Update app.py

app.py

@@ -1153,11 +1153,10 @@ except Exception as e:
 
 # =================== OBJECTIVE 5: Operator Fatigue Risk Gradient Dashboard =====================
 
-
+# ... (kode sebelumnya tetap sama) ...
 
 # =================== OBJECTIVE 5: Operator Fatigue Risk Gradient Dashboard =====================
-st.subheader("OBJECTIVE 5: See your team's fatigue risk gradient at a glance!")
-
+st.subheader("OBJECTIVE 5: See your team’s fatigue risk gradient at a glance!")
 # Custom CSS untuk tampilan ala market saham yang sangat fancy dan profesional
 st.markdown("""
 <style>
@@ -1295,18 +1294,12 @@ else:
             st.info("No operator data after filtering.")
             st.stop()
 
-        # Tambahkan kolom shift jika ada
-        if 'shift' in df_op.columns:
-            df_op['shift'] = df_op['shift'].fillna('Unknown')
-        else:
-            # Jika tidak ada kolom shift, buat kolom shift berdasarkan waktu
-            df_op['shift'] = df_op['start'].dt.hour.apply(
-                lambda x: 'Shift 1' if 6 <= x < 14 else ('Shift 2' if 14 <= x < 22 else 'Shift 3')
-            )
+        # Pastikan col_operator bukan None sebelum digunakan
+        if col_operator is None:
+            st.error(f"Operator column could not be auto-detected. Please check your data.")
+            st.stop()
 
-        # Buat kolom date dan daily_count
-        df_op["date"] = df_op["start"].dt.date
-        daily = df_op.groupby([col_operator, "date"]).size().reset_index(name="daily_count")
+        df_op["year_week"] = df_op["start"].dt.strftime("%Y-W%U")
 
         # Fuzzy match fleet names
         fleet_clean = df_op[col_fleet_type].str.strip().str.upper()
@@ -1316,60 +1309,52 @@ else:
         ob_data = df_op[df_op["is_ob"]]
         coal_data = df_op[df_op["is_coal"]]
 
-        # Fungsi hitung top 10 (untuk bar chart) - berdasarkan daily avg events tertinggi
+        # Fungsi hitung top 10 (untuk bar chart) - berdasarkan weekly avg events tertinggi
         def get_top10_with_slope(data):
             if data.empty:
                 st.warning("Data is empty in get_top10_with_slope.")
                 return pd.DataFrame()
-            
             # Pastikan col_operator tidak None dan ada di data
             if col_operator is None or col_operator not in data.columns:
                 st.error(f"Operator column '{col_operator}' not found in data subset for get_top10.")
                 return pd.DataFrame()
 
-            # Hitung daily count untuk masing-masing operator dan tanggal
-            daily_data = data.groupby([col_operator, "date"]).size().reset_index(name="daily_count")
-            
+            weekly = data.groupby([col_operator, "year_week"]).size().reset_index(name="weekly_sum")
             metrics = []
             try:
-                for nik, grp in daily_data.groupby(col_operator):
+                for nik, grp in weekly.groupby(col_operator):
                     # Lewati jika nik adalah None
                     if pd.isna(nik):
                         continue
-                    grp = grp.sort_values("date")
-                    counts = grp["daily_count"].values
-                    dates = np.arange(len(counts))
-                    daily_avg = counts.mean()
+                    grp = grp.sort_values("year_week")
+                    counts = grp["weekly_sum"].values
+                    weeks = np.arange(len(counts))
+                    weekly_avg = counts.mean()
                     total_events = counts.sum()
-                    n_days = len(counts)
-                    
-                    if n_days >= 2:
-                        x_mean = dates.mean()
+                    n_weeks = len(counts)
+                    if n_weeks >= 2:
+                        x_mean = weeks.mean()
                         y_mean = counts.mean()
-                        numerator = np.sum((dates - x_mean) * (counts - y_mean))
-                        denominator = np.sum((dates - x_mean) ** 2)
+                        numerator = np.sum((weeks - x_mean) * (counts - y_mean))
+                        denominator = np.sum((weeks - x_mean) ** 2)
                         slope = numerator / denominator if denominator != 0 else 0.0
                     else:
                         slope = 0.0
-                    
                     metrics.append({
                         col_operator: nik,
-                        "daily_avg": daily_avg,
+                        "weekly_avg": weekly_avg,
                         "slope": slope,
                         "total_events": total_events,
-                        "n_days": n_days
+                        "n_weeks": n_weeks
                     })
             except KeyError as e:
                 st.error(f"KeyError in get_top10_with_slope: {e}. This might happen if the operator column contains invalid data types or unexpected values.")
                 return pd.DataFrame()
-            
-            # Ambil top 10 berdasarkan daily_avg (descending order)
+            # Ambil top 10 berdasarkan weekly_avg (descending order)
             if not metrics:
                 st.warning("No valid operator data found for slope calculation in get_top10.")
                 return pd.DataFrame()
-            
-            df_metrics = pd.DataFrame(metrics)
-            return df_metrics.nlargest(10, "daily_avg")
+            return pd.DataFrame(metrics).nlargest(10, "weekly_avg")
 
         top_ob = get_top10_with_slope(ob_data)
         top_coal = get_top10_with_slope(coal_data)
@@ -1379,52 +1364,45 @@ else:
             if data.empty:
                 st.warning("Data is empty in get_all_operators_with_slope.")
                 return pd.DataFrame()
-            
             # Pastikan col_operator tidak None dan ada di data
             if col_operator is None or col_operator not in data.columns:
                 st.error(f"Operator column '{col_operator}' not found in data subset for get_all.")
                 return pd.DataFrame()
 
