def refit_and_predict(cut_points_estimates, X_train, X_test, Y_train,
delta_train, Y_test, delta_test):
binarizer = FeaturesBinarizer(method='given',
bins_boundaries=cut_points_estimates,
remove_first=True)
binarizer.fit(pd.concat([X_train, X_test]))
X_bin_train = binarizer.transform(X_train)
X_bin_test = binarizer.transform(X_test)
learner = CoxRegression(penalty='none',
tol=1e-5,
solver='agd',
verbose=False,
max_iter=100,
step=0.3,
warm_start=True)
learner._solver_obj.linesearch = False
learner.fit(X_bin_train, Y_train, delta_train)
coeffs = learner.coeffs
marker = X_bin_test.dot(coeffs)
lp_train = X_bin_train.dot(coeffs)
c_index = concordance_index(Y_test, marker, delta_test)
c_index = max(c_index, 1 - c_index)
return c_index, marker, lp_train
def test_binarizer_fit(self):
"""...Test binarizer fit
"""
n_cuts = 3
enc = OneHotEncoder(sparse=True)
expected_binarization = enc.fit_transform(
self.default_expected_intervals)
binarizer = FeaturesBinarizer(method='quantile',
n_cuts=n_cuts,
detect_column_type="auto",
remove_first=False)
# for pandas dataframe
binarizer.fit(self.df_features)
binarized_df = binarizer.transform(self.df_features)
self.assertEqual(binarized_df.__class__, csr.csr_matrix)
np.testing.assert_array_equal(expected_binarization.toarray(),
binarized_df.toarray())
# for numpy array
binarizer.fit(self.features)
binarized_array = binarizer.transform(self.features)
self.assertEqual(binarized_array.__class__, csr.csr_matrix)
np.testing.assert_array_equal(expected_binarization.toarray(),
binarized_array.toarray())
# test fit_transform
binarized_array = binarizer.fit_transform(self.features)
self.assertEqual(binarized_array.__class__, csr.csr_matrix)
np.testing.assert_array_equal(expected_binarization.toarray(),
binarized_array.toarray())
def test_binarizer_remove_first(self):
"""...Test binarizer fit when remove_first=True
"""
n_cuts = 3
one_hot_encoder = OneHotEncoder(sparse=True)
expected_binarization = one_hot_encoder.fit_transform(
self.default_expected_intervals)
binarizer = FeaturesBinarizer(method='quantile',
n_cuts=n_cuts,
detect_column_type="auto",
remove_first=True)
binarizer.fit(self.features)
binarized_array = binarizer.transform(self.features)
self.assertEqual(binarized_array.__class__, csr.csr_matrix)
expected_binarization_without_first = \
np.delete(expected_binarization.toarray(), [0, 4, 8, 10], 1)
np.testing.assert_array_equal(expected_binarization_without_first,
binarized_array.toarray())
return
predictions = estim_proba(marker_cox, lp_train, Y_train, delta_train)
ibs_cox = integrated_brier_score(predictions['values'],
predictions['times'], Y_test,
delta_test, Y_train, delta_train)
# Binacox
print("Train Binacox screening_cox_topP...")
X_train_ = X_train[screening_cox_topP]
X_test_ = X_test[screening_cox_topP]
# binarize feature
n_cuts = 50
binarizer = FeaturesBinarizer(n_cuts=n_cuts)
binarizer.fit(pd.concat([X_train_, X_test_]))
X_bin_train = binarizer.transform(X_train_)
blocks_start = binarizer.blocks_start
blocks_length = binarizer.blocks_length
boundaries = binarizer.boundaries
# fit binacox
learner = CoxRegression(penalty='binarsity',
tol=1e-5,
solver='agd',
verbose=False,
max_iter=100,
step=0.3,
blocks_start=blocks_start,
blocks_length=blocks_length,
C=C_chosen[cancer],