Update app.py

app.py

@@ -18,7 +18,17 @@ st.set_page_config(
 EMBED_MODEL = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')
 GEN_MODEL = pipeline('text2text-generation', model='google/flan-t5-base')
 
-# Custom Style
+# Optional: Units per parameter
+unit_map = {
+    "temperature": "°C",
+    "vibration": "mm/s",
+    "pressure": "bar",
+    "current": "A",
+    "voltage": "V",
+    "speed": "RPM"
+}
+
+# Style
 st.markdown("""
     <style>
     html, body, [class*="css"] {
@@ -33,12 +43,6 @@ st.markdown("""
         margin-bottom: 1rem;
         box-shadow: 0 0 8px rgba(88,166,255,0.2);
     }
-    .metric-box {
-        background-color: #1f2937;
-        padding: 0.75rem;
-        border-radius: 8px;
-        margin-top: 0.5rem;
-    }
     </style>
 """, unsafe_allow_html=True)
 
@@ -51,20 +55,20 @@ st.markdown("""
     </div>
 """, unsafe_allow_html=True)
 
-# Upload CSV
+# File Upload
 uploaded_file = st.sidebar.file_uploader("📂 Upload sensor log (CSV)", type=["csv"])
 
 if uploaded_file:
     df = pd.read_csv(uploaded_file)
     numeric_cols = df.select_dtypes(include=np.number).columns.tolist()
 
-    # Run Anomaly Detection
-    iso = IsolationForest(contamination=0.02)
+    # Anomaly Detection
+    iso = IsolationForest(contamination=0.02, random_state=42)
     labels = iso.fit_predict(df[numeric_cols])
     df['status'] = ['❌ Fault Detected' if x == -1 else '✅ Healthy' for x in labels]
     df['maintenance_flag'] = ['🔧 Inspect Required' if x == -1 else '🟢 Stable' for x in labels]
 
-    # NLP Embeddings for RAG
+    # NLP Embeddings
     if 'chunks' not in st.session_state or 'embeddings' not in st.session_state:
         chunks = [
             f"[Entry {i}] " + ", ".join([f"{col}: {row[col]:.2f}" for col in numeric_cols])
@@ -74,32 +78,38 @@ if uploaded_file:
         st.session_state.chunks = chunks
         st.session_state.embeddings = embeddings
 
-    # Dashboard Layout
+    # Health Summary
     col1, col2 = st.columns(2)
-
     with col1:
         st.markdown("### 🧠 Machine Health Summary")
         status_counts = df['status'].value_counts()
-        fig1, ax1 = plt.subplots()
-        ax1.bar(status_counts.index, status_counts.values, color=["red", "green"])
-        ax1.set_title("Health Status Count")
-        ax1.set_ylabel("Instances")
+        fig1, ax1 = plt.subplots(figsize=(5, 4))
+        bars = ax1.bar(status_counts.index, status_counts.values, color=["red", "green"])
+        ax1.set_title("Detected Machine Health Conditions", fontsize=14)
+        ax1.set_ylabel("Record Count")
+        ax1.set_xlabel("Status")
         ax1.set_facecolor("#0f1117")
         ax1.tick_params(colors='white')
         ax1.title.set_color('white')
+        ax1.xaxis.label.set_color('white')
         ax1.yaxis.label.set_color('white')
         for spine in ax1.spines.values():
             spine.set_edgecolor('white')
+        for bar in bars:
+            height = bar.get_height()
+            ax1.annotate(f'{height:,}', xy=(bar.get_x() + bar.get_width()/2, height),
+                         xytext=(0, 6), textcoords="offset points", ha='center', color='white')
         st.pyplot(fig1)
 
     with col2:
         st.markdown("### 🧪 Parameters Monitored")
         st.markdown(f"""
             <div class="card">
-                <div style='line-height: 1.8;'>{' • '.join(numeric_cols)}</div>
+                {' • '.join(numeric_cols)}
             </div>
         """, unsafe_allow_html=True)
 
+    # Trend Plot
     st.markdown("### 📉 Sensor Trend (with Fault Overlay)")
     col3, col4 = st.columns(2)
     time_col = col3.selectbox("🕒 Time Column", ["None"] + list(df.columns))
@@ -110,17 +120,18 @@ if uploaded_file:
 
     x_vals = df[time_col] if time_col != "None" else df.index
     y_vals = df[trend_param]
+    y_label = f"{trend_param} ({unit_map.get(trend_param.lower(), '')})"
 
