Update app.py

app.py

@@ -10,69 +10,79 @@ df = pd.DataFrame()
 
 def upload_csv(file):
     global df
+    debug_msg = "Starting CSV upload process...\n"
     try:
         if file is None:
-            return ["All"], ["All"], ["All"], "No file uploaded. Please upload a CSV file.", "All", "All", "All", None, None, None, None
+            return ["All"], ["All"], ["All"], f"{debug_msg}No file uploaded. Please upload a CSV file.", "All", "All", "All", None, None, None, None
         
         # Read the CSV file
+        debug_msg += "Reading CSV file...\n"
         df = pd.read_csv(file)
         
         if df.empty:
-            return ["All"], ["All"], ["All"], "The uploaded CSV file is empty.", "All", "All", "All", None, None, None, None
+            return ["All"], ["All"], ["All"], f"{debug_msg}The uploaded CSV file is empty.", "All", "All", "All", None, None, None, None
         
         # Debug: Show the CSV content and column names
-        csv_info = f"CSV Columns: {', '.join(df.columns)}\nRaw CSV Content:\n{df.to_string()}"
+        debug_msg += f"CSV Columns: {', '.join(df.columns)}\nRaw CSV Content:\n{df.to_string()}\n\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"{csv_info}\n\nError: CSV is missing required columns: {', '.join(missing_cols)}", "All", "All", "All", None, None, None, None
+            return ["All"], ["All"], ["All"], f"{debug_msg}Error: CSV is missing required columns: {', '.join(missing_cols)}", "All", "All", "All", None, None, None, None
         
         # Debug: Check data types and sample values
-        debug_msg = f"{csv_info}\n\nData Types:\n{df.dtypes}\n\nSample Values:\n{df.head().to_string()}"
+        debug_msg += f"Data Types:\n{df.dtypes}\n\nSample Values:\n{df.head().to_string()}\n\n"
         
         # Check for empty or all-NaN columns
+        if df['Lab'].dropna().empty:
+            debug_msg += "Error: Lab column is empty or contains only NaN values.\n"
+        if df['Type'].dropna().empty:
+            debug_msg += "Error: Type column is empty or contains only NaN values.\n"
         if df['Lab'].dropna().empty or df['Type'].dropna().empty:
-            return ["All"], ["All"], ["All"], f"{debug_msg}\n\nError: Lab or Type columns are empty or contain only NaN values.", "All", "All", "All", None, None, None, None
+            return ["All"], ["All"], ["All"], debug_msg, "All", "All", "All", None, None, None, None
         
         # Convert Timestamp to datetime with error handling
+        debug_msg += "Converting Timestamp column...\n"
         try:
             df['Timestamp'] = pd.to_datetime(df['Timestamp'], errors='coerce')
-            debug_msg += f"\n\nTimestamps after conversion:\n{df['Timestamp'].head().to_string()}"
+            debug_msg += f"Timestamps after conversion:\n{df['Timestamp'].to_string()}\n\n"
             if df['Timestamp'].isna().all():
-                return ["All"], ["All"], ["All"], f"{debug_msg}\n\nError: All Timestamp values are invalid or unparseable.", "All", "All", "All", None, None, None, None
+                return ["All"], ["All"], ["All"], f"{debug_msg}Error: All Timestamp values are invalid or unparseable.", "All", "All", "All", None, None, None, None
         except Exception as e:
-            return ["All"], ["All"], ["All"], f"{debug_msg}\n\nError: Failed to parse Timestamp column: {str(e)}", "All", "All", "All", None, None, None, None
+            return ["All"], ["All"], ["All"], f"{debug_msg}Error: Failed to parse Timestamp column: {str(e)}", "All", "All", "All", None, None, None, None
         
         # Extract unique values for dropdowns
+        debug_msg += "Extracting unique values for dropdowns...\n"
         labs = ['All'] + sorted([str(lab) for lab in df['Lab'].fillna('Unknown').unique()])
         types = ['All'] + sorted([str(type_) for type_ in df['Type'].fillna('Unknown').unique()])
+        debug_msg += f"Lab options: {labs}\nType options: {types}\n\n"
         
         # Extract date range for filter
         min_date = df['Timestamp'].min()
         max_date = df['Timestamp'].max()
         if pd.isna(min_date) or pd.isna(max_date):
             date_ranges = ['All']
-            debug_msg += "\n\nWarning: Could not determine date range due to invalid timestamps."
+            debug_msg += "Warning: Could not determine date range due to invalid timestamps.\n"
         else:
             min_date = min_date.strftime('%Y-%m-%d')
             max_date = max_date.strftime('%Y-%m-%d')
             date_ranges = ['All', f"{min_date} to {max_date}"]
-            debug_msg += f"\n\nDate Range: {min_date} to {max_date}"
+            debug_msg += f"Date Range: {min_date} to {max_date}\n"
         
