Adding another check to see if live before computing dset peek

data_measurements/dataset_statistics.py

@@ -554,11 +554,12 @@ class DatasetStatisticsCacheClass:
             with open(self.dset_peek_json_fid, "r") as f:
                 self.dset_peek = json.load(f)["dset peek"]
         else:
-            if self.dset is None:
-                self.get_base_dataset()
-            self.dset_peek = self.dset[:100]
-            if save:
-                write_json({"dset peek": self.dset_peek}, self.dset_peek_json_fid)
+            if not self.live:
+                if self.dset is None:
+                    self.get_base_dataset()
+                self.dset_peek = self.dset[:100]
+                if save:
+                    write_json({"dset peek": self.dset_peek}, self.dset_peek_json_fid)
 
     def load_or_prepare_tokenized_df(self, save=True):
         if self.use_cache and exists(self.tokenized_df_fid):