Update app.py

app.py

@@ -16,6 +16,8 @@ import plotly.io as pio
 import tempfile
 import os
 import requests
+import warnings
+warnings.filterwarnings("ignore", message=".*secrets.*")
 
 DESIGN_SYSTEM = {
     'colors': {
@@ -89,117 +91,20 @@ def load_css():
         box-shadow: 0 1px 3px rgba(0,0,0,0.1);
         margin-bottom: 1rem;
     }}
-    
-    /* Updated Quality Check Styles */
-    .quality-grid {{
-        display: grid;
-        grid-template-columns: repeat(auto-fit, minmax(280px, 1fr));
-        gap: 16px;
-        margin-top: 20px;
-    }}
-    .quality-card {{
-        background: white;
-        border: 1px solid {DESIGN_SYSTEM['colors']['border']};
-        border-radius: 12px;
-        padding: 24px;
-        min-height: 140px;
-        box-shadow: 0 4px 12px rgba(0,0,0,0.08);
-        border-left: 4px solid transparent;
-        transition: all 0.3s ease;
-        position: relative;
-    }}
-    .quality-card:hover {{
-        transform: translateY(-2px);
-        box-shadow: 0 8px 25px rgba(0,0,0,0.15);
-    }}
-    .card-warning {{
-        border-left-color: {DESIGN_SYSTEM['colors']['warning']};
-    }}
-    .card-success {{
-        border-left-color: {DESIGN_SYSTEM['colors']['success']};
-    }}
-    .card-title {{
-        font-size: 16px;
-        font-weight: 600;
-        color: {DESIGN_SYSTEM['colors']['text']};
-        margin-bottom: 12px;
-    }}
-    .status-badge {{
-        display: inline-block;
-        padding: 6px 12px;
-        border-radius: 16px;
-        font-size: 12px;
-        font-weight: 600;
-        text-transform: uppercase;
-        letter-spacing: 0.5px;
-        margin-bottom: 12px;
-    }}
-    .status-warning {{
-        background: rgba(217, 119, 6, 0.15);
-        color: {DESIGN_SYSTEM['colors']['warning']};
-    }}
-    .status-success {{
-        background: rgba(16, 185, 129, 0.15);
-        color: {DESIGN_SYSTEM['colors']['success']};
-    }}
-    .outliers-info {{
-        display: flex;
-        align-items: baseline;
-        margin-bottom: 12px;
-    }}
-    .outliers-count {{
-        font-size: 24px;
-        font-weight: 700;
-        margin-right: 8px;
-    }}
-    .outliers-count.warning {{
-        color: {DESIGN_SYSTEM['colors']['warning']};
-    }}
-    .outliers-count.success {{
+    .alert-success {{
+        background: linear-gradient(135deg, {DESIGN_SYSTEM['colors']['success']}15, {DESIGN_SYSTEM['colors']['success']}25);
+        border: 1px solid {DESIGN_SYSTEM['colors']['success']};
+        border-radius: 8px;
+        padding: 1rem;
         color: {DESIGN_SYSTEM['colors']['success']};
     }}
-    .outliers-text {{
-        color: #6B7280;
-        font-size: 14px;
-    }}
-    .range-info {{
-        background: #F8F9FA;
-        padding: 12px;
+    .alert-warning {{
+        background: linear-gradient(135deg, {DESIGN_SYSTEM['colors']['warning']}15, {DESIGN_SYSTEM['colors']['warning']}25);
+        border: 1px solid {DESIGN_SYSTEM['colors']['warning']};
         border-radius: 8px;
-        margin-bottom: 12px;
-        font-size: 13px;
-        color: #495057;
-    }}
-    .range-label {{
-        font-weight: 600;
-        color: {DESIGN_SYSTEM['colors']['text']};
-        margin-bottom: 4px;
-    }}
-    .dates-section {{
-        font-size: 12px;
-        color: #6B7280;
-    }}
-    .dates-label {{
-        font-size: 11px;
-        color: #9CA3AF;
-        text-transform: uppercase;
-        letter-spacing: 0.5px;
-        margin-bottom: 8px;
-        font-weight: 600;
-    }}
-    .dates-list {{
-        line-height: 1.6;
-    }}
-    .success-center {{
-        text-align: center;
-        margin-top: 16px;
-    }}
-    .success-message {{
-        font-size: 14px;
-        color: {DESIGN_SYSTEM['colors']['success']};
-        font-weight: 500;
+        padding: 1rem;
+        color: {DESIGN_SYSTEM['colors']['warning']};
     }}
-    
     .stButton > button {{
         background: {DESIGN_SYSTEM['colors']['primary']};
         color: white;
@@ -223,10 +128,21 @@ def load_css():
 
