Update app.py

app.py

@@ -3,115 +3,68 @@ import pandas as pd
 from datetime import datetime
 import logging
 import plotly.express as px
-from sklearn.ensemble import IsolationForest  # For anomaly detection
+from sklearn.ensemble import IsolationForest
 from transformers import pipeline
-import torch  # For GPU availability check
-from simple_salesforce import Salesforce  # For Salesforce connection
+import torch
+from simple_salesforce import Salesforce
+import io
+import base64
+from contextlib import redirect_stdout
 
 # Configure logging for debugging
 logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
 
-# Salesforce credentials (replace with your actual credentials or use environment variables)
-SALESFORCE_USERNAME = "your_username"
-SALESFORCE_PASSWORD = "your_password"
-SALESFORCE_SECURITY_TOKEN = "your_security_token"
-SALESFORCE_DOMAIN = "login"  # Use "test" for sandbox, "login" for production
-
-# Preload Hugging Face summarization model at startup
-logging.info("Preloading Hugging Face model...")
-try:
-    device = 0 if torch.cuda.is_available() else -1
-    summarizer = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6", device=device)  # Lighter model
-    logging.info(f"Hugging Face model preloaded successfully on device: {'GPU' if device == 0 else 'CPU'}")
-except Exception as e:
-    logging.error(f"Failed to preload model: {str(e)}")
-    raise e
-
-# Connect to Salesforce
+# Salesforce connection configuration
 def connect_to_salesforce():
     try:
         sf = Salesforce(
-            username=SALESFORCE_USERNAME,
-            password=SALESFORCE_PASSWORD,
-            security_token=SALESFORCE_SECURITY_TOKEN,
-            domain=SALESFORCE_DOMAIN
+            username='your_salesforce_username',
+            password='your_salesforce_password',
+            security_token='your_security_token',
+            instance_url='your_instance_url'
         )
-        logging.info("Successfully connected to Salesforce")
+        logging.info("Connected to Salesforce successfully")
         return sf
     except Exception as e:
         logging.error(f"Failed to connect to Salesforce: {str(e)}")
         raise e
 
-# Fetch data from Salesforce
-def fetch_salesforce_data(sf, row_limit=10000, progress=gr.Progress()):
-    progress(0.05, "Fetching data from Salesforce...")
+# Fetch data from Salesforce Smart_Log__c object
+def fetch_salesforce_data(sf, row_limit=10000):
     try:
-        # Query Salesforce for LabEquipmentLog__c object
-        query = """
-            SELECT Device_ID__c, Log_Type__c, Status__c, Timestamp__c, 
-                   Usage_Hours__c, Downtime__c, AMC_Date__c 
-            FROM LabEquipmentLog__c
-            LIMIT {}
-        """.format(row_limit)
+        query = f"""
+            SELECT Device_ID__c, Log_Type__c, Status__c, Timestamp__c, Usage_Hours__c, Downtime__c, AMC_Date__c
+            FROM Smart_Log__c
+            LIMIT {row_limit}
+        """
         result = sf.query_all(query)
-        records = result["records"]
-        
-        # Convert to DataFrame
+        records = result['records']
         df = pd.DataFrame(records)
+        # Rename columns to match existing code
         df = df.rename(columns={
-            "Device_ID__c": "device_id",
-            "Log_Type__c": "log_type",
-            "Status__c": "status",
-            "Timestamp__c": "timestamp",
-            "Usage_Hours__c": "usage_hours",
-            "Downtime__c": "downtime",
-            "AMC_Date__c": "amc_date"
+            'Device_ID__c': 'device_id',
+            'Log_Type__c': 'log_type',
+            'Status__c': 'status',
+            'Timestamp__c': 'timestamp',
+            'Usage_Hours__c': 'usage_hours',
+            'Downtime__c': 'downtime',
+            'AMC_Date__c': 'amc_date'
         })
-        
-        # Ensure proper data types
-        df["timestamp"] = pd.to_datetime(df["timestamp"], errors='coerce')
-        df["amc_date"] = pd.to_datetime(df["amc_date"], errors='coerce')
-        df["usage_hours"] = df["usage_hours"].astype("float32", errors='ignore')
-        df["downtime"] = df["downtime"].astype("float32", errors='ignore')
-        df["device_id"] = df["device_id"].astype("string")
-        
         logging.info(f"Fetched {len(df)} records from Salesforce")
         return df
     except Exception as e:
         logging.error(f"Failed to fetch Salesforce data: {str(e)}")
         raise e
 
