Update app.py

app.py

@@ -5,6 +5,7 @@ import logging
 import plotly.express as px
 import plotly.graph_objects as go
 from sklearn.ensemble import IsolationForest
+from concurrent.futures import ThreadPoolExecutor  # Added missing import
 import os
 import io
 import time
@@ -25,7 +26,7 @@ except ImportError:
     logging.warning("reportlab module not found. PDF generation disabled.")
     reportlab_available = False
 
-# Summarize logs (without Hugging Face)
+# Summarize logs
 def summarize_logs(df):
     try:
         total_devices = df["device_id"].nunique()
@@ -41,7 +42,7 @@ def detect_anomalies(df):
         if "usage_hours" not in df.columns or "downtime" not in df.columns:
             return "Anomaly detection requires 'usage_hours' and 'downtime' columns.", pd.DataFrame()
         features = df[["usage_hours", "downtime"]].fillna(0)
-        if len(features) > 50:  # Reduced sample size
+        if len(features) > 50:
             features = features.sample(n=50, random_state=42)
         iso_forest = IsolationForest(contamination=0.1, random_state=42)
         df["anomaly"] = iso_forest.fit_predict(features)
@@ -69,7 +70,7 @@ def check_amc_reminders(df, current_date):
         logging.error(f"AMC reminder generation failed: {str(e)}")
         return f"AMC reminder generation failed: {str(e)}", pd.DataFrame()
 
-# Dashboard insights (without Hugging Face)
+# Dashboard insights
 def generate_dashboard_insights(df):
     try:
         total_devices = df["device_id"].nunique()
@@ -374,18 +375,26 @@ async def process_logs(file_obj, lab_site_filter, equipment_type_filter, date_ra
         preview_html = preview_df.to_html(index=False, classes='table table-striped', border=0)
 
         # Run critical tasks concurrently
-        with ThreadPoolExecutor(max_workers=2) as executor:  # Reduced workers
-            future_anomalies = executor.submit(detect_anomalies, filtered_df)
-            future_amc = executor.submit(check_amc_reminders, filtered_df, datetime.now())
-
-            summary = f"Step 1: Summary Report\n{summarize_logs(filtered_df)}"
-            anomalies, anomalies_df = future_anomalies.result()
-            anomalies = f"Anomaly Detection\n{anomalies}"
-            amc_reminders, reminders_df = future_amc.result()
-            amc_reminders = f"AMC Reminders\n{amc_reminders}"
-            insights = f"Dashboard Insights\n{generate_dashboard_insights(filtered_df)}"
-
-        # Generate charts sequentially to avoid contention
+        try:
+            with ThreadPoolExecutor(max_workers=2) as executor:
+                future_anomalies = executor.submit(detect_anomalies, filtered_df)
+                future_amc = executor.submit(check_amc_reminders, filtered_df, datetime.now())
+
+                summary = f"Step 1: Summary Report\n{summarize_logs(filtered_df)}"
+                anomalies, anomalies_df = future_anomalies.result()
+                anomalies = f"Anomaly Detection\n{anomalies}"
+                amc_reminders, reminders_df = future_amc.result()
+                amc_reminders = f"AMC Reminders\n{amc_reminders}"
+                insights = f"Dashboard Insights\n{generate_dashboard_insights(filtered_df)}"
+        except Exception as e:
+            logging.error(f"Concurrent task execution failed: {str(e)}")
+            summary = "Failed to generate summary due to processing error."
+            anomalies = "Anomaly detection failed due to processing error."
+            amc_reminders = "AMC reminders failed due to processing error."
+            insights = "Insights generation failed due to processing error."
+            anomalies_df = pd.DataFrame()
+
+        # Generate charts sequentially
         usage_chart = create_usage_chart(filtered_df)
         downtime_chart = create_downtime_chart(filtered_df)
         daily_log_chart = create_daily_log_trends_chart(filtered_df)
@@ -395,7 +404,7 @@ async def process_logs(file_obj, lab_site_filter, equipment_type_filter, date_ra
 
         elapsed_time = time.time() - start_time
         logging.info(f"Processing completed in {elapsed_time:.2f} seconds")
-        if elapsed_time > 3:  # Very strict threshold
+        if elapsed_time > 3:
             logging.warning(f"Processing time exceeded 3 seconds: {elapsed_time:.2f} seconds")
 
         return (summary, preview_html, usage_chart, device_cards, daily_log_chart, weekly_uptime_chart, anomaly_alerts_chart, downtime_chart, anomalies, amc_reminders, insights, None, current_modified_time, df, filtered_df)