Update app.py

app.py

@@ -29,6 +29,8 @@ import time
 from sklearn.cluster import KMeans
 import scipy.stats as stats
 import mimetypes
+import matplotlib.pyplot as plt
+from sklearn.model_selection import learning_curve
 
 # Configurations
 st.set_page_config(page_title="Executive Insights Pro", layout="wide", page_icon="📈")
@@ -737,6 +739,9 @@ elif app_mode == "Model Training":
                         from sklearn.metrics import confusion_matrix, roc_curve, auc, precision_recall_curve, classification_report #Import here to avoid library bloat
                         import seaborn as sns
                         import matplotlib.pyplot as plt #Added import statement
+                        import numpy as np
+                        import pandas as pd
+                        from sklearn.model_selection import learning_curve, validation_curve
 
                         #Weighted averaging for metrics for multiclass
                         average_method = "weighted" #changed from None
@@ -766,21 +771,51 @@ elif app_mode == "Model Training":
                         st.pyplot(fig_conf)
 
 
-                     # Feature Importance (Tree-based Models)
-                    if model_name in ["Random Forest", "Gradient Boosting"] and problem_type == "Classification":
-                        importances = model.feature_importances_ # Assumed tree-based model
-                        feat_importances = pd.Series(importances, index=X_train.columns)
-                        feat_importances = feat_importances.nlargest(20)
+                    #Added section for model visualization
+                    st.subheader("Model Visualization")
 
-                        fig_feat, ax_feat = plt.subplots()
-                        feat_importances.plot(kind='barh', ax=ax_feat)
-                        ax_feat.set_xlabel('Relative Importance')
-                        ax_feat.set_ylabel('Features')
-                        ax_feat.set_title('Feature Importances')
-                        st.pyplot(fig_feat)
+                    if problem_type == "Classification":
+
+                        try: #All the plotting code here.
+                            #Added code that calculates the learning curves
+                            train_sizes, train_scores, valid_scores = learning_curve(model, X_train_selected, y_train, cv=5, scoring='accuracy')
+
+                            #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)
+
+                            fig_lc, ax_lc = plt.subplots() #plot the curve in matplotlib
+
+
+                            ax_lc.plot(train_sizes, train_mean, color='blue', marker='o', markersize=5, label='Training Accuracy')
+                            ax_lc.fill_between(train_sizes, train_mean + train_std, train_mean - train_std, alpha=0.15, color='blue')
+                            ax_lc.plot(train_sizes, valid_mean, color='green', linestyle='--', marker='s', markersize=5, label='Validation Accuracy')
+                            ax_lc.fill_between(train_sizes, valid_mean + valid_std, valid_mean - valid_std, alpha=0.15, color='green')
+
+                            ax_lc.set_title('Learning Curves')
+                            ax_lc.set_xlabel('Training Set Size')
+                            ax_lc.set_ylabel('Accuracy')
+                            ax_lc.legend(loc='best')
+                            st.pyplot(fig_lc)  # Display the figure in Streamlit
+
+
+                            #Feature Importance (Tree-based Models)
+                            if model_name in ["Random Forest", "Gradient Boosting"] : #Make sure its the correct type for extraction
+                                importances = model.feature_importances_ # Assumed tree-based model
+                                feat_importances = pd.Series(importances, index=X_train.columns)
+                                feat_importances = feat_importances.nlargest(20)
+
+                                fig_feat, ax_feat = plt.subplots()
+                                feat_importances.plot(kind='barh', ax=ax_feat)
+                                ax_feat.set_xlabel('Relative Importance')
+                                ax_feat.set_ylabel('Features')
+                                ax_feat.set_title('Feature Importances')
+                                st.pyplot(fig_feat)
+                        except Exception as e: #Local error
+                            st.write(f"Plotting functions requires tree based-models and for classification: {e}")
 
-                except Exception as e:
-                    st.error(f"An error occurred: {e}")
     else:
         st.write("Please upload and clean data first.")
 
@@ -803,7 +838,7 @@ elif app_mode == "Model Training":
 
        #Model Evaluation Section
         if 'X_test' in locals() and st.session_state.model is not None:
-            try:
+            try: #Error catching with new test data
                 y_pred = st.session_state.model.predict(X_test)
 
                 if problem_type == "Regression":
@@ -812,11 +847,12 @@ elif app_mode == "Model Training":
                     st.write(f"Mean Squared Error: {mse:.4f}")
                     st.write(f"R-squared: {r2:.4f}")
                 else:
-                    from sklearn.metrics import confusion_matrix, roc_curve, auc, precision_recall_curve, classification_report #Import here to avoid library bloat
-                    accuracy = accuracy_score(y_test, y_pred)
-                    st.write(f"Accuracy: {accuracy:.4f}")
-            except Exception as e:
-                 st.error(f"An error occurred during model evaluation: {e}")
+                     from sklearn.metrics import confusion_matrix, roc_curve, auc, precision_recall_curve, classification_report #Import here to avoid library bloat
+                     accuracy = accuracy_score(y_test, y_pred)
+                     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")