Comparision with sklearn metrics done - testing

eval/metrics.py

@@ -29,12 +29,12 @@ def f1_score(y_true, y_pred, labels, average):
             f_score = calculate_f1_score(precision, recall)
             f1_sum += f_score
             if average is None:
-                f1_score_list.append(Result(precision, recall, average, item['label'], round(f_score, 3)))
+                f1_score_list.append(Result(precision, recall, average, item['label'], round(f_score, 4)))
 
         if average is None:
             return f1_score_list
         elif average == const.AVG_MACRO:
-            return [Result(None, None, average, None, round(f1_sum / len(pr_list), 3))]
+            return [Result(None, None, average, None, round(f1_sum / len(pr_list), 4))]
 
     elif average == const.AVG_MICRO:
         aggregate_tp = 0
@@ -51,7 +51,7 @@ def f1_score(y_true, y_pred, labels, average):
         agg_recall = get_recall(aggregate_tp, aggregate_fn)
 
         agg_f1_score = calculate_f1_score(agg_precision, agg_recall)
-        return [Result(agg_precision, agg_recall, average, None, round(agg_f1_score, 3))]
+        return [Result(agg_precision, agg_recall, average, None, round(agg_f1_score, 4))]
 
     return None
 

testing/eval_testing.py

@@ -1,5 +1,6 @@
 from eval.metrics import f1_score
 import utils.constants as const
+from sklearn.metrics import f1_score as f1
 
 y_true = ['positive', 'positive', 'negative', 'negative', 'positive', 'positive', 'negative', 'negative', 'positive', 'positive', 'negative', 'negative', 'positive', 'positive', 'negative', 'negative']
 y_pred = ['positive', 'negative', 'negative', 'positive', 'positive', 'negative', 'negative', 'positive', 'positive', 'negative', 'negative', 'positive', 'positive', 'negative', 'negative', 'negative']
@@ -9,7 +10,11 @@ result_list = f1_score(y_true, y_pred, ['positive', 'negative'], const.AVG_MICRO
 for result in result_list:
     result.print_result()
 
+print('SK Learn F1 Score (MICRO):: ', f1(y_true, y_pred, ['positive', 'negative'], average='micro'))
+
 result_list = f1_score(y_true, y_pred, ['positive', 'negative'], const.AVG_MACRO)
 
 for result in result_list:
     result.print_result()
+
+print('SK Learn F1 Score (MACRO):: ', f1(y_true, y_pred, ['positive', 'negative'], average='macro'))