Update app.py

app.py

@@ -0,0 +1,181 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+import seaborn as sns
+from io import BytesIO
+from docx import Document
+
+# ==========================================
+# 1. PREMIUM UI & BRANDING
+# ==========================================
+st.set_page_config(page_title="Shaking Table Optimization | Emaan Rashid", layout="wide")
+
+st.markdown("""
+    <style>
+    .stApp { background: #f8f9fa; }
+    [data-testid="stSidebar"] { background-color: #f0f2f6 !important; border-right: 2px solid #0e314d; }
+    [data-testid="stSidebar"] .stMarkdown p, [data-testid="stSidebar"] label {
+        color: #0e314d !important; font-weight: bold !important;
+    }
+    div[data-testid="stMetric"] {
+        background: white; padding: 25px !important; border-radius: 15px !important;
+        box-shadow: 0 10px 25px rgba(0,0,0,0.05) !important; border-top: 5px solid #0e314d !important;
+    }
+    h1, h2, h3 { color: #0e314d !important; font-weight: 800 !important; }
+    </style>
+    """, unsafe_allow_html=True)
+
+# ==========================================
+# 2. ACADEMIC HEADER
+# ==========================================
+st.markdown("""
+    <div style="background: white; padding: 30px; border-radius: 15px; border-left: 10px solid #d4af37; box-shadow: 0 4px 15px rgba(0,0,0,0.1); margin-bottom: 30px;">
+        <h1 style="margin:0; font-size: 28px;">🟫 Advanced Simulation of Gravity Separation Processes</h1>
+        <p style="margin:5px 0; color: #666;">Project Focus: Digital Twin for Shaking Table Optimization</p>
+        <hr style="border: 0.5px solid #eee;">
+        <div style="display: flex; justify-content: space-between; align-items: center;">
+            <span><strong>Submitted To:</strong> Dr. Muhammad Badar Hayat</span>
+            <span><strong>Submitted By:</strong> Emaan Rashid (Reg No: 2022-min-13)</span>
+            <span style="background: #0e314d; color: white; padding: 5px 15px; border-radius: 20px; font-size: 12px;">Mining Engineering | UET Lahore</span>
+        </div>
+    </div>
+    """, unsafe_allow_html=True)
+
+# ==========================================
+# 3. GLOBAL ENGINE & FIXED SIDEBAR
+# ==========================================
+FEED_GRADES = {"Gold": 0.80, "Ilmenite": 1.5, "Rutile": 0.30, "Monazite": 0.15}
+DEFAULT_PRICES = {"Gold": 80.0, "Ilmenite": 250.0, "Rutile": 800.0, "Monazite": 1500.0}
+
+# Default plant data dictionary
+current_plant_rec = {"Gold": 75.0, "Ilmenite": 60.0, "Rutile": 65.0, "Monazite": 70.0}
+
+st.sidebar.title("🎛️ Control Panel")
+
+# --- 📥 NEW ROBUST IMPORT & TEMPLATE SECTION ---
+st.sidebar.markdown("### 📥 Calibration Data")
+
+# 1. Provide a Template to avoid errors
+template_df = pd.DataFrame({"Mineral": ["Gold", "Ilmenite", "Rutile", "Monazite"], "Recovery": [75.0, 60.0, 65.0, 70.0]})
+csv_template = template_df.to_csv(index=False).encode('utf-8')
+st.sidebar.download_button("1. Download Sample File", data=csv_template, file_name="plant_data_template.csv", mime='text/csv')
+
+# 2. Upload with better error handling
+uploaded_file = st.sidebar.file_uploader("2. Upload Your File", type=['csv', 'xlsx'])
+
+if uploaded_file is not None:
+    try:
+        if uploaded_file.name.endswith('.csv'):
+            df_up = pd.read_csv(uploaded_file)
+        else:
+            df_up = pd.read_excel(uploaded_file)
+        
+        # Standardize column names
+        df_up.columns = [str(c).strip().title() for c in df_up.columns]
+        
+        # Check if required columns exist
+        if 'Mineral' in df_up.columns and 'Recovery' in df_up.columns:
+            # Map values
+            for _, row in df_up.iterrows():
+                m_name = str(row['Mineral']).strip().capitalize()
+                if m_name in current_plant_rec:
+                    current_plant_rec[m_name] = float(row['Recovery'])
+            st.sidebar.success("✅ Plant Data Calibrated!")
