debug

app.py

@@ -133,6 +133,7 @@ def split_corpus(corpus, n):
         yield corpus_split[i:i + n]
 
 def compute_coherence_values_base_lda(dictionary, corpus, texts, limit, coherence, start=2, step=1):
+    print('compute coherence values base lda')
     coherence_values = []
     model_list = []
     for num_topics in range(start, limit, step):
@@ -274,7 +275,6 @@ def full_lda(df):
         training_corpus = corpus_split
         training_corpus.remove(training_corpus[i])
         # print(training_corpus[i])
-        print(training_corpus)
         model_list, coherence_values = compute_coherence_values_base_lda(dictionary=id2word, 
                                                             corpus=training_corpus,
                                                             texts=df['lemma_tokens'],
@@ -282,7 +282,7 @@ def full_lda(df):
                                                             limit=10,
                                                             step=1,
                                                             coherence='c_v')
-        print(model_list + str(i))
+        # print(model_list + str(i))
         print(coherence_values + str(i))
         for j in range(len(coherence_values)):
             coherence_averages[j] += coherence_values[j]