')
cp.print_summary()
output = out.getvalue().strip().split()
expected = """n=432, number of events=114
coef exp(coef) se(coef) z p lower 0.95 upper 0.95
fin -1.897e-01 8.272e-01 9.579e-02 -1.981e+00 4.763e-02 -3.775e-01 -1.938e-03 *
age -3.500e-01 7.047e-01 1.344e-01 -2.604e+00 9.210e-03 -6.134e-01 -8.651e-02 **
race 1.032e-01 1.109e+00 1.012e-01 1.020e+00 3.078e-01 -9.516e-02 3.015e-01
wexp -7.486e-02 9.279e-01 1.051e-01 -7.124e-01 4.762e-01 -2.809e-01 1.311e-01
mar -1.421e-01 8.675e-01 1.254e-01 -1.134e+00 2.570e-01 -3.880e-01 1.037e-01
paro -4.134e-02 9.595e-01 9.522e-02 -4.341e-01 6.642e-01 -2.280e-01 1.453e-01
prio 2.639e-01 1.302e+00 8.291e-02 3.182e+00 1.460e-03 1.013e-01 4.264e-01 **
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Concordance = 0.640""".strip().split()
for i in [0, 1, 2, -2, -1]:
assert output[i] == expected[i]
finally:
sys.stdout = saved_stdout
def test_print_summary(self):
import sys
try:
from StringIO import StringIO
except:
from io import StringIO
saved_stdout = sys.stdout
try:
out = StringIO()
sys.stdout = out
cp = CoxPHFitter()
df = load_rossi()
cp.fit(df, duration_col='week', event_col='arrest')
cp.print_summary()
output = out.getvalue().strip().split()
expected = """n=432, number of events=114
coef exp(coef) se(coef) z p lower 0.95 upper 0.95
fin -1.897e-01 8.272e-01 9.579e-02 -1.981e+00 4.763e-02 -3.775e-01 -1.938e-03 *
age -3.500e-01 7.047e-01 1.344e-01 -2.604e+00 9.210e-03 -6.134e-01 -8.651e-02 **
race 1.032e-01 1.109e+00 1.012e-01 1.020e+00 3.078e-01 -9.516e-02 3.015e-01
wexp -7.486e-02 9.279e-01 1.051e-01 -7.124e-01 4.762e-01 -2.809e-01 1.311e-01
mar -1.421e-01 8.675e-01 1.254e-01 -1.134e+00 2.570e-01 -3.880e-01 1.037e-01
paro -4.134e-02 9.595e-01 9.522e-02 -4.341e-01 6.642e-01 -2.280e-01 1.453e-01
prio 2.639e-01 1.302e+00 8.291e-02 3.182e+00 1.460e-03 1.013e-01 4.264e-01 **
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Concordance = 0.640""".strip().split()
for i in [0, 1, 2, -2, -1]:
assert output[i] == expected[i]
finally:
sys.stdout = saved_stdout
# -*- coding: utf-8 -*-
# weibull aft
if __name__ == "__main__":
import pandas as pd
import time
from lifelines import WeibullAFTFitter
from lifelines.datasets import load_rossi
df = load_rossi()
df = pd.concat([df] * 1)
# df = df.reset_index()
# df['week'] = np.random.exponential(1, size=df.shape[0])
wp = WeibullAFTFitter()
start_time = time.time()
wp.fit(df, duration_col="week", event_col="arrest")
print("--- %s seconds ---" % (time.time() - start_time))
wp.print_summary()
def test_cross_validator_with_stratified_cox_model():
cf = CoxPHFitter(strata=["race"])
utils.k_fold_cross_validation(cf, load_rossi(), duration_col="week", event_col="arrest")
from lifelines.datasets import load_rossi from pyBMA.CoxPHFitter import CoxPHFitter # Replication of http://lifelines.readthedocs.io/en/latest/Survival%20Regression.html bmaCox = CoxPHFitter() print(bmaCox.fit(load_rossi(), "week", event_col= "arrest").summary) # If you wanted to have a model with few variables bmaCox = CoxPHFitter() print(bmaCox.fit(load_rossi(), "week", event_col= "arrest", priors= [0.2]*7).summary) # If you wanted to have a model with many variables bmaCox = CoxPHFitter() print(bmaCox.fit(load_rossi(), "week", event_col= "arrest", priors= [0.8]*7).summary) # If you're very confident that race has no impact # rossi columns: fin age race wexp mar paro prio bmaCox = CoxPHFitter() print(bmaCox.fit(load_rossi(), "week", event_col= "arrest", priors= [0.5, 0.5, 0.1, 0.5, 0.5, 0.5, 0.5]).summary) # If you're very confident that both age and race should be included # rossi columns: fin age race wexp mar paro prio bmaCox = CoxPHFitter() print(bmaCox.fit(load_rossi(), "week", event_col= "arrest", priors= [0.5, 0.9, 0.9, 0.5, 0.5, 0.5, 0.5]).summary)
def test_cross_validator_with_stratified_cox_model():
cf = CoxPHFitter(strata=['race'])
utils.k_fold_cross_validation(cf, load_rossi(), duration_col='week', event_col='arrest')
def rossi():
return load_rossi()
def test_input_column_order_is_equal_to_output_hazards_order(self):
rossi = load_rossi()
cp = CoxPHFitter()
expected = ['fin', 'age', 'race', 'wexp', 'mar', 'paro', 'prio']
cp.fit(rossi, event_col='week', duration_col='arrest')
assert list(cp.hazards_.columns) == expected
def test_strata_removes_variable_from_summary_output(self):
df = load_rossi()
cp = CoxPHFitter()
cp.fit(df, 'week', 'arrest', strata=['race'])
assert 'race' not in cp.summary.index
