Improve explainability inner workings

app.py

@@ -10,13 +10,15 @@ from settings import (
     CHILDREN_MIN_MAX,
     INCOME_MIN_MAX,
     AGE_MIN_MAX,
-    EMPLOYED_MIN_MAX,
     FAMILY_MIN_MAX,
     INCOME_TYPES,
     OCCUPATION_TYPES,
     HOUSING_TYPES,
     EDUCATION_TYPES,
     FAMILY_STATUS,
+    YEARS_EMPLOYED_BINS,
+    INCOME_VALUE,
+    AGE_VALUE,
 )
 from backend import (
     keygen_send,
@@ -25,7 +27,7 @@ from backend import (
     pre_process_encrypt_send_third_party,
     run_fhe,
     get_output_and_decrypt,
-    years_employed_encrypt_run_decrypt,
+    explain_encrypt_run_decrypt,
 )
 
 
@@ -97,18 +99,67 @@ with demo:
     with gr.Row():
         with gr.Column():
             gr.Markdown("### User")
-            bool_inputs = gr.CheckboxGroup(["Car", "Property", "Mobile phone"], label="Which of the following do you actively hold or own?")
-            num_children = gr.Slider(**CHILDREN_MIN_MAX, step=1, label="Number of children", info="How many children do you have ?")
-            household_size = gr.Slider(**FAMILY_MIN_MAX, step=1, label="Household size", info="How many members does your household have ?")
-            total_income = gr.Slider(**INCOME_MIN_MAX, label="Income", info="What's you total yearly income (in euros) ?")
-            age = gr.Slider(**AGE_MIN_MAX, step=1, label="Age", info="How old are you ?")
+            bool_inputs = gr.CheckboxGroup(
+                ["Car", "Property", "Mobile phone"], 
+                label="Which of the following do you actively hold or own?"
+            )
+            num_children = gr.Slider(
+                **CHILDREN_MIN_MAX, 
+                step=1, 
+                label="Number of children", 
+                info="How many children do you have ?"
+            )
+            household_size = gr.Slider(
+                **FAMILY_MIN_MAX, 
+                step=1, 
+                label="Household size", 
+                info="How many members does your household have ?"
+            )
+            total_income = gr.Slider(
+                **INCOME_MIN_MAX,
+                value=INCOME_VALUE,
+                label="Income", 
+                info="What's you total yearly income (in euros) ?"
+            )
+            age = gr.Slider(
+                **AGE_MIN_MAX,
+                value=AGE_VALUE, 
+                step=1, 
+                label="Age", 
+                info="How old are you ?"
+            )
 
         with gr.Column():
-            income_type = gr.Dropdown(choices=INCOME_TYPES, value=INCOME_TYPES[0], label="Income type", info="What is your main type of income ?")
-            education_type = gr.Dropdown(choices=EDUCATION_TYPES, value=EDUCATION_TYPES[0], label="Education", info="What is your education background ?")
-            family_status = gr.Dropdown(choices=FAMILY_STATUS, value=FAMILY_STATUS[0], label="Family", info="What is your family status ?")
-            occupation_type = gr.Dropdown(choices=OCCUPATION_TYPES, value=OCCUPATION_TYPES[0], label="Occupation", info="What is your main occupation ?")
-            housing_type = gr.Dropdown(choices=HOUSING_TYPES, value=HOUSING_TYPES[0], label="Housing", info="In what type of housing do you live ?")
+            income_type = gr.Dropdown(
+                choices=INCOME_TYPES, 
+                value=INCOME_TYPES[0], 
+                label="Income type", 
+                info="What is your main type of income ?"
+            )
+            education_type = gr.Dropdown(
+                choices=EDUCATION_TYPES, 
+                value=EDUCATION_TYPES[0], 
+                label="Education", 
+                info="What is your education background ?"
+            )
+            family_status = gr.Dropdown(
+                choices=FAMILY_STATUS, 
+                value=FAMILY_STATUS[0], 
+                label="Family", 
+                info="What is your family status ?"
+            )
+            occupation_type = gr.Dropdown(
+                choices=OCCUPATION_TYPES, 
+                value=OCCUPATION_TYPES[0], 
+                label="Occupation", 
+                info="What is your main occupation ?"
+            )
+            housing_type = gr.Dropdown(
+                choices=HOUSING_TYPES, 
+                value=HOUSING_TYPES[0], 
+                label="Housing", 
+                info="In what type of housing do you live ?"
+            )
 
         with gr.Column():
             encrypt_button_user = gr.Button("Encrypt the inputs and send to server.")
@@ -120,7 +171,12 @@ with demo:
     with gr.Row():
         with gr.Column(scale=2):
             gr.Markdown("### Bank ")
-            account_age = gr.Slider(**ACCOUNT_MIN_MAX, step=1, label="Account age (months)", info="How long have this person had this bank account (in months) ?")
+            account_age = gr.Slider(
+                **ACCOUNT_MIN_MAX, 
+                step=1, 
+                label="Account age (months)", 
+                info="How long have this person had this bank account (in months) ?"
+            )
 
         with gr.Column():
             encrypt_button_bank = gr.Button("Encrypt the inputs and send to server.")
@@ -133,7 +189,12 @@ with demo:
         with gr.Column(scale=2):
             gr.Markdown("### Third party ")
             employed = gr.Radio(["Yes", "No"], label="Is the person employed ?", value="Yes")
-            years_employed = gr.Slider(**EMPLOYED_MIN_MAX, step=1, label="Years of employment", info="How long have this person been employed (in years) ?")
+            years_employed = gr.Dropdown(
+                choices=YEARS_EMPLOYED_BINS, 
+                value=YEARS_EMPLOYED_BINS[0], 
+                label="Years of employment", 
+                info="How long have this person been employed (in years) ?"
+            )
 
         with gr.Column():
             encrypt_button_third_party = gr.Button("Encrypt the inputs and send to server.")
@@ -163,7 +224,7 @@ with demo:
     # client side to the server    
     encrypt_button_third_party.click(
         pre_process_encrypt_send_third_party,
-        inputs=[client_id, employed, years_employed],
+        inputs=[client_id, years_employed, employed],
         outputs=[encrypted_input_third_party],
     )
 
@@ -230,20 +291,18 @@ with demo:
         parties, runs the new prediction in FHE and decrypts the output. 
         """
     )
-    years_employed_prediction_button = gr.Button(
+    explain_button = gr.Button(
         "Encrypt the inputs, compute in FHE and decrypt the output."
     )
-    years_employed_prediction = gr.Textbox(
+    explain_prediction = gr.Textbox(
         label="Additional years of employed required.", max_lines=1, interactive=False
     )
 
