Merge branch 'm-kovalsky/093'

Author: m-kovalsky

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=0.9.2&style=flat)](https://readthedocs.org/projects/semantic-link-labs/)
+[![Read The Docs](https://readthedocs.org/projects/semantic-link-labs/badge/?version=0.9.3&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)
 
@@ -119,6 +119,7 @@ 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
+* [0.9.3](https://github.com/microsoft/semantic-link-labs/releases/tag/0.9.3) (February 13, 2025)
 * [0.9.2](https://github.com/microsoft/semantic-link-labs/releases/tag/0.9.2) (February 5, 2025)
 * [0.9.1](https://github.com/microsoft/semantic-link-labs/releases/tag/0.9.1) (January 22, 2025)
 * [0.9.0](https://github.com/microsoft/semantic-link-labs/releases/tag/0.9.0) (January 22, 2025)

docs/source/conf.py

@@ -13,7 +13,7 @@
 project = 'semantic-link-labs'
 copyright = '2024, Microsoft and community'
 author = 'Microsoft and community'
-release = '0.9.2'
+release = '0.9.3'
 
 # -- General configuration ---------------------------------------------------
 # https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration

pyproject.toml

@@ -7,7 +7,7 @@ name="semantic-link-labs"
 authors = [
     { name = "Microsoft Corporation" },
 ]
-version="0.9.2"
+version="0.9.3"
 description="Semantic Link Labs for Microsoft Fabric"
 readme="README.md"
 requires-python=">=3.10,<3.12"

src/sempy_labs/_delta_analyzer.py

@@ -63,11 +63,11 @@ def delta_analyzer(
     """
     import notebookutils
 
-    display_toggle = notebookutils.common.configs.pandas_display
+    # display_toggle = notebookutils.common.configs.pandas_display
 
     # Turn off notebookutils display
-    if display_toggle is True:
-        notebookutils.common.configs.pandas_display = False
+    # if display_toggle is True:
+    #    notebookutils.common.configs.pandas_display = False
 
     prefix = "SLL_DeltaAnalyzer_"
     now = datetime.datetime.now()
@@ -93,7 +93,7 @@ def delta_analyzer(
     table_path = f"{local_path}/Tables/{table_name}"
 
     # Set back to original value
-    notebookutils.common.configs.pandas_display = display_toggle
+    # notebookutils.common.configs.pandas_display = display_toggle
 
     parquet_file_df_columns = {
         "ParquetFile": "string",
@@ -247,15 +247,15 @@ def delta_analyzer(
                 table_name=table_name,
                 column_name=col_name,
                 function="approx",
-                lakehouse=lakehouse_name,
+                lakehouse=lakehouse,
                 workspace=workspace,
             )
         else:
             dc = _get_column_aggregate(
                 table_name=table_name,
                 column_name=col_name,
                 function="distinctcount",
-                lakehouse=lakehouse_name,
+                lakehouse=lakehouse,
                 workspace=workspace,
             )
 
@@ -288,7 +288,7 @@ def delta_analyzer(
             runId = 1
         else:
             max_run_id = _get_column_aggregate(
-                lakehouse=lakehouse_name, table_name=save_table
+                table_name=save_table,
             )
             runId = max_run_id + 1
 

src/sempy_labs/_helper_functions.py

@@ -544,7 +544,8 @@ def save_as_delta_table(
             f"{icons.red_dot} Invalid 'delta_table_name'. Delta tables in the lakehouse cannot have spaces in their names."
         )
 
-    dataframe.columns = dataframe.columns.str.replace(" ", "_")
+    dataframe.columns = [col.replace(" ", "_") for col in dataframe.columns]
+
     spark = _create_spark_session()
 
     type_mapping = {
@@ -1617,7 +1618,7 @@ def _create_spark_session():
     return SparkSession.builder.getOrCreate()
 
 
-def _read_delta_table(path: str) -> pd.DataFrame:
+def _read_delta_table(path: str):
 
     spark = _create_spark_session()
 

src/sempy_labs/_model_bpa_rules.py

@@ -74,9 +74,7 @@ def model_bpa_rules(
                 "Info",
                 "Check if dynamic row level security (RLS) is necessary",
                 lambda obj, tom: any(
-                    re.search(
-                        pattern, obj.FilterExpression, flags=re.IGNORECASE
-                    )
+                    re.search(pattern, obj.FilterExpression, flags=re.IGNORECASE)
                     for pattern in ["USERPRINCIPALNAME()", "USERNAME()"]
                 ),
                 "Usage of dynamic row level security (RLS) can add memory and performance overhead. Please research the pros/cons of using it.",
@@ -253,9 +251,7 @@ def model_bpa_rules(
                 "Warning",
                 "Reduce usage of calculated columns that use the RELATED function",
                 lambda obj, tom: obj.Type == TOM.ColumnType.Calculated
-                and re.search(
-                    r"related\s*\(", obj.Expression, flags=re.IGNORECASE
-                ),
+                and re.search(r"related\s*\(", obj.Expression, flags=re.IGNORECASE),
                 "Calculated columns do not compress as well as data columns and may cause longer processing times. As such, calculated columns should be avoided if possible. One scenario where they may be easier to avoid is if they use the RELATED function.",
                 "https://www.sqlbi.com/articles/storage-differences-between-calculated-columns-and-calculated-tables",
             ),
@@ -666,9 +662,7 @@ def model_bpa_rules(
                 "Column",
                 "Warning",
                 "Provide format string for 'Date' columns",
-                lambda obj, tom: (
-                    re.search(r"date", obj.Name, flags=re.IGNORECASE)
-                )
+                lambda obj, tom: (re.search(r"date", obj.Name, flags=re.IGNORECASE))
                 and (obj.DataType == TOM.DataType.DateTime)
                 and (obj.FormatString != "mm/dd/yyyy"),
                 'Columns of type "DateTime" that have "Month" in their names should be formatted as "mm/dd/yyyy".',
@@ -766,9 +760,7 @@ def model_bpa_rules(
                 "Column",
                 "Info",
                 "Month (as a string) must be sorted",
-                lambda obj, tom: (
-                    re.search(r"month", obj.Name, flags=re.IGNORECASE)
-                )
+                lambda obj, tom: (re.search(r"month", obj.Name, flags=re.IGNORECASE))
                 and not (re.search(r"months", obj.Name, flags=re.IGNORECASE))
                 and (obj.DataType == TOM.DataType.String)
                 and len(str(obj.SortByColumn)) == 0,
@@ -788,9 +780,7 @@ def model_bpa_rules(
                 "Column",
                 "Warning",
                 'Provide format string for "Month" columns',
-                lambda obj, tom: re.search(
-                    r"month", obj.Name, flags=re.IGNORECASE
-                )
+                lambda obj, tom: re.search(r"month", obj.Name, flags=re.IGNORECASE)
                 and obj.DataType == TOM.DataType.DateTime
                 and obj.FormatString != "MMMM yyyy",
                 'Columns of type "DateTime" that have "Month" in their names should be formatted as "MMMM yyyy".',

src/sempy_labs/tom/_model.py

@@ -3412,7 +3412,10 @@ def create_pattern(tableList, b):
                     if c.Name == obj.Name:
                         tableList.append(c.Parent.Name)
                 if (
-                    re.search(create_pattern(tableList, re.escape(obj.Name)), object.Expression)
+                    re.search(
+                        create_pattern(tableList, re.escape(obj.Name)),
+                        object.Expression,
+                    )
                     is not None
                 ):
                     yield obj