def test_logrank_test_output_against_R_1():
df = load_g3()
ix = (df['group'] == 'RIT')
d1, e1 = df.loc[ix]['time'], df.loc[ix]['event']
d2, e2 = df.loc[~ix]['time'], df.loc[~ix]['event']
expected = 0.0138
result = stats.logrank_test(d1, d2, event_observed_A=e1, event_observed_B=e2)
assert abs(result.p_value - expected) < 0.0001
def test_logrank_test_output_against_R_1():
df = load_g3()
ix = df["group"] == "RIT"
d1, e1 = df.loc[ix]["time"], df.loc[ix]["event"]
d2, e2 = df.loc[~ix]["time"], df.loc[~ix]["event"]
expected = 0.0138
result = stats.logrank_test(d1, d2, event_observed_A=e1, event_observed_B=e2)
assert abs(result.p_value - expected) < 0.0001
def test_kmf_survival_curve_output_against_R(self):
df = load_g3()
ix = df['group'] == 'RIT'
kmf = KaplanMeierFitter()
expected = np.array([[0.909, 0.779]]).T
kmf.fit(df.ix[ix]['time'], df.ix[ix]['event'], timeline=[25, 53])
npt.assert_array_almost_equal(kmf.survival_function_.values, expected, decimal=3)
expected = np.array([[0.833, 0.667, 0.5, 0.333]]).T
kmf.fit(df.ix[~ix]['time'], df.ix[~ix]['event'], timeline=[9, 19, 32, 34])
npt.assert_array_almost_equal(kmf.survival_function_.values, expected, decimal=3)
def test_logrank_test_output_against_R_1():
df = load_g3()
ix = (df['group'] == 'RIT')
d1, e1 = df.loc[ix]['time'], df.loc[ix]['event']
d2, e2 = df.loc[~ix]['time'], df.loc[~ix]['event']
expected = 0.0138
result = stats.logrank_test(d1,
d2,
event_observed_A=e1,
event_observed_B=e2)
assert abs(result.p_value - expected) < 0.0001
def test_kmf_survival_curve_output_against_R(self):
df = load_g3()
ix = df['group'] == 'RIT'
kmf = KaplanMeierFitter()
expected = np.array([[0.909, 0.779]]).T
kmf.fit(df.ix[ix]['time'], df.ix[ix]['event'], timeline=[25, 53])
npt.assert_array_almost_equal(kmf.survival_function_.values, expected, decimal=3)
expected = np.array([[0.833, 0.667, 0.5, 0.333]]).T
kmf.fit(df.ix[~ix]['time'], df.ix[~ix]['event'], timeline=[9, 19, 32, 34])
npt.assert_array_almost_equal(kmf.survival_function_.values, expected, decimal=3)
def test_kmf_confidence_intervals_output_against_R(self):
# this uses conf.type = 'log-log'
df = load_g3()
ix = df['group'] != 'RIT'
kmf = KaplanMeierFitter()
kmf.fit(df.ix[ix]['time'], df.ix[ix]['event'], timeline=[9, 19, 32, 34])
expected_lower_bound = np.array([0.2731, 0.1946, 0.1109, 0.0461])
npt.assert_array_almost_equal(kmf.confidence_interval_['KM_estimate_lower_0.95'].values,
expected_lower_bound, decimal=3)
expected_upper_bound = np.array([0.975, 0.904, 0.804, 0.676])
npt.assert_array_almost_equal(kmf.confidence_interval_['KM_estimate_upper_0.95'].values,
expected_upper_bound, decimal=3)
def test_kmf_confidence_intervals_output_against_R(self):
# this uses conf.type = 'log-log'
df = load_g3()
ix = df['group'] != 'RIT'
kmf = KaplanMeierFitter()
kmf.fit(df.ix[ix]['time'], df.ix[ix]['event'], timeline=[9, 19, 32, 34])
expected_lower_bound = np.array([0.2731, 0.1946, 0.1109, 0.0461])
npt.assert_array_almost_equal(kmf.confidence_interval_['KM_estimate_lower_0.95'].values,
expected_lower_bound, decimal=3)
expected_upper_bound = np.array([0.975, 0.904, 0.804, 0.676])
npt.assert_array_almost_equal(kmf.confidence_interval_['KM_estimate_upper_0.95'].values,
expected_upper_bound, decimal=3)