     # Button to explain the prediction
-    years_employed_prediction_button.click(
-        years_employed_encrypt_run_decrypt,
-        inputs=[client_id, prediction_output, bool_inputs, num_children, household_size, \
-                total_income, age, income_type, education_type, family_status, occupation_type, \
-                housing_type, account_age, employed, years_employed],
-        outputs=[years_employed_prediction],
+    explain_button.click(
+        explain_encrypt_run_decrypt,
+        inputs=[client_id, prediction_output, years_employed, employed],
+        outputs=[explain_prediction],
     )
 
     gr.Markdown(

backend.py

@@ -14,26 +14,22 @@ from settings import (
     FHE_KEYS,
     CLIENT_FILES,
     SERVER_FILES,
-    APPROVAL_DEPLOYMENT_PATH,
-    EXPLAIN_DEPLOYMENT_PATH,
-    APPROVAL_PROCESSED_INPUT_SHAPE,
-    EXPLAIN_PROCESSED_INPUT_SHAPE,
+    DEPLOYMENT_PATH,
+    PROCESSED_INPUT_SHAPE,
     INPUT_INDEXES,
-    APPROVAL_INPUT_SLICES,
-    EXPLAIN_INPUT_SLICES,
+    INPUT_SLICES,
     PRE_PROCESSOR_USER_PATH, 
     PRE_PROCESSOR_BANK_PATH,
     PRE_PROCESSOR_THIRD_PARTY_PATH,
     CLIENT_TYPES,
     USER_COLUMNS,
     BANK_COLUMNS,
-    APPROVAL_THIRD_PARTY_COLUMNS,
+    THIRD_PARTY_COLUMNS,
+    YEARS_EMPLOYED_BINS,
+    YEARS_EMPLOYED_BIN_NAME_TO_INDEX,
 )
 
-from utils.client_server_interface import MultiInputsFHEModelClient, MultiInputsFHEModelServer
-
-# Load the server used for explaining the prediction
-EXPLAIN_FHE_SERVER = MultiInputsFHEModelServer(EXPLAIN_DEPLOYMENT_PATH)
+from utils.client_server_interface import MultiInputsFHEModelClient
 
 # Load pre-processor instances
 with (
@@ -93,22 +89,18 @@ def clean_temporary_files(n_keys=20):
                 shutil.rmtree(directory)
 
 
-def _get_client(client_id, is_approval=True):
+def _get_client(client_id):
     """Get the client instance.
 
     Args:
         client_id (int): The client ID to consider.
-        is_approval (bool): If client is representing the 'approval' model (else, it is 
-            representing the 'explain' model). Default to True.
 
     Returns:
         FHEModelClient: The client instance.
     """
-    key_suffix = "approval" if is_approval else "explain"
-    key_dir = FHE_KEYS / f"{client_id}_{key_suffix}"
-    client_dir = APPROVAL_DEPLOYMENT_PATH if is_approval else EXPLAIN_DEPLOYMENT_PATH
+    key_dir = FHE_KEYS / f"{client_id}"
 
-    return MultiInputsFHEModelClient(client_dir, key_dir=key_dir, nb_inputs=len(CLIENT_TYPES))
+    return MultiInputsFHEModelClient(DEPLOYMENT_PATH, key_dir=key_dir, nb_inputs=len(CLIENT_TYPES))
 
 
 def _get_client_file_path(name, client_id, client_type=None):
@@ -206,7 +198,7 @@ def keygen_send():
     return client_id, evaluation_key_short, gr.update(value="Keys are generated and evaluation key is sent ✅")
 
 
-def _encrypt_send(client_id, inputs, client_type, app_mode=True):
+def _encrypt_send(client_id, inputs, client_type):
     """Encrypt the given inputs for a specific client and send it to the server.
 
     Args:
@@ -227,8 +219,8 @@ def _encrypt_send(client_id, inputs, client_type, app_mode=True):
     encrypted_inputs = client.quantize_encrypt_serialize_multi_inputs(
         inputs, 
         input_index=INPUT_INDEXES[client_type], 
-        processed_input_shape=APPROVAL_PROCESSED_INPUT_SHAPE, 
-        input_slice=APPROVAL_INPUT_SLICES[client_type],
+        processed_input_shape=PROCESSED_INPUT_SHAPE, 
+        input_slice=INPUT_SLICES[client_type],
     )
 
     file_name = "encrypted_inputs"
@@ -248,14 +240,15 @@ def _encrypt_send(client_id, inputs, client_type, app_mode=True):
     return encrypted_inputs_short
 
 
-def _pre_process_user(*inputs):
-    """Pre-process the user inputs.
+def pre_process_encrypt_send_user(client_id, *inputs):
+    """Pre-process, encrypt and send the user inputs for a specific client to the server.
 
     Args:
+        client_id (str): The current client ID to consider.
         *inputs (Tuple[numpy.ndarray]): The inputs to pre-process.
     
     Returns:
-        (numpy.ndarray): The pre-processed inputs. 
+        (str): A short representation of the encrypted input to send in hex. 
     """
     bool_inputs, num_children, household_size, total_income, age, income_type, education_type, \
         family_status, occupation_type, housing_type = inputs
@@ -284,32 +277,18 @@ def _pre_process_user(*inputs):
 
     preprocessed_user_inputs = PRE_PROCESSOR_USER.transform(user_inputs)
 
-    return preprocessed_user_inputs
-
-
-def pre_process_encrypt_send_user(client_id, *inputs):
-    """Pre-process, encrypt and send the user inputs for a specific client to the server.
-
-    Args:
-        client_id (str): The current client ID to consider.
-        *inputs (Tuple[numpy.ndarray]): The inputs to pre-process.
-    
-    Returns:
-        (str): A short representation of the encrypted input to send in hex. 
-    """
-    preprocessed_user_inputs = _pre_process_user(*inputs)
-
     return _encrypt_send(client_id, preprocessed_user_inputs, "user")
 
 
-def _pre_process_bank(*inputs):
-    """Pre-process the bank inputs.
+def pre_process_encrypt_send_bank(client_id, *inputs):
+    """Pre-process, encrypt and send the bank inputs for a specific client to the server.
 
     Args:        
+        client_id (str): The current client ID to consider.
         *inputs (Tuple[numpy.ndarray]): The inputs to pre-process.
     
     Returns:
-        (numpy.ndarray): The pre-processed inputs.
+        (str): A short representation of the encrypted input to send in hex. 
     """
     account_age = inputs[0]
 
@@ -321,52 +300,7 @@ def _pre_process_bank(*inputs):
 
     preprocessed_bank_inputs = PRE_PROCESSOR_BANK.transform(bank_inputs)
     
-    return preprocessed_bank_inputs
-
-
-def pre_process_encrypt_send_bank(client_id, *inputs):
-    """Pre-process, encrypt and send the bank inputs for a specific client to the server.
-
-    Args:        
-        client_id (str): The current client ID to consider.
-        *inputs (Tuple[numpy.ndarray]): The inputs to pre-process.
-    
-    Returns:
-        (str): A short representation of the encrypted input to send in hex. 
-    """
-    preprocessed_bank_inputs = _pre_process_bank(*inputs)
-    
     return _encrypt_send(client_id, preprocessed_bank_inputs, "bank")
-    
-
-def _pre_process_third_party(*inputs):
-    """Pre-process the third party inputs.
-
-    Args:
-        *inputs (Tuple[numpy.ndarray]): The inputs to pre-process.
-
-    Returns:
-        (numpy.ndarray): The pre-processed inputs.
-    """
-    third_party_data = {}
-    if len(inputs) == 1:
-        employed = inputs[0]
-    else:
-        employed, years_employed = inputs
-        third_party_data["Years_employed"] = [years_employed]
-
-    is_employed = employed == "Yes"
-    third_party_data["Employed"] = [is_employed]
-
-    third_party_inputs = pandas.DataFrame(third_party_data)
-
-    if len(inputs) == 1:
-        preprocessed_third_party_inputs = third_party_inputs.to_numpy()
-    else:
-        third_party_inputs = third_party_inputs.reindex(APPROVAL_THIRD_PARTY_COLUMNS, axis=1)
-        preprocessed_third_party_inputs = PRE_PROCESSOR_THIRD_PARTY.transform(third_party_inputs)
-
-    return preprocessed_third_party_inputs
 
