semantic-link-labs 0.8.2__py3-none-any.whl → 0.8.3__py3-none-any.whl

sempy_labs/admin/_basic_functions.py

@@ -7,7 +7,6 @@ from sempy_labs._helper_functions import (
     resolve_workspace_name_and_id,
     pagination,
 )
-import datetime
 import numpy as np
 import pandas as pd
 import time
@@ -106,27 +105,28 @@ def assign_workspaces_to_capacity(
     if isinstance(workspace, str):
         workspace = [workspace]
 
-    dfC = fabric.list_capacities()
-    dfC_filt = dfC[dfC["Display Name"] == source_capacity]
-    source_capacity_id = dfC_filt["Id"].iloc[0]
+    dfC = list_capacities()
+    dfC_filt = dfC[dfC["Capacity Name"] == source_capacity]
+    source_capacity_id = dfC_filt["Capacity Id"].iloc[0]
 
-    dfC_filt = dfC[dfC["Display Name"] == target_capacity]
-    target_capacity_id = dfC_filt["Id"].iloc[0]
+    dfC_filt = dfC[dfC["Capacity Name"] == target_capacity]
+    target_capacity_id = dfC_filt["Capacity Id"].iloc[0]
 
     if workspace is None:
-        workspaces = fabric.list_workspaces(
-            filter=f"capacityId eq '{source_capacity_id.upper()}'"
-        )["Id"].values
+        # workspaces = fabric.list_workspaces(
+        #    filter=f"capacityId eq '{source_capacity_id.upper()}'"
+        # )["Id"].values
+        dfW = list_workspaces()
+        dfW = dfW[dfW["Capacity Id"].str.upper() == source_capacity_id.upper()]
+        workspaces = dfW["Id"].tolist()
     else:
-        dfW = fabric.list_workspaces()
-        workspaces = dfW[dfW["Name"].isin(workspace)]["Id"].values
+        dfW = list_workspaces()
+        workspaces = dfW[dfW["Name"].isin(workspace)]["Id"].tolist()
 
     workspaces = np.array(workspaces)
     batch_size = 999
     for i in range(0, len(workspaces), batch_size):
         batch = workspaces[i : i + batch_size].tolist()
-        batch_length = len(batch)
-        start_time = datetime.datetime.now()
         request_body = {
             "capacityMigrationAssignments": [
                 {
@@ -144,10 +144,6 @@ def assign_workspaces_to_capacity(
 
         if response.status_code != 200:
             raise FabricHTTPException(response)
-        end_time = datetime.datetime.now()
-        print(
-            f"Total time for assigning {str(batch_length)} workspaces is {str((end_time - start_time).total_seconds())}"
-        )
     print(
         f"{icons.green_dot} The workspaces have been assigned to the '{target_capacity}' capacity."
     )
@@ -157,9 +153,6 @@ def list_capacities() -> pd.DataFrame:
     """
     Shows the a list of capacities and their properties. This function is the admin version.
 
-    Parameters
-    ----------
-
     Returns
     -------
     pandas.DataFrame
@@ -488,7 +481,8 @@ def scan_workspaces(
     workspace: Optional[str | List[str]] = None,
 ) -> dict:
 
-    workspace = fabric.resolve_workspace_name(workspace)
+    if workspace is None:
+        workspace = fabric.resolve_workspace_name()
 
     if isinstance(workspace, str):
         workspace = [workspace]
@@ -886,3 +880,112 @@ def list_items(
             df = pd.concat([df, pd.DataFrame(new_data, index=[0])], ignore_index=True)
 
