fixing issues with session_id states, adding visualizations

questions were not getting printed in the states so fix the issue (code still had session_state.generated_questions in it there so.. :) )

app.py

@@ -36,7 +36,8 @@ st.set_page_config(
         "About" : "#Hi this our project."
     }
 )
-
+# st.set_option(deprecation.showPyplotGlobalUse=False)
+# st.set_option('base','dark')
 # Initialize Wikipedia API with a user agent
 user_agent = 'QGen/1.0 (channingfisher7@gmail.com)'
 wiki_wiki = wikipediaapi.Wikipedia(user_agent= user_agent,language='en')
@@ -65,7 +66,7 @@ def set_state(session_id, key, value):
 
 @st.cache_resource
 def load_model():
-    model_name = "DevBM/t5-large-squad"
+    model_name = "DevBM/t5-small-squad"
     model = T5ForConditionalGeneration.from_pretrained(model_name)
     tokenizer = T5Tokenizer.from_pretrained(model_name)
     return model, tokenizer
@@ -198,7 +199,6 @@ def get_synonyms(word, n=3):
 def generate_options(answer, context, n=3):
     options = [answer]
     
-
     # Add contextually relevant words using a pre-trained model
     context_embedding = context_model.encode(context)
     answer_embedding = context_model.encode(answer)
@@ -337,9 +337,6 @@ def main():
     st.title(":blue[Question Generator System]")
     session_id = get_session_id()
     state = initialize_state(session_id)
-    # Initialize session state
-    if 'generated_questions' not in st.session_state:
-        st.session_state.generated_questions = []
 
     with st.sidebar:
         st.subheader("Customization Options")
@@ -359,6 +356,7 @@ def main():
             extract_all_keywords = st.toggle("Extract Max Keywords",value=False)
         with col2:
             enable_feedback_mode = st.toggle("Enable Feedback Mode",False)
+    # set_state(session_id, 'generated_questions', state['generated_questions'])
     text = None
     if input_type == "Text Input":
         text = st.text_area("Enter text here:", value="Joe Biden, the current US president is on a weak wicket going in for his reelection later this November against former President Donald Trump.")
@@ -370,7 +368,8 @@ def main():
         text = clean_text(text)
         segments = segment_text(text)
     generate_questions_button = st.button("Generate Questions")
-    if generate_questions_button and text:
+    q_count = 0
+    if generate_questions_button:
         state['generated_questions'] = []
         # st.session_state.generated_questions = []
         for text in segments:
@@ -380,6 +379,8 @@ def main():
             for i, (keyword, context) in enumerate(keyword_sentence_mapping.items()):
                 if i >= num_questions:
                     break
+                if q_count>num_questions:
+                    break
                 question = generate_question(context, keyword, num_beams=num_beams)
                 options = generate_options(keyword,context)
                 overall_score, relevance_score, complexity_score, spelling_correctness = assess_question_quality(context,question,keyword)
@@ -395,20 +396,22 @@ def main():
                     "complexity_score" : complexity_score,
                     "spelling_correctness" : spelling_correctness,
                 }
+                print("\n\n",tpl,"\n\n")
                 # st.session_state.generated_questions.append(tpl)
                 state['generated_questions'].append(tpl)
-     
+                q_count += 1
+        print("\n\n!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!\n\n")
+        data = get_state(session_id)
+        print(data)
         set_state(session_id, 'generated_questions', state['generated_questions'])
+        a = get_state(session_id)
     
     # sort question based on their quality score
-    # st.session_state.generated_questions = sorted(st.session_state.generated_questions,key = lambda x: x['overall_score'], reverse=True)
     state['generated_questions'] = sorted(state['generated_questions'],key = lambda x: x['overall_score'], reverse=True)
     # Display generated questions
-    # if st.session_state.generated_questions:
     if state['generated_questions']:
         st.header("Generated Questions:",divider='blue')
-        for i, q in enumerate(st.session_state.generated_questions):
-            # with st.expander(f"Question {i+1}"):
+        for i, q in enumerate(state['generated_questions']):
             st.subheader(body=f":orange[Q{i+1}:] {q['question']}")
 
             if show_context is True:
@@ -430,7 +433,7 @@ def main():
                 m3.metric("Complexity Score", value=f"{q['complexity_score']:,.2f}")
                 m4.metric("Spelling Correctness", value=f"{q['spelling_correctness']:,.2f}")
 
