def fit_and_score_features(X, y):
n_features = X.shape[1]
scores = np.empty(n_features)
m = IPCRidge()
for j in range(n_features):
Xj = X[:, j:j + 1]
m.fit(Xj, y)
scores[j] = m.score(Xj, y)
return scores
def test_predict(make_whas500):
whas500 = make_whas500()
model = IPCRidge()
model.fit(whas500.x[:400], whas500.y[:400])
x_test = whas500.x[400:]
y_test = whas500.y[400:]
p = model.predict(x_test)
assert_cindex_almost_equal(y_test['fstat'], y_test['lenfol'], -p,
(0.66925817946226107, 2066, 1021, 0, 1))
assert model.score(x_test, y_test) == 1.0 - 0.66925817946226107
def test_predict(self):
model = IPCRidge()
model.fit(self.x[:400], self.y[:400])
x_test = self.x[400:]
y_test = self.y[400:]
p = model.predict(x_test)
ci = concordance_index_censored(y_test['fstat'], y_test['lenfol'], -p)
self.assertAlmostEqual(ci[0], 0.66925817946226107)
self.assertEqual(ci[1], 2066)
self.assertEqual(ci[2], 1021)
self.assertEqual(ci[3], 0)
self.assertEqual(ci[4], 6)
self.assertEqual(model.score(x_test, y_test), 1.0 - ci[0])
for c in X.columns.values:
if c != 'AGE AT DOC':
X[c] = X[c].astype('category')
data_x_numeric = OneHotEncoder().fit_transform(X)
#%%
estimator = IPCRidge()
estimator.fit(data_x_numeric, y)
#%%
print()
print(pd.Series(estimator.coef_, index=data_x_numeric.columns))
print()
print(estimator.score(data_x_numeric, y))
print()
scores = fit_and_score_features(data_x_numeric.values, y)
print(
pd.Series(scores,
index=data_x_numeric.columns).sort_values(ascending=False))
#%%
from sklearn.feature_selection import SelectKBest
from sklearn.pipeline import Pipeline
pipe = Pipeline([('encode', OneHotEncoder()),
('select', SelectKBest(fit_and_score_features, k=3)),
('model', IPCRidge())])