Update app.py

app.py

@@ -1187,142 +1187,168 @@ if WORDCLOUD_AVAILABLE:
 
 else:
     st.info("WordCloud library not installed. Install `wordcloud` and `matplotlib` to enable this feature.")
+
 # =================== 5. Matrix (Tetap Dipertahankan) ===================
 st.markdown("<h3 class='section-title'>OBJECTIVE 5 - Findings vs Lead Time: Which Divisions Move Slow?</h3>", unsafe_allow_html=True)
 
 import math
 import plotly.express as px
 import pandas as pd
+
 try:
     df_local_matrix = df.copy()
-    # ============================
-    # 0. Filter: ONLY 1 COMPANY & 1 PROFILE (if applicable)
-    # ============================
-    # (Skipped for general dashboard view)
-    # ============================
+
     # 1. Exclude Positive findings
-    # ============================
     if 'temuan_kategori' in df_local_matrix.columns:
         df_local_matrix = df_local_matrix[df_local_matrix["temuan_kategori"] != "Positive"]
-    # ============================
+
     # 2. Ensure datetime columns
-    # ============================
     df_local_matrix['created_at'] = pd.to_datetime(df_local_matrix['created_at'], errors='coerce')
     df_local_matrix['close_at'] = pd.to_datetime(df_local_matrix['close_at'], errors='coerce')
-    # ============================
-    # 3. Compute LEAD TIME
-    # ============================
+
+    # 3. Compute LEAD TIME in days
     df_local_matrix['lead_time_days'] = (df_local_matrix['close_at'] - df_local_matrix['created_at']).dt.days
     df_local_matrix['lead_time_days'] = df_local_matrix['lead_time_days'].fillna(0)
-    # ============================
-    # 4. Average Monthly Finding Count per Operator
-    # ============================
+
+    # 4. Avg Monthly Finding Count per Division ('nama')
     if 'nama' not in df_local_matrix.columns:
-        st.error("❌ Kolom 'nama' (operator) tidak ditemukan.")
-        # st.stop() # Stop bisa dihilangkan agar script tetap jalan
+        st.error("❌ Kolom 'nama' (Division/Operator) tidak ditemukan.")
     else:
-        # Buat kolom bulan (YYYY-MM)
+        # Create YYYY-MM month column
         df_local_matrix = df_local_matrix.assign(month=df_local_matrix['created_at'].dt.to_period('M').astype(str))
-        # Hitung jumlah temuan per operator per bulan
+
+        # Count unique findings per division per month
         monthly_counts = (
             df_local_matrix
             .groupby(['nama', 'month'])['kode_temuan']
             .nunique()
             .reset_index(name='monthly_count')
         )
-        # Hitung rata-rata bulanan per operator
+
+        # Average findings per month per division
         operator_avg = (
             monthly_counts
             .groupby('nama')['monthly_count']
-            .mean()  # <-- RATA-RATA per bulan (bukan total!)
+            .mean()
             .reset_index(name='Finding Count')
         )
-        # ============================
-        # 5. Average Lead Time per Operator
-        # ============================
+
+        # 5. Average Lead Time per Division
         operator_lead = (
-            df_local_matrix.groupby('nama')['lead_time_days']
+            df_local_matrix
+            .groupby('nama')['lead_time_days']
             .mean()
-            .reset_index(name='Lead Time')
+            .reset_index(name='Average Lead Time')  # 🔑 Renamed here!
         )
-        # ============================
-        # 6. Merge Risk Matrix
-        # ============================
+
+        # 6. Merge → Risk Matrix
         risk_matrix = operator_avg.merge(operator_lead, on='nama', how='left')
         risk_matrix = risk_matrix.rename(columns={'nama': 'Division'})
-        # Handle operator tanpa lead time (e.g., belum closed)
-        risk_matrix['Average Lead Time'] = risk_matrix['Average Lead Time'].fillna(0)
-        # ============================
-        # 7. Quadrant Logic (unchanged)
