Update app.py

app.py

@@ -45,12 +45,11 @@ except ImportError:
 logging.info("Preloading Hugging Face model...")
 try:
     device = 0 if torch.cuda.is_available() else -1
-    # Use a smaller model for faster inference
     summarizer = pipeline(
         "summarization",
         model="t5-small",
         device=device,
-        max_length=50,
+        max_length=30,  # Reduced for faster processing
         min_length=10,
         num_beams=2
     )
@@ -98,64 +97,6 @@ picklist_mapping = {
     }
 }
 
-# Cache folder ID
-def get_folder_id(folder_name):
-    if sf is None:
-        return None
-    try:
-        query = f"SELECT Id FROM Folder WHERE Name = '{folder_name}' AND Type = 'Report'"
-        result = sf.query(query)
-        if result['totalSize'] > 0:
-            folder_id = result['records'][0]['Id']
-            logging.info(f"Found folder ID for '{folder_name}': {folder_id}")
-            return folder_id
-        else:
-            logging.error(f"Folder '{folder_name}' not found in Salesforce.")
-            return None
-    except Exception as e:
-        logging.error(f"Failed to fetch folder ID for '{folder_name}': {str(e)}")
-        return None
-
-LABOPS_REPORTS_FOLDER_ID = get_folder_id('LabOps Reports')
-
-# Salesforce report creation
-def create_salesforce_reports(df):
-    if sf is None or not LABOPS_REPORTS_FOLDER_ID:
-        return
-    try:
-        timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
-        reports = [
-            {
-                "reportMetadata": {
-                    "name": f"SmartLog_Usage_Report_{timestamp}",
-                    "developerName": f"SmartLog_Usage_Report_{timestamp}",
-                    "reportType": {"type": "CustomEntity", "value": "SmartLog__c"},
-                    "reportFormat": "TABULAR",
-                    "reportBooleanFilter": None,
-                    "reportFilters": [],
-                    "detailColumns": ["SmartLog__c.Device_Id__c", "SmartLog__c.Usage_Hours__c"],
-                    "folderId": LABOPS_REPORTS_FOLDER_ID
-                }
-            },
-            {
-                "reportMetadata": {
-                    "name": f"SmartLog_AMC_Reminders_{timestamp}",
-                    "developerName": f"SmartLog_AMC_Reminders_{timestamp}",
-                    "reportType": {"type": "CustomEntity", "value": "SmartLog__c"},
-                    "reportFormat": "TABULAR",
-                    "reportBooleanFilter": None,
-                    "reportFilters": [],
-                    "detailColumns": ["SmartLog__c.Device_Id__c", "SmartLog__c.AMC_Date__c"],
-                    "folderId": LABOPS_REPORTS_FOLDER_ID
-                }
-            }
-        ]
-        for report in reports:
-            sf.restful('analytics/reports', method='POST', json=report)
-        logging.info("Salesforce reports created")
-    except Exception as e:
-        logging.error(f"Failed to create Salesforce reports: {str(e)}")
-
 # Save to Salesforce
 def save_to_salesforce(df, reminders_df):
     if sf is None:
@@ -181,6 +122,7 @@ def save_to_salesforce(df, reminders_df):
                     amc_date_dt = datetime.strptime(amc_date, '%Y-%m-%d')
                     if status == "Active" and current_date.date() <= amc_date_dt.date() <= next_30_days.date():
                         logging.info(f"AMC Reminder for Device ID {row['device_id']}")
+                    amc_date_str = amc_date
                 except:
                     amc_date_str = None
 
@@ -208,7 +150,7 @@ def summarize_logs(df):
         total_devices = df["device_id"].nunique()
         most_used = df.groupby("device_id")["usage_hours"].sum().idxmax() if not df.empty else "N/A"
         prompt = f"Maintenance logs: {total_devices} devices. Most used: {most_used}."
-        summary = summarizer(prompt, max_length=50, min_length=10, do_sample=False)[0]["summary_text"]
+        summary = summarizer(prompt, max_length=30, min_length=10, do_sample=False)[0]["summary_text"]
         return summary
     except Exception as e:
         logging.error(f"Summary generation failed: {str(e)}")
@@ -220,8 +162,8 @@ 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) > 500:
-            features = features.sample(n=500, random_state=42)
+        if len(features) > 200:  # Reduced sample size
+            features = features.sample(n=200, 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"]]
@@ -254,7 +196,7 @@ def generate_dashboard_insights(df):
         total_devices = df["device_id"].nunique()
         avg_usage = df["usage_hours"].mean() if "usage_hours" in df.columns else 0
         prompt = f"Insights: {total_devices} devices, avg usage {avg_usage:.2f} hours."
-        insights = summarizer(prompt, max_length=50, min_length=10, do_sample=False)[0]["summary_text"]
+        insights = summarizer(prompt, max_length=30, min_length=10, do_sample=False)[0]["summary_text"]
         return insights
     except Exception as e:
         logging.error(f"Dashboard insights generation failed: {str(e)}")
@@ -395,32 +337,12 @@ def generate_device_cards(df):
         logging.error(f"Failed to generate device cards: {str(e)}")
         return f'<p>Error generating device cards: {str(e)}</p>'
 
