updates

utils/interp_space_utils.py

@@ -549,14 +549,14 @@ def compute_clusters_style_representation_3(
     cluster_ids: List[Any],
     cluster_label_clm_name: str = 'authorID',
     max_num_feats: int = 25,
-    max_num_documents_per_author=1,
+    max_num_documents_per_author=10,
     max_num_authors=10,
     max_authors_for_span_extraction=4,
     top_k: int = 10
     ):
 
     print(f"Computing style representation for visible clusters: {len(cluster_ids)}")
-    # STEP 1: Identify features on 5 visible authors
+    # STEP 1: Identify features on max_num_authors's max_num_documents_per_author number of documents
     background_corpus_df['fullText'] = background_corpus_df['fullText'].map(lambda x: '\n\n'.join(x[:max_num_documents_per_author]) if isinstance(x, list) else x)
     background_corpus_df_feat_id = background_corpus_df[background_corpus_df[cluster_label_clm_name].isin(cluster_ids)]