semantic-link-labs 0.8.3__py3-none-any.whl → 0.8.5__py3-none-any.whl

sempy_labs/_model_bpa_rules.py

@@ -158,6 +158,7 @@ def model_bpa_rules(
                     and r.ToTable.Name == obj.Name
                     for r in tom.used_in_relationships(object=obj)
                 ),
+                "When using DirectQuery, dimension tables should be set to Dual mode in order to improve query performance.",
                 "https://learn.microsoft.com/power-bi/transform-model/desktop-storage-mode#propagation-of-the-dual-setting",
             ),
             (
@@ -492,6 +493,7 @@ def model_bpa_rules(
                     obj.Expression,
                     flags=re.IGNORECASE,
                 ),
+                "Adding a constant value may lead to performance degradation.",
             ),
             (
                 "DAX Expressions",
@@ -643,14 +645,15 @@ def model_bpa_rules(
                 "Calculation groups with no calculation items",
                 lambda obj, tom: obj.CalculationGroup is not None
                 and not any(obj.CalculationGroup.CalculationItems),
+                "Calculation groups have no function unless they have calculation items.",
             ),
             (
                 "Maintenance",
-                "Column",
+                ["Column", "Measure", "Table"],
                 "Info",
                 "Visible objects with no description",
                 lambda obj, tom: obj.IsHidden is False and len(obj.Description) == 0,
-                "Calculation groups have no function unless they have calculation items.",
+                "Add descriptions to objects. These descriptions are shown on hover within the Field List in Power BI Desktop. Additionally, you can leverage these descriptions to create an automated data dictionary.",
             ),
             (
                 "Formatting",
@@ -710,6 +713,7 @@ def model_bpa_rules(
                 "Percentages should be formatted with thousands separators and 1 decimal",
                 lambda obj, tom: "%" in obj.FormatString
                 and obj.FormatString != "#,0.0%;-#,0.0%;#,0.0%",
+                "For a better user experience, percengage measures should be formatted with a '%' sign.",
             ),
             (
                 "Formatting",
@@ -719,6 +723,7 @@ def model_bpa_rules(
                 lambda obj, tom: "$" not in obj.FormatString
                 and "%" not in obj.FormatString
                 and obj.FormatString not in ["#,0", "#,0.0"],
+                "For a better user experience, whole numbers should be formatted with commas.",
             ),
             (
                 "Formatting",
@@ -731,7 +736,7 @@ def model_bpa_rules(
                     and r.FromCardinality == TOM.RelationshipEndCardinality.Many
                     for r in tom.used_in_relationships(object=obj)
                 ),
-                "Foreign keys should always be hidden.",
+                "Foreign keys should always be hidden as they should not be used by end users.",
             ),
             (
                 "Formatting",

sempy_labs/_model_dependencies.py

@@ -160,28 +160,26 @@ def get_model_calc_dependencies(
     """
 
