Added example and tests, found major bug???

examples/active_learners/pref_gp_ucb_learner.py

@@ -0,0 +1,76 @@
+# Copyright 2024 Ian Rankin
+#
+# Permission is hereby granted, free of charge, to any person obtaining a copy of this
+# software and associated documentation files (the "Software"), to deal in the Software
+# without restriction, including without limitation the rights to use, copy, modify, merge,
+# publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons
+# to whom the Software is furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in all copies or
+# substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED,
+# INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR
+# PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE
+# FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+# OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+# DEALINGS IN THE SOFTWARE.
+
+# GP_UCB_learner.py
+# Written Ian Rankin - January 2024
+#
+# An example usage of preference GP with a UCB active learning algorithm
+# This is done using a 1D function.
+
+
+import numpy as np
+import matplotlib.pyplot as plt
+
+import lop
+
+
+# the function to approximate
+def f_sin(x, data=None):
+    return 2 * np.cos(np.pi * (x-2)) * np.exp(-(0.9*x))
+
+def main():
+    al = lop.GV_UCBLearner()
+    model = lop.PreferenceGP(lop.RBF_kern(0.5,0.7), active_learner=al, normalize_gp=True)
+
+
+    # Generate active learning point and add it to the model
+    for i in range(10):
+        # generate random test set to select test point from
+        x_canidiates = np.random.random(20)*10
+
+        test_pt_idxs = model.select(x_canidiates, 2)
+
+
+        x_train = x_canidiates[test_pt_idxs]
+        y_train = f_sin(x_train)
+        y_pairs = lop.gen_pairs_from_idx(np.argmax(y_train), list(range(len(y_train))))
+
+        model.add(x_train, y_pairs)
+
+    # Create test output of model
+    x_test = np.arange(0,10,0.005)
+    y_test = f_sin(x_test)
+    y_pred,y_sigma = model.predict(x_test)
+    std = np.sqrt(y_sigma)
+
+    print(std)
+
+    # Plot output of model with uncertianty
+    sigma_to_plot = 1.96
+    plt.plot(x_test, y_test, zorder=5)
+    plt.plot(x_test, y_pred, zorder=5)
+    plt.scatter(model.X_train, model.F, zorder=10)
+    plt.gca().fill_between(x_test, y_pred-(sigma_to_plot*std), y_pred+(sigma_to_plot*std), color='#dddddd', zorder=1)
+    plt.xlabel('input values')
+    plt.ylabel('GP output')
+    plt.legend(['Real function', 'Predicted function', 'Active learning points', '95% condidence region'])
+    plt.show()
+
+if __name__ == '__main__':
+    main()
+

tests/active_learning/test_GV_UCB_learner.py

@@ -46,3 +46,32 @@ def test_GV_UCB_learner_trains_basic_GP():
 
     assert (np.abs(y_pred - y_test) < 0.2).all()
 
+
+def test_GV_UCB_learner_trains_preference_GP():
+    al = lop.GV_UCBLearner()
+    model = lop.PreferenceGP(lop.RBF_kern(0.5,1.0), active_learner=al, normalize_positive=True)
+
+
+    np.random.seed(5) # just to ensure it doesn't break the test on a bad dice roll
+    for i in range(10):
+        # generate random test set to select test point from
+        x_canidiates = np.random.random(20)*10
+
+        test_pt_idxs = model.select(x_canidiates, 3)
+
+
+        x_train = x_canidiates[test_pt_idxs]
+        y_train = f_sin(x_train)
+
+        y_pairs = lop.gen_pairs_from_idx(np.argmax(y_train), list(range(len(y_train))))
+
+        model.add(x_train, y_pairs)
+
+    x_test = np.array([1.6,1.8,2.1,2.3,2.5,2.7])
+    y_test = f_sin(x_test)
+    y_pred = model(x_test)
+
+    assert not np.isnan(y_pred).any()
+
+    assert (np.abs(y_pred - y_test) < 0.5).all()
+

tests/utilities/test_utility.py

@@ -55,3 +55,22 @@ def test_fake_pairs():
         assert p[1] == 0
         assert p[2] == i+1
 
+
+
+def test_gen_pairs_from_idx():
+    y_train = np.array([0,1,2,3])
+
+    y_pairs = lop.gen_pairs_from_idx(np.argmax(y_train), list(range(len(y_train))))
+
+    assert len(y_pairs) == 3
+    assert y_pairs[0][0] == -1
+    assert y_pairs[0][1] == 3
+    assert y_pairs[0][2] == 0
+    assert y_pairs[1][0] == -1
+    assert y_pairs[1][1] == 3
+    assert y_pairs[1][2] == 1
+    assert y_pairs[2][0] == -1
+    assert y_pairs[2][1] == 3
+    assert y_pairs[2][2] == 2
+
+