ng.py 文件源码

def encode(self, data, metric='euclidean'):
        """ Employ a nearest-neighbor rule to encode the given ``data`` using the codebook.

        Parameters
        ----------
        data : real array-like, shape(n_samples, n_features)
            Data matrix, each row represents a sample.

        metric : string
            One of the following valid options as defined for function http://scikit-learn.org/stable/modules/generated/sklearn.metrics.pairwise.pairwise_distances.html.

            Valid options include:

             - euclidean
             - cityblock
             - l1
             - cosine

        Returns
        -------
        encoded_data : real array-like, shape(n_samples, n_features)
            ``data``, as represented by the prototypes in codebook.
        ts_symbols : list, shape(n_samples, 1)
            A discrete symbolic time series
        """
        # Perform a proposed data mining procedure as described in [Laskaris2004].
        mds = MDS(1, random_state=self.rng)
        protos_1d = mds.fit_transform(self.protos).ravel()
        sorted_protos_1d = np.argsort(protos_1d)

        sprotos = self.protos[sorted_protos_1d]

        nbrs = NearestNeighbors(n_neighbors=1, algorithm='auto', metric=metric).fit(sprotos)
        _, self.__symbols = nbrs.kneighbors(data)
        self.__encoding = sprotos[self.__symbols]

        return (self.__encoding, self.__symbols)