Update app.py

app.py

@@ -469,6 +469,10 @@ def generate_device_cards(df):
         counts = df_clean.groupby('device_id').size().reset_index(name='count')
         device_stats = device_stats.merge(counts, on='device_id')
 
+        # Limit to top 10 devices by count
+        device_stats = device_stats.nlargest(10, 'count')
+        logging.info(f"Limited device cards to top {len(device_stats)} devices by usage count.")
+
         device_stats['health'] = device_stats['status'].map({
             'Active': 'Healthy',
             'Inactive': 'Unhealthy',
@@ -595,34 +599,24 @@ def generate_pdf_content(summary, preview, anomalies, amc_reminders, insights, d
         logging.error(f"Failed to generate PDF: {str(e)}", exc_info=True)
         return None
 
-# Validate inputs before generating PDF
-def validate_and_generate_pdf(summary, preview, anomalies, amc_reminders, insights, device_cards, daily_log_chart, weekly_uptime_chart, anomaly_alerts_chart, downtime_chart, df, month_filter):
-    if not all([summary, preview, anomalies, amc_reminders, insights, device_cards, df is not None]):
-        logging.error("One or more required inputs for PDF generation are missing.")
-        return None, "Please click 'Analyze' to process the data before generating a PDF."
-    pdf_path = generate_pdf_content(summary, preview, anomalies, amc_reminders, insights, device_cards, daily_log_chart, weekly_uptime_chart, anomaly_alerts_chart, downtime_chart, df, month_filter)
-    if pdf_path is None:
-        return None, "Failed to generate PDF. Check logs for details."
-    return pdf_path, "PDF generated successfully."
-
 # Main Gradio function
 async def process_logs(file_obj, lab_site_filter, equipment_type_filter, date_range, month_filter, last_modified_state):
     try:
         start_time = datetime.now()
 
         if not file_obj:
-            return "No file uploaded.", "No data to preview.", None, '<p>No device cards available.</p>', None, None, None, None, "No anomalies detected.", "No AMC reminders.", "No insights generated.", None, last_modified_state, None, None, None, None, None, None, False, "Please upload a CSV file to analyze."
+            return "No file uploaded.", "No data to preview.", None, '<p>No device cards available.</p>', None, None, None, None, "No anomalies detected.", "No AMC reminders.", "No insights generated.", None, last_modified_state, None, None, None, None, None, None, "Please upload a CSV file to analyze."
         
         file_path = file_obj.name
         current_modified_time = os.path.getmtime(file_path)
         
         if last_modified_state and current_modified_time == last_modified_state:
-            return None, None, None, None, None, None, None, None, None, None, None, None, last_modified_state, None, None, None, None, None, None, False, "No changes detected in the file."
+            return None, None, None, None, None, None, None, None, None, None, None, None, last_modified_state, None, None, None, None, None, None, "No changes detected in the file."
 
         logging.info(f"Processing file: {file_path}, last modified: {current_modified_time}")
         
         if not file_path.endswith(".csv"):
-            return "Please upload a CSV file.", "", None, '<p>No device cards available.</p>', None, None, None, None, "", "", "", None, last_modified_state, None, None, None, None, None, None, False, "Invalid file format. Please upload a CSV file."
+            return "Please upload a CSV file.", "", None, '<p>No device cards available.</p>', None, None, None, None, "", "", "", None, last_modified_state, None, None, None, None, None, None, "Invalid file format. Please upload a CSV file."
 
