shareboost cookbook with integration test data

doc/cookbook/source/examples/multiclass_classifier/shareboost.rst

@@ -0,0 +1,33 @@
+==========
+ShareBoost
+==========
+
+ShareBoost algorithm learns a multiclass predictor from a subset of shared features of the samples with forward greedy selection approach.
+
+See :cite:`shalev2011shareboost` for a detailed introduction.
+
+-------
+Example
+-------
+Imagine we have files with training and test data. We create CDenseFeatures (here 64 bit floats aka RealFeatures) and :sgclass:`CMulticlassLabels` as
+
+.. sgexample:: shareboost.sg:create_features
+
+We create an instance of the :sgclass:`CShareBoost` classifier by setting the number of features expected to be used for learning.
+
+.. sgexample:: shareboost.sg:create_instance
+
+Then we train and apply it to test data, which gives :sgclass:`CMulticlassLabels`.
+
+.. sgexample:: shareboost.sg:train_and_apply
+
+We can evaluate test performance via e.g. :sgclass:`CMulticlassAccuracy`.
+
+.. sgexample:: shareboost.sg:evaluate_accuracy
+
+----------
+References
+----------
+
+.. bibliography:: ../../references.bib
+    :filter: docname in docnames

doc/cookbook/source/references.bib

@@ -79,3 +79,10 @@ @inproceedings{gao2011discriminative
   year={2011},
   organization={IEEE}
 }
+@inproceedings{shalev2011shareboost,
+  title={Shareboost: Efficient multiclass learning with feature sharing},
+  author={Shalev-Shwartz, Shai and Wexler, Yonatan and Shashua, Amnon},
+  booktitle={Advances in Neural Information Processing Systems},
+  pages={1179--1187},
+  year={2011}
+}

examples/meta/generator/targets/cpp.json

@@ -15,6 +15,7 @@
     "Assign": "$lhs = $expr",
     "Type": {
         "RealFeatures": "DenseFeatures<float64_t>",
+        "RealSubsetFeatures": "DenseSubsetFeatures<float64_t>",
         "StringCharFeatures": "CStringFeatures<char>",
         "Default": "$type",
         "bool": "bool",

examples/meta/src/multiclass_classifier/shareboost.sg

@@ -0,0 +1,29 @@
+CSVFile f_feats_train("../../data/classifier_4class_2d_linear_features_train.dat")
+CSVFile f_feats_test("../../data/classifier_4class_2d_linear_features_test.dat")
+CSVFile f_labels_train("../../data/classifier_4class_2d_linear_labels_train.dat")
+CSVFile f_labels_test("../../data/classifier_4class_2d_linear_labels_test.dat")
+
+#![create_features]
+RealFeatures features_train(f_feats_train)
+RealFeatures features_test(f_feats_test)
+MulticlassLabels labels_train(f_labels_train)
+MulticlassLabels labels_test(f_labels_test)
+#![create_features]
+
+#![create_instance]
+ShareBoost shareboost(features_train, labels_train, 2)
+#![create_instance]
+
+#![train_and_apply]
+shareboost.train()
+RealSubsetFeatures features_test_sub(features_test, shareboost.get_activeset())
+MulticlassLabels labels_predict = shareboost.apply_multiclass(features_test_sub)
+#![train_and_apply]
+
+#![evaluate_accuracy]
+MulticlassAccuracy eval()
+real accuracy = eval.evaluate(labels_predict, labels_test)
+#![evaluate_accuracy]
+
+# additional integration testing variables
+RealVector output = labels_predict.get_labels()