Update app.py

app.py

@@ -6,6 +6,11 @@ import plotly.express as px
 from sklearn.ensemble import IsolationForest
 from transformers import pipeline
 import torch
+from reportlab.lib.pagesizes import letter
+from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer
+from reportlab.lib.styles import getSampleStyleSheet
+import os
+import io
 
 # Configure logging for debugging
 logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
@@ -32,7 +37,7 @@ def summarize_logs(df, progress=gr.Progress()):
         return summary
     except Exception as e:
         logging.error(f"Summary generation failed: {str(e)}")
-        return "Failed to generate summary."
+        return f"Failed to generate summary: {str(e)}"
 
 # Anomaly Detection using Isolation Forest
 def detect_anomalies(df, progress=gr.Progress()):
@@ -50,7 +55,7 @@ def detect_anomalies(df, progress=gr.Progress()):
         anomalies = df[df["anomaly"] == -1][["device_id", "usage_hours", "downtime", "timestamp"]]
         if anomalies.empty:
             return "No anomalies detected."
-        anomaly_lines = ["**Detected Anomalies:**"]
+        anomaly_lines = ["Detected Anomalies:"]
         for idx, row in anomalies.head(5).iterrows():
             anomaly_lines.append(f"- Device ID: {row['device_id']}, Usage Hours: {row['usage_hours']}, Downtime: {row['downtime']}, Timestamp: {row['timestamp']}")
         anomaly_list = "\n".join(anomaly_lines)
@@ -73,7 +78,7 @@ def check_amc_reminders(df, current_date, progress=gr.Progress()):
         reminders = df[(df["days_to_amc"] >= 0) & (df["days_to_amc"] <= 30)][["device_id", "amc_date"]]
         if reminders.empty:
             return "No AMC reminders due within the next 30 days."
-        reminder_lines = ["**Upcoming AMC Reminders:**"]
+        reminder_lines = ["Upcoming AMC Reminders:"]
         for idx, row in reminders.head(5).iterrows():
             reminder_lines.append(f"- Device ID: {row['device_id']}, AMC Date: {row['amc_date']}")
         reminder_list = "\n".join(reminder_lines)
@@ -127,51 +132,55 @@ def create_usage_chart(df, progress=gr.Progress()):
         logging.error(f"Failed to create usage chart: {str(e)}")
         return None
 
-# Generate LaTeX PDF content
+# Generate PDF content using reportlab
 def generate_pdf_content(summary, preview, anomalies, amc_reminders, insights):
-    latex_content = r"""
-\documentclass[a4paper,11pt]{article}
-\usepackage[utf8]{inputenc}
-\usepackage[T1]{fontenc}
-\usepackage{lmodern}
-\usepackage{geometry}
-\geometry{margin=1in}
-\usepackage{enumitem}
-\usepackage{parskip}
-\setlength{\parskip}{0.5em}
-\setlength{\parindent}{0em}
-\usepackage{titling}
-\usepackage{xcolor彼此
-
-System: color}
-\usepackage{noto}
-
-\title{LabOps Log Analysis Report}
-\author{AI-Powered Analysis}
-\date{\today}
-
-\begin{document}
-
-\maketitle
-
-\section*{Summary Report}
-""" + summary.replace("**", r"\textbf{").replace(":", r":}").replace("\n", r"\\") + r"""
-
-\section*{Log Preview}
-""" + preview.replace("**", r"\textbf{").replace(":", r":}").replace("\n", r"\\") + r"""
-
-\section*{Anomaly Detection}
-""" + anomalies.replace("**", r"\textbf{").replace(":", r":}").replace("\n", r"\\") + r"""
-
-\section*{AMC Reminders}
-""" + amc_reminders.replace("**", r"\textbf{").replace(":", r":}").replace("\n", r"\\") + r"""
-
-\section*{Dashboard Insights}
-""" + insights.replace("**", r"\textbf{").replace(":", r":}").replace("\n", r"\\") + r"""
-
-\end{document}
-"""
-    return latex_content
+    try:
+        pdf_path = "analysis_report.pdf"
+        doc = SimpleDocTemplate(pdf_path, pagesize=letter)
+        styles = getSampleStyleSheet()
+        story = []
+
+        # Title
+        story.append(Paragraph("LabOps Log Analysis Report", styles['Title']))
+        story.append(Paragraph(f"Generated on {datetime.now().strftime('%Y-%m-%d')}", styles['Normal']))
+        story.append(Spacer(1, 12))
+
+        # Summary Report
+        story.append(Paragraph("Summary Report", styles['Heading2']))
+        for line in summary.split('\n'):
+            story.append(Paragraph(line.replace('**', ''), styles['Normal']))
+        story.append(Spacer(1, 12))
+
+        # Log Preview
+        story.append(Paragraph("Log Preview", styles['Heading2']))
+        for line in preview.split('\n'):
+            story.append(Paragraph(line.replace('**', ''), styles['Normal']))
+        story.append(Spacer(1, 12))
+
+        # Anomaly Detection
+        story.append(Paragraph("Anomaly Detection", styles['Heading2']))
+        for line in anomalies.split('\n'):
+            story.append(Paragraph(line.replace('**', ''), styles['Normal']))
+        story.append(Spacer(1, 12))
+
+        # AMC Reminders
+        story.append(Paragraph("AMC Reminders", styles['Heading2']))
+        for line in amc_reminders.split('\n'):
+            story.append(Paragraph(line.replace('**', ''), styles['Normal']))
+        story.append(Spacer(1, 12))
+
+        # Dashboard Insights
+        story.append(Paragraph("Dashboard Insights", styles['Heading2']))
+        for line in insights.split('\n'):
+            story.append(Paragraph(line.replace('**', ''), styles['Normal']))
+
+        # Build PDF
+        doc.build(story)
+        logging.info(f"PDF generated successfully at {pdf_path}")
+        return pdf_path
+    except Exception as e:
+        logging.error(f"Failed to generate PDF: {str(e)}")
+        return None
 