-# Generate monthly status
-def generate_monthly_status(df, selected_month):
-    try:
-        total_devices = df['device_id'].nunique()
-        total_usage_hours = df['usage_hours'].sum()
-        total_downtime = df['downtime'].sum()
-        avg_usage = total_usage_hours / total_devices if total_devices > 0 else 0
-        avg_downtime = total_downtime / total_devices if total_devices > 0 else 0
-        return f"""
-        Monthly Status for {selected_month}:
-        - Total Devices: {total_devices}
-        - Total Usage Hours: {total_usage_hours:.2f}
-        - Total Downtime Hours: {total_downtime:.2f}
-        - Average Usage per Device: {avg_usage:.2f} hours
-        - Average Downtime per Device: {avg_downtime:.2f} hours
-        """
-    except Exception as e:
-        logging.error(f"Failed to generate monthly status: {str(e)}")
-        return f"Failed to generate monthly status: {str(e)}"
-
 # Generate PDF content
-def generate_pdf_content(summary, preview_df, anomalies, amc_reminders, insights, device_cards_html, daily_log_chart, weekly_uptime_chart, anomaly_alerts_chart, downtime_chart, df, selected_month):
+def generate_pdf_content(summary, preview_df, anomalies, amc_reminders, insights, device_cards_html, daily_log_chart, weekly_uptime_chart, anomaly_alerts_chart, downtime_chart):
     if not reportlab_available:
         return None
     try:
-        pdf_path = f"monthly_status_report_{selected_month.replace(' ', '_')}_{datetime.now().strftime('%Y%m%d_%H%M%S')}.pdf"
+        pdf_path = f"status_report_{datetime.now().strftime('%Y%m%d_%H%M%S')}.pdf"
         doc = SimpleDocTemplate(pdf_path, pagesize=letter)
         styles = getSampleStyleSheet()
         story = []
@@ -428,16 +350,10 @@ def generate_pdf_content(summary, preview_df, anomalies, amc_reminders, insights
         def safe_paragraph(text, style):
             return Paragraph(str(text).replace('\n', '<br/>'), style) if text else Paragraph("", style)
 
-        story.append(Paragraph("LabOps Monthly Status Report", styles['Title']))
+        story.append(Paragraph("LabOps Status Report", styles['Title']))
         story.append(Paragraph(f"Generated on {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}", styles['Normal']))
         story.append(Spacer(1, 12))
 
-        if selected_month != "All":
-            monthly_status = generate_monthly_status(df, selected_month)
-            story.append(Paragraph("Monthly Status Summary", styles['Heading2']))
-            story.append(safe_paragraph(monthly_status, styles['Normal']))
-            story.append(Spacer(1, 12))
-
         story.append(Paragraph("Summary Report", styles['Heading2']))
         story.append(safe_paragraph(summary, styles['Normal']))
         story.append(Spacer(1, 12))
@@ -492,7 +408,7 @@ def generate_pdf_content(summary, preview_df, anomalies, amc_reminders, insights
         return None
 
 # Main processing function
-async def process_logs(file_obj, lab_site_filter, equipment_type_filter, date_range, month_filter, last_modified_state):
+async def process_logs(file_obj, lab_site_filter, equipment_type_filter, date_range, last_modified_state):
     start_time = time.time()
     try:
         if not file_obj:
@@ -540,12 +456,6 @@ async def process_logs(file_obj, lab_site_filter, equipment_type_filter, date_ra
             start_date = today + pd.Timedelta(days=days_start)
             end_date = today + pd.Timedelta(days=days_end) + pd.Timedelta(days=1) - pd.Timedelta(seconds=1)
             filtered_df = filtered_df[(filtered_df['timestamp'] >= start_date) & (filtered_df['timestamp'] <= end_date)]
-        if month_filter and month_filter != "All":
-            selected_date = pd.to_datetime(month_filter, format="%B %Y")
-            filtered_df = filtered_df[
-                (filtered_df['timestamp'].dt.year == selected_date.year) &
-                (filtered_df['timestamp'].dt.month == selected_date.month)
-            ]
 
