semantic-link-labs 0.9.2__py3-none-any.whl → 0.9.4__py3-none-any.whl

sempy_labs/_eventhouses.py

@@ -7,12 +7,18 @@ from sempy_labs._helper_functions import (
     _print_success,
     resolve_item_id,
     _create_dataframe,
+    _conv_b64,
+    _decode_b64,
 )
 from uuid import UUID
+import sempy_labs._icons as icons
 
 
 def create_eventhouse(
-    name: str, description: Optional[str] = None, workspace: Optional[str | UUID] = None
+    name: str,
+    definition: Optional[dict],
+    description: Optional[str] = None,
+    workspace: Optional[str | UUID] = None,
 ):
     """
     Creates a Fabric eventhouse.
@@ -23,6 +29,8 @@ def create_eventhouse(
     ----------
     name: str
         Name of the eventhouse.
+    definition : dict
+        The definition (EventhouseProperties.json) of the eventhouse.
     description : str, default=None
         A description of the environment.
     workspace : str | uuid.UUID, default=None
@@ -38,6 +46,20 @@ def create_eventhouse(
     if description:
         payload["description"] = description
 
+    if definition is not None:
+        if not isinstance(definition, dict):
+            raise ValueError(f"{icons.red_dot} The definition must be a dictionary.")
+
+        payload["definition"] = {
+            "parts": [
+                {
+                    "path": "EventhouseProperties.json",
+                    "payload": _conv_b64(definition),
+                    "payloadType": "InlineBase64",
+                }
+            ]
+        }
+
     _base_api(
         request=f"/v1/workspaces/{workspace_id}/eventhouses",
         method="post",
@@ -123,3 +145,50 @@ def delete_eventhouse(name: str, workspace: Optional[str | UUID] = None):
         workspace_name=workspace_name,
         action="deleted",
     )
+
+
+def get_eventhouse_definition(
+    eventhouse: str | UUID,
+    workspace: Optional[str | UUID] = None,
+    return_dataframe: bool = False,
+) -> dict | pd.DataFrame:
+    """
+    Gets the eventhouse definition.
+
+    This is a wrapper function for the following API: `Items - Get Eventhouse Definition <https://learn.microsoft.com/rest/api/fabric/eventhouse/items/get-eventhouse-definition>`_.
+
+    Parameters
+    ----------
+    eventhouse : str
+        Name of the eventhouse.
+    workspace : str | uuid.UUID, default=None
+        The Fabric workspace name or ID in which the eventhouse resides.
+        Defaults to None which resolves to the workspace of the attached lakehouse
+        or if no lakehouse attached, resolves to the workspace of the notebook.
+    return_dataframe : bool, default=False
+        If True, returns a dataframe. If False, returns a json dictionary.
+
+    Returns
+    -------
+    dict | pandas.DataFrame
+        The eventhouse definition in .json format or as a pandas dataframe.
+    """
+
+    (workspace_name, workspace_id) = resolve_workspace_name_and_id(workspace)
+    item_id = resolve_item_id(item=eventhouse, type="Eventhouse", workspace=workspace)
+
+    result = _base_api(
+        request=f"/v1/workspaces/{workspace_id}/eventhouses/{item_id}/getDefinition",
+        method="post",
+        status_codes=None,
+        lro_return_json=True,
+    )
+
+    df = pd.json_normalize(result["definition"]["parts"])
+
+    if return_dataframe:
+        return df
+    else:
+        df_filt = df[df["path"] == "EventhouseProperties.json"]
+        payload = df_filt["payload"].iloc[0]
+        return _decode_b64(payload)

sempy_labs/_gateways.py

@@ -21,6 +21,8 @@ def list_gateways() -> pd.DataFrame:
 
     This is a wrapper function for the following API: `Gateways - List Gateways <https://learn.microsoft.com/rest/api/fabric/core/gateways/list-gateways>`_.
 
+    Service Principal Authentication is supported (see `here <https://github.com/microsoft/semantic-link-labs/blob/main/notebooks/Service%20Principal.ipynb>`_ for examples).
+
     Returns
     -------
     pandas.DataFrame
@@ -41,7 +43,9 @@ def list_gateways() -> pd.DataFrame:
     }
     df = _create_dataframe(columns=columns)
 
-    responses = _base_api(request="/v1/gateways", uses_pagination=True)
+    responses = _base_api(
+        request="/v1/gateways", client="fabric_sp", uses_pagination=True
+    )
 
     for r in responses:
         for v in r.get("value", []):
@@ -85,6 +89,8 @@ def delete_gateway(gateway: str | UUID):
 
     This is a wrapper function for the following API: `Gateways - Delete Gateway <https://learn.microsoft.com/rest/api/fabric/core/gateways/delete-gateway>`_.
 
