semantic-link-labs 0.8.0__py3-none-any.whl → 0.8.1__py3-none-any.whl

sempy_labs/_warehouses.py

@@ -0,0 +1,132 @@
+import sempy.fabric as fabric
+from sempy_labs._helper_functions import (
+    resolve_workspace_name_and_id,
+    pagination,
+    lro,
+)
+import pandas as pd
+from typing import Optional
+import sempy_labs._icons as icons
+from sempy.fabric.exceptions import FabricHTTPException
+
+
+def create_warehouse(
+    warehouse: str, description: Optional[str] = None, workspace: Optional[str] = None
+):
+    """
+    Creates a Fabric warehouse.
+
+    Parameters
+    ----------
+    warehouse: str
+        Name of the warehouse.
+    description : str, default=None
+        A description of the warehouse.
+    workspace : str, default=None
+        The Fabric workspace name.
+        Defaults to None which resolves to the workspace of the attached lakehouse
+        or if no lakehouse attached, resolves to the workspace of the notebook.
+    """
+
+    (workspace, workspace_id) = resolve_workspace_name_and_id(workspace)
+
+    request_body = {"displayName": warehouse}
+
+    if description:
+        request_body["description"] = description
+
+    client = fabric.FabricRestClient()
+    response = client.post(
+        f"/v1/workspaces/{workspace_id}/warehouses/", json=request_body
+    )
+
+    lro(client, response, status_codes=[201, 202])
+
+    print(
+        f"{icons.green_dot} The '{warehouse}' warehouse has been created within the '{workspace}' workspace."
+    )
+
+
+def list_warehouses(workspace: Optional[str] = None) -> pd.DataFrame:
+    """
+    Shows the warehouses within a workspace.
+
+    Parameters
+    ----------
+    workspace : str, default=None
+        The Fabric workspace name.
+        Defaults to None which resolves to the workspace of the attached lakehouse
+        or if no lakehouse attached, resolves to the workspace of the notebook.
+
+    Returns
+    -------
+    pandas.DataFrame
+        A pandas dataframe showing the warehouses within a workspace.
+    """
+
+    df = pd.DataFrame(
+        columns=[
+            "Warehouse Name",
+            "Warehouse Id",
+            "Description",
+            "Connection Info",
+            "Created Date",
+            "Last Updated Time",
+        ]
+    )
+
+    (workspace, workspace_id) = resolve_workspace_name_and_id(workspace)
+
+    client = fabric.FabricRestClient()
+    response = client.get(f"/v1/workspaces/{workspace_id}/warehouses")
+    if response.status_code != 200:
+        raise FabricHTTPException(response)
+
+    responses = pagination(client, response)
+
+    for r in responses:
+        for v in r.get("value", []):
+            prop = v.get("properties", {})
+
+            new_data = {
+                "Warehouse Name": v.get("displayName"),
+                "Warehouse Id": v.get("id"),
+                "Description": v.get("description"),
+                "Connection Info": prop.get("connectionInfo"),
+                "Created Date": prop.get("createdDate"),
+                "Last Updated Time": prop.get("lastUpdatedTime"),
+            }
+            df = pd.concat([df, pd.DataFrame(new_data, index=[0])], ignore_index=True)
+
+    return df
+
+
+def delete_warehouse(name: str, workspace: Optional[str] = None):
+    """
+    Deletes a Fabric warehouse.
+
+    Parameters
+    ----------
+    name: str
+        Name of the warehouse.
+    workspace : str, default=None
+        The Fabric workspace name.
+        Defaults to None which resolves to the workspace of the attached lakehouse
+        or if no lakehouse attached, resolves to the workspace of the notebook.
+    """
+
+    (workspace, workspace_id) = resolve_workspace_name_and_id(workspace)
+
+    item_id = fabric.resolve_item_id(
+        item_name=name, type="Warehouse", workspace=workspace
+    )
+
+    client = fabric.FabricRestClient()
+    response = client.delete(f"/v1/workspaces/{workspace_id}/warehouses/{item_id}")
+
+    if response.status_code != 200:
+        raise FabricHTTPException(response)
+
+    print(
+        f"{icons.green_dot} The '{name}' warehouse within the '{workspace}' workspace has been deleted."
+    )

