Update app.py

app.py

@@ -4,12 +4,12 @@ import vlai_template
 
 # Import Logistic Regression core
 try:
-    from src import logistic_regression
+    from src import softmax_regression
     LR_AVAILABLE = True
 except ImportError as e:
-    print(f"❌ Logistic Regression module failed to load: {str(e)}")
+    print(f"❌ Softmax Regression module failed to load: {str(e)}")
     LR_AVAILABLE = False
-    logistic_regression = None
+    softmax_regression = None
 
 vlai_template.configure(
     project_name="Softmax Regression Demo",
@@ -41,21 +41,21 @@ def load_sample_data_fallback(dataset_choice="Breast Cancer"):
         df["target"] = data.target
         return df
     
-    def wine_to_binary_df(wine_data):
+    def wine_to_df(wine_data):
         df = pd.DataFrame(wine_data.data, columns=wine_data.feature_names)
-        df["target"] = (wine_data.target == 0).astype(int)
+        df["target"] = wine_data.target
         return df
     
     def synthetic_classification():
-        X, y = make_classification(n_samples=1000, n_features=20, n_informative=15, 
-                                   n_redundant=5, n_classes=2, random_state=42)
+        X, y = make_classification(n_samples=1000, n_features=10, n_informative=8, 
+                                   n_redundant=2, n_classes=3, random_state=42)
         df = pd.DataFrame(X, columns=[f"feature_{i}" for i in range(X.shape[1])])
         df["target"] = y
         return df
     
     datasets = {
-        "Breast Cancer": lambda: sklearn_to_df(load_breast_cancer()),
-        "Wine (Binary)": lambda: wine_to_binary_df(load_wine()),
+        "Iris": lambda: sklearn_to_df(load_iris())),
+        "Wine (Binary)": lambda: wine_to_df(load_wine()),
         "Synthetic": lambda: synthetic_classification(),
     }
     
@@ -91,9 +91,9 @@ def create_input_components_fallback(df, target_col):
     return components
 
 SAMPLE_DATA_CONFIG = {
-    "Breast Cancer": {"target_column": "target", "problem_type": "classification"},
-    "Wine (Binary)": {"target_column": "target", "problem_type": "classification"},
-    "Synthetic": {"target_column": "target", "problem_type": "classification"},
+    "Iris": {"target_column": "target", "problem_type": "classification"},
+    "Wine (Multi-class)": {"target_column": "target", "problem_type": "classification"},
+    "Synthetic (3-Class)": {"target_column": "target", "problem_type": "classification"},
 }
 
 force_light_theme_js = """
@@ -112,8 +112,6 @@ def validate_config(df, target_col):
 
     target_series = df[target_col]
     unique_vals = target_series.nunique()
-
-    # For logistic regression, we only support binary classification (2 classes)
     problem_type = "classification"
     
     if target_series.isnull().any():
@@ -122,15 +120,15 @@ def validate_config(df, target_col):
     if target_series.dtype == "object":
         return False, "⚠️ Target must be numeric for classification. Please select a numeric column.", None
     
-    if unique_vals != 2:
-        return False, f"⚠️ Target must have exactly 2 unique values for binary classification. Found {unique_vals} unique values.", None
+    if unique_vals < 2:
+        return False, f"⚠️ Target must have at least 2 unique values. Found {unique_vals}.", None
+
+    if not pd.api.types.is_numeric_dtype(target_series):
+         return False, "⚠️ For this demo, target labels must be numeric (e.g., 0, 1, 2). Please encode your labels first.", None
 
-    # Check if values are 0 and 1
     unique_values = sorted(target_series.unique())
-    if set(unique_values) != {0, 1}:
-        return True, f"\n✅ Configuration is valid! Target will be mapped to binary (0/1). Original values: {unique_values}", problem_type
 
-    return True, f"\n✅ Configuration is valid! Ready for binary classification with values {unique_values}.", problem_type
+    return True, f"\n✅ Ready for Multi-class Softmax Classification! Found {unique_vals} classes: {unique_values}", problem_type
 
 
 def get_status_message(is_sample, dataset_choice, target_col, problem_type, is_valid, validation_msg):
@@ -176,7 +174,7 @@ def load_and_configure_data_simple(dataset_choice="Breast Cancer"):
         return [pd.DataFrame(), gr.Dropdown(choices=[], value=None), f"❌ **Error loading data**: {str(e)} | Please try a different dataset."]
 