         # Automatically trigger filter_and_visualize after upload with default filters
+        debug_msg += "Triggering initial visualization with default filters...\n"
         try:
             result = filter_and_visualize("All", "All", "All")
             device_cards, plot_daily, plot_uptime, anomaly_text, filter_msg = result
-            debug_msg += f"\n\nInitial Filter Result: {filter_msg}"
+            debug_msg += f"Initial Filter Result: {filter_msg}\n"
         except Exception as e:
-            debug_msg += f"\n\nInitial Filter Error: {str(e)}"
+            debug_msg += f"Initial Filter Error: {str(e)}\n"
             device_cards, plot_daily, plot_uptime, anomaly_text = None, None, None, None
         
         return labs, types, date_ranges, debug_msg, "All", "All", "All", device_cards, plot_daily, plot_uptime, anomaly_text
     except Exception as e:
-        return ["All"], ["All"], ["All"], f"Failed to load CSV: {str(e)}", "All", "All", "All", None, None, None, None
+        return ["All"], ["All"], ["All"], f"{debug_msg}Failed to load CSV: {str(e)}", "All", "All", "All", None, None, None, None
 
 def filter_and_visualize(selected_lab, selected_type, selected_date_range):
     global df
@@ -80,84 +90,123 @@ def filter_and_visualize(selected_lab, selected_type, selected_date_range):
         return None, None, None, None, "No data available."
     
     # Debug: Log the filter parameters
-    error_msg = f"Applying filters: Lab={selected_lab}, Type={selected_type}, Date Range={selected_date_range}"
+    error_msg = f"Applying filters: Lab={selected_lab}, Type={selected_type}, Date Range={selected_date_range}\n"
     
     # Filter the DataFrame
     filtered_df = df.copy()
+    error_msg += f"Initial DataFrame: {len(filtered_df)} rows\n"
+    
     if selected_lab != "All":
         filtered_df = filtered_df[filtered_df["Lab"] == selected_lab]
-        error_msg += f"\nAfter Lab filter ({selected_lab}): {len(filtered_df)} rows"
+        error_msg += f"After Lab filter ({selected_lab}): {len(filtered_df)} rows\n"
     if selected_type != "All":
         filtered_df = filtered_df[filtered_df["Type"] == selected_type]
-        error_msg += f"\nAfter Type filter ({selected_type}): {len(filtered_df)} rows"
+        error_msg += f"After Type filter ({selected_type}): {len(filtered_df)} rows\n"
     if selected_date_range != "All" and selected_date_range != "No data available.":
         try:
             start_date, end_date = selected_date_range.split(" to ")
             start_date = pd.to_datetime(start_date)
             end_date = pd.to_datetime(end_date) + timedelta(days=1)  # Include end date
             filtered_df = filtered_df[(filtered_df["Timestamp"] >= start_date) & (filtered_df["Timestamp"] < end_date)]
-            error_msg += f"\nAfter Date Range filter ({start_date} to {end_date}): {len(filtered_df)} rows"
+            error_msg += f"After Date Range filter ({start_date} to {end_date}): {len(filtered_df)} rows\n"
         except Exception as e:
-            error_msg += f"\nError parsing date range: {str(e)}"
+            error_msg += f"Error parsing date range: {str(e)}\n"
             return None, None, None, None, error_msg
     
     if filtered_df.empty:
-        return None, None, None, None, f"{error_msg}\nNo data matches the selected filters."
+        return None, None, None, None, f"{error_msg}No data matches the selected filters."
     
     # Debug: Log the filtered DataFrame
-    error_msg += f"\nFiltered DataFrame:\n{filtered_df.to_string()}"
+    error_msg += f"Filtered DataFrame:\n{filtered_df.to_string()}\n"
     
     # Device Cards (as a table)
     device_cards = filtered_df[['DeviceID', 'Lab', 'Type', 'UsageCount', 'Timestamp']].sort_values(by='Timestamp', ascending=False)
     
