Update app.py

app.py

@@ -231,12 +231,12 @@ def generate_device_cards(df):
             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'
             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>Usage Count:</b> {row['count']}</p>
-                <p><b>Last Log:</b> {timestamp_str}</p>
-            </div>
+                <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>Usage Count:</b> {row['count']}</p>
+                    <p><b>Last Log:</b> {timestamp_str}</p>
+                </div>
             """
         cards_html += '</div>'
         return cards_html
@@ -314,21 +314,21 @@ def generate_pdf_content(summary, preview_df, anomalies, amc_reminders, insights
         logging.error(f"Failed to generate PDF: {str(e)}")
         return None
 
-# Main processing function (Updated)
-async def process_logs(file_obj, lab_site_filter, equipment_type_filter, date_range, last_modified_state, cached_df_state, cached_filtered_df_state):
+# Main processing function
+async def process_logs(file_obj, lab_site_filter, equipment_type_filter, date_range, cached_df_state, last_modified_state):
     start_time = time.time()
     try:
         if not file_obj:
-            return "No file uploaded.", pd.DataFrame(), None, '<p>No device cards available.</p>', None, None, None, None, "No anomalies detected.", "No AMC reminders.", "No insights generated.", None, last_modified_state, cached_df_state, None
+            return "No file uploaded.", "<p>No data available.</p>", None, '<p>No device cards available.</p>', None, None, None, None, "No anomalies detected.", "No AMC reminders.", "No insights generated.", None, cached_df_state, last_modified_state
 
         file_path = file_obj.name
         current_modified_time = os.path.getmtime(file_path)
 
-        # Load or use cached original dataframe
+        # Read file only if it's new or modified
         if cached_df_state is None or current_modified_time != last_modified_state:
-            logging.info(f"Processing file: {file_path}")
+            logging.info(f"Processing new or modified file: {file_path}")
             if not file_path.endswith(".csv"):
-                return "Please upload a CSV file.", pd.DataFrame(), None, '<p>No device cards available.</p>', None, None, None, None, "", "", "", None, last_modified_state, cached_df_state, None
+                return "Please upload a CSV file.", "<p>Invalid file format.</p>", None, '<p>No device cards available.</p>', None, None, None, None, "", "", "", None, cached_df_state, last_modified_state
 
             required_columns = ["device_id", "log_type", "status", "timestamp", "usage_hours", "downtime", "amc_date"]
             dtypes = {
@@ -342,19 +342,18 @@ async def process_logs(file_obj, lab_site_filter, equipment_type_filter, date_ra
             df = pd.read_csv(file_path, dtype=dtypes)
             missing_columns = [col for col in required_columns if col not in df.columns]
             if missing_columns:
-                return f"Missing columns: {missing_columns}", pd.DataFrame(), None, '<p>No device cards available.</p>', None, None, None, None, None, None, None, None, last_modified_state, cached_df_state, None
+                return f"Missing columns: {missing_columns}", "<p>Missing required columns.</p>", None, '<p>No device cards available.</p>', None, None, None, None, "", "", "", None, cached_df_state, last_modified_state
 
             df["timestamp"] = pd.to_datetime(df["timestamp"], errors='coerce')
             df["amc_date"] = pd.to_datetime(df["amc_date"], errors='coerce')
             if df["timestamp"].dt.tz is None:
                 df["timestamp"] = df["timestamp"].dt.tz_localize('UTC').dt.tz_convert('Asia/Kolkata')
             if df.empty:
-                return "No data available.", pd.DataFrame(), None, '<p>No device cards available.</p>', None, None, None, None, None, None, None, None, last_modified_state, df, None
-            cached_df_state = df
+                return "No data available.", "<p>No data available.</p>", None, '<p>No device cards available.</p>', None, None, None, None, "", "", "", None, df, current_modified_time
         else:
             df = cached_df_state
 
-        # Always apply current filters to the original dataframe
+        # Apply filters
         filtered_df = df.copy()
         if lab_site_filter and lab_site_filter != 'All' and 'lab_site' in filtered_df.columns:
             filtered_df = filtered_df[filtered_df['lab_site'] == lab_site_filter]
@@ -362,37 +361,34 @@ async def process_logs(file_obj, lab_site_filter, equipment_type_filter, date_ra
             filtered_df = filtered_df[filtered_df['equipment_type'] == equipment_type_filter]
         if date_range and len(date_range) == 2:
             days_start, days_end = date_range
-            today = pd.to_datetime(datetime.now().date()).tz_localize('Asia/Kolkata')
+            today = pd.to_datetime(datetime.now()).tz_localize('Asia/Kolkata')
             start_date = today + pd.Timedelta(days=days_start)
             end_date = today + pd.Timedelta(days=days_end) + pd.Timedelta(days=1) - pd.Timedelta(seconds=1)
+            start_date = start_date.tz_convert('Asia/Kolkata') if start_date.tzinfo else start_date.tz_localize('Asia/Kolkata')
+            end_date = end_date.tz_convert('Asia/Kolkata') if end_date.tzinfo else end_date.tz_localize('Asia/Kolkata')
+            logging.info(f"Date range filter: start_date={start_date}, end_date={end_date}")
+            logging.info(f"Before date filter: {len(filtered_df)} rows")
             filtered_df = filtered_df[(filtered_df['timestamp'] >= start_date) & (filtered_df['timestamp'] <= end_date)]
+            logging.info(f"After date filter: {len(filtered_df)} rows")
 