 
-def load_and_configure_data(file_obj=None, dataset_choice="Breast Cancer"):
+def load_and_configure_data(file_obj=None, dataset_choice="Iris"):
     global current_dataframe
     try:
         if not LR_AVAILABLE:
@@ -356,7 +354,7 @@ def update_configuration(df_preview, target_col):
 
 # Logistic Regression prediction function
 
-def execute_prediction(df_preview, target_col, epochs, learning_rate_power, batch_size_power, train_test_split_ratio, threshold, *input_values):
+def execute_prediction(df_preview, target_col, epochs, learning_rate_power, batch_size_power, train_test_split_ratio, *input_values):
     global current_dataframe
     df = current_dataframe
 
@@ -408,8 +406,8 @@ def execute_prediction(df_preview, target_col, epochs, learning_rate_power, batc
             actual_batch_size = 2 ** int(batch_size_power)
             batch_size_str = str(actual_batch_size)
 
-        train_loss_fig, val_loss_fig, results_display, prediction = logistic_regression.run_logistic_regression_and_visualize(
-            df, target_col, new_point_dict, epochs, lr_float, batch_size_str, train_test_split_ratio, threshold
+        train_loss_fig, val_loss_fig, results_display, prediction = sofmax_regression.run_softmax_regression_and_visualize(
+            df, target_col, new_point_dict, epochs, lr_float, batch_size_str, train_test_split_ratio
         )
 
         return (train_loss_fig, val_loss_fig, results_display)
@@ -429,11 +427,11 @@ with gr.Blocks(theme="gstaff/sketch", css=vlai_template.custom_css, fill_width=T
     
     gr.HTML(vlai_template.render_info_card(
         icon="📊",
-        title="About this Logistic Regression Demo",
-        description="Interactive demonstration of Logistic Regression using NumPy and gradient descent. Learn binary classification with sigmoid activation, binary cross-entropy loss, and adjustable prediction threshold. Visualize training metrics and experiment with different threshold values."
+        title="About this Softmax Regression Demo",
+        description="Interactive demonstration of Softmax Regression for multi-class classification. Learn how it uses the Softmax activation function and Categorical Cross-Entropy loss to predict probabilities across multiple categories."
     ))
     
-    gr.Markdown("### 📊 **How to Use**: Select binary classification data → Configure target (must have 2 classes) → Set training parameters → Adjust threshold → Enter feature values → Run training!")
+    gr.Markdown("### 📊 **How to Use**: Select multi-class data → Configure target → Set training parameters → Enter feature values → Run training!")
 
     with gr.Row(equal_height=False, variant="panel"):
         with gr.Column(scale=45):
@@ -479,15 +477,6 @@ with gr.Blocks(theme="gstaff/sketch", css=vlai_template.custom_css, fill_width=T
                         value=0.8, minimum=0.6, maximum=0.9, step=0.05,
                         info="Proportion of data used for training (e.g., 0.8 = 80% train, 20% validation)"
                     )
-                
-                gr.Markdown("**🎯 Prediction Threshold Configuration**")
-                with gr.Row():
-                    threshold = gr.Slider(
-                        label="Classification Threshold",
-                        value=0.5, minimum=0.0, maximum=1.0, step=0.01,
-                        info="Probability threshold for binary classification. Predict class 1 if probability ≥ threshold, else class 0. Adjust to balance precision/recall."
-                    )
-                    threshold_display = gr.Markdown("**Current Threshold:** 0.50")
 
                 inputs_group = gr.Group(visible=False)
                 with inputs_group:
@@ -506,16 +495,16 @@ with gr.Blocks(theme="gstaff/sketch", css=vlai_template.custom_css, fill_width=T
                 run_prediction_btn = gr.Button("📊 Run Training & Prediction", variant="primary", size="lg")
 
         with gr.Column(scale=55):
-            gr.Markdown("### 📊 **Logistic Regression Results & Visualization**")
+            gr.Markdown("### 📊 **Softmax Regression Results & Visualization**")
             
             train_loss_chart = gr.Plot(label="Training Loss & Accuracy Over Epochs", visible=True)
             val_loss_chart = gr.Plot(label="Validation Loss & Accuracy Over Epochs", visible=True)
-            results_display = gr.HTML("**📊 Logistic Regression Results**<br><br>Training details will appear here showing model performance, learned parameters, and predictions with current threshold.", label="📊 Results & Predictions")
+            results_display = gr.HTML("**📊 Softmax Regression Results**<br><br>Training details will appear here showing model performance, learned parameters, and predictions with current threshold.", label="📊 Results & Predictions")
 
