reduce waiting time and use environment variable for label path

examples/splitlearning_titanic/client/forward.py

@@ -56,7 +56,7 @@ def forward_pass(client_id, out_embedding_path, data_path=None):
 
     # save embeddings locally
     if not os.path.exists(f"{abs_path}/embeddings"):
-        os.makedirs(f"{abs_path}/embeddings", exist_ok=True)
+        os.makedirs(f"{abs_path}/embeddings")
     np.savez(f"{abs_path}/embeddings/embeddings_{client_id}.npz", embedding)
 
 

examples/splitlearning_titanic/readme.rst

@@ -19,7 +19,7 @@ Also install the following libraries into your virtual environment:
     pip install pandas torch scikit-learn
 
 
-Create a client.yaml file in the examples/splitlearning_titanic folder and add the following content:
+Make sure a client.yaml file is available in the examples/splitlearning_titanic folder with the following content:
 
 .. code-block:: bash
     network_id: fedn-network
@@ -34,7 +34,7 @@ Data Preparation
 Make sure the titanic dataset is downloaded in the splitlearning_titanic/data folder with the files "labels.csv", "train.csv" and "test.csv".
 Download the dataset from https://www.kaggle.com/competitions/titanic/data if necessary.
 
-We split the dataset (vertical split) into 2 clients. For this, locate yourself in the examples/splitlearning_titanic folder and run:
+We split the dataset (vertical split) into 2 clients. For this, locate yourself in the examples/splitlearning_titanic/client folder and run:
 
 .. code-block:: bash
 
@@ -43,41 +43,62 @@ We split the dataset (vertical split) into 2 clients. For this, locate yourself
 Compute Package
 ---------------
 
-Then, to create the compute package, run:
+Then, locate yourself into the examples/splitlearning_titanic folder. To create the compute package, run:
 
 .. code-block:: bash
 
     fedn package create --path client
 
 Note: For split learning, we do not need a seed model as for horizontal federated learning. 
 
-Environment Variables
+Local Setup with FEDn
 ---------------------
 
-Now, set up the necessary environment variables:
+Currently, Split Learning can only be run locally. To start all necessary services, run the following commands in different terminals:
+
+To start mongo and minio
+
+.. code-block:: bash
+
+    docker compose up -d mongo minio
+
+
+We need to set some environment variables in order to let the system know where to find the data and labels. 
+In another terminal, set the compute package directory to the examples/splitlearning_titanic folder (the directory where package.tgz is located) and start the controller.
 
 .. code-block:: bash
 
     export FEDN_COMPUTE_PACKAGE_DIR=/path/to/fedn/examples/splitlearning_titanic
+    fedn controller start
+
+Now, we start the combiner. First, we set the labels path to the labels.pt file in the client folder.
+
+.. code-block:: bash
+
     export FEDN_LABELS_PATH=/path/to/labels.pt
+    fedn combiner start
 
-In 2 different client terminals, set the data path to the client data folder generated by the data.py script.
+Open 2 new client terminals. Both clients should have access to their respective vertical dataset. 
+This is why we set the datapath to the different data folders which are generated by the data.py script. 
+To start the first client, run:
 
 .. code-block:: bash
 
     export FEDN_DATA_PATH=./data/clients/1/titanic.pt  
+    fedn client start --api-url http://localhost --api-port 8092 -in client.yaml --local-package
+
+and to start the second client, run:
+
+.. code-block:: bash
+
     export FEDN_DATA_PATH=./data/clients/2/titanic.pt  
+    fedn client start --api-url http://localhost --api-port 8092 -in client.yaml --local-package
+
 
-Local Setup with FEDn
----------------------
 
-Currently, Split Learning can only be run locally. To start all necessary services, run the following commands in different terminals:
 
-To start mongo and minio
 
-.. code-block:: bash
 
-    docker compose up -d mongo minio
 
 Start the controller
 

fedn/network/combiner/aggregators/splitlearningagg.py

@@ -16,7 +16,7 @@ class ServerModel(nn.Module):
 
     def __init__(self):
         super(ServerModel, self).__init__()
-        self.fc1 = nn.Linear(12, 6) # TODO: make this dynamic
+        self.fc1 = nn.Linear(12, 6)
         self.fc2 = nn.Linear(6, 1)
 
     def forward(self, x):

fedn/network/combiner/roundhandler.py

@@ -282,7 +282,7 @@ def _backward_pass(self, config: dict, clients: list):
 
         self.server.request_backward_pass(session_id=config["session_id"], gradient_id=config["model_id"], config=config, clients=clients)
 
-        time.sleep(3) # TODO: this is an easy hack for now. There needs to be some waiting time for the backward pass to complete.
+        time.sleep(1) # TODO: this is an easy hack for now. There needs to be some waiting time for the backward pass to complete.
         # the above mechanism cannot be used, as the backward pass is not returning any model updates (update_handler.waitforit checks for aggregation on the queue)
         return meta
 

fedn/network/controller/control.py

@@ -547,13 +547,13 @@ def check_combiners_done_reporting():
             "round_id": round_id,
             "task": "backward",
             "session_id": session_id,
-            "model_id": model_id 
+            "model_id": model_id
         })
 
         participating_combiners = [(combiner, backward_config) for combiner, _ in participating_combiners]
         _ = self.request_model_updates(participating_combiners)
 
-        time.sleep(3) # TODO: this is an easy hack for now. There needs to be some waiting time for the backward pass to complete.
+        time.sleep(1) # TODO: this is an easy hack for now. There needs to be some waiting time for the backward pass to complete.
         # the above mechanism cannot be used, as the backward pass is not producing any model updates (unlike the forward pass)
 
         logger.info("CONTROLLER: Backward pass completed.")

fedn/utils/helpers/plugins/splitlearninghelper.py

@@ -1,6 +1,6 @@
 import os
 import tempfile
-from io import BytesIO
+import time
 
 import numpy as np
 import torch
@@ -34,15 +34,13 @@ def save(self, data_dict, path=None, file_type="npz"):
 
         # Ensure all values are numpy arrays
         processed_dict = {str(k): np.array(v) for k, v in data_dict.items()}
-        
+
         # Use with statement to ensure proper file closure
         with open(path, "wb") as f:
             np.savez_compressed(f, **processed_dict)
-        
+
         # Small delay to ensure file is fully written
-        import time
         time.sleep(0.1)
-
         return path
 
     def load(self, path):
@@ -61,27 +59,18 @@ def load(self, path):
         except Exception as e:
             logger.error(f"Error in splitlearninghelper: loading data from {path}: {str(e)}")
             raise
-
-    def load_targets(self, data_path=None):
-        """Load target labels for split learning.
-        
-        Args:
-            data_path (str, optional): Path to the labels file. Defaults to None.
-        
-        Returns:
-            torch.Tensor: The target labels
-        """
-        if data_path is None:
-            # Try to get path from environment variable first
-            # data_path = os.environ.get("FEDN_LABELS_PATH")
-            data_path = "/Users/jonas/Documents/fedn/examples/splitlearning_titanic/client/data/clients/labels.pt"
-            logger.info("label path is {}".format(data_path))
-            # if data_path is None:
-            #     raise ValueError("FEDN_LABELS_PATH environment variable is not set. Set via export FEDN_LABELS_PATH='path/to/labels.pt'")
-
+
+    def load_targets(self):
+        """Load target labels for split learning."""
+        try:
+            data_path = os.environ.get("FEDN_LABELS_PATH")
+        except Exception as e:
+            logger.error("FEDN_LABELS_PATH environment variable is not set. Set via export FEDN_LABELS_PATH='path/to/labels.pt'")
+            raise
+
         try:
             data = torch.load(data_path, weights_only=True)
-            targets = data["y_train"] #.float()
+            targets = data["y_train"]
             return targets.reshape(-1, 1)  # Reshape to match model output shape
         except Exception as e:
             logger.error(f"Error loading labels from {data_path}: {str(e)}")