Update app.py

app.py

@@ -38,26 +38,41 @@ def upload_csv(file):
     debug_msg_local = debug_msg + "\nStarting CSV upload process...\n"
     try:
         if file is None:
-            return ["All"], ["All"], ["All"], f"{debug_msg_local}No file uploaded. Please upload a CSV file.", "All", "All", "All", None, None, None, None
+            debug_msg_local += "No file uploaded. Please upload a CSV file.\n"
+            print(debug_msg_local)  # Log to console for debugging
+            return ["All"], ["All"], ["All"], debug_msg_local, "All", "All", "All", None, None, None, None
         
-        # Read the CSV file
+        # Read the CSV file with encoding handling
         debug_msg_local += "Reading CSV file...\n"
-        df = pd.read_csv(file)
+        try:
+            df = pd.read_csv(file, encoding='utf-8')
+        except UnicodeDecodeError:
+            debug_msg_local += "Error: CSV file encoding is not UTF-8. Trying latin1 encoding...\n"
+            df = pd.read_csv(file, encoding='latin1')
+        except Exception as e:
+            debug_msg_local += f"Error reading CSV file: {str(e)}\n{traceback.format_exc()}\n"
+            print(debug_msg_local)
+            return ["All"], ["All"], ["All"], debug_msg_local, "All", "All", "All", None, None, None, None
         
         if df.empty:
-            return ["All"], ["All"], ["All"], f"{debug_msg_local}The uploaded CSV file is empty.", "All", "All", "All", None, None, None, None
+            debug_msg_local += "The uploaded CSV file is empty.\n"
+            print(debug_msg_local)
+            return ["All"], ["All"], ["All"], debug_msg_local, "All", "All", "All", None, None, None, None
         
-        # Debug: Show the CSV content and column names
-        debug_msg_local += f"CSV Columns: {', '.join(df.columns)}\nRaw CSV Content:\n{df.to_string()}\n\n"
+        # Debug: Show the CSV column names (limit verbosity)
+        debug_msg_local += f"CSV Columns: {', '.join(df.columns)}\n"
         
         # Define required columns
         required_columns = {'DeviceID', 'Lab', 'Type', 'Timestamp', 'Status', 'UsageCount'}
         if not required_columns.issubset(df.columns):
             missing_cols = required_columns - set(df.columns)
-            return ["All"], ["All"], ["All"], f"{debug_msg_local}Error: CSV is missing required columns: {', '.join(missing_cols)}", "All", "All", "All", None, None, None, None
+            debug_msg_local += f"Error: CSV is missing required columns: {', '.join(missing_cols)}\n"
+            print(debug_msg_local)
+            return ["All"], ["All"], ["All"], debug_msg_local, "All", "All", "All", None, None, None, None
         
-        # Debug: Check data types and sample values
-        debug_msg_local += f"Data Types:\n{df.dtypes}\n\nSample Values:\n{df.head().to_string()}\n\n"
+        # Debug: Check data types and sample values (limit to 5 rows)
+        debug_msg_local += f"Data Types:\n{df.dtypes.to_string()}\n"
+        debug_msg_local += f"Sample Values (first 5 rows):\n{df.head(5).to_string()}\n"
         
         # Check for empty or all-NaN columns
         if df['Lab'].dropna().empty:
@@ -65,25 +80,31 @@ def upload_csv(file):
         if df['Type'].dropna().empty:
             debug_msg_local += "Error: Type column is empty or contains only NaN values.\n"
         if df['Lab'].dropna().empty or df['Type'].dropna().empty:
+            print(debug_msg_local)
             return ["All"], ["All"], ["All"], debug_msg_local, "All", "All", "All", None, None, None, None
         
-        # Convert Timestamp to datetime with error handling
+        # Convert Timestamp to datetime with a specific format and fallback
         debug_msg_local += "Converting Timestamp column...\n"
         try:
-            df['Timestamp'] = pd.to_datetime(df['Timestamp'], errors='coerce')
-            debug_msg_local += f"Timestamps after conversion:\n{df['Timestamp'].to_string()}\n\n"
+            # Try parsing with a common format first
+            df['Timestamp'] = pd.to_datetime(df['Timestamp'], format='%Y-%m-%d %H:%M:%S', errors='coerce')
+            # If parsing fails for some rows, try without a specific format
+            if df['Timestamp'].isna().any():
+                debug_msg_local += "Some timestamps failed to parse with format '%Y-%m-%d %H:%M:%S'. Falling back to generic parsing...\n"
+                df['Timestamp'] = pd.to_datetime(df['Timestamp'], errors='coerce')
             timestamps_invalid = df['Timestamp'].isna().all()
             if timestamps_invalid:
                 debug_msg_local += "Warning: All Timestamp values are invalid or unparseable. Date range filtering will be disabled.\n"
         except Exception as e:
             debug_msg_local += f"Error parsing Timestamp column: {str(e)}\n{traceback.format_exc()}\n"
+            print(debug_msg_local)
             return ["All"], ["All"], ["All"], debug_msg_local, "All", "All", "All", None, None, None, None
         
