word_movers_knn.py 文件源码

def _wmd(self, i, row, X_train):
        """Compute the WMD between training sample i and given test row.

        Assumes that `row` and train samples are sparse BOW vectors summing to 1.
        """
        union_idx = np.union1d(X_train[i].indices, row.indices) - 1
        W_minimal = self.W_embed[union_idx]
        W_dist = euclidean_distances(W_minimal)
        bow_i = X_train[i, union_idx].A.ravel()
        bow_j = row[:, union_idx].A.ravel()
        return emd(bow_i, bow_j, W_dist)