MEDfl 0.1.0__py3-none-any.whl

Medfl-0.1.0.data/scripts/setup_mysql.sh

@@ -0,0 +1,22 @@
+echo '#!/bin/bash
+
+# Update package lists
+sudo apt update
+
+# Install MySQL
+sudo apt install mysql-server
+
+# Secure MySQL installation
+sudo mysql_secure_installation
+
+# Install phpMyAdmin
+sudo apt install phpmyadmin
+
+# Create symbolic link for Apache
+sudo ln -s /etc/phpmyadmin/apache.conf /etc/apache2/conf-available/phpmyadmin.conf
+sudo a2enconf phpmyadmin
+sudo systemctl reload apache2
+
+# Print completion message
+echo "MySQL and phpMyAdmin setup complete."
+' > setup_mysql.sh && chmod +x setup_mysql.sh && python3 scripts/create_db.py

Medfl-0.1.0.dist-info/METADATA

@@ -0,0 +1,125 @@
+Metadata-Version: 2.1
+Name: Medfl
+Version: 0.1.0
+Summary: Python Open-source package for simulating federated learning and differential privacy
+Home-page: https://github.com/HaithemLamri/MEDfl
+Author: MEDomics consortium
+Author-email: medomics.info@gmail.com
+Project-URL: Documentation, https://
+Project-URL: Github, https://github.com/HaithemLamri/MEDfl
+Keywords: federated learning differential privacy medical research
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Requires-Python: >=3.8,<3.10
+Description-Content-Type: text/markdown
+Requires-Dist: flwr (~=1.7.0)
+Requires-Dist: matplotlib (~=3.6.3)
+Requires-Dist: numpy (~=1.24.2)
+Requires-Dist: opacus (~=1.3.0)
+Requires-Dist: pandas (~=1.5.2)
+Requires-Dist: PyYAML (~=6.0)
+Requires-Dist: setuptools (~=68.0.0)
+Requires-Dist: Sphinx (~=5.3.0)
+Requires-Dist: SQLAlchemy (~=1.4.47)
+Requires-Dist: torch (~=1.13.1)
+Requires-Dist: datetime (~=5.1)
+Requires-Dist: scikit-learn (~=1.1.1)
+Requires-Dist: sphinx-jsonschema (==1.19.1)
+Requires-Dist: sphinx-rtd-dark-mode (==1.2.4)
+Requires-Dist: plotly (==5.19.0)
+Requires-Dist: optuna (==3.5.0)
+
+# MEDfl : Federated Learning and Differential Privacy Simulation Tool for Tabular Data
+![Python Versions](https://img.shields.io/badge/python-3.9-blue)
+![Build Status](https://travis-ci.org/MEDomics-UdeS/MEDfl.svg?branch=main)
+
+![GitHub contributors](https://img.shields.io/github/contributors/scottydocs/README-template.md)
+![License: MIT](https://img.shields.io/badge/license-MIT-green)
+
+
+
+
+## Table of Contents
+  * [1. Introduction](#1-introduction)
+  * [2. Installation](#2-installation)
+  * [3. Documentation](#3-documentation)
+  * [4. Getting started](#4-Getting-started)
+  * [5. Acknowledgement](#5-acknowledgement)
+  * [6. Authors](#6-authors)
+  * [7. Statement](#7-statement)
+
+## 1. Introduction
+This Python package is an open-source tool designed for simulating federated learning and incorporating differential privacy. It empowers researchers and developers to effortlessly create, execute, and assess federated learning pipelines while seamlessly working with various tabular datasets.
+
+
+
+
+
+## 2. Installation
+
+### Python installation
+The MEDfl package requires *python 3.9* or more to be run. If you don't have it installed  on your machine, check out the following link  [Python ](https://www.python.org/downloads/).
+It also requires MySQL database
+
+### Package installation
+For now, you can  install the ``MEDfl``package as:
+```
+git clone https://github.com/MEDomics-UdeS/MEDfl.git
+cd MEDfl
+pip install -e .
+```
+### MySQL DB configuration
+MEDfl requires a MySQL DB connection, and this is in order to allow users to work with their own tabular datasets,  we have created a bash script to install and configure A MySQL DB with phpmyadmin monitoring system, run the following command then change your credential on the MEDfl/scripts/base.py and MEDfl/scripts/config.ini files
+```
+sudo bash MEDfl/scripts/setup_mysql.sh
+```
+
+### Project Base URL Update
+Please ensure to modify the `base_url` parameter in the `MEDfl/global_params.yaml` file. The `base_url` represents the path to the MEDfl project on your local machine. Update this value accordingly.
+
+## 3. Documentation
+We used sphinx to create the documentation for this project.  you can generate and host it locally by compiling the documentation source code using:
+```
+cd docs
+make clean
+make html
+```
+
+Then open it locally using:
+
+```
+cd _build/html
+python -m http.server
+```
+
+## 4. Getting started
+
+We have created a complete tutorial for the different functionalities of the package. it can be found here [tutorial](https://github.com/MEDomics-UdeS/MEDfl/notebooks/First_tuto.ipynb)
+
+
+
+## 5. Acknowledgment
+MEDfl is an open-source package that welcomes any contribution and feedback. We wish that this package could serve the growing private AI research community.
+
+## 6. Authors
+* [MEDomics](https://github.com/medomics/): MEDomics consortium.
+
+## 7. Statement
+
+This package is part of https://github.com/medomics, a package providing research utility tools for developing precision medicine applications.
+
+```
+MIT License
+
+Copyright (C) 2022 MEDomics consortium
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+```

Medfl-0.1.0.dist-info/RECORD

@@ -0,0 +1,10 @@
+Medfl-0.1.0.data/scripts/setup_mysql.sh,sha256=r4ygRl7zdasUSZT-ccC1Tjtt6GKDS5Puza9hCec2Cns,538
+alembic/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+alembic/env.py,sha256=-aSZ6SlJeK1ZeqHgM-54hOi9LhJRFP0SZGjut-JnY-4,1588
+scripts/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+scripts/base.py,sha256=xyiLkJ46nVrs3rNHP39LIH_03bmn5FU_gqpSTGJ_nVE,923
+scripts/create_db.py,sha256=NYysjkiMWNjEawpOJL8iLAwNGUk4YITUMudiJgLQIGA,3364
+Medfl-0.1.0.dist-info/METADATA,sha256=71x4zhRdj7KsRqK8hFiQCAl41NHL1F_P8o3n3Y5TqXw,5422
+Medfl-0.1.0.dist-info/WHEEL,sha256=g4nMs7d-Xl9-xC9XovUrsDHGXt-FT0E17Yqo92DEfvY,92
+Medfl-0.1.0.dist-info/top_level.txt,sha256=mXk5utWsktWUZwSh3_kKF4Fv3MiV9-MtMMY8okENUBQ,16
+Medfl-0.1.0.dist-info/RECORD,,

Medfl-0.1.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: bdist_wheel (0.34.2)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

Medfl-0.1.0.dist-info/top_level.txt

@@ -0,0 +1,2 @@
+alembic
+scripts

alembic/env.py

@@ -0,0 +1,61 @@
+from logging.config import fileConfig
+import logging
+from sqlalchemy import engine_from_config, create_engine
+from sqlalchemy import pool
+import sys
+import os
+from alembic import context
+
+sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+from scripts.base import my_eng
+
+# this is the Alembic Config object, which provides
+# access to the values within the .ini file in use.
+config = context.config
+
+# Interpret the config file for Python logging.
+# This line sets up loggers basically.
+fileConfig(config.config_file_name)
+
+# add your model's MetaData object here
+# for 'autogenerate' support
+# from myapp import mymodel
+# target_metadata = mymodel.Base.metadata
+target_metadata = None
+
+# other values from the config, defined by the needs of env.py,
+# can be acquired:
+# my_important_option = config.get_main_option("my_important_option")
+# ... etc.
+def configure_logger(name):
+    # This is the standard logging configuration
+    logging.config.fileConfig(
+        'alembic_logging.ini',  # Path to your logging configuration file
+        defaults={
+            'logfilename': 'alembic.log',  # Log file name
+        },
+        disable_existing_loggers=False,
+    )
+
+    return logging.getLogger(name)
+
+
+
+def run_migrations_offline():
+    """Run migrations in 'offline' mode."""
+    pass
+
+def run_migrations_online():
+    """Run migrations in 'online' mode."""
+    pass
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

scripts/base.py

@@ -0,0 +1,33 @@
+import mysql.connector
+from sqlalchemy import create_engine, text
+from configparser import ConfigParser
+import yaml
+import pkg_resources
+import os
+
+# Load base_url from global_params.yaml
+parent_directory = os.path.abspath(os.path.join(pkg_resources.resource_filename(__name__, ''), '..'))
+global_params_path = os.path.join(parent_directory, 'global_params.yaml')
+
+with open(global_params_path, 'r') as file:
+    params = yaml.safe_load(file)
+    base_url = params['base_url']
+
+# Load configuration from the config file
+config = ConfigParser()
+config.read(base_url + '/scripts/config.ini')
+mysql_config = config['mysql']
+
+
+
+connection_string = (
+    f"mysql+mysqlconnector://{mysql_config['user']}:{mysql_config['password']}@"
+    f"{mysql_config['host']}:{mysql_config['port']}/{mysql_config['database']}"
+)
+
+eng = create_engine(
+    connection_string,
+    execution_options={"autocommit": True},
+)
+
+my_eng = eng.connect()

scripts/create_db.py

@@ -0,0 +1,113 @@
+import mysql.connector
+import pandas as pd
+from mysql.connector import Error
+from Medfl.LearningManager.utils import params
+
+try:
+    mydb = mysql.connector.connect(host="localhost", user="ouael", password="ouael")
+    mycursor = mydb.cursor()
+
+    # Create the 'MEDfl' database if it doesn't exist
+    mycursor.execute("CREATE DATABASE IF NOT EXISTS MEDfl")
+
+    # Select the 'MEDfl' database
+    mycursor.execute("USE MEDfl")
+
+    # Get the list of all tables in the database
+    mycursor.execute("SHOW TABLES")
+    tables = mycursor.fetchall()
+
+    
+
+
+    # Drop each table one by one
+    for table in tables:
+        table_name = table[0]
+        mycursor.execute(f"DROP TABLE IF EXISTS {table_name}")
+
+    # Create Networks table
+    mycursor.execute(
+        "CREATE TABLE Networks( \
+                     NetId INT NOT NULL AUTO_INCREMENT, \
+                     NetName VARCHAR(255), \
+                     PRIMARY KEY (NetId) \
+                     );"
+    )
+
+    # Create FLsetup table
+    mycursor.execute("CREATE TABLE FLsetup (\
+    FLsetupId int NOT NULL AUTO_INCREMENT,\
+    name varchar(255)  NOT NULL, \
+    description varchar(255) CHARACTER SET utf8mb4 COLLATE utf8mb4_0900_ai_ci NOT NULL,\
+    creation_date datetime NOT NULL,\
+    NetId int NOT NULL,\
+    column_name varchar(255) DEFAULT NULL,\
+    PRIMARY KEY (`FLsetupId`) \
+    )")
+
+    # Create Nodes table
+    mycursor.execute("CREATE TABLE Nodes ( \
+     NodeId int NOT NULL AUTO_INCREMENT,\
+     NodeName varchar(255) DEFAULT NULL,\
+     train tinyint(1) DEFAULT '1',\
+     NetId int DEFAULT NULL,\
+     PRIMARY KEY (NodeId)\
+    )")
+
+    data_df = pd.read_csv(params['path_to_master_csv'])
+    columns = data_df.columns.tolist()
+    column_map = {"object": "VARCHAR(255)", "int64": "INT", "float64": "FLOAT"}
+    sub_query = "".join(f"{col} {column_map[str(data_df[col].dtype)]}," for col in columns)
+
+    # Create Datasets table by getting columns from the master csv file
+    mycursor.execute(
+        f"CREATE TABLE DataSets( \
+                     DataSetId INT NOT NULL AUTO_INCREMENT, \
+                     DataSetName VARCHAR(255), \
+                     NodeId INT CHECK (NodeId = -1 OR NodeId IS NOT NULL),\
+                     {sub_query}\
+                     PRIMARY KEY (DataSetId)\
+                     )"
+    )
+
+    # Create FLpipeline table
+    mycursor.execute("CREATE TABLE FLpipeline(\
+     id int NOT NULL AUTO_INCREMENT,\
+     name varchar(255) NOT NULL, \
+     description varchar(255) NOT NULL,\
+     creation_date datetime NOT NULL,\
+     results longtext   NOT NULL,\
+     PRIMARY KEY (id)\
+    ) ")
+
+    # Create test results table
+    mycursor.execute("CREATE TABLE testResults(\
+     pipelineId INT,\
+     nodename VARCHAR(100) NOT NULL, \
+     confusionmatrix VARCHAR(255),\
+     accuracy LONG,\
+     sensivity LONG,\
+     ppv LONG,\
+     npv LONG,\
+     f1score LONG,\
+     fpr LONG,\
+     tpr LONG, \
+     PRIMARY KEY (pipelineId , nodename)\
+    ) ")
+
+    # Create FederatedDataset table
+    mycursor.execute("CREATE TABLE FedDatasets (\
+     FedId int NOT NULL AUTO_INCREMENT,\
+     FLsetupId int DEFAULT NULL,\
+     FLpipeId int DEFAULT NULL,\
+     name varchar(255) NOT NULL,\
+     PRIMARY KEY (FedId)\
+    )")
+
+    # Commit and close the cursor
+    mydb.commit()
+    mycursor.close()
+    mydb.close()
+
+except Error as e:
+    print(f"Error: {e}")