vantage6-algorithm-tools 5.0.0a0__tar.gz → 5.0.0a7__tar.gz

{vantage6-algorithm-tools-5.0.0a0/vantage6_algorithm_tools.egg-info → vantage6_algorithm_tools-5.0.0a7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
-Name: vantage6-algorithm-tools
-Version: 5.0.0a0
+Name: vantage6_algorithm_tools
+Version: 5.0.0a7
 Summary: Vantage6 algorithm tools
 Home-page: https://github.com/vantage6/vantage6
 Requires-Python: >=3.6

{vantage6-algorithm-tools-5.0.0a0 → vantage6_algorithm_tools-5.0.0a7}/setup.py

@@ -23,7 +23,7 @@ with codecs.open(version_path) as f:
 
 # setup the package
 setup(
-    name="vantage6-algorithm-tools",
+    name="vantage6_algorithm_tools",
     version=version_ns["__version__"],
     description="Vantage6 algorithm tools",
     long_description=long_description,

vantage6_algorithm_tools-5.0.0a7/vantage6/algorithm/client/__build__

@@ -0,0 +1 @@
+7

{vantage6-algorithm-tools-5.0.0a0 → vantage6_algorithm_tools-5.0.0a7}/vantage6/algorithm/client/__init__.py

@@ -1,4 +1,4 @@
-""" Client for the algorithm container to communicate with the vantage6 server. """
+"""Client for the algorithm container to communicate with the vantage6 server."""
 
 import jwt
 import json as json_lib
@@ -339,7 +339,7 @@ class AlgorithmClient(ClientBase):
 
         def create(
             self,
-            input_: bytes,
+            input_: dict,
             organizations: list[int] = None,
             name: str = "subtask",
             description: str = None,
@@ -353,8 +353,9 @@ class AlgorithmClient(ClientBase):
 
             Parameters
             ----------
-            input_ : bytes
-                Input to the task. Should be b64 encoded.
+            input_ : dict
+                Input to the task. This dictionary usually contains the algorithm method
+                to call and the arguments to pass to the method.
             organizations : list[int]
                 List of organization IDs that should execute the task.
             name: str, optional
@@ -626,23 +627,6 @@ class AlgorithmClient(ClientBase):
             """
             return self.parent.request(f"collaboration/{self.parent.collaboration_id}")
 
-    class Node(ClientBase.SubClient):
-        """
-        Get information about the node.
-        """
-
-        def get(self) -> dict:
-            """
-            Get the node data.
-
-            Returns
-            -------
-            dict
-                Dictionary containing data on the node this algorithm is
-                running on.
-            """
-            return self.parent.request(f"node/{self.parent.node_id}")
-
     class Study(ClientBase.SubClient):
         """
         Get information about the study or studies.

{vantage6-algorithm-tools-5.0.0a0 → vantage6_algorithm_tools-5.0.0a7}/vantage6/algorithm/decorator/action.py

@@ -67,7 +67,7 @@ def _convert_to_parquet(data: Any) -> pa.Table:
     SessionError
         If the DataFrame cannot be converted to a Parquet Table.
     DataTypeError
-        If the data extraction function returns an unsupported data frame type.
+        If the data extraction function returns an unsupported dataframe type.
     """
     info("Converting algorithm output to a Parquet Table.")
     match type(data):

{vantage6-algorithm-tools-5.0.0a0 → vantage6_algorithm_tools-5.0.0a7}/vantage6/algorithm/decorator/data.py

@@ -7,27 +7,26 @@ from vantage6.common.globals import ContainerEnvNames
 from vantage6.algorithm.tools.util import info, error, warn
 
 
-def _get_user_database_labels() -> list[str]:
+def _get_user_dataframes() -> list[str]:
     """
-    Get the database labels from the environment
+    Get the database names that the user requested from the environment
 
     Returns
     -------
     list[str]
-        List of database labels
+        List of database names
     """
-    # read the labels that the user requested, which is a comma-separated str of labels.
-    labels = os.environ[ContainerEnvNames.USER_REQUESTED_DATAFRAME_HANDLES.value]
-    return labels.split(",")
+    dfs = os.environ[ContainerEnvNames.USER_REQUESTED_DATAFRAMES.value]
+    return dfs.split(",")
 
 
-def _get_data_from_handle(label: str) -> pd.DataFrame:
+def _read_df_from_disk(df_name: str) -> pd.DataFrame:
     """
-    Load data from a database based on the label
+    Load data from a dataframe file
 
     Parameters
     ----------
-    label : str
+    df_name : str
         Label of the database to load
 
     Returns
@@ -35,14 +34,14 @@ def _get_data_from_handle(label: str) -> pd.DataFrame:
     pd.DataFrame
         Data from the database
     """
-    # Load the dataframe by the user specified handle. The dataframes are always stored
+    # Load the dataframe by the user specified df name. The dataframes are always stored
     # in the session folder, which is set by the vantage6 node. The label is the name of
     # the dataframe file, which is set by the user when creating the task.
     dataframe_folder = os.environ[ContainerEnvNames.SESSION_FOLDER.value]
-    dataframe_uri = os.path.join(dataframe_folder, f"{label}.parquet")
-    info(f"Using '{dataframe_uri}' with label '{label}' as database")
+    dataframe_file = os.path.join(dataframe_folder, f"{df_name}.parquet")
+    info(f"Using '{dataframe_file}' with dataframe name '{df_name}' as database")
 