-# Load data from CSV file
-def load_csv_data(file_obj, row_limit=10000, progress=gr.Progress()):
-    progress(0.05, "Loading CSV file...")
-    try:
-        file_name = file_obj.name if hasattr(file_obj, 'name') else file_obj
-        logging.info(f"Processing CSV file: {file_name}")
-        
-        if not file_name.endswith(".csv"):
-            logging.error("Unsupported file format")
-            raise ValueError("Unsupported file format. Please upload a CSV file.")
-
-        usecols = ["device_id", "log_type", "status", "timestamp", "usage_hours", "downtime", "amc_date"]
-        dtypes = {
-            "device_id": "string",
-            "log_type": "string",
-            "status": "string",
-            "usage_hours": "float32",
-            "downtime": "float32",
-            "amc_date": "string"
-        }
-        df = pd.read_csv(file_name, usecols=usecols, dtype=dtypes, nrows=row_limit)
-        
-        # Convert timestamps
-        df["timestamp"] = pd.to_datetime(df["timestamp"], errors='coerce')
-        df["amc_date"] = pd.to_datetime(df["amc_date"], errors='coerce')
-        
-        logging.info(f"File loaded successfully with {len(df)} rows (limited to {row_limit} rows)")
-        return df
-    except Exception as e:
-        logging.error(f"Failed to load CSV: {str(e)}")
-        raise e
+# Preload Hugging Face summarization model at startup
+logging.info("Preloading Hugging Face model...")
+try:
+    device = 0 if torch.cuda.is_available() else -1
+    summarizer = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6", device=device)
+    logging.info(f"Hugging Face model preloaded successfully on device: {'GPU' if device == 0 else 'CPU'}")
+except Exception as e:
+    logging.error(f"Failed to preload model: {str(e)}")
+    raise e
 
 # Format summary prompt and generate report
 def summarize_logs(df, progress=gr.Progress()):
@@ -119,7 +72,6 @@ def summarize_logs(df, progress=gr.Progress()):
     try:
         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"]
         logging.info("Summary generated successfully")
@@ -128,26 +80,22 @@ def summarize_logs(df, progress=gr.Progress()):
         logging.error(f"Summary generation failed: {str(e)}")
         return "Failed to generate summary."
 
-# Anomaly Detection using Isolation Forest with sampling for large datasets
+# Anomaly Detection using Isolation Forest
 def detect_anomalies(df, progress=gr.Progress()):
     progress(0.4, "Detecting anomalies...")
     try:
         if "usage_hours" not in df.columns or "downtime" not in df.columns:
             logging.warning("Required columns for anomaly detection not found")
             return "Anomaly detection requires 'usage_hours' and 'downtime' columns."
-
         if len(df) > 5000:
             df = df.sample(n=5000, random_state=42)
             logging.info("Sampled data for anomaly detection to 5,000 rows")
-
         features = df[["usage_hours", "downtime"]].fillna(0)
         iso_forest = IsolationForest(contamination=0.1, random_state=42, n_jobs=-1)
         df["anomaly"] = iso_forest.fit_predict(features)
-       
         anomalies = df[df["anomaly"] == -1][["device_id", "usage_hours", "downtime", "timestamp"]]
         if anomalies.empty:
             return "No anomalies detected."
-       
         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']}")
@@ -165,16 +113,12 @@ def check_amc_reminders(df, current_date, progress=gr.Progress()):
         if "device_id" not in df.columns or "amc_date" not in df.columns:
             logging.warning("Required columns for AMC reminders not found")
             return "AMC reminders require 'device_id' and 'amc_date' columns."
-
         df["amc_date"] = pd.to_datetime(df["amc_date"], errors='coerce')
         current_date = pd.to_datetime(current_date)
-       
         df["days_to_amc"] = (df["amc_date"] - current_date).dt.days
         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:**"]
         for idx, row in reminders.head(5).iterrows():
             reminder_lines.append(f"- Device ID: {row['device_id']}, AMC Date: {row['amc_date']}")
@@ -185,7 +129,7 @@ def check_amc_reminders(df, current_date, progress=gr.Progress()):
         logging.error(f"AMC reminder generation failed: {str(e)}")
         return f"AMC reminder generation failed: {str(e)}"
 
