From 80043d5181355739b80e88097fc1d9f2f8ea8ba0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ricardo=20Monta=C3=B1ana=20G=C3=B3mez?= Date: Thu, 16 May 2024 14:32:59 +0200 Subject: [PATCH] First approach to BoostA2DE::trainModel --- bayesnet/ensembles/BoostA2DE.cc | 149 +++++++++++++++----------------- 1 file changed, 72 insertions(+), 77 deletions(-) diff --git a/bayesnet/ensembles/BoostA2DE.cc b/bayesnet/ensembles/BoostA2DE.cc index 887c1a2..209173b 100644 --- a/bayesnet/ensembles/BoostA2DE.cc +++ b/bayesnet/ensembles/BoostA2DE.cc @@ -81,89 +81,84 @@ namespace bayesnet { // run out of features bool ascending = order_algorithm == Orders.ASC; std::mt19937 g{ 173 }; + std::vector> pairSelection; while (!finished) { // Step 1: Build ranking with mutual information - auto pairSelection = metrics.SelectKPairs(weights_, featuresUsed, ascending, 0); // Get all the pairs sorted + pairSelection = metrics.SelectKPairs(weights_, featuresUsed, ascending, 0); // Get all the pairs sorted if (order_algorithm == Orders.RAND) { std::shuffle(pairSelection.begin(), pairSelection.end(), g); } - // // Remove used features - // featureSelection.erase(remove_if(begin(featureSelection), end(featureSelection), [&](auto x) - // { return std::find(begin(featuresUsed), end(featuresUsed), x) != end(featuresUsed);}), - // end(featureSelection) - // ); - // int k = bisection ? pow(2, tolerance) : 1; - // int counter = 0; // The model counter of the current pack - // VLOG_SCOPE_F(1, "counter=%d k=%d featureSelection.size: %zu", counter, k, featureSelection.size()); - // while (counter++ < k && featureSelection.size() > 0) { - // auto feature = featureSelection[0]; - // featureSelection.erase(featureSelection.begin()); - // std::unique_ptr model; - // model = std::make_unique(feature); - // model->fit(dataset, features, className, states, weights_); - // alpha_t = 0.0; - // if (!block_update) { - // auto ypred = model->predict(X_train); - // // Step 3.1: Compute the classifier amout of say - // std::tie(weights_, alpha_t, finished) = update_weights(y_train, ypred, weights_); - // } - // // Step 3.4: Store classifier and its accuracy to weigh its future vote - // numItemsPack++; - // featuresUsed.push_back(feature); - // models.push_back(std::move(model)); - // significanceModels.push_back(alpha_t); - // n_models++; - // VLOG_SCOPE_F(2, "numItemsPack: %d n_models: %d featuresUsed: %zu", numItemsPack, n_models, featuresUsed.size()); - // } - // if (block_update) { - // std::tie(weights_, alpha_t, finished) = update_weights_block(k, y_train, weights_); - // } - // if (convergence && !finished) { - // auto y_val_predict = predict(X_test); - // double accuracy = (y_val_predict == y_test).sum().item() / (double)y_test.size(0); - // if (priorAccuracy == 0) { - // priorAccuracy = accuracy; - // } else { - // improvement = accuracy - priorAccuracy; - // } - // if (improvement < convergence_threshold) { - // VLOG_SCOPE_F(3, " (improvement=threshold) Reset. tolerance: %d numItemsPack: %d improvement: %f prior: %f current: %f", tolerance, numItemsPack, improvement, priorAccuracy, accuracy); - // tolerance = 0; // Reset the counter if the model performs better - // numItemsPack = 0; - // } - // if (convergence_best) { - // // Keep the best accuracy until now as the prior accuracy - // priorAccuracy = std::max(accuracy, priorAccuracy); - // } else { - // // Keep the last accuray obtained as the prior accuracy - // priorAccuracy = accuracy; - // } - // } - // VLOG_SCOPE_F(1, "tolerance: %d featuresUsed.size: %zu features.size: %zu", tolerance, featuresUsed.size(), features.size()); - // finished = finished || tolerance > maxTolerance || featuresUsed.size() == features.size(); + int k = bisection ? pow(2, tolerance) : 1; + int counter = 0; // The model counter of the current pack + // VLOG_SCOPE_F(1, "counter=%d k=%d featureSelection.size: %zu", counter, k, featureSelection.size()); + while (counter++ < k && pairSelection.size() > 0) { + auto feature_pair = pairSelection[0]; + pairSelection.erase(pairSelection.begin()); + std::unique_ptr model; + model = std::make_unique(std::vector({ feature_pair.first, feature_pair.second })); + model->fit(dataset, features, className, states, weights_); + alpha_t = 0.0; + if (!block_update) { + auto ypred = model->predict(X_train); + // Step 3.1: Compute the classifier amout of say + std::tie(weights_, alpha_t, finished) = update_weights(y_train, ypred, weights_); + } + // Step 3.4: Store classifier and its accuracy to weigh its future vote + numItemsPack++; + models.push_back(std::move(model)); + significanceModels.push_back(alpha_t); + n_models++; + // VLOG_SCOPE_F(2, "numItemsPack: %d n_models: %d featuresUsed: %zu", numItemsPack, n_models, featuresUsed.size()); + } + if (block_update) { + std::tie(weights_, alpha_t, finished) = update_weights_block(k, y_train, weights_); + } + if (convergence && !finished) { + auto y_val_predict = predict(X_test); + double accuracy = (y_val_predict == y_test).sum().item() / (double)y_test.size(0); + if (priorAccuracy == 0) { + priorAccuracy = accuracy; + } else { + improvement = accuracy - priorAccuracy; + } + if (improvement < convergence_threshold) { + // VLOG_SCOPE_F(3, " (improvement=threshold) Reset. tolerance: %d numItemsPack: %d improvement: %f prior: %f current: %f", tolerance, numItemsPack, improvement, priorAccuracy, accuracy); + tolerance = 0; // Reset the counter if the model performs better + numItemsPack = 0; + } + if (convergence_best) { + // Keep the best accuracy until now as the prior accuracy + priorAccuracy = std::max(accuracy, priorAccuracy); + } else { + // Keep the last accuray obtained as the prior accuracy + priorAccuracy = accuracy; + } + } + // VLOG_SCOPE_F(1, "tolerance: %d featuresUsed.size: %zu features.size: %zu", tolerance, featuresUsed.size(), features.size()); + finished = finished || tolerance > maxTolerance || pairSelection.size() == 0; } - // if (tolerance > maxTolerance) { - // if (numItemsPack < n_models) { - // notes.push_back("Convergence threshold reached & " + std::to_string(numItemsPack) + " models eliminated"); - // VLOG_SCOPE_F(4, "Convergence threshold reached & %d models eliminated of %d", numItemsPack, n_models); - // for (int i = 0; i < numItemsPack; ++i) { - // significanceModels.pop_back(); - // models.pop_back(); - // n_models--; - // } - // } else { - // notes.push_back("Convergence threshold reached & 0 models eliminated"); - // VLOG_SCOPE_F(4, "Convergence threshold reached & 0 models eliminated n_models=%d numItemsPack=%d", n_models, numItemsPack); - // } - // } - // if (featuresUsed.size() != features.size()) { - // notes.push_back("Used features in train: " + std::to_string(featuresUsed.size()) + " of " + std::to_string(features.size())); - // status = WARNING; - // } - // notes.push_back("Number of models: " + std::to_string(n_models)); + if (tolerance > maxTolerance) { + if (numItemsPack < n_models) { + notes.push_back("Convergence threshold reached & " + std::to_string(numItemsPack) + " models eliminated"); + // VLOG_SCOPE_F(4, "Convergence threshold reached & %d models eliminated of %d", numItemsPack, n_models); + for (int i = 0; i < numItemsPack; ++i) { + significanceModels.pop_back(); + models.pop_back(); + n_models--; + } + } else { + notes.push_back("Convergence threshold reached & 0 models eliminated"); + // VLOG_SCOPE_F(4, "Convergence threshold reached & 0 models eliminated n_models=%d numItemsPack=%d", n_models, numItemsPack); + } + } + if (pairSelection.size() > 0) { + notes.push_back("Used pairs not used in train: " + std::to_string(pairSelection.size())); + status = WARNING; + } + notes.push_back("Number of models: " + std::to_string(n_models)); } std::vector BoostA2DE::graph(const std::string& title) const {