-            # Hitung daily count untuk masing-masing operator dan tanggal
-            daily_data = data.groupby([col_operator, "date"]).size().reset_index(name="daily_count")
-            
+            weekly = data.groupby([col_operator, "year_week"]).size().reset_index(name="weekly_sum")
             metrics = []
             try:
-                for nik, grp in daily_data.groupby(col_operator):
+                for nik, grp in weekly.groupby(col_operator):
                     # Lewati jika nik adalah None
                     if pd.isna(nik):
                         continue
-                    grp = grp.sort_values("date")
-                    counts = grp["daily_count"].values
-                    dates = np.arange(len(counts))
-                    daily_avg = counts.mean()
+                    grp = grp.sort_values("year_week")
+                    counts = grp["weekly_sum"].values
+                    weeks = np.arange(len(counts))
+                    weekly_avg = counts.mean()
                     total_events = counts.sum()
-                    n_days = len(counts)
-                    
-                    if n_days >= 2:
-                        x_mean = dates.mean()
+                    n_weeks = len(counts)
+                    if n_weeks >= 2:
+                        x_mean = weeks.mean()
                         y_mean = counts.mean()
-                        numerator = np.sum((dates - x_mean) * (counts - y_mean))
-                        denominator = np.sum((dates - x_mean) ** 2)
+                        numerator = np.sum((weeks - x_mean) * (counts - y_mean))
+                        denominator = np.sum((weeks - x_mean) ** 2)
                         slope = numerator / denominator if denominator != 0 else 0.0
                     else:
                         slope = 0.0
-                    
                     metrics.append({
                         col_operator: nik,
-                        "daily_avg": daily_avg,
+                        "weekly_avg": weekly_avg,
                         "slope": slope,
                         "total_events": total_events,
-                        "n_days": n_days
+                        "n_weeks": n_weeks
                     })
             except KeyError as e:
                 st.error(f"KeyError in get_all_operators_with_slope: {e}. This might happen if the operator column contains invalid data types or unexpected values.")
                 return pd.DataFrame()
-            
             if not metrics:
                 st.warning("No valid operator data found for slope calculation in get_all.")
                 return pd.DataFrame()
-            
             return pd.DataFrame(metrics)
 
         all_ob = get_all_operators_with_slope(ob_data)
@@ -1481,7 +1459,7 @@ else:
                     <span>Stable (0)</span>
                 </div>
                 <br>
-                <i>Note: Only appears when operator data shows consistent behavior within a single day observation period.</i>
+                <i>Note: Only appears when operator data shows consistent behavior within a single week observation period.</i>
             </div>
         </div>
         """, unsafe_allow_html=True)
@@ -1502,8 +1480,8 @@ else:
                 fig.update_layout(height=350, title=title)
                 return fig
 
-            # Urutkan data berdasarkan daily_avg dari besar ke kecil
-            data_sorted = data.sort_values('daily_avg', ascending=False)
+            # Urutkan data berdasarkan weekly_avg dari besar ke kecil
+            data_sorted = data.sort_values('weekly_avg', ascending=False)
 
             # Kategorisasi warna berdasarkan slope dengan gradasi yang berbeda
             def get_color(slope):
@@ -1535,22 +1513,22 @@ else:
             # Buat trace bar, TANPA argumen 'title'
             bar_trace = go.Bar(
                 x=data_sorted[col_operator].astype(str),
-                y=data_sorted["daily_avg"],
+                y=data_sorted["weekly_avg"],
                 marker=dict(
                     color=colors,
                     line=dict(width=2, color="rgba(0,0,0,0.2)")
                 ),
-                text=[f"{v:.1f}" for v in data_sorted["daily_avg"]],
+                text=[f"{v:.1f}" for v in data_sorted["weekly_avg"]],
                 textposition="outside",
                 hovertemplate=(
                     "<b>%{x}</b><br>" +
-                    "Daily Avg: %{y:.2f}<br>" +
+                    "Weekly Avg: %{y:.2f}<br>" +
                     "Trend Slope: %{customdata[0]:+.3f}<br>" +
                     "Total Events: %{customdata[1]}<br>" +
-                    "Days Active: %{customdata[2]}<br>" +
+                    "Weeks Active: %{customdata[2]}<br>" +
                     "<extra></extra>"
                 ),
-                customdata=np.stack([data_sorted["slope"], data_sorted["total_events"], data_sorted["n_days"]], axis=-1)
+                customdata=np.stack([data_sorted["slope"], data_sorted["total_events"], data_sorted["n_weeks"]], axis=-1)
             )
 
