\iLdZddlmZmZddlZddlmZddlm Z GddZ y)z2Pattern embedding module for vectorizing patterns.)ListUnionN)SentenceTransformer)PathceZdZdZd defdZdeedejfdZ deeedejfdZ de fd Z y ) PatternEmbedderz4Pattern embedder for converting patterns to vectors. model_namecttjjjjdz dz }t t ||_y)z{Initialize pattern embedder. Args: model_name: Name of the sentence transformer model modelszall-MiniLM-L6-v2N)r__file__resolveparentrstrmodel)selfr _MODEL_DIRs D/home/ubuntu/codebase/yexijia/保研/iCoLoc/src/learning/embedder.py__init__zPatternEmbedder.__init__ sC(^++-44;;BBXMPbb (Z9 patternreturncZdj|}|jj|S)zEncode a single pattern to vector. Args: pattern: List of feature types in the pattern Returns: Vector representation of the pattern  joinrencode)rrtexts rencode_patternzPatternEmbedder.encode_patterns'xx zz  &&rpatternsc~|Dcgc]}dj|}}|jj|Scc}w)zEncode multiple patterns to vectors. Args: patterns: List of patterns, each is a list of feature types Returns: Array of vectors, shape (n_patterns, embedding_dim) rr)rrptextss rencode_patternszPatternEmbedder.encode_patterns&s:'//h!h/zz  ''0s:c6|jjS)zlGet the dimension of sentence embeddings. Returns: Embedding dimension )r get_sentence_embedding_dimension)rs rr%z0PatternEmbedder.get_sentence_embedding_dimension2s zz::< :3 : 'd3i 'BJJ ' (T#Y (BJJ (=#=rr) r)typingrrnumpyr*sentence_transformersrpathlibrrr-rrr2s85.=.=r