def run()

in senteval/sts.py [0:0]

• 38 lines of code
• 9 McCabe index (conditional complexity)

    def run(self, params, batcher):
        results = {}
        for dataset in self.datasets:
            sys_scores = []
            input1, input2, gs_scores = self.data[dataset]
            for ii in range(0, len(gs_scores), params.batch_size):
                batch1 = input1[ii:ii + params.batch_size]
                batch2 = input2[ii:ii + params.batch_size]

                # we assume get_batch already throws out the faulty ones
                if len(batch1) == len(batch2) and len(batch1) > 0:
                    enc1 = batcher(params, batch1)
                    enc2 = batcher(params, batch2)

                    for kk in range(enc2.shape[0]):
                        sys_score = self.similarity(enc1[kk], enc2[kk])
                        sys_scores.append(sys_score)

            results[dataset] = {'pearson': pearsonr(sys_scores, gs_scores),
                                'spearman': spearmanr(sys_scores, gs_scores),
                                'nsamples': len(sys_scores)}
            logging.debug('%s : pearson = %.4f, spearman = %.4f' %
                          (dataset, results[dataset]['pearson'][0],
                           results[dataset]['spearman'][0]))

        weights = [results[dset]['nsamples'] for dset in results.keys()]
        list_prs = np.array([results[dset]['pearson'][0] for
                            dset in results.keys()])
        list_spr = np.array([results[dset]['spearman'][0] for
                            dset in results.keys()])

        avg_pearson = np.average(list_prs)
        avg_spearman = np.average(list_spr)
        wavg_pearson = np.average(list_prs, weights=weights)
        wavg_spearman = np.average(list_spr, weights=weights)

        results['all'] = {'pearson': {'mean': avg_pearson,
                                      'wmean': wavg_pearson},
                          'spearman': {'mean': avg_spearman,
                                       'wmean': wavg_spearman}}
        logging.debug('ALL (weighted average) : Pearson = %.4f, \
            Spearman = %.4f' % (wavg_pearson, wavg_spearman))
        logging.debug('ALL (average) : Pearson = %.4f, \
            Spearman = %.4f\n' % (avg_pearson, avg_spearman))

        return results