Update app.py

app.py

@@ -63,83 +63,56 @@ class GANRiskAnalyzer:
 # Risk Analysis
 def analyze_financial_data(file):
     try:
-        # Read the uploaded CSV file
-        data = pd.read_csv(file.name, encoding="utf-8", on_bad_lines='skip')
-    except UnicodeDecodeError:
-        try:
-            data = pd.read_csv(file.name, encoding="ISO-8859-1", on_bad_lines='skip')
-        except Exception as e:
-            return {"error": f"Failed to read file: {str(e)}"}
+        # Read the uploaded Excel or CSV file
+        if file.name.endswith('.xlsx'):
+            data = pd.read_excel(file.name)
+        else:
+            data = pd.read_csv(file.name, encoding='utf-8', on_bad_lines='skip')
     except Exception as e:
-        return {"error": f"An unexpected error occurred: {str(e)}"}
+        return {"error": f"Failed to read file: {str(e)}"}
 
     if data.empty:
         return {"error": "The uploaded file is empty or has an invalid structure."}
 
-    # Dynamically map required columns
-    expected_columns = ["Revenue", "Profit", "Loss", "Expenses", "Risk_Level"]
-    available_columns = data.columns.tolist()
-    column_mapping = {}
-    
-    for expected_col in expected_columns:
-        for available_col in available_columns:
-            if expected_col.lower() in available_col.lower():
-                column_mapping[expected_col] = available_col
-                break
-    
-    if len(column_mapping) != len(expected_columns):
-        return {"error": f"The CSV must contain columns similar to: {', '.join(expected_columns)}"}
-    
-    data.rename(columns=column_mapping, inplace=True)
-
+    # Dynamically detect column names
+    expected_columns = data.columns.tolist()
     try:
-        # Data Preprocessing
-        X = data[[column_mapping["Revenue"], column_mapping["Profit"], column_mapping["Loss"], column_mapping["Expenses"]]].dropna()
-        y = data[column_mapping["Risk_Level"]].dropna()
-
-        if X.empty or y.empty:
-            return {"error": "The data contains missing values or invalid rows after cleaning."}
-
-        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])
-
-        total_revenue = data[column_mapping["Revenue"]].sum()
-        total_profit = data[column_mapping["Profit"]].sum()
-        total_loss = data[column_mapping["Loss"]].sum()
-
-        return {
-            "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}"
-            }
-        }
+        X = data.drop(columns=[expected_columns[-1]]).dropna()
+        y = data[expected_columns[-1]].dropna()
     except Exception as e:
-        return {"error": f"An error occurred during analysis: {str(e)}"}
+        return {"error": "Invalid data format. Please ensure the last column contains labels."}
+
+    if X.empty or y.empty:
+        return {"error": "The data contains missing values or invalid rows after cleaning."}
+
+    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)
+
+    # 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])
+
+    insights = f"The analysis reveals an accuracy of {accuracy * 100:.2f}%. "
+    insights += "Potential risks were identified using advanced AI techniques, indicating areas of improvement such as better expense control and optimized revenue streams. "
+    insights += "Consider reviewing operational inefficiencies and diversifying revenue sources to mitigate financial risks."
+
+    return insights
 
 # Gradio Interface
 with gr.Blocks(theme=gr.themes.Monochrome()) as interface:
@@ -147,10 +120,10 @@ with gr.Blocks(theme=gr.themes.Monochrome()) as interface:
     gr.Markdown("Analyze your financial risks and identify anomalies using AI models.")
     with gr.Row():
         with gr.Column():
-            data_file = gr.File(label="Upload Financial Data (CSV)", file_types=[".csv"])
+            data_file = gr.File(label="Upload Financial Data (CSV/XLSX)", file_types=[".csv", ".xlsx"])
             submit_button = gr.Button("Analyze")
         with gr.Column():
-            output = gr.JSON(label="Risk Analysis Insights")
+            output = gr.Textbox(label="Risk Analysis Insights")
 
     submit_button.click(analyze_financial_data, inputs=data_file, outputs=output)