 @st.cache_resource
 def init_ai():
-    api_key = st.secrets.get("GOOGLE_API_KEY", "")
+    """Initialize AI model with proper error handling for secrets"""
+    try:
+        # Try to get API key from Streamlit secrets
+        api_key = st.secrets.get("GOOGLE_API_KEY", "")
+    except (FileNotFoundError, KeyError, AttributeError):
+        # If secrets file doesn't exist or key not found, try environment variable
+        api_key = os.environ.get("GOOGLE_API_KEY", "")
+    
     if api_key:
-        genai.configure(api_key=api_key)
-        return genai.GenerativeModel('gemini-1.5-flash')
+        try:
+            genai.configure(api_key=api_key)
+            return genai.GenerativeModel('gemini-1.5-flash')
+        except Exception as e:
+            st.error(f"AI configuration failed: {str(e)}")
+            return None
     return None
 
 @st.cache_data
@@ -256,7 +172,7 @@ def generate_sample_data(year):
     dates = pd.date_range(start=start_date, end=end_date, freq='D')
     weekdays = dates[dates.weekday < 5]
     data = []
-    materials = ['steel', 'aluminum', 'polymer', 'copper']
+    materials = ['steel', 'aluminum', 'plastic', 'copper']
     shifts = ['day', 'night']
     for date in weekdays:
         for material in materials:
@@ -264,7 +180,7 @@ def generate_sample_data(year):
                 base_weight = {
                     'steel': 1500,
                     'aluminum': 800,
-                    'polymer': 600,
+                    'plastic': 600,
                     'copper': 400
                 }[material]
                 weight = base_weight + np.random.normal(0, base_weight * 0.2)
@@ -426,145 +342,82 @@ def detect_outliers(df):
     return outliers
 