-    gr.Markdown("""📊 **Logistic Regression Guide**:
+    gr.Markdown("""📊 **Softmax Regression Guide**:
 
 **📈 Training Metrics**:
-- **Loss (BCE)**: Binary Cross-Entropy loss decreases as model learns. Lower loss indicates better fit.
+- **Categorical Cross-Entropy (CCE)**: The loss function used to optimize multi-class models.
 - **Accuracy**: Classification accuracy improves during training. Monitor both training and validation accuracy.
 
 **🔧 Training Parameters**:
@@ -524,29 +513,21 @@ with gr.Blocks(theme="gstaff/sketch", css=vlai_template.custom_css, fill_width=T
 - **Batch Size**: Samples processed before updating parameters. Powers of 2: 1, 2, 4, 8... or Full Batch. Smaller = faster updates but noisier. Larger = more stable.
 - **Train/Validation Split**: Proportion of data for training vs validation. Default 80/20 split.
 
-**🎯 Threshold Parameter**:
-- **Threshold**: Probability cutoff for binary classification. If predicted probability ≥ threshold → class 1, else → class 0.
-- **Default**: 0.5 (balanced)
-- **Lower threshold** (e.g., 0.3): More predictions of class 1 → higher recall, lower precision
-- **Higher threshold** (e.g., 0.7): Fewer predictions of class 1 → higher precision, lower recall
-- **Experiment**: Adjust threshold to see how predictions and accuracy change!
-
 **🧮 Algorithm Details**:
-- **Sigmoid Activation**: Maps linear output to probability (0-1 range)
-- **Binary Cross-Entropy Loss**: Optimized for binary classification tasks
-- **Feature Normalization**: Automatic standardization (zero mean, unit variance) for stable training
+- **Softmax Activation**: Converts raw scores (logits) into a probability distribution that sums to 1.0 across all classes.
+- **Categorical Cross-Entropy (CCE)**: The loss function used to optimize multi-class models.
+- **Feature Normalization**: Automatic standardization (zero mean, unit variance) for stable training.
 
 **💡 Tips**:
 - Start with default parameters (100 epochs, learning rate 0.01, threshold 0.5)
 - Monitor validation metrics to detect overfitting
-- Adjust threshold based on your classification goals (precision vs recall)
 - Use batch size = Full Batch for most stable training
 """)
 
     vlai_template.create_footer()
 
     load_evt = demo.load(
-        fn=lambda: load_and_configure_data(None, "Breast Cancer"),
+        fn=lambda: load_and_configure_data(None, "Iris"),
         outputs=[data_preview, target_column, status_message] + input_components + [inputs_group, input_status],
     ).then(
         fn=update_batch_size_slider, 
@@ -562,7 +543,7 @@ with gr.Blocks(theme="gstaff/sketch", css=vlai_template.custom_css, fill_width=T
         outputs=[learning_rate_display],
     )
     upload_evt = file_upload.upload(
-        fn=lambda file: load_and_configure_data(file, "Breast Cancer"),
+        fn=lambda file: load_and_configure_data(file, "Iris"),
         inputs=[file_upload],
         outputs=[data_preview, target_column, status_message] + input_components + [inputs_group, input_status],
     ).then(
@@ -629,15 +610,9 @@ with gr.Blocks(theme="gstaff/sketch", css=vlai_template.custom_css, fill_width=T
         outputs=[learning_rate_display],
     )
     
-    threshold.change(
-        fn=lambda t: f"**Current Threshold:** {t:.2f}",
-        inputs=[threshold],
-        outputs=[threshold_display],
-    )
-    
     run_prediction_btn.click(
         fn=execute_prediction,
-        inputs=[data_preview, target_column, epochs, learning_rate_slider, batch_size_slider, train_test_split_ratio, threshold] + input_components,
+        inputs=[data_preview, target_column, epochs, learning_rate_slider, batch_size_slider, train_test_split_ratio] + input_components,
         outputs=[train_loss_chart, val_loss_chart, results_display],
     )