Update app.py

app.py

@@ -1,5 +1,5 @@
 """
-LabOps Log Analyzer Dashboard with optional CSV file upload and PDF generation
+LabOps Log Analyzer Dashboard with CSV file upload and optional PDF generation
 """
 import gradio as gr
 import pandas as pd
@@ -10,18 +10,20 @@ from sklearn.ensemble import IsolationForest
 from transformers import pipeline
 import torch
 
-# Try to configure import logging reportlab for debugging
+# Try to import reportlab for PDF generation
 try:
-    logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
     from reportlab.lib.pagesizes import letter
     from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer
     from reportlab.lib.styles import getSampleStyleSheet
     reportlab_available = True
     logging.info("reportlab module successfully imported")
-except ImportError as e:
+except ImportError:
     logging.warning("reportlab module not found. PDF generation will be disabled. Install with: pip install reportlab")
     reportlab_available = False
 
+# Configure logging for debugging
+logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
+
 # Preload Hugging Face summarization model at startup
 logging.info("Preloading Hugging Face model...")
 try:
@@ -225,7 +227,7 @@ async def process_logs(file_obj, progress=gr.Progress()):
                 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:
+        except Exception as e:
             logging.error(f"Failed to load CSV: {str(e)}")
             return f"Failed to load CSV: {str(e)}", None, None, None, None, None, None
 
@@ -233,12 +235,12 @@ async def process_logs(file_obj, progress=gr.Progress()):
         try:
             df["timestamp"] = pd.to_datetime(df["timestamp"], errors='coerce')
         except Exception as e:
-            logging.error(f"Error conversion failed: {error(e)}")
-            return f"error converting timestamp to datetime: {error(e)}", None, None, None, None, None, None
+            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 provided in the file")
-            return "No data available in provided.", "No data to preview.", None, "No anomalies detected.", "No AMC reminders.", "No insights generated.", None"
+            return "No data available in provided.", "No data to preview.", None, "No anomalies detected.", "No AMC reminders.", "No insights generated.", None
 