 def generate_ai_summary(model, df, stats, outliers):
-    """Generate professional data analysis with actionable insights"""
     if not model:
-        return "AI analysis unavailable - API key not configured"
-    
+        return "AI analysis unavailable - Google API key not configured. Please set the GOOGLE_API_KEY environment variable or in Streamlit secrets to enable AI insights."
     try:
-        total_production = stats['_total_']['total']
-        work_days = stats['_total_']['work_days']
-        daily_avg = stats['_total_']['daily_avg']
         materials = [k for k in stats.keys() if k != '_total_']
-        total_outliers = sum(info['count'] for info in outliers.values())
-        
-        # Get top material and its percentage
-        top_material = max(materials, key=lambda x: stats[x]['total'])
-        top_percentage = stats[top_material]['percentage']
-        
-        # Calculate shift info if available
-        shift_info = ""
-        if 'shift' in df.columns:
-            day_total = df[df['shift'] == 'day']['weight_kg'].sum()
-            night_total = df[df['shift'] == 'night']['weight_kg'].sum()
-            day_pct = (day_total / total_production) * 100
-            night_pct = (night_total / total_production) * 100
-            shift_info = f"Day shift: {day_pct:.1f}%, Night shift: {night_pct:.1f}%"
-        
-        context = f"""
-Production Analysis Data:
-- Period: {df['date'].min().strftime('%B %d, %Y')} to {df['date'].max().strftime('%B %d, %Y')}
-- Total production: {total_production:,.0f} kg over {work_days} work days
-- Daily average: {daily_avg:,.0f} kg
-- Materials tracked: {', '.join([m.title() for m in materials])}
-- Top material: {top_material.title()} ({top_percentage:.1f}% of total)
-- Quality issues: {total_outliers} outliers detected across all materials
-- {shift_info}
-
-Material breakdown:
-"""
+        context_parts = [
+            "# Production Data Analysis Context",
+            f"## Overview",
+            f"- Total Production: {stats['_total_']['total']:,.0f} kg",
+            f"- Production Period: {stats['_total_']['work_days']} working days", 
+            f"- Daily Average: {stats['_total_']['daily_avg']:,.0f} kg",
+            f"- Materials Tracked: {len(materials)}",
+            "",
+            "## Material Breakdown:"
+        ]
         for material in materials:
             info = stats[material]
-            outlier_count = outliers[material]['count']
-            context += f"- {material.title()}: {info['total']:,.0f} kg ({info['percentage']:.1f}%), {outlier_count} outliers\n"
-        
+            context_parts.append(f"- {material.title()}: {info['total']:,.0f} kg ({info['percentage']:.1f}%), avg {info['daily_avg']:,.0f} kg/day")
+        daily_data = df.groupby('date')['weight_kg'].sum()
+        trend_direction = "increasing" if daily_data.iloc[-1] > daily_data.iloc[0] else "decreasing"
+        volatility = daily_data.std() / daily_data.mean() * 100
+        context_parts.extend([
+            "",
+            "## Trend Analysis:",
+            f"- Overall trend: {trend_direction}",
+            f"- Production volatility: {volatility:.1f}% coefficient of variation",
+            f"- Peak production: {daily_data.max():,.0f} kg",
+            f"- Lowest production: {daily_data.min():,.0f} kg"
+        ])
+        total_outliers = sum(info['count'] for info in outliers.values())
+        context_parts.extend([
+            "",
+            "## Quality Control:",
+            f"- Total outliers detected: {total_outliers}",
+            f"- Materials with quality issues: {sum(1 for info in outliers.values() if info['count'] > 0)}"
+        ])
+        if 'shift' in df.columns:
+            shift_stats = df.groupby('shift')['weight_kg'].sum()
+            context_parts.extend([
+                "",
+                "## Shift Performance:",
+                f"- Day shift: {shift_stats.get('day', 0):,.0f} kg",
+                f"- Night shift: {shift_stats.get('night', 0):,.0f} kg"
+            ])
+        context_text = "\n".join(context_parts)
         prompt = f"""
-{context}
+{context_text}
 
-Provide a professional production analysis with these sections:
+As an expert AI analyst embedded within the "Production Monitor with AI Insights" platform, provide a comprehensive analysis based on the data provided. Your tone should be professional and data-driven. Your primary goal is to highlight how the platform's features reveal critical insights.
 
-**EXECUTIVE ASSESSMENT**
-One paragraph overview emphasizing production strengths and improvement opportunities (not problems).
+Structure your response in the following format:
 
-**KEY DATA INSIGHTS**
-2-3 specific insights focusing on optimization potential. Frame outliers as "improvement opportunities" and imbalances as "enhancement areas." Use positive language.
+**PRODUCTION ASSESSMENT**
+Evaluate the overall production status (Excellent/Good/Needs Attention). Briefly justify your assessment using key metrics from the data summary.
 
-**ACTIONABLE RECOMMENDATIONS**
-2-3 collaborative recommendations starting with "We recommend" and mentioning how Nilsen Service & Consulting can assist in implementation.
+**KEY FINDINGS**
+Identify 3-4 of the most important insights. For each finding, explicitly mention the platform feature that made the discovery possible. Use formats like "(revealed by the 'Quality Check' module)" or "(visualized in the 'Production Trend' chart)".
 
-**PARTNERSHIP OPPORTUNITIES**
-How Nilsen Service & Consulting can collaborate to unlock further potential.
+Example Finding format:
+• Finding X: [Your insight, e.g., "Liquid-Ctu production shows high volatility..."] (as identified by the 'Materials Analysis' view).
 