sempy_labs/_workspaces.py

@@ -22,9 +22,6 @@ def delete_user_from_workspace(email_address: str, workspace: Optional[str] = No
         The name of the workspace.
         Defaults to None which resolves to the workspace of the attached lakehouse
         or if no lakehouse attached, resolves to the workspace of the notebook.
-
-    Returns
-    -------
     """
 
     (workspace, workspace_id) = resolve_workspace_name_and_id(workspace)

sempy_labs/admin/_basic_functions.py

@@ -3,7 +3,10 @@ from typing import Optional, List, Union
 from uuid import UUID
 import sempy_labs._icons as icons
 from sempy.fabric.exceptions import FabricHTTPException
-from sempy_labs._helper_functions import resolve_workspace_name_and_id, pagination
+from sempy_labs._helper_functions import (
+    resolve_workspace_name_and_id,
+    pagination,
+)
 import datetime
 import numpy as np
 import pandas as pd
@@ -387,7 +390,7 @@ def revoke_external_data_share(
 
 
 def list_capacities_delegated_tenant_settings(
-    return_dataframe: Optional[bool] = True,
+    return_dataframe: bool = True,
 ) -> Optional[pd.DataFrame | dict]:
     """
     Returns list of tenant setting overrides that override at the capacities.
@@ -477,11 +480,11 @@ def list_capacities_delegated_tenant_settings(
 
 
 def scan_workspaces(
-    data_source_details: Optional[bool] = False,
-    dataset_schema: Optional[bool] = False,
-    dataset_expressions: Optional[bool] = False,
-    lineage: Optional[bool] = False,
-    artifact_users: Optional[bool] = False,
+    data_source_details: bool = False,
+    dataset_schema: bool = False,
+    dataset_expressions: bool = False,
+    lineage: bool = False,
+    artifact_users: bool = False,
     workspace: Optional[str | List[str]] = None,
 ) -> dict:
 
@@ -519,6 +522,16 @@ def scan_workspaces(
 
 
 def list_datasets() -> pd.DataFrame:
+    """
+    Shows a list of datasets for the organization.
+
+    Returns
+    -------
+    pandas.DataFrame
+        A pandas dataframe showing a list of datasets for the organization.
+    """
+
+    # https://learn.microsoft.com/en-us/rest/api/power-bi/admin/datasets-get-datasets-as-admin
 
     df = pd.DataFrame(
         columns=[
@@ -544,8 +557,7 @@ def list_datasets() -> pd.DataFrame:
         ]
     )
 
-    client = fabric.FabricRestClient()
-
+    client = fabric.PowerBIRestClient()
     response = client.get("/v1.0/myorg/admin/datasets")
 
     if response.status_code != 200:
@@ -600,6 +612,25 @@ def list_datasets() -> pd.DataFrame:
 def list_item_access_details(
     item_name: str, type: str, workspace: Optional[str] = None
 ) -> pd.DataFrame:
+    """
+    Returns a list of users (including groups and service principals) and lists their workspace roles.
+
+    Parameters
+    ----------
+    item_name : str
+        Name of the Fabric item.
+    type : str
+        Type of Fabric item.
+    workspace : str, default=None
+        The Fabric workspace name.
+        Defaults to None which resolves to the workspace of the attached lakehouse
+        or if no lakehouse attached, resolves to the workspace of the notebook.
+
+    Returns
+    -------
+    pandas.DataFrame
+        A pandas dataframe showing a list of users (including groups and service principals) and lists their workspace roles.
+    """
 
     # https://learn.microsoft.com/en-us/rest/api/fabric/admin/items/list-item-access-details?tabs=HTTP
 
@@ -652,6 +683,19 @@ def list_item_access_details(
 def list_access_entities(
     user_email_address: str,
 ) -> pd.DataFrame:
+    """
+    Shows a list of permission details for Fabric and PowerBI items the specified user can access.
+
+    Parameters
+    ----------
+    user_email_address : str
+        The user's email address.
+
+    Returns
+    -------
+    pandas.DataFrame
+        A pandas dataframe showing a list of permission details for Fabric and PowerBI items the specified user can access.
+    """
 
     # https://learn.microsoft.com/en-us/rest/api/fabric/admin/users/list-access-entities?tabs=HTTP
 
@@ -691,8 +735,23 @@ def list_access_entities(
 def list_workspace_access_details(
     workspace: Optional[Union[str, UUID]] = None
 ) -> pd.DataFrame:
+    """
+    Shows a list of users (including groups and Service Principals) that have access to the specified workspace.
 
-    # https://learn.microsoft.com/en-us/rest/api/fabric/admin/items/list-items?tabs=HTTP
+    Parameters
+    ----------
+    workspace : str, default=None
+        The Fabric workspace name.
+        Defaults to None which resolves to the workspace of the attached lakehouse
+        or if no lakehouse attached, resolves to the workspace of the notebook.
+
+    Returns
+    -------
+    pandas.DataFrame
+        A pandas dataframe showing a list of users (including groups and Service Principals) that have access to the specified workspace.
+    """
+
+    # https://learn.microsoft.com/en-us/rest/api/fabric/admin/workspaces/list-workspace-access-details?tabs=HTTP
 
     workspace_name = fabric.resolve_workspace_name(workspace)
     workspace_id = fabric.resolve_workspace_id(workspace_name)
@@ -732,6 +791,29 @@ def list_items(
     state: Optional[str] = None,
     type: Optional[str] = None,
 ) -> pd.DataFrame:
+    """
+    Shows a list of active Fabric and PowerBI items.
+
+    Parameters
+    ----------
+    capacity_name : str, default=None
+        The capacity name.
+    workspace : str, default=None
+        The Fabric workspace name.
+        Defaults to None which resolves to the workspace of the attached lakehouse
+        or if no lakehouse attached, resolves to the workspace of the notebook.
+    state : str, default=None
+        The item state.
+    type : str, default=None
+        The item type.
+
+    Returns
+    -------
+    pandas.DataFrame
+        A pandas dataframe showing a list of active Fabric and Power BI items.
+    """
+
+    # https://learn.microsoft.com/en-us/rest/api/fabric/admin/items/list-items?tabs=HTTP
 
     url = "/v1/admin/items?"
 

sempy_labs/admin/_domains.py

@@ -30,7 +30,7 @@ def resolve_domain_id(domain_name: str) -> UUID:
     return dfL_filt["Domain ID"].iloc[0]
 
 
-def list_domains(non_empty_only: Optional[bool] = False) -> pd.DataFrame:
+def list_domains(non_empty_only: bool = False) -> pd.DataFrame:
     """
     Shows a list of domains.
 

sempy_labs/directlake/_directlake_schema_sync.py

@@ -12,7 +12,7 @@ import sempy_labs._icons as icons
 def direct_lake_schema_sync(
     dataset: str,
     workspace: Optional[str] = None,
-    add_to_model: Optional[bool] = False,
+    add_to_model: bool = False,
     **kwargs,
 ):
     """

sempy_labs/directlake/_dl_helper.py

@@ -5,7 +5,11 @@ from typing import Optional, List, Union, Tuple
 from uuid import UUID
 import sempy_labs._icons as icons
 from sempy._utils._log import log
-from sempy_labs._helper_functions import retry, resolve_dataset_id
+from sempy_labs._helper_functions import (
+    retry,
+    resolve_dataset_id,
+    resolve_lakehouse_name,
+)
 
 
 def check_fallback_reason(
@@ -28,16 +32,17 @@ def check_fallback_reason(
     pandas.DataFrame
         The tables in the semantic model and their fallback reason.
     """
+    from sempy_labs.tom import connect_semantic_model
 
     workspace = fabric.resolve_workspace_name(workspace)
 
