Generated first ROC curve to see behavior

model_selection/cv_metric_gen.py

@@ -175,8 +175,8 @@ if __name__ == "__main__":
     # Metric generation through cv for tuned models3
     # --------------------------------------------------------------------------------------------------------
     scores_sheets = {} # To store score dfs as sheets in the same excel file
-    for i, group in enumerate(['pre', 'post']):
-        for j, method in enumerate(['', '', 'over_', 'under_']):
+    for i, group in enumerate(['pre']): # 'post'
+        for j, method in enumerate(['']): # '', 'over_', 'under_'
             # print(f"{group}-{method_names[j]}")
             # Get train dataset based on group and method
             X_train = data_dic['X_train_' + method + group]
@@ -191,28 +191,29 @@ if __name__ == "__main__":
                 axes = [axes]
             # Metric generation for each model
             for model_idx, (model_name, model) in enumerate(models.items()):
-                print(f"{group}-{method_names[j]}-{model_name}")
-                # Retrieve cv scores for our metrics of interest
-                scores = cross_validate(model, X_train, y_train, scoring=scorings, cv=cv, return_train_score=True, n_jobs=10)
-                # Save results of each fold
-                for metric_name in scorings.keys():
-                    scores_df.loc[model_name + f'_{metric_name}']=list(np.around(np.array(scores[f"test_{metric_name}"]),4)) 
-                # Generate ROC curves
-                mean_fpr = np.linspace(0, 1, 100)
-                tprs, aucs = [], []
-                # Loop through each fold in the cross-validation
-                for fold_idx, (train, test) in enumerate(cv.split(X_train, y_train)):
-                    # Fit the model on the training data
-                    model.fit(X_train[train], y_train[train])
-                    # Use RocCurveDisplay to generate the ROC curve
-                    roc_display = RocCurveDisplay.from_estimator(model, X_train[test], y_train[test], 
-                                                                name=f"ROC fold {fold_idx}", alpha=0.3, lw=1, ax=axes[model_idx])
-                    # Interpolate the true positive rates to get a smooth curve
-                    interp_tpr = np.interp(mean_fpr, roc_display.fpr, roc_display.tpr)
-                    interp_tpr[0] = 0.0
-                    # Append the interpolated TPR and AUC for this fold
-                    tprs.append(interp_tpr)
-                    aucs.append(roc_display.roc_auc)
+                if model_name == 'DT':
+                    print(f"{group}-{method_names[j]}-{model_name}")
+                    # Retrieve cv scores for our metrics of interest
+                    scores = cross_validate(model, X_train, y_train, scoring=scorings, cv=cv, return_train_score=True, n_jobs=10)
+                    # Save results of each fold
+                    for metric_name in scorings.keys():
+                        scores_df.loc[model_name + f'_{metric_name}']=list(np.around(np.array(scores[f"test_{metric_name}"]),4)) 
+                    # Generate ROC curves
+                    mean_fpr = np.linspace(0, 1, 100)
+                    tprs, aucs = [], []
+                    # Loop through each fold in the cross-validation
+                    for fold_idx, (train, test) in enumerate(cv.split(X_train, y_train)):
+                        # Fit the model on the training data
+                        model.fit(X_train[train], y_train[train])
+                        # Use RocCurveDisplay to generate the ROC curve
+                        roc_display = RocCurveDisplay.from_estimator(model, X_train[test], y_train[test], 
+                                                                    name=f"ROC fold {fold_idx}", alpha=0.3, lw=1, ax=axes[model_idx])
+                        # Interpolate the true positive rates to get a smooth curve
+                        interp_tpr = np.interp(mean_fpr, roc_display.fpr, roc_display.tpr)
+                        interp_tpr[0] = 0.0
+                        # Append the interpolated TPR and AUC for this fold
+                        tprs.append(interp_tpr)
+                        aucs.append(roc_display.roc_auc)
                 # Plot the diagonal line representing random guessing
                 axes[model_idx].plot([0, 1], [0, 1], linestyle='--', lw=2, color='r', alpha=.8)
                 # Compute the mean and standard deviation of the TPRs
@@ -220,19 +221,16 @@ if __name__ == "__main__":
                 mean_tpr[-1] = 1.0
                 mean_auc = auc(mean_fpr, mean_tpr)  # Calculate the mean AUC
                 std_auc = np.std(aucs)
-
                 # Plot the mean ROC curve
                 axes[model_idx].plot(mean_fpr, mean_tpr, color='b',
                                     label=r'Mean ROC (AUC = %0.2f $\pm$ %0.2f)' % (mean_auc, std_auc),
                                     lw=2, alpha=.8)
-
                 # Plot the standard deviation of the TPRs
                 std_tpr = np.std(tprs, axis=0)
                 tprs_upper = np.minimum(mean_tpr + std_tpr, 1)
                 tprs_lower = np.maximum(mean_tpr - std_tpr, 0)
                 axes[model_idx].fill_between(mean_fpr, tprs_lower, tprs_upper, color='grey', alpha=.2,
                                             label=r'$\pm$ 1 std. dev.')
-
                 # Set plot limits and title
                 axes[model_idx].set(xlim=[-0.05, 1.05], ylim=[-0.05, 1.05],
                                     title=f"ROC Curve - {model_name} ({group}-{method_names[j]})")