llc.py 文件源码

def transform(self, X):
        """Compute the LLC representation of the provided data.

        Parameters
        ----------
        X : array_like or list
            The local features to aggregate. They must be either nd arrays or
            a list of nd arrays. In case of a list each item is aggregated
            separately.
        """
        # Get the local features and the number of local features per document
        X, lengths = self._reshape_local_features(X)

        # Preprocess the lengths list into indexes in the local feature array
        starts = np.cumsum([0] + lengths).astype(int)
        ends = np.cumsum(lengths).astype(int)

        # Calculate the nearest neighbors
        centroids = self._clusterer.cluster_centers_
        distances = pairwise_distances(X, centroids)
        K = self.neighbors
        neighbors = np.argpartition(distances, K)[:, :K]

        # Compute the llc representation
        llc = np.zeros((len(lengths), self.n_codewords))
        L2 = self.beta * np.eye(X.shape[1])
        for i, (s, e) in enumerate(zip(starts, ends)):
            for j in range(s, e):
                # a = argmin_{1^T a = 1} ||x - Ca||_2^2 + \beta ||a||_2^2
                C = centroids[neighbors[j]]
                a = C.dot(np.linalg.inv(C.T.dot(C) + L2)).dot(X[j])
                llc[i, neighbors[j]] = np.maximum(
                    llc[i, neighbors[j]],
                    a / a.sum()
                )

        return llc