         # Step 1: Summary
         progress(0.2, "Generating summary...")
@@ -248,8 +250,8 @@ async def process_logs(file_obj, progress=gr.Progress()):
         progress(0.3, "Previewing logs...")
         if not df.empty:
             preview_lines = ["Step 2: Log Preview (First 5 Rows)"]
-            for idx, row in enumerate(df.head(5).iterrows(), start=1):
-                preview_lines.append(f"Row {idx}: 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']}")
+            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 = "\n".join(preview_lines)
         else:
             preview = "Step 2: Log Preview\nNo data available."
@@ -357,4 +359,96 @@ if __name__ == "__main__":
     except Exception as e:
         logging.error(f"Failed to launch Gradio interface: {str(e)}")
         print(f"Error launching app: {str(e)}")
-        raise e
+        raise e
+</xArtifact>
+
+### Key Changes Made
+1. **Fixed Syntax Error**:
+   - Removed the invalid leading double quote (`"`) before `except Exception as e:` in the CSV loading section (around line 228).
+   - Corrected the syntax to ensure proper error handling:
+     ```python
+     except Exception as e:
+         logging.error(f"Failed to load CSV: {str(e)}")
+         return f"Failed to load CSV: {str(e)}", None, None, None, None, None, None
+     ```
+   - Fixed another syntax error in the timestamp conversion error message, replacing `error(e)` with `str(e)`.
+
+2. **Preserved Functionality**:
+   - Retained all analysis functions (`summarize_logs`, `detect_anomalies`, `check_amc_reminders`, `generate_dashboard_insights`, `create_usage_chart`) unchanged.
+   - Kept the optional `reportlab` PDF generation with graceful fallback if `reportlab` is not installed.
+   - Maintained the Gradio interface layout and CSS styling.
+   - Ensured CSV file upload functionality without a row limit.
+
+3. **Error Handling**:
+   - Fixed syntax errors in error messages (e.g., corrected `error(e)` to `str(e)`).
+   - Kept robust logging to diagnose issues, including CSV loading, timestamp conversion, and PDF generation.
+
+4. **CSV Validation**:
+   - Retained validation for required columns (`device_id`, `log_type`, `status`, `timestamp`, `usage_hours`, `downtime`, `amc_date`).
+   - Corrected the log preview loop to use `df.head().iterrows()` consistently.
+
+### Prerequisites
+- Install required packages:
+  ```bash
+  pip install gradio pandas plotly scikit-learn transformers torch
+  ```
+- For PDF generation (optional but recommended):
+  ```bash
+  pip install reportlab
+  ```
+- No external tools (e.g., `wkhtmltopdf` or LaTeX) are required unless `reportlab` is installed.
+
+### CSV File Requirements
+- The CSV file must contain the columns: `device_id`, `log_type`, `status`, `timestamp`, `usage_hours`, `downtime`, and `amc_date`.
+- Example CSV structure:
+  ```csv
+  device_id,log_type,status,timestamp,usage_hours,downtime,amc_date
+  DEV001,Maintenance,Active,2025-06-01T10:00:00,5.5,0.2,2025-07-01
+  DEV002,Operation,Inactive,2025-06-02T12:00:00,3.0,1.5,2025-06-15
+  ```
+
+### How to Use
+1. Install the required Python packages listed above. Install `reportlab` if you want PDF generation.
+2. Save the code as `app.py` and run it:
+   ```bash
+   python app.py
+   ```
+3. Open the Gradio interface in your browser (default: `http://0.0.0.0:7860`).
+4. Upload a CSV file with the required columns and click "Analyze".
+5. View the analysis results in the dashboard (summary, preview, chart, anomalies, AMC reminders, insights).
+6. If `reportlab` is installed, download the PDF report from the "Download Report" section. If not, the PDF section will be empty, but other outputs will display.
+
+### Troubleshooting
+- **SyntaxError: unterminated string literal**:
+  - This error should now be resolved. If you encounter another syntax error, check for stray quotes or indentation issues in `app.py`. Ensure your editor uses 4 spaces for indentation and no mixed tabs/spaces.
+
+- **ModuleNotFoundError: No module named 'reportlab'**:
+  - If you see a warning like `reportlab module not found. PDF generation will be disabled`, install `reportlab` using `pip install reportlab` or ignore it if PDF output is not needed.
+
+- **CSV Parsing Error**:
+  - Ensure the CSV file has all required columns and valid data (e.g., `usage_hours` and `downtime` as numbers, `timestamp` and `amc_date` in a recognizable date format like `YYYY-MM-DD` or `YYYY-MM-DDTHH:MM:SS`).
+  - Check the terminal for errors like `Missing required columns` or `Failed to load CSV`.
+
+- **Gradio Interface Issues**:
+  - Ensure port 7860 is available and you’re accessing the correct URL.
+  - Check the terminal for errors like `Failed to initialize Gradio interface`.
+
+- **Other Errors**:
+  - If the interface loads but no output appears, check the terminal for logged errors (e.g., `Failed to process file`).
+  - Share the specific error message or terminal output for further assistance.
+
+- **Dependency Issues**:
+  - Verify all packages are installed using `pip list`. If you encounter version conflicts, use a virtual environment:
+    ```bash
+    python -m venv env
+    source env/bin/activate  # On Windows: env\Scripts\activate
+    pip install gradio pandas plotly scikit-learn transformers torch reportlab
+    ```
+
+### Notes
+- **PDF Generation**: If `reportlab` is not installed, PDF generation is skipped, and a warning is logged. Install `reportlab` for full functionality.
+- **Chart in PDF**: The chart is excluded from the PDF due to complexity in rendering Plotly charts. If needed, I can add code to generate a static image using `plotly.io` and embed it.
+- **Performance**: Large CSV files may slow processing. The anomaly detection function samples to 5,000 rows for larger datasets to prevent memory issues.
+- **Further Issues**: If you encounter other errors, please share the full traceback or terminal output, and I’ll provide a targeted fix.
+
+If you need additional features (e.g., chart inclusion in the PDF, custom PDF styling, or stricter CSV validation) or face another error, please let me know with details!