         # Extract unique values for dropdowns
         debug_msg_local += "Extracting unique values for dropdowns...\n"
         labs = ['All'] + sorted([str(lab) for lab in df['Lab'].dropna().unique()])
         types = ['All'] + sorted([str(v) for v in df['Type'].dropna().unique()])
-        debug_msg_local += f"Lab options: {', '.join(labs)}\nType options: {', '.join(types)}\n\n"
+        debug_msg_local += f"Lab options: {', '.join(labs)}\nType options: {', '.join(types)}\n"
         
         # Extract date range for filter
         if timestamps_invalid:
@@ -110,9 +131,14 @@ def upload_csv(file):
             debug_msg_local += f"Initial Filter Error: {str(e)}\n{traceback.format_exc()}\n"
             device_cards, plot_daily, plot_uptime, anomaly_text = None, None, None, None
         
+        # Truncate debug message to prevent Gradio rendering issues
+        debug_msg_local = debug_msg_local[:5000]  # Limit to 5000 characters
+        print(debug_msg_local)
         return labs, types, date_ranges, debug_msg_local, "All", "All", "All", device_cards, plot_daily, plot_uptime, anomaly_text
     except Exception as e:
         debug_msg_local += f"Failed to process CSV: {str(e)}\n{traceback.format_exc()}\n"
+        debug_msg_local = debug_msg_local[:5000]  # Limit to 5000 characters
+        print(debug_msg_local)
         return ["All"], ["All"], ["All"], debug_msg_local, "All", "All", "All", None, None, None, None
 
 def filter_and_visualize(selected_lab, selected_type, selected_date_range):
@@ -120,7 +146,9 @@ def filter_and_visualize(selected_lab, selected_type, selected_date_range):
     error_msg = "Starting filter and visualize process...\n"
     try:
         if df.empty:
-            return None, None, None, None, f"{error_msg}No data available."
+            error_msg += "No data available.\n"
+            print(error_msg)
+            return None, None, None, None, error_msg
         
         # Debug: Log the filter parameters
         error_msg += f"Applying filters: Lab={selected_lab}, Type={selected_type}, Date Range={selected_date_range}\n"
@@ -146,10 +174,12 @@ def filter_and_visualize(selected_lab, selected_type, selected_date_range):
                 error_msg += f"Error parsing date range: {str(e)}\n{traceback.format_exc()}\n"
         
         if filtered_df.empty:
-            return None, None, None, None, f"{error_msg}No data matches the selected filters."
+            error_msg += "No data matches the selected filters.\n"
+            print(error_msg)
+            return None, None, None, None, error_msg
         
-        # Debug: Log the filtered DataFrame
-        error_msg += f"Filtered DataFrame:\n{filtered_df.to_string()}\n"
+        # Debug: Log the filtered DataFrame (limit verbosity)
+        error_msg += f"Filtered DataFrame (first 5 rows):\n{filtered_df.head(5).to_string()}\n"
         
         # Device Cards (as a table)
         device_cards = filtered_df[['DeviceID', 'Lab', 'Type', 'UsageCount', 'Timestamp']].sort_values(by='Timestamp', ascending=False)
@@ -260,6 +290,8 @@ def filter_and_visualize(selected_lab, selected_type, selected_date_range):
             error_msg += f"Error generating Anomaly Alerts: {str(e)}\n{traceback.format_exc()}\n"
             anomaly_text = "Error generating anomaly alerts."
         
+        error_msg = error_msg[:5000]  # Limit to 5000 characters
+        print(error_msg)
         return device_cards, plot_daily, plot_uptime, anomaly_text, f"{error_msg}Filters applied successfully."
     except Exception as e:
         error_msg += f"Unexpected error in filter_and_visualize: {str(e)}\n{traceback.format_exc()}\n"
@@ -281,6 +313,8 @@ def filter_and_visualize(selected_lab, selected_type, selected_date_range):
         plt.close()
         plot_uptime.seek(0)
         
+        error_msg = error_msg[:5000]  # Limit to 5000 characters
+        print(error_msg)
         return None, plot_daily, plot_uptime, "Error generating anomaly alerts.", error_msg
 
 def download_pdf(selected_lab, selected_type, selected_date_range):