+    Service Principal Authentication is supported (see `here <https://github.com/microsoft/semantic-link-labs/blob/main/notebooks/Service%20Principal.ipynb>`_ for examples).
+
     Parameters
     ----------
     gateway : str | uuid.UUID
@@ -92,7 +98,7 @@ def delete_gateway(gateway: str | UUID):
     """
 
     gateway_id = _resolve_gateway_id(gateway)
-    _base_api(request=f"/v1/gateways/{gateway_id}", method="delete")
+    _base_api(request=f"/v1/gateways/{gateway_id}", client="fabric_sp", method="delete")
     print(f"{icons.green_dot} The '{gateway}' gateway has been deleted.")
 
 
@@ -102,6 +108,8 @@ def list_gateway_role_assigments(gateway: str | UUID) -> pd.DataFrame:
 
     This is a wrapper function for the following API: `Gateways - List Gateway Role Assignments <https://learn.microsoft.com/rest/api/fabric/core/gateways/list-gateway-role-assignments>`_.
 
+    Service Principal Authentication is supported (see `here <https://github.com/microsoft/semantic-link-labs/blob/main/notebooks/Service%20Principal.ipynb>`_ for examples).
+
     Parameters
     ----------
     gateway : str | uuid.UUID
@@ -122,7 +130,9 @@ def list_gateway_role_assigments(gateway: str | UUID) -> pd.DataFrame:
     df = _create_dataframe(columns=columns)
     gateway_id = _resolve_gateway_id(gateway)
     responses = _base_api(
-        request=f"/v1/gateways/{gateway_id}/roleAssignments", uses_pagination=True
+        request=f"/v1/gateways/{gateway_id}/roleAssignments",
+        client="fabric_sp",
+        uses_pagination=True,
     )
 
     for r in responses:
@@ -145,6 +155,8 @@ def delete_gateway_role_assignment(gateway: str | UUID, role_assignment_id: UUID
 
     This is a wrapper function for the following API: `Gateways - Delete Gateway Role Assignment <https://learn.microsoft.com/rest/api/fabric/core/gateways/delete-gateway-role-assignment>`_.
 
+    Service Principal Authentication is supported (see `here <https://github.com/microsoft/semantic-link-labs/blob/main/notebooks/Service%20Principal.ipynb>`_ for examples).
+
     Parameters
     ----------
     gateway : str | uuid.UUID
@@ -156,6 +168,7 @@ def delete_gateway_role_assignment(gateway: str | UUID, role_assignment_id: UUID
     gateway_id = _resolve_gateway_id(gateway)
     _base_api(
         request=f"/v1/gateways/{gateway_id}/roleAssignments/{role_assignment_id}",
+        client="fabric_sp",
         method="delete",
     )
 
@@ -187,6 +200,8 @@ def delete_gateway_member(gateway: str | UUID, gateway_member: str | UUID):
 
     This is a wrapper function for the following API: `Gateways - Delete Gateway Member <https://learn.microsoft.com/rest/api/fabric/core/gateways/delete-gateway-member>`_.
 
+    Service Principal Authentication is supported (see `here <https://github.com/microsoft/semantic-link-labs/blob/main/notebooks/Service%20Principal.ipynb>`_ for examples).
+
     Parameters
     ----------
     gateway : str | uuid.UUID
@@ -200,7 +215,11 @@ def delete_gateway_member(gateway: str | UUID, gateway_member: str | UUID):
         gateway=gateway_id, gateway_member=gateway_member
     )
 
-    _base_api(request=f"/v1/gateways/{gateway_id}/members/{member_id}", method="delete")
+    _base_api(
+        request=f"/v1/gateways/{gateway_id}/members/{member_id}",
+        client="fabric_sp",
+        method="delete",
+    )
     print(
         f"{icons.green_dot} The '{member_id}' member for the '{gateway}' gateway has been deleted."
     )
@@ -212,6 +231,8 @@ def list_gateway_members(gateway: str | UUID) -> pd.DataFrame:
 
     This is a wrapper function for the following API: `Gateways - List Gateway Members <https://learn.microsoft.com/rest/api/fabric/core/gateways/list-gateway-members>`_.
 
