MEDfl 0.2.1__py3-none-any.whl → 2.0.0__py3-none-any.whl

Medfl/NetManager/net_manager_queries.py

@@ -0,0 +1,142 @@
+from .net_helper import is_str
+
+INSERT_DATASET = """
+    INSERT INTO DataSets(DataSetName, NodeId, {columns})
+    VALUES (:name, :NodeId, {values})
+"""
+DELETE_DATASET = """
+    DELETE FROM DataSets WHERE DataSetName = :name
+"""
+
+SELECT_ALL_DATASET_NAMES = """
+    SELECT DISTINCT DataSetName,NodeId FROM DataSets
+"""
+
+SELECT_DATASET_BY_NAME = """
+    SELECT * FROM DataSets WHERE DataSetName = :name
+"""
+
+# node queries
+# sql_queries.py
+
+INSERT_NODE_QUERY = (
+    "INSERT INTO Nodes(NodeName,NetId,train) VALUES ('{}',{}, {})"
+)
+DELETE_NODE_QUERY = "DELETE FROM Nodes WHERE NodeName = '{}'"
+SELECT_MASTER_COLUMNS_QUERY = "SELECT * FROM MasterDataset LIMIT 1"
+SELECT_DATASET_BY_COLUMN_QUERY = "SELECT * FROM MasterDataset WHERE {} = '{}'"
+SELECT_DATASET_BY_NODE_ID_QUERY = "SELECT * FROM DataSets WHERE NodeId = {}"
+
+SELECT_ALL_DATASETS_QUERY = "SELECT DISTINCT DataSetName,NodeName FROM DataSets,Nodes WHERE Nodes.NodeName = '{}' and Nodes.NodeId = DataSets.NodeId"
+SELECT_ALL_NODES_QUERY = "SELECT * FROM Nodes"
+
+
+# SQL query to insert a new network
+INSERT_NETWORK_QUERY = "INSERT INTO Networks(NetName) VALUES (:name)"
+
+# SQL query to delete a network
+DELETE_NETWORK_QUERY = "DELETE FROM Networks WHERE NetName = '{name}'"
+
+# SQL query to delete a network
+GET_NETWORK_QUERY = "SELECT * FROM Networks WHERE NetName = '{name}'"
+
+
+# SQL query to update a network
+UPDATE_NETWORK_QUERY = (
+    "UPDATE Networks SET FLsetupId = {FLsetupId} WHERE NetId = {id}"
+)
+
+# SQL query to retrieve all nodes for a network
+LIST_ALL_NODES_QUERY = """
+SELECT Nodes.NodeName, Networks.NetName 
+FROM Nodes 
+JOIN Networks ON Networks.NetId = Nodes.NetId 
+WHERE Networks.NetName = :name
+"""
+
+# SQL query to create the MasterDataset table (SQLite-compatible)
+CREATE_MASTER_DATASET_TABLE_QUERY = """
+CREATE TABLE IF NOT EXISTS MasterDataset (
+    PatientId INTEGER PRIMARY KEY AUTOINCREMENT,
+    {}
+);
+"""
+
+
+# SQL query to create the datasets table (SQLite-compatible)
+CREATE_DATASETS_TABLE_QUERY = """