-    dfP = fabric.list_partitions(dataset=dataset, workspace=workspace)
-    dfP_filt = dfP[dfP["Mode"] == "DirectLake"]
-
-    if len(dfP_filt) == 0:
-        raise ValueError(
-            f"{icons.red_dot} The '{dataset}' semantic model is not in Direct Lake. This function is only applicable to Direct Lake semantic models."
-        )
+    with connect_semantic_model(
+        dataset=dataset, workspace=workspace, readonly=True
+    ) as tom:
+        if not tom.is_direct_lake():
+            raise ValueError(
+                f"{icons.red_dot} The '{dataset}' semantic model is not in Direct Lake. This function is only applicable to Direct Lake semantic models."
+            )
 
     df = fabric.evaluate_dax(
         dataset=dataset,
@@ -73,8 +78,9 @@ def generate_direct_lake_semantic_model(
     workspace: Optional[str] = None,
     lakehouse: Optional[str] = None,
     lakehouse_workspace: Optional[str] = None,
-    overwrite: Optional[bool] = False,
-    refresh: Optional[bool] = True,
+    schema: str = "dbo",
+    overwrite: bool = False,
+    refresh: bool = True,
 ):
     """
     Dynamically generates a Direct Lake semantic model based on tables in a Fabric lakehouse.
@@ -96,23 +102,32 @@ def generate_direct_lake_semantic_model(
         The Fabric workspace in which the lakehouse 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.
+    schema : str, default="dbo"
+        The schema used for the lakehouse.
     overwrite : bool, default=False
         If set to True, overwrites the existing semantic model if it already exists.
     refresh: bool, default=True
         If True, refreshes the newly created semantic model after it is created.
-
-    Returns
-    -------
     """
 
     from sempy_labs.lakehouse import get_lakehouse_tables, get_lakehouse_columns
-    from sempy_labs import create_blank_semantic_model, refresh_semantic_model
-    from sempy_labs.tom import connect_semantic_model
     from sempy_labs.directlake import get_shared_expression
+    from sempy_labs.tom import connect_semantic_model
+    from sempy_labs._generate_semantic_model import create_blank_semantic_model
+    from sempy_labs._refresh_semantic_model import refresh_semantic_model
 
     if isinstance(lakehouse_tables, str):
         lakehouse_tables = [lakehouse_tables]
 
+    workspace = fabric.resolve_workspace_name(workspace)
+    if lakehouse_workspace is None:
+        lakehouse_workspace = workspace
+    if lakehouse is None:
+        lakehouse_id = fabric.get_lakehouse_id()
+        lakehouse_workspace_id = fabric.get_workspace_id()
+        lakehouse_workspace = fabric.resolve_workspace_name(lakehouse_workspace_id)
+        lakehouse = resolve_lakehouse_name(lakehouse_id, lakehouse_workspace)
+
     dfLT = get_lakehouse_tables(lakehouse=lakehouse, workspace=lakehouse_workspace)
 
     # Validate lakehouse tables
@@ -158,7 +173,7 @@ def generate_direct_lake_semantic_model(
 
         for t in lakehouse_tables:
             tom.add_table(name=t)
-            tom.add_entity_partition(table_name=t, entity_name=t)
+            tom.add_entity_partition(table_name=t, entity_name=t, schema_name=schema)
             dfLC_filt = dfLC[dfLC["Table Name"] == t]
             for i, r in dfLC_filt.iterrows():
                 lakeCName = r["Column Name"]
@@ -212,6 +227,7 @@ def get_direct_lake_source(
     response = client.post(
         "metadata/relations/upstream?apiVersion=3", json=request_body
     )
+
     artifacts = response.json().get("artifacts", [])
     sql_id, sql_object_name, sql_workspace_id, artifact_type = None, None, None, None
 

sempy_labs/directlake/_guardrails.py

@@ -7,10 +7,7 @@ import sempy_labs._icons as icons
 def get_direct_lake_guardrails() -> pd.DataFrame:
     """
     Shows the guardrails for when Direct Lake semantic models will fallback to Direct Query
-     based on Microsoft's `online documentation <https://learn.microsoft.com/power-bi/enterprise/directlake-overview>`_.
-
-    Parameters
-    ----------
+    based on Microsoft's `online documentation <https://learn.microsoft.com/power-bi/enterprise/directlake-overview>`_.
 
     Returns
     -------
@@ -21,9 +18,12 @@ def get_direct_lake_guardrails() -> pd.DataFrame:
     url = "https://learn.microsoft.com/power-bi/enterprise/directlake-overview"
 
     tables = pd.read_html(url)
-    df = tables[0]
-    df["Fabric SKUs"] = df["Fabric SKUs"].str.split("/")
-    df = df.explode("Fabric SKUs", ignore_index=True)
+    for df in tables:
+        first_column_name = df.columns[0]
+        if first_column_name.startswith("Fabric"):
+            df[first_column_name] = df[first_column_name].str.split("/")
+            df = df.explode(first_column_name, ignore_index=True)
+            break
 
     return df
 

sempy_labs/directlake/_update_directlake_partition_entity.py

@@ -100,7 +100,7 @@ def add_table_to_direct_lake_semantic_model(
     dataset: str,
     table_name: str,
     lakehouse_table_name: str,
-    refresh: Optional[bool] = True,
+    refresh: bool = True,
     workspace: Optional[str] = None,
 ):
     """

sempy_labs/directlake/_warm_cache.py

@@ -15,7 +15,7 @@ import sempy_labs._icons as icons
 def warm_direct_lake_cache_perspective(
     dataset: str,
     perspective: str,
-    add_dependencies: Optional[bool] = False,
+    add_dependencies: bool = False,
     workspace: Optional[str] = None,
 ) -> pd.DataFrame:
     """

sempy_labs/lakehouse/_get_lakehouse_tables.py

@@ -24,9 +24,9 @@ from sempy.fabric.exceptions import FabricHTTPException
 def get_lakehouse_tables(
     lakehouse: Optional[str] = None,
     workspace: Optional[str] = None,
-    extended: Optional[bool] = False,
-    count_rows: Optional[bool] = False,
-    export: Optional[bool] = False,
+    extended: bool = False,
+    count_rows: bool = False,
+    export: bool = False,
 ) -> pd.DataFrame:
     """
     Shows the tables of a lakehouse and their respective properties. Option to include additional properties relevant to Direct Lake guardrails.

sempy_labs/lakehouse/_lakehouse.py

@@ -1,9 +1,7 @@
 import sempy.fabric as fabric
 from tqdm.auto import tqdm
-from pyspark.sql import SparkSession
 from sempy_labs._helper_functions import resolve_lakehouse_name
 from typing import List, Optional, Union
-import sempy_labs._icons as icons
 from sempy._utils._log import log
 
 
@@ -16,6 +14,7 @@ def lakehouse_attached() -> bool:
     bool
         Returns True if a lakehouse is attached to the notebook.
     """
+    from pyspark.sql import SparkSession
 
     spark = SparkSession.builder.getOrCreate()
     lakeId = spark.conf.get("trident.lakehouse.id")
@@ -49,6 +48,7 @@ def optimize_lakehouse_tables(
         or if no lakehouse attached, resolves to the workspace of the notebook.
     """
 
+    from pyspark.sql import SparkSession
     from sempy_labs.lakehouse._get_lakehouse_tables import get_lakehouse_tables
     from delta import DeltaTable
 