 
 def pre_process_encrypt_send_third_party(client_id, *inputs):
@@ -379,7 +313,18 @@ def pre_process_encrypt_send_third_party(client_id, *inputs):
     Returns:
         (str): A short representation of the encrypted input to send in hex. 
     """
-    preprocessed_third_party_inputs = _pre_process_third_party(*inputs)
+    years_employed_bin, employed = inputs
+
+    years_employed = YEARS_EMPLOYED_BIN_NAME_TO_INDEX[years_employed_bin]
+    is_employed = employed == "Yes"
+
+    third_party_inputs = pandas.DataFrame({
+        "Years_employed": [years_employed],
+        "Employed": [is_employed],
+    })
+
+    third_party_inputs = third_party_inputs.reindex(THIRD_PARTY_COLUMNS, axis=1)
+    preprocessed_third_party_inputs = PRE_PROCESSOR_THIRD_PARTY.transform(third_party_inputs)
 
     return _encrypt_send(client_id, preprocessed_third_party_inputs, "third_party")
 
@@ -459,7 +404,7 @@ def get_output_and_decrypt(client_id):
             raise gr.Error("Please run the FHE execution first and wait for it to be completed.")
 
 
-def years_employed_encrypt_run_decrypt(client_id, prediction_output, *inputs):
+def explain_encrypt_run_decrypt(client_id, prediction_output, *inputs):
     """Pre-process and encrypt the inputs, run the prediction in FHE and decrypt the output. 
 
     Args:
@@ -470,8 +415,7 @@ def years_employed_encrypt_run_decrypt(client_id, prediction_output, *inputs):
     
     Returns:
         (str): A message indicating the number of additional years of employment that could be 
-            required in order to increase the chance of 
-            credit card approval.
+            required in order to increase the chance of credit card approval.
     """
 
     if "approved" in prediction_output:
@@ -479,63 +423,60 @@ def years_employed_encrypt_run_decrypt(client_id, prediction_output, *inputs):
             "Explaining the prediction can only be done if the credit card is likely to be denied."
         )
 
-    # Retrieve the client instance
-    client = _get_client(client_id, is_approval=False)
+    # Retrieve the third party inputs
+    years_employed, employed = inputs
 
-    # Generate the private and evaluation keys
-    client.generate_private_and_evaluation_keys(force=False)
+    # Years_employed is divided into several ordered bins. Here, we retrieve the index representing 
+    # the bin from the input
+    bin_index = YEARS_EMPLOYED_BIN_NAME_TO_INDEX[years_employed]
 
-    # Retrieve the serialized evaluation key
-    evaluation_key = client.get_serialized_evaluation_keys()
+    # If the bin is not the last (representing the most years of employment), we run the model in 
+    # FHE for each bins "older" than the given bin, in order. Then, we retrieve the first bin that
+    # changes the model's prediction to "approval" and display it to the user.  
+    if bin_index != len(YEARS_EMPLOYED_BINS) - 1:
 
-    bool_inputs, num_children, household_size, total_income, age, income_type, education_type, \
-        family_status, occupation_type, housing_type, account_age, employed, years_employed = inputs
+        output_predictions = []
+        
+        # Loop over the bins "older" than the input one
+        for years_employed_bin in YEARS_EMPLOYED_BINS[bin_index+1:]:
+            
+            # Send the new encrypted input
+            pre_process_encrypt_send_third_party(client_id, years_employed_bin, employed)
 
-    preprocessed_user_inputs = _pre_process_user(
-        bool_inputs, num_children, household_size, total_income, age, income_type, education_type,
-        family_status, occupation_type, housing_type,
-    )
-    preprocessed_bank_inputs = _pre_process_bank(account_age)
-    preprocessed_third_party_inputs = _pre_process_third_party(employed)
+            # Run the model in FHE
+            run_fhe(client_id)
 
-    preprocessed_inputs = [
-        preprocessed_user_inputs, 
-        preprocessed_bank_inputs, 
-        preprocessed_third_party_inputs
-    ]
+            # Retrieve the new prediction
+            output_prediction = get_output_and_decrypt(client_id)
 
-    # Quantize, encrypt and serialize the inputs
-    encrypted_inputs = []
-    for client_type, preprocessed_input in zip(CLIENT_TYPES, preprocessed_inputs):
-        encrypted_input = client.quantize_encrypt_serialize_multi_inputs(
-            preprocessed_input, 
-            input_index=INPUT_INDEXES[client_type], 
-            processed_input_shape=EXPLAIN_PROCESSED_INPUT_SHAPE, 
-            input_slice=EXPLAIN_INPUT_SLICES[client_type],
-        )
-        encrypted_inputs.append(encrypted_input)
-    
-    # Run the FHE computation
-    encrypted_output = EXPLAIN_FHE_SERVER.run(
-        *encrypted_inputs, 
-        serialized_evaluation_keys=evaluation_key
-    )
+            is_approved = "approved" in output_prediction[0]
+            output_predictions.append(is_approved)
+        
+        # Re-send the initial third party inputs in order to avoid unwanted conflict (as sending
+        # some inputs basically re-writes the associated file on the server side)
+        pre_process_encrypt_send_third_party(client_id, years_employed, employed)
+        
+        # In case the model predicted at least one approval
+        if any(output_predictions):
 
-    # Decrypt the output
-    output_prediction = client.deserialize_decrypt_dequantize(encrypted_output)
+            # Retrieve the first bin that made the model predict an approval 
+            first_approved_prediction_index = numpy.argmax(output_predictions)
+            years_employed_bin_needed = YEARS_EMPLOYED_BINS[first_approved_prediction_index + bin_index + 1]
 
-    # Get the difference with the initial 'years of employment' input
-    years_employed_diff = int(numpy.ceil(output_prediction.squeeze() - years_employed))
+            return (
+                f"Having at least {years_employed_bin_needed} more years of employment would "
+                "increase your chance of having your credit card approved."
+            )
 