             # Buat figure dan tambahkan trace
@@ -1563,7 +1541,7 @@ else:
                 height=450,
                 margin=dict(l=50, r=20, t=60, b=120),
                 xaxis_title="<b>Operator ID</b>",
-                yaxis_title="<b>Daily Avg Events</b>",
+                yaxis_title="<b>Weekly Avg Events</b>",
                 font=dict(family="Segoe UI", size=12),
                 bargap=0.3,
                 plot_bgcolor="rgba(0,0,0,0)",
@@ -1595,14 +1573,14 @@ else:
                 st.markdown("### OB HAULER Analysis")
                 ob_worsening = len(top_ob[top_ob['slope'] > 0])
                 ob_improving = len(top_ob[top_ob['slope'] < 0])
-                ob_avg_risk = top_ob['daily_avg'].mean()
-                ob_max_risk = top_ob['daily_avg'].max()
+                ob_avg_risk = top_ob['weekly_avg'].mean()
+                ob_max_risk = top_ob['weekly_avg'].max()
                 ob_insights = []
                 if ob_worsening > ob_improving:
                     ob_insights.append(f"{ob_worsening} out of 10 top risk operators are showing <span class='trend-up'>worsening</span> trends, indicating potential fatigue issues in this fleet type.")
                 else:
                     ob_insights.append(f"{ob_improving} out of 10 top risk operators are showing <span class='trend-down'>improvement</span>, suggesting effective fatigue management strategies.")
-                ob_insights.append(f"Average risk level among top 10 operators is {ob_avg_risk:.2f} events per day with maximum {ob_max_risk:.2f}.")
+                ob_insights.append(f"Average risk level among top 10 operators is {ob_avg_risk:.2f} events per week with maximum {ob_max_risk:.2f}.")
 
                 for insight in ob_insights:
                     st.markdown(f"""
@@ -1620,14 +1598,14 @@ else:
                 st.markdown("### HAULING COAL Analysis")
                 coal_worsening = len(top_coal[top_coal['slope'] > 0])
                 coal_improving = len(top_coal[top_coal['slope'] < 0])
-                coal_avg_risk = top_coal['daily_avg'].mean()
-                coal_max_risk = top_coal['daily_avg'].max()
+                coal_avg_risk = top_coal['weekly_avg'].mean()
+                coal_max_risk = top_coal['weekly_avg'].max()
                 coal_insights = []
                 if coal_worsening > coal_improving:
                     coal_insights.append(f"{coal_worsening} out of 10 top risk operators are showing <span class='trend-up'>worsening</span> trends, requiring immediate attention.")
                 else:
                     coal_insights.append(f"{coal_improving} out of 10 top risk operators are showing <span class='trend-down'>improvement</span>, indicating positive trends in safety management.")
-                coal_insights.append(f"Average risk level among top 10 operators is {coal_avg_risk:.2f} events per day with maximum {coal_max_risk:.2f}.")
+                coal_insights.append(f"Average risk level among top 10 operators is {coal_avg_risk:.2f} events per week with maximum {coal_max_risk:.2f}.")
 
                 for insight in coal_insights:
                     st.markdown(f"""
@@ -1654,7 +1632,7 @@ else:
             recommendations = {}
             if not top_ob.empty:
                 ob_worsening = len(top_ob[top_ob['slope'] > 0])
-                ob_avg_risk = top_ob['daily_avg'].mean()
+                ob_avg_risk = top_ob['weekly_avg'].mean()
                 if ob_worsening > 5:  # Lebih dari setengah
                     recommendations['ob'] = "Implement immediate fatigue monitoring protocols for operators showing worsening trends."
                     reason_ob = "High percentage of operators showing increasing risk trends indicates potential systemic fatigue issues requiring immediate intervention."
@@ -1668,7 +1646,7 @@ else:
 
             if not top_coal.empty:
                 coal_worsening = len(top_coal[top_coal['slope'] > 0])
-                coal_avg_risk = top_coal['daily_avg'].mean()
+                coal_avg_risk = top_coal['weekly_avg'].mean()
                 if coal_worsening > 5:  # Lebih dari setengah
                     recommendations['coal'] = "Implement immediate fatigue monitoring protocols for operators showing worsening trends."
                     reason_coal = "High percentage of operators showing increasing risk trends indicates potential systemic fatigue issues requiring immediate intervention."
@@ -1716,6 +1694,9 @@ else:
         st.error(f"Error in Top 10 Operator analysis: {str(e)}")
         st.code(f"Error: {e}", language="python")
 
+
+
+
 # =================== OBJECTIVE 6: Automated Insights & AI Recommendations =====================
 st.subheader("OBJECTIVE 6: Instant Insights & Recommendations")