neighbors.py 文件源码

def fit(self, X, y):
        """Fit the model using X as training data
        Parameters
        ----------
        X : {array-like, sparse matrix, BallTree, KDTree}
            Training data, shape [n_samples, n_features],

        """
        X = check_array(X, accept_sparse='csr')
        y = np.asarray(y, dtype='int')
        y_unique = np.unique(y)

        index = np.arange(len(y), dtype='int')

        if len(y_unique) == 0:
            raise ValueError('The training set must have at least '
                             'one document category!')

        # define nearest neighbors search objects for each category
        self._mod = [NearestNeighbors(n_neighbors=1,
                                      leaf_size=self.leaf_size,
                                      algorithm=self.algorithm,
                                      n_jobs=self.n_jobs,
                                      # euclidean metric by default
                                      metric='cosine',
                                      ) for el in range(len(y_unique))]

        index_mapping = []
        for imod, y_val in enumerate(y_unique):
            mask = (y == y_val)
            index_mapping.append(index[mask])
            self._mod[imod].fit(X[mask])

        self.index_mapping = index_mapping