Milad Alshomary commited on
Commit
0e62aa1
·
1 Parent(s): bd0cb8d
Files changed (1) hide show
  1. cluster_corpus.py +8 -0
cluster_corpus.py CHANGED
@@ -65,6 +65,13 @@ def main():
65
  choices=['cosine', 'euclidean'],
66
  help="Distance metric for DBSCAN clustering."
67
  )
 
 
 
 
 
 
 
68
 
69
  args = parser.parse_args()
70
 
@@ -98,6 +105,7 @@ def main():
98
  background_corpus_df=clustered_df,
99
  test_corpus_df=clustered_test_df,
100
  embedding_clm=embedding_col_name,
 
101
  min_samples=args.min_samples,
102
  metric=args.metric
103
  )
 
65
  choices=['cosine', 'euclidean'],
66
  help="Distance metric for DBSCAN clustering."
67
  )
68
+ parser.add_argument(
69
+ "--eps_values",
70
+ type=float,
71
+ nargs='+',
72
+ default=None,
73
+ help="A list of specific eps values to test for DBSCAN. If not provided, a default range is used."
74
+ )
75
 
76
  args = parser.parse_args()
77
 
 
105
  background_corpus_df=clustered_df,
106
  test_corpus_df=clustered_test_df,
107
  embedding_clm=embedding_col_name,
108
+ eps_values=args.eps_values,
109
  min_samples=args.min_samples,
110
  metric=args.metric
111
  )