Screeners (Experimental)

class ExecutiveNarrativeFactor[source]
__init__(llm_model, main_theme, companies, start_date, end_date, fiscal_year, sources=None, rerank_threshold=None, focus='')[source]

This class will track executive narratives in company transcripts.

Parameters:

  • llm_model (str) – LLM <provider::model> to be used in text processing and analysis. For example, “openai::gpt-4o-mini”.

  • main_theme (str) – The main theme to screen for in the companies received. A list of sub-themes will be generated based on this main theme.

  • companies (List[Company]) – List of companies to analyze.

  • start_date (str) – The start date for searching relevant documents. Format: YYYY-MM-DD.

  • end_date (str) – The end date for searching relevant documents. Format: YYYY-MM-DD.

  • fiscal_year (int) – The fiscal year that will be analyzed.

  • sources (Optional[List[str]]) – Used to filter search results by the sources of the documents. If not provided, the search is run across all available sources.

  • rerank_threshold (Optional[float]) – The threshold for reranking the search results. See https://sdk.bigdata.com/en/latest/how_to_guides/rerank_search.html.

  • focus (Optional[str]) – The focus of the analysis. No value by default. If used, generated sub-themes will be based on this.

screen_companies(document_limit=10, batch_size=10, frequency='3M', export_path=None)[source]

Screen companies for the Executive Narrative Factor.

Parameters:

  • document_limit (int) – The maximum number of documents to return per Bigdata query.

  • batch_size (int) – The number of entities to include in each batched query.

  • frequency (str) – The frequency of the date ranges. Supported values: - ‘Y’: Yearly intervals. - ‘M’: Monthly intervals. - ‘W’: Weekly intervals. - ‘D’: Daily intervals. Defaults to ‘3M’.

  • export_path (str) – Optional path to export results to an Excel file.

Returns:

  • df_labeled: The DataFrame with the labeled search results.

  • df_company: The DataFrame with the output by company.

  • df_industry: The DataFrame with the output by industry.

  • theme_tree: The ThemeTree created for the screening.

Return type:

dict