+CREATE TABLE IF NOT EXISTS Datasets (
+    DataSetId INTEGER PRIMARY KEY AUTOINCREMENT, 
+    DataSetName VARCHAR(255), 
+    NodeId INT,
+    {}
+);
+"""
+
+
+
+# SQL query to insert dataset values
+INSERT_DATASET_VALUES_QUERY = "INSERT INTO MasterDataset({columns}, NodeId) VALUES ('{name}', {nodeId}, {values})"
+
+
+# FL setup_queries
+# sql_queries.py
+
+CREATE_FLSETUP_QUERY = """
+    INSERT INTO FLsetup (name, description, creation_date, NetId, column_name)
+    VALUES (:name, :description, :creation_date, :net_id, :column_name)
+"""
+
+DELETE_FLSETUP_QUERY = """
+    DELETE FROM FLsetup
+    WHERE name = :name
+"""
+
+UPDATE_FLSETUP_QUERY = UPDATE_NETWORK_QUERY = (
+    "UPDATE FLsetup SET column_name ='{column_name}' WHERE name ='{FLsetupName}'"
+)
+
+
+READ_SETUP_QUERY = """
+    SELECT * FROM FLsetup
+    WHERE FLsetupId = :flsetup_id
+"""
+
+READ_ALL_SETUPS_QUERY = """
+    SELECT * FROM FLsetup
+"""
+
+READ_NETWORK_BY_ID_QUERY = """
+    SELECT * FROM Networks
+    WHERE NetId = :net_id
+"""
+
+READ_DISTINCT_NODES_QUERY = """
+SELECT DISTINCT {} FROM MasterDataset 
+"""
+
+
+# FederatedDataset Queries
+INSERT_FLDATASET_QUERY = (
+    "INSERT INTO FedDatasets(name, FLsetupId) VALUES (:name, :FLsetupId)"
+)
+DELETE_FLDATASET_BY_SETUP_AND_PIPELINE_QUERY = "DELETE FROM FedDatasets WHERE FLsetupId = :FLsetupId AND FLpipeId = :FLpipeId"
+
+
+UPDATE_FLDATASET_QUERY = (
+    "UPDATE FedDatasets SET FLpipeId = :FLpipeId WHERE FedId = :FedId"
+)
+SELECT_FLDATASET_BY_NAME_QUERY = "SELECT * FROM FedDatasets WHERE name = :name"
+
+CREATE_FLPIPELINE_QUERY = """
+INSERT INTO FLpipeline (name, description, creation_date, results)
+VALUES ('{name}', '{description}', '{creation_date}', '{result}')
+"""
+DELETE_FLPIPELINE_QUERY = "DELETE FROM FLpipeline WHERE name = '{name}'"
+
+SELECT_FLPIPELINE_QUERY = "SELECT FROM FLpipeline WHERE name = '{name}'"
+
+CREATE_TEST_RESULTS_QUERY = """
+INSERT INTO testResults (pipelineid, nodename, confusionmatrix, accuracy , sensivity, ppv , npv , f1score , fpr , tpr )
+VALUES ('{pipelineId}', '{nodeName}', '{confusion_matrix}', '{accuracy}' , '{sensivity}' , '{ppv}' , '{npv}' , '{f1score}' , '{fpr}' , '{tpr}')
+"""

Medfl/NetManager/network.py

@@ -0,0 +1,194 @@
+# src/MEDfl/NetManager/network.py
+
+from MEDfl.LearningManager.utils import *
+from .net_helper import *
+from .net_manager_queries import (CREATE_MASTER_DATASET_TABLE_QUERY,
+                                  CREATE_DATASETS_TABLE_QUERY,
+                                  DELETE_NETWORK_QUERY,
+                                  INSERT_NETWORK_QUERY, LIST_ALL_NODES_QUERY,
+                                  UPDATE_NETWORK_QUERY, GET_NETWORK_QUERY)
+from .node import Node
+import pandas as pd
+from MEDfl.LearningManager.utils import params
+
+from sqlalchemy import text
+from sqlalchemy.exc import SQLAlchemyError
+
+class Network:
+    """
+    A class representing a network.
+
+    Attributes:
+        name (str): The name of the network.
+        mtable_exists (int): An integer flag indicating whether the MasterDataset table exists (1) or not (0).
+    """
+
+    def __init__(self, name: str = ""):
+        """
+        Initialize a Network instance.
+
+        Parameters:
+            name (str): The name of the network.
+        """
+        self.name = name
+        self.mtable_exists = int(master_table_exists())
+        self.validate()
+
+        db_manager = DatabaseManager() 
+        db_manager.connect() 
+        self.eng = db_manager.get_connection()
+
+    def validate(self):
+        """Validate name"""
+
+        if not isinstance(self.name, str):
+            raise TypeError("name argument must be a string")
+
+    def create_network(self):
+        """Create a new network in the database."""
+        try:
+            print(self.name)
+            self.eng.execute(text(INSERT_NETWORK_QUERY), {"name": self.name})
+            self.id = self.get_netid_from_name(self.name)
+        except SQLAlchemyError as e:
+            print(f"Error creating network: {e}")
+
+    def use_network(self, network_name: str):
+        """Use a network in the database.
+
+        Parameters:
+            network_name (str): The name of the network to use.
+
+        Returns:
+            Network or None: An instance of the Network class if the network exists, else None.
+        """
+        try:
+            network = pd.read_sql(
+                text(GET_NETWORK_QUERY),
+                self.eng,
+                params={"name": network_name}
+            )
+            if not network.empty:
+                self.name = network.iloc[0]['NetName']
+                self.id = network.iloc[0]['NetId']
+                self.mtable_exists = int(master_table_exists())
+                self.validate()
+                return self
+            else:
+                return None
+        except SQLAlchemyError as e:
+            print(f"Error using network: {e}")
+            return None
+
+    def delete_network(self):
+        """Delete the network from the database."""
+        try:
+            self.eng.execute(text(DELETE_NETWORK_QUERY), {"name": self.name})
+        except SQLAlchemyError as e:
+            print(f"Error deleting network: {e}")
+
+    def update_network(self, FLsetupId: int):
+        """Update the network's FLsetupId in the database.
+
+        Parameters:
+            FLsetupId (int): The FLsetupId to update.
+        """
+        try:
+            self.eng.execute(
+                text(UPDATE_NETWORK_QUERY),
+                {"FLsetupId": FLsetupId, "id": self.id}
+            )
+        except SQLAlchemyError as e:
+            print(f"Error updating network: {e}")
+
+    def add_node(self, node: Node):
