def test_add_features_with_index():
X, y = make_classification(n_samples=1000,
n_features=100,
n_informative=2,
n_redundant=0,
n_repeated=0,
n_classes=2,
n_clusters_per_class=1,
weights=None,
class_sep=1.0,
hypercube=True,
scale=2.0,
shuffle=True,
random_state=0)
X_og = X.copy()
index = [0, 8, 9, 20]
X_two_less = np.delete(X_og, index, axis=1)
nb = CustomNaiveBayes(encode_data=True)
nb.fit(X_two_less, y)
nb.add_features(X_og[:, index], y, index=index)
independent = nb.indepent_term_
smoothed_log_counts_ = nb.smoothed_log_counts_
added = nb.predict_proba(X)
nb.fit(X, y)
og = nb.predict_proba(X)
assert np.allclose(nb.indepent_term_, independent)
assert np.allclose(nb.smoothed_log_counts_, smoothed_log_counts_)
assert np.allclose(og, added)
class PazzaniWrapperNB(PazzaniWrapper):
''''Optimized version of Pazzani's wrapper for the Naive Bayes classifier.
LOO cross validation
Update, add, delete features
'''
def __init__(self, seed=None, strategy="BSEJ", verbose=0):
super().__init__(seed=seed,
strategy=strategy,
verbose=verbose,
cv=None)
def _generate_neighbors_bsej(self, current_columns, X):
if X.shape[1] > 1:
for column_to_drop in range(X.shape[1]):
new_columns = current_columns.copy()
del new_columns[column_to_drop]
yield new_columns, column_to_drop, None, True # Updated column list, columns to remove, columns to add, delete?
for features in combinations(np.arange(X.shape[1]), 2):
new_col_name = flatten([
current_columns[features[0]], current_columns[features[1]]
])
new_columns = current_columns.copy()
new_columns.append(tuple(new_col_name))
columns_to_drop = sorted(features, reverse=True)
del new_columns[columns_to_drop[0]]
del new_columns[columns_to_drop[1]]
combined_columns = combine_columns(X, list(features))
yield new_columns, list(
columns_to_drop), combined_columns, False
def fit_bsej(self, X, y):
self.evaluate = memoize(_evaluate, attribute_to_cache="columns")
current_best = X.copy()
current_columns = deque(range(X.shape[1]))
best_score = self.evaluate(self.classifier,
current_best,
y,
columns=current_columns,
fit=True)
stop = False
while not stop:
update = False
stop = True
if self.verbose:
print("Current Best: ", current_columns, " Score: ",
best_score)
for new_columns, columns_to_delete, columns_to_add, delete in self._generate_neighbors_bsej(
current_columns, current_best):
if delete:
action = "DELETE"
# Update classifier and get validation result
self.classifier.remove_feature(columns_to_delete)
neighbor = np.delete(current_best,
columns_to_delete,
axis=1)
score = self.evaluate(self.classifier,
neighbor,
y,
columns=new_columns,
fit=False)
# Restore the column for the next iteration
self.classifier.add_features(
current_best[:, columns_to_delete].reshape(-1, 1),
y,
index=[columns_to_delete])
else:
action = "ADD"
self.classifier.add_features(columns_to_add, y)
self.classifier.remove_feature(columns_to_delete[0])
self.classifier.remove_feature(columns_to_delete[1])
neighbor = np.delete(current_best,
columns_to_delete,
axis=1)
neighbor = np.concatenate([neighbor, columns_to_add],
axis=1)
score = self.evaluate(self.classifier,
neighbor,
y,
columns=new_columns,
fit=False)
if self.classifier.n_features_ == 1:
# We reverse it for insert order
self.classifier.add_features(
current_best[:, columns_to_delete], y)
self.classifier.remove_feature(0)
else:
self.classifier.remove_feature(neighbor.shape[1] - 1)
# We reverse it for insert order
self.classifier.add_features(
current_best[:, columns_to_delete],
y,
index=columns_to_delete)
if self.verbose == 2:
print("\tNeighbor: ", new_columns, " Score: ", score)
if score > best_score:
stop = False
best_columns = new_columns
best_action = action
best_score = score
best_columns_to_delete = columns_to_delete
update = True
if best_action == "ADD":
best_columns_to_add = columns_to_add
if score == 1.0:
stop = True
break
if update:
current_columns = best_columns
if best_action == "DELETE":
current_best = np.delete(current_best,
best_columns_to_delete,
axis=1)
# Update best
self.classifier.remove_feature(best_columns_to_delete)
else:
current_best = np.delete(current_best,
best_columns_to_delete,
axis=1)
current_best = np.concatenate(
[current_best, best_columns_to_add], axis=1)
# Update classifier
self.classifier.add_features(best_columns_to_add, y)
self.classifier.remove_feature(best_columns_to_delete[0])
self.classifier.remove_feature(best_columns_to_delete[1])
if self.verbose:
print("Final best: ", list(current_columns), " Score: ",
best_score)
self.features_ = current_columns
self.feature_transformer = lambda X: join_columns(
X, columns=self.features_)
model = self.classifier.fit(self.feature_transformer(X), y)
return self
def _generate_neighbors_fssj(self, current_columns, individual,
original_data, available_columns):
if available_columns:
for index, col in enumerate(available_columns):
new_columns = current_columns.copy()
new_columns.append(col)
new_available_columns = available_columns.copy()
del new_available_columns[index]
column_to_add = original_data[:, col].reshape(-1, 1)