-    if years_employed_diff > 0:
         return (
-            f"Having at least {years_employed_diff} more years of employment would increase "
-            "your chance of having your credit card approved."
+            f"Increasing the number of years of employment up to {YEARS_EMPLOYED_BINS[-1]} years "
+            "does not seem to be enough to get an approval based on the given inputs. Other inputs "
+            "like the income or the account's age might have bigger impact in this particular case."
         )
 
     return (
-        "The number of years of employment you provided seems to be enough. The negative prediction "
-        "might come from other inputs."
+        f"You already have the maximum amount of years of employment ({years_employed} years). "
+        "Other inputs like the income or the account's age might have bigger impact in this "
+        "particular case."
     )
-
     

data/data.csv

@@ -1,57 +1,57 @@
 Own_car,Own_property,Mobile_phone,Num_children,Household_size,Total_income,Age,Income_type,Education_type,Family_status,Occupation_type,Housing_type,Account_age,Employed,Years_employed,Target
-1,1,1,2,4,27500.000000000004,35,Salaried,Higher education,Married,Engineer,House / apartment,36,1,5,1
+1,1,1,2,4,27500.000000000004,35,Salaried,Higher education,Married,Engineer,House / apartment,36,1,1,1
 0,0,1,0,1,11000.0,50,Pensioner,Secondary,Widow,Retired,Rented apartment,12,0,0,0
-1,1,0,1,3,41250.0,40,Self-employed,Higher education,Married,Business Owner,House / apartment,48,1,10,1
-0,1,0,1,2,16500.0,28,Salaried,Secondary,Single,Teacher,With parents,24,1,3,1
-1,0,1,0,1,24750.000000000004,32,Self-employed,Higher education,Divorced,Entrepreneur,Rented apartment,60,1,7,1
-0,1,1,3,5,19250.0,45,Salaried,Incomplete higher,Married,Office Worker,House / apartment,30,1,10,1
+1,1,0,1,3,41250.0,40,Self-employed,Higher education,Married,Business Owner,House / apartment,48,1,3,1
+0,1,0,1,2,16500.0,28,Salaried,Secondary,Single,Teacher,With parents,24,1,1,1
+1,0,1,0,1,24750.000000000004,32,Self-employed,Higher education,Divorced,Entrepreneur,Rented apartment,60,1,2,1
+0,1,1,3,5,19250.0,45,Salaried,Incomplete higher,Married,Office Worker,House / apartment,30,1,3,1
 1,0,0,0,1,13750.000000000002,55,Pensioner,Lower secondary,Widow,Retired,House / apartment,120,0,0,0
-0,1,1,2,3,33000.0,37,Salaried,Higher education,Married,Manager,House / apartment,36,1,12,1
-1,1,1,0,1,44000.0,29,Self-employed,Higher education,Single,Entrepreneur,House / apartment,48,1,6,1
-0,1,1,4,6,22000.0,38,Salaried,Secondary,Married,Salesperson,With parents,60,1,15,1
-1,0,0,1,2,30250.000000000004,26,Self-employed,Higher education,Married,Designer,Rented apartment,12,1,3,1
+0,1,1,2,3,33000.0,37,Salaried,Higher education,Married,Manager,House / apartment,36,1,4,1
+1,1,1,0,1,44000.0,29,Self-employed,Higher education,Single,Entrepreneur,House / apartment,48,1,2,1
+0,1,1,4,6,22000.0,38,Salaried,Secondary,Married,Salesperson,With parents,60,1,4,1
+1,0,0,1,2,30250.000000000004,26,Self-employed,Higher education,Married,Designer,Rented apartment,12,1,1,1
 0,0,0,0,1,16500.0,60,Pensioner,Lower secondary,Widow,Retired,House / apartment,180,0,0,0
-1,1,1,2,4,38500.0,45,Salaried,Higher education,Married,Manager,House / apartment,72,1,20,1
-0,1,1,3,5,35750.0,50,Salaried,Incomplete higher,Divorced,Teacher,House / apartment,96,1,25,1
-1,0,1,0,1,46750.00000000001,33,Self-employed,Higher education,Single,Consultant,Rented apartment,36,1,10,1
+1,1,1,2,4,38500.0,45,Salaried,Higher education,Married,Manager,House / apartment,72,1,5,1
+0,1,1,3,5,35750.0,50,Salaried,Incomplete higher,Divorced,Teacher,House / apartment,96,1,5,1
+1,0,1,0,1,46750.00000000001,33,Self-employed,Higher education,Single,Consultant,Rented apartment,36,1,3,1
 0,1,0,1,3,17600.0,55,Pensioner,Secondary,Widow,Retired,House / apartment,150,0,0,0
-1,1,1,2,4,49500.00000000001,41,Salaried,Higher education,Married,Doctor,House / apartment,60,1,15,1
+1,1,1,2,4,49500.00000000001,41,Salaried,Higher education,Married,Doctor,House / apartment,60,1,4,1
 0,0,1,0,1,12650.000000000002,24,Student,Incomplete higher,Single,Student,With parents,6,0,0,0
-1,0,0,1,3,26400.000000000004,35,Self-employed,Secondary,Divorced,Cooking Staff,Rented apartment,24,1,5,1
-0,1,1,3,5,30250.000000000004,50,Salaried,Higher education,Widow,Engineer,House / apartment,120,1,20,1
-1,0,1,0,2,38500.0,30,Salaried,Higher education,Married,Lawyer,Rented apartment,36,1,8,1
-0,1,0,2,4,17600.0,40,Self-employed,Secondary,Married,Carpenter,House / apartment,48,1,12,1
+1,0,0,1,3,26400.000000000004,35,Self-employed,Secondary,Divorced,Cooking Staff,Rented apartment,24,1,1,1
+0,1,1,3,5,30250.000000000004,50,Salaried,Higher education,Widow,Engineer,House / apartment,120,1,5,1
+1,0,1,0,2,38500.0,30,Salaried,Higher education,Married,Lawyer,Rented apartment,36,1,2,1
+0,1,0,2,4,17600.0,40,Self-employed,Secondary,Married,Carpenter,House / apartment,48,1,4,1
 1,0,1,1,2,14300.000000000002,29,Student,Higher education,Single,Student,With parents,12,0,0,0
 0,1,1,0,1,24750.000000000004,55,Pensioner,Lower secondary,Divorced,Retired,House / apartment,180,0,0,0
-1,1,1,1,3,44000.0,46,Salaried,Higher education,Married,Architect,House / apartment,72,1,18,1
-0,0,0,2,5,20350.0,33,Self-employed,Secondary,Single,Plumber,With parents,24,1,6,1
-1,1,1,0,1,35750.0,28,Self-employed,Higher education,Single,Designer,Rented apartment,36,1,4,1
+1,1,1,1,3,44000.0,46,Salaried,Higher education,Married,Architect,House / apartment,72,1,4,1
+0,0,0,2,5,20350.0,33,Self-employed,Secondary,Single,Plumber,With parents,24,1,2,1
