semantic-link-labs 0.8.7__tar.gz → 0.8.9__tar.gz

{semantic_link_labs-0.8.7 → semantic_link_labs-0.8.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: semantic-link-labs
-Version: 0.8.7
+Version: 0.8.9
 Summary: Semantic Link Labs for Microsoft Fabric
 Author: Microsoft Corporation
 License: MIT License
@@ -27,7 +27,7 @@ Requires-Dist: pytest>=8.2.1; extra == "test"
 # Semantic Link Labs
 
 [![PyPI version](https://badge.fury.io/py/semantic-link-labs.svg)](https://badge.fury.io/py/semantic-link-labs)
-[![Read The Docs](https://readthedocs.org/projects/semantic-link-labs/badge/?version=0.8.7&style=flat)](https://readthedocs.org/projects/semantic-link-labs/)
+[![Read The Docs](https://readthedocs.org/projects/semantic-link-labs/badge/?version=0.8.9&style=flat)](https://readthedocs.org/projects/semantic-link-labs/)
 [![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
 [![Downloads](https://static.pepy.tech/badge/semantic-link-labs)](https://pepy.tech/project/semantic-link-labs)
 
@@ -141,6 +141,8 @@ An even better way to ensure the semantic-link-labs library is available in your
 2. Select your newly created environment within the 'Environment' drop down in the navigation bar at the top of the notebook
 
 ## Version History
+* [0.8.9](https://github.com/microsoft/semantic-link-labs/releases/tag/0.8.9) (December 4, 2024)
+* [0.8.8](https://github.com/microsoft/semantic-link-labs/releases/tag/0.8.8) (November 28, 2024)
 * [0.8.7](https://github.com/microsoft/semantic-link-labs/releases/tag/0.8.7) (November 27, 2024)
 * [0.8.6](https://github.com/microsoft/semantic-link-labs/releases/tag/0.8.6) (November 14, 2024)
 * [0.8.5](https://github.com/microsoft/semantic-link-labs/releases/tag/0.8.5) (November 13, 2024)

{semantic_link_labs-0.8.7 → semantic_link_labs-0.8.9}/README.md

@@ -1,7 +1,7 @@
 # Semantic Link Labs
 
 [![PyPI version](https://badge.fury.io/py/semantic-link-labs.svg)](https://badge.fury.io/py/semantic-link-labs)
-[![Read The Docs](https://readthedocs.org/projects/semantic-link-labs/badge/?version=0.8.7&style=flat)](https://readthedocs.org/projects/semantic-link-labs/)
+[![Read The Docs](https://readthedocs.org/projects/semantic-link-labs/badge/?version=0.8.9&style=flat)](https://readthedocs.org/projects/semantic-link-labs/)
 [![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
 [![Downloads](https://static.pepy.tech/badge/semantic-link-labs)](https://pepy.tech/project/semantic-link-labs)
 
@@ -115,6 +115,8 @@ An even better way to ensure the semantic-link-labs library is available in your
 2. Select your newly created environment within the 'Environment' drop down in the navigation bar at the top of the notebook
 
 ## Version History
+* [0.8.9](https://github.com/microsoft/semantic-link-labs/releases/tag/0.8.9) (December 4, 2024)
+* [0.8.8](https://github.com/microsoft/semantic-link-labs/releases/tag/0.8.8) (November 28, 2024)
 * [0.8.7](https://github.com/microsoft/semantic-link-labs/releases/tag/0.8.7) (November 27, 2024)
 * [0.8.6](https://github.com/microsoft/semantic-link-labs/releases/tag/0.8.6) (November 14, 2024)
 * [0.8.5](https://github.com/microsoft/semantic-link-labs/releases/tag/0.8.5) (November 13, 2024)

{semantic_link_labs-0.8.7 → semantic_link_labs-0.8.9}/docs/source/conf.py

@@ -13,7 +13,7 @@ sys.path.insert(0, os.path.abspath('../../src/'))
 project = 'semantic-link-labs'
 copyright = '2024, Microsoft and community'
 author = 'Microsoft and community'
-release = '0.8.7'
+release = '0.8.9'
 
 # -- General configuration ---------------------------------------------------
 # https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration

{semantic_link_labs-0.8.7 → semantic_link_labs-0.8.9}/pyproject.toml

@@ -7,7 +7,7 @@ name="semantic-link-labs"
 authors = [
     { name = "Microsoft Corporation" },
 ]
-version="0.8.7"
+version="0.8.9"
 description="Semantic Link Labs for Microsoft Fabric"
 readme="README.md"
 requires-python=">=3.10,<3.12"

{semantic_link_labs-0.8.7 → semantic_link_labs-0.8.9}/src/semantic_link_labs.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: semantic-link-labs
-Version: 0.8.7
+Version: 0.8.9
 Summary: Semantic Link Labs for Microsoft Fabric
 Author: Microsoft Corporation
 License: MIT License
@@ -27,7 +27,7 @@ Requires-Dist: pytest>=8.2.1; extra == "test"
 # Semantic Link Labs
 
 [![PyPI version](https://badge.fury.io/py/semantic-link-labs.svg)](https://badge.fury.io/py/semantic-link-labs)
-[![Read The Docs](https://readthedocs.org/projects/semantic-link-labs/badge/?version=0.8.7&style=flat)](https://readthedocs.org/projects/semantic-link-labs/)
+[![Read The Docs](https://readthedocs.org/projects/semantic-link-labs/badge/?version=0.8.9&style=flat)](https://readthedocs.org/projects/semantic-link-labs/)
 [![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
 [![Downloads](https://static.pepy.tech/badge/semantic-link-labs)](https://pepy.tech/project/semantic-link-labs)
 
@@ -141,6 +141,8 @@ An even better way to ensure the semantic-link-labs library is available in your
 2. Select your newly created environment within the 'Environment' drop down in the navigation bar at the top of the notebook
 
 ## Version History
+* [0.8.9](https://github.com/microsoft/semantic-link-labs/releases/tag/0.8.9) (December 4, 2024)
+* [0.8.8](https://github.com/microsoft/semantic-link-labs/releases/tag/0.8.8) (November 28, 2024)
 * [0.8.7](https://github.com/microsoft/semantic-link-labs/releases/tag/0.8.7) (November 27, 2024)
 * [0.8.6](https://github.com/microsoft/semantic-link-labs/releases/tag/0.8.6) (November 14, 2024)
 * [0.8.5](https://github.com/microsoft/semantic-link-labs/releases/tag/0.8.5) (November 13, 2024)

{semantic_link_labs-0.8.7 → semantic_link_labs-0.8.9}/src/sempy_labs/__init__.py

@@ -190,6 +190,7 @@ from sempy_labs._generate_semantic_model import (
     get_semantic_model_bim,
     get_semantic_model_size,
     update_semantic_model_from_bim,
+    get_semantic_model_definition,
 )
 from sempy_labs._list_functions import (
     list_reports_using_semantic_model,
@@ -456,4 +457,5 @@ __all__ = [
     "create_vnet_gateway",
     "update_vnet_gateway",
     "update_on_premises_gateway",
+    "get_semantic_model_definition",
 ]

{semantic_link_labs-0.8.7 → semantic_link_labs-0.8.9}/src/sempy_labs/_connections.py

@@ -237,7 +237,7 @@ def list_item_connections(
     )
 
     client = fabric.FabricRestClient()
-    response = client.post(f"/v1/workspaces/{workspace_id}/items/{item_id}/connections")
+    response = client.get(f"/v1/workspaces/{workspace_id}/items/{item_id}/connections")
 
     df = pd.DataFrame(
         columns=[

{semantic_link_labs-0.8.7 → semantic_link_labs-0.8.9}/src/sempy_labs/_dax.py

@@ -6,7 +6,7 @@ from sempy_labs._helper_functions import (
     format_dax_object_name,
 )
 from sempy_labs._model_dependencies import get_model_calc_dependencies
-from typing import Optional
+from typing import Optional, List
 from sempy._utils._log import log
 from tqdm.auto import tqdm
 
