development.py

"""Train and compile the model."""

import shutil
import numpy
import pandas
import pickle

from settings import (
    DEPLOYMENT_PATH,
    DATA_PATH, 
    INPUT_SLICES, 
    PRE_PROCESSOR_USER_PATH, 
    PRE_PROCESSOR_BANK_PATH,
    PRE_PROCESSOR_THIRD_PARTY_PATH,
    USER_COLUMNS,
    BANK_COLUMNS,
    THIRD_PARTY_COLUMNS,
)
from utils.client_server_interface import MultiInputsFHEModelDev
from utils.model import MultiInputDecisionTreeClassifier
from utils.pre_processing import get_pre_processors


def get_processed_multi_inputs(data):
    return (
        data[:, INPUT_SLICES["user"]], 
        data[:, INPUT_SLICES["bank"]], 
        data[:, INPUT_SLICES["third_party"]]
    )

print("Load and pre-process the data")

# Load the data
data = pandas.read_csv(DATA_PATH, encoding="utf-8")

# Define input and target data
data_x = data.copy()
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[THIRD_PARTY_COLUMNS].copy()

# Feature engineer the data
pre_processor_user, pre_processor_bank, pre_processor_third_party = get_pre_processors()

preprocessed_data_user = pre_processor_user.fit_transform(data_user)
preprocessed_data_bank = pre_processor_bank.fit_transform(data_bank)
preprocessed_data_third_party = pre_processor_third_party.fit_transform(data_third_party)

preprocessed_data_x = numpy.concatenate((preprocessed_data_user, preprocessed_data_bank, preprocessed_data_third_party), axis=1)


print("\nTrain and compile the model")

model = MultiInputDecisionTreeClassifier()

model, sklearn_model = model.fit_benchmark(preprocessed_data_x, data_y)
 
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)

# Save files needed for deployment (and enable cross-platform deployment)
fhe_dev = MultiInputsFHEModelDev(DEPLOYMENT_PATH, model)
fhe_dev.save(via_mlir=True)

# Save pre-processors
with (
    PRE_PROCESSOR_USER_PATH.open('wb') as file_user, 
    PRE_PROCESSOR_BANK_PATH.open('wb') as file_bank,
    PRE_PROCESSOR_THIRD_PARTY_PATH.open('wb') as file_third_party,
):
    pickle.dump(pre_processor_user, file_user)
    pickle.dump(pre_processor_bank, file_bank)
    pickle.dump(pre_processor_third_party, file_third_party)

print("\nDone !")