Update src/bin/target_family_classifier.py

src/bin/target_family_classifier.py

@@ -96,7 +96,7 @@ def score_protein_rep(dataset):
     train_index = train_index.dropna(axis=1)
     test_index = test_index.dropna(axis=1)
 
-    conf_matrices = []
+    #conf_matrices = []
 
     print('Producing protein family predictions...\n')
     for i in tqdm(range(10)):
@@ -122,29 +122,24 @@ def score_protein_rep(dataset):
         ac = accuracy_score(test_y, y_pred)
         accuracy.append(ac)
 
-        c_report = classification_report(test_y, y_pred, target_names=target_names, output_dict=True)
-        c_matrix = confusion_matrix(test_y, y_pred, labels=labels)
-        conf_matrices.append(c_matrix)
+        #c_report = classification_report(test_y, y_pred, target_names=target_names, output_dict=True)
+        #c_matrix = confusion_matrix(test_y, y_pred, labels=labels)
+        #conf_matrices.append(c_matrix)
 
-        class_report = class_based_scores(c_report, c_matrix)
+        #class_report = class_based_scores(c_report, c_matrix)
         mcc_score = matthews_corrcoef(test_y, y_pred)
         mcc.append(mcc_score)
         
-        report_list.append(class_report)
+        #report_list.append(class_report)
 
-    f1_perclass = pd.concat([r['f1-score'] for r in report_list], axis=1)
-    ac_perclass = pd.concat([r['accuracy'] for r in report_list], axis=1)
-    mcc_perclass = pd.concat([r['mcc'] for r in report_list], axis=1)
+    #f1_perclass = pd.concat([r['f1-score'] for r in report_list], axis=1)
+    #ac_perclass = pd.concat([r['accuracy'] for r in report_list], axis=1)
+    #mcc_perclass = pd.concat([r['mcc'] for r in report_list], axis=1)
 
     results = {
         "f1": f1,
         "accuracy": accuracy,
         "mcc": mcc,
-        "confusion_matrices": conf_matrices,
-        "class_reports": report_list,
-        "f1_per_class": f1_perclass,
-        "accuracy_per_class": ac_perclass,
-        "mcc_per_class": mcc_perclass
     }
 
     return results