Update app.py

app.py

@@ -12,6 +12,23 @@ import tempfile
 # Configure logging to match the log format
 logging.basicConfig(level=logging.INFO, format='%(asctime)s,%(msecs)03d - %(levelname)s - %(message)s')
 
+def validate_csv(df):
+    """
+    Validate that the CSV has the required columns.
+    Returns True if valid, False otherwise with an error message.
+    """
+    required_columns = ['equipment', 'usage_count', 'status', 'amc_expiry']
+    missing_columns = [col for col in required_columns if col not in df.columns]
+    if missing_columns:
+        return False, f"Missing required columns: {', '.join(missing_columns)}"
+    # Validate data types
+    try:
+        df['usage_count'] = pd.to_numeric(df['usage_count'], errors='raise')
+        df['amc_expiry'] = pd.to_datetime(df['amc_expiry'], errors='raise')
+    except Exception as e:
+        return False, f"Invalid data types: {str(e)}"
+    return True, ""
+
 def process_files(uploaded_files):
     """
     Process uploaded CSV files, generate usage plots, detect anomalies, and process AMC expiries.
@@ -39,6 +56,11 @@ def process_files(uploaded_files):
         try:
             df = pd.read_csv(file.name)
             logging.info(f"Loaded {len(df)} records from {file.name}")
+            # Validate CSV structure
+            is_valid, error_msg = validate_csv(df)
+            if not is_valid:
+                logging.error(f"Failed to load {file.name}: {error_msg}")
+                return None, None, None, f"Error loading {file.name}: {error_msg}"
             all_data.append(df)
         except Exception as e:
             logging.error(f"Failed to load {file.name}: {str(e)}")
@@ -79,7 +101,7 @@ def process_files(uploaded_files):
     # Prepare output dataframe (combine original data with anomalies)
     output_df = combined_df.copy()
     if anomaly_df is not None:
-        output_df['anomaly'] = anomaly_df['anomaly']
+        output_df['anomaly'] = anomaly_df['anomaly'].map({1: "Normal", -1: "Anomaly"})
 
     return output_df, plot_path, pdf_path, amc_message
 
@@ -89,20 +111,27 @@ def generate_usage_plot(df):
     Returns the path to the saved plot.
     """
     try:
-        plt.figure(figsize=(10, 6))
+        plt.figure(figsize=(12, 6))
+        # Define colors for statuses
+        status_colors = {'Active': '#36A2EB', 'Inactive': '#FF6384', 'Down': '#FFCE56', 'Online': '#4BC0C0'}
         for status in df['status'].unique():
             subset = df[df['status'] == status]
-            plt.bar(subset['equipment'] + f" ({status})", subset['usage_count'], label=status)
-        plt.xlabel("Equipment (Status)")
-        plt.ylabel("Usage Count")
-        plt.title("Usage Count by Equipment and Status")
-        plt.legend()
-        plt.xticks(rotation=45)
+            plt.bar(
+                subset['equipment'] + f" ({status})",
+                subset['usage_count'],
+                label=status,
+                color=status_colors.get(status, '#999999')
+            )
+        plt.xlabel("Equipment (Status)", fontsize=12)
+        plt.ylabel("Usage Count", fontsize=12)
+        plt.title("Usage Count by Equipment and Status", fontsize=14)
+        plt.legend(title="Status")
+        plt.xticks(rotation=45, ha='right')
         plt.tight_layout()
 
         # Save plot to temporary file
         with tempfile.NamedTemporaryFile(delete=False, suffix='.png') as tmp:
-            plt.savefig(tmp.name, format='png')
+            plt.savefig(tmp.name, format='png', dpi=100)
             plot_path = tmp.name
         plt.close()
         return plot_path
@@ -136,8 +165,8 @@ def process_amc_expiries(df):
         df['amc_expiry'] = pd.to_datetime(df['amc_expiry'])
         upcoming_expiries = df[df['amc_expiry'] <= threshold]
         unique_devices = upcoming_expiries['equipment'].unique()
-        message = f"Found {len(unique_devices)} devices with upcoming AMC expiries."
-        logging.info(message)
+        message = f"Found {len(unique_devices)} devices with upcoming AMC expiries: {', '.join(unique_devices)}."
+        logging.info(f"Found {len(unique_devices)} devices with upcoming AMC expiries.")
         return message, upcoming_expiries
     except Exception as e:
         logging.error(f"Failed to process AMC expiries: {str(e)}")
@@ -149,38 +178,59 @@ def generate_pdf_report(original_df, anomaly_df, amc_df):
     Returns the path to the saved PDF.
     """
     try:
-        if original_df is None:
+        if original_df is None or original_df.empty:
             logging.warning("No data available for PDF generation.")
             return None
 
         with tempfile.NamedTemporaryFile(delete=False, suffix='.pdf') as tmp:
             c = canvas.Canvas(tmp.name, pagesize=letter)
+            c.setFont("Helvetica-Bold", 16)
             c.drawString(100, 750, "Equipment Log Analysis Report")
-            y = 700
+            c.setFont("Helvetica", 12)
+            y = 720
 
             # Summary
+            c.drawString(100, y, "Summary")
+            y -= 20
             c.drawString(100, y, f"Total Records: {len(original_df)}")
-            c.drawString(100, y-20, f"Devices: {', '.join(original_df['equipment'].unique())}")
+            y -= 20
+            c.drawString(100, y, f"Devices: {', '.join(original_df['equipment'].unique())}")
             y -= 40
 
             # Anomalies
+            c.drawString(100, y, "Anomaly Detection Results")
+            y -= 20
             if anomaly_df is not None:
                 num_anomalies = sum(anomaly_df['anomaly'] == -1)
                 c.drawString(100, y, f"Anomalies Detected: {num_anomalies}")
+                y -= 20
                 if num_anomalies > 0:
-                    anomaly_equipment = anomaly_df[anomaly_df['anomaly'] == -1]['equipment'].unique()
-                    c.drawString(100, y-20, f"Anomalous Devices: {', '.join(anomaly_equipment)}")
-                y -= 40
+                    anomaly_records = anomaly_df[anomaly_df['anomaly'] == -1][['equipment', 'usage_count']]
+                    c.drawString(100, y, "Anomalous Records:")
+                    y -= 20
+                    for _, row in anomaly_records.iterrows():
+                        c.drawString(100, y, f"{row['equipment']}: Usage Count = {row['usage_count']}")
+                        y -= 20
+                        if y < 50:
+                            c.showPage()
+                            y = 750
             else:
                 c.drawString(100, y, "Anomaly detection failed.")
                 y -= 20
+            y -= 20
 
             # AMC Expiries
+            c.drawString(100, y, "AMC Expiries Within 7 Days")
+            y -= 20
             if amc_df is not None and not amc_df.empty:
                 c.drawString(100, y, f"Devices with Upcoming AMC Expiries: {len(amc_df['equipment'].unique())}")
+                y -= 20
                 for _, row in amc_df.iterrows():
-                    c.drawString(100, y-20, f"{row['equipment']}: {row['amc_expiry'].strftime('%Y-%m-%d')}")
+                    c.drawString(100, y, f"{row['equipment']}: {row['amc_expiry'].strftime('%Y-%m-%d')}")
                     y -= 20
+                    if y < 50:
+                        c.showPage()
+                        y = 750
             else:
                 c.drawString(100, y, "No AMC expiry data available.")
                 y -= 20