Add create clusters init vers

This commit is contained in:
William Jeynes
2026-04-09 14:25:43 +01:00
parent ac49351425
commit 2326e61457
3 changed files with 200 additions and 10 deletions
+2 -2
View File
@@ -10,10 +10,10 @@ from sklearn.metrics.pairwise import cosine_similarity
from tqdm import tqdm
INPUT_CSV = "../../data/dataset-dev.csv"
INPUT_CSV = "../../data/dataset.csv"
OUTPUT_JSON = "../../data/clustered_output.json"
MODEL_NAME = "all-MiniLM-L6-v2"
SIMILARITY_THRESHOLD = 0.65
SIMILARITY_THRESHOLD = 0.8
def generate_guid():
return str(uuid.uuid4())