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_fit(self):
model = IPCRidge()
model.fit(self.x, self.y)
self.assertAlmostEqual(model.intercept_, 5.8673567124629571)
expected = numpy.array([
0.168517, -0.249717, 2.18515, 0.536795, -0.514571, 0.091203,
0.613006, 0.480385, -0.055949, 0.238529, -0.127148, -0.144134,
-1.625041, -0.217469
])
assert_array_almost_equal(model.coef_, expected)
def test_fit(make_whas500):
whas500 = make_whas500()
model = IPCRidge()
model.fit(whas500.x, whas500.y)
assert round(abs(model.intercept_ - 5.8673567124629571), 7) == 0
expected = numpy.array([
0.168517, -0.249717, 2.18515, 0.536795, -0.514571, 0.091203,
0.613006, 0.480385, -0.055949, 0.238529, -0.127148, -0.144134,
-1.625041, -0.217469
])
assert_array_almost_equal(model.coef_, expected)
def test_fit(make_whas500):
whas500 = make_whas500()
model = IPCRidge()
model.fit(whas500.x, whas500.y)
assert round(abs(model.intercept_ - 5.867520370855396), 7) == 0
expected = numpy.array([
0.168481, -0.24962, 2.185086, 0.53682, -0.514611, 0.09124,
0.613114, 0.480357, -0.055972, 0.238472, -0.127209, -0.144063,
-1.625081, -0.217591
])
assert_array_almost_equal(model.coef_, expected)
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 _create_regression_ensemble():
aft_grid = ParameterGrid({"alpha": 2. ** numpy.arange(-2, 12, 2)})
svm_grid = ParameterGrid({"alpha": 2. ** numpy.arange(-12, 0, 2)})
base_estimators = []
for i, params in enumerate(aft_grid):
model = IPCRidge(max_iter=1000, **params)
base_estimators.append(("aft_%d" % i, model))
for i, params in enumerate(svm_grid):
model = FastSurvivalSVM(rank_ratio=0, fit_intercept=True, max_iter=100,
random_state=1, **params)
base_estimators.append(("svm_%d" % i, model))
cv = KFold(n_splits=4, shuffle=True, random_state=0)
meta = EnsembleSelectionRegressor(base_estimators, n_estimators=0.4,
scorer=_score_rmse,
cv=cv, n_jobs=1)
return meta
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])
data = x.astype("float")
allTarget = np.zeros((2000), dtype=[('indicator', bool), ('time', float)])
for i in range(0, 2000):
if data[i][22] < 0:
allTarget[i]['time'] = data[i][23]
allTarget[i]['indicator'] = False
else:
allTarget[i]['time'] = data[i][22]
allTarget[i]['indicator'] = True
trainingTargetKidney = allTarget[0:800]
testTargetKidney = allTarget[800:1000]
estimator = IPCRidge()
estimator.fit(trainingData, trainingTargetKidney)
prediction = estimator.predict(testData)
estimator = CoxPHSurvivalAnalysis()
estimator.fit(trainingData, trainingTargetStruc)
prediction0 = estimator.predict(testData)
result = concordance_index_censored(testTargetStruc["indicator"],
testTargetStruc["targetValue"], prediction)
result0 = concordance_index_censored(testTargetStruc["indicator"],
testTargetStruc["targetValue"],
prediction0)
print(result)
print(prediction)
print(result0)
E = df['LapseIndicator'].apply(lambda x: True if x == 1 else False)
df2['E'] = E
df2['T'] = T
X, y = get_x_y(df2, ['E', 'T'], pos_label=True)
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))
#%%
