Update app.py

app.py

@@ -614,10 +614,10 @@ elif app_mode == "Model Training":
             min_features = 1 # Ensure at least one feature is used
             max_features = len(feature_columns) if len(feature_columns) > 0 else 1 # Use 1 if no features are selected
             param_grid = {
-                'n_estimators': list(range(st.slider("Number of Estimators", 10, 200, 100, help="Number of trees in the forest."),(st.slider("Number of Estimators", 10, 200, 100, help="Number of trees in the forest.")+1))),
-                'max_depth': list(range(st.slider("Max Depth", 3, 20, 10, help="Maximum depth of the tree."),(st.slider("Max Depth", 3, 20, 10, help="Maximum depth of the tree.")+1))),
-                'min_samples_split': list(range(st.slider("Minimum Samples Split", 2, 10, 2, help="Minimum samples required to split an internal node"),(st.slider("Minimum Samples Split", 2, 10, 2, help="Minimum samples required to split an internal node")+1))), #New hyperparameter
-                'min_samples_leaf': list(range(st.slider("Minimum Samples Leaf", 1, 10, 1, help="Minimum samples required to be at a leaf node"),(st.slider("Minimum Samples Leaf", 1, 10, 1, help="Minimum samples required to be at a leaf node")+1))), #New hyperparameter
+                'n_estimators': list(range(st.slider("Number of Estimators", 10, 200, 100, help="Number of trees in the forest.", key="n_estimators1"),(st.slider("Number of Estimators", 10, 200, 100, help="Number of trees in the forest.", key = "n_estimators2")+1))),
+                'max_depth': list(range(st.slider("Max Depth", 3, 20, 10, help="Maximum depth of the tree.", key="max_depth1"),(st.slider("Max Depth", 3, 20, 10, help="Maximum depth of the tree.", key = "max_depth2")+1))),
+                'min_samples_split': list(range(st.slider("Minimum Samples Split", 2, 10, 2, help="Minimum samples required to split an internal node", key="min_samples_split1"),(st.slider("Minimum Samples Split", 2, 10, 2, help="Minimum samples required to split an internal node", key = "min_samples_split2")+1))), #New hyperparameter
+                'min_samples_leaf': list(range(st.slider("Minimum Samples Leaf", 1, 10, 1, help="Minimum samples required to be at a leaf node", key="min_samples_leaf1"),(st.slider("Minimum Samples Leaf", 1, 10, 1, help="Minimum samples required to be at a leaf node", key = "min_samples_leaf2")+1))), #New hyperparameter
             }
 
         # Train-Test Split
@@ -661,7 +661,7 @@ elif app_mode == "Model Training":
 
                     #Feature Selection
                     if feature_selection_method == "SelectKBest":
-                        k = st.slider("Number of Features to Select", 1, len(feature_columns), len(feature_columns))
+                        k = st.slider("Number of Features to Select", 1, len(feature_columns), len(feature_columns), key = "featureselector")
                         selector = SelectKBest(k=k)
                         X_train_selected = selector.fit_transform(X_train_processed, y_train)
                         X_test_selected = selector.transform(X_test_processed)
@@ -762,7 +762,7 @@ elif app_mode == "Model Training":
 
                         #Heatmap
                         fig_conf, ax_conf = plt.subplots()
-                        sns.heatmap(conf_matrix, ax=ax_conf, annot=True, fmt='d', cmap='Blues')
+                        sns.heatmap(conf_matrix, annot=True, fmt='d', cmap='Blues', ax_conf)
                         ax_conf.set_xlabel('Predicted Labels')
                         ax_conf.set_ylabel('True Labels')
                         ax_conf.set_title('Confusion Matrix')
@@ -790,17 +790,12 @@ elif app_mode == "Model Training":
                          #Create data that determines the learning and validation curve and what we have to add
                             train_sizes, train_scores, valid_scores = learning_curve(model, X_train_selected, y_train, cv=5, scoring='accuracy' if problem_type =="Classification" else 'neg_mean_squared_error', n_jobs=-1) #Define cross validation for run
 
-
-                            #Take and define what this is for from the results that has been generated
+                            #Then add a plot for the learning curve and use st.pyplot
                             train_mean = np.mean(train_scores, axis=1)
                             train_std = np.std(train_scores, axis=1)
                             valid_mean = np.mean(valid_scores, axis=1)
                             valid_std = np.std(valid_scores, axis=1)
 
-
-                            #Plot each of the variables that has to be used.
-
-
                             fig_lc, ax_lc = plt.subplots()
                             ax_lc.plot(train_sizes, train_mean, color='blue', marker='o', markersize=5, label='Training ' + ('Accuracy' if problem_type == "Classification" else "Neg MSE"))
                             ax_lc.fill_between(train_sizes, train_mean + train_std, train_mean - train_std, alpha=0.15, color='blue')
@@ -818,7 +813,6 @@ elif app_mode == "Model Training":
 
                 except Exception as e:
                     st.error(f"An error occurred: {e}")
-
     else:
         st.write("Please upload and clean data first.")
 
@@ -856,7 +850,6 @@ elif app_mode == "Model Training":
                      st.write(f"Accuracy: {accuracy:.4f}")
             except Exception as e: #local error
                  st.error(f"An error occurred during model evaluation: {e}")
-
 elif app_mode == "Predictions":
     st.title("🔮 Make Predictions")