     return df
+
+
+def list_activity_events(
+    start_time: str,
+    end_time: str,
+    activity_filter: Optional[str] = None,
+    user_id_filter: Optional[str] = None,
+):
+    """
+    Shows a list of audit activity events for a tenant.
+
+    Parameters
+    ----------
+    start_time : str
+        Start date and time of the window for audit event results. Example: "2024-09-25T07:55:00".
+    end_time : str
+        End date and time of the window for audit event results. Example: "2024-09-25T08:55:00".
+    activity_filter : str, default=None
+        Filter value for activities. Example: 'viewreport'.
+    user_id_filter : str, default=None
+        Email address of the user.
+
+    Returns
+    -------
+    pandas.DataFrame
+        A pandas dataframe showing a list of audit activity events for a tenant.
+    """
+
+    # https://learn.microsoft.com/en-us/rest/api/power-bi/admin/get-activity-events
+
+    df = pd.DataFrame(
+        columns=[
+            "Id",
+            "Record Type",
+            "Creation Time",
+            "Operation",
+            "Organization Id",
+            "User Type",
+            "User Key",
+            "Workload",
+            "Result Status",
+            "User Id",
+            "Client IP",
+            "User Agent",
+            "Activity",
+            "Workspace Name",
+            "Workspace Id",
+            "Object Id",
+            "Request Id",
+            "Object Type",
+            "Object Display Name",
+            "Experience",
+            "Refresh Enforcement Policy",
+        ]
+    )
+
+    tic = "%27"
+    space = "%20"
+    client = fabric.PowerBIRestClient()
+    base_url = "/v1.0/myorg/admin/activityevents"
+    conditions = []
+
+    if activity_filter is not None:
+        conditions.append(f"Activity{space}eq{space}{tic}{activity_filter}{tic}")
+    if user_id_filter is not None:
+        conditions.append(f"UserId{space}eq{space}{tic}{user_id_filter}{tic}")
+
+    filter_value = (
+        f"&filter={f'{space}and{space}'.join(conditions)}" if conditions else ""
+    )
+
+    full_url = f"{base_url}?startDateTime={tic}{start_time}{tic}&endDateTime={tic}{end_time}{tic}{filter_value}"
+    response = client.get(full_url)
+    if response.status_code != 200:
+        raise FabricHTTPException(response)
+
+    responses = pagination(client, response)
+
+    for r in responses:
+        for i in r.get("activityEventEntities", []):
+            new_data = {
+                "Id": i.get("id"),
+                "Record Type": i.get("RecordType"),
+                "Creation Time": i.get("CreationTime"),
+                "Operation": i.get("Operation"),
+                "Organization Id": i.get("OrganizationId"),
+                "User Type": i.get("UserType"),
+                "User Key": i.get("UserKey"),
+                "Workload": i.get("Workload"),
+                "Result Status": i.get("ResultStatus"),
+                "User Id": i.get("UserId"),
+                "Client IP": i.get("ClientIP"),
+                "User Agent": i.get("UserAgent"),
+                "Activity": i.get("Activity"),
+                "Workspace Name": i.get("WorkSpaceName"),
+                "Workspace Id": i.get("WorkspaceId"),
+                "Object Id": i.get("ObjectId"),
+                "Request Id": i.get("RequestId"),
+                "Object Type": i.get("ObjectType"),
+                "Object Display Name": i.get("ObjectDisplayName"),
+                "Experience": i.get("Experience"),
+                "Refresh Enforcement Policy": i.get("RefreshEnforcementPolicy"),
+            }
+            df = pd.concat(
+                [df, pd.DataFrame(new_data, index=[0])],
+                ignore_index=True,
+            )
+
+    return df

sempy_labs/directlake/_directlake_schema_sync.py

@@ -56,11 +56,6 @@ def direct_lake_schema_sync(
         )
     lakehouse_workspace = fabric.resolve_workspace_name(lakehouse_workspace_id)
 
-    if artifact_type == "Warehouse":
-        raise ValueError(
-            f"{icons.red_dot} This function is only valid for Direct Lake semantic models which source from Fabric lakehouses (not warehouses)."
-        )
-
     lc = get_lakehouse_columns(lakehouse_name, lakehouse_workspace)
 
     with connect_semantic_model(

sempy_labs/directlake/_generate_shared_expression.py

@@ -11,7 +11,7 @@ from sempy.fabric.exceptions import FabricHTTPException
 
 def generate_shared_expression(
     item_name: Optional[str] = None,
-    item_type: Optional[str] = "Lakehouse",
+    item_type: str = "Lakehouse",
     workspace: Optional[str] = None,
 ) -> str:
     """

sempy_labs/directlake/_guardrails.py

@@ -72,7 +72,7 @@ def get_directlake_guardrails_for_sku(sku_size: str) -> pd.DataFrame:
     Parameters
     ----------
     sku_size : str
-        Sku size of a workspace/capacity
+        Sku size of a workspace/capacity.
 