column_to_delete = None
# New columns, Availables,ColumnToDelete,ColumnToAdd,Delete?
yield new_columns, new_available_columns, column_to_delete, column_to_add, False
if individual is not None and individual.shape[
1] > 0 and available_columns:
for features_index in product(np.arange(len(available_columns)),
np.arange(len(current_columns))):
features = available_columns[
features_index[0]], current_columns[features_index[1]]
new_col_name = flatten([features[0], features[1]])
new_available_columns = available_columns.copy()
del new_available_columns[features_index[0]]
new_columns = current_columns.copy()
new_columns.append(tuple(new_col_name))
del new_columns[features_index[1]]
separated_columns = np.concatenate([
original_data[:, features[0]].reshape(-1, 1),
individual[:, features_index[1]].reshape(-1, 1)
],
axis=1)
if isinstance(features[1], tuple):
features = list(features)
features[1] = list(features[1])
features = tuple(features)
column_to_delete = features_index[1]
combined_columns = combine_columns(separated_columns)
column_to_add = combined_columns
yield new_columns, new_available_columns, column_to_delete, column_to_add, True
def fit_fssj(self, X, y):
self.evaluate = memoize(_evaluate, attribute_to_cache="columns")
current_best = None
current_columns = deque()
available_columns = list(range(X.shape[1]))
best_score = -float("inf")
stop = False
while not stop:
update = False
stop = True
# self.classifier.encode_data=True
if self.verbose:
print("Current Best: ", current_columns, " Score: ",
best_score, "Available columns: ", available_columns)
for new_columns, new_available_columns, column_to_delete, column_to_add, delete in self._generate_neighbors_fssj(
current_columns=current_columns,
individual=current_best,
original_data=X,
available_columns=available_columns):
if delete:
action = "JOIN"
# Update classifier and get validation result
self.classifier.add_features(column_to_add, y)
self.classifier.remove_feature(column_to_delete)
neighbor = np.concatenate([current_best, column_to_add],
axis=1)
neighbor = np.delete(neighbor, column_to_delete, axis=1)
score = self.evaluate(self.classifier,
neighbor,
y,
columns=new_columns,
fit=False)
# Restore the column for the next iteration
if neighbor.shape[1] == 1:
self.classifier.fit(current_best, y)
else:
self.classifier.remove_feature(neighbor.shape[1] - 1)
self.classifier.add_features(
current_best[:, column_to_delete].reshape(-1, 1),
y,
index=[column_to_delete])
else:
action = "ADD"
if current_best is None:
neighbor = column_to_add
self.classifier.fit(neighbor, y)
else:
neighbor = np.concatenate(
[current_best, column_to_add], axis=1)
self.classifier.add_features(column_to_add, y)
score = self.evaluate(self.classifier,
neighbor,
y,
columns=new_columns,
fit=False)
if current_best is None:
self.classifier = NaiveBayes(encode_data=True)
else:
self.classifier.remove_feature(neighbor.shape[1] - 1)
if self.verbose == 2:
print("\tNeighbour: ", new_columns, " Score: ", score,
"Available columns: ", new_available_columns)
if score > best_score:
stop = False
best_columns = new_columns
best_available_columns = new_available_columns
best_action = action
best_score = score
best_column_to_delete = column_to_delete
best_column_to_add = column_to_add
update = True
if score == 1.0:
stop = True
break
if update:
current_columns = best_columns
available_columns = best_available_columns
if best_action == "JOIN":
self.classifier.add_features(best_column_to_add, y)
self.classifier.remove_feature(best_column_to_delete)
current_best = np.concatenate(
[current_best, best_column_to_add], axis=1)
current_best = np.delete(current_best,
best_column_to_delete,
axis=1)
else:
if current_best is None:
current_best = best_column_to_add
self.classifier.fit(current_best, y)
else:
current_best = np.concatenate(
[current_best, best_column_to_add], axis=1)
self.classifier.add_features(best_column_to_add, y)
if self.verbose:
print("Final best: ", list(current_columns), " Score: ",
best_score)
self.features_ = current_columns
self.feature_transformer = lambda X: join_columns(
X, columns=self.features_)
model = self.classifier.fit(self.feature_transformer(X), y)
return self
def evaluate(self, classifier, X, y, fit=True, columns=None):
return _evaluate(classifier, X, y, fit=True, columns=None)
class RankerLogicalFeatureConstructor(TransformerMixin, ClassifierMixin,
BaseEstimator):
"""First proposal: Hybrid-Ranker Wrapper.
