small fix

IBM · May 4, 2022 · 927a145 · 927a145
1 parent 83ae8d2
commit 927a145
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 8 deletions.
diff --git a/examples/ex1_sib_cluster_20ng.py b/examples/ex1_sib_cluster_20ng.py
@@ -91,12 +91,9 @@
 clusters = clustering_utils.get_clusters(sib.labels_)
 cluster_key_terms = clustering_utils.get_key_terms(vectors, clusters,
                                                    p_value_threshold=0.01, top_k=15)
-cluster_key_texts = clustering_utils.get_ket_texts(vectors, clusters, cluster_key_terms, 2)
 p_value_analysis_end_t = time()
 print("P-value analysis time: %.3f secs." % (p_value_analysis_end_t - p_value_analysis_start_t))
 
-print(cluster_key_texts)
-
 # step 6 - align the generated clusters to the original classes
 # this is done only for having a more informative report
 label_enrichment = clustering_utils.get_enriched_labels(gold_labels, sib.labels_,

diff --git a/src/sib/clustering_utils.py b/src/sib/clustering_utils.py
@@ -68,10 +68,7 @@ def get_binary_vectors(vectors):
     return binary_vectors
 
 
-def get_key_terms(vectors, labels, p_value_threshold, top_k):
-    # map from cluster id to cluster elements
-    clusters = get_clusters(labels)
-
+def get_key_terms(vectors, clusters, p_value_threshold, top_k):
     # perform document-level analysis. count every token only once per document.
     binary_vectors = get_binary_vectors(vectors)
     p_values = calc_p_value_doc_level(binary_vectors, clusters)
@@ -91,7 +88,7 @@ def get_key_terms(vectors, labels, p_value_threshold, top_k):
     return result
 
 
-def get_ket_texts(vectors, clusters, key_terms, top_k):
+def get_key_texts(vectors, clusters, key_terms, top_k):
     binary_vectors = get_binary_vectors(vectors)
     result = {}
     for cluster_id, cluster_key_terms in key_terms.items():