+        """Add a node to the network.
+
+        Parameters:
+            node (Node): The node to add.
+        """
+        node.create_node(self.id)
+
+    def list_allnodes(self):
+        """List all nodes in the network.
+
+        Returns:
+            DataFrame: A DataFrame containing information about all nodes in the network.
+        """
+        try:
+            query = text(LIST_ALL_NODES_QUERY)
+            result_proxy = self.eng.execute(query, name=self.name)
+            result_df = pd.DataFrame(result_proxy.fetchall(), columns=result_proxy.keys())
+            return result_df
+        except SQLAlchemyError as e:
+            print(f"Error listing all nodes: {e}")
+            return pd.DataFrame()
+
+    def create_master_dataset(self, path_to_csv: str = params['path_to_master_csv']):
+        """
+        Create the MasterDataset table and insert dataset values.
+
+        :param path_to_csv: Path to the CSV file containing the dataset.
+        """
+        try:
+            print(path_to_csv)
+            data_df = pd.read_csv(path_to_csv)
+
+            if self.mtable_exists != 1:
+                columns = data_df.columns.tolist()
+                columns_str = ",\n".join(
+                    [
+                        f"{col} {column_map[str(data_df[col].dtype)]}"
+                        for col in columns
+                    ]
+                )
+                self.eng.execute(
+                    text(CREATE_MASTER_DATASET_TABLE_QUERY.format(columns_str))
+                )
+                self.eng.execute(text(CREATE_DATASETS_TABLE_QUERY.format(columns_str)))
+
+                # Process data
+                data_df = process_eicu(data_df)
+
+                # Insert data in batches
+                batch_size = 1000  # Adjust as needed
+                for start_idx in range(0, len(data_df), batch_size):
+                    batch_data = data_df.iloc[start_idx:start_idx + batch_size]
+                    insert_query = f"INSERT INTO MasterDataset ({', '.join(columns)}) VALUES ({', '.join([':' + col for col in columns])})"
+                    data_to_insert = batch_data.to_dict(orient='records')
+                    self.eng.execute(text(insert_query), data_to_insert)
+
+                self.mtable_exists = 1
+        except SQLAlchemyError as e:
+            print(f"Error creating master dataset: {e}")
+            
+    @staticmethod
+    def list_allnetworks():
+        """List all networks in the database.
+
+        Returns:
+            DataFrame: A DataFrame containing information about all networks in the database.
+        """
+        try:
+            db_manager = DatabaseManager() 
+            db_manager.connect() 
+            my_eng = db_manager.get_connection() 
+
+            result_proxy = my_eng.execute("SELECT * FROM Networks")
+            result = result_proxy.fetchall()
+            return pd.DataFrame(result, columns=result_proxy.keys())
+        except SQLAlchemyError as e:
+            print(f"Error listing all networks: {e}")
+            return pd.DataFrame()
+    
+    def get_netid_from_name(self, name):
+        """Get network ID from network name."""
+        try:
+            result = self.eng.execute(text("SELECT NetId FROM Networks WHERE NetName = :name"), {"name": name}).fetchone()
+            if result:
+                return result[0]
+            else:
+                return None
+        except SQLAlchemyError as e:
+            print(f"Error fetching network ID: {e}")
+            return None

Medfl/NetManager/node.py

@@ -0,0 +1,184 @@
+import pandas as pd
+
+from .net_helper import *
+from .net_manager_queries import *
+from MEDfl.LearningManager.utils import params
+from MEDfl.NetManager.database_connector import DatabaseManager
+
+from sqlalchemy import text, exc
+
+
+class Node:
+    """
+    A class representing a node in the network.
+
+    Attributes:
+        name (str): The name of the node.
+        train (int): An integer flag representing whether the node is used for training (1) or testing (0).
+        test_fraction (float, optional): The fraction of data used for testing when train=1. Default is 0.2.
+    """
+
+    def __init__(
+        self, name: str, train: int, test_fraction: float = 0.2, engine=None
+    ):
+        """
+        Initialize a Node instance.
+
+        Parameters:
+            name (str): The name of the node.
+            train (int): An integer flag representing whether the node is used for training (1) or testing (0).
+            test_fraction (float, optional): The fraction of data used for testing when train=1. Default is 0.2.
+        """
+        self.name = name
+        self.train = train
+        self.test_fraction = 1.0 if self.train == 0 else test_fraction
+       
+
+        db_manager = DatabaseManager() ; 
+        db_manager.connect() ; 
+        self.engine = db_manager.get_connection()
+
+    def validate(self):
+        """Validate name, train, test_fraction"""
+        if not isinstance(self.name, str):
+            raise TypeError("name argument must be a string")
+
+        if not isinstance(self.train, int):
+            raise TypeError("train argument must be an int")
+
+        if not isinstance(self.test_fraction, float):
+            raise TypeError("test_fraction argument must be a float")
+
+    def create_node(self, NetId: int):
+        """Create a node in the database.
+        Parameters:
+            NetId (int): The ID of the network to which the node belongs.
+
+        Returns:
+            None
+        """
+        self.engine.execute(
+            text(INSERT_NODE_QUERY.format(self.name, NetId, self.train))
+        )
+
+    def delete_node(self):
+        """Delete the node from the database."""
+        self.engine.execute(text(DELETE_NODE_QUERY.format(self.name)))
+
+    def check_dataset_compatibility(self, data_df):
+        """Check if the dataset is compatible with the master dataset.
+        Parameters:
+            data_df (DataFrame): The dataset to check.
+
+        Returns:
+            None
+        """
+        if master_table_exists() != 1:
+            print("MasterDataset doesn't exist")
+        else:
+            columns = data_df.columns.tolist()
+            
+            # get master_dataset columns
+            result_proxy = self.engine.execute(SELECT_MASTER_COLUMNS_QUERY)
+            master_table_columns = result_proxy.keys()
+
+
+            assert [x == y for x, y in zip(master_table_columns, columns)]
+
+    def update_node(self):
+        """Update the node information (not implemented)."""
+        pass
+
+    def get_dataset(self, column_name: str = None):
+        """Get the dataset for the node based on the given column name.
+        Parameters:
+            column_name (str, optional): The column name to filter the dataset. Default is None.
+
+        Returns:
+            DataFrame: The dataset associated with the node.
+        """
+        NodeId = get_nodeid_from_name(self.name)
+        if column_name is not None:
+            query = text(SELECT_DATASET_BY_COLUMN_QUERY.format(column_name, self.name))
+        else:
+            query = text(SELECT_DATASET_BY_NODE_ID_QUERY.format(NodeId))
+
+        result_proxy = self.engine.execute(query)
+        node_dataset = pd.DataFrame(result_proxy.fetchall(), columns=result_proxy.keys())
+
+        return node_dataset
+
+    def upload_dataset(self, dataset_name: str, path_to_csv: str = params['path_to_test_csv']):
+        """Upload the dataset to the database for the node.
+
+        Parameters:
+            dataset_name (str): The name of the dataset.
+            path_to_csv (str, optional): Path to the CSV file containing the dataset. Default is the path in params.
+
+        Returns:
+            None
+        """
+        try:
+            data_df = pd.read_csv(path_to_csv)
+            nodeId = get_nodeid_from_name(self.name)
+            columns = data_df.columns.tolist()
+            self.check_dataset_compatibility(data_df)
+
+            data_df = process_eicu(data_df)
+
+            # Insert data in batches
+            batch_size = 1000  # Adjust as needed
+            for start_idx in range(0, len(data_df), batch_size):
+                batch_data = data_df.iloc[start_idx:start_idx + batch_size]
+                insert_query = f"INSERT INTO Datasets (DataSetName, NodeId, {', '.join(columns)}) VALUES (:dataset_name, :nodeId, {', '.join([':' + col for col in columns])})"
+                data_to_insert = batch_data.to_dict(orient='records')
+                params = [{"dataset_name": dataset_name, "nodeId": nodeId, **row} for row in data_to_insert]
+                self.engine.execute(text(insert_query), params)
+        except exc.SQLAlchemyError as e:
+            print(f"Error uploading dataset: {e}")
+
+    def assign_dataset(self, dataset_name:str):
+        """Assigning existing dataSet to node
+        Parameters:
+            dataset_name (str): The name of the dataset to assign.
+
+        Returns:
+            None
+        """
+
+        nodeId = get_nodeid_from_name(self.name)
+        query = f"UPDATE DataSets SET nodeId = {nodeId} WHERE DataSetName = '{dataset_name}'"
+        self.engine.execute(text(query))
+
+    def unassign_dataset(self, dataset_name:str):
+        """unssigning existing dataSet to node
+        Parameters:
+            dataset_name (str): The name of the dataset to assign.
+
+        Returns:
+            None
+        """
+
+        query = f"UPDATE DataSets SET nodeId = {-1} WHERE DataSetName = '{dataset_name}'"
+        self.engine.execute(text(query))
+
+    def list_alldatasets(self):
+        """List all datasets associated with the node.
+        Returns:
+            DataFrame: A DataFrame containing information about all datasets associated with the node.
+        
+        """
+        return pd.read_sql(
+            text(SELECT_ALL_DATASETS_QUERY.format(self.name)), my_eng
+        )
+
+    @staticmethod
+    def list_allnodes():
+        """List all nodes in the database.
+        Returns:
+            DataFrame: A DataFrame containing information about all nodes in the database.
+        
+        """
+        query = text(SELECT_ALL_NODES_QUERY)
+        res = pd.read_sql(query, my_eng)
+        return res

Medfl/__init__.py

@@ -0,0 +1,3 @@
+from .LearningManager import *
+from .NetManager import *
+from .scripts import *

Medfl/scripts/__init__.py

@@ -0,0 +1,2 @@
+# from .base import *
+# from .create_db import *

Medfl/scripts/base.py

@@ -0,0 +1,30 @@
+import mysql.connector
+from sqlalchemy import create_engine, text
+from configparser import ConfigParser
+import yaml
+import pkg_resources
+import os
+
+# Get the directory of the current script
+current_directory = os.path.dirname(os.path.abspath(__file__))
+
+# Load configuration from the config file
+config_file_path = os.path.join(current_directory, 'db_config.ini')
+
+config = ConfigParser()
+config.read(config_file_path)
+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()

Medfl/scripts/create_db.py

@@ -0,0 +1,126 @@
+import sys
+import sqlite3
+import pandas as pd
+from configparser import ConfigParser
+import os
+import ast 
+
+from MEDfl.LearningManager.utils import *
+
+
+def main(csv_file_path):
+    try:
+        # Get the directory of the current script
+        current_directory = os.path.dirname(os.path.abspath(__file__))
+
+        # Load configuration from the config file
+        # config_file_path = os.path.join(current_directory, 'sqllite_config.ini')*
+
+        config_file_path = load_db_config()
+
+        # config = ConfigParser()
+        # config.read(config_file_path)
+        # sqlite_config = config['sqllite']
+
+        sqlite_config = config_file_path 
+
+
+        print('Im here !')
+
+        # Connect to SQLite database (it will be created if it doesn't exist)
+        database_path = sqlite_config['database']
+        conn = sqlite3.connect(database_path)
+        cursor = conn.cursor()
+
+        # Drop each table if it exists
+        tables = ['Networks', 'FLsetup', 'Nodes', 'DataSets', 'FLpipeline', 'testResults', 'FedDatasets']
+        for table in tables:
+            cursor.execute(f"DROP TABLE IF EXISTS {table}")
+
+        # Create Networks table
+        cursor.execute(
+            "CREATE TABLE Networks( \
+                         NetId INTEGER PRIMARY KEY AUTOINCREMENT, \
+                         NetName TEXT \
+                         );"
+        )
+
+        # Create FLsetup table
+        cursor.execute("CREATE TABLE FLsetup (\
+        FLsetupId INTEGER PRIMARY KEY AUTOINCREMENT,\
+        name TEXT NOT NULL, \
+        description TEXT NOT NULL,\
+        creation_date TEXT NOT NULL,\
+        NetId INTEGER NOT NULL,\
+        column_name TEXT\
+        )")
+
+        # Create Nodes table
+        cursor.execute("CREATE TABLE Nodes ( \
+         NodeId INTEGER PRIMARY KEY AUTOINCREMENT,\
+         NodeName TEXT,\
+         train BOOLEAN DEFAULT 1,\
+         NetId INTEGER\
+        )")
+
+        data_df = pd.read_csv(csv_file_path)
+        columns = data_df.columns.tolist()
+        column_map = {"object": "TEXT", "int64": "INTEGER", "float64": "REAL"}
+        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
+        cursor.execute(
+            f"CREATE TABLE DataSets( \
+                         DataSetId INTEGER PRIMARY KEY AUTOINCREMENT, \
+                         DataSetName TEXT, \
+                         NodeId INTEGER,\
+                         {sub_query}\
+                         )"
+        )
+
+        # Create FLpipeline table
+        cursor.execute("CREATE TABLE FLpipeline(\
+         id INTEGER PRIMARY KEY AUTOINCREMENT,\
+         name TEXT NOT NULL, \
+         description TEXT NOT NULL,\
+         creation_date TEXT NOT NULL,\
+         results TEXT NOT NULL\
+        ) ")
+
+        # Create test results table
+        cursor.execute("CREATE TABLE testResults(\
+         pipelineId INTEGER,\
+         nodename TEXT NOT NULL, \
+         confusionmatrix TEXT,\
+         accuracy REAL,\
+         sensivity REAL,\
+         ppv REAL,\
+         npv REAL,\
+         f1score REAL,\
+         fpr REAL,\
+         tpr REAL, \
+         PRIMARY KEY (pipelineId, nodename)\
+        ) ")
+
+        # Create FederatedDataset table
+        cursor.execute("CREATE TABLE FedDatasets (\
+         FedId INTEGER PRIMARY KEY AUTOINCREMENT,\
+         FLsetupId INTEGER,\
+         FLpipeId INTEGER,\
+         name TEXT NOT NULL\
+        )")
+
+        # Commit and close the cursor
+        conn.commit()
+        cursor.close()
+        conn.close()
+
+    except sqlite3.Error as e:
+        print(f"Error: {e}")
+
+if __name__ == "__main__":
+    if len(sys.argv) != 2:
+        print("Usage: python script.py <path_to_csv_file>")
+        sys.exit(1)
+    csv_file_path = sys.argv[1]
+    main(csv_file_path)