Updating topic_word

app/pages/01_Topic_Explorer_📚.py

@@ -44,12 +44,13 @@ def main():
     The `y` axis shows which words are closest to a topic centroid. The `x` axis shows how correlated they are.""")
 
     topic_num = st.sidebar.slider("Topic Number", 0, 19, value=0)
+    topic_num_str = f"{topic_num:02}"
     fig = go.Figure(go.Bar(
             x=st.session_state.model.topic_word_scores_reduced[topic_num][::-1],
             y=st.session_state.model.topic_words_reduced[topic_num][::-1],
             orientation='h'))
     fig.update_layout(
-            title=f'Words for Topic {topic_num}',
+            title=f'Words for Topic {topic_num_str}: {st.session_state.topic_str_to_word[topic_num_str]}',
             yaxis_title='Top 20 topic words',
             xaxis_title='Distance to topic centroid'
             )

app/pages/02_Document_Explorer_📖.py

@@ -72,6 +72,7 @@ def main():
     st.button("Reset", help="Will Reset the selected points and the selected topics", on_click=reset)
     data_to_model = st.session_state.data.sort_values(by='topic_id',
                                                       ascending=True)  # to make legend sorted https://bioinformatics.stackexchange.com/a/18847
+    data_to_model['topic_id'].replace(st.session_state.topic_str_to_word, inplace=True)
     fig = px.scatter(data_to_model, x='x', y='y', color='topic_id', template='plotly_dark',
                      hover_data=['id', 'topic_id', 'x', 'y'])
     st.session_state.selected_points = plotly_events(fig, select_event=True, click_event=False)
@@ -84,7 +85,9 @@ def main():
             filter_df()
             cols = ['id', 'topic_id', 'documents']
             data = st.session_state.selected_data[cols]
-            builder = GridOptionsBuilder.from_dataframe(data)
+            data['topic_word'] = data.topic_id.replace(st.session_state.topic_str_to_word)
+            ordered_cols = ['id', 'topic_id', 'topic_word', 'documents']
+            builder = GridOptionsBuilder.from_dataframe(data[ordered_cols])
             builder.configure_pagination()
             go = builder.build()
             AgGrid(st.session_state.selected_data[cols], theme='streamlit', gridOptions=go,

app/pages/03_Semantic_Search_🔍.py

@@ -89,7 +89,9 @@ def main():
 
     with tab1:
         cols = ['id', 'document_scores', 'topic_id', 'documents']
-        builder = GridOptionsBuilder.from_dataframe(st.session_state.data_to_model_without_point.loc[:, cols])
+        data = st.session_state.data_to_model_without_point.loc[:, cols]
+        data['topic_word'] = data.topic_id.replace(st.session_state.topic_str_to_word)
+        builder = GridOptionsBuilder.from_dataframe(data)
         builder.configure_pagination()
         builder.configure_column('document_scores', type=["numericColumn", "numberColumnFilter", "customNumericFormat"],
                                  precision=2)

app/utilities.py

@@ -35,6 +35,9 @@ def initialization():
             topics = pd.read_csv(proj_dir / 'data' / 'topics.csv')
             topics['topic_id'] = topics['topic_id'].apply(lambda x: f'{x:02d}')
             st.session_state.topics = topics
+            topics_dict = topics[['topic_id', 'topic_0']].to_dict()
+            topic_str_to_word = {topics_dict['topic_id'][i]: topics_dict['topic_0'][i] for i in range(20)}
+            st.session_state.topic_str_to_word = topic_str_to_word
 
         if 'selected_points' not in st.session_state:
             st.session_state.selected_points = []