Build a ranking based on Symmetrical Uncertainty (SU) of every possible logical feature of depth 1
(1 operator, 2 operands), using XOR, AND and OR operator. The steps are:
- Find out combinations of values in database of every pair of features Xi, Xj:
- Example:
- Xi = [1,2,3,2]
- Xj = ['a','b','c','a']
Possible combinations:
[(1,'a'),(2,'b'),(3,'c'),(2,'a')]
- Apply operator to every combination:
- Example:
- Xi = [1,2,3,2]
- Xj = ['a','b','c','a']
Possible combinations:
[(1,'a','AND'),(2,'b','AND'),(3,'c','AND'),(2,'a','AND'),
(1,'a','OR'),(2,'b','OR'),(3,'c','OR'),(2,'a','OR'),
(1,'a','XOR'),(2,'b','XOR'),(3,'c','XOR'),(2,'a','XOR')]
- Add original variables to the list
- Evaluate SU for every value in the list, and rank them
- Go over the list following one of the two strategies proposed and evaluate
the subset based on a leave-one-out cross-validation with the NaiveBayes classifier.
Parameters
----------
strategy : str {eager,skip}
After the ranking is built if the eager strategy is chosen we stop considering attributes
when there is no improvement from one iteration to the next
block_size : int, default=1
Number of features that are added in each iteration
encode_data : boolean
Whether or not to encode the received data. If set to false the classifier
expects data to be encoded with an ordinal encoder.
verbose : {boolean,int}
If set to true it displays information of the remaining time
and inside variables.
operators : array-like, deafult = ("XOR","AND","OR")
Operators used for the constructed features.
max_features : int, deafult = inf
Maximum number of features to include in the selected subset
max_iterations : int, deafult = inf
Maximum number of iterations in the wrapper step.
use_graph : bool, default = False
Generate Ranking from features obtained from the pruned-graph of the ACO algorithm.
(Experimentation not carried out)
use_initials: bool, default = False
Force the set of initial features in the final solution. The set if trimmed with a backward elimination before-hand.
Attributes
----------
feature_encoder_ : CustomOrdinalFeatureEncoder or None
Encodes data in ordinal way with unseen values handling if encode_data is set to True.
class_encoder_ : LabelEncoder or None
Encodes Data in ordinal way for the class if encode_data is set to True.
all_feature_constructors: array-like
List of FeatureConstructor objects with all the possible logical
features
symmetrical_uncertainty_rank: array-like
SU for every feature in all_feature_constructors
rank : array-like
Array of indexes corresponding to the sorted SU rank (in descending order).
final_feature_constructors:
Selected feature subset (list of constructors)
classifier: NaiveBayes
Classifier used in the wrapper and to perform predictions after fitting.