-        # ============================
-        X_LIMIT = 20
-        Y_LIMIT = 3
+
+        # Fill missing lead time (e.g., no closed findings) with 0
+        risk_matrix['Average Lead Time'] = risk_matrix['Average Lead Time'].fillna(0).round(2)
+        risk_matrix['Finding Count'] = risk_matrix['Finding Count'].round(2)
+
+        # 7. Quadrant Logic
+        X_LIMIT = 20  # avg findings/month threshold
+        Y_LIMIT = 3   # avg lead time (days) threshold
+
         def assign_quadrant(row):
-            if row['Finding Count'] >= X_LIMIT and row['Average Lead Time'] >= Y_LIMIT:
+            fc = row['Finding Count']
+            lt = row['Average Lead Time']
+            if fc >= X_LIMIT and lt >= Y_LIMIT:
                 return "Quadrant I – High Leadtime & High Count"
-            elif row['Finding Count'] < X_LIMIT and row['Average Lead Time'] >= Y_LIMIT:
+            elif fc < X_LIMIT and lt >= Y_LIMIT:
                 return "Quadrant II – High Leadtime but Low Count"
-            elif row['Finding Count'] >= X_LIMIT and row['Average Lead Time'] < Y_LIMIT:
+            elif fc >= X_LIMIT and lt < Y_LIMIT:
                 return "Quadrant III – Low Leadtime but High Count"
             else:
                 return "Quadrant IV – Low Leadtime & Low Count"
+
         risk_matrix['quadrant'] = risk_matrix.apply(assign_quadrant, axis=1)
         quadrant_count = risk_matrix['quadrant'].value_counts()
-        # ============================
-        # 8. Scatter Plot (format visual tetap sam persis)
-        # ============================
-        max_x = risk_matrix['Finding Count'].max() + 1
-        max_y = risk_matrix['Average Lead Time'].max() + 5
+
+        # 8. Plot Scatter with Quadrant Backgrounds
+        max_x = max(risk_matrix['Finding Count'].max() + 1, X_LIMIT + 5)
+        max_y = max(risk_matrix['Average Lead Time'].max() + 5, Y_LIMIT + 5)
+
         fig = px.scatter(
             risk_matrix,
             x='Finding Count',
             y='Average Lead Time',
-            hover_name="Division",
-            size=[12] * len(risk_matrix),
-            size_max=15,
-            # title="Audit Findings Risk Matrix: Avg Monthly Count vs Lead Time"
+            hover_name='Division',
+            color='quadrant',
+            color_discrete_map={
+                "Quadrant I – High Leadtime & High Count": "darkred",
+                "Quadrant II – High Leadtime but Low Count": "orange",
+                "Quadrant III – Low Leadtime but High Count": "tomato",
+                "Quadrant IV – Low Leadtime & Low Count": "green"
+            },
+            height=500
         )
-        # Background quadrant (same as original)
+
+        # Quadrant background shading
         fig.add_shape(type="rect", x0=X_LIMIT, x1=max_x, y0=Y_LIMIT, y1=max_y,
-                      fillcolor="rgba(255,0,0,0.25)", line_width=0)      # Q1
+                      fillcolor="rgba(255,0,0,0.15)", line_width=0, layer="below")
         fig.add_shape(type="rect", x0=0, x1=X_LIMIT, y0=Y_LIMIT, y1=max_y,
-                      fillcolor="rgba(255,150,50,0.25)", line_width=0)  # Q2
+                      fillcolor="rgba(255,150,50,0.15)", line_width=0, layer="below")
         fig.add_shape(type="rect", x0=X_LIMIT, x1=max_x, y0=0, y1=Y_LIMIT,
-                      fillcolor="rgba(255,200,200,0.25)", line_width=0) # Q3
+                      fillcolor="rgba(255,200,200,0.15)", line_width=0, layer="below")
         fig.add_shape(type="rect", x0=0, x1=X_LIMIT, y0=0, y1=Y_LIMIT,
-                      fillcolor="rgba(0,120,255,0.15)", line_width=0)   # Q4
-        fig.add_vline(x=X_LIMIT, line_dash="dash", line_color="black")
-        fig.add_hline(y=Y_LIMIT, line_dash="dash", line_color="black")
-        # Quadrant count annotations (same positions & style)
-        fig.add_annotation(x=X_LIMIT + (max_x - X_LIMIT)/2,
-                           y=Y_LIMIT + (max_y - Y_LIMIT)/2,