-Write as a solution-oriented consultant. Frame challenges as opportunities. Use collaborative language like "enhance," "optimize," "unlock potential." Maximum 250 words total.
-"""
+**RECOMMENDATIONS**
+Provide 2-3 actionable recommendations. Frame these as steps the management can take, encouraging them to use the platform for further investigation.
+
+Example Recommendation format:
+• Recommendation Y: [Your recommendation, e.g., "Investigate the root causes of the 11 outliers..."] We recommend using the platform's interactive charts to drill down into the specific dates identified by the 'Quality Check' module.
 
+Keep the entire analysis concise and under 300 words.
+"""
         response = model.generate_content(prompt)
         return response.text
-        
     except Exception as e:
         return f"AI analysis error: {str(e)}"
 
-def render_ai_section(df, stats, model):
-    """Showcase our AI capabilities and technical achievements"""
-    
-    if model:
-        st.markdown('<div class="section-header">AI-Powered Solution</div>', unsafe_allow_html=True)
-        
-        # Demonstrate our capabilities
-        st.markdown("### **Nilsen Service & Consulting - Technical Achievements**")
-        outliers = detect_outliers(df)
-        with st.spinner("Demonstrating our AI capabilities..."):
-            ai_summary = generate_ai_summary(model, df, stats, outliers)
-            st.success(ai_summary)
-        
-        # Show our system's intelligence
-        st.markdown("### **Experience Our Advanced Analytics**")
-        st.markdown("*See how our AI system provides professional insights for your operations:*")
-        
-        demo_questions = [
-            "How does our monitoring system ensure production quality?",
-            "What operational advantages does our platform provide?",
-            "How does our AI deliver cost savings and efficiency gains?"
-        ]
-        
-        cols = st.columns(len(demo_questions))
-        for i, question in enumerate(demo_questions):
-            with cols[i]:
-                if st.button(f"{question}", key=f"demo_q_{i}"):
-                    with st.spinner("Our AI analyzing..."):
-                        answer = query_ai(model, stats, question, df)
-                        st.info(f"**Nilsen AI Response:** {answer}")
-        
-        # Interactive demonstration
-        st.markdown("### **Test Our AI Intelligence**")
-        col1, col2 = st.columns([3, 1])
-        
-        with col1:
-            custom_question = st.text_input("Ask our AI system about production management:", 
-                                            placeholder="e.g., 'How can your system improve our operational efficiency?'",
-                                            key="demo_question")
-        with col2:
-            st.markdown("<br>", unsafe_allow_html=True)
-            if st.button("See Our AI in Action", key="demo_btn", type="primary"):
-                if custom_question:
-                    with st.spinner("Nilsen AI processing..."):
-                        answer = query_ai(model, stats, custom_question, df)
-                        st.success(f"**Your Question:** {custom_question}")
-                        st.info(f"**Our AI Solution:** {answer}")
-                else:
-                    st.warning("Please enter a question to see our AI capabilities")
-        
-        # Value proposition
-        st.markdown("---")
-        st.markdown("""
-        <div style="background: linear-gradient(135deg, #1E40AF15, #05966925); padding: 1rem; border-radius: 8px; border: 1px solid #1E40AF;">
-        <h4>Why Choose Nilsen Service & Consulting?</h4>
-        <ul>
-        <li><strong>Advanced AI Integration:</strong> Cutting-edge analytics for your operations</li>
-        <li><strong>Professional Reliability:</strong> Enterprise-grade monitoring systems</li>
-        <li><strong>Proven Results:</strong> Data-driven insights that deliver ROI</li>
-        <li><strong>Complete Solution:</strong> From data processing to actionable recommendations</li>
-        </ul>
-        </div>
-        """, unsafe_allow_html=True)
-        
-    else:
-        st.markdown('<div class="section-header">AI-Powered Solution</div>', unsafe_allow_html=True)
-        st.error("AI demonstration requires API configuration")
-        st.info("**Our AI system provides:** Advanced analytics, predictive insights, automated reporting, and intelligent recommendations for production optimization.")
-
 def query_ai(model, stats, question, df=None):
     if not model:
-        return "AI assistant not available"
+        return "AI assistant not available - Please configure Google API key"
     context_parts = [
         "Production Data Summary:",
         *[f"- {mat.title()}: {info['total']:,.0f}kg ({info['percentage']:.1f}%)" 
@@ -584,8 +437,8 @@ def query_ai(model, stats, question, df=None):
     try:
         response = model.generate_content(context)
         return response.text
-    except:
-        return "Error getting AI response"
+    except Exception as e:
+        return f"Error getting AI response: {str(e)}"
 