@@ -107,6 +107,7 @@ def vacuum_lakehouse_tables(
         The default retention period is 168 hours (7 days) unless manually configured via table properties.
     """
 
+    from pyspark.sql import SparkSession
     from sempy_labs.lakehouse._get_lakehouse_tables import get_lakehouse_tables
     from delta import DeltaTable
 

sempy_labs/migration/_migrate_calctables_to_lakehouse.py

@@ -8,6 +8,7 @@ from sempy_labs._helper_functions import (
     resolve_lakehouse_id,
     create_abfss_path,
     retry,
+    generate_guid,
 )
 from sempy_labs.tom import connect_semantic_model
 from pyspark.sql import SparkSession
@@ -343,6 +344,8 @@ def migrate_field_parameters(
 
                 tbl = TOM.Table()
                 tbl.Name = tName
+                tbl.LineageTag = generate_guid()
+                tbl.SourceLineageTag = generate_guid()
                 tbl.Partitions.Add(par)
 
                 columns = ["Value1", "Value2", "Value3"]
@@ -352,6 +355,8 @@ def migrate_field_parameters(
                     col.Name = colName
                     col.SourceColumn = "[" + colName + "]"
                     col.DataType = TOM.DataType.String
+                    col.LineageTag = generate_guid()
+                    col.SourceLineageTag = generate_guid()
 
                     tbl.Columns.Add(col)
 

sempy_labs/report/_generate_report.py

@@ -313,7 +313,7 @@ def _create_report(
     dataset: str,
     dataset_workspace: Optional[str] = None,
     report_workspace: Optional[str] = None,
-    update_if_exists: Optional[bool] = False,
+    update_if_exists: bool = False,
 ):
 
     from sempy_labs.report import report_rebind

sempy_labs/report/_report_bpa.py

@@ -14,6 +14,7 @@ from sempy_labs._helper_functions import (
 from sempy_labs.lakehouse import get_lakehouse_tables, lakehouse_attached
 import sempy_labs._icons as icons
 from IPython.display import display, HTML
+import sempy_labs.report._report_helper as helper
 
 
 @log
@@ -22,8 +23,8 @@ def run_report_bpa(
     rules: Optional[pd.DataFrame] = None,
     workspace: Optional[str] = None,
     # language: Optional[str] = None,
-    export: Optional[bool] = False,
-    return_dataframe: Optional[bool] = False,
+    export: bool = False,
+    return_dataframe: bool = False,
 ):
     """
     Displays an HTML visualization of the results of the Best Practice Analyzer scan for a report.
@@ -50,6 +51,7 @@ def run_report_bpa(
     """
 
     rpt = ReportWrapper(report=report, workspace=workspace)
+
     dfCV = rpt.list_custom_visuals()
     dfP = rpt.list_pages()
     dfRF = rpt.list_report_filters()
@@ -57,6 +59,12 @@ def run_report_bpa(
         dfRF["Table Name"], dfRF["Object Name"]
     )
     dfPF = rpt.list_page_filters()
+    # Convert back to dataframe
+    # if isinstance(dfPF, pd.io.formats.style.Styler):
+    #    dfPF = dfPF.data
+    # if isinstance(dfP, pd.io.formats.style.Styler):
+    #    dfP = dfP.data
+
     dfPF["Filter Object"] = (
         dfPF["Page Display Name"]
         + " : "
@@ -134,7 +142,9 @@ def run_report_bpa(
             df_output["Severity"] = row["Severity"]
             df_output["Description"] = row["Description"]
             df_output["URL"] = row["URL"]
-            df_output["Report URL"] = rpt._get_web_url()
+            df_output["Report URL"] = helper.get_web_url(
+                report=report, workspace=workspace
+            )
 
             page_mapping_dict = dfP.set_index("Page Display Name")["Page URL"].to_dict()