kneighbour_l2r_classifier.py 文件源码

def _extract_and_write(self, X, neighbor_id_lists, distances_to_neighbors, fileName = "l2r_train", y = None):

        labels_in_neighborhood = Parallel(n_jobs=self.n_jobs)(
            delayed(_create_training_samples)(cur_doc, neighbor_list, X, y, cur_doc + 1, distances_to_neighbors, 
                                              self.count_concepts, self.count_terms, self.number_of_concepts, 
                                              self.ibm1 if self.n_jobs == 1 and self.translation_probability else None) for cur_doc, neighbor_list in enumerate(neighbor_id_lists))


        doc_to_neighborhood_dict = self._merge_dicts(labels_in_neighborhood)

        filenames = ["samples_" + str(qid + 1) + ".tmp" for qid in range(len(doc_to_neighborhood_dict))]
        with open(fileName, 'w') as outfile:
            for fname in filenames:
                with open(fname) as infile:
                    for line in infile:
                        outfile.write(line)
                outfile.write('\n')

        return doc_to_neighborhood_dict