chore: release 0.26.0 (#293)

Signed-off-by: Olivier Léobal <[email protected]> Signed-off-by: ThibaultFy <[email protected]> Co-authored-by: ThibaultFy <[email protected]>
Substra · Apr 7, 2023 · 904686b · 904686b
1 parent 7158577
commit 904686b
Show file tree

Hide file tree

Showing 7 changed files with 106 additions and 67 deletions.
diff --git a/.gitignore b/.gitignore
@@ -151,6 +151,7 @@ docs/source/substrafl_doc/examples
 # Data folder when run locally
 **/data_iris
 **/data_mnist
+**/data
 
 # Algo files folder when run locally
 **/algo_files

diff --git a/docs/source/additional/release.rst b/docs/source/additional/release.rst
@@ -28,24 +28,50 @@ This is an overview of the main changes, please have a look at the changelog of
 - `backend changelog <https://github.com/Substra/substra-backend/blob/main/CHANGELOG.md>`__
 - `orchestrator changelog <https://github.com/Substra/orchestrator/blob/main/CHANGELOG.md>`__
 
-Substra 0.25.0 - 2023-02-17
-^^^^^^^^^^^^^^^^^^^^^^^^^^^
+Substra 0.26.0 --- 2023-04-03
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+- Improve backend performance when handling large amounts of compute plans and tasks. This will result in faster front-end pages.
+- Rename Algo to Function.
+- SSO Login
+- Experimental: Add a task duration breakdown for every task in the front-end. Note that this is an experimental feature and only works on the current backend you are logged into.
+
+.. figure:: ../static/images/substra-0.26-task-duration.png
+  :align: center
+  :alt: Screenshot of task duration
+
+Front-end:
+
+- Fix issue where a performance of ``0`` was displayed as ``-``.
+
+SubstraFL:
+
+- **BREAKING CHANGE**: ``algo`` are now passed as a parameter to the ``strategy`` and not to ``execute_experiement`` anymore.
+- **BREAKING CHANGE**: a ``strategy`` needs to implement a new method ``build_graph`` to build the graph of tasks to be executed in ``execute_experiment``.
+- **BREAKING CHANGE**: ``predict`` method of ``strategy`` has been renamed to ``perform_predict``.
+- **BREAKING CHANGE**: clarify ``EvaluationStrategy`` arguments: change ``rounds`` to ``eval_frequency`` and ``eval_rounds``.
+- Fix an issue where ``aggregation_lr`` could not be changed in the Scaffold strategy.
+- Add Initialization task to each strategy in SubstraFL
+
+
+Substra 0.25.0 --- 2023-02-17
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
 - **BREAKING CHANGE**: ``DataSampleSpec`` does not have a ``test_only`` field anymore.
 - SubstraFL: It is now possible to test on an organization where no training have been performed.
 - New ``creator`` field in Compute Plan.
 - Fix an issue where Skaffold spawned too many backends.
 - Add contributing guide & code of conduct to all repos.
 
-Substra 0.24.0 - 2023-01-13
-^^^^^^^^^^^^^^^^^^^^^^^^^^^
+Substra 0.24.0 --- 2023-01-13
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
 - Fix issue where launching a large compute sometimes fails with: ``ERROR: could not serialize access due to read/write dependencies among transactions (SQLSTATE 40001)``
 - Documentation: add **contributing guide** and **code of conduct**
 - Update **Substra Tools** base docker image to ``substra-tools:0.20.0-nvidiacuda11.6.0-base-ubuntu20.04-python3.*``
 
-Substra 0.23.1 - 2022-11-24
-^^^^^^^^^^^^^^^^^^^^^^^^^^^
+Substra 0.23.1 --- 2022-11-24
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
 Main changes
 
@@ -195,8 +221,8 @@ Substra Backend:
 
 - Prevent use of ``__`` in asset metadata keys
 
-Substra 0.22.0 - 2022-10-20
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+Substra 0.22.0 --- 2022-10-20
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
 Main changes
 
@@ -350,8 +376,8 @@ could be replace with:
       tools.metrics.execute(AUC())
 
 
-Substra 0.21.0 - 2022-09-12
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+Substra 0.21.0 --- 2022-09-12
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
 This is our first open source release since 2021! When the product was closed source it used to be named Connect. It is now renamed Substra.
 

diff --git a/docs/source/additional/releases.yaml b/docs/source/additional/releases.yaml
@@ -9,6 +9,44 @@ components: # for table headers
   - substra-tests
 
 releases:
+  - version: 0.26.0
+    components:
+      substrafl:
+        version: 0.35.0
+        link: https://github.com/Substra/substrafl/releases/tag/0.35.0
+      substra:
+        version: 0.43.0
+        link: https://github.com/Substra/substra/releases/tag/0.43.0
+      substra-tools:
+        version: 0.20.0
+        link: https://github.com/Substra/substra-tools/releases/tag/0.20.0
+      substra-backend:
+        version: 0.36.0
+        link: https://github.com/Substra/substra-backend/releases/tag/0.36.0
+        helm:
+          version: 22.4.2
+          link: https://artifacthub.io/packages/helm/substra/substra-backend/22.4.2
+      orchestrator:
+        version: 0.33.0
+        link: https://github.com/Substra/orchestrator/releases/tag/0.33.0
+        helm:
+          version: 7.4.12
+          link: https://artifacthub.io/packages/helm/substra/orchestrator/7.4.12
+      substra-frontend:
+        version: 0.40.0
+        link: https://github.com/Substra/substra-frontend/releases/tag/0.40.0
+        helm:
+          version: 1.0.16
+          link: https://artifacthub.io/packages/helm/substra/substra-frontend/1.0.16
+      hlf-k8s:
+        version: 0.2.3
+        link: https://github.com/Substra/hlf-k8s/releases/tag/0.2.3
+        helm:
+          version: 10.2.3
+          link: https://artifacthub.io/packages/helm/substra/hlf-k8s/10.2.3
+      substra-tests:
+        version: 0.39.0
+        link: https://github.com/Substra/substra-tests/releases/tag/0.39.0
   - version: 0.25.0
     components:
       substrafl:

diff --git a/docs/source/conf.py b/docs/source/conf.py
@@ -29,9 +29,9 @@
 TMP_FOLDER = Path(__file__).parents[2] / "tmp"
 
 if os.environ.get("READTHEDOCS_VERSION_TYPE") == "tag":
-    SUBSTRA_VERSION = "0.42.0"
+    SUBSTRA_VERSION = "0.43.0"
     TOOLS_VERSION = "0.20.0"
-    SUBSTRAFL_VERSION = "0.34.0"
+    SUBSTRAFL_VERSION = "0.35.0"
 
 else:
     SUBSTRA_VERSION = "main"

diff --git a/docs/source/documentation/get_performances.rst b/docs/source/documentation/get_performances.rst
@@ -59,11 +59,11 @@ This script will automatically end if the :code:`performance.json` file has not
         df = pd.DataFrame(dict_perf)
 
         for _, row in df.iterrows():
-            if row["testtuple_key"] in logged_rows:
+            if row["task_key"] in logged_rows:
                 continue
 
-            logged_rows.append(row["testtuple_key"])
+            logged_rows.append(row["task_key"])
 
-            step = int(row["round_idx"]) if row["round_idx"] is not None else int(row["testtuple_rank"])
+            step = int(row["round_idx"]) if row["round_idx"] is not None else int(row["task_rank"])
 
-            log_metric(f"{row['metric_name']}_{row['worker']}", row["performance"], step)
+            log_metric(f"{row['function_name']}_{row['worker']}", row["performance"], step)
diff --git a/docs/source/static/images/substra-0.26-task-duration.png b/docs/source/static/images/substra-0.26-task-duration.png
diff --git a/examples/diabetes_example/run_diabetes.py b/examples/diabetes_example/run_diabetes.py
@@ -104,7 +104,9 @@
 # - Permissions allow you to execute a function on a certain dataset.
 #
 
-permissions = Permissions(public=False, authorized_ids=[ANALYTICS_PROVIDER_ORG_ID])
+permissions_local = Permissions(public=False, authorized_ids=DATA_PROVIDER_ORGS_ID)
+permissions_aggregation = Permissions(public=False, authorized_ids=[ANALYTICS_PROVIDER_ORG_ID])
+
 # %%
 # Next, we need to define the asset directory. You should have already downloaded the assets folder as stated above.
 #
@@ -136,15 +138,12 @@
     type="csv",
     data_opener=assets_directory / "dataset" / "diabetes_opener.py",
     description=data_path / "description.md",
-    permissions=permissions,
-    logs_permission=permissions,
+    permissions=permissions_local,
+    logs_permission=permissions_local,
 )
 
 # We register the dataset for each of the organisations
-dataset_keys = {
-    client_id: clients[client_id].add_dataset(dataset)
-    for client_id in DATA_PROVIDER_ORGS_ID
-}
+dataset_keys = {client_id: clients[client_id].add_dataset(dataset) for client_id in DATA_PROVIDER_ORGS_ID}
 
 for client_id, key in dataset_keys.items():
     print(f"Dataset key for {client_id}: {key}")
@@ -210,6 +209,7 @@
 
 # %%
 
+
 local_first_order_computation_docker_files = [
     assets_directory / "functions" / "federated_analytics_functions.py",
     assets_directory / "functions" / "local_first_order_computation" / "Dockerfile",
@@ -227,15 +227,11 @@
         optional=False,
         multiple=True,
     ),
-    FunctionInputSpec(
-        identifier="opener", kind=AssetKind.data_manager, optional=False, multiple=False
-    ),
+    FunctionInputSpec(identifier="opener", kind=AssetKind.data_manager, optional=False, multiple=False),
 ]
 
 local_first_order_function_outputs = [
-    FunctionOutputSpec(
-        identifier="local_analytics_first_moments", kind=AssetKind.model, multiple=False
-    )
+    FunctionOutputSpec(identifier="local_analytics_first_moments", kind=AssetKind.model, multiple=False)
 ]
 
 local_first_order_function = FunctionSpec(
@@ -244,13 +240,12 @@
     outputs=local_first_order_function_outputs,
     description=assets_directory / "functions" / "description.md",
     file=local_archive_first_order_computation_path,
-    permissions=permissions,
+    permissions=permissions_local,
 )
 
 
 local_first_order_function_keys = {
-    client_id: clients[client_id].add_function(local_first_order_function)
-    for client_id in DATA_PROVIDER_ORGS_ID
+    client_id: clients[client_id].add_function(local_first_order_function) for client_id in DATA_PROVIDER_ORGS_ID
 }
 
 print(f"Local function key for step 1: computing first order moments {local_first_order_function_keys}")
@@ -271,9 +266,7 @@
     assets_directory / "functions" / "aggregation" / "Dockerfile",
 ]
 
-aggregate_archive_path = (
-    assets_directory / "functions" / "aggregate_function_analytics.zip"
-)
+aggregate_archive_path = assets_directory / "functions" / "aggregate_function_analytics.zip"
 with zipfile.ZipFile(aggregate_archive_path, "w") as z:
     for filepath in aggregate_function_docker_files:
         z.write(filepath, arcname=os.path.basename(filepath))
@@ -287,17 +280,15 @@
     ),
 ]
 
-aggregate_function_outputs = [
-    FunctionOutputSpec(identifier="shared_states", kind=AssetKind.model, multiple=False)
-]
+aggregate_function_outputs = [FunctionOutputSpec(identifier="shared_states", kind=AssetKind.model, multiple=False)]
 
 aggregate_function = FunctionSpec(
     name="Aggregate Federated Analytics",
     inputs=aggregate_function_inputs,
     outputs=aggregate_function_outputs,
     description=assets_directory / "functions" / "description.md",
     file=aggregate_archive_path,
-    permissions=permissions,
+    permissions=permissions_aggregation,
 )
 
