gsdmm-coherence-score.py

# import library from gensim  
from gensim.models import CoherenceModel

# define function to get words in topics
def get_topics_lists(model, top_clusters, n_words):
    '''
    Gets lists of words in topics as a list of lists.
    
    model: gsdmm instance
    top_clusters:  numpy array containing indices of top_clusters
    n_words: top n number of words to include
    
    '''
    # create empty list to contain topics
    topics = []
    
    # iterate over top n clusters
    for cluster in top_clusters:
        #create sorted dictionary of word distributions
        sorted_dict = sorted(model.cluster_word_distribution[cluster].items(), key=lambda k: k[1], reverse=True)[:n_words]
         
        #create empty list to contain words
        topic = []
        
        #iterate over top n words in topic
        for k,v in sorted_dict:
            #append words to topic list
            topic.append(k)
            
        #append topics to topics list    
        topics.append(topic)
    
    return topics

# get topics to feed to coherence model
topics = get_topics_lists(gsdmm, top_index, 20) 

# evaluate model using Topic Coherence score
cm_gsdmm = CoherenceModel(topics=topics, 
                          dictionary=dictionary, 
                          corpus=bow_corpus, 
                          texts=docs, 
                          coherence='c_v')

# get coherence value
coherence_gsdmm = cm_gsdmm.get_coherence()  

print(coherence_gsdmm)