Feature Selection ToolboxFST3 Library / DocumentationShare

File List

Here is a list of all documented files with brief descriptions:
branch_and_bound_predictor.hppInterface for Implementations of Prediction Mechanism in Fast Branch & Bound and Branch & Bound with Partial Prediction
branch_and_bound_predictor_averaging.hppAveraging Prediction Mechanism for use in Fast Branch & Bound and Branch & Bound with Partial Prediction
candidate_evaluator_threaded.hppImplements concurrent evaluation of a criterion on a set of subset candidates
classifier.hppDefines interface for classifier implementations
classifier_knn.hppImplements k-Nearest Neighbor classifier
classifier_multinom_naivebayes.hppImplements Naive-like Bayes classifier based on multinomial model
classifier_normal_bayes.hppImplements Bayes classifier based on normal (gaussian) model
classifier_svm.hppWraps external Support Vector Machine implementation (in LibSVM) to serve as FST3 classifier
clonable.hppDefines interface for classes that may need to get cloned
criterion.hppDefines interface for feature selection criterion classes
criterion_multinom.hppDefines interface for feature selection criterion implementations based on multinomial model
criterion_multinom_bhattacharyya.hppImplements Bhattacharyya distance based on multinomial model to serve as feature selection criterion
criterion_negative.hppCriterion_Negative returns the negative of another Criterion's result
criterion_normal.hppDefines interface for feature selection criterion implementations based on normal model
criterion_normal_bhattacharyya.hppImplements Bhattacharyya distance based on normal (gaussian) model to serve as feature selection criterion
criterion_normal_divergence.hppImplements Divergence (distance) based on normal (gaussian) model to serve as feature selection criterion
criterion_normal_gmahalanobis.hppImplements Generalized Mahalanobis distance based on normal (gaussian) model to serve as feature selection criterion
criterion_subsetsize.hppCriterion_Subset_Size returns negative subset size - rates smaller subsets higher
criterion_sumofweights.hppCriterion_Sum_Of_Weights returns sum of pre-specified feature weights for features in the evaluated subset
criterion_wrapper.hppClassifier_Wrapper adapts Classifier objects to serve as feature selection criterion
criterion_wrapper_bias_estimate.hppWrapper Bias Evaluator - returns classifier bias estimate (difference between accuracy on training and validation data parts)
data_accessor.hppDefines interface for data access implementations
data_accessor_splitting.hppDefines support for data splitting
data_accessor_splitting_mem.hppImplements data access to data cached entirely in memory, concrete file type support is delegated to derived classes
data_accessor_splitting_memARFF.hppImplements data access to data cached entirely in memory, read once from ARFF files
data_accessor_splitting_memTRN.hppImplements data access to data cached entirely in memory, read once from TRN files
data_file_ARFF.hppEnables data accessor objects to read ARFF (Weka) type of data files
data_file_TRN.hppEnables data accessor objects to read TRN type of data files
data_intervaller.hppContainer to hold a list of Data_Interval; implements nested interval reduction
data_scaler.hppDefines interface for data scaling implementations (for use in data accessors)
data_scaler_to01.hppImplements data normalization (of all feature values) to interval [0,1]
data_scaler_void.hppVoid data scaler, to bypass data normalization
data_scaler_white.hppImplements data whitening (as result, each feature mean value is 0 with normalized stddev)
data_splitter.hppDefines interface for data splitting implementations (for use in data accessors)
data_splitter_5050.hppImplements train/test data splitting: first 50% of original data for training, second 50% for testing
data_splitter_cv.hppImplements train/test data splitting: by means of k-fold cross-validation
data_splitter_holdout.hppImplements train/test data splitting: use initial x% of original data for training, the rest for testing
data_splitter_leave1out.hppImplements train/test data splitting: by means of leave-one-out
data_splitter_randfix.hppImplements train/test data splitting: equal to Data_Splitter_RandomRandom except that the same test data is returned in each loop
data_splitter_randrand.hppImplements train/test data splitting: use randomly chosen x% of data samples for training and another y% of data for testing, without overlaps
data_splitter_resub.hppImplements train/test data splitting: use all data both for training and then once more for testing
demo10.cppExample 10: Basic Filter-based feature selection
demo11.cppExample 11: Wrapper-based feature selection with Floating Search
demo11t.cppExample 11t: Threaded wrapper-based feature selection with Floating Search
demo12t.cppExample 12t: Threaded SVM-wrapper-based feature selection with Dynamic Oscillating Search
demo20.cppExample 20: Retreating Sequential Search
demo21.cppExample 21: Generalized sequential feature subset search
demo22.cppExample 22: Randomized feature selection with Oscillating Search
demo23.cppExample 23: Combined feature subset contents, size and SVM parameters optimization
demo24.cppExample 24: Monte Carlo - random feature subset search
demo24t.cppExample 24t: Threaded Monte Carlo - random feature subset search
demo25t.cppExample 25t: Fast pre-selection followed by Dynamic Oscillating Search
demo26.cppExample 26: Wrapper-based (normal Bayes) feature selection with Floating Search, verified by 2 classifiers
demo30.cppExample 30: Feature selection on binary and/or natural-valued data
demo31.cppExample 31: Individual ranking (BIF) in very high-dimensional feature selection
demo32t.cppExample 32t: Threaded individual ranking (BIF) with SVM wrapper in very high-dimensional feature selection
demo33.cppExample 33: Oscillating Search in very high-dimensional feature selection
demo33t.cppExample 33t: Threaded Oscillating Search in very high-dimensional feature selection
demo34.cppExample 34: Dependency-Aware Feature Ranking (DAF0)
demo35t.cppExample 35t: Dependency-Aware Feature Ranking (DAF1) to enable Wrapper based FS on very-high-dimensional data
demo40.cppExample 40: Exhaustive (optimal) feature selection
demo40t.cppExample 40t: Threaded Exhaustive (optimal) feature selection
demo41.cppExample 41: Improved Branch and Bound (IBB) optimal feature selection
demo42.cppExample 42: Branch and Bound with Partial Prediction (BBPP) optimal feature selection
demo43.cppExample 43: Fast Branch and Bound (FBB) optimal feature selection
demo50.cppExample 50: Voting ensemble of criteria
demo51.cppExample 51: (DOS) Result regularization using secondary criterion
demo52t.cppExample 52t: (Threaded SFRS) Result regularization using secondary criterion
demo53.cppExample 53: Hybrid feature selection
demo54.cppExample 54: Feature Selection Stability Evaluation
demo55.cppExample 55: Evaluating Similarity of Two Feature Selection Processes
demo56.cppExample 56: Revealing feature selection results' bias
demo60.cppExample 60: Detecting alternative feature selection results with equal criterion value
demo61.cppExample 61: Feature selection that respects pre-specified feature weights
demo62.cppExample 62: (Missing data substitution) Combined feature subset contents, size and SVM parameters optimization
demo63.cppExample 63: Classification of new data samples on the selected subspace
distance.hppDefines interface for distance evaluators (to be used primarily in Classifier_kNN)
distance_euclid.hppImplements Euclidean (L_2) distance
distance_L1.hppImplements L_1 distance
distance_Lp.hppImplements L_{p} distance, p equals numerator/denominator (template parameters)
error.hppFST3 specific error passing class
global.cppGlobal definitions
global.hppGlobal definitions
indexed_matrix.hppMatrix representation and operations, allows operation in selected subspace
indexed_vector.hppVector representation and operations, allows operation in selected subspace
model.hppDefines interface for data model implementations
model_multinom.hppImplements multinomial model
model_normal.hppImplements normal (gaussian) model
result_tracker.hppDefines interface for classes that enable collecting multiple results
result_tracker_dupless.hppEnables collecting multiple results
result_tracker_feature_stats.hppComputes feature occurence statistics in a series of evaluated subsets
result_tracker_regularizer.hppEnables eventual selection of a different subset
result_tracker_stabileval.hppEnables collecting multiple results, then evaluating various stability measures
search.hppDefines interface for search method implementations
search_bif.hppImplements Best Individual Features, i.e., individual feature ranking
search_bif_threaded.hppThreaded implementation of Best Individual Features, i.e., individual feature ranking
search_branch_and_bound.hppImplements Branch and Bound template method as basis for more advanced B&B implementations
search_branch_and_bound_basic.hppImplements Branch and Bound Basic method, i.e., with randomized node ordering
search_branch_and_bound_fast.hppImplements Fast Branch and Bound, i.e., B&B with full utilization of prediction mechanism
search_branch_and_bound_improved.hppImplements Improved Branch and Bound (IBB) method, i.e., with fully computed node ordering
search_branch_and_bound_improved_threaded.hppImplements Threaded version of Improved Branch and Bound (IBB) method, i.e., with fully computed node ordering
search_branch_and_bound_partial_prediction.hppImplements Branch and Bound with Partial Prediction (BBPP) method, i.e., with predicted node ordering
search_exhaustive.hppDefines interface for search method implementations
search_exhaustive_threaded.hppImplements threaded version of exhaustive (optimal) search yielding optimal feature subset with respect to chosen criterion
search_monte_carlo.hppRepeatedly samples random subsets to eventually yield the one with highest criterion value
search_monte_carlo_threaded.hppImplements threaded version of randomized search that repeatedly samples random subsets to eventually yield the one with highest criterion value
search_seq.hppDefines interface for sequential search method implementations
search_seq_dos.hppImplements Dynamic_Oscillating_Search
search_seq_os.hppImplements Oscillating_Search
search_seq_sffs.hppImplements Sequential_Forward_Floating_Search and Sequential_Backward_Floating_Search
search_seq_sfrs.hppImplements Sequential_Forward_Retreating_Search and Sequential_Backward_Retreating_Search
search_seq_sfs.hppImplements Sequential_Forward_Selection and Sequential_Backward_Selection
seq_step.hppDefines interface for implementations of one selection step in sequential search type of methods
seq_step_ensemble.hppImplements voting ensemble selection step in sequential search type of methods
seq_step_hybrid.hppImplements hybrid selection step in sequential search type of methods
seq_step_straight.hppImplements standard sequential selection step in sequential search type of methods
seq_step_straight_threaded.hppImplements threaded version of sequential selection step in sequential search type of methods
stopwatch.hppSimple tool to measure run time
subset.hppStores the info on currently selected features, enables generating permutations, etc
thread_pool.hppImplements thread scheduler that assigns jobs up to maximum number of threads allowed

Generated on Thu Mar 31 11:39:05 2011 for FST3Library by  doxygen 1.6.1