 def save_plotly_as_image(fig, filename):
     try:
@@ -815,7 +668,7 @@ def create_enhanced_pdf_report(df, stats, outliers, model=None):
     else:
         elements.append(PageBreak())
         elements.append(Paragraph("AI Analysis", subtitle_style))
-        elements.append(Paragraph("AI analysis unavailable - API key not configured. Please configure Google AI API key to enable intelligent insights.", styles['Normal']))
+        elements.append(Paragraph("AI analysis unavailable - Google API key not configured. Please set the GOOGLE_API_KEY environment variable or configure it in Streamlit secrets to enable intelligent insights.", styles['Normal']))
     elements.append(Spacer(1, 30))
     footer_text = f"""
     <para alignment="center">
@@ -844,7 +697,7 @@ def create_csv_export(df, stats):
     return summary_df
 
 def add_export_section(df, stats, outliers, model):
-    st.markdown('<div class="section-header">Export Reports</div>', unsafe_allow_html=True)
+    st.markdown('<div class="section-header">📄 Export Reports</div>', unsafe_allow_html=True)
     if 'export_ready' not in st.session_state:
         st.session_state.export_ready = False
     if 'pdf_buffer' not in st.session_state:
@@ -858,13 +711,13 @@ def add_export_section(df, stats, outliers, model):
                 with st.spinner("Generating PDF with AI analysis..."):
                     st.session_state.pdf_buffer = create_enhanced_pdf_report(df, stats, outliers, model)
                     st.session_state.export_ready = True
-                st.success("PDF report with AI analysis generated successfully!")
+                st.success("✅ PDF report with AI analysis generated successfully!")
             except Exception as e:
-                st.error(f"PDF generation failed: {str(e)}")
+                st.error(f"❌ PDF generation failed: {str(e)}")
                 st.session_state.export_ready = False
         if st.session_state.export_ready and st.session_state.pdf_buffer:
             st.download_button(
-                label="Download PDF Report",
+                label="💾 Download PDF Report",
                 data=st.session_state.pdf_buffer,
                 file_name=f"production_report_ai_{datetime.now().strftime('%Y%m%d_%H%M')}.pdf",
                 mime="application/pdf",
@@ -874,13 +727,13 @@ def add_export_section(df, stats, outliers, model):
         if st.button("Generate CSV Summary", key="generate_csv_btn", type="primary"):
             try:
                 st.session_state.csv_data = create_csv_export(df, stats)
-                st.success("CSV summary generated successfully!")
+                st.success("✅ CSV summary generated successfully!")
             except Exception as e:
-                st.error(f"CSV generation failed: {str(e)}")
+                st.error(f"❌ CSV generation failed: {str(e)}")
         if st.session_state.csv_data is not None:
             csv_string = st.session_state.csv_data.to_csv(index=False)
             st.download_button(
-                label="Download CSV Summary",
+                label="💾 Download CSV Summary",
                 data=csv_string,
                 file_name=f"production_summary_{datetime.now().strftime('%Y%m%d_%H%M')}.csv",
                 mime="text/csv",
@@ -900,29 +753,26 @@ def main():
     load_css()
     st.markdown("""
     <div class="main-header">
-        <div class="main-title">Production Monitor with AI Insights</div>
+        <div class="main-title">🏭 Production Monitor with AI Insights</div>
         <div class="main-subtitle">Nilsen Service & Consulting AS | Real-time Production Analytics & Recommendations</div>
     </div>
     """, unsafe_allow_html=True)
-    
     model = init_ai()
-    
     if 'current_df' not in st.session_state:
         st.session_state.current_df = None
     if 'current_stats' not in st.session_state:
         st.session_state.current_stats = None
-    
     with st.sidebar:
-        st.markdown("### Data Source")
+        st.markdown("### 📊 Data Source")
         uploaded_file = st.file_uploader("Upload Production Data", type=['csv'])
         st.markdown("---")
-        st.markdown("### Quick Load")
+        st.markdown("### 📊 Quick Load")
         col1, col2 = st.columns(2)
         with col1:
-            if st.button("2024 Data", type="primary", key="load_2024"):
+            if st.button("📊 2024 Data", type="primary", key="load_2024"):