+1,1,1,0,1,35750.0,28,Self-employed,Higher education,Single,Designer,Rented apartment,36,1,1,1
 0,0,0,1,2,15950.000000000002,53,Pensioner,Incomplete higher,Widow,Retired,House / apartment,144,0,0,0
-1,1,0,3,6,31900.000000000004,39,Salaried,Secondary,Divorced,Teacher,House / apartment,60,1,10,1
-0,1,1,0,1,22000.0,31,Salaried,Higher education,Single,Nurse,Rented apartment,48,1,7,1
-1,0,1,2,4,28050.000000000004,42,Self-employed,Higher education,Married,Business Owner,House / apartment,60,1,14,1
-0,1,0,1,3,18700.0,47,Salaried,Secondary,Married,Factory Worker,With parents,72,1,9,0
-0,0,1,0,1,46750.00000000001,25,Self-employed,Higher education,Single,Entrepreneur,Rented apartment,12,1,2,1
-1,1,0,3,5,16500.0,55,Salaried,Secondary,Married,Teacher,House / apartment,240,1,30,1
-0,0,1,1,2,24750.000000000004,40,Salaried,Higher education,Divorced,Nurse,With parents,36,1,10,1
+1,1,0,3,6,31900.000000000004,39,Salaried,Secondary,Divorced,Teacher,House / apartment,60,1,3,1
+0,1,1,0,1,22000.0,31,Salaried,Higher education,Single,Nurse,Rented apartment,48,1,2,1
+1,0,1,2,4,28050.000000000004,42,Self-employed,Higher education,Married,Business Owner,House / apartment,60,1,4,1
+0,1,0,1,3,18700.0,47,Salaried,Secondary,Married,Factory Worker,With parents,72,1,3,0
+0,0,1,0,1,46750.00000000001,25,Self-employed,Higher education,Single,Entrepreneur,Rented apartment,12,1,0,1
+1,1,0,3,5,16500.0,55,Salaried,Secondary,Married,Teacher,House / apartment,240,1,5,1
+0,0,1,1,2,24750.000000000004,40,Salaried,Higher education,Divorced,Nurse,With parents,36,1,3,1
 1,0,1,0,1,11000.0,50,Pensioner,Lower secondary,Widow,Retired,Rented apartment,60,0,0,0
-0,1,0,2,4,19250.0,30,Salaried,Higher education,Married,Office Worker,House / apartment,24,1,5,1
-1,0,1,1,3,33000.0,33,Self-employed,Secondary,Single,Entrepreneur,Rented apartment,48,1,7,0
-0,0,0,0,1,41250.0,28,Salaried,Higher education,Single,Manager,With parents,12,1,3,1
-1,1,1,3,6,22000.0,45,Salaried,Incomplete higher,Married,Salesperson,House / apartment,96,1,15,1
-1,0,1,0,1,16500.0,65,Pensioner,Higher education,Widow,Retired,House / apartment,420,0,40,1
-0,1,0,1,2,12100.000000000002,26,Salaried,Secondary,Single,Office Worker,With parents,24,1,2,0
-1,0,1,2,4,9900.0,35,Salaried,Lower secondary,Married,Factory Worker,House / apartment,60,1,10,1
-0,0,1,0,1,27500.000000000004,55,Self-employed,Higher education,Divorced,Consultant,Rented apartment,180,1,30,1
-1,1,0,3,5,13750.000000000002,40,Salaried,Incomplete higher,Married,Cooking Staff,House / apartment,120,1,15,0
-0,1,1,1,2,19250.0,28,Self-employed,Secondary,Single,Designer,Rented apartment,36,1,5,1
-1,0,0,0,1,24750.000000000004,30,Salaried,Higher education,Married,Engineer,With parents,48,1,8,1
-0,1,1,2,3,14850.000000000002,48,Salaried,Secondary,Divorced,Salesperson,House / apartment,240,1,20,0
-1,0,1,2,4,22000.0,45,Self-employed,Secondary,Married,Artist,House / apartment,120,1,15,1
-0,1,0,0,1,30250.000000000004,50,Salaried,Higher education,Widow,Scientist,Rented apartment,300,0,25,1
-1,0,1,1,2,14300.000000000002,27,Salaried,Incomplete higher,Single,Accountant,With parents,36,1,3,0
-0,0,0,3,6,12100.000000000002,38,Salaried,Lower secondary,Divorced,Bus Driver,House / apartment,72,1,10,1
-1,1,0,0,1,17600.0,55,Pensioner,Higher education,Married,Retired,House / apartment,420,0,30,0
-0,1,1,2,3,15950.000000000002,33,Self-employed,Secondary,Married,Business Owner,Rented apartment,60,1,7,1
-1,0,1,1,2,37400.0,29,Salaried,Higher education,Single,Software Developer,With parents,48,1,6,1
-0,0,0,0,1,19800.0,42,Self-employed,Incomplete higher,Divorced,Entrepreneur,House / apartment,96,1,12,0
+0,1,0,2,4,19250.0,30,Salaried,Higher education,Married,Office Worker,House / apartment,24,1,1,1
+1,0,1,1,3,33000.0,33,Self-employed,Secondary,Single,Entrepreneur,Rented apartment,48,1,2,0
+0,0,0,0,1,41250.0,28,Salaried,Higher education,Single,Manager,With parents,12,1,1,1
+1,1,1,3,6,22000.0,45,Salaried,Incomplete higher,Married,Salesperson,House / apartment,96,1,4,1
+1,0,1,0,1,16500.0,65,Pensioner,Higher education,Widow,Retired,House / apartment,420,0,5,1
+0,1,0,1,2,12100.000000000002,26,Salaried,Secondary,Single,Office Worker,With parents,24,1,0,0
+1,0,1,2,4,9900.0,35,Salaried,Lower secondary,Married,Factory Worker,House / apartment,60,1,3,1
+0,0,1,0,1,27500.000000000004,55,Self-employed,Higher education,Divorced,Consultant,Rented apartment,180,1,5,1
+1,1,0,3,5,13750.000000000002,40,Salaried,Incomplete higher,Married,Cooking Staff,House / apartment,120,1,4,0
+0,1,1,1,2,19250.0,28,Self-employed,Secondary,Single,Designer,Rented apartment,36,1,1,1
+1,0,0,0,1,24750.000000000004,30,Salaried,Higher education,Married,Engineer,With parents,48,1,2,1
+0,1,1,2,3,14850.000000000002,48,Salaried,Secondary,Divorced,Salesperson,House / apartment,240,1,5,0
+1,0,1,2,4,22000.0,45,Self-employed,Secondary,Married,Artist,House / apartment,120,1,4,1
+0,1,0,0,1,30250.000000000004,50,Salaried,Higher education,Widow,Scientist,Rented apartment,300,0,5,1
+1,0,1,1,2,14300.000000000002,27,Salaried,Incomplete higher,Single,Accountant,With parents,36,1,1,0
+0,0,0,3,6,12100.000000000002,38,Salaried,Lower secondary,Divorced,Bus Driver,House / apartment,72,1,3,1
+1,1,0,0,1,17600.0,55,Pensioner,Higher education,Married,Retired,House / apartment,420,0,5,0
+0,1,1,2,3,15950.000000000002,33,Self-employed,Secondary,Married,Business Owner,Rented apartment,60,1,2,1
+1,0,1,1,2,37400.0,29,Salaried,Higher education,Single,Software Developer,With parents,48,1,2,1
+0,0,0,0,1,19800.0,42,Self-employed,Incomplete higher,Divorced,Entrepreneur,House / apartment,96,1,4,0

