token_container.py 文件源码

def index(self, metric='cosine'):
        """ Build a nearest neighbor retrieval index to perform similarity 
        lookups and analogies

        Arguments:
            metric: string, or sklearn compatible callable

        Returns:
            self

        Raises:
            TokenContainerException if no pretrained vectors have been loaded
        """

        if self.W is not None:
            alg = 'brute' if (metric == 'cosine') else 'auto'
            from sklearn.neighbors import NearestNeighbors
            self._nn = NearestNeighbors(metric=metric, algorithm=alg)
            self._nn.fit(self.W)
        else:
            raise TokenContainerException(
                'cannot build similarity on vectorless structure'
            )
        return self