 
@@ -335,12 +326,8 @@
         optional=False,
         multiple=True,
     ),
-    FunctionInputSpec(
-        identifier="opener", kind=AssetKind.data_manager, optional=False, multiple=False
-    ),
-    FunctionInputSpec(
-        identifier="shared_states", kind=AssetKind.model, optional=False, multiple=False
-    ),
+    FunctionInputSpec(identifier="opener", kind=AssetKind.data_manager, optional=False, multiple=False),
+    FunctionInputSpec(identifier="shared_states", kind=AssetKind.model, optional=False, multiple=False),
 ]
 
 local_second_order_function_outputs = [
@@ -357,13 +344,12 @@
     outputs=local_second_order_function_outputs,
     description=assets_directory / "functions" / "description.md",
     file=local_archive_second_order_computation_path,
-    permissions=permissions,
+    permissions=permissions_local,
 )
 
 
 local_second_order_function_keys = {
-    client_id: clients[client_id].add_function(local_second_order_function)
-    for client_id in DATA_PROVIDER_ORGS_ID
+    client_id: clients[client_id].add_function(local_second_order_function) for client_id in DATA_PROVIDER_ORGS_ID
 }
 
 print(f"Local function key for step 2: computing second order moments {local_second_order_function_keys}")
@@ -379,25 +365,19 @@
 #
 
 data_manager_input = {
-    client_id: [InputRef(identifier="opener", asset_key=key)]
-    for client_id, key in dataset_keys.items()
+    client_id: [InputRef(identifier="opener", asset_key=key)] for client_id, key in dataset_keys.items()
 }
 
 datasample_inputs = {
-    client_id: [InputRef(identifier="datasamples", asset_key=key)]
-    for client_id, key in datasample_keys.items()
+    client_id: [InputRef(identifier="datasamples", asset_key=key)] for client_id, key in datasample_keys.items()
 }
 
 local_task_1_keys = {
     client_id: clients[client_id].add_task(
         TaskSpec(
             function_key=local_first_order_function_keys[client_id],
             inputs=data_manager_input[client_id] + datasample_inputs[client_id],
-            outputs={
-                "local_analytics_first_moments": ComputeTaskOutputSpec(
-                    permissions=permissions
-                )
-            },
+            outputs={"local_analytics_first_moments": ComputeTaskOutputSpec(permissions=permissions_aggregation)},
             worker=client_id,
         )
     )
@@ -429,7 +409,7 @@
 aggregation_task_1 = TaskSpec(
     function_key=aggregate_function_key,
     inputs=aggregation_1_inputs,
-    outputs={"shared_states": ComputeTaskOutputSpec(permissions=permissions)},
+    outputs={"shared_states": ComputeTaskOutputSpec(permissions=permissions_local)},
     worker=ANALYTICS_PROVIDER_ORG_ID,
 )
 
@@ -450,14 +430,8 @@
     client_id: clients[client_id].add_task(
         TaskSpec(
             function_key=local_second_order_function_keys[client_id],
-            inputs=data_manager_input[client_id]
-            + datasample_inputs[client_id]
-            + shared_inputs,
-            outputs={
-                "local_analytics_second_moments": ComputeTaskOutputSpec(
-                    permissions=permissions
-                )
-            },
+            inputs=data_manager_input[client_id] + datasample_inputs[client_id] + shared_inputs,
+            outputs={"local_analytics_second_moments": ComputeTaskOutputSpec(permissions=permissions_aggregation)},
             worker=client_id,
         )
     )
@@ -477,7 +451,7 @@
 aggregation_task_2 = TaskSpec(
     function_key=aggregate_function_key,
     inputs=aggregation_2_inputs,
-    outputs={"shared_states": ComputeTaskOutputSpec(permissions=permissions)},
+    outputs={"shared_states": ComputeTaskOutputSpec(permissions=permissions_local)},
     worker=ANALYTICS_PROVIDER_ORG_ID,
 )