def _run_outer_loop(
self,
input_data: InputDataset,
outer_split: Split,
data_splitter: DataSplitter,
) -> OuterLoopResults:
feature_elimination_results = {}
feature_set = list(range(input_data.n_features))
while len(feature_set) >= self._minimum_features:
inner_results = []
for inner_split in data_splitter.iter_inner_splits(outer_split):
inner_loop_data = data_splitter.split_data(
input_data, inner_split, feature_set
)
feature_evaluation_results = self._feature_evaluator.evaluate_features(
inner_loop_data, feature_set
)
inner_results.append(feature_evaluation_results)
feature_elimination_results[tuple(feature_set)] = inner_results
feature_set = self._remove_features(feature_set, inner_results)
outer_loop_results = self._create_outer_loop_results(
feature_elimination_results, input_data, outer_split, data_splitter
)
return outer_loop_results
def test_split_data(dataset):
ds = DataSplitter(n_outer=5, n_inner=4, random_state=0, input_data=dataset)
split = Split(0, [0, 1, 2], [3, 4, 5, 6])
split_data = ds.split_data(dataset, split, features=[0, 1, 2])
assert split_data.test_data.X.shape == (4, 3)
assert split_data.test_data.y.size == 4
assert split_data.train_data.X.shape == (3, 3)
assert split_data.train_data.y.size == 3
def _evaluate_min_mid_and_max_features(
self,
input_data: InputDataset,
best_features: SelectedFeatures,
split: Split,
data_splitter: DataSplitter,
) -> Tuple[
FeatureEvaluationResults, FeatureEvaluationResults, FeatureEvaluationResults
]:
min_feats = best_features["min"]
mid_feats = best_features["mid"]
max_feats = best_features["max"]
data_min_feats = data_splitter.split_data(input_data, split, min_feats)
data_mid_feats = data_splitter.split_data(input_data, split, mid_feats)
data_max_feats = data_splitter.split_data(input_data, split, max_feats)
min_eval = self._feature_evaluator.evaluate_features(data_min_feats, min_feats)
mid_eval = self._feature_evaluator.evaluate_features(data_mid_feats, mid_feats)
max_eval = self._feature_evaluator.evaluate_features(data_max_feats, max_feats)
return min_eval, mid_eval, max_eval
def test_evaluate_features(dataset):
pipeline = Pipeline(
[("normalizer", Normalizer()), ("model", SVC(kernel="linear", random_state=0))]
)
fe = FeatureEvaluator(estimator=pipeline, metric="MISS", random_state=0,)
fe.set_n_initial_features(12)
ds = DataSplitter(n_outer=5, n_inner=4, random_state=0, input_data=dataset)
split = ds.iter_outer_splits().__next__()
evaluation_data = ds.split_data(dataset, split)
evaluation = fe.evaluate_features(evaluation_data, [0, 4, 6])
assert evaluation
assert evaluation.test_score >= 0
assert evaluation.ranks
assert isinstance(evaluation.ranks, FeatureRanks)
assert evaluation.ranks.n_feats == 12
assert evaluation.ranks[0]
assert evaluation.ranks[1]
with pytest.raises(ValueError):
_ = evaluation.ranks[100]