data/gpt_data.csv

@@ -1,57 +0,0 @@
-ID,Car,Property,Work phone,Phone,Email,Number of children,Household size,Income,Age,Income type,Education,Family,Occupation,Housing,Account age (months),Employed,Years of employment,Credit card Approval
-0,Yes,Yes,No,Yes,Yes,2,4,50000,35,Salaried,Higher education,Married,Engineer,House / apartment,36,Yes,5,Yes
-1,No,No,Yes,Yes,No,0,1,20000,50,Pensioner,Secondary,Widow,Retired,Rented apartment,12,No,0,No
-2,Yes,Yes,No,No,Yes,1,3,75000,40,Self-employed,Higher education,Civil marriage,Business Owner,House / apartment,48,Yes,10,Yes
-3,No,Yes,Yes,No,No,1,2,30000,28,Salaried,Secondary,Single,Teacher,With parents,24,Yes,3,Yes
-4,Yes,No,No,Yes,Yes,0,1,45000,32,Self-employed,Higher education,Divorced,Freelancer,Rented apartment,60,Yes,7,Yes
-5,No,Yes,Yes,Yes,No,3,5,35000,45,Salaried,Incomplete higher,Married,Clerk,House / apartment,30,Yes,10,Yes
-6,Yes,No,No,No,Yes,0,1,25000,55,Pensioner,Lower secondary,Widow,Retired,House / apartment,120,No,0,No
-7,No,Yes,Yes,Yes,Yes,2,3,60000,37,Salaried,Higher education,Civil marriage,Manager,House / apartment,36,Yes,12,Yes
-8,Yes,Yes,Yes,Yes,Yes,0,1,80000,29,Self-employed,Higher education,Single,Entrepreneur,House / apartment,48,Yes,6,Yes
-9,No,Yes,No,Yes,No,4,6,40000,38,Salaried,Secondary,Married,Salesperson,With parents,60,Yes,15,Yes
-10,Yes,No,Yes,No,Yes,1,2,55000,26,Self-employed,Higher education,Civil marriage,Designer,Rented apartment,12,Yes,3,Yes
-11,No,No,No,No,No,0,1,30000,60,Pensioner,Lower secondary,Widow,Retired,House / apartment,180,No,0,No
-12,Yes,Yes,Yes,Yes,Yes,2,4,70000,45,Salaried,Higher education,Married,Manager,House / apartment,72,Yes,20,Yes
-13,No,Yes,Yes,Yes,Yes,3,5,65000,50,Salaried,Incomplete higher,Divorced,Teacher,House / apartment,96,Yes,25,Yes
-14,Yes,No,Yes,Yes,No,0,1,85000,33,Self-employed,Higher education,Single,Consultant,Rented apartment,36,Yes,10,Yes
-15,No,Yes,No,No,Yes,1,3,32000,55,Pensioner,Secondary,Widow,Retired,House / apartment,150,No,0,No
-16,Yes,Yes,Yes,Yes,Yes,2,4,90000,41,Salaried,Higher education,Married,Doctor,House / apartment,60,Yes,15,Yes
-17,No,No,No,Yes,Yes,0,1,23000,24,Student,Incomplete higher,Single,Student,With parents,6,No,0,No
-18,Yes,No,Yes,No,Yes,1,3,48000,35,Self-employed,Secondary,Divorced,Chef,Rented apartment,24,Yes,5,Yes
-19,No,Yes,No,Yes,No,3,5,55000,50,Salaried,Higher education,Widow,Engineer,House / apartment,120,Yes,20,Yes
-20,Yes,No,Yes,Yes,Yes,0,2,70000,30,Salaried,Higher education,Civil marriage,Lawyer,Rented apartment,36,Yes,8,Yes
-21,No,Yes,Yes,No,Yes,2,4,32000,40,Self-employed,Secondary,Married,Carpenter,House / apartment,48,Yes,12,Yes
-22,Yes,No,No,Yes,No,1,2,26000,29,Student,Higher education,Single,Student,With parents,12,No,0,No
-23,No,Yes,Yes,Yes,Yes,0,1,45000,55,Pensioner,Lower secondary,Divorced,Retired,House / apartment,180,No,0,No
-24,Yes,Yes,No,Yes,Yes,1,3,80000,46,Salaried,Higher education,Married,Architect,House / apartment,72,Yes,18,Yes
-25,No,No,Yes,No,No,2,5,37000,33,Self-employed,Secondary,Single,Plumber,With parents,24,Yes,6,Yes
-26,Yes,Yes,Yes,Yes,No,0,1,65000,28,Self-employed,Higher education,Single,Graphic Designer,Rented apartment,36,Yes,4,Yes
-27,No,No,No,No,Yes,1,2,29000,53,Pensioner,Incomplete higher,Widow,Retired,House / apartment,144,No,0,No
-28,Yes,Yes,Yes,No,Yes,3,6,58000,39,Salaried,Secondary,Divorced,Teacher,House / apartment,60,Yes,10,Yes
-29,No,Yes,No,Yes,No,0,1,40000,31,Salaried,Higher education,Single,Nurse,Rented apartment,48,Yes,7,Yes
-30,Yes,No,Yes,Yes,Yes,2,4,51000,42,Self-employed,Higher education,Civil marriage,Business Owner,House / apartment,60,Yes,14,Yes
-31,No,Yes,No,No,No,1,3,34000,47,Salaried,Secondary,Married,Factory Worker,With parents,72,Yes,9,No
-32,No,No,Yes,Yes,Yes,0,1,85000,25,Self-employed,Higher education,Single,Entrepreneur,Rented apartment,12,Yes,2,Yes
-33,Yes,Yes,No,No,No,3,5,30000,55,Salaried,Secondary,Married,Teacher,House / apartment,240,Yes,30,Yes
-34,No,No,Yes,Yes,Yes,1,2,45000,40,Salaried,Higher education,Divorced,Nurse,With parents,36,Yes,10,Yes
-35,Yes,No,No,Yes,No,0,1,20000,50,Pensioner,Lower secondary,Widow,Retired,Rented apartment,60,No,0,No
-36,No,Yes,Yes,No,Yes,2,4,35000,30,Salaried,Higher education,Civil marriage,Clerk,House / apartment,24,Yes,5,Yes
-37,Yes,No,Yes,Yes,No,1,3,60000,33,Self-employed,Secondary,Single,Freelancer,Rented apartment,48,Yes,7,No
-38,No,No,No,No,Yes,0,1,75000,28,Salaried,Higher education,Single,Manager,With parents,12,Yes,3,Yes
-39,Yes,Yes,Yes,Yes,No,3,6,40000,45,Salaried,Incomplete higher,Married,Salesperson,House / apartment,96,Yes,15,Yes
-40,Yes,No,Yes,Yes,Yes,0,1,30000,65,Pensioner,Higher education,Widow,Retired,House / apartment,420,No,40,Yes
-41,No,Yes,No,No,No,1,2,22000,26,Salaried,Secondary,Single,Junior Clerk,With parents,24,Yes,2,No
-42,Yes,No,Yes,Yes,No,2,4,18000,35,Salaried,Lower secondary,Married,Factory Worker,House / apartment,60,Yes,10,Yes
-43,No,No,No,Yes,Yes,0,1,50000,55,Self-employed,Higher education,Divorced,Consultant,Rented apartment,180,Yes,30,Yes
-44,Yes,Yes,Yes,No,No,3,5,25000,40,Salaried,Incomplete higher,Married,Cook,House / apartment,120,Yes,15,No
-45,No,Yes,No,Yes,Yes,1,2,35000,28,Self-employed,Secondary,Single,Graphic Designer,Rented apartment,36,Yes,5,Yes
-46,Yes,No,Yes,No,Yes,0,1,45000,30,Salaried,Higher education,Civil marriage,Engineer,With parents,48,Yes,8,Yes
-47,No,Yes,Yes,Yes,No,2,3,27000,48,Salaried,Secondary,Divorced,Salesperson,House / apartment,240,Yes,20,No
-48,Yes,No,Yes,Yes,No,2,4,40000,45,Self-employed,Secondary,Married,Artist,House / apartment,120,Yes,15,Yes
-49,No,Yes,No,No,Yes,0,1,55000,50,Salaried,Higher education,Widow,Scientist,Rented apartment,300,No,25,Yes
-50,Yes,No,Yes,Yes,Yes,1,2,26000,27,Salaried,Incomplete higher,Single,Junior Accountant,With parents,36,Yes,3,No
-51,No,No,No,No,No,3,6,22000,38,Salaried,Lower secondary,Divorced,Bus Driver,House / apartment,72,Yes,10,Yes
-52,Yes,Yes,Yes,No,Yes,0,1,32000,55,Pensioner,Higher education,Married,Retired,House / apartment,420,No,30,No
-53,No,Yes,No,Yes,No,2,3,29000,33,Self-employed,Secondary,Civil marriage,Shop Owner,Rented apartment,60,Yes,7,Yes
-54,Yes,No,Yes,Yes,Yes,1,2,68000,29,Salaried,Higher education,Single,Software Developer,With parents,48,Yes,6,Yes
-55,No,No,No,No,Yes,0,1,36000,42,Self-employed,Incomplete higher,Divorced,Freelancer,House / apartment,96,Yes,12,No