         if filtered_df.empty:
-            return "No data after applying filters.", pd.DataFrame(), None, '<p>No device cards available.</p>', None, None, None, None, None, None, None, None, last_modified_state, cached_df_state, None
+            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_html = preview_df.to_html(index=False, classes='table table-striped', border=0)
 
         # Run critical tasks concurrently
-        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()
+        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)}"
 
         # Generate charts sequentially
         usage_chart = create_usage_chart(filtered_df)
@@ -407,10 +403,10 @@ async def process_logs(file_obj, lab_site_filter, equipment_type_filter, date_ra
         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, cached_df_state, filtered_df)
+        return (summary, preview_html, usage_chart, device_cards, daily_log_chart, weekly_uptime_chart, anomaly_alerts_chart, downtime_chart, anomalies, amc_reminders, insights, None, df, current_modified_time)
     except Exception as e:
         logging.error(f"Failed to process file: {str(e)}")
-        return f"Error: {str(e)}", pd.DataFrame(), None, '<p>Error processing data.</p>', None, None, None, None, None, None, None, None, last_modified_state, cached_df_state, None
+        return f"Error: {str(e)}", "<p>Error processing data.</p>", None, '<p>Error processing data.</p>', None, None, None, None, "", "", "", None, cached_df_state, last_modified_state
 
 # Generate PDF separately
 async def generate_pdf(summary, preview_html, usage_chart, device_cards, daily_log_chart, weekly_uptime_chart, anomaly_alerts_chart, downtime_chart, anomalies, amc_reminders, insights):
@@ -461,7 +457,6 @@ try:
         last_modified_state = gr.State(value=None)
         current_file_state = gr.State(value=None)
         cached_df_state = gr.State(value=None)
-        cached_filtered_df_state = gr.State(value=None)
 
         with gr.Row():
             with gr.Column(scale=1):
@@ -470,9 +465,9 @@ try:
                     gr.Markdown("### Filters")
                     lab_site_filter = gr.Dropdown(label="Lab Site", choices=['All'], value='All', interactive=True)
                     equipment_type_filter = gr.Dropdown(label="Equipment Type", choices=['All'], value='All', interactive=True)
-                    date_range_filter = gr.Slider(label="Date Range (Days from Today)", minimum=-365, maximum=0, step=1, value=[-30, 0])
-                submit_button = gr.Button("Analyze", variant="primary")
-                pdf_button = gr.Button("Export PDF", variant="secondary")
+                    date_range_filter = gr.Slider(label="Date Range (Days from Today, e.g., -7 to 0 means last 7 days)", minimum=-365, maximum=0, step=1, value=[-7, 0])
+                    submit_button = gr.Button("Analyze", variant="primary")
+                    pdf_button = gr.Button("Export PDF", variant="secondary")
 
             with gr.Column(scale=2):
                 with gr.Group(elem_classes="dashboard-container"):
@@ -520,8 +515,8 @@ try:
 
         submit_button.click(
             fn=process_logs,
-            inputs=[file_input, lab_site_filter, equipment_type_filter, date_range_filter, last_modified_state, cached_df_state, cached_filtered_df_state],
-            outputs=[summary_output, preview_output, usage_chart_output, device_cards_output, daily_log_trends_output, weekly_uptime_output, anomaly_alerts_output, downtime_chart_output, anomaly_output, amc_output, insights_output, pdf_output, last_modified_state, cached_df_state, cached_filtered_df_state]
+            inputs=[file_input, lab_site_filter, equipment_type_filter, date_range_filter, cached_df_state, last_modified_state],
+            outputs=[summary_output, preview_output, usage_chart_output, device_cards_output, daily_log_trends_output, weekly_uptime_output, anomaly_alerts_output, downtime_chart_output, anomaly_output, amc_output, insights_output, pdf_output, cached_df_state, last_modified_state]
         )
 
         pdf_button.click(
@@ -530,7 +525,7 @@ try:
             outputs=[pdf_output]
         )
 
-    logging.info("Gradio interface initialized successfully")
+        logging.info("Gradio interface initialized successfully")
 except Exception as e:
     logging.error(f"Failed to initialize Gradio interface: {str(e)}")
     raise e