def test_simple_input_mifs_no_beta_provided(self):
integer_matrix = np.random.randint(0, 10, (100, 10))
diverse_target = np.random.randint(0, 10, (100))
prev_variables_index = [3, 4, 5]
candidates_index = [0, 1, 2, 6, 7, 8, 9]
costs = [1.76, 0.19, -0.36, 0.96, 0.41, 0.17, -0.36, 0.75, 0.79, -1.38]
with self.assertWarns(Warning):
no_cost_find_best_feature(
j_criterion_func=mifs,
data=integer_matrix,
target_variable=diverse_target,
possible_variables_index=candidates_index,
costs=costs,
prev_variables_index=prev_variables_index)
def fit(self,
data,
target_variable,
costs,
j_criterion_func='cife',
**kwargs):
super().fit(data, target_variable, costs, j_criterion_func, **kwargs)
S = set()
U = set([i for i in range(self.data.shape[1])])
self.variables_selected_order = []
self.cost_variables_selected_order = []
while len(U) > 0:
k, _, cost = no_cost_find_best_feature(
j_criterion_func=self.j_criterion_func,
data=self.data,
target_variable=self.target_variable,
prev_variables_index=list(S),
possible_variables_index=list(U),
costs=self.costs)
S.add(k)
self.variables_selected_order.append(k)
self.cost_variables_selected_order.append(cost)
U = U.difference(set([k]))
def fit(self,
data,
target_variable,
costs,
j_criterion_func='cife',
**kwargs):
super().fit(data, target_variable, costs, j_criterion_func, **kwargs)
S = set()
U = set([i for i in range(self.data.shape[1])])
self.variables_selected_order = []
self.cost_variables_selected_order = []
for _ in tqdm(range(len(U)), desc='Scoring No-cost Features'):
k, _, cost = no_cost_find_best_feature(
j_criterion_func=self.j_criterion_func,
data=self.data,
target_variable=self.target_variable,
prev_variables_index=list(S),
possible_variables_index=list(U),
costs=self.costs)
S.add(k)
self.variables_selected_order.append(k)
self.cost_variables_selected_order.append(cost)
U = U.difference(set([k]))
if len(S) == self.number_of_features:
break
def _fit_no_cost(self, stop_budget=False, **kwargs):
S = set()
U = set([i for i in range(self.data.shape[1])])
self.no_cost_variables_selected_order = []
self.no_cost_cost_variables_selected_order = []
for _ in tqdm(range(self.number_of_features),
desc='Selecting No-cost Features'):
k, _, cost = no_cost_find_best_feature(
j_criterion_func=self.j_criterion_func,
data=self.data,
target_variable=self.target_variable,
prev_variables_index=list(S),
possible_variables_index=list(U),
costs=self.costs,
beta=self.beta)
S.add(k)
if stop_budget is True and (
sum(self.no_cost_cost_variables_selected_order) +
cost) >= (self.budget or np.inf):
break
self.no_cost_variables_selected_order.append(k)
self.no_cost_cost_variables_selected_order.append(cost)
U = U.difference(set([k]))
if len(S) == self.number_of_features:
break
def test_simple_input_mim(self):
integer_matrix = np.random.randint(0, 10, (100, 10))
diverse_target = np.random.randint(0, 10, (100))
candidates_index = [0, 1, 2, 6, 7, 8, 9]
costs = [1.76, 0.19, -0.36, 0.96, 0.41, 0.17, -0.36, 0.75, 0.79, -1.38]
selected_feature, criterion_value, cost = no_cost_find_best_feature(
j_criterion_func=mim,
data=integer_matrix,
target_variable=diverse_target,
possible_variables_index=candidates_index,
costs=costs)
self.assertIsInstance(selected_feature, int)
self.assertIsInstance(criterion_value, float)
self.assertIsInstance(cost, float)
def _no_cost_scoreCV(self, **kwargs):
# Rank variables with NoCostVariableSelector
S = set()
U = set([i for i in range(self.data.shape[1])])
self.no_cost_variables_selected_order = []
self.no_cost_cost_variables_selected_order = []
while len(U) > 0:
k, _, cost = no_cost_find_best_feature(
j_criterion_func=self.j_criterion_func,
data=self.data,
target_variable=self.target_variable,
prev_variables_index=list(S),
possible_variables_index=list(U),
costs=self.costs,
beta=self.beta)
S.add(k)
self.no_cost_variables_selected_order.append(k)
self.no_cost_cost_variables_selected_order.append(cost)
U = U.difference(set([k]))
current_cost = 0
self.no_cost_total_scores = []
self.no_cost_total_costs = []
for i, var_id in enumerate(self.no_cost_variables_selected_order):
cur_vars = self.no_cost_variables_selected_order[0:i + 1]
score = cross_val_score(
estimator=self.model,
X=self.data[:, cur_vars],
y=self.target_variable,
cv=self.cv_kwargs.get('cv'),
scoring=self.cv_kwargs.get('scoring'),
n_jobs=self.cv_kwargs.get('n_jobs')).mean()
current_cost += self.costs[var_id]
self.no_cost_total_scores.append(score)
self.no_cost_total_costs.append(current_cost)