def test_proflogit_patsy_demo_data(self):
X_train, y_train = load_data("../data/patsy_demo_train.dat", "y")
X_test, y_test = load_data("../data/patsy_demo_test.dat", 0)
pfl = ProfLogit(rga_kws={"niter": 5, "random_state": 42}, )
pfl.fit(X_train, y_train)
self.assertEqual(pfl.formula, "c + standardize(x)")
self.assertTrue("Intercept" in pfl.design_info.column_names)
self.assertTrue(pfl.intercept)
empc = pfl.score(X_test, y_test)
self.assertAlmostEqual(empc, 25.5035418741)
def test_proflogit_access_fit_method_directly(self):
X_train, y_train = load_data("../data/patsy_demo_train.dat", "y")
X_test, y_test = load_data("../data/patsy_demo_test.dat", 0)
pfl = ProfLogit(rga_kws={
"niter_diff": 3,
"disp": False,
"random_state": 42
}, ).fit(X_train, y_train)
self.assertEqual(pfl.formula, "c + standardize(x)")
self.assertTrue("Intercept" in pfl.design_info.column_names)
self.assertTrue(pfl.intercept)
empc = pfl.score(X_test, y_test)
self.assertAlmostEqual(empc, 25.0827084152)
def test_proflogit_no_intercept_through_formula(self):
ynm = "y"
X_train, y_train = load_data("../data/patsy_demo_train.dat", ynm)
X_test, y_test = load_data("../data/patsy_demo_test.dat", 0)
pfl = ProfLogit(
formula_like="c + standardize(x) - 1",
rga_kws={
"niter": 5,
"disp": False,
"random_state": 42
},
)
pfl.fit(X_train, y_train)
self.assertEqual(pfl.formula, "c + standardize(x) - 1")
self.assertFalse("Intercept" in pfl.design_info.column_names)
self.assertFalse(pfl.intercept)
empc = pfl.score(X_test, y_test)
self.assertAlmostEqual(empc, 25.5035418741)
def test_load_data(self):
ynm = "y"
yix = 0
X0, _ = load_data("../data/patsy_demo_train.dat")
y0 = X0[ynm]
del X0[ynm]
X1, y1 = load_data("../data/patsy_demo_train.dat", ynm)
X2, y2 = load_data("../data/patsy_demo_train.dat", yix)
d = [X0, X1, X2]
for dix, d0 in enumerate(d):
for d1 in d[dix + 1:]:
for (k0, v0), (k1, v1) in zip(d0.items(), d1.items()):
self.assertEqual(k0, k1)
if isinstance(v0, list) and isinstance(v1, list):
self.assertListEqual(v0, v1)
else:
npt.assert_array_almost_equal(v0, v1)
npt.assert_array_equal(y0, y1)
npt.assert_array_equal(y0, y2)
npt.assert_array_equal(y1, y2)
def test_proflogit_nfev_correct_large(self):
X, y = load_data("../data/patsy_demo_train.dat", "y")
n_fev = 43
pfl = ProfLogit(rga_kws={
"nfev": n_fev,
"disp": False,
"random_state": 42
}, )
pfl.fit(X, y)
self.assertEqual(pfl.rga.res.nfev, n_fev)
self.assertEqual(pfl.formula, "c + standardize(x)")
self.assertTrue("Intercept" in pfl.design_info.column_names)
self.assertTrue(pfl.intercept)
def test_proflogit_patsy(self):
yix = 0
X, y = load_data("../data/two-predictors.dat", yix, False)
form = " + ".join([
"standardize(f{})".format(cix) for cix in range(len(X) + 1)
if cix != yix
])
pfl = ProfLogit(rga_kws={
"niter": 5,
"disp": False,
"random_state": 42
}, )
pfl.fit(X, y)
self.assertEqual(pfl.formula, form)
self.assertTrue("Intercept" in pfl.design_info.column_names)
self.assertTrue(pfl.intercept)
y_score = pfl.predict_proba(X)
empc1 = EMPChurn(y, y_score).empc()
empc2 = pfl.score(X, y)
self.assertAlmostEqual(empc1, empc2)
def test_raise_error_variable_not_in_formula(self):
X, y = load_data("../data/patsy_demo_train.dat", "y")
with self.assertRaises(patsy.PatsyError):
ProfLogit("b + standardize(x)").fit(X, y) # 'b' not in X