adding smote oversampling (#27)

fani-lab · Mar 7, 2023 · 4c3710e · 4c3710e
1 parent 0cd4acf
commit 4c3710e
Showing 1 changed file with 4 additions and 4 deletions.
diff --git a/src/utils/dataset.py b/src/utils/dataset.py
@@ -145,6 +145,10 @@ def vectorize(self, tokens_records, encoder):
         logger.debug("transforming of records into vectors is finished")
         return vectors
 
+    def oversample_by_smote(self):
+        smote = SMOTE(random_state=42)
+        self.data, self.labels = smote.fit_resample(self.data.to_dense(), self.labels)
+
     def __getitem__(self, index):
         return self.data[index], self.labels[index]
 
@@ -155,10 +159,6 @@ def __len__(self):
     def shape(self):
         return self.data.shape
 
-    def oversample_by_smote(self):
-        smote = SMOTE(random_state=42)
-        self.data, self.labels = smote.fit_resample(self.data.to_dense(), self.labels)
-
 
 
 class TimeBasedBagOfWordsDataset(BagOfWordsDataset):