                 st.session_state.load_preset = "2024"
         with col2:
-            if st.button("2025 Data", type="primary", key="load_2025"):
+            if st.button("📊 2025 Data", type="primary", key="load_2025"):
                 st.session_state.load_preset = "2025"
         st.markdown("---")
         st.markdown("""
@@ -933,22 +783,21 @@ def main():
         - `shift`: day/night (optional)
         """)
         if model:
-            st.success("AI Assistant Ready")
+            st.success("🤖 AI Assistant Ready")
         else:
-            st.warning("AI Assistant Unavailable")
-    
+            st.warning("⚠️ AI Assistant Unavailable")
+            st.info("To enable AI features, set GOOGLE_API_KEY as environment variable or in Streamlit secrets")
     df = st.session_state.current_df
     stats = st.session_state.current_stats
-    
     if uploaded_file:
         try:
             df = load_data(uploaded_file)
             stats = get_material_stats(df)
             st.session_state.current_df = df
             st.session_state.current_stats = stats
-            st.success("Data uploaded successfully!")
+            st.success("✅ Data uploaded successfully!")
         except Exception as e:
-            st.error(f"Error loading uploaded file: {str(e)}")
+            st.error(f"❌ Error loading uploaded file: {str(e)}")
     elif 'load_preset' in st.session_state:
         year = st.session_state.load_preset
         try:
@@ -958,42 +807,34 @@ def main():
                 stats = get_material_stats(df)
                 st.session_state.current_df = df
                 st.session_state.current_stats = stats
-                st.success(f"{year} data loaded successfully!")
+                st.success(f"✅ {year} data loaded successfully!")
         except Exception as e:
-            st.error(f"Error loading {year} data: {str(e)}")
+            st.error(f"❌ Error loading {year} data: {str(e)}")
         finally:
             del st.session_state.load_preset
-    
     if df is not None and stats is not None:
-        st.markdown('<div class="section-header">Material Overview</div>', unsafe_allow_html=True)
+        st.markdown('<div class="section-header">📋 Material Overview</div>', unsafe_allow_html=True)
         materials = [k for k in stats.keys() if k != '_total_']
-        all_metrics = materials + ['_total_']
-        
-        # Display metrics in rows of 4
-        for i in range(0, len(all_metrics), 4):
-            row_metrics = all_metrics[i:i+4]
-            cols = st.columns(len(row_metrics))
-            
-            for j, item in enumerate(row_metrics):
-                with cols[j]:
-                    if item == '_total_':
-                        info = stats['_total_']
-                        st.metric(
-                            label="Total Production",
-                            value=f"{info['total']:,.0f} kg",
-                            delta="100% of total"
-                        )
-                        st.caption(f"Daily avg: {info['daily_avg']:,.0f} kg")
-                    else:
-                        info = stats[item]
-                        st.metric(
-                            label=item.replace('_', ' ').title(),
-                            value=f"{info['total']:,.0f} kg",
-                            delta=f"{info['percentage']:.1f}% of total"
-                        )
-                        st.caption(f"Daily avg: {info['daily_avg']:,.0f} kg")
-        
-        st.markdown('<div class="section-header">Production Trends</div>', unsafe_allow_html=True)
+        cols = st.columns(4)
+        for i, material in enumerate(materials[:3]):
+            info = stats[material]
+            with cols[i]:
+                st.metric(
+                    label=material.replace('_', ' ').title(),
+                    value=f"{info['total']:,.0f} kg",
+                    delta=f"{info['percentage']:.1f}% of total"
+                )
+                st.caption(f"Daily avg: {info['daily_avg']:,.0f} kg")
+        if len(materials) >= 3:
+            total_info = stats['_total_']
+            with cols[3]:
+                st.metric(
+                    label="Total Production",
+                    value=f"{total_info['total']:,.0f} kg",
+                    delta="100% of total"
+                )
+                st.caption(f"Daily avg: {total_info['daily_avg']:,.0f} kg")
