Spaces:
Running
Running
Fredrik Sitje
commited on
Commit
·
6b21293
1
Parent(s):
c3069c3
Optimize term-category pair filtering in Streamlit app by converting DataFrame to a list for improved performance. This change enhances efficiency by avoiding the use of iterrows, streamlining the data processing workflow.
Browse files- src/streamlit_app.py +5 -2
src/streamlit_app.py
CHANGED
|
@@ -709,9 +709,12 @@ def get_term_category_pairs(df):
|
|
| 709 |
# Sort by term name and category_index
|
| 710 |
all_pairs_df = all_pairs_df.sort_values(['term', 'category_index'])
|
| 711 |
|
|
|
|
|
|
|
|
|
|
| 712 |
# Filter out categories that have no subcategories after filtering Unknown answers
|
| 713 |
-
filtered_pairs = [(
|
| 714 |
-
if category_has_subcategories(
|
| 715 |
|
| 716 |
return filtered_pairs
|
| 717 |
|
|
|
|
| 709 |
# Sort by term name and category_index
|
| 710 |
all_pairs_df = all_pairs_df.sort_values(['term', 'category_index'])
|
| 711 |
|
| 712 |
+
# Convert to list efficiently (avoids slow iterrows)
|
| 713 |
+
all_pairs_list = all_pairs_df[['term', 'category']].values.tolist()
|
| 714 |
+
|
| 715 |
# Filter out categories that have no subcategories after filtering Unknown answers
|
| 716 |
+
filtered_pairs = [(term, category) for term, category in all_pairs_list
|
| 717 |
+
if category_has_subcategories(term, category, df)]
|
| 718 |
|
| 719 |
return filtered_pairs
|
| 720 |
|