update source code and pipeline

2025-09-04 14:39:02 +00:00
parent 9aabd991c5
commit 878310a551
82 changed files with 24373 additions and 0 deletions
--- a/filter/shuffle.py
+++ b/filter/shuffle.py
@@ -0,0 +1,12 @@
+import random
+
+import json
+
+with open('/home/nguyendc/sonnh/embedding-clustering/filter/008_label_data_sample_seed_1997.json', 'r') as f:
+    data = json.load(f)
+    
+random.seed(8272025)
+random.shuffle(data)
+
+with open('/home/nguyendc/sonnh/embedding-clustering/filter/032_shuffle_008.json', 'w') as f:
+    json.dump(data, f)