Update app.py

app.py

@@ -36,22 +36,28 @@ class DataQualitySystem:
         conn.close()
 
     def load_and_process_data(self, file):
-    try:
-        file_path = file.name  # This should work for both CSV and XLSX files
-        if file_path.endswith('.csv'):
-            df = pd.read_csv(file_path)
-        elif file_path.endswith('.xlsx'):
-            df = pd.read_excel(file_path)
-        else:
-            return None, "Unsupported file format. Please use CSV or XLSX."
-        # Continue with the rest of your method
-        metrics = self.initial_data_checks(df)
-        df_with_anomalies = self.detect_anomalies(df)
-        self.store_quality_metrics(metrics)
-        return df_with_anomalies, "Data processed successfully!"
-    except Exception as e:
-        logging.error(f"Error processing file: {str(e)}")
-        return None, f"Error processing file: {str(e)}"
+        try:
+            file_path = file.name  # This should work for both CSV and XLSX files
+            if file_path.endswith('.csv'):
+                df = pd.read_csv(file_path)
+            elif file_path.endswith('.xlsx'):
+                df = pd.read_excel(file_path)
+            else:
+                return None, "Unsupported file format. Please use CSV or XLSX."
+            
+            # Initial data checks
+            metrics = self.initial_data_checks(df)
+            
+            # Anomaly detection
+            df_with_anomalies = self.detect_anomalies(df)
+            
+            # Store quality metrics
+            self.store_quality_metrics(metrics)
+            
+            return df_with_anomalies, "Data processed successfully!"
+        except Exception as e:
+            logging.error(f"Error processing file: {str(e)}")
+            return None, f"Error processing file: {str(e)}"
 
     def initial_data_checks(self, df):
         metrics = {
@@ -115,21 +121,21 @@ class DataQualitySystem:
         summary_fig = go.Figure(data=[
             go.Table(
                 header=dict(values=['Statistic'] + list(summary_stats.columns)),
-                cells=dict(values=[summary_stats.index] + [summary_stats[col] for col in summary_stats.columns])
+                cells=dict(values=[summary_stats.index] + [summary_stats[col].tolist() for col in summary_stats.columns])
             )
         ])
         
         # Create anomaly distribution plot
         if 'anomaly_score' in df.columns:
             anomaly_fig = px.histogram(df, x='anomaly_score', 
-                                     title='Distribution of Anomaly Scores')
+                                       title='Distribution of Anomaly Scores')
         else:
             anomaly_fig = None
             
         # Create missing values plot
         missing_data = df.isnull().sum()
         missing_fig = px.bar(x=missing_data.index, y=missing_data.values,
-                            title='Missing Values by Column')
+                             title='Missing Values by Column')
             
         return summary_fig, anomaly_fig, missing_fig
 
@@ -148,8 +154,7 @@ def create_gradio_interface():
     
     # Create the interface
     with gr.Blocks() as app:
-        gr.Markdown("# Data Quality Assurance System"
-                    A.Joshi 91-8847374924)
+        gr.Markdown("# Data Quality Assurance System")
         
         with gr.Row():
             file_input = gr.File(label="Upload Data File (CSV or XLSX)")
@@ -190,4 +195,4 @@ def create_gradio_interface():
 # Launch the interface
 if __name__ == "__main__":
     app = create_gradio_interface()
-    app.launch()
+    app.launch()