Update app.py

app.py

@@ -5,7 +5,7 @@ import logging
 import plotly.express as px
 import plotly.graph_objects as go
 from sklearn.ensemble import IsolationForest
-from concurrent.futures import ThreadPoolExecutor  # Added missing import
+from concurrent.futures import ThreadPoolExecutor
 import os
 import io
 import time
@@ -314,61 +314,61 @@ def generate_pdf_content(summary, preview_df, anomalies, amc_reminders, insights
         logging.error(f"Failed to generate PDF: {str(e)}")
         return None
 
-# Main processing function
+# Main processing function (Updated)
 async def process_logs(file_obj, lab_site_filter, equipment_type_filter, date_range, last_modified_state, cached_df_state, cached_filtered_df_state):
     start_time = time.time()
     try:
         if not file_obj:
-            return "No file uploaded.", pd.DataFrame(), None, '<p>No device cards available.</p>', None, None, None, None, "No anomalies detected.", "No AMC reminders.", "No insights generated.", None, last_modified_state, cached_df_state, cached_filtered_df_state
+            return "No file uploaded.", pd.DataFrame(), None, '<p>No device cards available.</p>', None, None, None, None, "No anomalies detected.", "No AMC reminders.", "No insights generated.", None, last_modified_state, cached_df_state, None
 
         file_path = file_obj.name
         current_modified_time = os.path.getmtime(file_path)
-        if last_modified_state and current_modified_time == last_modified_state and cached_filtered_df_state is not None:
-            filtered_df = cached_filtered_df_state
+
+        # Load or use cached original dataframe
+        if cached_df_state is None or current_modified_time != last_modified_state:
+            logging.info(f"Processing file: {file_path}")
+            if not file_path.endswith(".csv"):
+                return "Please upload a CSV file.", pd.DataFrame(), None, '<p>No device cards available.</p>', None, None, None, None, "", "", "", None, last_modified_state, cached_df_state, None
+
+            required_columns = ["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_path, dtype=dtypes)
+            missing_columns = [col for col in required_columns if col not in df.columns]
+            if missing_columns:
+                return f"Missing columns: {missing_columns}", pd.DataFrame(), None, '<p>No device cards available.</p>', None, None, None, None, None, None, None, None, last_modified_state, cached_df_state, None
+
+            df["timestamp"] = pd.to_datetime(df["timestamp"], errors='coerce')
+            df["amc_date"] = pd.to_datetime(df["amc_date"], errors='coerce')
+            if df["timestamp"].dt.tz is None:
+                df["timestamp"] = df["timestamp"].dt.tz_localize('UTC').dt.tz_convert('Asia/Kolkata')
+            if df.empty:
+                return "No data available.", pd.DataFrame(), None, '<p>No device cards available.</p>', None, None, None, None, None, None, None, None, last_modified_state, df, None
+            cached_df_state = df
         else:
-            if cached_df_state is None or current_modified_time != last_modified_state:
-                logging.info(f"Processing file: {file_path}")
-                if not file_path.endswith(".csv"):
-                    return "Please upload a CSV file.", pd.DataFrame(), None, '<p>No device cards available.</p>', None, None, None, None, "", "", "", None, last_modified_state, cached_df_state, cached_filtered_df_state
-
-                required_columns = ["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_path, dtype=dtypes)
-                missing_columns = [col for col in required_columns if col not in df.columns]
-                if missing_columns:
-                    return f"Missing columns: {missing_columns}", pd.DataFrame(), None, '<p>No device cards available.</p>', None, None, None, None, None, None, None, None, last_modified_state, cached_df_state, cached_filtered_df_state
-
-                df["timestamp"] = pd.to_datetime(df["timestamp"], errors='coerce')
-                df["amc_date"] = pd.to_datetime(df["amc_date"], errors='coerce')
-                if df["timestamp"].dt.tz is None:
-                    df["timestamp"] = df["timestamp"].dt.tz_localize('UTC').dt.tz_convert('Asia/Kolkata')
-                if df.empty:
-                    return "No data available.", pd.DataFrame(), None, '<p>No device cards available.</p>', None, None, None, None, None, None, None, None, last_modified_state, df, cached_filtered_df_state
-            else:
-                df = cached_df_state
-
-            # Apply filters
-            filtered_df = df.copy()
-            if lab_site_filter and lab_site_filter != 'All' and 'lab_site' in filtered_df.columns:
-                filtered_df = filtered_df[filtered_df['lab_site'] == lab_site_filter]
-            if equipment_type_filter and equipment_type_filter != 'All' and 'equipment_type' in filtered_df.columns:
-                filtered_df = filtered_df[filtered_df['equipment_type'] == equipment_type_filter]
-            if date_range and len(date_range) == 2:
-                days_start, days_end = date_range
-                today = pd.to_datetime(datetime.now().date()).tz_localize('Asia/Kolkata')
-                start_date = today + pd.Timedelta(days=days_start)
-                end_date = today + pd.Timedelta(days=days_end) + pd.Timedelta(days=1) - pd.Timedelta(seconds=1)
-                filtered_df = filtered_df[(filtered_df['timestamp'] >= start_date) & (filtered_df['timestamp'] <= end_date)]
-
-            if filtered_df.empty:
-                return "No data after applying filters.", pd.DataFrame(), None, '<p>No device cards available.</p>', None, None, None, None, None, None, None, None, last_modified_state, df, filtered_df
+            df = cached_df_state
+
+        # Always apply current filters to the original dataframe
+        filtered_df = df.copy()
+        if lab_site_filter and lab_site_filter != 'All' and 'lab_site' in filtered_df.columns:
+            filtered_df = filtered_df[filtered_df['lab_site'] == lab_site_filter]
+        if equipment_type_filter and equipment_type_filter != 'All' and 'equipment_type' in filtered_df.columns:
+            filtered_df = filtered_df[filtered_df['equipment_type'] == equipment_type_filter]
+        if date_range and len(date_range) == 2:
+            days_start, days_end = date_range
+            today = pd.to_datetime(datetime.now().date()).tz_localize('Asia/Kolkata')
+            start_date = today + pd.Timedelta(days=days_start)
+            end_date = today + pd.Timedelta(days=days_end) + pd.Timedelta(days=1) - pd.Timedelta(seconds=1)
+            filtered_df = filtered_df[(filtered_df['timestamp'] >= start_date) & (filtered_df['timestamp'] <= end_date)]
+
+        if filtered_df.empty:
+            return "No data after applying filters.", pd.DataFrame(), None, '<p>No device cards available.</p>', None, None, None, None, None, None, None, None, last_modified_state, cached_df_state, None
 