         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
@@ -564,9 +474,8 @@ async def process_logs(file_obj, lab_site_filter, equipment_type_filter, date_ra
             future_downtime_chart = executor.submit(create_downtime_chart, filtered_df)
             future_daily_log_chart = executor.submit(create_daily_log_trends_chart, filtered_df)
             future_weekly_uptime_chart = executor.submit(create_weekly_uptime_chart, filtered_df)
-            future_anomaly_alerts_chart = executor.submit(create_anomaly_alerts_chart, pd.DataFrame())
+            future_anomaly_alerts_chart = executor.submit(create_anomaly_alerts_chart, future_anomalies.result()[1])  # Pass anomalies_df
             future_device_cards = executor.submit(generate_device_cards, filtered_df)
-            future_reports = executor.submit(create_salesforce_reports, filtered_df)
 
             summary = f"Step 1: Summary Report\n{future_summary.result()}"
             anomalies, anomalies_df = future_anomalies.result()
@@ -582,7 +491,7 @@ async def process_logs(file_obj, lab_site_filter, equipment_type_filter, date_ra
             device_cards = future_device_cards.result()
 
         save_to_salesforce(filtered_df, reminders_df)
-        pdf_file = generate_pdf_content(summary, preview_df, anomalies, amc_reminders, insights, device_cards, daily_log_chart, weekly_uptime_chart, anomaly_alerts_chart, downtime_chart, filtered_df, month_filter)
+        pdf_file = generate_pdf_content(summary, preview_df, anomalies, amc_reminders, insights, device_cards, daily_log_chart, weekly_uptime_chart, anomaly_alerts_chart, downtime_chart)
 
         elapsed_time = time.time() - start_time
         logging.info(f"Processing completed in {elapsed_time:.2f} seconds")
@@ -595,9 +504,9 @@ async def process_logs(file_obj, lab_site_filter, equipment_type_filter, date_ra
         return f"Error: {str(e)}", pd.DataFrame(), None, '<p>Error processing data.</p>', None, None, None, None, None, None, None, None, last_modified_state
 
 # Update filters
-def update_filters(file_obj):
-    if not file_obj:
-        return gr.update(choices=['All'], value='All'), gr.update(choices=['All'], value='All'), gr.update(choices=['All'], value='All')
+def update_filters(file_obj, current_file_state):
+    if not file_obj or file_obj.name == current_file_state:
+        return gr.update(), gr.update(), current_file_state
     try:
         with open(file_obj.name, 'rb') as f:
             csv_content = f.read().decode('utf-8')
@@ -606,12 +515,11 @@ def update_filters(file_obj):
 
         lab_site_options = ['All'] + [site for site in df['lab_site'].dropna().astype(str).unique().tolist() if site.strip()] if 'lab_site' in df.columns else ['All']
         equipment_type_options = ['All'] + [equip for equip in df['equipment_type'].dropna().astype(str).unique().tolist() if equip.strip()] if 'equipment_type' in df.columns else ['All']
-        month_options = ['All'] + sorted(df['timestamp'].dt.strftime('%B %Y').dropna().unique().tolist()) if 'timestamp' in df.columns else ['All']
 
-        return gr.update(choices=lab_site_options, value='All'), gr.update(choices=equipment_type_options, value='All'), gr.update(choices=month_options, value='All')
+        return gr.update(choices=lab_site_options, value='All'), gr.update(choices=equipment_type_options, value='All'), file_obj.name
     except Exception as e:
         logging.error(f"Failed to update filters: {str(e)}")
-        return gr.update(choices=['All'], value='All'), gr.update(choices=['All'], value='All'), gr.update(choices=['All'], value='All')
+        return gr.update(choices=['All'], value='All'), gr.update(choices=['All'], value='All'), current_file_state
 
 # Gradio Interface
 try:
@@ -632,6 +540,7 @@ try:
         gr.Markdown("Upload a CSV file to analyze. Click 'Analyze' to refresh the dashboard with the latest data.")
 
         last_modified_state = gr.State(value=None)
+        current_file_state = gr.State(value=None)
 
         with gr.Row():
             with gr.Column(scale=1):
@@ -641,7 +550,6 @@ try:
                     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])
-                    month_filter = gr.Dropdown(label="Select Month for Report", choices=['All'], value='All', interactive=True)
                 submit_button = gr.Button("Analyze", variant="primary")
 
             with gr.Column(scale=2):
@@ -679,18 +587,18 @@ try:
                         insights_output = gr.Markdown()
                     with gr.Group(elem_classes="dashboard-section"):
                         gr.Markdown("### Export Report")
-                        pdf_output = gr.File(label="Download Monthly Status Report as PDF")
+                        pdf_output = gr.File(label="Download Status Report as PDF")
 
         file_input.change(
             fn=update_filters,
-            inputs=[file_input],
-            outputs=[lab_site_filter, equipment_type_filter, month_filter],
+            inputs=[file_input, current_file_state],
+            outputs=[lab_site_filter, equipment_type_filter, current_file_state],
             queue=False
         )
 
         submit_button.click(
             fn=process_logs,
-            inputs=[file_input, lab_site_filter, equipment_type_filter, date_range_filter, month_filter, last_modified_state],
+            inputs=[file_input, lab_site_filter, equipment_type_filter, date_range_filter, 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, last_modified_state]
         )