-    return pd.read_parquet(dataframe_uri)
+    return pd.read_parquet(dataframe_file)
 
 
 def data(number_of_databases: int = 1) -> callable:
@@ -97,30 +96,30 @@ def data(number_of_databases: int = 1) -> callable:
             if mock_data is not None:
                 return func(*mock_data, *args, **kwargs)
 
-            # read the labels that the user requested
-            labels = _get_user_database_labels()
+            # get the dataframe names that the user requested
+            dataframes = _get_user_dataframes()
 
             # check if user provided enough databases
-            if len(labels) < number_of_databases:
+            if len(dataframes) < number_of_databases:
                 error(
                     f"Algorithm requires {number_of_databases} databases "
-                    f"but only {len(labels)} were provided. "
+                    f"but only {len(dataframes)} were provided. "
                     "Exiting..."
                 )
                 exit(1)
-            elif len(labels) > number_of_databases:
+            elif len(dataframes) > number_of_databases:
                 warn(
                     f"Algorithm requires only {number_of_databases} databases"
-                    f", but {len(labels)} were provided. Using the "
+                    f", but {len(dataframes)} were provided. Using the "
                     f"first {number_of_databases} databases."
                 )
 
             for i in range(number_of_databases):
 
-                label = labels[i]
+                dataframe_name = dataframes[i]
                 # read the data from the database
-                info("Reading data frame")
-                data_ = _get_data_from_handle(label)
+                info("Reading dataframe")
+                data_ = _read_df_from_disk(dataframe_name)
 
                 # add the data to the arguments
                 args = (data_, *args)

{vantage6-algorithm-tools-5.0.0a0 → vantage6_algorithm_tools-5.0.0a7}/vantage6/algorithm/tools/__init__.py

@@ -1,5 +1,4 @@
-""" Algorithm tools to support the development of algorithms for the vantage6 platform.
-"""
+"""Algorithm tools to support the development of algorithms for the vantage6 platform."""
 
 # make sure the version is available
 from vantage6.algorithm.client._version import __version__  # noqa: F401

{vantage6-algorithm-tools-5.0.0a0 → vantage6_algorithm_tools-5.0.0a7}/vantage6/algorithm/tools/mock_client.py

@@ -104,9 +104,9 @@ class MockAlgorithmClient:
             self.organizations_with_data.append(org_id)
             org_data = []
             for dataset in org_datasets:
-                db_handle = dataset.get("database")
-                if isinstance(db_handle, pd.DataFrame):
-                    df = db_handle
+                db = dataset.get("database")
+                if isinstance(db, pd.DataFrame):
+                    df = db
                 else:
                     df = load_data(
                         database_uri=dataset.get("database"),
@@ -542,51 +542,6 @@ class MockAlgorithmClient:
                 "organizations": f"/api/organization?collaboration_id={collab_id}",
             }
 
-    class Node(SubClient):
-        """
-        Node subclient for the MockAlgorithmClient
-        """
-
-        def get(self, is_online: bool = True) -> dict:
-            """
-            Get mocked node
-
-            Parameters
-            ----------
-            is_online : bool
-                Whether the node is online or not. Default True.
-
-            Returns
-            -------
-            dict
-                A mocked node.
-            """
-            node_id = self.parent.node_id
-            collab_id = self.parent.collaboration_id
-            return {
-                "id": node_id,
-                "name": "mock-node",
-                "status": (
-                    AuthStatus.ONLINE.value if is_online else AuthStatus.OFFLINE.value
-                ),
-                "ip": "1.2.3.4",
-                "config": {
-                    "key": "value",
-                },
-                "collaboration": {
-                    "id": collab_id,
-                    "link": f"/api/collaboration/{collab_id}",
-                    "methods": ["DELETE", "PATCH", "GET"],
-                },
-                "last_seen": "2021-01-01T00:00:00.000000",
-                "type": "node",
-                "organization": {
-                    "id": node_id,
-                    "link": f"/api/organization/{node_id}",
-                    "methods": ["GET", "PATCH"],
-                },
-            }
-
     # TODO implement the get_addresses method before using this part
     # class VPN(SubClient):
     #     """

{vantage6-algorithm-tools-5.0.0a0 → vantage6_algorithm_tools-5.0.0a7}/vantage6/algorithm/tools/wrap.py

@@ -57,6 +57,7 @@ def wrap_algorithm(log_traceback: bool = True) -> None:
 
     # read input from the mounted input file.
     input_file = os.environ[ContainerEnvNames.INPUT_FILE.value]
+
     info(f"Reading input file {input_file}")
     input_data = load_input(input_file)
 

{vantage6-algorithm-tools-5.0.0a0 → vantage6_algorithm_tools-5.0.0a7/vantage6_algorithm_tools.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: vantage6-algorithm-tools
-Version: 5.0.0a0
+Version: 5.0.0a7
 Summary: Vantage6 algorithm tools
 Home-page: https://github.com/vantage6/vantage6
 Requires-Python: >=3.6

{vantage6-algorithm-tools-5.0.0a0 → vantage6_algorithm_tools-5.0.0a7}/vantage6_algorithm_tools.egg-info/requires.txt

@@ -5,7 +5,7 @@ pyfiglet==0.8.post1
 SPARQLWrapper>=2.0.0
 sqlalchemy>=1.4.46
 pyarrow>=16.1.0
-vantage6-common==5.0.0.a0
+vantage6-common==5.0.0.a7
 
 [dev]
 black

vantage6-algorithm-tools-5.0.0a0/vantage6/algorithm/client/__build__

@@ -1 +0,0 @@
-0