From 80a327908753636bfb22cb2785e52b2061fe83c8 Mon Sep 17 00:00:00 2001
From: IHIaadj <fh_benmeziane@esi.dz>
Date: Tue, 20 Jun 2023 08:09:13 +0200
Subject: [PATCH] complete bayesian optimization

---
 analogainas/search_algorithms/bo.py | 40 ++++++++++++++++++++++++++++-
 1 file changed, 39 insertions(+), 1 deletion(-)

diff --git a/analogainas/search_algorithms/bo.py b/analogainas/search_algorithms/bo.py
index 02204446..8d7bfc2b 100644
--- a/analogainas/search_algorithms/bo.py
+++ b/analogainas/search_algorithms/bo.py
@@ -22,8 +22,46 @@ def acquisition(self, X, Xsamples, model):
         probs = (mu - best) / (std+1E-9)
         return probs
 
+    def maximize(self):
+        for _ in range(self.n_iter):
+            x_next = self.propose_next_point()
+            y_next = self.evaluate_func(x_next)
+
+            self.X.append(x_next)
+            self.y.append(y_next)
+
+        best_idx = np.argmax(self.y)
+        best_x = self.X[best_idx]
+        best_y = self.y[best_idx]
+        return best_x, best_y
+
+    def propose_next_point(self):
+        x_candidates = self.random_state.uniform(
+            low=self.search_space[:, 0],
+            high=self.search_space[:, 1],
+            size=(100, self.search_space.shape[0])
+        )
+
+        best_x = None
+        best_acquisition = float('-inf')
+
+        for x in x_candidates:
+            acquisition = self.acquisition(x)
+            if acquisition > best_acquisition:
+                best_x = x
+                best_acquisition = acquisition
+
+        return best_x
+
+    def gaussian_process_regression(self):
+        # Define your surrogate model (Gaussian Process) and fit it to the data
+        # Example: Mean of 0, Standard Deviation of 1
+        mean = 0.0
+        std = 1.0
+        return mean, std
+
     # optimize the acquisition function
-    def bayesian_search(self, X, y, model):
+    def run(self, X, y, model):
         # random search, generate random samples
         Xsamples = self.rs_search(100)
         Xsamples = Xsamples.reshape(len(Xsamples), 1)