Spaces:
Sleeping
Sleeping
Create similarityCalculator.py
Browse files- similarityCalculator.py +42 -0
similarityCalculator.py
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import os
|
| 2 |
+
from sklearn.metrics.pairwise import cosine_similarity
|
| 3 |
+
import numpy as np
|
| 4 |
+
|
| 5 |
+
class SimilarityCalculator:
|
| 6 |
+
"""
|
| 7 |
+
Class for calculating cosine similarity between embeddings.
|
| 8 |
+
"""
|
| 9 |
+
def __init__(self):
|
| 10 |
+
pass
|
| 11 |
+
|
| 12 |
+
def compute_similarity(template_embeddings: np.ndarray, contract_embeddings: np.ndarray) -> np.ndarray:
|
| 13 |
+
"""
|
| 14 |
+
Compute cosine similarity between template and contract embeddings.
|
| 15 |
+
|
| 16 |
+
Args:
|
| 17 |
+
template_embeddings (np.ndarray): A NumPy array of template embeddings.
|
| 18 |
+
contract_embeddings (np.ndarray): A NumPy array of contract embeddings.
|
| 19 |
+
|
| 20 |
+
Returns:
|
| 21 |
+
np.ndarray: A NumPy array of similarity scores between contracts and templates.
|
| 22 |
+
"""
|
| 23 |
+
return cosine_similarity(contract_embeddings, template_embeddings)
|
| 24 |
+
|
| 25 |
+
def clear_folder(path):
|
| 26 |
+
if not os.path.exists(path):
|
| 27 |
+
os.makedirs(path) # Create the directory if it doesn't exist
|
| 28 |
+
for file in os.listdir(path):
|
| 29 |
+
file_path = os.path.join(path, file)
|
| 30 |
+
try:
|
| 31 |
+
if os.path.isfile(file_path):
|
| 32 |
+
os.unlink(file_path)
|
| 33 |
+
except Exception as e:
|
| 34 |
+
print(f"Failed to delete {file_path}: {e}")
|
| 35 |
+
|
| 36 |
+
def save_uploaded_file(uploaded_file, path):
|
| 37 |
+
try:
|
| 38 |
+
with open(os.path.join(path, uploaded_file.name), "wb") as f:
|
| 39 |
+
f.write(uploaded_file.getbuffer())
|
| 40 |
+
return True
|
| 41 |
+
except:
|
| 42 |
+
return False
|