         required_columns = ["device_id", "log_type", "status", "timestamp", "usage_hours", "downtime", "amc_date"]
         dtypes = {
@@ -634,9 +628,13 @@ async def process_logs(file_obj, lab_site_filter, equipment_type_filter, date_ra
             "amc_date": "string"
         }
         df = pd.read_csv(file_path, dtype=dtypes)
+        # Downsample early if dataset is too large
+        if len(df) > 10000:
+            df = df.sample(n=10000, random_state=42)
+            logging.info(f"Downsampled DataFrame to 10,000 rows immediately after loading.")
         missing_columns = [col for col in required_columns if col not in df.columns]
         if missing_columns:
-            return f"Missing columns: {missing_columns}", None, None, '<p>No device cards available.</p>', None, None, None, None, None, None, None, None, last_modified_state, None, None, None, None, None, None, False, f"Missing required columns: {missing_columns}"
+            return f"Missing columns: {missing_columns}", None, None, '<p>No device cards available.</p>', None, None, None, None, None, None, None, None, last_modified_state, None, None, None, None, None, None, f"Missing required columns: {missing_columns}"
         
         df["timestamp"] = pd.to_datetime(df["timestamp"], errors='coerce')
         df["amc_date"] = pd.to_datetime(df["amc_date"], errors='coerce')
@@ -644,7 +642,7 @@ async def process_logs(file_obj, lab_site_filter, equipment_type_filter, date_ra
             logging.info("Localizing naive timestamps to IST")
             df["timestamp"] = df["timestamp"].dt.tz_localize('UTC').dt.tz_convert('Asia/Kolkata')
         if df.empty:
-            return "No data available.", None, None, '<p>No device cards available.</p>', None, None, None, None, None, None, None, None, last_modified_state, None, None, None, None, None, None, False, "No data available in the uploaded file."
+            return "No data available.", None, None, '<p>No device cards available.</p>', None, None, None, None, None, None, None, None, last_modified_state, None, None, None, None, None, None, "No data available in the uploaded file."
 
         logging.info(f"DataFrame before filtering:\n{df.head().to_string()}")
 
@@ -679,7 +677,7 @@ async def process_logs(file_obj, lab_site_filter, equipment_type_filter, date_ra
 
         if filtered_df.empty:
             logging.warning("Filtered DataFrame is empty after applying filters.")
-            return "No data after applying filters.", None, None, '<p>No device cards available.</p>', None, None, None, None, None, None, None, None, last_modified_state, None, None, None, None, None, None, False, "No data available after applying filters."
+            return "No data after applying filters.", None, None, '<p>No device cards available.</p>', None, None, None, None, None, None, None, None, last_modified_state, None, None, None, None, None, None, "No data available after applying filters."
 
         logging.info(f"Filtered DataFrame:\n{filtered_df.head().to_string()}")
 
@@ -788,24 +786,31 @@ async def process_logs(file_obj, lab_site_filter, equipment_type_filter, date_ra
             )
         preview_text = "\n".join(preview_lines)
 
-        with ThreadPoolExecutor() as executor:
-            executor.submit(save_to_salesforce, filtered_df, reminders_df, summary, anomalies, amc_reminders, insights)
-            executor.submit(create_salesforce_reports, filtered_df)
-
+        # Auto-generate PDF after analysis
         pdf_file = None
+        status_msg = "Analysis completed successfully."
+        if all([summary, preview_text, anomalies, amc_reminders, insights, device_cards, filtered_df is not None]):
+            pdf_file = generate_pdf_content(
+                summary, preview_text, anomalies, amc_reminders, insights, device_cards,
+                daily_log_chart, weekly_uptime_chart, anomaly_alerts_chart, downtime_chart,
+                filtered_df, month_filter
+            )
+            if pdf_file:
+                status_msg = "Analysis completed successfully. PDF report generated and available for download."
+            else:
+                status_msg = "Analysis completed successfully, but failed to generate PDF. Check logs for details."
+        else:
+            status_msg = "Analysis completed, but some data is missing for PDF generation."
 
         elapsed_time = (datetime.now() - start_time).total_seconds()
         logging.info(f"Processing completed in {elapsed_time:.2f} seconds")
         if elapsed_time > 10:
             logging.warning(f"Processing time exceeded 10 seconds: {elapsed_time:.2f} seconds")
 