+    Service Principal Authentication is supported (see `here <https://github.com/microsoft/semantic-link-labs/blob/main/notebooks/Service%20Principal.ipynb>`_ for examples).
+
     Parameters
     ----------
     gateway : str | uuid.UUID
@@ -235,7 +256,9 @@ def list_gateway_members(gateway: str | UUID) -> pd.DataFrame:
     }
     df = _create_dataframe(columns=columns)
 
-    response = _base_api(request=f"/v1/gateways/{gateway_id}/members")
+    response = _base_api(
+        request=f"/v1/gateways/{gateway_id}/members", client="fabric_sp"
+    )
 
     for v in response.json().get("value", []):
         new_data = {
@@ -269,6 +292,8 @@ def create_vnet_gateway(
 
     This is a wrapper function for the following API: `Gateways - Create Gateway <https://learn.microsoft.com/rest/api/fabric/core/gateways/create-gateway>`_.
 
+    Service Principal Authentication is supported (see `here <https://github.com/microsoft/semantic-link-labs/blob/main/notebooks/Service%20Principal.ipynb>`_ for examples).
+
     Parameters
     ----------
     name : str
@@ -304,7 +329,13 @@ def create_vnet_gateway(
         "numberOfMemberGateways": number_of_member_gateways,
     }
 
-    _base_api(request="/v1/gateways", method="post", payload=payload, status_codes=201)
+    _base_api(
+        request="/v1/gateways",
+        client="fabric_sp",
+        method="post",
+        payload=payload,
+        status_codes=201,
+    )
 
     print(
         f"{icons.green_dot} The '{name}' gateway was created within the '{capacity}' capacity."
@@ -322,6 +353,8 @@ def update_on_premises_gateway(
 
     This is a wrapper function for the following API: `Gateways - Update Gateway <https://learn.microsoft.com/rest/api/fabric/core/gateways/update-gateway>`_.
 
+    Service Principal Authentication is supported (see `here <https://github.com/microsoft/semantic-link-labs/blob/main/notebooks/Service%20Principal.ipynb>`_ for examples).
+
     Parameters
     ----------
     gateway : str | uuid.UUID
@@ -352,7 +385,12 @@ def update_on_premises_gateway(
 
     payload["type"] = "OnPremises"
 
-    _base_api(request=f"/v1/gateways/{gateway_id}", method="patch", payload=payload)
+    _base_api(
+        request=f"/v1/gateways/{gateway_id}",
+        client="fabric_sp",
+        method="patch",
+        payload=payload,
+    )
 
     print(f"{icons.green_dot} The '{gateway}' has been updated accordingly.")
 
@@ -368,6 +406,8 @@ def update_vnet_gateway(
 
     This is a wrapper function for the following API: `Gateways - Update Gateway <https://learn.microsoft.com/rest/api/fabric/core/gateways/update-gateway>`_.
 
+    Service Principal Authentication is supported (see `here <https://github.com/microsoft/semantic-link-labs/blob/main/notebooks/Service%20Principal.ipynb>`_ for examples).
+
     Parameters
     ----------
     gateway : str | uuid.UUID
@@ -399,7 +439,12 @@ def update_vnet_gateway(
 
     payload["type"] = "VirtualNetwork"
 
-    _base_api(request=f"/v1/gateways/{gateway_id}", method="patch", payload=payload)
+    _base_api(
+        request=f"/v1/gateways/{gateway_id}",
+        client="fabric_sp",
+        method="patch",
+        payload=payload,
+    )
     print(f"{icons.green_dot} The '{gateway}' has been updated accordingly.")
 
 
@@ -411,6 +456,8 @@ def bind_semantic_model_to_gateway(
 
     This is a wrapper function for the following API: `Datasets - Bind To Gateway In Group <https://learn.microsoft.com/rest/api/power-bi/datasets/bind-to-gateway-in-group>`_.
 
