Update app.py

app.py

@@ -687,47 +687,7 @@ elif app_mode == "Advanced EDA":
         st.write("**Sample Data**")
         st.dataframe(df.head())
 
-# Model Training Section
-elif app_mode == "Model Training":
-    st.title("🚂 Model Training Studio")
-    st.markdown("""
-        **Train and Evaluate Machine Learning Models** with advanced hyperparameter tuning and performance tracking.
-        Choose from a wide range of algorithms and configurations.
-    """)
-
-    # Initialize session state variables
-    if 'model' not in st.session_state:
-        st.session_state.model = None
-    if 'preprocessor' not in st.session_state:
-        st.session_state.preprocessor = None
-    if 'X_train_selected' not in st.session_state:
-        st.session_state.X_train_selected = None
-    if 'X_test_selected' not in st.session_state:
-        st.session_state.X_test_selected = None
-    if 'y_train' not in st.session_state:
-        st.session_state.y_train = None
-    if 'y_test' not in st.session_state:
-        st.session_state.y_test = None
-
-    df = st.session_state.cleaned_data.copy()
-
-    # Target Variable Selection
-    st.subheader("🎯 Target Variable")
-    target_column = st.selectbox("Select Target Variable", df.columns, help="Choose the column to predict.")
-
-    # Problem Type Selection
-    st.subheader("📝 Problem Type")
-    problem_type = st.radio("Select Problem Type", ["Regression", "Classification"], help="Choose the type of machine learning problem.")
-
-    # Feature Selection
-    st.subheader("🔧 Feature Selection")
-    use_all_features = st.checkbox("Use All Features", value=True, help="Select to use all features for training. Deselect to manually choose features.")
-    if use_all_features:
-        feature_columns = df.drop(columns=[target_column]).columns.tolist()
-    else:
-        feature_columns = st.multiselect("Select Feature Columns", df.drop(columns=[target_column]).columns, help="Choose the features you want to use for prediction.")
-
-    # Model Selection
+# Model Selection
     st.subheader("🤖 Model Selection")
     if problem_type == "Regression":
         model_options = ["Linear Regression", "Decision Tree", "Random Forest", "Gradient Boosting", "SVM", "Neural Network"]
@@ -735,23 +695,44 @@ elif app_mode == "Model Training":
         model_options = ["Logistic Regression", "Decision Tree", "Random Forest", "Gradient Boosting", "SVM", "Neural Network", "KNN", "Naive Bayes"]
     model_name = st.selectbox("Select Model", model_options, help="Choose a model.")
 
-    if model_name == "Gradient Boosting":
-        learning_rate = st.slider("Learning Rate", 0.01, 1.0, 0.1)
-        n_estimators = st.slider("Number of Estimators", 10, 200, 100)
-        max_depth = st.slider("Max Depth", 3, 20, 10)
-        hyperparams = {
-            'learning_rate': learning_rate,
-            'n_estimators': n_estimators,
-            'max_depth': max_depth
-        }
+    # Hyperparameter Tuning
+    st.subheader("🎛️ Hyperparameter Tuning")
+    with st.expander("Configure Hyperparameters", expanded=True):
+        if model_name == "Random Forest":
+            n_estimators = st.slider("Number of Estimators", 10, 200, 100)
+            max_depth = st.slider("Max Depth", 3, 20, 10)
+            min_samples_split = st.slider("Min Samples Split", 2, 10, 2)
+            min_samples_leaf = st.slider("Min Samples Leaf", 1, 10, 1)
+            hyperparams = {
+                'n_estimators': n_estimators,
+                'max_depth': max_depth,
+                'min_samples_split': min_samples_split,
+                'min_samples_leaf': min_samples_leaf
+            }
+        elif model_name == "Gradient Boosting":  # Correct placement of elif
+            learning_rate = st.slider("Learning Rate", 0.01, 1.0, 0.1)
+            n_estimators = st.slider("Number of Estimators", 10, 200, 100)
+            max_depth = st.slider("Max Depth", 3, 20, 10)
+            hyperparams = {
+                'learning_rate': learning_rate,
+                'n_estimators': n_estimators,
+                'max_depth': max_depth
+            }
         elif model_name == "Neural Network":
+            from tensorflow.keras.models import Sequential
+            from tensorflow.keras.layers import Dense, Dropout, BatchNormalization
+            from tensorflow.keras.optimizers import Adam, Nadam, RMSprop, SGD
+
             hidden_layers = st.slider("Number of Hidden Layers", 1, 5, 2)
             neurons_per_layer = st.slider("Neurons per Layer", 10, 200, 50)
-            activation = st.selectbox("Activation Function", ["relu", "tanh", "sigmoid", "selu", "swish"])
+            activation = st.selectbox("Activation Function",
+                ["relu", "tanh", "sigmoid", "selu", "swish"])
             dropout_rate = st.slider("Dropout Rate", 0.0, 0.5, 0.2)
-            initializer = st.selectbox("Weight Initializer", ["glorot_uniform", "he_normal", "lecun_uniform"])
+            initializer = st.selectbox("Weight Initializer",
+                ["glorot_uniform", "he_normal", "lecun_uniform"])
             learning_rate = st.slider("Learning Rate", 0.0001, 0.1, 0.001, format="%.4f")
-            optimizer_choice = st.selectbox("Optimizer", ["Adam", "Nadam", "RMSprop", "SGD"])
+            optimizer_choice = st.selectbox("Optimizer",
+                ["Adam", "Nadam", "RMSprop", "SGD"])
             batch_norm = st.checkbox("Batch Normalization", value=True)
             regularization = st.checkbox("L2 Regularization")
             epochs = st.slider("Epochs", 10, 200, 50)
@@ -769,9 +750,8 @@ elif app_mode == "Model Training":
                 'epochs': epochs,
                 'batch_size': batch_size
             }
-        
-                    else:
-                        hyperparams = {}
+        else:
+            hyperparams = {}
 
     # Train-Test Split
     st.subheader("✂️ Train-Test Split")