MEDfl 0.1.26__py3-none-any.whl → 0.1.27__py3-none-any.whl

Medfl/NetManager/database_connector.py

@@ -1,48 +1,48 @@
-import os
-from sqlalchemy import create_engine
-from configparser import ConfigParser
-
-import subprocess
-
-class DatabaseManager:
-    def __init__(self):
-
-        from MEDfl.LearningManager.utils import load_db_config
-        db_config = load_db_config()
-        if db_config:
-            self.config = db_config
-        else:
-            self.config = None
-        self.engine = None
-
-    def connect(self):
-        if not self.config:
-            raise ValueError("Database configuration not loaded. Use load_db_config() or set_config_path() first.")
-        connection_string = (
-            f"mysql+mysqlconnector://{self.config['user']}:{self.config['password']}@"
-            f"{self.config['host']}:{self.config['port']}/{self.config['database']}"
-        )
-        self.engine = create_engine(connection_string, pool_pre_ping=True)
-
-    def get_connection(self):
-        if not self.engine:
-            self.connect()
-        return self.engine.connect()
-    
-    def create_MEDfl_db(self , path_to_csv):
-        # Get the directory of the current script
-        current_directory = os.path.dirname(__file__)
-
-        # Define the path to the create_db.py script
-        create_db_script_path = os.path.join(current_directory, '..', 'scripts', 'create_db.py')
-
-        # Execute the create_db.py script
-        subprocess.run(['python', create_db_script_path, path_to_csv], check=True)
-
-        return
-
-    def close(self):
-        if self.engine:
-            self.engine.dispose()
-
-
+import os
+from sqlalchemy import create_engine
+from configparser import ConfigParser
+
+import subprocess
+
+class DatabaseManager:
+    def __init__(self):
+
+        from MEDfl.LearningManager.utils import load_db_config
+        db_config = load_db_config()
+        if db_config:
+            self.config = db_config
+        else:
+            self.config = None
+        self.engine = None
+
+    def connect(self):
+        if not self.config:
+            raise ValueError("Database configuration not loaded. Use load_db_config() or set_config_path() first.")
+        connection_string = (
+            f"mysql+mysqlconnector://{self.config['user']}:{self.config['password']}@"
+            f"{self.config['host']}:{self.config['port']}/{self.config['database']}"
+        )
+        self.engine = create_engine(connection_string, pool_pre_ping=True)
+
+    def get_connection(self):
+        if not self.engine:
+            self.connect()
+        return self.engine.connect()
+    
+    def create_MEDfl_db(self , path_to_csv):
+        # Get the directory of the current script
+        current_directory = os.path.dirname(__file__)
+
+        # Define the path to the create_db.py script
+        create_db_script_path = os.path.join(current_directory, '..', 'scripts', 'create_db.py')
+
+        # Execute the create_db.py script
+        subprocess.run(['python', create_db_script_path, path_to_csv], check=True)
+
+        return
+
+    def close(self):
+        if self.engine:
+            self.engine.dispose()
+
+

