grouping filetypes
diff --git a/DeReKo/explore_dereko.py b/DeReKo/explore_dereko.py
index ee56ee9..cb6bf51 100644
--- a/DeReKo/explore_dereko.py
+++ b/DeReKo/explore_dereko.py
@@ -1,4 +1,4 @@
-import glob
+import glob,re
from collections import defaultdict
DEREKO_DIR = "/export/netapp/kupietz/N-GRAMM-STUDIE/conllu/"
@@ -15,6 +15,7 @@
filenames = get_filenames(DEREKO_DIR)
for fn in filenames:
prefix = fn.split(".")[0]
+ prefix = re.findall("\D+", prefix)[0]
file_groups[prefix].append(fn)
for group,files in file_groups.items():
print(group, len(files))
\ No newline at end of file