"""
def __init__(self,
strategy="eager",
block_size=10,
encode_data=True,
n_intervals=5,
verbose=0,
operators=("AND", "OR", "XOR"),
max_features=float("inf"),
max_iterations=float("inf"),
metric="accuracy",
use_initials=False,
max_err=0,
prune=None,
use_graph=False):
self.strategy = strategy
self.block_size = max(block_size, 1)
self.encode_data = encode_data
self.verbose = verbose
self.operators = operators
self.max_features = max_features
self.max_iterations = max_iterations
self.n_intervals = n_intervals
self.metric = metric
self.max_err = max_err
self.use_initials = use_initials
self.prune = prune
self.use_graph = use_graph
allowed_strategies = ("eager", "skip")
if self.strategy not in allowed_strategies:
raise ValueError("Unknown operator type: %s, expected one of %s." %
(self.strategy, allowed_strategies))
def fit(self, X, y):
# Parse input
if isinstance(y, pd.DataFrame):
y = y.to_numpy()
if self.encode_data:
self.feature_encoder_ = CustomOrdinalFeatureEncoder(
n_intervals=self.n_intervals)
self.class_encoder_ = CustomLabelEncoder()
X = self.feature_encoder_.fit_transform(X)
y = self.class_encoder_.fit_transform(y)
if isinstance(X, pd.DataFrame):
X = X.to_numpy()
check_X_y(X, y)
# Reset the stored results for new fit
self.reset_evaluation()
# Generate rank
if self.use_graph:
# Construct the minimum graph and create rank
graph = AntFeatureGraphMI(seed=None, connections=1).compute_graph(
X, y, ("AND", "OR", "XOR"))
self.all_feature_constructors = graph.get_rank()
elif self.prune is not None:
# Construct the rank with pruning by selecting pais that maximise SU(X_iX_j,Y)
feature_combinations = list(
combinations(list(range(X.shape[1])),
2)) + [(i, i) for i in range(X.shape[1])]
rank_pairs = [
symmetrical_uncertainty_two_variables(X[:, i], X[:, j], y)
for i, j in feature_combinations
]
rank_pairs_index = np.argsort(rank_pairs)[::-1]
# Create the unsorted list
self.all_feature_constructors = []
for index in rank_pairs_index[:self.prune]:
i, j = feature_combinations[index]
if i == j:
from tfg.feature_construction import create_feature
self.all_feature_constructors.extend([
create_feature("OR", [(i, n), (i, m)])
for n, m in combinations(np.unique(X[:, i]), 2)
])
else:
self.all_feature_constructors.extend(
construct_features(X[:, [i, j]],
operators=self.operators,
same_feature=False))
else:
# Create the unsorted list of all features
self.all_feature_constructors = construct_features(
X, operators=self.operators)
if self.verbose:
print(
f"Total number of constructed features: {len(self.all_feature_constructors)}"
)
self.all_feature_constructors.extend(
[DummyFeatureConstructor(j) for j in range(X.shape[1])])
self.symmetrical_uncertainty_rank = []
# Sort the ranking
for feature_constructor in self.all_feature_constructors:
feature = feature_constructor.transform(X)
su = symmetrical_uncertainty(f1=feature.flatten(), f2=y)
self.symmetrical_uncertainty_rank.append(su)
# Store the descending order index
self.rank = np.argsort(self.symmetrical_uncertainty_rank)[::-1]
# If the initial variables are
if self.use_initials:
classifier = NaiveBayes(encode_data=False,
n_intervals=self.n_intervals,
metric=self.metric)
classifier.fit(X, y)
current_features = [
DummyFeatureConstructor(j) for j in range(X.shape[1])
]
# Store the backward result to reuse it for other executions
self.initial_backward_features = backward_search(
X, y, current_features, classifier)
# Feature Subset Selection (FSS) from the rank
self.filter_features(X, y)
return self
def predict(self, X):
X, _ = self.transform(X)
if self.encode_data:
return self.class_encoder_.inverse_transform(
self.classifier.predict(X))
return self.classifier.predict(X)
def reset_evaluation(self):
# Reset the memoize evaluations
self.evaluate_leave_one_out_cross_val = memoize(evaluate_leave_one_out)
def predict_proba(self, X):
X, _ = self.transform(X)
return self.classifier.predict_proba(X)
def score(self, X, y):
X, y = self.transform(X, y)
return self.classifier.score(X, y)
def filter_features(self, X, y):
'''After the rank is built this perform the greedy wrapper search'''
check_is_fitted(self)
self.classifier = NaiveBayes(encode_data=False,
n_intervals=self.n_intervals,
metric=self.metric)
current_score = np.NINF
first_iteration = True
current_features = []
current_data = None
if self.use_initials:
# Original Features have already been taken into account
rank_iter = filter(
lambda x: not isinstance(self.all_feature_constructors[x],
DummyFeatureConstructor),
iter(self.rank))
# Deep copy to avoid issues when modifying the list
current_features = deepcopy(self.initial_backward_features)
current_data = np.concatenate(
[f.transform(X) for f in current_features], axis=1)
# Get initial LOO score
current_score = self.evaluate_leave_one_out_cross_val(
self.classifier, current_features, current_data, y, fit=True)
else:
# Iterator over the sorted list of indexes
rank_iter = iter(self.rank)
if self.verbose:
progress_bar = tqdm(total=len(self.rank),
bar_format='{l_bar}{bar:20}{r_bar}{bar:-10b}')
iteration = 0
iterations_without_improvements = 0
# Loop for including {block size} elements at a time
# Rank is an iterator, so the for loop is not sequential!
for feature_constructor_index in rank_iter:
iteration += 1
if self.verbose:
progress_bar.set_postfix({
"n_features": len(current_features),
"score": current_score
})
progress_bar.update(1)
progress_bar.refresh()
# Add block size features
new_X = [
self.all_feature_constructors[feature_constructor_index].
