Change model to decision tree

deployment_files/client.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:859c5895ff365bfd7fa8b592784717d14094c29aaee032c2f23716d225c15855
-size 29354
+oid sha256:7bad4947dfc472f67c4ac52c5a26077177b8993ee8b1541ae3fb7c473d94d7fb
+size 28647

deployment_files/server.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3490a405f8634b3c95f6a2d3fb8cf0276e3f49adc4b25911afab7f97524c2f7a
-size 2308
+oid sha256:0b1e87acc2acda1565b6b23ea82be8d6c6cc4b3747106502f73ebc62397cceaa
+size 1731

development.py

@@ -17,7 +17,7 @@ from settings import (
     THIRD_PARTY_COLUMNS,
 )
 from utils.client_server_interface import MultiInputsFHEModelDev
-from utils.model import MultiInputXGBClassifier
+from utils.model import MultiInputDecisionTreeClassifier
 from utils.pre_processing import get_pre_processors
 
 
@@ -54,7 +54,7 @@ preprocessed_data_x = numpy.concatenate((preprocessed_data_user, preprocessed_da
 
 print("\nTrain and compile the model")
 
-model = MultiInputXGBClassifier(max_depth=3, n_estimators=20)
+model = MultiInputDecisionTreeClassifier()
 
 model, sklearn_model = model.fit_benchmark(preprocessed_data_x, data_y)
  
@@ -62,13 +62,12 @@ multi_inputs_train = get_processed_multi_inputs(preprocessed_data_x)
 
 model.compile(*multi_inputs_train, inputs_encryption_status=["encrypted", "encrypted", "encrypted"])
 
+print("\nSave deployment files")
+
 # Delete the deployment folder and its content if it already exists
 if DEPLOYMENT_PATH.is_dir():
     shutil.rmtree(DEPLOYMENT_PATH)
 
-
-print("\nSave deployment files")
-
 # Save files needed for deployment (and enable cross-platform deployment)
 fhe_dev = MultiInputsFHEModelDev(DEPLOYMENT_PATH, model)
 fhe_dev.save(via_mlir=True)

utils/model.py

@@ -13,10 +13,9 @@ from concrete.ml.common.utils import (
     check_there_is_no_p_error_options_in_configuration
 )
 from concrete.ml.quantization.quantized_module import QuantizedModule, _get_inputset_generator
-from concrete.ml.sklearn import XGBClassifier as ConcreteXGBClassifier
+from concrete.ml.sklearn import DecisionTreeClassifier
 
-
-class MultiInputXGBClassifier(ConcreteXGBClassifier):
+class MultiInputModel:
 
     def quantize_input(self, *X: numpy.ndarray) -> numpy.ndarray:
         self.check_model_is_fitted()
@@ -171,3 +170,7 @@ class MultiInputXGBClassifier(ConcreteXGBClassifier):
             print(f"FHE execution time per inference: {numpy.mean(execution_times) :.2}s")
 
         return numpy.array(y_preds)
+
+
+class MultiInputDecisionTreeClassifier(MultiInputModel, DecisionTreeClassifier):
+    pass