evaluate_new.py 文件源码

def evaluate_pca(dataset, iterator, args):
    # Select features
    if args.features is not None and args.features != dataset.feature_names:
        print('selecting features ...')
        features = _explode_features(args.features)
        start = timeit.default_timer()
        dataset = dataset.dataset_from_feature_names(features)
        print('done, took %fs' % (timeit.default_timer() - start))
    print('')

    pca_components = range(1, dataset.n_features)
    total_steps = len(pca_components)
    if 'pca' not in args.transformers:
        args.transformers.append('pca')

    curr_step = 0
    measures = []
    for n_components in pca_components:
        curr_step += 1
        prefix = '%.3d' % curr_step
        print('(%.3d/%.3d) evaluating with %d pca components ...' % (curr_step, total_steps, n_components))
        start = timeit.default_timer()
        try:
            args.pca_components = n_components

            ll_stats = _compute_averaged_pos_and_neg_lls(dataset, iterator, prefix, args)
            measure = _compute_measure(ll_stats, dataset, args)
        except:
            measure = np.nan
        if measure is np.isnan(measure):
            print('measure: not computable')
        else:
            print('measure: %f' % measure)

            # Correct score. The problem is that it is computed given the dataset, which has too many features.
            measure = (measure * float(dataset.n_features)) / float(n_components)
        measures.append(measure)
        print('done, took %fs' % (timeit.default_timer() - start))
        print('')
    assert len(pca_components) == len(measures)

    best_idx = np.nanargmax(np.array(measures))  # get the argmax ignoring NaNs
    print('best result with score %f: %d PCA components' % (measures[best_idx], pca_components[best_idx]))
    print('detailed reports have been saved')

    # Save results
    if args.output_dir is not None:
        filename = '_results.csv'
        with open(os.path.join(args.output_dir, filename), 'wb') as f:
            writer = csv.writer(f, delimiter=';')
            writer.writerow(['', 'idx', 'measure', 'components'])
            for idx, (measure, n_components) in enumerate(zip(measures, pca_components)):
                selected = '*' if best_idx == idx else ''
                writer.writerow([selected, '%d' % idx, '%f' % measure, '%d' % n_components])