-# Dashboard Insights (AI-generated executive-level insights)
+# Dashboard Insights (AI-generated)
 def generate_dashboard_insights(df, progress=gr.Progress()):
     progress(0.8, "Generating dashboard insights...")
     try:
@@ -207,7 +151,6 @@ def create_usage_chart(df, progress=gr.Progress()):
         if len(usage_data) > 5:
             usage_data = usage_data.nlargest(5, "usage_hours")
             logging.info("Limited chart data to top 5 devices")
-
         custom_colors = ['#FF6B6B', '#4ECDC4', '#45B7D1', '#96CEB4']
         fig = px.bar(
             usage_data,
@@ -230,22 +173,68 @@ def create_usage_chart(df, progress=gr.Progress()):
         logging.error(f"Failed to create usage chart: {str(e)}")
         return None
 
+# Generate LaTeX PDF content
+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}
+\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
+
 # Main Gradio function
-async def process_logs(file_obj=None, progress=gr.Progress()):
+async def process_logs(row_limit=10000, progress=gr.Progress()):
     try:
-        progress(0, "Starting data processing...")
+        progress(0, "Connecting to Salesforce...")
+        sf = connect_to_salesforce()
+        progress(0.05, "Fetching data from Salesforce...")
+        df = fetch_salesforce_data(sf, row_limit)
         
-        # Load data: prioritize CSV if uploaded, otherwise fetch from Salesforce
-        if file_obj:
-            df = load_csv_data(file_obj, row_limit=10000, progress=progress)
-        else:
-            progress(0.05, "No CSV uploaded, fetching from Salesforce...")
-            sf = connect_to_salesforce()
-            df = fetch_salesforce_data(sf, row_limit=10000, progress=progress)
+        progress(0.1, "Converting timestamps...")
+        try:
+            df["timestamp"] = pd.to_datetime(df["timestamp"], errors='coerce')
+        except Exception as e:
+            logging.error(f"Date conversion failed: {str(e)}")
+            return f"Failed to convert timestamp to datetime: {str(e)}", None, None, None, None, None, None
 
         if df.empty:
-            logging.warning("No data available")
-            return "No data available.", "No data to preview.", None, "No anomalies detected.", "No AMC reminders.", "No insights generated."
+            logging.warning("No data retrieved from Salesforce")
+            return "No data available from Salesforce.", "No data to preview.", None, "No anomalies detected.", "No AMC reminders.", "No insights generated.", None
 
         # Step 1: Summary Report
         progress(0.2, "Generating summary...")
@@ -256,12 +245,13 @@ async def process_logs(file_obj=None, progress=gr.Progress()):
         if not df.empty:
             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']}, Timestamp: {row['timestamp']}, Usage Hours: {row['usage_hours']}, Downtime: {row['downtime']}, AMC Date: {row['amc_date']}, Log Type: {row['log_type']}, Status: {row['status']}")
+                preview_lines.append(f"**Row {idx + 1}:** Device ID: {row['device_id']}, 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."
 
