themefinder 0.4.1__tar.gz → 0.5.3__tar.gz

{themefinder-0.4.1 → themefinder-0.5.3}/PKG-INFO

@@ -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 → themefinder-0.5.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "themefinder"
-version = "0.4.1"
+version = "0.5.3"
 description = "A topic modelling Python package designed for analysing one-to-many question-answer data eg free-text survey responses."
 authors = ["i.AI <packages@cabinetoffice.gov.uk>"]
 packages = [{include = "themefinder", from = "src"}]
@@ -17,7 +17,7 @@ classifiers = [
 
 
 [tool.poetry.dependencies]
-python = ">=3.12,<4.0"
+python = ">=3.10,<3.13"
 langchain = "*"
 langchain-openai = "0.1.17"
 pandas = "^2.2.2"

{themefinder-0.4.1 → themefinder-0.5.3}/src/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-0.4.1 → themefinder-0.5.3}/src/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-0.4.1 → themefinder-0.5.3}/src/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-0.4.1 → themefinder-0.5.3}/src/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: