themefinder 0.4.1__py3-none-any.whl → 0.5.3__py3-none-any.whl

themefinder/core.py

@@ -95,7 +95,7 @@ async def find_themes(
     return {
         "question": question,
         "sentiment": sentiment_df,
-        "topics": theme_df,
+        "themes": theme_df,
         "condensed_themes": condensed_theme_df,
         "refined_themes": refined_theme_df,
         "mapping": mapping_df,
@@ -106,7 +106,7 @@ async def sentiment_analysis(
     responses_df: pd.DataFrame,
     llm: Runnable,
     question: str,
-    batch_size: int = 10,
+    batch_size: int = 20,
     prompt_template: str | Path | PromptTemplate = "sentiment_analysis",
     system_prompt: str = CONSULTATION_SYSTEM_PROMPT,
 ) -> pd.DataFrame:
@@ -121,7 +121,7 @@ async def sentiment_analysis(
         llm (Runnable): Language model instance to use for sentiment analysis.
         question (str): The survey question.
         batch_size (int, optional): Number of responses to process in each batch.
-            Defaults to 10.
+            Defaults to 20.
         prompt_template (str | Path | PromptTemplate, optional): Template for structuring
             the prompt to the LLM. Can be a string identifier, path to template file,
             or PromptTemplate instance. Defaults to "sentiment_analysis".
@@ -224,7 +224,7 @@ async def theme_condensation(
         pd.DataFrame: DataFrame containing the condensed themes, where similar topics
             have been combined into broader categories.
     """
-    logger.info(f"Running theme condensation on {len(themes_df)} responses")
+    logger.info(f"Running theme condensation on {len(themes_df)} themes")
     themes_df["response_id"] = range(len(themes_df))
 
     n_themes = themes_df.shape[0]

themefinder/llm_batch_processor.py

@@ -174,7 +174,6 @@ def generate_prompts(
         to the prompt template as the 'responses' variable.
     """
     batched_prompts = []
-
     for df in response_dfs:
         prompt = prompt_template.format(
             responses=df.to_dict(orient="records"), **kwargs
@@ -275,7 +274,7 @@ def check_response_integrity(
     if returned_ids_set != response_ids_set:
         logger.info("Failed integrity check")
         logger.info(
-            f"Present in original but not returned from LLM: {response_ids_set - returned_ids_set}. Returned in LLM but not present in original: {returned_ids_set -response_ids_set}"
+            f"Present in original but not returned from LLM: {response_ids_set - returned_ids_set}. Returned in LLM but not present in original: {returned_ids_set - response_ids_set}"
         )
         return False
     return True

themefinder/prompts/sentiment_analysis.txt

@@ -20,6 +20,9 @@ The final output should be in the following JSON format:
     ...
 ]}}
 
+You MUST include every response ID in the output.
+If the response can not be labelled return empty sections where appropriate but you MUST return an entry
+with the correct response ID for each input object
 
 ## EXAMPLE
 Example 1:

themefinder/prompts/theme_mapping.txt

@@ -10,9 +10,9 @@ You will be given:
         {{'response_id': 'free text response'}}
 
 Your task is to analyze each response and decide which topics are present. Guidelines:
-    - You can only assign a response to a topic in the provided TOPIC LIST
+    - You can only assign to a response to a topic in the provided TOPIC LIST
     - A response doesn't need to exactly match the language used in the TOPIC LIST, it should be considered a match if it expresses a similar sentiment.
-    - You must use the alphabetic 'topic_id' to indicate which topic you have assigned.
+    - You must use the alphabetic 'topic_id' to indicate which topic you have assigned. Do not use the full topic description
     - Each response can be assigned to multiple topics if it matches more than one topic from the TOPIC LIST.
     - There is no limit on how many topics can be assigned to a response.
     - For each assignment provide a single rationale for why you have chosen the label.
@@ -20,6 +20,10 @@ Your task is to analyze each response and decide which topics are present. Guide
     - If a response contains both positive and negative statements about a topic within the same response, choose the stance that receives more emphasis or appears more central to the argument
     - The order of reasons and stances must align with the order of labels (e.g., stance_a applies to topic_a)
 
+You MUST include every response ID in the output.
+If the response can not be labelled return empty sections where appropriate but you MUST return an entry
+with the correct response ID for each input object.
+You must only return the alphabetic topic_ids in the labels section.
 
