def select_candidate_enhanced(train_df, train_labels, best_classifiers, ensemble, i):
initial_ensemble_size = 2
max_candidates=50
if len(ensemble) >= initial_ensemble_size:
candidates = choice(best_classifiers.index.values, min(max_candidates, len(best_classifiers)), replace = False)
candidate_scores = [common.score(train_labels, train_df[ensemble + [candidate]].mean(axis = 1)) for candidate in candidates]
best_candidate = candidates[common.argbest(candidate_scores)]
else:
best_candidate = best_classifiers.index.values[i]
return best_candidate
def select_candidate_sdi(train_df, train_labels, best_classifiers, ensemble,
i):
if len(ensemble) >= initial_ensemble_size:
candidates = choice(best_classifiers.index.values,
min(max_candidates, len(best_classifiers)),
replace=False)
candidate_diversity_scores = [
1 -
abs(common.diversity_score(
train_df[ensemble + [candidate]].values))
for candidate in candidates
] # 1 - kappa so larger = more diverse
candidate_scores = [
accuracy_weight * best_classifiers.ix[candidate] +
(1 - accuracy_weight) * candidate_diversity_scores[candidate_i]
for candidate_i, candidate in enumerate(candidates)
]
best_candidate = candidates[common.argbest(candidate_scores)]
else:
best_candidate = best_classifiers.index.values[i]
return best_candidate
def select_candidate_drep(train_df, train_labels, best_classifiers, ensemble,
i):
if len(ensemble) >= initial_ensemble_size:
candidates = choice(best_classifiers.index.values,
min(max_candidates, len(best_classifiers)),
replace=False)
candidate_diversity_scores = [
abs(common.diversity_score(train_df[ensemble +
[candidate]].values))
for candidate in candidates
]
candidate_diversity_ranks = array(candidate_diversity_scores).argsort()
diversity_candidates = candidates[
candidate_diversity_ranks[:max_diversity_candidates]]
candidate_accuracy_scores = [
common.score(train_labels,
train_df[ensemble + [candidate]].mean(axis=1))
for candidate in diversity_candidates
]
best_candidate = candidates[common.argbest(candidate_accuracy_scores)]
else:
best_candidate = best_classifiers.index.values[i]
return best_candidate