+        st.markdown('<div class="section-header">📊 Production Trends</div>', unsafe_allow_html=True)
         col1, col2 = st.columns([3, 1])
         with col2:
             time_view = st.selectbox("Time Period", ["daily", "weekly", "monthly"], key="time_view_select")
@@ -1003,8 +844,7 @@ def main():
                 total_chart = create_total_production_chart(df, time_view)
                 st.plotly_chart(total_chart, use_container_width=True)
                 st.markdown('</div>', unsafe_allow_html=True)
-        
-        st.markdown('<div class="section-header">Materials Analysis</div>', unsafe_allow_html=True)
+        st.markdown('<div class="section-header">🏷️ Materials Analysis</div>', unsafe_allow_html=True)
         col1, col2 = st.columns([3, 1])
         with col2:
             selected_materials = st.multiselect(
@@ -1020,77 +860,29 @@ def main():
                     materials_chart = create_materials_trend_chart(df, time_view, selected_materials)
                     st.plotly_chart(materials_chart, use_container_width=True)
                     st.markdown('</div>', unsafe_allow_html=True)
-        
         if 'shift' in df.columns:
-            st.markdown('<div class="section-header">Shift Analysis</div>', unsafe_allow_html=True)
+            st.markdown('<div class="section-header">🌓 Shift Analysis</div>', unsafe_allow_html=True)
             with st.container():
                 st.markdown('<div class="chart-container">', unsafe_allow_html=True)
                 shift_chart = create_shift_trend_chart(df, time_view)
                 st.plotly_chart(shift_chart, use_container_width=True)
                 st.markdown('</div>', unsafe_allow_html=True)
-        
-        # Updated Quality Check Section
-        st.markdown('<div class="section-header">Quality Check</div>', unsafe_allow_html=True)
+        st.markdown('<div class="section-header">⚠️ Quality Check</div>', unsafe_allow_html=True)
         outliers = detect_outliers(df)
-        
-        # Create quality cards using new modern design
-        materials_list = list(outliers.items())
-        num_materials = len(materials_list)
-        
-        # Create responsive grid
-        cols_per_row = min(3, num_materials) if num_materials <= 6 else 4
-        
-        for i in range(0, num_materials, cols_per_row):
-            row_materials = materials_list[i:i+cols_per_row]
-            cols = st.columns(len(row_materials))
-            
-            for j, (material, info) in enumerate(row_materials):
-                with cols[j]:
-                    material_title = material.replace("_", " ").title()
-                    
-                    if info['count'] > 0:
-                        # Show all dates
-                        dates_display = ', '.join(info['dates'])
-                        
-                        card_html = f'''
-                        <div class="quality-card card-warning">
-                            <div class="card-title">{material_title}</div>
-                            <div class="status-badge status-warning">Warning</div>
-                            <div class="outliers-info">
-                                <span class="outliers-count warning">{info["count"]}</span>
-                                <span class="outliers-text">Outliers</span>
-                            </div>
-                            <div class="range-info">
-                                <div class="range-label">Normal Range</div>
-                                <div>{info["range"]}</div>
-                            </div>
-                            <div class="dates-section">
-                                <div class="dates-label">Dates</div>
-                                <div class="dates-list">{dates_display}</div>
-                            </div>
-                        </div>
-                        '''
+        cols = st.columns(len(outliers))
+        for i, (material, info) in enumerate(outliers.items()):
+            with cols[i]:
+                if info['count'] > 0:
+                    if len(info['dates']) <= 5:
+                        dates_str = ", ".join(info['dates'])
                     else:
-                        card_html = f'''
-                        <div class="quality-card card-success">
-                            <div class="card-title">{material_title}</div>
