Cache classes to avoid reruns / change button tags to avoid redundency

app.py

@@ -71,6 +71,7 @@ import streamlit as st
 # Configure logging
 logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
 
+@st.cache_data(ttl=1800, max_entries=30, show_spinner='Retrieving data...')
 class UAPAnalyzer:
     """
     A class for analyzing and clustering textual data within a pandas DataFrame using 
@@ -785,7 +786,7 @@ def plot_cramers_v_heatmap(data, significance_level=0.05):
     plt.title(f"Heatmap of Cramér's V (p < {significance_level})")
     return plt
 
-
+@st.cache_data(ttl=1800, max_entries=30, show_spinner='Retrieving data...')
 class UAPVisualizer:
     def __init__(self, data=None):
         pass  # Initialization can be added if needed
@@ -925,7 +926,7 @@ class UAPVisualizer:
         plt.show()
 
 
-
+@st.cache_data(ttl=1800, max_entries=30, show_spinner='Retrieving data...')
 class UAPParser:
     def __init__(self, api_key, model="gpt-3.5-turbo-0125", col=None, format_long=None):
         os.environ['OPENAI_API_KEY'] = api_key
@@ -1140,9 +1141,19 @@ def filter_dataframe(df: pd.DataFrame) -> pd.DataFrame:
                     start_date, end_date = user_date_input
                     df_ = df_.loc[df_[column].between(start_date, end_date)]
             else:
-                user_text_input = right.text_input(
-                    f"Substring or regex in {column}",
-                )
+                try: # To avoid multiple buttons with same ID
+                    user_text_input = right.text_input(
+                        f"Substring or regex in {column}",
+                    )
+                except:
+                    try:
+                         user_text_input = right.text_input(
+                        f"Substring or regex {column}",
+                        )
+                    except Exception as e:
+                        print(f'Error : {e}')
+                        pass
+            
                 if user_text_input:
                     df_ = df_[df_[column].astype(str).str.contains(user_text_input)]
         # write len of df after filtering with % of original
@@ -1273,7 +1284,7 @@ def main():
         st.session_state['stage'] = 1
 
     # Analyze data
-    if st.session_state.stage > 0:
+    if st.session_state.stage > 0 and st.session_state.stage < 10 and parsed_responses is not None:
         columns_to_analyze = st.multiselect(
             label='Select columns to analyze',
             options=parsed_responses.columns
@@ -1340,13 +1351,15 @@ def main():
 
     if st.session_state['data_processed']:
         parsed2 = st.session_state.get('dataset', pd.DataFrame())
+        if parsed2 is not None:
+            st.session_state['stage'] = 10
         parsed2 = filter_dataframe(parsed2)
         col1, col2 = st.columns(2)
         st.dataframe(parsed2)
         with col1:
             col_parsed2 = st.selectbox("Which column do you want to query?", parsed2.columns)
         with col2:
-            GEMINI_KEY = st.text_input('Gemini API Key', GEMINI_KEY, type='password', help="Enter your Gemini API key")
+            GEMINI_KEY = st.text_input('Gemini API Key', GEMINI_KEY, type='password', help="Enter Gemini API key")
         if col_parsed and GEMINI_KEY:
             selected_column_data2 = parsed2[col_parsed2].tolist()
             question2 = st.text_input("Ask a question / leave empty for summarization")