 # Main Gradio function
 async def process_logs(file_obj, progress=gr.Progress()):
@@ -190,7 +199,7 @@ async def process_logs(file_obj, progress=gr.Progress()):
 
         progress(0.05, "Loading CSV file...")
         try:
-            usecols = ["device_id", "log_type", "status", "timestamp", "usage_hours", "downtime", "amc_date"]
+            required_columns = ["device_id", "log_type", "status", "timestamp", "usage_hours", "downtime", "amc_date"]
             dtypes = {
                 "device_id": "string",
                 "log_type": "string",
@@ -199,7 +208,12 @@ async def process_logs(file_obj, progress=gr.Progress()):
                 "downtime": "float32",
                 "amc_date": "string"
             }
-            df = pd.read_csv(file_name, usecols=usecols, dtype=dtypes)
+            df = pd.read_csv(file_name, dtype=dtypes)
+            # Validate required columns
+            missing_columns = [col for col in required_columns if col not in df.columns]
+            if missing_columns:
+                logging.error(f"Missing required columns: {missing_columns}")
+                return f"Missing required columns: {missing_columns}", None, None, None, None, None, None
             logging.info(f"File loaded successfully with {len(df)} rows")
         except Exception as e:
             logging.error(f"Failed to load CSV: {str(e)}")
@@ -218,39 +232,33 @@ async def process_logs(file_obj, progress=gr.Progress()):
 
         # Step 1: Summary Report
         progress(0.2, "Generating summary...")
-        summary = f"**Step 1: Summary Report**  \n{summarize_logs(df, progress)}"
+        summary = f"Step 1: Summary Report\n{summarize_logs(df, progress)}"
 
         # Step 2: Log Preview
         progress(0.3, "Previewing logs...")
         if not df.empty:
-            preview_lines = ["**Step 2: Log Preview (First 5 Rows)**"]
+            preview_lines = ["Step 2: Log Preview (First 5 Rows)"]
             for idx, row in df.head().iterrows():
-                preview_lines.append(f"**Row {idx + 1}:** Device ID: {row['device_id']}, Log Type: {row['log_type']}, Status: {row['status']}, Timestamp: {row['timestamp']}, Usage Hours: {row['usage_hours']}, Downtime: {row['downtime']}, AMC Date: {row['amc_date']}")
+                preview_lines.append(f"Row {idx + 1}: Device ID: {row['device_id']}, Log Type: {row['log_type']}, Status: {row['status']}, Timestamp: {row['timestamp']}, Usage Hours: {row['usage_hours']}, Downtime: {row['downtime']}, AMC Date: {row['amc_date']}")
             preview = "\n".join(preview_lines)
         else:
-            preview = "**Step 2: Log Preview**  \nNo data available."
+            preview = "Step 2: Log Preview\nNo data available."
 
         # Step 3: Usage Chart
         chart = create_usage_chart(df, progress)
 
         # Step 4: Anomaly Detection
-        anomalies = f"**Step 3: Anomaly Detection**  \n{detect_anomalies(df, progress)}"
+        anomalies = f"Step 3: Anomaly Detection\n{detect_anomalies(df, progress)}"
 
         # Step 5: AMC Reminders
-        amc_reminders = f"**Step 4: AMC Reminders**  \n{check_amc_reminders(df, datetime.now(), progress)}"
+        amc_reminders = f"Step 4: AMC Reminders\n{check_amc_reminders(df, datetime.now(), progress)}"
 
         # Step 6: Dashboard Insights
-        insights = f"**Step 5: Dashboard Insights (AI)**  \n{generate_dashboard_insights(df, progress)}"
+        insights = f"Step 5: Dashboard Insights (AI)\n{generate_dashboard_insights(df, progress)}"
 
         # Generate PDF
         progress(0.95, "Generating PDF report...")
-        try:
-            latex_content = generate_pdf_content(summary, preview, anomalies, amc_reminders, insights)
-            pdf_file = gr.File(value=latex_content, file_types=[".pdf"], label="Download Analysis Report")
-            logging.info("PDF content generated successfully")
-        except Exception as e:
-            logging.error(f"Failed to generate PDF: {str(e)}")
-            pdf_file = None
+        pdf_file = generate_pdf_content(summary, preview, anomalies, amc_reminders, insights)
 
         progress(1.0, "Processing complete!")
         return summary, preview, chart, anomalies, amc_reminders, insights, pdf_file
@@ -267,7 +275,6 @@ try:
         .dashboard-section {margin-bottom: 5px;}
         .dashboard-section h3 {font-size: 18px; margin-bottom: 2px;}
         .dashboard-section p {margin: 1px 0; line-height: 1.2;}
-        .dashboard-section li {margin: 1px 0; line-height: 1.2;}
         .dashboard-section ul {margin: 2px 0; padding-left: 20px;}
     """) as iface:
         gr.Markdown("<h1>LabOps Log Analyzer Dashboard (Hugging Face AI)</h1>")
@@ -308,8 +315,7 @@ try:
                         amc_output = gr.Markdown()
                     
                     # Step 6: Dashboard Insights
-                    with gr.Group(elem_classes="dashboard-section"):
-                        gr.Markdown("### Step 6: Dashboard Insights (AI)")
+                   MD("### Step 6: Dashboard Insights (AI)")
                         insights_output = gr.Markdown()
                     
                     # PDF Download