Update app.py

app.py

@@ -4,24 +4,24 @@ from pytorch_tabular import TabularModel
 from pytorch_tabular.config import DataConfig, TrainerConfig
 from pytorch_tabular.models import CategoryEmbeddingModelConfig
 
-# Sample Data
+# Sample meaningful data for loan approval prediction
 data = {
-    'feature1': [0.5, 0.3, 0.7, 0.2],
-    'feature2': [1, 0, 1, 1],
-    'feature3': [0.6, 0.1, 0.8, 0.4],
-    'target': [0, 1, 0, 1]  # Binary classification target
+    'age': [25, 45, 35, 50, 23, 63, 41, 34],
+    'income': [50000, 120000, 75000, 60000, 48000, 150000, 90000, 80000],
+    'credit_score': [650, 720, 680, 690, 640, 780, 710, 660],
+    'approved': [1, 1, 0, 0, 0, 1, 1, 0]  # Binary target: 1 for approved, 0 for rejected
 }
 df = pd.DataFrame(data)
 
 # Configure pytorch_tabular
 data_config = DataConfig(
-    target=["target"],
-    continuous_cols=["feature1", "feature2", "feature3"]
+    target=["approved"],
+    continuous_cols=["age", "income", "credit_score"]
 )
 
 model_config = CategoryEmbeddingModelConfig(
     task="classification",
-    layers="64-64",
+    layers="64-64",  # Hidden layer sizes for the model
     learning_rate=1e-3
 )
 
@@ -41,29 +41,28 @@ except ValueError as e:
     print(f"Error initializing TabularModel: {e}")
 
 # Define Inference Function
-def classify(feature1, feature2, feature3):
+def classify(age, income, credit_score):
     input_data = pd.DataFrame({
-        "feature1": [feature1],
-        "feature2": [feature2],
-        "feature3": [feature3]
+        "age": [age],
+        "income": [income],
+        "credit_score": [credit_score]
     })
     prediction = tabular_model.predict(input_data)["prediction"].iloc[0]
-    return "Class 1" if prediction == 1 else "Class 0"
+    return "Loan Approved" if prediction == 1 else "Loan Rejected"
 
 # Gradio Interface
 iface = gr.Interface(
     fn=classify,
     inputs=[
-        gr.Slider(0, 1, step=0.1, label="Feature 1"),
-        gr.Slider(0, 1, step=0.1, label="Feature 2"),
-        gr.Slider(0, 1, step=0.1, label="Feature 3")
+        gr.Slider(18, 70, step=1, label="Age"),
+        gr.Slider(30000, 200000, step=5000, label="Annual Income"),
+        gr.Slider(300, 850, step=10, label="Credit Score")
     ],
     outputs="text",
-    title="Tabular Classification with PyTorch Tabular",
-    description="Classify entries based on tabular data"
+    title="Loan Approval Prediction",
+    description="Predicts loan approval based on age, income, and credit score."
 )
 
 # Launch the Gradio app with necessary server settings
 print("Launching Gradio Interface...")
 iface.launch(server_name="0.0.0.0", server_port=7860, share=True)
-