     workspace = fabric.resolve_workspace_name(workspace)
-
     dep = fabric.evaluate_dax(
         dataset=dataset,
         workspace=workspace,
         dax_string="""
         SELECT
-        [TABLE] AS [Table Name]
-        ,[OBJECT] AS [Object Name]
-        ,[OBJECT_TYPE] AS [Object Type]
-        ,[EXPRESSION] AS [Expression]
-        ,[REFERENCED_TABLE] AS [Referenced Table]
-        ,[REFERENCED_OBJECT] AS [Referenced Object]
-        ,[REFERENCED_OBJECT_TYPE] AS [Referenced Object Type]
+            [TABLE] AS [Table Name],
+            [OBJECT] AS [Object Name],
+            [OBJECT_TYPE] AS [Object Type],
+            [EXPRESSION] AS [Expression],
+            [REFERENCED_TABLE] AS [Referenced Table],
+            [REFERENCED_OBJECT] AS [Referenced Object],
+            [REFERENCED_OBJECT_TYPE] AS [Referenced Object Type]
         FROM $SYSTEM.DISCOVER_CALC_DEPENDENCY
         """,
     )
-
+    # Format data columns
     dep["Object Type"] = dep["Object Type"].str.replace("_", " ").str.title()
     dep["Referenced Object Type"] = (
         dep["Referenced Object Type"].str.replace("_", " ").str.title()
     )
-
     dep["Full Object Name"] = format_dax_object_name(
         dep["Table Name"], dep["Object Name"]
     )
@@ -189,83 +187,39 @@ def get_model_calc_dependencies(
         dep["Referenced Table"], dep["Referenced Object"]
     )
     dep["Parent Node"] = dep["Object Name"]
-
-    df = dep
-
-    objs = ["Measure", "Calc Column", "Calculation Item", "Calc Table"]
-
-    df["Done"] = df.apply(
-        lambda row: False if row["Referenced Object Type"] in objs else True, axis=1
-    )
-
-    while any(df["Done"] == False):
-        for i, r in df.iterrows():
-            rObjFull = r["Referenced Full Object Name"]
-            rObj = r["Referenced Object"]
-            if r["Done"] == False:
-                dep_filt = dep[dep["Full Object Name"] == rObjFull]
-
-                for index, dependency in dep_filt.iterrows():
-                    d = True
-                    if dependency.iloc[5] in objs:
-                        d = False
-                        df = pd.concat(
-                            [
-                                df,
-                                pd.DataFrame(
-                                    [
-                                        {
-                                            "Table Name": r["Table Name"],
-                                            "Object Name": r["Object Name"],
-                                            "Object Type": r["Object Type"],
-                                            "Referenced Object": dependency.iloc[4],
-                                            "Referenced Table": dependency.iloc[3],
-                                            "Referenced Object Type": dependency.iloc[
-                                                5
-                                            ],
-                                            "Done": d,
-                                            "Full Object Name": r["Full Object Name"],
-                                            "Referenced Full Object Name": dependency.iloc[
-                                                7
-                                            ],
-                                            "Parent Node": rObj,
-                                        }
-                                    ]
-                                ),
-                            ],
-                            ignore_index=True,
-                        )
-                    else:
-                        df = pd.concat(
-                            [
-                                df,
-                                pd.DataFrame(
-                                    [
-                                        {
-                                            "Table Name": r["Table Name"],
-                                            "Object Name": r["Object Name"],
-                                            "Object Type": r["Object Type"],
-                                            "Referenced Object": dependency.iloc[5],
-                                            "Referenced Table": dependency.iloc[4],
-                                            "Referenced Object Type": dependency.iloc[
-                                                6
-                                            ],
-                                            "Done": d,
-                                            "Full Object Name": r["Full Object Name"],
-                                            "Referenced Full Object Name": dependency.iloc[
-                                                7
-                                            ],
-                                            "Parent Node": rObj,
-                                        }
-                                    ]
-                                ),
-                            ],
-                            ignore_index=True,
-                        )
-
-            df.loc[i, "Done"] = True
-
-    df = df.drop(["Done"], axis=1)
+    # Initialize dependency DataFrame with 'Done' status
+    df = dep.copy()
+    objs = {"Measure", "Calc Column", "Calculation Item", "Calc Table"}
+    df["Done"] = df["Referenced Object Type"].apply(lambda x: x not in objs)
+    # Expand dependencies iteratively
+    while not df["Done"].all():
+        incomplete_rows = df[df["Done"] == False]
+        for _, row in incomplete_rows.iterrows():
+            referenced_full_name = row["Referenced Full Object Name"]
+            dep_filt = dep[dep["Full Object Name"] == referenced_full_name]
+            # Expand dependencies and update 'Done' status as needed
+            new_rows = []
+            for _, dependency in dep_filt.iterrows():
+                is_done = dependency["Referenced Object Type"] not in objs
+                new_row = {
+                    "Table Name": row["Table Name"],
+                    "Object Name": row["Object Name"],
+                    "Object Type": row["Object Type"],
+                    "Referenced Table": dependency["Referenced Table"],
+                    "Referenced Object": dependency["Referenced Object"],
+                    "Referenced Object Type": dependency["Referenced Object Type"],
+                    "Done": is_done,
+                    "Full Object Name": row["Full Object Name"],
+                    "Referenced Full Object Name": dependency[
+                        "Referenced Full Object Name"
+                    ],
+                    "Parent Node": row["Referenced Object"],
+                }
+                new_rows.append(new_row)
+            df = pd.concat([df, pd.DataFrame(new_rows)], ignore_index=True)
+            df.loc[df.index == row.name, "Done"] = True
+    # Finalize DataFrame and yield result
+    df = df.drop(columns=["Done"])
 
     return df
 

sempy_labs/_notebooks.py

@@ -18,6 +18,8 @@ def get_notebook_definition(
     """
     Obtains the notebook definition.
 
+    This is a wrapper function for the following API: `Items - Get Notebook Definition <https://learn.microsoft.com/rest/api/fabric/notebook/items/get-notebook-definition>`_.
+
     Parameters
     ----------
     notebook_name : str
@@ -63,6 +65,7 @@ def import_notebook_from_web(
     url: str,
     description: Optional[str] = None,
     workspace: Optional[str] = None,
+    overwrite: bool = False,
 ):
     """
     Creates a new notebook within a workspace based on a Jupyter notebook hosted in the web.
@@ -83,16 +86,12 @@ def import_notebook_from_web(
         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.
+    overwrite : bool, default=False
+        If set to True, overwrites the existing notebook in the workspace if it exists.
     """
 
-    (workspace, workspace_id) = resolve_workspace_name_and_id(workspace)
-    client = fabric.FabricRestClient()
-    dfI = fabric.list_items(workspace=workspace, type="Notebook")
-    dfI_filt = dfI[dfI["Display Name"] == notebook_name]
-    if len(dfI_filt) > 0:
-        raise ValueError(
-            f"{icons.red_dot} The '{notebook_name}' already exists within the '{workspace}' workspace."
-        )
+    if workspace is None:
+        workspace = fabric.resolve_workspace_name(workspace)
 
     # Fix links to go to the raw github file
     starting_text = "https://github.com/"
@@ -105,11 +104,56 @@ def import_notebook_from_web(
     response = requests.get(url)
     if response.status_code != 200:
         raise FabricHTTPException(response)
-    file_content = response.content
-    notebook_payload = base64.b64encode(file_content)
+
+    dfI = fabric.list_items(workspace=workspace, type="Notebook")
+    dfI_filt = dfI[dfI["Display Name"] == notebook_name]
+    if len(dfI_filt) == 0:
+        create_notebook(
+            name=notebook_name,
+            notebook_content=response.content,
+            workspace=workspace,
+            description=description,
+        )
+    elif len(dfI_filt) > 0 and overwrite:
+        update_notebook_definition(
+            name=notebook_name, notebook_content=response.content, workspace=workspace
+        )
+    else:
+        raise ValueError(
+            f"{icons.red_dot} The '{notebook_name}' already exists within the '{workspace}' workspace and 'overwrite' is set to False."
+        )
+
+
+def create_notebook(
+    name: str,
+    notebook_content: str,
+    description: Optional[str] = None,
+    workspace: Optional[str] = None,
+):
+    """
+    Creates a new notebook with a definition within a workspace.
+
+    Parameters
+    ----------
+    name : str
+        The name of the notebook to be created.
+    notebook_content : str
+        The Jupyter notebook content (not in Base64 format).
+    description : str, default=None
+        The description of the notebook.
+        Defaults to None which does not place a description.
+    workspace : str, default=None
+        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.
+    """
+
+    (workspace, workspace_id) = resolve_workspace_name_and_id(workspace)
+    client = fabric.FabricRestClient()
+    notebook_payload = base64.b64encode(notebook_content)
 
     request_body = {
-        "displayName": notebook_name,
+        "displayName": name,
         "definition": {
             "format": "ipynb",
             "parts": [
@@ -129,5 +173,56 @@ def import_notebook_from_web(
     lro(client, response, status_codes=[201, 202])
 
