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

sempy_labs/_helper_functions.py

@@ -961,15 +961,15 @@ class FabricTokenCredential(TokenCredential):
         **kwargs: any,
     ) -> AccessToken:
 
-        from notebookutils import mssparkutils
+        import notebookutils
 
-        token = mssparkutils.credentials.getToken(scopes)
+        token = notebookutils.credentials.getToken(scopes)
         access_token = AccessToken(token, 0)
 
         return access_token
 
 
-def get_adls_client(account_name):
+def _get_adls_client(account_name):
 
     from azure.storage.filedatalake import DataLakeServiceClient
 
@@ -1017,19 +1017,22 @@ def get_language_codes(languages: str | List[str]):
     return languages
 
 
-def get_azure_token_credentials(
+def _get_azure_token_credentials(
     key_vault_uri: str,
     key_vault_tenant_id: str,
     key_vault_client_id: str,
     key_vault_client_secret: str,
+    audience: str = "https://management.azure.com/.default",
 ) -> Tuple[str, str, dict]:
 
-    from notebookutils import mssparkutils
+    import notebookutils
     from azure.identity import ClientSecretCredential
 
-    tenant_id = mssparkutils.credentials.getSecret(key_vault_uri, key_vault_tenant_id)
-    client_id = mssparkutils.credentials.getSecret(key_vault_uri, key_vault_client_id)
-    client_secret = mssparkutils.credentials.getSecret(
+    # "https://analysis.windows.net/powerbi/api/.default"
+
+    tenant_id = notebookutils.credentials.getSecret(key_vault_uri, key_vault_tenant_id)
+    client_id = notebookutils.credentials.getSecret(key_vault_uri, key_vault_client_id)
+    client_secret = notebookutils.credentials.getSecret(
         key_vault_uri, key_vault_client_secret
     )
 
@@ -1037,7 +1040,7 @@ def get_azure_token_credentials(
         tenant_id=tenant_id, client_id=client_id, client_secret=client_secret
     )
 
-    token = credential.get_token("https://management.azure.com/.default").token
+    token = credential.get_token(audience).token
 
     headers = {
         "Authorization": f"Bearer {token}",
@@ -1077,7 +1080,7 @@ def resolve_environment_id(environment: str, workspace: Optional[str] = None) ->
     )
 
 
-def make_clickable(val):
+def _make_clickable(val):
 
     return f'<a target="_blank" href="{val}">{val}</a>'
 
@@ -1132,7 +1135,7 @@ def generate_guid():
     return str(uuid.uuid4())
 
 
-def get_max_run_id(lakehouse: str, table_name: str) -> int:
+def _get_max_run_id(lakehouse: str, table_name: str) -> int:
 
     from pyspark.sql import SparkSession
 

sempy_labs/_list_functions.py

@@ -1487,7 +1487,7 @@ def list_semantic_model_object_report_usage(
         is sorted descending by 'Report Usage Count'.
     """
 
-    from sempy_labs._model_dependencies import get_measure_dependencies
+    from sempy_labs._model_dependencies import get_model_calc_dependencies
     from sempy_labs._helper_functions import format_dax_object_name
 
     workspace = fabric.resolve_workspace_name(workspace)
@@ -1503,7 +1503,7 @@ def list_semantic_model_object_report_usage(
         )
     else:
         df = pd.DataFrame(columns=["Table Name", "Object Name", "Object Type"])
-        dep = get_measure_dependencies(dataset=dataset, workspace=workspace)
+        dep = get_model_calc_dependencies(dataset=dataset, workspace=workspace)
 
         for i, r in dfR.iterrows():
             object_type = r["Object Type"]
@@ -1515,7 +1515,10 @@ def list_semantic_model_object_report_usage(
                 "Object Type": object_type,
             }
             df = pd.concat([df, pd.DataFrame(new_data, index=[0])], ignore_index=True)
-            if object_type == "Measure":
+            df["Referenced Object Type"] = df["Referenced Object Type"].replace(
+                "Attribute Hierarchy", "Column"
+            )
+            if object_type in ["Measure", "Calc Column", "Calc Table", "Hierarchy"]:
                 df_filt = dep[dep["Object Name"] == object_name][
                     ["Referenced Table", "Referenced Object", "Referenced Object Type"]
                 ]

sempy_labs/_model_bpa.py

@@ -12,7 +12,7 @@ from sempy_labs._helper_functions import (
     resolve_workspace_capacity,
     resolve_dataset_id,
     get_language_codes,
-    get_max_run_id,
+    _get_max_run_id,
 )
 from sempy_labs.lakehouse import get_lakehouse_tables, lakehouse_attached
 from sempy_labs.tom import connect_semantic_model
@@ -220,9 +220,9 @@ def run_model_bpa(
 
             rules = translate_using_spark(rules)
 
-        rules["Severity"].replace("Warning", icons.warning, inplace=True)
-        rules["Severity"].replace("Error", icons.error, inplace=True)
-        rules["Severity"].replace("Info", icons.info, inplace=True)
+        rules.loc[rules["Severity"] == "Warning", "Severity"] = icons.warning
+        rules.loc[rules["Severity"] == "Error", "Severity"] = icons.error
+        rules.loc[rules["Severity"] == "Info", "Severity"] = icons.info
 
         pd.set_option("display.max_colwidth", 1000)
 
@@ -350,7 +350,7 @@ def run_model_bpa(
         if len(lakeT_filt) == 0:
             runId = 1
         else:
-            max_run_id = get_max_run_id(
+            max_run_id = _get_max_run_id(
                 lakehouse=lakehouse, table_name=delta_table_name
             )
             runId = max_run_id + 1

sempy_labs/_model_bpa_bulk.py

@@ -6,7 +6,7 @@ from sempy_labs._helper_functions import (
     save_as_delta_table,
     resolve_workspace_capacity,
     retry,
-    get_max_run_id,
+    _get_max_run_id,
 )
 from sempy_labs.lakehouse import (
     get_lakehouse_tables,
@@ -49,8 +49,6 @@ def run_model_bpa_bulk(
         The semantic models to always skip when running this analysis.
     """
 
-    import pyspark.sql.functions as F
-
     if not lakehouse_attached():
         raise ValueError(
             f"{icons.red_dot} No lakehouse is attached to this notebook. Must attach a lakehouse to the notebook."
@@ -92,7 +90,7 @@ def run_model_bpa_bulk(
     if len(lakeT_filt) == 0:
         runId = 1
     else:
-        max_run_id = get_max_run_id(lakehouse=lakehouse, table_name=output_table)
+        max_run_id = _get_max_run_id(lakehouse=lakehouse, table_name=output_table)
         runId = max_run_id + 1
 
     if isinstance(workspace, str):
@@ -162,7 +160,7 @@ def run_model_bpa_bulk(
                         )
                         print(e)
 
-                df["Severity"].replace(icons.severity_mapping, inplace=True)
+                df["Severity"].replace(icons.severity_mapping)
 
                 # Append save results individually for each workspace (so as not to create a giant dataframe)
                 print(

sempy_labs/_notebooks.py

@@ -8,7 +8,6 @@ from sempy_labs._helper_functions import (
     resolve_workspace_name_and_id,
     lro,
     _decode_b64,
-    resolve_notebook_id,
 )
 from sempy.fabric.exceptions import FabricHTTPException
 
@@ -38,10 +37,12 @@ def get_notebook_definition(
     """
 
     (workspace, workspace_id) = resolve_workspace_name_and_id(workspace)
-    notebook_id = resolve_notebook_id(notebook=notebook_name, workspace=workspace)
+    item_id = fabric.resolve_item_id(
+        item_name=notebook_name, type="Notebook", workspace=workspace
+    )
     client = fabric.FabricRestClient()
     response = client.post(
-        f"v1/workspaces/{workspace_id}/notebooks/{notebook_id}/getDefinition",
+        f"v1/workspaces/{workspace_id}/notebooks/{item_id}/getDefinition",
     )
 
     result = lro(client, response).json()

sempy_labs/_sql.py

@@ -9,7 +9,7 @@ from sempy.fabric.exceptions import FabricHTTPException
 from sempy_labs._helper_functions import resolve_warehouse_id, resolve_lakehouse_id
 
 
-def bytes2mswin_bstr(value: bytes) -> bytes:
+def _bytes2mswin_bstr(value: bytes) -> bytes:
     """Convert a sequence of bytes into a (MS-Windows) BSTR (as bytes).
 
     See https://github.com/mkleehammer/pyodbc/issues/228#issuecomment-319190980
@@ -68,7 +68,7 @@ class ConnectBase:
 
         # Set up the connection string
         access_token = SynapseTokenProvider()()
-        tokenstruct = bytes2mswin_bstr(access_token.encode())
+        tokenstruct = _bytes2mswin_bstr(access_token.encode())
         conn_str = f"DRIVER={{ODBC Driver 18 for SQL Server}};SERVER={tds_endpoint};DATABASE={name};Encrypt=Yes;"
 
         if timeout is not None:

sempy_labs/_translations.py

@@ -40,7 +40,7 @@ def translate_semantic_model(
     from pyspark.sql import SparkSession
     from sempy_labs.tom import connect_semantic_model
 
-    def clean_text(text, exclude_chars):
+    def _clean_text(text, exclude_chars):
         if exclude_chars:
             for char in exclude_chars:
                 text = text.replace(char, " ")
@@ -60,8 +60,8 @@ def translate_semantic_model(
     ) as tom:
 
         for o in tom.model.Tables:
-            oName = clean_text(o.Name, exclude_characters)
-            oDescription = clean_text(o.Description, exclude_characters)
+            oName = _clean_text(o.Name, exclude_characters)
+            oDescription = _clean_text(o.Description, exclude_characters)
             new_data = {
                 "Object Type": "Table",
                 "Name": o.Name,
@@ -75,9 +75,9 @@ def translate_semantic_model(
                 [df_prep, pd.DataFrame(new_data, index=[0])], ignore_index=True
             )
         for o in tom.all_columns():
-            oName = clean_text(o.Name, exclude_characters)
-            oDescription = clean_text(o.Description, exclude_characters)
-            oDisplayFolder = clean_text(o.DisplayFolder, exclude_characters)
+            oName = _clean_text(o.Name, exclude_characters)
+            oDescription = _clean_text(o.Description, exclude_characters)
+            oDisplayFolder = _clean_text(o.DisplayFolder, exclude_characters)
             new_data = {
                 "Object Type": "Column",
                 "Name": o.Name,
@@ -91,9 +91,9 @@ def translate_semantic_model(
                 [df_prep, pd.DataFrame(new_data, index=[0])], ignore_index=True
             )
         for o in tom.all_measures():
-            oName = clean_text(o.Name, exclude_characters)
-            oDescription = clean_text(o.Description, exclude_characters)
-            oDisplayFolder = clean_text(o.DisplayFolder, exclude_characters)
+            oName = _clean_text(o.Name, exclude_characters)
+            oDescription = _clean_text(o.Description, exclude_characters)
+            oDisplayFolder = _clean_text(o.DisplayFolder, exclude_characters)
             new_data = {
                 "Object Type": "Measure",
                 "Name": o.Name,
@@ -107,9 +107,9 @@ def translate_semantic_model(
                 [df_prep, pd.DataFrame(new_data, index=[0])], ignore_index=True
             )
         for o in tom.all_hierarchies():
-            oName = clean_text(o.Name, exclude_characters)
-            oDescription = clean_text(o.Description, exclude_characters)
-            oDisplayFolder = clean_text(o.DisplayFolder, exclude_characters)
+            oName = _clean_text(o.Name, exclude_characters)
+            oDescription = _clean_text(o.Description, exclude_characters)
+            oDisplayFolder = _clean_text(o.DisplayFolder, exclude_characters)
             new_data = {
                 "Object Type": "Hierarchy",
                 "Name": o.Name,
@@ -123,8 +123,8 @@ def translate_semantic_model(
                 [df_prep, pd.DataFrame(new_data, index=[0])], ignore_index=True
             )
         for o in tom.all_levels():
-            oName = clean_text(o.Name, exclude_characters)
-            oDescription = clean_text(o.Description, exclude_characters)
+            oName = _clean_text(o.Name, exclude_characters)
+            oDescription = _clean_text(o.Description, exclude_characters)
             new_data = {
                 "Object Type": "Level",
                 "Name": o.Name,