-                            <div class="status-badge status-success">Normal</div>
-                            <div class="outliers-info">
-                                <span class="outliers-count success">0</span>
-                                <span class="outliers-text">Outliers</span>
-                            </div>
-                            <div class="success-center">
-                                <div class="success-message">All values within normal range</div>
-                            </div>
-                        </div>
-                        '''
-                    
-                    st.markdown(card_html, unsafe_allow_html=True)
-
+                        dates_str = f"{', '.join(info['dates'][:3])}, +{len(info['dates'])-3} more"
+                    st.markdown(f'<div class="alert-warning"><strong>{material.title()}</strong><br>{info["count"]} outliers detected<br>Normal range: {info["range"]}<br><small>Dates: {dates_str}</small></div>', unsafe_allow_html=True)
+                else:
+                    st.markdown(f'<div class="alert-success"><strong>{material.title()}</strong><br>All values normal</div>', unsafe_allow_html=True)
         add_export_section(df, stats, outliers, model)
-        
         if model:
-            st.markdown('<div class="section-header">AI Insights</div>', unsafe_allow_html=True)
+            st.markdown('<div class="section-header">🤖 AI Insights</div>', unsafe_allow_html=True)
             quick_questions = [
                 "How does production distribution on weekdays compare to weekends?",
                 "Which material exhibits the most volatility in our dataset?",
@@ -1103,7 +895,6 @@ def main():
                         with st.spinner("Analyzing..."):
                             answer = query_ai(model, stats, q, df)
                             st.info(answer)
-            
             custom_question = st.text_input("Ask about your production data:", 
                                             placeholder="e.g., 'Compare steel vs aluminum last month'",
                                             key="custom_ai_question")
@@ -1112,12 +903,33 @@ def main():
                     answer = query_ai(model, stats, custom_question, df)
                     st.success(f"**Q:** {custom_question}")
                     st.write(f"**A:** {answer}")
+        else:
+            st.markdown('<div class="section-header">🤖 AI Configuration</div>', unsafe_allow_html=True)
+            st.info("""
+            **AI Assistant is currently unavailable.**
+            
+            To enable AI features, you need to configure your Google AI API key:
+            
+            **Option 1: Environment Variable**
+            ```bash
+            export GOOGLE_API_KEY="your_api_key_here"
+            ```
+            
+            **Option 2: Streamlit Secrets**
+            Create `.streamlit/secrets.toml`:
+            ```toml
+            GOOGLE_API_KEY = "your_api_key_here"
+            ```
+            
+            **Option 3: Azure App Service**
+            Set environment variable in Azure portal under Configuration > Application settings.
+            """)
     else:
-        st.markdown('<div class="section-header">How to Use This Platform</div>', unsafe_allow_html=True)
+        st.markdown('<div class="section-header">📖 How to Use This Platform</div>', unsafe_allow_html=True)
         col1, col2 = st.columns(2)
         with col1:
             st.markdown("""
-            ### Quick Start
+            ### 🚀 Quick Start
             1. Upload your TSV data in the sidebar
             2. Or click Quick Load buttons for preset data
             3. View production by material type
@@ -1128,7 +940,7 @@ def main():
             """)
         with col2:
             st.markdown("""
-            ### Key Features
+            ### 📊 Key Features
             - Real-time interactive charts
             - One-click preset data loading
             - Time-period comparisons
@@ -1137,7 +949,7 @@ def main():
             - AI-powered PDF reports
             - Intelligent recommendations
             """)
-        st.info("Ready to start? Upload your production data or use Quick Load buttons to begin analysis!")
+        st.info("📁 Ready to start? Upload your production data or use Quick Load buttons to begin analysis!")
 
 if __name__ == "__main__":
     main()