-                           text=f"<b>{quadrant_count.get('Quadrant I – High Leadtime & High Count',0)}</b>",
-                           showarrow=False, font=dict(size=22, color="darkred"))
-        fig.add_annotation(x=X_LIMIT/2,
-                           y=Y_LIMIT + (max_y - Y_LIMIT)/2,
-                           text=f"<b>{quadrant_count.get('Quadrant II – High Leadtime but Low Count',0)}</b>",
-                           showarrow=False, font=dict(size=22, color="orange"))
-        fig.add_annotation(x=X_LIMIT + (max_x - X_LIMIT)/2,
-                           y=Y_LIMIT/2,
-                           text=f"<b>{quadrant_count.get('Quadrant III – Low Leadtime but High Count',0)}</b>",
-                           showarrow=False, font=dict(size=22, color="red"))
-        fig.add_annotation(x=X_LIMIT/2,
-                           y=Y_LIMIT/2,
-                           text=f"<b>{quadrant_count.get('Quadrant IV – Low Leadtime & Low Count',0)}</b>",
-                           showarrow=False, font=dict(size=22, color="green"))
+                      fillcolor="rgba(0,120,255,0.10)", line_width=0, layer="below")
+
+        # Threshold lines
+        fig.add_vline(x=X_LIMIT, line_dash="dash", line_color="gray", opacity=0.7)
+        fig.add_hline(y=Y_LIMIT, line_dash="dash", line_color="gray", opacity=0.7)
+
+        # Quadrant labels & counts
+        annotations = [
+            (X_LIMIT + (max_x - X_LIMIT)/2, Y_LIMIT + (max_y - Y_LIMIT)/2, "Q1", "darkred"),
+            (X_LIMIT/2, Y_LIMIT + (max_y - Y_LIMIT)/2, "Q2", "orange"),
+            (X_LIMIT + (max_x - X_LIMIT)/2, Y_LIMIT/2, "Q3", "tomato"),
+            (X_LIMIT/2, Y_LIMIT/2, "Q4", "green"),
+        ]
+
+        for x, y, label, color in annotations:
+            count = quadrant_count.get(f"Quadrant {label.replace('Q','I ' if '1' in label else ('II ' if '2' in label else ('III ' if '3' in label else 'IV '))}– ...", 0)
+            # Safer lookup: reconstruct key
+            key = next((k for k in quadrant_count.index if label in k), None)
+            cnt = quadrant_count.get(key, 0) if key else 0
+            fig.add_annotation(
+                x=x, y=y,
+                text=f"<b>{label}<br>{int(cnt)}</b>",
+                showarrow=False,
+                font=dict(size=16, color=color),
+                bgcolor="white",
+                opacity=0.8
+            )
+
+        # Axis & layout tuning
+        fig.update_layout(
+            xaxis_title="Average Monthly Findings per Division",
+            yaxis_title="Average Lead Time (Days)",
+            legend_title="Quadrant",
+            margin=dict(t=40, b=40, l=40, r=40)
+        )
+
         st.plotly_chart(fig, use_container_width=True)
-        # ============================
-        # 9. Summary Table
-        # ============================
-        # st.markdown("<h3 style='font-size:12px; margin-bottom:6px;'>Summary (Avg Monthly Count vs Avg Lead Time)</h3>",unsafe_allow_html=True)
 
+        # 9. Summary Table (sorted descending by Finding Count)
+        st.markdown("<h4 style='text-align:center;'>Division Performance Summary</h4>", unsafe_allow_html=True)
         st.dataframe(
-            risk_matrix.sort_values("Finding Count", ascending=False),
-            use_container_width=True
+            risk_matrix[
+                ['Division', 'Finding Count', 'Average Lead Time', 'quadrant']
+            ].sort_values("Finding Count", ascending=False)
+            .round(2),
+            use_container_width=True,
+            hide_index=True
         )
+
 except Exception as e:
-    st.error(f"⚠️ Error Risk Matrix: {e}")
-    # st.exception(e) # Uncomment for debugging
+    st.error(f"⚠️ Error in Risk Matrix (Objective 5): {e}")
+    st.exception(e)  # Optional: show full traceback during dev
+
+# st.exception(e) # Uncomment for debugging
 
 import streamlit as st
 import plotly.graph_objects as go