@@ -67,8 +67,9 @@ def evaluate_dax_impersonation(
 @log
 def get_dax_query_dependencies(
     dataset: str,
-    dax_string: str,
+    dax_string: str | List[str],
     put_in_memory: bool = False,
+    show_vertipaq_stats: bool = True,
     workspace: Optional[str] = None,
 ) -> pd.DataFrame:
     """
@@ -78,10 +79,12 @@ def get_dax_query_dependencies(
     ----------
     dataset : str
         Name of the semantic model.
-    dax_string : str
-        The DAX query.
+    dax_string : str | List[str]
+        The DAX query or list of DAX queries.
     put_in_memory : bool, default=False
         If True, ensures that the dependent columns are put into memory in order to give realistic Vertipaq stats (i.e. Total Size etc.).
+    show_vertipaq_stats : bool, default=True
+        If True, shows vertipaq stats (i.e. Total Size, Data Size, Dictionary Size, Hierarchy Size)
     workspace : str, default=None
         The Fabric workspace name.
         Defaults to None which resolves to the workspace of the attached lakehouse
@@ -96,67 +99,79 @@ def get_dax_query_dependencies(
     if workspace is None:
         workspace = fabric.resolve_workspace_name(workspace)
 
-    # Escape quotes in dax
-    dax_string = dax_string.replace('"', '""')
-    final_query = f"""
-        EVALUATE
-        VAR source_query = "{dax_string}"
-        VAR all_dependencies = SELECTCOLUMNS(
-            INFO.CALCDEPENDENCY("QUERY", source_query),
-                "Referenced Object Type",[REFERENCED_OBJECT_TYPE],
-                "Referenced Table", [REFERENCED_TABLE],
-                "Referenced Object", [REFERENCED_OBJECT]
-            )             
-        RETURN all_dependencies
-        """
-    dep = fabric.evaluate_dax(
-        dataset=dataset, workspace=workspace, dax_string=final_query
-    )
+    if isinstance(dax_string, str):
+        dax_string = [dax_string]
 
-    # Clean up column names and values (remove outside square brackets, underscorees in object type)
-    dep.columns = dep.columns.map(lambda x: x[1:-1])
-    dep["Referenced Object Type"] = (
-        dep["Referenced Object Type"].str.replace("_", " ").str.title()
-    )
-    dep
-
-    # Dataframe df will contain the output of all dependencies of the objects used in the query
-    df = dep.copy()
+    final_df = pd.DataFrame(columns=["Object Type", "Table", "Object"])
 
     cd = get_model_calc_dependencies(dataset=dataset, workspace=workspace)
 
-    for _, r in dep.iterrows():
-        ot = r["Referenced Object Type"]
-        object_name = r["Referenced Object"]
-        table_name = r["Referenced Table"]
-        cd_filt = cd[
-            (cd["Object Type"] == ot)
-            & (cd["Object Name"] == object_name)
-            & (cd["Table Name"] == table_name)
-        ]
-
-        # Adds in the dependencies of each object used in the query (i.e. relationship etc.)
-        if len(cd_filt) > 0:
-            subset = cd_filt[
-                ["Referenced Object Type", "Referenced Table", "Referenced Object"]
+    for dax in dax_string:
+        # Escape quotes in dax
+        dax = dax.replace('"', '""')
+        final_query = f"""
+            EVALUATE
+            VAR source_query = "{dax}"
+            VAR all_dependencies = SELECTCOLUMNS(
+                INFO.CALCDEPENDENCY("QUERY", source_query),
+                    "Referenced Object Type",[REFERENCED_OBJECT_TYPE],
+                    "Referenced Table", [REFERENCED_TABLE],
+                    "Referenced Object", [REFERENCED_OBJECT]
+                )             
+            RETURN all_dependencies
+            """
+        dep = fabric.evaluate_dax(
+            dataset=dataset, workspace=workspace, dax_string=final_query
+        )
+
+        # Clean up column names and values (remove outside square brackets, underscorees in object type)
+        dep.columns = dep.columns.map(lambda x: x[1:-1])
+        dep["Referenced Object Type"] = (
+            dep["Referenced Object Type"].str.replace("_", " ").str.title()
+        )
+
+        # Dataframe df will contain the output of all dependencies of the objects used in the query
+        df = dep.copy()
+
+        for _, r in dep.iterrows():
+            ot = r["Referenced Object Type"]
+            object_name = r["Referenced Object"]
+            table_name = r["Referenced Table"]
+            cd_filt = cd[
+                (cd["Object Type"] == ot)
+                & (cd["Object Name"] == object_name)
+                & (cd["Table Name"] == table_name)
             ]
-            df = pd.concat([df, subset], ignore_index=True)
-
-    df.columns = df.columns.map(lambda x: x.replace("Referenced ", ""))
-    # Remove duplicates
-    df = df.drop_duplicates().reset_index(drop=True)
-    # Only show columns and remove the rownumber column
-    df = df[
-        (df["Object Type"].isin(["Column", "Calc Column"]))
-        & (~df["Object"].str.startswith("RowNumber-"))
+
+            # Adds in the dependencies of each object used in the query (i.e. relationship etc.)
+            if len(cd_filt) > 0:
+                subset = cd_filt[
+                    ["Referenced Object Type", "Referenced Table", "Referenced Object"]
+                ]
+                df = pd.concat([df, subset], ignore_index=True)
+
+        df.columns = df.columns.map(lambda x: x.replace("Referenced ", ""))
+        final_df = pd.concat([df, final_df], ignore_index=True)
+
+    final_df = final_df[
+        (final_df["Object Type"].isin(["Column", "Calc Column"]))
+        & (~final_df["Object"].str.startswith("RowNumber-"))
     ]
+    final_df = final_df.drop_duplicates().reset_index(drop=True)
+    final_df = final_df.rename(columns={"Table": "Table Name", "Object": "Column Name"})
+    final_df.drop(columns=["Object Type"], inplace=True)
+
+    if not show_vertipaq_stats:
+        return final_df
 
