cat-llm 0.0.70__tar.gz → 0.0.72__tar.gz

{cat_llm-0.0.70 → cat_llm-0.0.72}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cat-llm
-Version: 0.0.70
+Version: 0.0.72
 Summary: A tool for categorizing text data and images using LLMs and vision models
 Project-URL: Documentation, https://github.com/chrissoria/cat-llm#readme
 Project-URL: Issues, https://github.com/chrissoria/cat-llm/issues

{cat_llm-0.0.70 → cat_llm-0.0.72}/src/catllm/__about__.py

@@ -1,7 +1,7 @@
 # SPDX-FileCopyrightText: 2025-present Christopher Soria <chrissoria@berkeley.edu>
 #
 # SPDX-License-Identifier: MIT
-__version__ = "0.0.70"
+__version__ = "0.0.72"
 __author__ = "Chris Soria"
 __email__ = "chrissoria@berkeley.edu"
 __title__ = "cat-llm"

{cat_llm-0.0.70 → cat_llm-0.0.72}/src/catllm/text_functions.py

@@ -726,14 +726,18 @@ def multi_class(
         .map({True: 'error', False: 'success'})
     )
 
-    categorized_data.loc[categorized_data[cat_cols].apply(pd.to_numeric, errors='coerce').isna().any(axis=1), cat_cols] = np.nan
+    categorized_data.loc[
+        categorized_data[cat_cols].apply(pd.to_numeric, errors='coerce').isna().any(axis=1), 
+        cat_cols
+    ] = pd.NA
+
     categorized_data[cat_cols] = categorized_data[cat_cols].astype('Int64')
 
-    categorized_data['categories_present'] = categorized_data[cat_cols].apply(
+    categorized_data['categories_id'] = categorized_data[cat_cols].apply(
         lambda x: ','.join(x.dropna().astype(str)), axis=1
     )
 
-    categorized_data['categories_counted'] = categorized_data[cat_cols].count(axis=1)
+    categorized_data['categories_present'] = categorized_data[cat_cols].sum(axis=1)
 
     if to_csv:
         if save_directory is None: