Update app.py

app.py

@@ -64,60 +64,73 @@ class GANRiskAnalyzer:
 def analyze_financial_data(file):
     try:
         # Attempt to read the CSV file
-        data = pd.read_csv(file, encoding="utf-8")
+        data = pd.read_csv(file, encoding="utf-8", error_bad_lines=False)
     except UnicodeDecodeError:
         # Fallback for files with non-UTF-8 encodings
-        data = pd.read_csv(file, encoding="ISO-8859-1")
-    
+        data = pd.read_csv(file, encoding="ISO-8859-1", error_bad_lines=False)
+    except Exception as e:
+        return f"An error occurred while reading the file: {str(e)}"
+
+    # Handle empty or malformed data
+    if data.empty:
+        return "The uploaded file is empty or has an invalid structure."
+
     # Check required columns
     required_columns = ["Revenue", "Profit", "Loss", "Expenses", "Risk_Level"]
     if not all(column in data.columns for column in required_columns):
         return "The uploaded CSV must include these columns: Revenue, Profit, Loss, Expenses, Risk_Level."
 
     # Data Preprocessing
-    X = data[["Revenue", "Profit", "Loss", "Expenses"]]
-    y = data["Risk_Level"]
-    
-    scaler = StandardScaler()
-    X_scaled = scaler.fit_transform(X)
-    
-    # Dimensionality Reduction
-    pca = PCA(n_components=2)
-    X_pca = pca.fit_transform(X_scaled)
-    
-    # Train-Test Split
-    X_train, X_test, y_train, y_test = train_test_split(X_pca, y, test_size=0.2, random_state=42)
-    
-    # Gradient Boosting Classifier
-    model = GradientBoostingClassifier(n_estimators=100, learning_rate=0.1, max_depth=5)
-    model.fit(X_train, y_train)
-    y_pred = model.predict(X_test)
-    
-    accuracy = accuracy_score(y_test, y_pred)
-    report = classification_report(y_test, y_pred, output_dict=True)
-
-    # GAN-based Anomaly Detection
-    gan = GANRiskAnalyzer(input_dim=X_pca.shape[1], hidden_dim=128, output_dim=X_pca.shape[1])
-    gan.train(torch.tensor(X_pca, dtype=torch.float32), epochs=200)
-    anomalies = gan.generate(n_samples=5, input_dim=X_pca.shape[1])
-
-    # Analysis Insights
-    total_revenue = data["Revenue"].sum()
-    total_profit = data["Profit"].sum()
-    total_loss = data["Loss"].sum()
-
-    insights = {
-        "Accuracy": f"{accuracy * 100:.2f}%",
-        "Classification Report": report,
-        "Generated Anomalies (GAN)": anomalies.tolist(),
-        "Financial Summary": {
-            "Total Revenue": f"${total_revenue:,.2f}",
-            "Total Profit": f"${total_profit:,.2f}",
-            "Total Loss": f"${total_loss:,.2f}",
-            "Net Balance": f"${(total_revenue - total_loss):,.2f}"
+    try:
+        X = data[["Revenue", "Profit", "Loss", "Expenses"]].dropna()
+        y = data["Risk_Level"].dropna()
+
+        # Check for empty rows after cleaning
+        if X.empty or y.empty:
+            return "The data has missing values or invalid rows after cleaning. Please check the file."
+        
+        scaler = StandardScaler()
+        X_scaled = scaler.fit_transform(X)
+        
+        # Dimensionality Reduction
+        pca = PCA(n_components=2)
+        X_pca = pca.fit_transform(X_scaled)
+        
+        # Train-Test Split
+        X_train, X_test, y_train, y_test = train_test_split(X_pca, y, test_size=0.2, random_state=42)
+        
+        # Gradient Boosting Classifier
+        model = GradientBoostingClassifier(n_estimators=100, learning_rate=0.1, max_depth=5)
+        model.fit(X_train, y_train)
+        y_pred = model.predict(X_test)
+        
+        accuracy = accuracy_score(y_test, y_pred)
+        report = classification_report(y_test, y_pred, output_dict=True)
+
+        # GAN-based Anomaly Detection
+        gan = GANRiskAnalyzer(input_dim=X_pca.shape[1], hidden_dim=128, output_dim=X_pca.shape[1])
+        gan.train(torch.tensor(X_pca, dtype=torch.float32), epochs=200)
+        anomalies = gan.generate(n_samples=5, input_dim=X_pca.shape[1])
+
+        # Analysis Insights
+        total_revenue = data["Revenue"].sum()
+        total_profit = data["Profit"].sum()
+        total_loss = data["Loss"].sum()
+
+        insights = {
+            "Accuracy": f"{accuracy * 100:.2f}%",
+            "Classification Report": report,
+            "Generated Anomalies (GAN)": anomalies.tolist(),
+            "Financial Summary": {
+                "Total Revenue": f"${total_revenue:,.2f}",
+                "Total Profit": f"${total_profit:,.2f}",
+                "Total Loss": f"${total_loss:,.2f}",
+                "Net Balance": f"${(total_revenue - total_loss):,.2f}"
+            }
         }
-    }
-    return insights
+        return insights
+    except Exception as e:
+        return f"An error occurred during analysis: {str(e)}"
 
 with gr.Blocks(theme=gr.themes.Monochrome()) as interface:
     gr.Markdown("# **AI Risk Analyst Agent**")