bench_plot_incremental_pca.py 文件源码

def fixed_batch_size_comparison(data):
    all_features = [i.astype(int) for i in np.linspace(data.shape[1] // 10,
                                                       data.shape[1], num=5)]
    batch_size = 1000
    # Compare runtimes and error for fixed batch size
    all_times = defaultdict(list)
    all_errors = defaultdict(list)
    for n_components in all_features:
        pca = PCA(n_components=n_components)
        rpca = RandomizedPCA(n_components=n_components, random_state=1999)
        ipca = IncrementalPCA(n_components=n_components, batch_size=batch_size)
        results_dict = {k: benchmark(est, data) for k, est in [('pca', pca),
                                                               ('ipca', ipca),
                                                               ('rpca', rpca)]}

        for k in sorted(results_dict.keys()):
            all_times[k].append(results_dict[k]['time'])
            all_errors[k].append(results_dict[k]['error'])

    plot_feature_times(all_times, batch_size, all_features, data)
    plot_feature_errors(all_errors, batch_size, all_features, data)