Merge pull request #597 from pluskid/multiclass

ShareBoost
shogun-toolbox · Jun 24, 2012 · 0587779 · 0587779
2 parents ddad7f3 + e0731f6
commit 0587779
Show file tree

Hide file tree

Showing 11 changed files with 2,893 additions and 1 deletion.
diff --git a/examples/undocumented/libshogun/classifier_multiclass_shareboost.cpp b/examples/undocumented/libshogun/classifier_multiclass_shareboost.cpp
@@ -0,0 +1,94 @@
+#include <algorithm>
+
+#include <shogun/labels/MulticlassLabels.h>
+#include <shogun/io/StreamingAsciiFile.h>
+#include <shogun/io/SGIO.h>
+#include <shogun/features/StreamingDenseFeatures.h>
+#include <shogun/features/DenseFeatures.h>
+#include <shogun/features/DenseSubsetFeatures.h>
+#include <shogun/base/init.h>
+#include <shogun/multiclass/ShareBoost.h>
+
+#define  EPSILON  1e-5
+
+using namespace shogun;
+
+int main(int argc, char** argv)
+{
+	int32_t num_vectors = 0;
+	int32_t num_feats   = 0;
+
+	init_shogun_with_defaults();
+
+	const char*fname_train = "../data/7class_example4_train.dense";
+	CStreamingAsciiFile *train_file = new CStreamingAsciiFile(fname_train);
+	SG_REF(train_file);
+
+	CStreamingDenseFeatures<float64_t> *stream_features = new CStreamingDenseFeatures<float64_t>(train_file, true, 1024);
+	SG_REF(stream_features);
+
+	SGMatrix<float64_t> mat;
+	SGVector<float64_t> labvec(1000);
+
+	stream_features->start_parser();
+	SGVector< float64_t > vec;
+	while (stream_features->get_next_example())
+	{
+		vec = stream_features->get_vector();
+		if (num_feats == 0)
+		{
+			num_feats = vec.vlen;
+			mat = SGMatrix<float64_t>(num_feats, 1000);
+		}
+		std::copy(vec.vector, vec.vector+vec.vlen, mat.get_column_vector(num_vectors));
+		labvec[num_vectors] = stream_features->get_label();
+		num_vectors++;
+		stream_features->release_example();
+	}
+	stream_features->end_parser();
+	mat.num_cols = num_vectors;
+	labvec.vlen = num_vectors;
+
+	CMulticlassLabels* labels = new CMulticlassLabels(labvec);
+	SG_REF(labels);
+
+	// Create features with the useful values from mat
+	CDenseFeatures< float64_t >* features = new CDenseFeatures<float64_t>(mat);
+	SG_REF(features);
+
+	SG_SPRINT("Performing ShareBoost on a %d-class problem\n", labels->get_num_classes());
+
+	// Create ShareBoost Machine
+	CShareBoost *machine = new CShareBoost(features, labels, 10);
+	SG_REF(machine);
+
+	machine->train();
+
+	SGVector<int32_t> activeset = machine->get_activeset();
+	SG_SPRINT("%d out of %d features are selected:\n", activeset.vlen, mat.num_rows);
+	for (int32_t i=0; i < activeset.vlen; ++i)
+		SG_SPRINT("activeset[%02d] = %d\n", i, activeset[i]);
+
+	CDenseSubsetFeatures<float64_t> *subset_fea = new CDenseSubsetFeatures<float64_t>(features, machine->get_activeset());
+	SG_REF(subset_fea);
+	CMulticlassLabels* output = CMulticlassLabels::obtain_from_generic(machine->apply(subset_fea));
+
+	int32_t correct = 0;
+	for (int32_t i=0; i < output->get_num_labels(); ++i)
+		if (output->get_int_label(i) == labels->get_int_label(i))
+			correct++;
+	SG_SPRINT("Accuracy = %.4f\n", float64_t(correct)/labels->get_num_labels());
+
+	// Free resources
+	SG_UNREF(machine);
+	SG_UNREF(output);
+	SG_UNREF(subset_fea);
+	SG_UNREF(features);
+	SG_UNREF(labels);
+	SG_UNREF(train_file);
+	SG_UNREF(stream_features);
+	exit_shogun();
+
+	return 0;
+}
+
diff --git a/examples/undocumented/libshogun/optimization_lbfgs.cpp b/examples/undocumented/libshogun/optimization_lbfgs.cpp
@@ -0,0 +1,81 @@
+#include <cstdio>
+#include <shogun/optimization/lbfgs/lbfgs.h>
+
+static lbfgsfloatval_t evaluate(
+    void *instance,
+    const lbfgsfloatval_t *x,
+    lbfgsfloatval_t *g,
+    const int n,
+    const lbfgsfloatval_t step
+    )
+{
+    int i;
+    lbfgsfloatval_t fx = 0.0;
+
+    for (i = 0;i < n;i += 2) {
+        lbfgsfloatval_t t1 = 1.0 - x[i];
+        lbfgsfloatval_t t2 = 10.0 * (x[i+1] - x[i] * x[i]);
+        g[i+1] = 20.0 * t2;
+        g[i] = -2.0 * (x[i] * g[i+1] + t1);
+        fx += t1 * t1 + t2 * t2;
+    }
+    return fx;
+}
+
+static int progress(
+    void *instance,
+    const lbfgsfloatval_t *x,
+    const lbfgsfloatval_t *g,
+    const lbfgsfloatval_t fx,
+    const lbfgsfloatval_t xnorm,
+    const lbfgsfloatval_t gnorm,
+    const lbfgsfloatval_t step,
+    int n,
+    int k,
+    int ls
+    )
+{
+    printf("Iteration %d:\n", k);
+    printf("  fx = %f, x[0] = %f, x[1] = %f\n", fx, x[0], x[1]);
+    printf("  xnorm = %f, gnorm = %f, step = %f\n", xnorm, gnorm, step);
+    printf("\n");
+    return 0;
+}
+
+#define N   100
+
+int main(int argc, char *argv[])
+{
+    int i, ret = 0;
+    lbfgsfloatval_t fx;
+    lbfgsfloatval_t *x = lbfgs_malloc(N);
+    lbfgs_parameter_t param;
+
+    if (x == NULL) {
+        printf("ERROR: Failed to allocate a memory block for variables.\n");
+        return 1;
+    }
+
+    /* Initialize the variables. */
+    for (i = 0;i < N;i += 2) {
+        x[i] = -1.2;
+        x[i+1] = 1.0;
+    }
+
+    /* Initialize the parameters for the L-BFGS optimization. */
+    lbfgs_parameter_init(&param);
+    /*param.linesearch = LBFGS_LINESEARCH_BACKTRACKING;*/
+
+    /*
+        Start the L-BFGS optimization; this will invoke the callback functions
+        evaluate() and progress() when necessary.
+     */
+    ret = lbfgs(N, x, &fx, evaluate, progress, NULL, &param);
+
+    /* Report the result. */
+    printf("L-BFGS optimization terminated with status code = %d\n", ret);
+    printf("  fx = %f, x[0] = %f, x[1] = %f\n", fx, x[0], x[1]);
+
+    lbfgs_free(x);
+    return 0;
+}
diff --git a/src/shogun/features/DenseSubsetFeatures.cpp b/src/shogun/features/DenseSubsetFeatures.cpp
@@ -0,0 +1,12 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Written (W) 2012 Chiyuan Zhang
+ * Copyright (C) 2012 Chiyuan Zhang
+ */
+
+#include <shogun/features/DenseSubsetFeatures.h>
+