utils_nlp/eval/SentEval/senteval/sick.py [56:80]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        return sick_data

    def run(self, params, batcher):
        sick_embed = {'train': {}, 'dev': {}, 'test': {}}
        bsize = params.batch_size

        for key in self.sick_data:
            logging.info('Computing embedding for {0}'.format(key))
            # Sort to reduce padding
            sorted_corpus = sorted(zip(self.sick_data[key]['X_A'],
                                       self.sick_data[key]['X_B'],
                                       self.sick_data[key]['y']),
                                   key=lambda z: (len(z[0]), len(z[1]), z[2]))

            self.sick_data[key]['X_A'] = [x for (x, y, z) in sorted_corpus]
            self.sick_data[key]['X_B'] = [y for (x, y, z) in sorted_corpus]
            self.sick_data[key]['y'] = [z for (x, y, z) in sorted_corpus]

            for txt_type in ['X_A', 'X_B']:
                sick_embed[key][txt_type] = []
                for ii in range(0, len(self.sick_data[key]['y']), bsize):
                    batch = self.sick_data[key][txt_type][ii:ii + bsize]
                    embeddings = batcher(params, batch)
                    sick_embed[key][txt_type].append(embeddings)
                sick_embed[key][txt_type] = np.vstack(sick_embed[key][txt_type])
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



utils_nlp/eval/SentEval/senteval/sick.py [160:184]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        return sick_data

    def run(self, params, batcher):
        sick_embed = {'train': {}, 'dev': {}, 'test': {}}
        bsize = params.batch_size

        for key in self.sick_data:
            logging.info('Computing embedding for {0}'.format(key))
            # Sort to reduce padding
            sorted_corpus = sorted(zip(self.sick_data[key]['X_A'],
                                       self.sick_data[key]['X_B'],
                                       self.sick_data[key]['y']),
                                   key=lambda z: (len(z[0]), len(z[1]), z[2]))

            self.sick_data[key]['X_A'] = [x for (x, y, z) in sorted_corpus]
            self.sick_data[key]['X_B'] = [y for (x, y, z) in sorted_corpus]
            self.sick_data[key]['y'] = [z for (x, y, z) in sorted_corpus]

            for txt_type in ['X_A', 'X_B']:
                sick_embed[key][txt_type] = []
                for ii in range(0, len(self.sick_data[key]['y']), bsize):
                    batch = self.sick_data[key][txt_type][ii:ii + bsize]
                    embeddings = batcher(params, batch)
                    sick_embed[key][txt_type].append(embeddings)
                sick_embed[key][txt_type] = np.vstack(sick_embed[key][txt_type])
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -