Skip to content

Added return_df parameter to run_model_bpa_bulk #580

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Added return_df parameter to run_model_bpa_bulk #580

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
33a2bcc
Added return_df parameter
AkhilGrandhi Mar 20, 2025
05e2781
Updated the return df logic
AkhilGrandhi Mar 31, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 14 additions & 0 deletions src/sempy_labs/_model_bpa_bulk.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,7 @@ def run_model_bpa_bulk(
workspace: Optional[str | UUID | List[str | UUID]] = None,
skip_models: Optional[str | List[str]] = ["ModelBPA", "Fabric Capacity Metrics"],
skip_models_in_workspace: Optional[dict] = None,
return_df: bool = False,
):
"""
Runs the semantic model Best Practice Analyzer across all semantic models in a workspace (or all accessible workspaces).
Expand All @@ -54,6 +55,7 @@ def run_model_bpa_bulk(
"Workspace A": ["Dataset1", "Dataset2"],
"Workspace B": ["Dataset5", "Dataset 8"],
}
return_df: bool = False (default: False) – If set to True, it will return the BPA rules as a DataFrame for the specified workspaces.`
"""

if not lakehouse_attached():
Expand All @@ -66,6 +68,9 @@ def run_model_bpa_bulk(

skip_models.extend(["ModelBPA", "Fabric Capacity Metrics"])

#Declaring a tempDf to return the BPARules
tempDf = pd.DataFrame()

now = datetime.datetime.now()
output_table = "modelbparesults"
lakeT = get_lakehouse_tables()
Expand Down Expand Up @@ -175,6 +180,9 @@ def run_model_bpa_bulk(
for key, value in icons.bpa_schema.items()
}

#Appending all the dfs to tempDf
tempDf = pd.concat([tempDf, df], ignore_index=True)

save_as_delta_table(
dataframe=df,
delta_table_name=output_table,
Expand All @@ -185,6 +193,9 @@ def run_model_bpa_bulk(
print(
f"{icons.green_dot} Saved BPA results to the '{output_table}' delta table."
)
#If `return_df` is set to `True`, it will return the BPA rules result as a DataFrame.
if(return_df):
return tempDf

print(f"{icons.green_dot} Bulk BPA scan complete.")

Expand Down Expand Up @@ -227,6 +238,9 @@ def create_model_bpa_semantic_model(
lakehouse=lakehouse, workspace=lakehouse_workspace_id
)




# Generate the shared expression based on the lakehouse and lakehouse workspace
expr = generate_shared_expression(
item_name=lakehouse_name,
Expand Down