Update app.py

app.py

@@ -31,7 +31,9 @@ def summarize_logs(df):
     try:
         total_devices = df["device_id"].nunique()
         total_usage = df["usage_hours"].sum() if "usage_hours" in df.columns else 0
-        return f"{total_devices} devices processed with {total_usage:.2f} total usage hours."
+        lab_sites = df["lab_site"].nunique() if "lab_site" in df.columns else 0
+        equipment_types = df["equipment_type"].nunique() if "equipment_type" in df.columns else 0
+        return f"{total_devices} devices processed with {total_usage:.2f} total usage hours across {lab_sites} lab sites and {equipment_types} equipment types."
     except Exception as e:
         logging.error(f"Summary generation failed: {str(e)}")
         return "Failed to generate summary."
@@ -46,10 +48,10 @@ def detect_anomalies(df):
             features = features.sample(n=50, random_state=42)
         iso_forest = IsolationForest(contamination=0.1, random_state=42)
         df["anomaly"] = iso_forest.fit_predict(features)
-        anomalies = df[df["anomaly"] == -1][["device_id", "usage_hours", "downtime", "timestamp"]]
+        anomalies = df[df["anomaly"] == -1][["device_id", "usage_hours", "downtime", "timestamp", "lab_site", "equipment_type"]]
         if anomalies.empty:
             return "No anomalies detected.", anomalies
-        return "\n".join([f"- Device ID: {row['device_id']}, Usage: {row['usage_hours']}, Downtime: {row['downtime']}, Timestamp: {row['timestamp']}" for _, row in anomalies.head(5).iterrows()]), anomalies
+        return "\n".join([f"- Device ID: {row['device_id']}, Usage: {row['usage_hours']}, Downtime: {row['downtime']}, Timestamp: {row['timestamp']}, Lab Site: {row['lab_site']}, Equipment Type: {row['equipment_type']}" for _, row in anomalies.head(5).iterrows()]), anomalies
     except Exception as e:
         logging.error(f"Anomaly detection failed: {str(e)}")
         return f"Anomaly detection failed: {str(e)}", pd.DataFrame()
@@ -62,10 +64,10 @@ def check_amc_reminders(df, current_date):
         df["amc_date"] = pd.to_datetime(df["amc_date"], errors='coerce')
         current_date = pd.to_datetime(current_date)
         df["days_to_amc"] = (df["amc_date"] - current_date).dt.days
-        reminders = df[(df["days_to_amc"] >= 0) & (df["days_to_amc"] <= 30)][["device_id", "log_type", "status", "timestamp", "usage_hours", "downtime", "amc_date"]]
+        reminders = df[(df["days_to_amc"] >= 0) & (df["days_to_amc"] <= 30)][["device_id", "log_type", "status", "timestamp", "usage_hours", "downtime", "amc_date", "lab_site", "equipment_type"]]
         if reminders.empty:
             return "No AMC reminders due within the next 30 days.", reminders
-        return "\n".join([f"- Device ID: {row['device_id']}, AMC Date: {row['amc_date']}" for _, row in reminders.head(5).iterrows()]), reminders
+        return "\n".join([f"- Device ID: {row['device_id']}, AMC Date: {row['amc_date']}, Lab Site: {row['lab_site']}, Equipment Type: {row['equipment_type']}" for _, row in reminders.head(5).iterrows()]), reminders
     except Exception as e:
         logging.error(f"AMC reminder generation failed: {str(e)}")
         return f"AMC reminder generation failed: {str(e)}", pd.DataFrame()
@@ -75,7 +77,9 @@ def generate_dashboard_insights(df):
     try:
         total_devices = df["device_id"].nunique()
         avg_usage = df["usage_hours"].mean() if "usage_hours" in df.columns else 0
-        return f"{total_devices} devices with average usage of {avg_usage:.2f} hours."
+        lab_sites = df["lab_site"].unique().tolist() if "lab_site" in df.columns else []
+        equipment_types = df["equipment_type"].unique().tolist() if "equipment_type" in df.columns else []
+        return f"{total_devices} devices with average usage of {avg_usage:.2f} hours. Lab Sites: {', '.join(lab_sites)}. Equipment Types: {', '.join(equipment_types)}."
     except Exception as e:
         logging.error(f"Dashboard insights generation failed: {str(e)}")
         return "Failed to generate insights."
@@ -219,6 +223,8 @@ def generate_device_cards(df):
         device_stats = df.groupby('device_id').agg({
             'status': 'last',
             'timestamp': 'max',
+            'lab_site': 'last',
+            'equipment_type': 'last'
         }).reset_index()
         device_stats['count'] = df.groupby('device_id').size().reindex(device_stats['device_id']).values
         device_stats['health'] = device_stats['status'].map({
@@ -230,10 +236,14 @@ def generate_device_cards(df):
         for _, row in device_stats.iterrows():
             health_color = {'Healthy': 'green', 'Unhealthy': 'red', 'Warning': 'orange', 'Unknown': 'gray'}.get(row['health'], 'gray')
             timestamp_str = str(row['timestamp']) if pd.notna(row['timestamp']) else 'Unknown'
+            lab_site = row['lab_site'] if pd.notna(row['lab_site']) else 'Unknown'
+            equipment_type = row['equipment_type'] if pd.notna(row['equipment_type']) else 'Unknown'
             cards_html += f"""
                 <div style="border: 1px solid #e0e0e0; padding: 10px; border-radius: 5px; width: 200px;">
                     <h4>Device: {row['device_id']}</h4>
                     <p><b>Health:</b> <span style="color: {health_color}">{row['health']}</span></p>
+                    <p><b>Lab Site:</b> {lab_site}</p>
+                    <p><b>Equipment Type:</b> {equipment_type}</p>
                     <p><b>Usage Count:</b> {row['count']}</p>
                     <p><b>Last Log:</b> {timestamp_str}</p>
                 </div>
@@ -337,7 +347,9 @@ async def process_logs(file_obj, lab_site_filter, equipment_type_filter, date_ra
                 "status": "string",
                 "usage_hours": "float32",
                 "downtime": "float32",
-                "amc_date": "string"
+                "amc_date": "string",
+                "lab_site": "string",
+                "equipment_type": "string"
             }
             df = pd.read_csv(file_path, dtype=dtypes)
             missing_columns = [col for col in required_columns if col not in df.columns]
@@ -375,7 +387,7 @@ async def process_logs(file_obj, lab_site_filter, equipment_type_filter, date_ra
             return "No data after applying filters.", "<p>No data after filters.</p>", None, '<p>No device cards available.</p>', None, None, None, None, "", "", "", None, df, current_modified_time
 
         # Generate table for preview
-        preview_df = filtered_df[['device_id', 'log_type', 'status', 'timestamp', 'usage_hours', 'downtime', 'amc_date']].head(5)
+        preview_df = filtered_df[['device_id', 'log_type', 'status', 'timestamp', 'usage_hours', 'downtime', 'amc_date', 'lab_site', 'equipment_type']].head(5)
         preview_html = preview_df.to_html(index=False, classes='table table-striped', border=0)
 
         # Run critical tasks concurrently