add tests for new gpr models

server/analysis/gp_tf.py

@@ -36,7 +36,7 @@ class GPRGDResult(GPRResult):
 
 class GPR(object):
 
-    def __init__(self, length_scale=1.0, magnitude=1.0, ridge=1.0, max_train_size=7000,
+    def __init__(self, length_scale=2.0, magnitude=1.0, ridge=1.0, max_train_size=7000,
                  batch_size=3000, num_threads=4, check_numerics=True, debug=False,
                  hyperparameter_trainable=False):
         assert np.isscalar(length_scale)
@@ -348,7 +348,7 @@ class GPRGD(GPR):
     GP_BETA_CONST = "CONST"
 
     def __init__(self,
-                 length_scale=1.0,
+                 length_scale=2.0,
                  magnitude=1.0,
                  ridge=1.0,
                  max_train_size=7000,

server/analysis/tests/test_gpr.py

@@ -4,11 +4,16 @@
 # Copyright (c) 2017-18, Carnegie Mellon University Database Group
 #
 import unittest
+import random
 import numpy as np
+import gpflow
+import tensorflow as tf
 from sklearn import datasets
 from analysis.gp import GPRNP
 from analysis.gp_tf import GPR
 from analysis.gp_tf import GPRGD
+from analysis.gpr import gpr_models
+from analysis.gpr.optimize import tf_optimize
 
 # test numpy version GPR
 class TestGPRNP(unittest.TestCase):
@@ -88,3 +93,78 @@ class TestGPRGD(unittest.TestCase):
         sigmas_round = [round(x[0], 4) for x in self.gpr_result.sigmas]
         expected_sigmas = [1.4142, 1.4142, 1.4142, 1.4142, 1.4142, 1.4142]
         self.assertEqual(sigmas_round, expected_sigmas)
+
+
+# test Gradient Descent in GPFlow model
+class TestGPRGP(unittest.TestCase):
+
+    @classmethod
+    def setUpClass(cls):
+        super(TestGPRGP, cls).setUpClass()
+        boston = datasets.load_boston()
+        data = boston['data']
+        X_train = data[0:500]
+        X_test = data[500:501]
+        y_train = boston['target'][0:500].reshape(500, 1)
+        X_min = np.min(X_train, 0)
+        X_max = np.max(X_train, 0)
+
+        random.seed(0)
+        np.random.seed(0)
+        tf.set_random_seed(0)
+
+        model_kwargs = {}
+        opt_kwargs = {}
+        opt_kwargs['learning_rate'] = 0.01
+        opt_kwargs['maxiter'] = 10
+        opt_kwargs['bounds'] = [X_min, X_max]
+        opt_kwargs['ucb_beta'] = 1.0
+
+        tf.reset_default_graph()
+        graph = tf.get_default_graph()
+        gpflow.reset_default_session(graph=graph)
+        cls.m = gpr_models.create_model('BasicGP', X=X_train, y=y_train, **model_kwargs)
+        cls.gpr_result = tf_optimize(cls.m.model, X_test, **opt_kwargs)
+
+    def test_gprnp_ypreds(self):
+        ypreds_round = [round(x[0], 4) for x in self.gpr_result.ypreds]
+        expected_ypreds = [0.5272]
+        self.assertEqual(ypreds_round, expected_ypreds)
+
+    def test_gprnp_sigmas(self):
+        sigmas_round = [round(x[0], 4) for x in self.gpr_result.sigmas]
+        expected_sigmas = [1.4153]
+        self.assertEqual(sigmas_round, expected_sigmas)
+
+
+# test Gradient Descent in Tensorflow GPRGD model
+class TestGPRGDGD(unittest.TestCase):
+
+    @classmethod
+    def setUpClass(cls):
+        super(TestGPRGDGD, cls).setUpClass()
+        boston = datasets.load_boston()
+        data = boston['data']
+        X_train = data[0:500]
+        X_test = data[500:501]
+        y_train = boston['target'][0:500].reshape(500, 1)
+        Xmin = np.min(X_train, 0)
+        Xmax = np.max(X_train, 0)
+        random.seed(0)
+        np.random.seed(0)
+        tf.set_random_seed(0)
+
+        cls.model = GPRGD(length_scale=2.0, magnitude=1.0, max_iter=10, learning_rate=0.01,
+                          ridge=1.0, hyperparameter_trainable=True, sigma_multiplier=1.0)
+        cls.model.fit(X_train, y_train, Xmin, Xmax)
+        cls.gpr_result = cls.model.predict(X_test)
+
+    def test_gprnp_ypreds(self):
+        ypreds_round = [round(x[0], 4) for x in self.gpr_result.ypreds]
+        expected_ypreds = [0.5272]
+        self.assertEqual(ypreds_round, expected_ypreds)
+
+    def test_gprnp_sigmas(self):
+        sigmas_round = [round(x[0], 4) for x in self.gpr_result.sigmas]
+        expected_sigmas = [1.4153]
+        self.assertEqual(sigmas_round, expected_sigmas)

server/website/website/settings/constants.py

@@ -27,7 +27,7 @@ FLIP_PROB_DECAY = 0.5
 # ---GPR CONSTANTS---
 USE_GPFLOW = True
 
-DEFAULT_LENGTH_SCALE = 1.0
+DEFAULT_LENGTH_SCALE = 2.0
 
 DEFAULT_MAGNITUDE = 1.0
 
@@ -54,7 +54,7 @@ DEFAULT_RIDGE = 1.0
 
 DEFAULT_EPSILON = 1e-6
 
-DEFAULT_SIGMA_MULTIPLIER = 3.0
+DEFAULT_SIGMA_MULTIPLIER = 1.0
 
 DEFAULT_MU_MULTIPLIER = 1.0