-    fig2, ax2 = plt.subplots()
-    ax2.plot(x_vals, y_vals, label=trend_param, color="skyblue")
+    fig2, ax2 = plt.subplots(figsize=(8, 4.5))
+    ax2.plot(x_vals, y_vals, label=trend_param, color="skyblue", linewidth=1.5)
     ax2.scatter(
         x_vals[df['status'] == '❌ Fault Detected'],
         y_vals[df['status'] == '❌ Fault Detected'],
         color='red', label='Fault Detected', zorder=5
     )
-    ax2.set_title(f"{trend_param} Trend")
+    ax2.set_title(f"{trend_param} Sensor Trend")
     ax2.set_xlabel("Time" if time_col != "None" else "Index")
-    ax2.set_ylabel(trend_param)
+    ax2.set_ylabel(y_label)
     ax2.legend()
     ax2.set_facecolor("#0f1117")
     ax2.tick_params(colors='white')
@@ -131,25 +142,45 @@ if uploaded_file:
         spine.set_edgecolor('white')
     st.pyplot(fig2)
 
-    # Export Fault Records
+    img_buffer = BytesIO()
+    fig2.savefig(img_buffer, format='png', bbox_inches="tight")
+    st.download_button("📷 Download Trend Chart (PNG)", img_buffer.getvalue(), file_name="sensor_trend.png")
+
+    # Fault Rate Over Time
+    if time_col != "None":
+        st.markdown("### 📈 Fault Rate Over Time")
+        df[time_col] = pd.to_datetime(df[time_col], errors='coerce')
+        df['fault_flag'] = df['status'].apply(lambda x: 1 if x == '❌ Fault Detected' else 0)
+        freq = 'H' if (df[time_col].max() - df[time_col].min()).days <= 3 else 'D'
+        grouped = df.set_index(time_col)['fault_flag'].resample(freq).mean() * 100
+
+        fig3, ax3 = plt.subplots(figsize=(8, 4))
+        ax3.plot(grouped.index, grouped, color='orange', linewidth=2)
+        ax3.set_title("Fault Rate Over Time")
+        ax3.set_ylabel("Fault Rate (%)")
+        ax3.set_xlabel("Time")
+        ax3.set_facecolor("#0f1117")
+        ax3.tick_params(colors='white')
+        ax3.title.set_color('white')
+        ax3.yaxis.label.set_color('white')
+        ax3.xaxis.label.set_color('white')
+        for spine in ax3.spines.values():
+            spine.set_edgecolor('white')
+        st.pyplot(fig3)
+
+    # Export Faults
     st.markdown("### 📤 Export Anomalies")
-    anomalies_df = df[df['status'] == '❌ Fault Detected']
-    buffer = BytesIO()
-    anomalies_df.to_csv(buffer, index=False)
-    st.download_button(
-        label="⬇️ Download Fault Log",
-        data=buffer.getvalue(),
-        file_name="fault_anomalies.csv",
-        mime="text/csv"
-    )
+    fault_df = df[df['status'] == '❌ Fault Detected']
+    buf = BytesIO()
+    fault_df.to_csv(buf, index=False)
+    st.download_button("⬇️ Download Fault Log", data=buf.getvalue(), file_name="faults.csv", mime="text/csv")
 
-    # Fault Correlation
+    # Metadata correlation
     st.markdown("### 🏷️ Fault Distribution by Machine/Component")
-    metadata_cols = [col for col in df.columns if 'machine' in col.lower() or 'component' in col.lower()]
-    for meta in metadata_cols:
-        st.markdown(f"**{meta} – Fault Frequency**")
-        meta_counts = df[df['status'] == '❌ Fault Detected'][meta].value_counts()
-        st.bar_chart(meta_counts)
+    meta_cols = [c for c in df.columns if 'machine' in c.lower() or 'component' in c.lower()]
+    for col in meta_cols:
+        st.markdown(f"**{col} – Fault Frequency**")
+        st.bar_chart(df[df['status'] == '❌ Fault Detected'][col].value_counts())
 
     # Role Assistant
     st.markdown("### 💬 Technical Assistant by Role")
@@ -169,20 +200,20 @@ if uploaded_file:
     }
 
     role = st.selectbox("👤 Select your role", roles.keys())
-    user_input = st.text_input("🧠 Ask a question")
+    question = st.text_input("🧠 Ask a question")
 
-    if user_input:
-        query_vec = EMBED_MODEL.encode([user_input])[0]
-        sims = np.dot(st.session_state.embeddings, query_vec)
-        top_idxs = np.argsort(sims)[-5:][::-1]
-        context = "\n".join([st.session_state.chunks[i] for i in top_idxs])
+    if question:
+        qvec = EMBED_MODEL.encode([question])[0]
+        sims = np.dot(st.session_state.embeddings, qvec)
+        idxs = np.argsort(sims)[-5:][::-1]
+        context = "\n".join([st.session_state.chunks[i] for i in idxs])
 
         prompt = (
             f"ROLE: {role}\n"
             f"RESPONSIBILITIES: {roles[role]['description']}\n"
             f"COMMUNICATION STYLE: {roles[role]['style']}\n\n"
             f"DATA CONTEXT:\n{context}\n\n"
-            f"QUESTION:\n{user_input}\n\n"
+            f"QUESTION:\n{question}\n\n"
             f"ANSWER:\n"
         )
         result = GEN_MODEL(prompt, max_length=400)[0]['generated_text']