feature_grid_search.py 文件源码

def generate_laplacian_score_scalar(X_ent, X_word, kNeighbors):
    # Generate cosine similarity graph
    n = X_ent.shape[0]
    cosX = cosine_similarity(X_word)
    graph = np.zeros((n, n))
    for i in range(n):
        for j in np.argpartition(cosX[i], -kNeighbors)[-kNeighbors:]:
            if j == i:
                continue
            graph[i, j] = cosX[i, j]
            graph[j, i] = cosX[i, j]

    D = sparse.diags([graph.sum(axis=0)], [0])
    L = D - graph
    f_tilde = X_ent - (float(X_ent.transpose() * D * np.ones((n, 1))) / D.sum().sum()) * np.ones((n, 1))
    score = float(f_tilde.transpose() * L * f_tilde) / float(f_tilde.transpose() * D * f_tilde + 1e-10)
    laplacian_score = score
    return laplacian_score