chore: better accuracy

compiled_model/client.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a0e943aec188cb35e60d78e2280a4a4b346aded279b692a6be2d01f1a045710
-size 104293
+oid sha256:d39a9cede3a266cbf62cec33bf05fffe63c5bc11fbfe0781e0d49043ae133754
+size 104292

compiled_model/server.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72f18576ba0bfe05cdadcc34a8a65233286e158c8f2b70880d99457b1b860378
+oid sha256:c876bee83abe4fc626d129544390568d9d05786f72ef19f3ff656499505e1494
 size 2687

creating_models.py

@@ -11,7 +11,7 @@ def compile_and_make_it_deployable(model_dev, X_train):
     path_to_model = Path("compiled_model")
 
     # Compile into FHE
-    model_dev.compile(X_train, p_error=0.8)
+    model_dev.compile(X_train, p_error=0.01)
 
     # Saving the model
     shutil.rmtree(path_to_model, ignore_errors=True)
@@ -27,6 +27,12 @@ def compile_and_make_it_deployable(model_dev, X_train):
 
     print(f"Your keys will be {sys.getsizeof(evaluation_keys) / 1024 / 1024}-megabytes long")
 
+    # Check accuracy with p_error
+    y_pred_concrete = model_dev.predict_proba(x_test, fhe="simulate")[:, 1]
+    concrete_average_precision = average_precision_score(y_test, y_pred_concrete)
+
+    print(f"Concrete average precision score (simulate): {concrete_average_precision:0.2f}")
+
 
 # This is the spam classifier. Taken from https://github.com/zama-ai/concrete-ml/blob/main/docs/advanced_examples/DecisionTreeClassifier.ipynb
 import numpy