-        # Log state variable assignments for debugging
-        logging.info(f"Setting state variables: summary={summary}, preview={preview_text}, anomalies={anomalies}, amc_reminders={amc_reminders}, insights={insights}, device_cards={device_cards[:50]}..., df={'set' if df is not None else 'None'}")
-
-        return (summary, preview_html, usage_chart, device_cards, daily_log_chart, weekly_uptime_chart, anomaly_alerts_chart, downtime_chart, anomalies, amc_reminders, insights, pdf_file, current_modified_time, summary, preview_text, anomalies, amc_reminders, insights, device_cards, filtered_df, True, "Analysis completed successfully. You can now generate the PDF report.")
+        return (summary, preview_html, usage_chart, device_cards, daily_log_chart, weekly_uptime_chart, anomaly_alerts_chart, downtime_chart, anomalies, amc_reminders, insights, pdf_file, current_modified_time, summary, preview_text, anomalies, amc_reminders, insights, device_cards, filtered_df, status_msg)
     except Exception as e:
         logging.error(f"Failed to process file: {str(e)}")
-        return f"Error: {str(e)}", None, None, '<p>Error processing data.</p>', None, None, None, None, None, None, None, None, last_modified_state, None, None, None, None, None, None, False, f"Failed to process file: {str(e)}"
+        return f"Error: {str(e)}", None, None, '<p>Error processing data.</p>', None, None, None, None, None, None, None, None, last_modified_state, None, None, None, None, None, None, f"Failed to process file: {str(e)}"
 
 # Update filter options
 def update_filters(file_obj):
@@ -863,7 +868,7 @@ try:
         .dashboard-section ul {margin: 2px 0; padding-left: 20px;}
     """) as iface:
         gr.Markdown("<h1>LabOps Log Analyzer Dashboard</h1>")
-        gr.Markdown("Upload a CSV file to analyze. Click 'Analyze' to refresh the dashboard with the latest data.")
+        gr.Markdown("Upload a CSV file to analyze. Click 'Analyze' to refresh the dashboard with the latest data. A PDF report will be generated automatically.")
 
         last_modified_state = gr.State(value=None)
         summary_state = gr.State()
@@ -873,7 +878,6 @@ try:
         insights_state = gr.State()
         device_cards_state = gr.State()
         df_state = gr.State()
-        is_analyzed_state = gr.State(value=False)
 
         with gr.Row():
             with gr.Column(scale=1):
@@ -957,7 +961,6 @@ try:
                         
                     with gr.Group(elem_classes="dashboard-section"):
                         gr.Markdown("### Export Report")
-                        pdf_button = gr.Button("Generate PDF Report", interactive=False)  # Disabled by default
                         pdf_output = gr.File(label="Download Monthly Status Report as PDF")
 
         file_input.change(
@@ -998,40 +1001,10 @@ try:
                 insights_state,
                 device_cards_state,
                 df_state,
-                is_analyzed_state,
                 status_message
             ]
         )
 
-        def update_pdf_button_interactivity(is_analyzed):
-            return gr.update(interactive=is_analyzed)
-
-        is_analyzed_state.change(
-            fn=update_pdf_button_interactivity,
-            inputs=[is_analyzed_state],
-            outputs=[pdf_button],
-            queue=False
-        )
-
-        pdf_button.click(
-            fn=validate_and_generate_pdf,
-            inputs=[
-                summary_state,
-                preview_state,
-                anomalies_state,
-                amc_reminders_state,
-                insights_state,
-                device_cards_state,
-                daily_log_trends_output,
-                weekly_uptime_output,
-                anomaly_alerts_output,
-                downtime_chart_output,
-                df_state,
-                month_filter
-            ],
-            outputs=[pdf_output, status_message]
-        )
-
     logging.info("Gradio interface initialized successfully")
 except Exception as e:
     logging.error(f"Failed to initialize Gradio interface: {str(e)}")