     # Get vertipaq stats, filter to just the objects in the df dataframe
-    df["Full Object"] = format_dax_object_name(df["Table"], df["Object"])
+    final_df["Full Object"] = format_dax_object_name(
+        final_df["Table Name"], final_df["Column Name"]
+    )
     dfC = fabric.list_columns(dataset=dataset, workspace=workspace, extended=True)
     dfC["Full Object"] = format_dax_object_name(dfC["Table Name"], dfC["Column Name"])
 
-    dfC_filtered = dfC[dfC["Full Object"].isin(df["Full Object"].values)][
+    dfC_filtered = dfC[dfC["Full Object"].isin(final_df["Full Object"].values)][
         [
             "Table Name",
             "Column Name",

{semantic_link_labs-0.8.7 → semantic_link_labs-0.8.9}/src/sempy_labs/_generate_semantic_model.py

@@ -2,7 +2,7 @@ import sempy.fabric as fabric
 import pandas as pd
 import json
 import os
-from typing import Optional
+from typing import Optional, List
 from sempy_labs._helper_functions import (
     resolve_lakehouse_name,
     resolve_workspace_name_and_id,
@@ -329,8 +329,6 @@ def get_semantic_model_bim(
     """
     Extracts the Model.bim file for a given semantic model.
 
-    This is a wrapper function for the following API: `Items - Get Semantic Model Definition <https://learn.microsoft.com/rest/api/fabric/semanticmodel/items/get-semantic-model-definition>`_.
-
     Parameters
     ----------
     dataset : str
@@ -352,20 +350,9 @@ def get_semantic_model_bim(
         The Model.bim file for the semantic model.
     """
 
-    (workspace, workspace_id) = resolve_workspace_name_and_id(workspace)
-
-    fmt = "TMSL"
-    client = fabric.FabricRestClient()
-    dataset_id = resolve_dataset_id(dataset=dataset, workspace=workspace)
-    response = client.post(
-        f"/v1/workspaces/{workspace_id}/semanticModels/{dataset_id}/getDefinition?format={fmt}",
+    bimJson = get_semantic_model_definition(
+        dataset=dataset, workspace=workspace, format="TMSL", return_dataframe=False
     )
-    result = lro(client, response).json()
-    df_items = pd.json_normalize(result["definition"]["parts"])
-    df_items_filt = df_items[df_items["path"] == "model.bim"]
-    payload = df_items_filt["payload"].iloc[0]
-    bimFile = _decode_b64(payload)
-    bimJson = json.loads(bimFile)
 
     if save_to_file_name is not None:
         if not lakehouse_attached():
@@ -384,12 +371,80 @@ def get_semantic_model_bim(
         with open(filePath, "w") as json_file:
             json.dump(bimJson, json_file, indent=4)
         print(
-            f"{icons.green_dot} The .bim file for the '{dataset}' semantic model has been saved to the '{lakehouse}' in this location: '{filePath}'.\n\n"
+            f"{icons.green_dot} The {fileExt} file for the '{dataset}' semantic model has been saved to the '{lakehouse}' in this location: '{filePath}'.\n\n"
         )
 