         # Generate table for preview
         preview_df = filtered_df[['device_id', 'log_type', 'status', 'timestamp', 'usage_hours', 'downtime', 'amc_date']].head(5)
@@ -407,10 +407,10 @@ async def process_logs(file_obj, lab_site_filter, equipment_type_filter, date_ra
         if elapsed_time > 3:
             logging.warning(f"Processing time exceeded 3 seconds: {elapsed_time:.2f} seconds")
 
-        return (summary, preview_html, usage_chart, device_cards, daily_log_chart, weekly_uptime_chart, anomaly_alerts_chart, downtime_chart, anomalies, amc_reminders, insights, None, current_modified_time, df, filtered_df)
+        return (summary, preview_html, usage_chart, device_cards, daily_log_chart, weekly_uptime_chart, anomaly_alerts_chart, downtime_chart, anomalies, amc_reminders, insights, None, current_modified_time, cached_df_state, filtered_df)
     except Exception as e:
         logging.error(f"Failed to process file: {str(e)}")
-        return f"Error: {str(e)}", pd.DataFrame(), None, '<p>Error processing data.</p>', None, None, None, None, None, None, None, None, last_modified_state, cached_df_state, cached_filtered_df_state
+        return f"Error: {str(e)}", pd.DataFrame(), None, '<p>Error processing data.</p>', None, None, None, None, None, None, None, None, last_modified_state, cached_df_state, None
 
 # Generate PDF separately
 async def generate_pdf(summary, preview_html, usage_chart, device_cards, daily_log_chart, weekly_uptime_chart, anomaly_alerts_chart, downtime_chart, anomalies, amc_reminders, insights):