transform(X)
]
selected_features = [
self.all_feature_constructors[feature_constructor_index]
]
for _ in range(self.block_size - 1):
try:
index = next(rank_iter)
selected_features.append(
self.all_feature_constructors[index])
new_X.append(
self.all_feature_constructors[index].transform(X))
if self.verbose:
progress_bar.update(1)
progress_bar.refresh()
except:
# Block size does not divide the number of elements in the rank. The search is halted
break
# Evaluate features
new_X = np.concatenate(new_X, axis=1)
if iteration == 1 and not self.use_initials:
current_data = new_X
current_score = self.evaluate_leave_one_out_cross_val(
self.classifier,
selected_features,
current_data,
y,
fit=True)
current_features = selected_features
first_iteration = False
if self.max_iterations <= iteration or (
len(current_features) +
self.block_size) > self.max_features:
break
continue
data = np.concatenate([current_data, new_X], axis=1)
self.classifier.add_features(new_X, y)
# LOO evaluation
score = self.evaluate_leave_one_out_cross_val(self.classifier,
current_features +
selected_features,
data,
y,
fit=False)
if score > current_score:
current_score = score
current_data = data
current_features.extend(selected_features)
iterations_without_improvements = 0
else:
iterations_without_improvements += 1
# Remove last added block
for feature_index_to_remove in range(
data.shape[1], data.shape[1] - new_X.shape[1], -1):
self.classifier.remove_feature(feature_index_to_remove - 1)
if self.strategy == "eager" and self.max_err < iterations_without_improvements:
# Stops as soon as no impovement
break
if self.max_iterations <= iteration or (
len(current_features) +
self.block_size) > self.max_features:
break
if self.verbose:
progress_bar.close()
print(
f"\nFinal number of included features: {len(current_features)} - Final Score: {current_score}"
)
self.final_feature_constructors = current_features
return self
def transform(self, X, y=None):
check_is_fitted(self)
if isinstance(y, pd.DataFrame):
y = y.to_numpy()
if self.encode_data:
X = self.feature_encoder_.transform(X)
if y is not None:
y = self.class_encoder_.transform(y)
if isinstance(X, pd.DataFrame):
X = X.to_numpy()
new_X = []
for feature_constructor in self.final_feature_constructors:
new_X.append(feature_constructor.transform(X))
return np.concatenate(new_X, axis=1), y
def explore(self, X, y, graph, random_generator, parallel, max_errors=0):
'''
Search method that follows the following steps:
1. The initial node is connected to all the others (roulette wheel selection is performed)
2. There are 2 type of nodes (corresponding to an original feature (2.1) or corresponding to a value of a feature (2.2)):
2.1. If the selected node is an original feature we add it to the selected subset and go to step 3.
2.2. If the selected node is part of a logical feature then we select another node (the CONSTRUCTION step will not return full original features)
3. Compute the score
3.1. If it improves the previous one
3.1.1 Add the feature to the current subset
3.1.2 Update the score
3.1.3 Select another node (SELECTION step)
3.1.4 Go to step 2
3.2. If not, the exploration ends
Note: Threading does not speed up the calculations as they are CPU bound and in python only I/O operations will benefit from this parallelism
GPU improvement would reduce the time of the exploration.
