Update oneclass.py

oneclass.py

@@ -0,0 +1,21 @@
+from sklearn.cluster import AgglomerativeClustering
+from sklearn.metrics import pairwise_distances
+import numpy as np
+import pandas as pd
+
+# Cosine distance clustering with BERT embeddings
+cosine_distances_bert = pairwise_distances(bert_embeddings_unlabeled, bert_embeddings_positive, metric='cosine')
+cosine_distances_bert_square = pairwise_distances(bert_embeddings_unlabeled, metric='cosine')
+clustering_cosine_bert = AgglomerativeClustering(n_clusters=None, distance_threshold=0.2, affinity='precomputed', linkage='average')
+clustering_cosine_bert.fit(cosine_distances_bert_square)
+unlabeled_clusters_cosine_bert = clustering_cosine_bert.labels_
+
+# Function to get recommended paper indices based on clustering
+def get_recommended_papers_indices(unlabeled_clusters, unlabeled_distances, top_n=20):
+    recommended_indices = []
+    for cluster_id in np.unique(unlabeled_clusters):
+        cluster_indices = np.where(unlabeled_clusters == cluster_id)[0]
+        cluster_distances = unlabeled_distances[cluster_indices].min(axis=1)
+        sorted_indices = cluster_indices[np.argsort(cluster_distances)]
+        recommended_indices.extend(sorted_indices[:top_n])
+    return recommended_indices