def test_cife(self):
# Given
n_cols = 10
n_rows = 100
model = LogisticRegression()
# When
mg = MatrixGenerator()
X, y, costs = mg.generate(n_rows=n_rows,
n_basic_cols=n_cols,
noise_sigmas=[2, 3],
seed=2)
lamb = 1
beta = 0.5
dvs = DiffVariableSelector()
dvs.fit(data=X,
target_variable=y,
costs=costs,
lamb=lamb,
j_criterion_func='cife',
budget=5,
stop_budget=True,
beta=beta)
# Then
self.assertGreater(len(costs), len(dvs.variables_selected_order))
def test_cife(self):
# Given
n_cols = 20
n_rows = 1000
model = LogisticRegression()
# When
mg = MatrixGenerator()
X, y, costs = mg.generate(n_rows=n_rows, n_cols=n_cols, seed=2)
lamb = 1
beta = 0.5
dvs = DiffVariableSelector()
dvs.fit(data=X,
target_variable=y,
costs=costs,
lamb=lamb,
j_criterion_func='cife',
beta=beta)
dvs.scoreCV(model=model, cv=5)
dvs.plot_scores(compare_no_cost_method=True, model=model)
# Then
self.assertIsInstance(dvs.variables_selected_order, list)
self.assertEqual(len(dvs.variables_selected_order), len(costs))
self.assertAlmostEqual(sum(costs),
sum(dvs.cost_variables_selected_order))
def test_theoretical_output(self):
integer_matrix = np.array([[0, 1, 0], [0, 1, 0], [0, 1, 2], [0, 1, 3],
[1, 1, 5]])
diverse_target = np.array([0, 0, 0, 0, 1])
costs = [1, 1, 1]
lamb = 1
dvs = DiffVariableSelector()
dvs.fit(data=integer_matrix,
target_variable=diverse_target,
costs=costs,
lamb=lamb,
j_criterion_func='mim')
self.assertEqual(dvs.variables_selected_order[0], 2)
def test_pandas_input(self):
integer_matrix = pd.DataFrame(np.random.randint(0, 10, (100, 3)),
columns=['AA', 'BB', 'CC'])
diverse_target = pd.Series(np.random.randint(0, 2, (100)))
costs = {'AA': 10, 'BB': 1, 'CC': 1.5}
lamb = 1
dvs = DiffVariableSelector()
dvs.fit(data=integer_matrix,
target_variable=diverse_target,
costs=costs,
lamb=lamb,
j_criterion_func='mim')
self.assertIsInstance(dvs.variables_selected_order, list)
self.assertEqual(len(dvs.variables_selected_order), len(costs))
def test_stop_budget(self):
integer_matrix = pd.DataFrame(np.random.randint(0, 10, (100, 3)),
columns=['AA', 'BB', 'CC'])
diverse_target = pd.Series(np.random.randint(0, 2, (100)))
costs = {'AA': 2, 'BB': 1.1, 'CC': 1.5}
lamb = 1
dvs = DiffVariableSelector()
dvs.fit(data=integer_matrix,
target_variable=diverse_target,
costs=costs,
lamb=lamb,
j_criterion_func='mim',
budget=2,
stop_budget=True)
self.assertGreater(2, sum(dvs.cost_variables_selected_order))
self.assertGreaterEqual(2, len(dvs.variables_selected_order))
def test_numpy_input(self):
integer_matrix = np.random.randint(0, 10, (100, 10))
diverse_target = np.random.randint(0, 10, (100))
costs = [1.76, 0.19, 0.36, 0.96, 0.41, 0.17, 0.36, 0.75, 0.79, 1.38]
lamb = 1
dvs = DiffVariableSelector()
dvs.fit(data=integer_matrix,
target_variable=diverse_target,
costs=costs,
lamb=lamb,
j_criterion_func='mim')
self.assertIsInstance(dvs.variables_selected_order, list)
self.assertEqual(len(dvs.variables_selected_order), len(costs))
self.assertAlmostEqual(sum(costs),
sum(dvs.cost_variables_selected_order))
def test_plot_comparision(self):
mg = MatrixGenerator()
X, y, costs = mg.generate(n_basic_cols=10, noise_sigmas=[0.1, 1])
lamb = 1
dvs = DiffVariableSelector()
dvs.fit(data=X,
target_variable=y,
costs=costs,
lamb=lamb,
j_criterion_func='mim')
model = LogisticRegression()
dvs.score(model, scoring_function=roc_auc_score)
dvs.plot_scores(compare_no_cost_method=True, budget=1, model=model)
def test_plot_without_comparision(self):
integer_matrix = np.random.randint(0, 10, (100, 10))
diverse_target = np.random.randint(0, 2, (100))
costs = [1.76, 0.19, 0.36, 0.96, 0.41, 0.17, 0.36, 0.75, 0.79, 1.38]
lamb = 1
dvs = DiffVariableSelector()
dvs.fit(data=integer_matrix,
target_variable=diverse_target,
costs=costs,
lamb=lamb,
j_criterion_func='mim')
model = LogisticRegression()
dvs.score(model, scoring_function=roc_auc_score)
dvs.plot_scores(budget=1)
def test_score(self):
integer_matrix = np.random.randint(0, 10, (100, 10))
diverse_target = np.random.randint(0, 2, (100))
costs = [1.76, 0.19, -0.36, 0.96, 0.41, 0.17, -0.36, 0.75, 0.79, -1.38]
lamb = 1
dvs = DiffVariableSelector()
dvs.fit(data=integer_matrix,
target_variable=diverse_target,
costs=costs,
lamb=lamb,
j_criterion_func='mim')
model = LogisticRegression()
dvs.score(model, scoring_function=roc_auc_score)
self.assertEqual(len(dvs.total_scores), len(costs))
def test_run_score_before_fit(self):
dvs = DiffVariableSelector()
model = LogisticRegression()
with self.assertRaises(AssertionError):
dvs.score(model, scoring_function=roc_auc_score)