-            # q['context'] = st.text_area(f"Edit Context {i+1}:", value=q['context'], key=f"context_{i}")
+                # q['context'] = st.text_area(f"Edit Context {i+1}:", value=q['context'], key=f"context_{i}")
             if enable_feedback_mode:
                 q['question'] = st.text_input(f"Edit Question {i+1}:", value=q['question'], key=f"question_{i}")
                 q['rating'] = st.selectbox(f"Rate this question (1-5)", options=[1, 2, 3, 4, 5], key=f"rating_{i}")
@@ -443,43 +446,51 @@ def main():
         # if st.session_state.generated_questions:
         if state['generated_questions']:
             with st.sidebar:
-                csv_data = export_to_csv(st.session_state.generated_questions)
+                csv_data = export_to_csv(state['generated_questions'])
                 st.download_button(label="Download CSV", data=csv_data, file_name='questions.csv', mime='text/csv')
 
-                pdf_data = export_to_pdf(st.session_state.generated_questions)
+                pdf_data = export_to_pdf(state['generated_questions'])
                 st.download_button(label="Download PDF", data=pdf_data, file_name='questions.pdf', mime='application/pdf')
-
-        # View Feedback Statistics
-        with st.expander("View Feedback Statistics"):
-            feedback_file = 'question_feedback.json'
-            if os.path.exists(feedback_file):
-                with open(feedback_file, 'r') as f:
-                    feedback_data = json.load(f)
-                
-                st.subheader("Feedback Statistics")
-                
-                # Calculate average rating
-                ratings = [feedback['rating'] for feedback in feedback_data]
-                avg_rating = sum(ratings) / len(ratings) if ratings else 0
-                st.write(f"Average Question Rating: {avg_rating:.2f}")
-                
-                # Show distribution of ratings
-                rating_counts = {i: ratings.count(i) for i in range(1, 6)}
-                st.bar_chart(rating_counts)
+            with st.expander("View Visualizations"):
+                questions = [tpl['question'] for tpl in state['generated_questions']]
+                overall_scores = [tpl['overall_score'] for tpl in state['generated_questions']]
+                st.subheader('WordCloud of Questions',divider='rainbow')
+                display_word_cloud(questions)
+                st.subheader('Overall Scores',divider='violet')
+                overall_scores = pd.DataFrame(overall_scores,columns=['Overall Scores'])
+                st.line_chart(overall_scores)
+
+
+    # View Feedback Statistics
+    with st.expander("View Feedback Statistics"):
+        feedback_file = 'question_feedback.json'
+        if os.path.exists(feedback_file):
+            with open(feedback_file, 'r') as f:
+                feedback_data = json.load(f)
+            
+            st.subheader("Feedback Statistics")
+            
+            # Calculate average rating
+            ratings = [feedback['rating'] for feedback in feedback_data]
+            avg_rating = sum(ratings) / len(ratings) if ratings else 0
+            st.write(f"Average Question Rating: {avg_rating:.2f}")
+            
+            # Show distribution of ratings
+            rating_counts = {i: ratings.count(i) for i in range(1, 6)}
+            st.bar_chart(rating_counts)
                     
-                # Show some highly rated questions
-                st.subheader("Highly Rated Questions")
-                sorted_feedback = sorted(feedback_data, key=lambda x: x['rating'], reverse=True)
-                top_questions = sorted_feedback[:5]
-                for feedback in top_questions:
-                    st.write(f"Question: {feedback['question']}")
-                    st.write(f"Answer: {feedback['answer']}")
-                    st.write(f"Rating: {feedback['rating']}")
-                    st.write("---")
-            else:
-                st.write("No feedback data available yet.")
-
-        print("********************************************************************************")
+            # Show some highly rated questions
+            st.subheader("Highly Rated Questions")
+            sorted_feedback = sorted(feedback_data, key=lambda x: x['rating'], reverse=True)
+            top_questions = sorted_feedback[:5]
+            for feedback in top_questions:
+                st.write(f"Question: {feedback['question']}")
+                st.write(f"Answer: {feedback['answer']}")
+                st.write(f"Rating: {feedback['rating']}")
+                st.write("---")
+        else:
+            st.write("No feedback data available yet.")
+    print("********************************************************************************")
 
 if __name__ == '__main__':
     main()