Medfl/NetManager/dataset.py

@@ -1,92 +1,92 @@
-import pandas as pd
-from sqlalchemy import text
-
-from .net_helper import *
-from .net_manager_queries import (DELETE_DATASET, INSERT_DATASET,
-                                  SELECT_ALL_DATASET_NAMES)
-from MEDfl.NetManager.database_connector import DatabaseManager
-
-class DataSet:
-    def __init__(self, name: str, path: str, engine=None):
-        """
-        Initialize a DataSet object.
-
-        :param name: The name of the dataset.
-        :type name: str
-        :param path: The file path of the dataset CSV file.
-        :type path: str
-        """
-        self.name = name
-        self.path = path
-        db_manager = DatabaseManager()
-        db_manager.connect()
-        self.engine = db_manager.get_connection()
-
-    def validate(self):
-        """
-        Validate name and path attributes.
-
-        :raises TypeError: If name or path is not a string.
-        """
-        if not isinstance(self.name, str):
-            raise TypeError("name argument must be a string")
-
-        if not isinstance(self.path, str):
-            raise TypeError("path argument must be a string")
-
-    def upload_dataset(self, NodeId=-1):
-        """
-        Upload the dataset to the database.
-
-        :param NodeId: The NodeId associated with the dataset.
-        :type NodeId: int
-
-        Notes:
-        - Assumes the file at self.path is a valid CSV file.
-        - The dataset is uploaded to the 'DataSets' table in the database.
-        """
-
-        data_df = pd.read_csv(self.path)
-        nodeId = NodeId
-        columns = data_df.columns.tolist()
-        
-
-        data_df = process_eicu(data_df)
-        for index, row in data_df.iterrows():
-            query_1 = "INSERT INTO DataSets(DataSetName,nodeId," + "".join(
-                f"{x}," for x in columns
-            )
-            query_2 = f" VALUES ('{self.name}',{nodeId}, " + "".join(
-                f"{is_str(data_df, row, x)}," for x in columns
-            )
-            query = query_1[:-1] + ")" + query_2[:-1] + ")"
-             
-            self.engine.execute(text(query))
-
-    def delete_dataset(self):
-        """
-        Delete the dataset from the database.
-
-        Notes:
-        - Assumes the dataset name is unique in the 'DataSets' table.
-        """
-        self.engine.execute(text(DELETE_DATASET), {"name": self.name})
-
-    def update_data(self):
-        """
-        Update the data in the dataset.
-
-        Not implemented yet.
-        """
-        pass
-
-    @staticmethod
-    def list_alldatasets(engine):
-        """
-        List all dataset names from the 'DataSets' table.
-
-        :returns: A DataFrame containing the names of all datasets in the 'DataSets' table.
-        :rtype: pd.DataFrame
-        """
-        res = pd.read_sql(text(SELECT_ALL_DATASET_NAMES), engine)
-        return res
+import pandas as pd
+from sqlalchemy import text
+
+from .net_helper import *
+from .net_manager_queries import (DELETE_DATASET, INSERT_DATASET,
+                                  SELECT_ALL_DATASET_NAMES)
+from MEDfl.NetManager.database_connector import DatabaseManager
+
+class DataSet:
+    def __init__(self, name: str, path: str, engine=None):
+        """
+        Initialize a DataSet object.
+
+        :param name: The name of the dataset.
+        :type name: str
+        :param path: The file path of the dataset CSV file.
+        :type path: str
+        """
+        self.name = name
+        self.path = path
+        db_manager = DatabaseManager()
+        db_manager.connect()
+        self.engine = db_manager.get_connection()
+
+    def validate(self):
+        """
+        Validate name and path attributes.
+
+        :raises TypeError: If name or path is not a string.
+        """
+        if not isinstance(self.name, str):
+            raise TypeError("name argument must be a string")
+
+        if not isinstance(self.path, str):
+            raise TypeError("path argument must be a string")
+
+    def upload_dataset(self, NodeId=-1):
+        """
+        Upload the dataset to the database.
+
+        :param NodeId: The NodeId associated with the dataset.
+        :type NodeId: int
+
+        Notes:
+        - Assumes the file at self.path is a valid CSV file.
+        - The dataset is uploaded to the 'DataSets' table in the database.
+        """
+
+        data_df = pd.read_csv(self.path)
+        nodeId = NodeId
+        columns = data_df.columns.tolist()
+        
+
+        data_df = process_eicu(data_df)
+        for index, row in data_df.iterrows():
+            query_1 = "INSERT INTO DataSets(DataSetName,nodeId," + "".join(
+                f"{x}," for x in columns
+            )
+            query_2 = f" VALUES ('{self.name}',{nodeId}, " + "".join(
+                f"{is_str(data_df, row, x)}," for x in columns
+            )
+            query = query_1[:-1] + ")" + query_2[:-1] + ")"
+             
+            self.engine.execute(text(query))
+
+    def delete_dataset(self):
+        """
+        Delete the dataset from the database.
+
+        Notes:
+        - Assumes the dataset name is unique in the 'DataSets' table.
+        """
+        self.engine.execute(text(DELETE_DATASET), {"name": self.name})
+
+    def update_data(self):
+        """
+        Update the data in the dataset.
+
+        Not implemented yet.
+        """
+        pass
+
+    @staticmethod
+    def list_alldatasets(engine):
+        """
+        List all dataset names from the 'DataSets' table.
+
+        :returns: A DataFrame containing the names of all datasets in the 'DataSets' table.
+        :rtype: pd.DataFrame
+        """
+        res = pd.read_sql(text(SELECT_ALL_DATASET_NAMES), engine)
+        return res