 The final output should be in the following JSON format:
 

{themefinder-0.4.1.dist-info → themefinder-0.5.3.dist-info}/METADATA

@@ -1,17 +1,18 @@
 Metadata-Version: 2.3
 Name: themefinder
-Version: 0.4.1
+Version: 0.5.3
 Summary: A topic modelling Python package designed for analysing one-to-many question-answer data eg free-text survey responses.
 License: MIT
 Author: i.AI
 Author-email: packages@cabinetoffice.gov.uk
-Requires-Python: >=3.12,<4.0
+Requires-Python: >=3.10,<3.13
 Classifier: Intended Audience :: Developers
 Classifier: Intended Audience :: Science/Research
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
-Classifier: Programming Language :: Python :: 3.13
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Classifier: Topic :: Text Processing :: Linguistic
 Requires-Dist: boto3 (>=1.29,<2.0)

{themefinder-0.4.1.dist-info → themefinder-0.5.3.dist-info}/RECORD

@@ -1,15 +1,15 @@
 themefinder/__init__.py,sha256=p6QoCgA-BYWljk8yPOeTgkNcN5m_gA_o3Q86Eh0QjSM,327
-themefinder/core.py,sha256=gLvWfDxHKwKlcozAZkqbJyMsBoIqWEjxIqQ-mpFIvqk,17541
-themefinder/llm_batch_processor.py,sha256=VToyxuVDRzh3SFbVq9HnkU1F8YNsZqmYvCoznvLt22c,12573
+themefinder/core.py,sha256=B6Du59rPsZbBcP8tkKmXQn6h5vvLN_PZIferPnF3LNY,17538
+themefinder/llm_batch_processor.py,sha256=SDDeMJeX1J3u7FGFddRhVSxty6U8lFVXwG4eNI_0C5o,12573
 themefinder/prompts/consultation_system_prompt.txt,sha256=_A07oY_an4hnRx-9pQ0y-TLXJz0dd8vDI-MZne7Mdb4,89
-themefinder/prompts/sentiment_analysis.txt,sha256=nisBTu4hW0nXB8V_BjQ-1balkuj1E2lRDz5zDjxM7cQ,1626
+themefinder/prompts/sentiment_analysis.txt,sha256=e3DcUKga6pSFcfeo2TAq8x9LXk0YDV-D7P2gtymcyuc,1832
 themefinder/prompts/theme_condensation.txt,sha256=GFwwQO_oZHhqhPnAfTn887fDzAIVxKoCyj0hXagyBIU,1645
 themefinder/prompts/theme_generation.txt,sha256=JMXuNojxdSAcxPRU1Jg12Xunv_dX4hNvXYU2pXMWTAw,2500
-themefinder/prompts/theme_mapping.txt,sha256=hiyGdWIR7UWdF1g7yqN_kL7o58LFyLtBVVrfJvGcsVU,2088
+themefinder/prompts/theme_mapping.txt,sha256=nb_D7gwKGd8BzrAlzSZC3mQIPYaCRXdE6XmoJaJEKZQ,2405
 themefinder/prompts/theme_refinement.txt,sha256=HCgvWAoz-cpFgjX_QS_VVY0X06d4ds0ekBgcoWyFyfg,3360
 themefinder/prompts/theme_target_alignment.txt,sha256=-_ghr4--KAN6Tz8ExO9s2IXvI6pjWaEA_nG5L83GV5I,1035
 themefinder/themefinder_logging.py,sha256=n5SUQovEZLC4skEbxicjz_fOGF9mOk3S-Wpj5uXsaL8,314
-themefinder-0.4.1.dist-info/LICENCE,sha256=C9ULIN0ctF60ZxUWH_hw1H434bDLg49Z-Qzn6BUHgqs,1060
-themefinder-0.4.1.dist-info/METADATA,sha256=GFqwQ6Gss61JCuTXz9RjlSnus6Rrgvy1L9KCifoEhpc,6431
-themefinder-0.4.1.dist-info/WHEEL,sha256=IYZQI976HJqqOpQU6PHkJ8fb3tMNBFjg-Cn-pwAbaFM,88
-themefinder-0.4.1.dist-info/RECORD,,
+themefinder-0.5.3.dist-info/LICENCE,sha256=C9ULIN0ctF60ZxUWH_hw1H434bDLg49Z-Qzn6BUHgqs,1060
+themefinder-0.5.3.dist-info/METADATA,sha256=o9rzrhRK-4PMAv9wS8ZrnmTw1rTSYGU8zfPbB31r1DU,6483
+themefinder-0.5.3.dist-info/WHEEL,sha256=XbeZDeTWKc1w7CSIyre5aMDU_-PohRwTQceYnisIYYY,88
+themefinder-0.5.3.dist-info/RECORD,,

{themefinder-0.4.1.dist-info → themefinder-0.5.3.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: poetry-core 2.0.1
+Generator: poetry-core 2.1.1
 Root-Is-Purelib: true
 Tag: py3-none-any