deployment_files/explain_model/versions.json

@@ -1 +0,0 @@
-{"concrete-python": "2.5.0rc1", "concrete-ml": "1.3.0", "python": "3.10.11"}

deployment_files/{approval_model → model}/client.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2ceb4a6e07cd13471c8c8c963d9e4de52d5af624e81775ebeb2421e29b9ba8c
-size 28667
+oid sha256:09a8c2ae9e2e2e18a7e48123222312e3de32ef3b751bf88e8e090739f92c12f3
+size 28549

deployment_files/{approval_model/server.zip → model/pre_processor_bank.pkl}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e724012427c90fdc8df14360942909e5fa0accc8b27584880baab2a91533e78
-size 1729
+oid sha256:c76179d6cb576a61f6d57e29f45545d8c4dd2d86a3818730f5c6bdd35faebe4a
+size 1098

deployment_files/{explain_model/client.zip → model/pre_processor_third_party.pkl}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:506276661b4612d664d59f0d90aac1b5c09f942a850ec189aa16204d54433b27
-size 27714
+oid sha256:3a8d320eea9a0b2d28b9ee46b5b02df1dc85176746385d64e4c742edc99339f4
+size 647

deployment_files/model/pre_processor_user.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4300414ee222355b2ac9e0f5e4dc21b50f0a4de8e17e0ed4121dc766231d010
+size 3340

deployment_files/{explain_model → model}/server.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:596ae66c7effd9733a8780088984d4fc08479d67c11586ee5787111329cb353f
-size 2035
+oid sha256:87df3659c986799920676e358c316fc99f8c65951b71ccb9288c94af90c8a57b
+size 1775

deployment_files/pre_processor_third_party.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bc9d12a6ac40e3b7f88f3f15e688879b819bc4a995ad0e91fc08af85f55513b
-size 1128
+oid sha256:a4ac1351641df7d247a18c15405b22926584c88aa9640857cb1943a2bb7ee32e
+size 1098

development.py

@@ -6,46 +6,34 @@ import pandas
 import pickle
 
 from settings import (
-    APPROVAL_DEPLOYMENT_PATH,
-    EXPLAIN_DEPLOYMENT_PATH,
+    DEPLOYMENT_PATH,
     DATA_PATH, 
-    APPROVAL_INPUT_SLICES, 
-    EXPLAIN_INPUT_SLICES,
+    INPUT_SLICES, 
     PRE_PROCESSOR_USER_PATH, 
     PRE_PROCESSOR_BANK_PATH,
     PRE_PROCESSOR_THIRD_PARTY_PATH,
     USER_COLUMNS,
     BANK_COLUMNS,
-    APPROVAL_THIRD_PARTY_COLUMNS,
-    EXPLAIN_THIRD_PARTY_COLUMNS,
+    THIRD_PARTY_COLUMNS,
 )
 from utils.client_server_interface import MultiInputsFHEModelDev
 from utils.model import MultiInputDecisionTreeClassifier, MultiInputDecisionTreeRegressor
 from utils.pre_processing import get_pre_processors
 
 
-def get_multi_inputs(data, is_approval):
+def get_multi_inputs(data):
     """Get inputs for all three parties from the input data, using fixed slices.
     
     Args:
         data (numpy.ndarray): The input data to consider.
-        is_approval (bool): If the data should be used for the 'approval' model (else, otherwise for 
-            the 'explain' model).
     
     Returns:
         (Tuple[numpy.ndarray]): The inputs for all three parties.
     """
-    if is_approval:
-        return (
-            data[:, APPROVAL_INPUT_SLICES["user"]], 
-            data[:, APPROVAL_INPUT_SLICES["bank"]], 
-            data[:, APPROVAL_INPUT_SLICES["third_party"]]
-        )
-    
     return (
-        data[:, EXPLAIN_INPUT_SLICES["user"]], 
-        data[:, EXPLAIN_INPUT_SLICES["bank"]], 
-        data[:, EXPLAIN_INPUT_SLICES["third_party"]]
+        data[:, INPUT_SLICES["user"]], 
+        data[:, INPUT_SLICES["bank"]], 
+        data[:, INPUT_SLICES["third_party"]]
     )
 
 
@@ -61,7 +49,7 @@ data_y = data_x.pop("Target").copy().to_frame()
 # Get data from all parties
 data_user = data_x[USER_COLUMNS].copy()
 data_bank = data_x[BANK_COLUMNS].copy()
-data_third_party = data_x[APPROVAL_THIRD_PARTY_COLUMNS].copy()
+data_third_party = data_x[THIRD_PARTY_COLUMNS].copy()
 
 # Feature engineer the data
 pre_processor_user, pre_processor_bank, pre_processor_third_party = get_pre_processors()
@@ -75,23 +63,23 @@ preprocessed_data_x = numpy.concatenate((preprocessed_data_user, preprocessed_da
 
 print("\nTrain and compile the model")
 
-model_approval = MultiInputDecisionTreeClassifier()
+model = MultiInputDecisionTreeClassifier()
 
-model_approval, sklearn_model_approval = model_approval.fit_benchmark(preprocessed_data_x, data_y)
+model, sklearn_model = model.fit_benchmark(preprocessed_data_x, data_y)
  
-multi_inputs_train = get_multi_inputs(preprocessed_data_x, is_approval=True)
+multi_inputs_train = get_multi_inputs(preprocessed_data_x)
 
-model_approval.compile(*multi_inputs_train, inputs_encryption_status=["encrypted", "encrypted", "encrypted"])
+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 APPROVAL_DEPLOYMENT_PATH.is_dir():
-    shutil.rmtree(APPROVAL_DEPLOYMENT_PATH)
+if DEPLOYMENT_PATH.is_dir():
+    shutil.rmtree(DEPLOYMENT_PATH)
 
 # Save files needed for deployment (and enable cross-platform deployment)
-fhe_model_dev_approval = MultiInputsFHEModelDev(APPROVAL_DEPLOYMENT_PATH, model_approval)
-fhe_model_dev_approval.save(via_mlir=True)
+fhe_model_dev = MultiInputsFHEModelDev(DEPLOYMENT_PATH, model)
+fhe_model_dev.save(via_mlir=True)
 
 # Save pre-processors
 with (
@@ -103,44 +91,4 @@ with (
     pickle.dump(pre_processor_bank, file_bank)
     pickle.dump(pre_processor_third_party, file_third_party)
 
-
-print("\nLoad, train, compile and save files for the 'explain' model")
-
-# Define input and target data
-data_x = data.copy()
-data_y = data_x.pop("Years_employed").copy().to_frame()
-target_values = data_x.pop("Target").copy()
-
-# Get all data points whose target value is True (credit card has been approved)
-approved_mask = target_values == 1
-data_x_approved = data_x[approved_mask]
-data_y_approved = data_y[approved_mask]
-
-# Get data from all parties
-data_user = data_x_approved[USER_COLUMNS].copy()
-data_bank = data_x_approved[BANK_COLUMNS].copy()
-data_third_party = data_x_approved[EXPLAIN_THIRD_PARTY_COLUMNS].copy()
-
-preprocessed_data_user = pre_processor_user.transform(data_user)
-preprocessed_data_bank = pre_processor_bank.transform(data_bank)
-preprocessed_data_third_party = data_third_party.to_numpy() 
-
-preprocessed_data_x = numpy.concatenate((preprocessed_data_user, preprocessed_data_bank, preprocessed_data_third_party), axis=1)
-
-model_explain = MultiInputDecisionTreeRegressor()
-
-model_explain, sklearn_model_explain = model_explain.fit_benchmark(preprocessed_data_x, data_y_approved)
-
-multi_inputs_train = get_multi_inputs(preprocessed_data_x, is_approval=False)
-
-model_explain.compile(*multi_inputs_train, inputs_encryption_status=["encrypted", "encrypted", "encrypted"])
-
-# Delete the deployment folder and its content if it already exists
-if EXPLAIN_DEPLOYMENT_PATH.is_dir():
-    shutil.rmtree(EXPLAIN_DEPLOYMENT_PATH)
-
-# Save files needed for deployment (and enable cross-platform deployment)
-fhe_model_dev_explain = MultiInputsFHEModelDev(EXPLAIN_DEPLOYMENT_PATH, model_explain)
-fhe_model_dev_explain.save(via_mlir=True)
-
 print("\nDone !")

server.py

@@ -5,11 +5,11 @@ from typing import List, Optional
 from fastapi import FastAPI, File, Form, UploadFile
 from fastapi.responses import JSONResponse, Response
 
-from settings import APPROVAL_DEPLOYMENT_PATH, SERVER_FILES, CLIENT_TYPES
+from settings import DEPLOYMENT_PATH, SERVER_FILES, CLIENT_TYPES
 from utils.client_server_interface import MultiInputsFHEModelServer
 
 # Load the server
-FHE_SERVER = MultiInputsFHEModelServer(APPROVAL_DEPLOYMENT_PATH)
+FHE_SERVER = MultiInputsFHEModelServer(DEPLOYMENT_PATH)
 
 
 def _get_server_file_path(name, client_id, client_type=None):

settings.py

@@ -13,8 +13,7 @@ CLIENT_FILES = REPO_DIR / "client_files"
 SERVER_FILES = REPO_DIR / "server_files"
 
 # ALl deployment directories
-APPROVAL_DEPLOYMENT_PATH = DEPLOYMENT_PATH / "approval_model"
-EXPLAIN_DEPLOYMENT_PATH = DEPLOYMENT_PATH / "explain_model"
+DEPLOYMENT_PATH = DEPLOYMENT_PATH / "model"
 
 # Path targeting pre-processor saved files
 PRE_PROCESSOR_USER_PATH = DEPLOYMENT_PATH / 'pre_processor_user.pkl'
@@ -33,8 +32,7 @@ SERVER_URL = "http://localhost:8000/"
 DATA_PATH = "data/data.csv"
 
 # Development settings
-APPROVAL_PROCESSED_INPUT_SHAPE = (1, 39)
-EXPLAIN_PROCESSED_INPUT_SHAPE = (1, 38)
+PROCESSED_INPUT_SHAPE = (1, 39)
 
 CLIENT_TYPES = ["user", "bank", "third_party"]
 INPUT_INDEXES = {
@@ -42,16 +40,11 @@ INPUT_INDEXES = {
     "bank": 1,
     "third_party": 2,
 }
-APPROVAL_INPUT_SLICES = {
+INPUT_SLICES = {
     "user": slice(0, 36),  # First position: start from 0
     "bank": slice(36, 37),  # Second position: start from n_feature_user
     "third_party": slice(37, 39),  # Third position: start from n_feature_user + n_feature_bank
 }
-EXPLAIN_INPUT_SLICES = {
-    "user": slice(0, 36),  # First position: start from 0
-    "bank": slice(36, 37),  # Second position: start from n_feature_user
-    "third_party": slice(37, 38),  # Third position: start from n_feature_user + n_feature_bank
-}
 
 # Fix column order for pre-processing steps
 USER_COLUMNS = [
@@ -60,8 +53,7 @@ USER_COLUMNS = [
     'Occupation_type',
 ]
 BANK_COLUMNS = ["Account_age"]
-APPROVAL_THIRD_PARTY_COLUMNS = ["Years_employed", "Employed"]
-EXPLAIN_THIRD_PARTY_COLUMNS = ["Employed"]
+THIRD_PARTY_COLUMNS = ["Years_employed", "Employed"]
 
 _data = pandas.read_csv(DATA_PATH, encoding="utf-8")
 
@@ -77,13 +69,23 @@ ACCOUNT_MIN_MAX = get_min_max(_data, "Account_age")
 CHILDREN_MIN_MAX = get_min_max(_data, "Num_children")
 INCOME_MIN_MAX = get_min_max(_data, "Total_income")
 AGE_MIN_MAX = get_min_max(_data, "Age")
-EMPLOYED_MIN_MAX = get_min_max(_data, "Years_employed")
 FAMILY_MIN_MAX = get_min_max(_data, "Household_size")
 
+# Default values
+INCOME_VALUE = 12000
+AGE_VALUE = 30
+
 # App data choices 
 INCOME_TYPES = list(_data["Income_type"].unique())
 OCCUPATION_TYPES = list(_data["Occupation_type"].unique())
 HOUSING_TYPES = list(_data["Housing_type"].unique())
 EDUCATION_TYPES = list(_data["Education_type"].unique())
 FAMILY_STATUS = list(_data["Family_status"].unique())
+YEARS_EMPLOYED_BINS = ['0-2', '2-5', '5-8', '8-11', '11-18', '18+']
+
+# Years_employed bin order 
+YEARS_EMPLOYED_BIN_NAME_TO_INDEX = {bin_name: i for i, bin_name in enumerate(YEARS_EMPLOYED_BINS)}
 
+assert len(YEARS_EMPLOYED_BINS) == len(list(_data["Years_employed"].unique())), (
+    "Years_employed bins are not matching the expected list"
+)

utils/pre_processing.py

@@ -56,9 +56,7 @@ def get_pre_processors():
     )
 
     pre_processor_third_party = ColumnTransformer(
-        transformers=[
-            ('standard_scaler', StandardScaler(), ['Years_employed']),
-        ],
+        transformers=[],
         remainder='passthrough',
         verbose_feature_names_out=False,
     )