Spaces:
Sleeping
Sleeping
| import streamlit as st | |
| import pandas as pd | |
| from data_handler import load_data | |
| from analyzer import DataAnalysisWorkflow, AIAssistant | |
| def main(): | |
| st.set_page_config( | |
| page_title="Data Analysis Platform", | |
| page_icon="📊", | |
| layout="wide" | |
| ) | |
| st.title("📊 Data Analysis Platform") | |
| st.markdown("**Optimized workflow with caching and pagination**") | |
| # Initialize session state | |
| if 'current_stage' not in st.session_state: | |
| st.session_state.current_stage = 1 | |
| if 'workflow' not in st.session_state: | |
| st.session_state.workflow = None | |
| if 'ai_assistant' not in st.session_state: | |
| st.session_state.ai_assistant = AIAssistant() | |
| # File upload | |
| uploaded_file = st.file_uploader("Upload Dataset", type=['csv', 'xlsx']) | |
| if uploaded_file is not None: | |
| try: | |
| # Load data | |
| df = load_data(uploaded_file) | |
| st.success(f"✅ Dataset loaded! Shape: {df.shape}") | |
| # Initialize workflow | |
| if st.session_state.workflow is None: | |
| st.session_state.workflow = DataAnalysisWorkflow(df) | |
| # Progress sidebar | |
| st.sidebar.header("Progress") | |
| progress = st.sidebar.progress(st.session_state.current_stage / 5) | |
| stages = ["Data Overview", "Exploration", "Quality Check", "Analysis", "Summary"] | |
| for i, stage in enumerate(stages, 1): | |
| if i == st.session_state.current_stage: | |
| st.sidebar.write(f"🔄 **{i}. {stage}**") | |
| elif i < st.session_state.current_stage: | |
| st.sidebar.write(f"✅ {i}. {stage}") | |
| else: | |
| st.sidebar.write(f"⏳ {i}. {stage}") | |
| # Navigation | |
| col1, col2 = st.sidebar.columns(2) | |
| with col1: | |
| if st.button("← Previous") and st.session_state.current_stage > 1: | |
| st.session_state.current_stage -= 1 | |
| st.rerun() | |
| with col2: | |
| if st.button("Next →") and st.session_state.current_stage < 5: | |
| st.session_state.current_stage += 1 | |
| st.rerun() | |
| # Recent insights | |
| st.sidebar.header("💡 Recent Insights") | |
| recent_insights = st.session_state.workflow.insights[-3:] | |
| for insight in recent_insights: | |
| st.sidebar.info(f"**Stage {insight['stage']}:** {insight['insight']}") | |
| # Main content with AI assistant | |
| main_col, ai_col = st.columns([3, 1]) | |
| with main_col: | |
| # Execute current stage | |
| if st.session_state.current_stage == 1: | |
| st.session_state.workflow.stage_1_overview() | |
| elif st.session_state.current_stage == 2: | |
| st.session_state.workflow.stage_2_exploration() | |
| elif st.session_state.current_stage == 3: | |
| st.session_state.workflow.stage_3_cleaning() | |
| elif st.session_state.current_stage == 4: | |
| st.session_state.workflow.stage_4_analysis() | |
| elif st.session_state.current_stage == 5: | |
| st.session_state.workflow.stage_5_summary() | |
| with ai_col: | |
| st.subheader("🤖 AI Assistant") | |
| # AI model selection | |
| available_models = st.session_state.ai_assistant.get_available_models() | |
| if available_models: | |
| selected_model = st.selectbox("AI Model:", available_models) | |
| if st.button("Get AI Insights"): | |
| if st.session_state.workflow.insights: | |
| with st.spinner("Analyzing with AI..."): | |
| ai_analysis = st.session_state.ai_assistant.analyze_insights( | |
| df, st.session_state.workflow.insights, selected_model | |
| ) | |
| st.write("**AI Analysis:**") | |
| st.write(ai_analysis) | |
| else: | |
| st.warning("Complete some analysis stages first.") | |
| else: | |
| st.warning("No AI models available.") | |
| st.info("Set GOOGLE_API_KEY or OPENAI_API_KEY environment variables.") | |
| # Quick insights | |
| st.subheader("📊 Quick Stats") | |
| if st.session_state.workflow.insights: | |
| st.metric("Total Insights", len(st.session_state.workflow.insights)) | |
| st.metric("Current Stage", f"{st.session_state.current_stage}/5") | |
| # Latest insight | |
| if st.session_state.workflow.insights: | |
| latest = st.session_state.workflow.insights[-1] | |
| st.info(f"**Latest:** {latest['insight']}") | |
| # Data quality indicator | |
| quality_score = 100 | |
| if st.session_state.workflow.stats['missing_values'] > 0: | |
| quality_score -= 30 | |
| if st.session_state.workflow.stats['duplicates'] > 0: | |
| quality_score -= 20 | |
| st.metric("Data Quality", f"{quality_score}%") | |
| except Exception as e: | |
| st.error(f"Error: {str(e)}") | |
| st.info("Please check your file format and try again.") | |
| if __name__ == "__main__": | |
| main() |