def testNumeric(self):
N_SAMPLES = 200
X, y = make_classification(n_samples=N_SAMPLES, n_features=10, n_informative=2, random_state=42)
X_train, X_test, y_train, y_test = train_test_split(X, y, stratify=y, test_size=0.3, random_state=42)
column_names = ['X%i' % i for i in range(10)]
D_train = pd.DataFrame(X_train, columns=column_names)
D_test = pd.DataFrame(X_test, columns=column_names)
lastochka = LastochkaTransformer(verbose=True, n_final=3, n_initial=10)
log = LogisticRegression()
pipe = Pipeline(steps=[
('lastochka', lastochka),
('log', log)])
pipe.fit(D_train, y_train)
X_w = lastochka.transform(D_train)
X_wt = lastochka.transform(D_test)
for variable in column_names:
vt = lastochka.get_transformer(variable)
acceptable_values = vt.optimizer_instance.bin_stats["woe_value"]
real_values_train = X_w[variable].unique()
real_values_test = X_wt[variable].unique()
self.assertTrue(set(acceptable_values) == set(real_values_train))
self.assertTrue((set(acceptable_values)) == set(real_values_test))
def testSpecial(self):
_boston = load_boston()
X = pd.DataFrame(_boston["data"], columns=_boston["feature_names"])
y = (_boston["target"] >= np.median(_boston["target"])).astype(int)
specs = {"PTRATIO": [20.2, 14.7]}
lastochka = LastochkaTransformer(verbose=True, n_final=3, n_initial=10, specials=specs)
lastochka.fit(X, y)
lastochka.transform(X)
self.assertTrue(list(lastochka.get_transformer("PTRATIO").specials_stats.keys()) == specs["PTRATIO"])
def testMissing(self):
_boston = load_boston()
X = pd.DataFrame(_boston["data"], columns=_boston["feature_names"])
np.random.seed(2)
indexes = np.random.choice(X.index.tolist(), 200)
X.loc[indexes, "ZN"] = np.nan
y = (_boston["target"] >= np.median(_boston["target"])).astype(int)
lastochka = LastochkaTransformer(verbose=True, n_final=3, n_initial=10)
lastochka.fit(X, y)
lastochka.transform(X)
self.assertTrue(lastochka.get_transformer("ZN").missing_woe_value is not None)
def testCategory(self):
_boston = load_boston()
X = pd.DataFrame(_boston["data"], columns=_boston["feature_names"])
X["RAD_CAT"] = X["RAD"].astype(str)
X = X.drop("RAD", axis=1)
y = (_boston["target"] >= np.median(_boston["target"])).astype(int)
lastochka = LastochkaTransformer(verbose=True, n_final=3, n_initial=10)
lastochka.fit(X, y)
lastochka.transform(X)
optimizer_instance = lastochka.get_transformer("RAD_CAT").optimizer_instance
self.assertIsInstance(optimizer_instance, CategoryOptimizer)