     return bimJson
 
 
+def get_semantic_model_definition(
+    dataset: str,
+    format: str = "TMSL",
+    workspace: Optional[str] = None,
+    return_dataframe: bool = True,
+) -> pd.DataFrame | dict | List:
+    """
+    Extracts the semantic model definition.
+
+    This is a wrapper function for the following API: `Items - Get Semantic Model Definition <https://learn.microsoft.com/rest/api/fabric/semanticmodel/items/get-semantic-model-definition>`_.
+
+    Parameters
+    ----------
+    dataset : str
+        Name of the semantic model.
+    format : str, default="TMSL"
+        The output format. Valid options are "TMSL" or "TMDL". "TMSL" returns the .bim file whereas "TMDL" returns the collection of TMDL files. Can also enter 'bim' for the TMSL version.
+    workspace : str, default=None
+        The Fabric workspace name in which the semantic model 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=True
+        If True, returns a dataframe.
+        If False, returns the .bim file for TMSL format. Returns a list of the TMDL files (decoded) for TMDL format.
+
+    Returns
+    -------
+    pandas.DataFrame | dict | List
+        A pandas dataframe with the semantic model definition or the file or files comprising the semantic model definition.
+    """
+
+    valid_formats = ["TMSL", "TMDL"]
+
+    format = format.upper()
+    if format == "BIM":
+        format = "TMSL"
+    if format not in valid_formats:
+        raise ValueError(
+            f"{icons.red_dot} Invalid format. Valid options: {valid_formats}."
+        )
+
+    (workspace, workspace_id) = resolve_workspace_name_and_id(workspace)
+
+    client = fabric.FabricRestClient()
+    dataset_id = resolve_dataset_id(dataset=dataset, workspace=workspace)
+    response = client.post(
+        f"/v1/workspaces/{workspace_id}/semanticModels/{dataset_id}/getDefinition?format={format}",
+    )
+    result = lro(client, response).json()
+
+    files = result["definition"]["parts"]
+
+    if return_dataframe:
+        return pd.json_normalize(files)
+    elif format == "TMSL":
+        payload = next(
+            (part["payload"] for part in files if part["path"] == "model.bim"), None
+        )
+        return json.loads(_decode_b64(payload))
+    else:
+        decoded_parts = [
+            {"file_name": part["path"], "content": _decode_b64(part["payload"])}
+            for part in files
+        ]
+
+        return decoded_parts
+
+
 def get_semantic_model_size(dataset: str, workspace: Optional[str] = None):
 
     workspace = fabric.resolve_workspace_name(workspace)

{semantic_link_labs-0.8.7 → semantic_link_labs-0.8.9}/src/sempy_labs/_model_bpa_bulk.py

@@ -82,7 +82,7 @@ def run_model_bpa_bulk(
     if isinstance(workspace, str):
         workspace = [workspace]
 
-    dfW = fabric.list_workspaces()
+    dfW = fabric.list_workspaces("type ne 'AdminInsights'")
     if workspace is None:
         dfW_filt = dfW.copy()
     else:
@@ -150,7 +150,7 @@ def run_model_bpa_bulk(
 
                         if df.empty:
                             df = bpa_df
-                        if not bpa_df.empty:
+                        elif not bpa_df.empty:
                             df = pd.concat([df, bpa_df], ignore_index=True)
                         print(
                             f"{icons.green_dot} Collected Model BPA stats for the '{dataset_name}' semantic model within the '{wksp}' workspace."

{semantic_link_labs-0.8.7 → semantic_link_labs-0.8.9}/src/sempy_labs/_model_dependencies.py

@@ -198,7 +198,11 @@ def get_model_calc_dependencies(
         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]
+            referenced_object_type = row["Referenced Object Type"]
+            dep_filt = dep[
+                (dep["Full Object Name"] == referenced_full_name)
+                & (dep["Object Type"] == referenced_object_type)
+            ]
             # Expand dependencies and update 'Done' status as needed
             new_rows = []
             for _, dependency in dep_filt.iterrows():