'''
self.step = math.ceil(math.log2(X.shape[1]))
self.current_features = []
selected_nodes = set()
constructed_nodes = set()
classifier = NaiveBayes(encode_data=False, metric=self.metric)
current_score = np.NINF
score = 0
if self.use_initials:
self.current_features = [
DummyFeatureConstructor(j) for j in range(X.shape[1])
]
classifier.fit(X, y)
current_transformed_features_numpy = np.concatenate(
[f.transform(X) for f in self.current_features], axis=1)
score = self.evaluate_loo(self.current_features, classifier,
current_transformed_features_numpy, y)
current_score = score
selected_nodes.update(graph.get_original_ids())
if len(self.current_features) == 0:
current_transformed_features_numpy = None
initial, pheromones, heuristics = graph.get_initial_nodes(
selected_nodes)
probabilities = self.compute_probability(pheromones, heuristics)
index = self.choose_next(probabilities, random_generator)
node_id, selected_node = initial[index]
# SU variable contains the MIFS-SU for the selected variable
current_su = 0
su = heuristics[index]
is_fitted = self.use_initials
feature_constructor = None
n_errors = 0
number_steps = 1
while True:
current_score = score
if selected_node[1] is None:
# Original Feature
feature_constructor = DummyFeatureConstructor(selected_node[0])
selected_nodes.add(node_id)
else:
# Need to construct next feature and compute heuristic value for the feature to replace temporal su from half-var
neighbours, pheromones = graph.get_neighbours(
selected_node, constructed_nodes, step="CONSTRUCTION")
if len(neighbours) == 0:
break
if self.beta != 0:
if parallel:
with concurrent.futures.ThreadPoolExecutor(
) as executor:
futures = []
for neighbour in neighbours:
futures.append(
executor.submit(
self.compute_neighbour_sufs,
neighbour=neighbour,
transformed_features=
current_transformed_features_numpy,
constructors=self.current_features,
selected_node=selected_node,
current_su=current_su,
X=X,
y=y))
concurrent.futures.wait(
futures,
timeout=None,
return_when='ALL_COMPLETED')
su = [future.result() for future in futures]
else:
su = [
self.compute_neighbour_sufs(
neighbour=neighbour,
transformed_features=
current_transformed_features_numpy,
selected_node=selected_node,
constructors=self.current_features,
current_su=current_su,
X=X,
y=y) for neighbour in neighbours
]
else:
#Avoid unnecessary evaluation
su = np.ones(len(neighbours))
probabilities = self.compute_probability(
pheromones, np.array(su))
index = self.choose_next(probabilities, random_generator)
su = su[index]
feature_constructor = create_feature(
neighbours[index][2],
[selected_node, neighbours[index][1]])
constructed_nodes.add(
frozenset(
(node_id, neighbours[index][0], neighbours[index][2])))
node_id, selected_node = neighbours[index][:2]
# Assess new feature
transformed_feature = feature_constructor.transform(X)
if is_fitted:
classifier.add_features(transformed_feature, y)
else:
classifier.fit(transformed_feature, y)
is_fitted = True
if current_transformed_features_numpy is None:
current_transformed_features_numpy = transformed_feature
else:
current_transformed_features_numpy = append_column_to_numpy(
current_transformed_features_numpy, transformed_feature)
if number_steps >= self.step:
score = self.evaluate_loo(
self.current_features + [feature_constructor], classifier,
current_transformed_features_numpy, y)
if score <= current_score:
if n_errors >= max_errors:
break
else:
n_errors += 1
else:
n_errors = 0
number_steps = 0
else:
number_steps += 1
current_su = su
self.current_features.append(feature_constructor)
current_score = score
# Select next
neighbours, pheromones = graph.get_neighbours(selected_node,
selected_nodes,
step="SELECTION")
# Compute heuristic
su = []
if len(neighbours) == 0:
break
if self.beta != 0:
for neighbour, pheromone in zip(neighbours, pheromones):
if neighbour[1][1] is None:
# Original variable
su.append(
self.compute_sufs_cached(
current_su,
current_transformed_features_numpy,
X[:, neighbour[1][0]],
self.current_features,
DummyFeatureConstructor(neighbour[1][0]),
y,
minimum=0))
else:
# This is a temporal variable that will not be finally selected but only used to calculate the heuristic
su.append(
self.compute_sufs_cached(
current_su,
current_transformed_features_numpy,
X[:, neighbour[1][0]] == neighbour[1][1],
self.current_features,
FeatureOperand(feature_index=neighbour[1][0],
value=neighbour[1][1]),
y,
minimum=0))
else:
su = np.ones(len(neighbours))
probabilities = self.compute_probability(pheromones, np.array(su))
index = self.choose_next(probabilities, random_generator)
su = su[index]
node_id, selected_node = neighbours[index][:2]
if current_transformed_features_numpy.shape[1] > len(
self.current_features):
current_transformed_features_numpy = np.delete(
current_transformed_features_numpy, -1, axis=1)
self.final_score = self.evaluate_loo(
self.current_features, classifier,
current_transformed_features_numpy, y)
return self.final_score