+        else:
+            st.sidebar.error("❌ Need 'Mineral' & 'Recovery' columns")
+    except Exception as e:
+        st.sidebar.error("❌ Invalid File Format")
+
+# --- MECHANICAL CONTROLS ---
+with st.sidebar:
+    st.divider()
+    st.subheader("⚙️ Machine Parameters")
+    feed_rate = st.slider("Feed Rate (TPH)", 20, 250, 85)
+    stroke = st.slider("Stroke Length (mm)", 10.0, 35.0, 22.0)
+    slope = st.slider("Deck Inclination (°)", 2.0, 8.0, 4.5)
+    water = st.slider("Wash Water (m³/h)", 5.0, 40.0, 18.0)
+    st.divider()
+    st.subheader("💰 Economics")
+    mining_cost = st.number_input("Mining Cost ($/t)", 5.0, 50.0, 12.5)
+    op_cost = st.number_input("Fixed OPEX ($/h)", 50.0, 500.0, 210.0)
+
+# ==========================================
+# 4. CALCULATIONS
+# ==========================================
+def run_model(rate, s, sl, w, target_dict):
+    eff = max(0.45, (s/22) * (1 - abs(sl-4.5)/10) * (1 - abs(w-18)/40))
+    conc_mass = rate * 0.25 
+    tail_mass = rate - conc_mass
+    res = []
+    total_rev = 0
+    for m, p_rec in target_dict.items():
+        m_rec = min(p_rec * eff, 99.0)
+        feed_val = rate * (FEED_GRADES[m] if m == "Gold" else FEED_GRADES[m]/100)
+        rev = (feed_val * (m_rec/100)) * DEFAULT_PRICES[m]
+        total_rev += rev
+        res.append({"Mineral": m, "Plant Rec%": p_rec, "Model Rec%": round(m_rec, 2), "Revenue ($/h)": round(rev, 2)})
+    return pd.DataFrame(res), total_rev, eff, conc_mass, tail_mass
+
+df_results, hourly_rev, sys_eff, c_mass, t_mass = run_model(feed_rate, stroke, slope, water, current_plant_rec)
+profit = hourly_rev - ((feed_rate * mining_cost) + op_cost)
+
+# ==========================================
+# 5. DASHBOARD TABS
+# ==========================================
+tab1, tab2, tab3, tab4 = st.tabs(["🚀 Executive Dashboard", "📊 Validation & Analytics", "📉 Quality Curves", "📑 Export Center"])
+
+with tab1:
+    st.subheader("Mass Balance & Plant Performance")
+    m1, m2, m3 = st.columns(3)
+    m1.metric("Total Feed", f"{feed_rate} TPH")
+    m2.metric("Concentrate", f"{c_mass:.2f} TPH")
+    m3.metric("Tailings", f"{t_mass:.2f} TPH")
+    
+    st.divider()
+    l, r = st.columns(2)
+    with l:
+        fig_pie, ax_pie = plt.subplots()
+        ax_pie.pie([c_mass, t_mass], labels=['Concentrate', 'Tailings'], autopct='%1.1f%%', colors=['#d4af37', '#0e314d'])
+        st.pyplot(fig_pie)
+    with r:
+        st.metric("Net Profit", f"${profit:,.0f}/h")
+        st.metric("Efficiency", f"{sys_eff*100:.1f}%")
+
+    st.markdown("#### Performance Matrix")
+    st.dataframe(df_results.style.background_gradient(cmap='Blues'), use_container_width=True)
+
+with tab2:
+    st.subheader("Calibration Analysis")
+    df_results['Error %'] = abs(df_results['Model Rec%'] - df_results['Plant Rec%'])
+    st.info(f"Mean Calibration Deviation: {df_results['Error %'].mean():.2f}%")
+    
+    fig_bar, ax_bar = plt.subplots(figsize=(10, 4))
+    x = np.arange(len(df_results))
+    ax_bar.bar(x-0.2, df_results['Plant Rec%'], 0.4, label='Plant (Input)', color='#adb5bd')
+    ax_bar.bar(x+0.2, df_results['Model Rec%'], 0.4, label='Twin (Model)', color='#d4af37')
+    ax_bar.set_xticks(x); ax_bar.set_xticklabels(df_results['Mineral']); ax_bar.legend()
+    st.pyplot(fig_bar)
+
+with tab3:
+    st.subheader("Grade-Recovery Engineering")
+    
+    m_choice = st.selectbox("Select Mineral", list(FEED_GRADES.keys()))
+    recs = np.linspace(30, 98, 50)
+    f_mass = feed_rate * (FEED_GRADES[m_choice] if m_choice=="Gold" else FEED_GRADES[m_choice]/100)
+    grades = [(f_mass * (r/100))/c_mass * (1 if m_choice=="Gold" else 100) for r in recs]
+    fig_gr, ax_gr = plt.subplots(figsize=(10, 4))
+    ax_gr.plot(recs, grades, color='#0e314d', lw=2)
+    st.pyplot(fig_gr)
+
+with tab4:
+    st.subheader("Official Report")
+    if st.button("Generate Final Word Report"):
+        doc = Document()
+        doc.add_heading(f"Digital Twin Calibration Report", 0)
+        doc.add_paragraph(f"Student: Emaan Rashid | 2022-min-13")
+        bio = BytesIO(); doc.save(bio)
+        st.download_button("Download .docx", bio.getvalue(), "Emaan_Rashid_Final.docx")
+
+st.divider()
+st.caption("Developed by Gemini AI | Senior Digital Twin Engine | UET Lahore")