     Returns
     -------

sempy_labs/directlake/_show_unsupported_directlake_objects.py

@@ -11,7 +11,7 @@ def show_unsupported_direct_lake_objects(
 ) -> Tuple[pd.DataFrame, pd.DataFrame, pd.DataFrame]:
     """
     Returns a list of a semantic model's objects which are not supported by Direct Lake based on
-     `official documentation <https://learn.microsoft.com/power-bi/enterprise/directlake-overview#known-issues-and-limitations>`_.
+    `official documentation <https://learn.microsoft.com/power-bi/enterprise/directlake-overview#known-issues-and-limitations>`_.
 
     Parameters
     ----------

sempy_labs/migration/_create_pqt_file.py

@@ -13,11 +13,11 @@ import sempy_labs._icons as icons
 def create_pqt_file(
     dataset: str,
     workspace: Optional[str] = None,
-    file_name: Optional[str] = "PowerQueryTemplate",
+    file_name: str = "PowerQueryTemplate",
 ):
     """
     Dynamically generates a `Power Query Template <https://learn.microsoft.com/power-query/power-query-template>`_ file based on the semantic model. The .pqt file is
-     saved within the Files section of your lakehouse.
+    saved within the Files section of your lakehouse.
 
     Dataflows Gen2 has a `limit of 50 tables <https://learn.microsoft.com/power-query/power-query-online-limits>`_. If there are more than 50 tables, this will save multiple Power Query Template
     files (with each file having a max of 50 tables).

sempy_labs/report/_generate_report.py

@@ -2,7 +2,6 @@ import sempy.fabric as fabric
 import pandas as pd
 import json
 import os
-import time
 from typing import Optional
 from sempy_labs._helper_functions import (
     resolve_workspace_name_and_id,
@@ -12,7 +11,6 @@ from sempy_labs._helper_functions import (
 )
 import sempy_labs._icons as icons
 from sempy._utils._log import log
-from sempy.fabric.exceptions import FabricHTTPException
 
 
 def create_report_from_reportjson(
@@ -113,7 +111,7 @@ def create_report_from_reportjson(
 
     response = client.post(f"/v1/workspaces/{workspace_id}/reports", json=request_body)
 
-    lro(client, response, status_codes=[201, 202])
+    lro(client, response, status_codes=[201, 202], return_status_code=True)
 
     print(
         f"{icons.green_dot} Succesfully created the '{report}' report within the '{workspace}' workspace."
@@ -313,50 +311,48 @@ def _create_report(
     dataset: str,
     dataset_workspace: Optional[str] = None,
     report_workspace: Optional[str] = None,
-    update_if_exists: bool = False,
+    overwrite: bool = False,
 ):
 
     from sempy_labs.report import report_rebind
 
     report_workspace = fabric.resolve_workspace_name(report_workspace)
     report_workspace_id = fabric.resolve_workspace_id(report_workspace)
-    client = fabric.FabricRestClient()
+    dataset_workspace = fabric.resolve_workspace_name(dataset_workspace)
 
     dfR = fabric.list_reports(workspace=report_workspace)
     dfR_filt = dfR[dfR["Name"] == report]
 
     updated_report = False
-
+    client = fabric.FabricRestClient()
     # Create report if it does not exist
     if len(dfR_filt) == 0:
         response = client.post(
             f"/v1/workspaces/{report_workspace_id}/reports",
             json=request_body,
-            lro_wait=True,
         )
-        if response.status_code not in [200, 201]:
-            raise FabricHTTPException(response)
+
+        lro(client, response, status_codes=[201, 202], return_status_code=True)
+
         print(
             f"{icons.green_dot} The '{report}' report has been created within the '{report_workspace}'"
         )
         updated_report = True
     # Update the report if it exists
-    elif len(dfR_filt) > 0 and update_if_exists:
+    elif len(dfR_filt) > 0 and overwrite:
         report_id = dfR_filt["Id"].iloc[0]
         response = client.post(
             f"/v1/workspaces/{report_workspace_id}/reports/{report_id}/updateDefinition",
             json=request_body,
-            lro_wait=True,
         )
-        if response.status_code not in [200, 201]:
-            raise FabricHTTPException(response)
+        lro(client, response, return_status_code=True)
         print(
             f"{icons.green_dot} The '{report}' report has been updated within the '{report_workspace}'"
         )
         updated_report = True
     else:
         raise ValueError(
-            f"{icons.red_dot} The '{report}' report within the '{report_workspace}' workspace already exists and it was selected not to update it if the report already exists."
+            f"{icons.red_dot} The '{report}' report within the '{report_workspace}' workspace already exists and the 'overwrite' parameter was set to False."
         )
 
     # Rebind the report to the semantic model to make sure it is pointed at the correct semantic model

sempy_labs/report/_report_bpa.py

@@ -10,6 +10,7 @@ from sempy_labs._helper_functions import (
     resolve_report_id,
     resolve_lakehouse_name,
     resolve_workspace_capacity,
+    _get_max_run_id,
 )
 from sempy_labs.lakehouse import get_lakehouse_tables, lakehouse_attached
 import sempy_labs._icons as icons
@@ -192,8 +193,6 @@ def run_report_bpa(
         return finalDF
 
     if export:
-        from pyspark.sql import SparkSession
-
         if not lakehouse_attached():
             raise ValueError(
                 f"{icons.red_dot} In order to export the BPA results, a lakehouse must be attached to the notebook."
@@ -202,7 +201,7 @@ def run_report_bpa(
         now = datetime.datetime.now()
         delta_table_name = "reportbparesults"
         lakehouse_id = fabric.get_lakehouse_id()
-        lake_workspace = fabric.get_workspace_id()
+        lake_workspace = fabric.resolve_workspace_name()
         lakehouse = resolve_lakehouse_name(
             lakehouse_id=lakehouse_id, workspace=lake_workspace
         )
@@ -210,15 +209,13 @@ def run_report_bpa(
         lakeT = get_lakehouse_tables(lakehouse=lakehouse, workspace=lake_workspace)
         lakeT_filt = lakeT[lakeT["Table Name"] == delta_table_name]
 
-        spark = SparkSession.builder.getOrCreate()
-        query = f"SELECT MAX(RunId) FROM {lakehouse}.{delta_table_name}"
-
         if len(lakeT_filt) == 0:
             runId = 1
         else:
-            dfSpark = spark.sql(query)
-            maxRunId = dfSpark.collect()[0][0]
-            runId = maxRunId + 1
+            max_run_id = _get_max_run_id(
+                lakehouse=lakehouse, table_name=delta_table_name
+            )
+            runId = max_run_id + 1
 
         export_df = finalDF.copy()
         capacity_id, capacity_name = resolve_workspace_capacity(workspace=workspace)
@@ -232,7 +229,7 @@ def run_report_bpa(
         export_df["Timestamp"] = now
         export_df["RunId"] = export_df["RunId"].astype(int)
 
-        export_df = [
+        export_df = export_df[
             [
                 "Capacity Name",
                 "Capacity Id",
@@ -249,6 +246,7 @@ def run_report_bpa(
                 "URL",
             ]
         ]
+
         save_as_delta_table(
             dataframe=export_df,
             delta_table_name=delta_table_name,

sempy_labs/report/_report_functions.py

@@ -181,6 +181,8 @@ def export_report(
     """
 
     # https://learn.microsoft.com/rest/api/power-bi/reports/export-to-file-in-group
+    # https://learn.microsoft.com/rest/api/power-bi/reports/get-export-to-file-status-in-group
+    # https://learn.microsoft.com/rest/api/power-bi/reports/get-file-of-export-to-file-in-group
 
     if not lakehouse_attached():
         raise ValueError(
@@ -222,7 +224,6 @@ def export_report(
     }
 
     export_format = export_format.upper()
-
     fileExt = validFormats.get(export_format)
     if fileExt is None:
         raise ValueError(
@@ -286,9 +287,6 @@ def export_report(
     reportId = dfI_filt["Id"].iloc[0]
     client = fabric.PowerBIRestClient()
 
