Update src/data_preprocessing.py

src/data_preprocessing.py

@@ -94,29 +94,3 @@ def visualize(topics, df, W1, H1, lda_model, vectorizer):
     ax.invert_yaxis()
   
   return histogram_fig, fig
-
-
-
-
-  # df_doc_topic
-  # print("Perplexity: ", lda_model.perplexity(countidf_vectors))
-
-
-
-
-  # sns.heatmap(df_doc_topic.corr())
-  # plt.show()
-
-
-  # fig, axes = plt.subplots(2, 4, figsize=(30, 15), sharex=True)
-  # axes = axes.flatten()
-  # for topic_idx, topic in enumerate(best_lda_model.components_):
-  #     top_features_ind = topic.argsort()[:-10 - 1:-1]
-  #     top_features = [vectorizer_count.get_feature_names_out()[i] for i in top_features_ind]
-  #     weights = topic[top_features_ind]
-
-  #     ax = axes[topic_idx]
-  #     ax.barh(top_features, weights, height=0.7)
-  #     ax.set_title(f'Topic {topic_idx +1}')
-  #     ax.invert_yaxis()
-  # plt.show()