matrix_factorization.py 文件源码

def prepare_matrix(val, row_var, col_var):
        # Takes a vector of observed values and two categorical variables
        # and returns a sparse matrix in coo format that can be used to
        # instantiate the class. Also returned are dictionaries that maps the
        # row and column categories to indices of a matrix
        #
        # Params:
        # val, row_var, col_var: numpy arrays

        row_id = row_var.unique()
        col_id = col_var.unique()
        nrow = row_id.size
        ncol = col_id.size

        # Associate each of the unique id names to a row and column index.
        row_id_map = {row_id[index]: index for index in range(len(row_id))}
        col_id_map = {col_id[index]: index for index in range(len(col_id))}

        row_indices = np.array([row_id_map[id] for id in row_var])
        col_indices = np.array([col_id_map[id] for id in col_var])
        y_coo = scipy.sparse.coo_matrix((val, (row_indices, col_indices)), shape=(nrow, ncol))

        return y_coo, row_id_map, col_id_map