-    dfVisual = list_report_visuals(report=report, workspace=workspace)
-    dfPage = list_report_pages(report=report, workspace=workspace)
-
     if (
         export_format in ["BMP", "EMF", "GIF", "JPEG", "TIFF"]
         and reportType == "PaginatedReport"
@@ -314,6 +312,7 @@ def export_report(
             request_body = {"format": export_format, "powerBIReportConfiguration": {}}
 
             request_body["powerBIReportConfiguration"]["pages"] = []
+            dfPage = list_report_pages(report=report, workspace=workspace)
 
             for page in page_name:
                 dfPage_filt = dfPage[dfPage["Page ID"] == page]
@@ -335,9 +334,11 @@ def export_report(
             request_body = {"format": export_format, "powerBIReportConfiguration": {}}
 
             request_body["powerBIReportConfiguration"]["pages"] = []
+            dfVisual = list_report_visuals(report=report, workspace=workspace)
             a = 0
             for page in page_name:
                 visual = visual_name[a]
+
                 dfVisual_filt = dfVisual[
                     (dfVisual["Page ID"] == page) & (dfVisual["Visual ID"] == visual)
                 ]
@@ -360,32 +361,25 @@ def export_report(
         request_body["powerBIReportConfiguration"]["reportLevelFilters"] = [
             report_level_filter
         ]
-    print(request_body)
-    response = client.post(
-        f"/v1.0/myorg/groups/{workspace_id}/reports/{reportId}/ExportTo",
-        json=request_body,
-    )
+
+    base_url = f"/v1.0/myorg/groups/{workspace_id}/reports/{reportId}"
+    response = client.post(f"{base_url}/ExportTo", json=request_body)
+
     if response.status_code == 202:
         response_body = json.loads(response.content)
-        exportId = response_body["id"]
-        response = client.get(
-            f"/v1.0/myorg/groups/{workspace_id}/reports/{reportId}/exports/{exportId}"
-        )
+        export_id = response_body["id"]
+        response = client.get(f"{base_url}/exports/{export_id}")
         response_body = json.loads(response.content)
         while response_body["status"] not in ["Succeeded", "Failed"]:
             time.sleep(3)
-            response = client.get(
-                f"/v1.0/myorg/groups/{workspace_id}/reports/{reportId}/exports/{exportId}"
-            )
+            response = client.get(f"{base_url}/exports/{export_id}")
             response_body = json.loads(response.content)
         if response_body["status"] == "Failed":
             raise ValueError(
                 f"{icons.red_dot} The export for the '{report}' report within the '{workspace}' workspace in the '{export_format}' format has failed."
             )
         else:
-            response = client.get(
-                f"/v1.0/myorg/groups/{workspace_id}/reports/{reportId}/exports/{exportId}/file"
-            )
+            response = client.get(f"{base_url}/exports/{export_id}/file")
             print(
                 f"{icons.in_progress} Saving the '{export_format}' export for the '{report}' report within the '{workspace}' workspace to the lakehouse..."
             )

sempy_labs/report/_report_rebind.py

@@ -1,5 +1,8 @@
 import sempy.fabric as fabric
-from sempy_labs._helper_functions import resolve_dataset_id, resolve_report_id
+from sempy_labs._helper_functions import (
+    resolve_dataset_id,
+    resolve_report_id,
+)
 from typing import Optional, List
 from sempy._utils._log import log
 import sempy_labs._icons as icons

sempy_labs/report/_reportwrapper.py

@@ -7,7 +7,7 @@ from sempy_labs._helper_functions import (
     _extract_json,
     _add_part,
     lro,
-    make_clickable,
+    # _make_clickable,
 )
 from typing import Optional, List
 import pandas as pd
@@ -370,7 +370,7 @@ class ReportWrapper:
             df = self._add_extended(dataframe=df)
 
         return df
-        # return df.style.format({"Page URL": make_clickable})
+        # return df.style.format({"Page URL": _make_clickable})
 
     def list_visual_filters(self, extended: bool = False) -> pd.DataFrame:
         """
@@ -642,7 +642,7 @@ class ReportWrapper:
         )
 
         return df
-        # return df.style.format({"Page URL": make_clickable})
+        # return df.style.format({"Page URL": _make_clickable})
 
     def list_visuals(self) -> pd.DataFrame:
         """