random changes

app.py

@@ -24,8 +24,8 @@ def main():
 
     if st.session_state.step == 1:
         step_1_upload_and_analyze()
-    elif st.session_state.step == 2:
-        step_2_clean_data()
+    # elif st.session_state.step == 2:
+    #     step_2_clean_data()
     elif st.session_state.step == 3:
         step_3_chat_with_data()
 
@@ -49,63 +49,63 @@ def step_1_upload_and_analyze():
                 st.write(df.head())
                 st.write("---")
 
-        if st.button("Proceed to Data Cleaning"):
-            st.session_state.step = 2
+        if st.button("Explore Data"):
+            st.session_state.step = 3
 
-def step_2_clean_data():
-    st.subheader("Step 2: Clean Data")
+# def step_2_clean_data():
+#     st.subheader("Step 2: Clean Data")
 
-    llm = OpenAI(temperature=0)
+#     llm = OpenAI(temperature=0)
     
-    for name, df in st.session_state.dataframes.items():
-        st.write(f"Cleaning recommendations for {name}:")
+#     for name, df in st.session_state.dataframes.items():
+#         st.write(f"Cleaning recommendations for {name}:")
         
-        # Create a summary of the dataframe
-        summary = f"Dataframe '{name}' summary:\n"
-        summary += f"- Shape: {df.shape}\n"
-        summary += f"- Columns: {', '.join(df.columns)}\n"
-        summary += "- Data types:\n"
-        for col, dtype in df.dtypes.items():
-            summary += f"  - {col}: {dtype}\n"
-        summary += "- Sample data (first 5 rows):\n"
-        summary += df.head().to_string()
-
-        # Split the summary into smaller chunks
-        chunk_size = 1500  # Reduced chunk size
-        chunks = textwrap.wrap(summary, chunk_size)
-
-        cleaning_recommendations = []
-        with st.spinner("Analyzing data and generating recommendations..."):
-            for i, chunk in enumerate(chunks):
-                chunk_result = analyze_chunk(llm, df, chunk)
-                cleaning_recommendations.append(chunk_result)
-
-        # Combine all recommendations
-        full_recommendations = "\n".join(cleaning_recommendations)
-        st.write(full_recommendations)
+#         # Create a summary of the dataframe
+#         summary = f"Dataframe '{name}' summary:\n"
+#         summary += f"- Shape: {df.shape}\n"
+#         summary += f"- Columns: {', '.join(df.columns)}\n"
+#         summary += "- Data types:\n"
+#         for col, dtype in df.dtypes.items():
+#             summary += f"  - {col}: {dtype}\n"
+#         summary += "- Sample data (first 5 rows):\n"
+#         summary += df.head().to_string()
+
+#         # Split the summary into smaller chunks
+#         chunk_size = 1500  # Reduced chunk size
+#         chunks = textwrap.wrap(summary, chunk_size)
+
+#         cleaning_recommendations = []
+#         with st.spinner("Analyzing data and generating recommendations..."):
+#             for i, chunk in enumerate(chunks):
+#                 chunk_result = analyze_chunk(llm, df, chunk)
+#                 cleaning_recommendations.append(chunk_result)
+
+#         # Combine all recommendations
+#         full_recommendations = "\n".join(cleaning_recommendations)
+#         st.write(full_recommendations)
         
-        # Create checkboxes for cleaning operations
-        cleaning_ops = [op.strip() for op in full_recommendations.split('\n') if op.strip()]
-        st.session_state.cleaning_operations[name] = []
-        for op in cleaning_ops:
-            if st.checkbox(op, key=f"{name}_{op}"):
-                st.session_state.cleaning_operations[name].append(op)
-
-    if st.button("Apply Cleaning and Proceed to Chat"):
-        for name, ops in st.session_state.cleaning_operations.items():
-            df = st.session_state.dataframes[name]
-            for op in ops:
-                # Here you would implement the actual cleaning operations
-                # For now, we'll just print what would be done
-                st.write(f"Applying to {name}: {op}")
+#         # Create checkboxes for cleaning operations
+#         cleaning_ops = [op.strip() for op in full_recommendations.split('\n') if op.strip()]
+#         st.session_state.cleaning_operations[name] = []
+#         for op in cleaning_ops:
+#             if st.checkbox(op, key=f"{name}_{op}"):
+#                 st.session_state.cleaning_operations[name].append(op)
+
+#     if st.button("Apply Cleaning and Proceed to Chat"):
+#         for name, ops in st.session_state.cleaning_operations.items():
+#             df = st.session_state.dataframes[name]
+#             for op in ops:
+#                 # Here you would implement the actual cleaning operations
+#                 # For now, we'll just print what would be done
+#                 st.write(f"Applying to {name}: {op}")
         
-        st.session_state.step = 3
-        st.success("Cleaning operations applied. Proceeding to chat interface.")
-        st.button("Go to Chat Interface")
+#         st.session_state.step = 3
+#         st.success("Cleaning operations applied. Proceeding to chat interface.")
+#         st.button("Go to Chat Interface")
 
-    if st.button("Back to Data Upload"):
-        st.session_state.step = 1
-        st.experimental_rerun()
+#     if st.button("Back to Data Upload"):
+#         st.session_state.step = 1
+#         st.experimental_rerun()
 
 def step_3_chat_with_data():
     st.subheader("Step 3: Chat with your data")
@@ -116,11 +116,11 @@ def step_3_chat_with_data():
         st.session_state.chat_history.append(("User", user_input))
         st.session_state.chat_history.append(("AI", response))
 
-    for role, message in st.session_state.chat_history:
+    for role, message in reversed(st.session_state.chat_history):
         if role == "User":
             st.text_area("You:", value=message, height=50, disabled=True)
         else:
-            st.text_area("AI:", value=message, height=100, disabled=True)
+            st.write(message)
 
 def process_user_input(user_input):
     llm = OpenAI(temperature=0)
@@ -136,10 +136,12 @@ def process_user_input(user_input):
         combined_df,
         verbose=True,
         agent_type=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
-        allow_dangerous_code=True
+        allow_dangerous_code=True,
+        handle_parsing_errors=True
     )
 
-    full_input = f"{df_summary}\nThe data from all files has been combined into a single DataFrame with an additional 'source' column indicating the original file.\n\nUser question: {user_input}"
+   # full_input = f"{df_summary}\nThe data from all files has been combined into a single DataFrame with an additional 'source' column indicating the original file.\n\nUser question: {user_input}"
+    full_input = f"{combined_df}\nAs a data analyst, process the data to answer the user question.\n\nUser question: {user_input}"
 
     response = agent.run(full_input)
     return response
@@ -163,4 +165,4 @@ def analyze_chunk(llm, df, chunk, timeout=30):
         return f"Analysis timed out or encountered an error: {str(e)}"
 
 if __name__ == "__main__":
-    main()
+    main()