sempy_labs/_vertipaq.py

@@ -13,7 +13,7 @@ from sempy_labs._helper_functions import (
     resolve_dataset_id,
     save_as_delta_table,
     resolve_workspace_capacity,
-    get_max_run_id,
+    _get_max_run_id,
 )
 from sempy_labs._list_functions import list_relationships, list_tables
 from sempy_labs.lakehouse import lakehouse_attached, get_lakehouse_tables
@@ -74,68 +74,71 @@ def vertipaq_analyzer(
     data_type_timestamp = "timestamp"
     data_type_double = "double"
     data_type_bool = "bool"
+    int_format = "int"
+    pct_format = "pct"
+    no_format = ""
 
     vertipaq_map = {
         "Model": {
-            "Dataset Name": data_type_string,
-            "Total Size": data_type_long,
-            "Table Count": data_type_long,
-            "Column Count": data_type_long,
-            "Compatibility Level": data_type_long,
-            "Default Mode": data_type_string,
+            "Dataset Name": [data_type_string, no_format],
+            "Total Size": [data_type_long, int_format],
+            "Table Count": [data_type_long, int_format],
+            "Column Count": [data_type_long, int_format],
+            "Compatibility Level": [data_type_long, no_format],
+            "Default Mode": [data_type_string, no_format],
         },
         "Tables": {
-            "Table Name": data_type_string,
-            "Type": data_type_string,
-            "Row Count": data_type_long,
-            "Total Size": data_type_long,
-            "Dictionary Size": data_type_long,
-            "Data Size": data_type_long,
-            "Hierarchy Size": data_type_long,
-            "Relationship Size": data_type_long,
-            "User Hierarchy Size": data_type_long,
-            "Partitions": data_type_long,
-            "Columns": data_type_long,
-            "% DB": data_type_double,
+            "Table Name": [data_type_string, no_format],
+            "Type": [data_type_string, no_format],
+            "Row Count": [data_type_long, int_format],
+            "Total Size": [data_type_long, int_format],
+            "Dictionary Size": [data_type_long, int_format],
+            "Data Size": [data_type_long, int_format],
+            "Hierarchy Size": [data_type_long, int_format],
+            "Relationship Size": [data_type_long, int_format],
+            "User Hierarchy Size": [data_type_long, int_format],
+            "Partitions": [data_type_long, int_format],
+            "Columns": [data_type_long, int_format],
+            "% DB": [data_type_double, pct_format],
         },
         "Partitions": {
-            "Table Name": data_type_string,
-            "Partition Name": data_type_string,
-            "Mode": data_type_string,
-            "Record Count": data_type_long,
-            "Segment Count": data_type_long,
-            "Records per Segment": data_type_double,
+            "Table Name": [data_type_string, no_format],
+            "Partition Name": [data_type_string, no_format],
+            "Mode": [data_type_string, no_format],
+            "Record Count": [data_type_long, int_format],
+            "Segment Count": [data_type_long, int_format],
+            "Records per Segment": [data_type_double, int_format],
         },
         "Columns": {
-            "Table Name": data_type_string,
-            "Column Name": data_type_string,
-            "Type": data_type_string,
-            "Cardinality": data_type_long,
-            "Total Size": data_type_long,
-            "Data Size": data_type_long,
-            "Dictionary Size": data_type_long,
-            "Hierarchy Size": data_type_long,
-            "% Table": data_type_double,
-            "% DB": data_type_double,
-            "Data Type": data_type_string,
-            "Encoding": data_type_string,
-            "Is Resident": data_type_bool,
-            "Temperature": data_type_double,
-            "Last Accessed": data_type_timestamp,
+            "Table Name": [data_type_string, no_format],
+            "Column Name": [data_type_string, no_format],
+            "Type": [data_type_string, no_format],
+            "Cardinality": [data_type_long, int_format],
+            "Total Size": [data_type_long, int_format],
+            "Data Size": [data_type_long, int_format],
+            "Dictionary Size": [data_type_long, int_format],
+            "Hierarchy Size": [data_type_long, int_format],
+            "% Table": [data_type_double, pct_format],
+            "% DB": [data_type_double, pct_format],
+            "Data Type": [data_type_string, no_format],
+            "Encoding": [data_type_string, no_format],
+            "Is Resident": [data_type_bool, no_format],
+            "Temperature": [data_type_double, int_format],
+            "Last Accessed": [data_type_timestamp, no_format],
         },
         "Hierarchies": {
-            "Table Name": data_type_string,
-            "Hierarchy Name": data_type_string,
-            "Used Size": data_type_long,
+            "Table Name": [data_type_string, no_format],
+            "Hierarchy Name": [data_type_string, no_format],
+            "Used Size": [data_type_long, int_format],
         },
         "Relationships": {
-            "From Object": data_type_string,
-            "To Object": data_type_string,
-            "Multiplicity": data_type_string,
-            "Used Size": data_type_long,
-            "Max From Cardinality": data_type_long,
-            "Max To Cardinality": data_type_long,
-            "Missing Rows": data_type_long,
+            "From Object": [data_type_string, no_format],
+            "To Object": [data_type_string, no_format],
+            "Multiplicity": [data_type_string, no_format],
+            "Used Size": [data_type_long, int_format],
+            "Max From Cardinality": [data_type_long, int_format],
+            "Max To Cardinality": [data_type_long, int_format],
+            "Missing Rows": [data_type_long, int_format],
         },
     }
 
@@ -163,7 +166,8 @@ def vertipaq_analyzer(
         table_count = tom.model.Tables.Count
         column_count = len(list(tom.all_columns()))
 
-    dfR["Missing Rows"] = None
+    dfR["Missing Rows"] = 0
+    dfR["Missing Rows"] = dfR["Missing Rows"].astype(int)
 
     # Direct Lake
     if read_stats_from_data:
@@ -323,38 +327,16 @@ def vertipaq_analyzer(
     dfC["% DB"] = round((dfC["Total Size"] / db_total_size) * 100, 2)
     columnList = list(vertipaq_map["Columns"].keys())
 
+    dfC = dfC[dfC["Type"] != "RowNumber"].reset_index(drop=True)
+
     colSize = dfC[columnList].sort_values(by="Total Size", ascending=False)
     temp = dfC[columnList].sort_values(by="Temperature", ascending=False)
     colSize.reset_index(drop=True, inplace=True)
     temp.reset_index(drop=True, inplace=True)
 
     export_Col = colSize.copy()
-
-    int_cols = []
-    pct_cols = []
-    for k, v in vertipaq_map["Columns"].items():
-        if v in ["int", "long"]:
-            int_cols.append(k)
-        elif v in ["float", "double"] and k != "Temperature":
-            pct_cols.append(k)
-    colSize[int_cols] = colSize[int_cols].map("{:,}".format)
-    temp[int_cols] = temp[int_cols].map("{:,}".format)
-    colSize[pct_cols] = colSize[pct_cols].map("{:.2f}%".format)
-    temp[pct_cols] = temp[pct_cols].map("{:.2f}%".format)
-
-    # Tables
-    int_cols = []
-    pct_cols = []
-    for k, v in vertipaq_map["Tables"].items():
-        if v in ["int", "long"]:
-            int_cols.append(k)
-        elif v in ["float", "double"]:
-            pct_cols.append(k)
     export_Table = dfT.copy()
 
-    dfT[int_cols] = dfT[int_cols].map("{:,}".format)
-    dfT[pct_cols] = dfT[pct_cols].map("{:.2f}%".format)
-
     #  Relationships
     dfR = pd.merge(
         dfR,
@@ -386,14 +368,6 @@ def vertipaq_analyzer(
     dfR.reset_index(drop=True, inplace=True)
     export_Rel = dfR.copy()
 
-    int_cols = []
-    for k, v in vertipaq_map["Relationships"].items():
-        if v in ["int", "long"]:
-            int_cols.append(k)
-    if not read_stats_from_data:
-        int_cols.remove("Missing Rows")
-    dfR[int_cols] = dfR[int_cols].map("{:,}".format)
-
     # Partitions
     dfP = dfP[
         [
@@ -410,12 +384,6 @@ def vertipaq_analyzer(
     )  # Remove after records per segment is fixed
     dfP.reset_index(drop=True, inplace=True)
     export_Part = dfP.copy()
-    int_cols = []
-    for k, v in vertipaq_map["Partitions"].items():
-        if v in ["int", "long", "double", "float"]:
-            int_cols.append(k)
-    intList = ["Record Count", "Segment Count", "Records per Segment"]
-    dfP[intList] = dfP[intList].map("{:,}".format)
 
     # Hierarchies
     dfH_filt = dfH[dfH["Level Ordinal"] == 0]
@@ -426,8 +394,6 @@ def vertipaq_analyzer(
     dfH_filt.fillna({"Used Size": 0}, inplace=True)
     dfH_filt["Used Size"] = dfH_filt["Used Size"].astype(int)
     export_Hier = dfH_filt.copy()
-    intList = ["Used Size"]
-    dfH_filt[intList] = dfH_filt[intList].map("{:,}".format)
 
     # Model
     # Converting to KB/MB/GB necessitates division by 1024 * 1000.
@@ -453,11 +419,63 @@ def vertipaq_analyzer(
     dfModel.reset_index(drop=True, inplace=True)
     dfModel["Default Mode"] = dfModel["Default Mode"].astype(str)
     export_Model = dfModel.copy()
-    int_cols = []
-    for k, v in vertipaq_map["Model"].items():
-        if v in ["long", "int"] and k != "Compatibility Level":
-            int_cols.append(k)
-    dfModel[int_cols] = dfModel[int_cols].map("{:,}".format)
+
+    def _style_columns_based_on_types(dataframe: pd.DataFrame, column_type_mapping):
+
+        format_mapping = {
+            "int": "{:,}",
+            "pct": "{:.2f}%",
+            "": "{}",
+        }
+
+        format_dict = {
+            col: format_mapping[dt] for col, dt in column_type_mapping.items()
+        }
+
+        return dataframe.style.format(format_dict)
+
+    dfModel = _style_columns_based_on_types(
+        dfModel,
+        column_type_mapping={
+            key: values[1] for key, values in vertipaq_map["Model"].items()
+        },
+    )
+    dfT = _style_columns_based_on_types(
+        dfT,
+        column_type_mapping={
+            key: values[1] for key, values in vertipaq_map["Tables"].items()
+        },
+    )
+    dfP = _style_columns_based_on_types(
+        dfP,
+        column_type_mapping={
+            key: values[1] for key, values in vertipaq_map["Partitions"].items()
+        },
+    )
+    colSize = _style_columns_based_on_types(
+        colSize,
+        column_type_mapping={
+            key: values[1] for key, values in vertipaq_map["Columns"].items()
+        },
+    )
+    temp = _style_columns_based_on_types(
+        temp,
+        column_type_mapping={
+            key: values[1] for key, values in vertipaq_map["Columns"].items()
+        },
+    )
+    dfR = _style_columns_based_on_types(
+        dfR,
+        column_type_mapping={
+            key: values[1] for key, values in vertipaq_map["Relationships"].items()
+        },
+    )
+    dfH_filt = _style_columns_based_on_types(
+        dfH_filt,
+        column_type_mapping={
+            key: values[1] for key, values in vertipaq_map["Hierarchies"].items()
+        },
+    )
 
     dataFrames = {
         "dfModel": dfModel,
@@ -484,8 +502,6 @@ def vertipaq_analyzer(
             )
 
     if export == "table":
-        # spark = SparkSession.builder.getOrCreate()
-
         lakehouse_id = fabric.get_lakehouse_id()
         lake_workspace = fabric.resolve_workspace_name()
         lakehouse = resolve_lakehouse_name(
@@ -499,7 +515,7 @@ def vertipaq_analyzer(
         if len(lakeT_filt) == 0:
             runId = 1
         else:
-            max_run_id = get_max_run_id(lakehouse=lakehouse, table_name=lakeTName)
+            max_run_id = _get_max_run_id(lakehouse=lakehouse, table_name=lakeTName)
             runId = max_run_id + 1
 
         dfMap = {
@@ -560,7 +576,7 @@ def vertipaq_analyzer(
 
             schema.update(
                 {
-                    key.replace(" ", "_"): value
+                    key.replace(" ", "_"): value[0]
                     for key, value in vertipaq_map[key_name].items()
                 }
             )
@@ -739,7 +755,11 @@ def visualize_vertipaq(dataframes):
             "ColumnName": "Column Name",
             "Tooltip": "The name of the column",
         },
-        {"ViewName": "Column", "ColumnName": "Type", "Tooltip": "The type of column"},
+        {
+            "ViewName": "Column",
+            "ColumnName": "Type",
+            "Tooltip": "The type of column",
+        },
         {
             "ViewName": "Column",
             "ColumnName": "Cardinality",

sempy_labs/_warehouses.py

@@ -11,7 +11,10 @@ from sempy.fabric.exceptions import FabricHTTPException
 
 
 def create_warehouse(
-    warehouse: str, description: Optional[str] = None, workspace: Optional[str] = None
+    warehouse: str,
+    description: Optional[str] = None,
+    case_insensitive_collation: bool = False,
+    workspace: Optional[str] = None,
 ):
     """
     Creates a Fabric warehouse.
@@ -22,6 +25,8 @@ def create_warehouse(
         Name of the warehouse.
     description : str, default=None
         A description of the warehouse.
+    case_insensitive_collation: bool, default=False
+        If True, creates the warehouse with case-insensitive collation.
     workspace : str, default=None
         The Fabric workspace name.
         Defaults to None which resolves to the workspace of the attached lakehouse
@@ -34,6 +39,11 @@ def create_warehouse(
 
     if description:
         request_body["description"] = description
+    if case_insensitive_collation:
+        request_body.setdefault("creationPayload", {})
+        request_body["creationPayload"][
+            "defaultCollation"
+        ] = "Latin1_General_100_CI_AS_KS_WS_SC_UTF8"
 
     client = fabric.FabricRestClient()
     response = client.post(

sempy_labs/admin/__init__.py

@@ -12,6 +12,7 @@ from sempy_labs.admin._basic_functions import (
     list_access_entities,
     list_workspace_access_details,
     list_items,
+    list_activity_events,
 )
 from sempy_labs.admin._domains import (
     list_domains,
@@ -50,4 +51,5 @@ __all__ = [
     "unassign_workspaces_from_capacity",
     "list_external_data_shares",
     "revoke_external_data_share",
+    "list_activity_events",
 ]