         # Step 3: Usage Chart
+        progress(0.9, "Creating usage chart...")
         chart = create_usage_chart(df, progress)
 
         # Step 4: Anomaly Detection
@@ -273,13 +263,23 @@ async def process_logs(file_obj=None, progress=gr.Progress()):
         # Step 6: Dashboard Insights
         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
+
         progress(1.0, "Processing complete!")
-        return summary, preview, chart, anomalies, amc_reminders, insights
+        return summary, preview, chart, anomalies, amc_reminders, insights, pdf_file
     except Exception as e:
         logging.error(f"Failed to process data: {str(e)}")
-        return f"Failed to process data: {str(e)}", None, None, None, None, None
+        return f"Failed to process data: {str(e)}", None, None, None, None, None, None
 
-# Gradio Interface with Step-by-Step Layout
+# Gradio Interface
 try:
     logging.info("Initializing Gradio Blocks interface...")
     with gr.Blocks(css="""
@@ -291,52 +291,56 @@ try:
         .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 (Salesforce + Hugging Face AI)</h1>")
-        gr.Markdown("Upload a CSV file or fetch lab equipment logs from Salesforce to analyze usage.")
-
+        gr.Markdown("<h1>LabOps Log Analyzer Dashboard (Hugging Face AI + Salesforce)</h1>")
+        gr.Markdown("Analyze equipment logs fetched from Salesforce Smart_Log__c object.")
+        
         with gr.Row():
             with gr.Column(scale=1):
-                file_input = gr.File(label="Upload Logs (CSV)", file_types=[".csv"])
-                submit_button = gr.Button("Analyze Data", variant="primary")
-           
+                row_limit = gr.Number(label="Row Limit (Max Records to Fetch)", value=10000, precision=0)
+                submit_button = gr.Button("Fetch and Analyze", variant="primary")
             with gr.Column(scale=2):
                 with gr.Group(elem_classes="dashboard-container"):
                     gr.Markdown("<div class='dashboard-title'>Analysis Results (Step-by-Step)</div>")
-                   
+                    
                     # Step 1: Summary Report
                     with gr.Group(elem_classes="dashboard-section"):
                         gr.Markdown("### Step 1: Summary Report")
                         summary_output = gr.Markdown()
-                   
+                    
                     # Step 2: Log Preview
                     with gr.Group(elem_classes="dashboard-section"):
                         gr.Markdown("### Step 2: Log Preview")
                         preview_output = gr.Markdown()
-                   
+                    
                     # Step 3: Usage Chart
                     with gr.Group(elem_classes="dashboard-section"):
                         gr.Markdown("### Step 3: Usage Chart")
                         chart_output = gr.Plot()
-                   
+                    
                     # Step 4: Anomaly Detection
                     with gr.Group(elem_classes="dashboard-section"):
                         gr.Markdown("### Step 4: Anomaly Detection")
                         anomaly_output = gr.Markdown()
-                   
+                    
                     # Step 5: AMC Reminders
                     with gr.Group(elem_classes="dashboard-section"):
                         gr.Markdown("### Step 5: AMC Reminders")
                         amc_output = gr.Markdown()
-                   
+                    
                     # Step 6: Dashboard Insights
                     with gr.Group(elem_classes="dashboard-section"):
                         gr.Markdown("### Step 6: Dashboard Insights (AI)")
                         insights_output = gr.Markdown()
+                    
+                    # PDF Download
+                    with gr.Group(elem_classes="dashboard-section"):
+                        gr.Markdown("### Download Report")
+                        pdf_output = gr.File(label="Download Analysis Report as PDF")
 
         submit_button.click(
             fn=process_logs,
-            inputs=[file_input],
-            outputs=[summary_output, preview_output, chart_output, anomaly_output, amc_output, insights_output]
+            inputs=[row_limit],
+            outputs=[summary_output, preview_output, chart_output, anomaly_output, amc_output, insights_output, pdf_output]
         )
 
     logging.info("Gradio interface initialized successfully")