+    Service Principal Authentication is supported (see `here <https://github.com/microsoft/semantic-link-labs/blob/main/notebooks/Service%20Principal.ipynb>`_ for examples).
+
     Parameters
     ----------
     dataset : str | uuid.UUID
@@ -435,6 +482,7 @@ def bind_semantic_model_to_gateway(
 
     _base_api(
         request=f"/v1.0/myorg/groups/{workspace_id}/datasets/{dataset_id}/Default.BindToGateway",
+        client="fabric_sp",
         method="post",
         payload=payload,
     )

sempy_labs/_generate_semantic_model.py

@@ -11,6 +11,7 @@ from sempy_labs._helper_functions import (
     _conv_b64,
     _decode_b64,
     _base_api,
+    _mount,
 )
 from sempy_labs.lakehouse._lakehouse import lakehouse_attached
 import sempy_labs._icons as icons
@@ -252,6 +253,7 @@ def deploy_semantic_model(
     target_workspace: Optional[str | UUID] = None,
     refresh_target_dataset: bool = True,
     overwrite: bool = False,
+    perspective: Optional[str] = None,
 ):
     """
     Deploys a semantic model based on an existing semantic model.
@@ -274,6 +276,8 @@ def deploy_semantic_model(
         If set to True, this will initiate a full refresh of the target semantic model in the target workspace.
     overwrite : bool, default=False
         If set to True, overwrites the existing semantic model in the workspace if it exists.
+    perspective : str, default=None
+        Set this to the name of a perspective in the model and it will reduce the deployed model down to the tables/columns/measures/hierarchies within that perspective.
     """
 
     (source_workspace_name, source_workspace_id) = resolve_workspace_name_and_id(
@@ -307,7 +311,21 @@ def deploy_semantic_model(
             f"{icons.warning} The '{target_dataset}' semantic model already exists within the '{target_workspace_name}' workspace. The 'overwrite' parameter is set to False so the source semantic model was not deployed to the target destination."
         )
 
-    bim = get_semantic_model_bim(dataset=source_dataset, workspace=source_workspace_id)
+    if perspective is not None:
+
+        from sempy_labs.tom import connect_semantic_model
+
+        with connect_semantic_model(
+            dataset=source_dataset, workspace=source_workspace, readonly=True
+        ) as tom:
+
+            df_added = tom._reduce_model(perspective_name=perspective)
+            bim = tom.get_bim()
+
+    else:
+        bim = get_semantic_model_bim(
+            dataset=source_dataset, workspace=source_workspace_id
+        )
 
     # Create the semantic model if the model does not exist
     if dfD_filt.empty:
@@ -325,6 +343,9 @@ def deploy_semantic_model(
     if refresh_target_dataset:
         refresh_semantic_model(dataset=target_dataset, workspace=target_workspace_id)
 
+    if perspective is not None:
+        return df_added
+
 
 @log
 def get_semantic_model_bim(
@@ -368,16 +389,16 @@ def get_semantic_model_bim(
                 f"{icons.red_dot} In order to save the model.bim file, a lakehouse must be attached to the notebook. Please attach a lakehouse to this notebook."
             )
 
-        lakehouse = resolve_lakehouse_name()
-        folderPath = "/lakehouse/default/Files"
-        fileExt = ".bim"
-        if not save_to_file_name.endswith(fileExt):
-            save_to_file_name = f"{save_to_file_name}{fileExt}"
-        filePath = os.path.join(folderPath, save_to_file_name)
-        with open(filePath, "w") as json_file:
+        local_path = _mount()
+        save_folder = f"{local_path}/Files"
+        file_ext = ".bim"
+        if not save_to_file_name.endswith(file_ext):
+            save_to_file_name = f"{save_to_file_name}{file_ext}"
+        file_path = os.path.join(save_folder, save_to_file_name)
+        with open(file_path, "w") as json_file:
             json.dump(bimJson, json_file, indent=4)
         print(
-            f"{icons.green_dot} The {fileExt} file for the '{dataset_name}' semantic model has been saved to the '{lakehouse}' in this location: '{filePath}'.\n\n"
+            f"{icons.green_dot} The {file_ext} file for the '{dataset_name}' semantic model has been saved to the lakehouse attached to the notebook within: 'Files/{save_to_file_name}'.\n\n"
         )
 
     return bimJson

sempy_labs/_helper_functions.py

@@ -31,7 +31,9 @@ def _build_url(url: str, params: dict) -> str:
 
 
 def create_abfss_path(
-    lakehouse_id: UUID, lakehouse_workspace_id: UUID, delta_table_name: str
+    lakehouse_id: UUID,
+    lakehouse_workspace_id: UUID,
+    delta_table_name: Optional[str] = None,
 ) -> str:
     """
     Creates an abfss path for a delta table in a Fabric lakehouse.
@@ -42,18 +44,22 @@ def create_abfss_path(
         ID of the Fabric lakehouse.
     lakehouse_workspace_id : uuid.UUID
         ID of the Fabric workspace.
-    delta_table_name : str
+    delta_table_name : str, default=None
         Name of the delta table name.
 
     Returns
     -------
     str
-        An abfss path which can be used to save/reference a delta table in a Fabric lakehouse.
+        An abfss path which can be used to save/reference a delta table in a Fabric lakehouse or lakehouse.
     """
 
     fp = _get_default_file_path()
+    path = f"abfss://{lakehouse_workspace_id}@{fp}/{lakehouse_id}"
+
+    if delta_table_name is not None:
+        path += f"/Tables/{delta_table_name}"
 
-    return f"abfss://{lakehouse_workspace_id}@{fp}/{lakehouse_id}/Tables/{delta_table_name}"
+    return path
 
 
 def _get_default_file_path() -> str:
@@ -506,7 +512,6 @@ def save_as_delta_table(
         or if no lakehouse attached, resolves to the workspace of the notebook.
     """
 
-    from pyspark.sql import SparkSession
     from pyspark.sql.types import (
         StringType,
         IntegerType,
@@ -538,8 +543,9 @@ def save_as_delta_table(
             f"{icons.red_dot} Invalid 'delta_table_name'. Delta tables in the lakehouse cannot have spaces in their names."
         )
 
-    dataframe.columns = dataframe.columns.str.replace(" ", "_")
-    spark = SparkSession.builder.getOrCreate()
+    dataframe.columns = [col.replace(" ", "_") for col in dataframe.columns]
+
+    spark = _create_spark_session()
 
     type_mapping = {
         "string": StringType(),
@@ -1248,7 +1254,6 @@ def _get_column_aggregate(
     default_value: int = 0,
 ) -> int:
 
-    from pyspark.sql import SparkSession
     from pyspark.sql.functions import approx_count_distinct
     from pyspark.sql import functions as F
 
@@ -1257,7 +1262,7 @@ def _get_column_aggregate(
     lakehouse_id = resolve_lakehouse_id(lakehouse, workspace)
     path = create_abfss_path(lakehouse_id, workspace_id, table_name)
 
-    spark = SparkSession.builder.getOrCreate()
+    spark = _create_spark_session()
     df = spark.read.format("delta").load(path)
 
     if function in {"COUNTDISTINCT", "DISTINCTCOUNT"}:
@@ -1591,3 +1596,73 @@ def _print_success(item_name, item_type, workspace_name, action="created"):
         )
     else:
         raise NotImplementedError
+
+
+def _pure_python_notebook() -> bool:
+
+    from sempy.fabric._environment import _on_jupyter
+
+    return _on_jupyter()
+
+
+def _create_spark_session():
+
+    if _pure_python_notebook():
+        raise ValueError(
+            f"{icons.red_dot} This function is only available in a PySpark notebook."
+        )
+
+    from pyspark.sql import SparkSession
+
+    return SparkSession.builder.getOrCreate()
+
+
+def _read_delta_table(path: str):
+
+    spark = _create_spark_session()
+
+    return spark.read.format("delta").load(path)
+
+
+def _delta_table_row_count(table_name: str) -> int:
+
+    spark = _create_spark_session()
+
+    return spark.table(table_name).count()
+
+
+def _run_spark_sql_query(query):
+
+    spark = _create_spark_session()
+
+    return spark.sql(query)
+
+
+def _mount(lakehouse, workspace) -> str:
+    """
+    Mounts a lakehouse to a notebook if it is not already mounted. Returns the local path to the lakehouse.
+    """
+
+    import notebookutils
+
+    (workspace_name, workspace_id) = resolve_workspace_name_and_id(workspace=workspace)
+    (lakehouse_name, lakehouse_id) = resolve_lakehouse_name_and_id(
+        lakehouse=lakehouse, workspace=workspace
+    )
+
+    lake_path = create_abfss_path(lakehouse_id, workspace_id)
+    mounts = notebookutils.fs.mounts()
+    mount_point = f"/{workspace_name.replace(' ', '')}{lakehouse_name.replace(' ', '')}"
+    if not any(i.get("source") == lake_path for i in mounts):
+        # Mount lakehouse if not mounted
+        notebookutils.fs.mount(lake_path, mount_point)
+        print(
+            f"{icons.green_dot} Mounted the '{lakehouse_name}' lakehouse within the '{workspace_name}' to the notebook."
+        )
+
+    mounts = notebookutils.fs.mounts()
+    local_path = next(
+        i.get("localPath") for i in mounts if i.get("source") == lake_path
+    )
+
+    return local_path