     print(
-        f"{icons.green_dot} The '{notebook_name}' notebook was created within the '{workspace}' workspace."
+        f"{icons.green_dot} The '{name}' notebook was created within the '{workspace}' workspace."
+    )
+
+
+def update_notebook_definition(
+    name: str, notebook_content: str, workspace: Optional[str] = None
+):
+    """
+    Updates an existing notebook with a new definition.
+
+    Parameters
+    ----------
+    name : str
+        The name of the notebook to be updated.
+    notebook_content : str
+        The Jupyter notebook content (not in Base64 format).
+    workspace : str, default=None
+        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.
+    """
+
+    (workspace, workspace_id) = resolve_workspace_name_and_id(workspace)
+    client = fabric.FabricRestClient()
+    notebook_payload = base64.b64encode(notebook_content)
+    notebook_id = fabric.resolve_item_id(
+        item_name=name, type="Notebook", workspace=workspace
+    )
+
+    request_body = {
+        "displayName": name,
+        "definition": {
+            "format": "ipynb",
+            "parts": [
+                {
+                    "path": "notebook-content.py",
+                    "payload": notebook_payload,
+                    "payloadType": "InlineBase64",
+                }
+            ],
+        },
+    }
+
+    response = client.post(
+        f"v1/workspaces/{workspace_id}/notebooks/{notebook_id}/updateDefinition",
+        json=request_body,
+    )
+
+    lro(client, response, return_status_code=True)
+
+    print(
+        f"{icons.green_dot} The '{name}' notebook was updated within the '{workspace}' workspace."
     )

sempy_labs/_query_scale_out.py

@@ -13,6 +13,8 @@ def qso_sync(dataset: str, workspace: Optional[str] = None):
     """
     Triggers a query scale-out sync of read-only replicas for the specified dataset from the specified workspace.
 
+    This is a wrapper function for the following API: `Datasets - Trigger Query Scale Out Sync In Group <https://learn.microsoft.com/rest/api/power-bi/datasets/trigger-query-scale-out-sync-in-group>`_.
+
     Parameters
     ----------
     dataset : str
@@ -23,8 +25,6 @@ def qso_sync(dataset: str, workspace: Optional[str] = None):
         or if no lakehouse attached, resolves to the workspace of the notebook.
     """
 
-    # https://learn.microsoft.com/en-us/rest/api/power-bi/datasets/trigger-query-scale-out-sync-in-group
-
     (workspace, workspace_id) = resolve_workspace_name_and_id(workspace)
     dataset_id = resolve_dataset_id(dataset, workspace)
 
@@ -46,6 +46,8 @@ def qso_sync_status(
     """
     Returns the query scale-out sync status for the specified dataset from the specified workspace.
 
+    This is a wrapper function for the following API: `Datasets - Get Query Scale Out Sync Status In Group <https://learn.microsoft.com/rest/api/power-bi/datasets/get-query-scale-out-sync-status-in-group>`_.
+
     Parameters
     ----------
     dataset : str
@@ -61,8 +63,6 @@ def qso_sync_status(
         2 pandas dataframes showing the query scale-out sync status.
     """
 
-    # https://learn.microsoft.com/en-us/rest/api/power-bi/datasets/get-query-scale-out-sync-status-in-group
-
     df = pd.DataFrame(
         columns=[
             "Scale Out Status",
@@ -143,6 +143,8 @@ def disable_qso(dataset: str, workspace: Optional[str] = None) -> pd.DataFrame:
     """
     Sets the max read-only replicas to 0, disabling query scale out.
 
+    This is a wrapper function for the following API: `Datasets - Update Dataset In Group <https://learn.microsoft.com/rest/api/power-bi/datasets/update-dataset-in-group>`_.
+
     Parameters
     ----------
     dataset : str
@@ -188,6 +190,8 @@ def set_qso(
     """
     Sets the query scale out settings for a semantic model.
 
+    This is a wrapper function for the following API: `Datasets - Update Dataset In Group <https://learn.microsoft.com/rest/api/power-bi/datasets/update-dataset-in-group>`_.
+
     Parameters
     ----------
     dataset : str
@@ -209,8 +213,6 @@ def set_qso(
 
     from sempy_labs._helper_functions import is_default_semantic_model
 
-    # https://learn.microsoft.com/en-us/rest/api/power-bi/datasets/update-dataset-in-group
-
     (workspace, workspace_id) = resolve_workspace_name_and_id(workspace)
     dataset_id = resolve_dataset_id(dataset, workspace)