Added another function to recommend

ucsinfer/gather.py

@@ -1,12 +1,24 @@
 from datasets import Dataset, Features, Value, ClassLabel, DatasetInfo
 from datasets.dataset_dict import DatasetDict
 
-from typing import Generator, Any
+from typing import Iterator
+
+from tabulate import tabulate
+
+def print_dataset_stats(dataset: DatasetDict, catlist: list[str]):
+    
+    data_table = []
+    data_table.append([["Total records in combined dataset:",  len(dataset)]])
+    data_table.append([["Total records in `train`:", len(dataset['train'])]])
+
+    tab = tabulate(data_table)
+
+    print(tab)
 
 # https://www.sbert.net/docs/sentence_transformer/loss_overview.html 
 
 def build_sentence_class_dataset(
-        records: Generator[tuple[str, str], Any, None], 
+        records: Iterator[tuple[str, str]], 
         catlist: list[str]) -> DatasetDict:
     """
     Create a new dataset for `records` which contains (sentence, class) pairs.