     # Daily Log Trends (Line Chart)
-    daily_logs = filtered_df.groupby(filtered_df['Timestamp'].dt.date).size()
-    plt.figure(figsize=(8, 4))
-    daily_logs.plot(kind='line', marker='o', color='blue')
-    plt.title("Daily Log Trends")
-    plt.xlabel("Date")
-    plt.ylabel("Number of Logs")
-    plt.xticks(rotation=45)
-    buf1 = io.BytesIO()
-    plt.savefig(buf1, format="png", bbox_inches="tight")
-    plt.close()
-    buf1.seek(0)
-    
-    # Weekly Uptime % (Bar Chart)
-    end_date = filtered_df['Timestamp'].max()
-    start_date = end_date - timedelta(days=7)
-    weekly_df = filtered_df[(filtered_df['Timestamp'] >= start_date) & (filtered_df['Timestamp'] <= end_date)]
-    if weekly_df.empty:
-        error_msg += "\nWarning: No data for Weekly Uptime % (date range too narrow)."
-        buf2 = io.BytesIO()
+    try:
+        daily_logs = filtered_df.groupby(filtered_df['Timestamp'].dt.date).size()
+        if daily_logs.empty:
+            error_msg += "Warning: No data for Daily Log Trends (invalid timestamps).\n"
+            plt.figure(figsize=(8, 4))
+            plt.title("Daily Log Trends - No Data")
+            plt.xlabel("Date")
+            plt.ylabel("Number of Logs")
+            buf1 = io.BytesIO()
+            plt.savefig(buf1, format="png", bbox_inches="tight")
+            plt.close()
+            buf1.seek(0)
+        else:
+            plt.figure(figsize=(8, 4))
+            daily_logs.plot(kind='line', marker='o', color='blue')
+            plt.title("Daily Log Trends")
+            plt.xlabel("Date")
+            plt.ylabel("Number of Logs")
+            plt.xticks(rotation=45)
+            buf1 = io.BytesIO()
+            plt.savefig(buf1, format="png", bbox_inches="tight")
+            plt.close()
+            buf1.seek(0)
+    except Exception as e:
+        error_msg += f"Error generating Daily Log Trends: {str(e)}\n"
         plt.figure(figsize=(8, 4))
-        plt.title("Weekly Uptime % - No Data")
+        plt.title("Daily Log Trends - Error")
         plt.xlabel("Date")
-        plt.ylabel("Uptime %")
-        plt.savefig(buf2, format="png", bbox_inches="tight")
+        plt.ylabel("Number of Logs")
+        buf1 = io.BytesIO()
+        plt.savefig(buf1, format="png", bbox_inches="tight")
         plt.close()
-        buf2.seek(0)
-    else:
-        uptime = weekly_df.groupby(weekly_df['Timestamp'].dt.date)['Status'].apply(lambda x: (x == 'Up').mean() * 100)
+        buf1.seek(0)
+    
+    # Weekly Uptime % (Bar Chart)
+    try:
+        end_date = filtered_df['Timestamp'].max()
+        start_date = end_date - timedelta(days=7)
+        weekly_df = filtered_df[(filtered_df['Timestamp'] >= start_date) & (filtered_df['Timestamp'] <= end_date)]
+        if weekly_df.empty:
+            error_msg += "Warning: No data for Weekly Uptime % (date range too narrow).\n"
+            plt.figure(figsize=(8, 4))
+            plt.title("Weekly Uptime % - No Data")
+            plt.xlabel("Date")
+            plt.ylabel("Uptime %")
+            buf2 = io.BytesIO()
+            plt.savefig(buf2, format="png", bbox_inches="tight")
+            plt.close()
+            buf2.seek(0)
+        else:
+            uptime = weekly_df.groupby(weekly_df['Timestamp'].dt.date)['Status'].apply(lambda x: (x == 'Up').mean() * 100)
+            plt.figure(figsize=(8, 4))
+            uptime.plot(kind='bar', color='green')
+            plt.title("Weekly Uptime %")
+            plt.xlabel("Date")
+            plt.ylabel("Uptime %")
+            plt.xticks(rotation=45)
+            buf2 = io.BytesIO()
+            plt.savefig(buf2, format="png", bbox_inches="tight")
+            plt.close()
+            buf2.seek(0)
+    except Exception as e:
+        error_msg += f"Error generating Weekly Uptime %: {str(e)}\n"
         plt.figure(figsize=(8, 4))
-        uptime.plot(kind='bar', color='green')
-        plt.title("Weekly Uptime %")
+        plt.title("Weekly Uptime % - Error")
         plt.xlabel("Date")
         plt.ylabel("Uptime %")
-        plt.xticks(rotation=45)
         buf2 = io.BytesIO()
         plt.savefig(buf2, format="png", bbox_inches="tight")
         plt.close()
         buf2.seek(0)
     
     # Anomaly Alerts (Text)
-    anomalies = filtered_df[(filtered_df['UsageCount'] > 80) | (filtered_df['Status'] == 'Down')]
-    if anomalies.empty:
-        anomaly_text = "No anomalies detected."
-    else:
-        anomaly_text = "Anomalies Detected:\n" + anomalies[['DeviceID', 'Lab', 'Type', 'Status', 'UsageCount']].to_string(index=False)
+    try:
+        anomalies = filtered_df[(filtered_df['UsageCount'] > 80) | (filtered_df['Status'] == 'Down')]
+        if anomalies.empty:
+            anomaly_text = "No anomalies detected."
+        else:
+            anomaly_text = "Anomalies Detected:\n" + anomalies[['DeviceID', 'Lab', 'Type', 'Status', 'UsageCount']].to_string(index=False)
+    except Exception as e:
+        error_msg += f"Error generating Anomaly Alerts: {str(e)}\n"
+        anomaly_text = "Error generating anomaly alerts."
     
-    return device_cards, buf1, buf2, anomaly_text, f"{error_msg}\nFilters applied successfully."
+    return device_cards, buf1, buf2, anomaly_text, f"{error_msg}Filters applied successfully."
 
 def download_pdf(selected_lab, selected_type, selected_date_range):
     global df