spb/wp2_uqo Public

1# Author: Simon-Pierre Boucher — contact@spboucher.ai2#3"""Sentence embeddings and cosine-similarity features."""45import numpy as np67from . import config8from .references import REFERENCES, SIM_COLS91011def encode_references(model=None):12    """Encode the 20 reference descriptions. Returns (names, embeddings)."""13    if model is None:14        from sentence_transformers import SentenceTransformer15        model = SentenceTransformer(config.EMBEDDING_MODEL)16    names = list(REFERENCES.keys())17    embeddings = model.encode(list(REFERENCES.values()), normalize_embeddings=True)18    return names, embeddings192021def encode_remarks(texts, model=None, show_progress=True):22    """Encode listing descriptions with the paper's embedding model."""23    if model is None:24        from sentence_transformers import SentenceTransformer25        model = SentenceTransformer(config.EMBEDDING_MODEL)26    return model.encode(27        list(texts),28        batch_size=config.ENCODE_BATCH_SIZE,29        show_progress_bar=show_progress,30        normalize_embeddings=True,31    )323334def load_or_encode_remarks(texts, cache_path=config.EMBEDDINGS_NPY, force=False):35    """Load cached embeddings if they match the sample size, else encode.3637    Embeddings are deterministic for a given model version, so the cache is a38    pure speed-up; pass force=True to re-encode from scratch.39    """40    if not force and cache_path.exists():41        cached = np.load(cache_path)42        if len(cached) == len(texts):43            return cached, True44    embeddings = encode_remarks(texts)45    cache_path.parent.mkdir(parents=True, exist_ok=True)46    np.save(cache_path, embeddings)47    return embeddings, False484950def similarity_features(prop_embeddings, ref_embeddings):51    """Cosine similarities (dot product of normalized vectors): n x 20 matrix."""52    return prop_embeddings @ ref_embeddings.T535455def add_similarity_columns(df, sim_matrix):56    """Attach the 20 ``sim_<slug>`` columns to the DataFrame (in place)."""57    for i, col in enumerate(SIM_COLS):58        df[col] = sim_matrix[:, i]59    return df60