TELF.post_processing.Fox: Report generation tool for text data from HNMFk using local LLMs#

Report generation tool for text data from HNMFk using local LLMs.

Available Functions#

`Fox.__init__`([summary_model, api_key, ...])
`Fox.post_process`(npz_path, vocabulary_path, ...)
`Fox.post_process_stats`(processing_path[, ...])
`Fox.makeSummariesAndLabelsOpenAi`(processing_path)
`Fox.rename_cluster_dirs_from_stats`(...)
`Fox.getApiKey`()
`Fox.setApiKey`(api_key)
`Fox.getSummaryModel`()
`Fox.setSummaryModel`(summary_model)
`ClusterSummarizer.__init__`([api_key, ...])
`ClusterSummarizer.generate_labels_and_summaries`(...)
`DirectoryManager.__init__`()
`DirectoryManager.rename_from_stats`(...)	Renames cluster directories using label and document count from stats.csv.

class TELF.post_processing.Fox.fox.ClusterSummarizer(api_key=None, summary_model=None)[source]#

Bases: object

class TELF.post_processing.Fox.fox.DirectoryManager[source]#

Bases: object

rename_from_stats(post_processed_df_path: str)[source]#

Renames cluster directories using label and document count from stats.csv.

Format:: <cluster>-<label>_<num_papers>-documents OR if no label: <cluster>-unlabeled_<num_papers>-documents

class TELF.post_processing.Fox.fox.Fox(summary_model=None, api_key=None, verbose=False, debug=False)[source]#

Bases: object

post_process(npz_path: str, vocabulary_path: str, src_decomp_data_path: str, output_dir: str = None, top_words_per_cluster: int = 50, clean_cols_name: str = 'clean_title_abstract', terms: list = None) → str[source]#

post_process_stats(processing_path: str, clean_cols_name: str = 'clean_title_abstract')[source]#