def setup_catalogue(dirname, dataset_name='olfactory_bulb'): if os.path.exists(dirname): shutil.rmtree(dirname) dataio = DataIO(dirname=dirname) localdir, filenames, params = download_dataset(name=dataset_name) dataio.set_data_source(type='RawData', filenames=filenames, **params) if dataset_name=='olfactory_bulb': channels = [5, 6, 7, 8, 9] else: channels = [0,1,2,3] dataio.add_one_channel_group(channels=channels) catalogueconstructor = CatalogueConstructor(dataio=dataio) params = { 'duration' : 60., 'preprocessor' : { 'highpass_freq' : 300., 'chunksize' : 1024, 'lostfront_chunksize' : 100, }, 'peak_detector' : { 'peak_sign' : '-', 'relative_threshold' : 7., 'peak_span_ms' : 0.5, }, 'extract_waveforms' : { 'wf_left_ms' : -2.5, 'wf_right_ms' : 4.0, 'nb_max' : 10000, }, 'clean_waveforms' : { 'alien_value_threshold' : 60., }, 'noise_snippet' : { 'nb_snippet' : 300, }, 'feature_method': 'global_pca', 'feature_kargs':{'n_components': 5}, 'cluster_method' : 'kmeans', 'cluster_kargs' : {'n_clusters': 12}, 'clean_cluster' : False, 'clean_cluster_kargs' : {}, } apply_all_catalogue_steps(catalogueconstructor, params, verbose=True) catalogueconstructor.trash_small_cluster() catalogueconstructor.order_clusters(by='waveforms_rms') catalogueconstructor.make_catalogue_for_peeler()
def test_make_catalogue(): if os.path.exists('test_catalogueconstructor'): shutil.rmtree('test_catalogueconstructor') dataio = DataIO(dirname='test_catalogueconstructor') localdir, filenames, params = download_dataset(name='olfactory_bulb') dataio.set_data_source(type='RawData', filenames=filenames, **params) #~ dataio.set_manual_channel_group(range(14)) dataio.set_manual_channel_group([5, 6, 7, 8, 9]) catalogueconstructor = CatalogueConstructor(dataio=dataio) catalogueconstructor.set_preprocessor_params(chunksize=1024, #signal preprocessor highpass_freq=300, backward_chunksize=1280, #peak detector peak_sign='-', relative_threshold=7, peak_span=0.0005, ) t1 = time.perf_counter() catalogueconstructor.estimate_signals_noise(seg_num=0, duration=10.) t2 = time.perf_counter() print('estimate_signals_noise', t2-t1) t1 = time.perf_counter() catalogueconstructor.run_signalprocessor() t2 = time.perf_counter() print('run_signalprocessor', t2-t1) print(catalogueconstructor) t1 = time.perf_counter() catalogueconstructor.extract_some_waveforms(n_left=-12, n_right=15, nb_max=10000) t2 = time.perf_counter() print('extract_some_waveforms', t2-t1) # PCA t1 = time.perf_counter() catalogueconstructor.project(method='pca', n_components=12, batch_size=16384) t2 = time.perf_counter() print('project', t2-t1) # cluster t1 = time.perf_counter() catalogueconstructor.find_clusters(method='kmeans', n_clusters=13) t2 = time.perf_counter() print('find_clusters', t2-t1) # trash_small_cluster catalogueconstructor.trash_small_cluster() catalogueconstructor.make_catalogue()
def test_trash_small_cluster(): dirname = 'test_cleancluster' restore_savepoint(dirname, savepoint='after_trash_low_extremum') dataio = DataIO(dirname=dirname) cc = CatalogueConstructor(dataio=dataio) t1 = time.perf_counter() cc.trash_small_cluster() t2 = time.perf_counter() print('trash_small_cluster', t2 - t1)
def setup_catalogue(): if os.path.exists('test_peeler'): shutil.rmtree('test_peeler') dataio = DataIO(dirname='test_peeler') localdir, filenames, params = download_dataset(name='olfactory_bulb') dataio.set_data_source(type='RawData', filenames=filenames, **params) dataio.add_one_channel_group(channels=[5, 6, 7, 8, 9]) catalogueconstructor = CatalogueConstructor(dataio=dataio) fullchain_kargs = { 'duration': 60., 'preprocessor': { 'highpass_freq': 300., 'chunksize': 1024, 'lostfront_chunksize': 100, }, 'peak_detector': { 'peak_sign': '-', 'relative_threshold': 7., 'peak_span': 0.0005, #~ 'peak_span' : 0.000, }, 'extract_waveforms': { 'n_left': -25, 'n_right': 40, 'nb_max': 10000, }, 'clean_waveforms': { 'alien_value_threshold': 60., }, 'noise_snippet': { 'nb_snippet': 300, }, } apply_all_catalogue_steps(catalogueconstructor, fullchain_kargs, 'global_pca', {'n_components': 12}, 'kmeans', {'n_clusters': 12}, verbose=True) catalogueconstructor.trash_small_cluster() catalogueconstructor.make_catalogue_for_peeler()
def test_catalogue_constructor(): if os.path.exists('test_catalogueconstructor'): shutil.rmtree('test_catalogueconstructor') dataio = DataIO(dirname='test_catalogueconstructor') localdir, filenames, params = download_dataset(name='olfactory_bulb') #~ localdir, filenames, params = download_dataset(name='locust') dataio.set_data_source(type='RawData', filenames=filenames, **params) channels = range(14) #~ channels=list(range(4)) dataio.add_one_channel_group(channels=channels, chan_grp=0) cc = CatalogueConstructor(dataio=dataio) for memory_mode in ['ram', 'memmap']: for mode in ['dense', 'sparse']: print('*' * 5) print('memory_mode', memory_mode, 'mode', mode) if mode == 'dense': peak_engine = 'numpy' peak_method = 'global' adjacency_radius_um = None elif mode == 'sparse': peak_engine = 'numpy' peak_method = 'geometrical' adjacency_radius_um = 450. cc.set_global_params( chunksize=1024, memory_mode=memory_mode, mode=mode, n_jobs=1, #~ adjacency_radius_um=adjacency_radius_um, ) cc.set_preprocessor_params( #signal preprocessor highpass_freq=300, lowpass_freq=5000., common_ref_removal=False, smooth_size=0, lostfront_chunksize=None) cc.set_peak_detector_params( #peak detector method=peak_method, engine=peak_engine, peak_sign='-', relative_threshold=7, peak_span_ms=0.5, adjacency_radius_um=adjacency_radius_um, ) t1 = time.perf_counter() cc.estimate_signals_noise(seg_num=0, duration=10.) t2 = time.perf_counter() print('estimate_signals_noise', t2 - t1) t1 = time.perf_counter() cc.run_signalprocessor(duration=10., detect_peak=True) t2 = time.perf_counter() print('run_signalprocessor_loop', t2 - t1) for seg_num in range(dataio.nb_segment): mask = cc.all_peaks['segment'] == seg_num print('seg_num', seg_num, 'nb peak', np.sum(mask)) # redetect peak cc.re_detect_peak(method=peak_method, engine=peak_engine, peak_sign='-', relative_threshold=5, peak_span_ms=0.7, adjacency_radius_um=adjacency_radius_um) for seg_num in range(dataio.nb_segment): mask = cc.all_peaks['segment'] == seg_num print('seg_num', seg_num, 'nb peak', np.sum(mask)) cc.set_waveform_extractor_params(n_left=-25, n_right=40) t1 = time.perf_counter() cc.clean_peaks(alien_value_threshold=100, mode='extremum_amplitude') t2 = time.perf_counter() print('clean_peaks extremum_amplitude', t2 - t1) t1 = time.perf_counter() cc.clean_peaks(alien_value_threshold=100, mode='full_waveform') t2 = time.perf_counter() print('clean_peaks full_waveforms', t2 - t1) t1 = time.perf_counter() cc.sample_some_peaks(mode='rand', nb_max=5000) t2 = time.perf_counter() print('sample_some_peaks', t2 - t1) print(cc) #extract_some_noise t1 = time.perf_counter() cc.extract_some_noise(nb_snippet=400) t2 = time.perf_counter() print('extract_some_noise', t2 - t1) if mode == 'dense': # PCA t1 = time.perf_counter() cc.extract_some_features(method='global_pca', n_components=12) t2 = time.perf_counter() print('project pca', t2 - t1) # cluster t1 = time.perf_counter() cc.find_clusters(method='kmeans', n_clusters=11) t2 = time.perf_counter() print('find_clusters', t2 - t1) elif mode == 'sparse': # PCA t1 = time.perf_counter() cc.extract_some_features(method='pca_by_channel', n_components_by_channel=3) t2 = time.perf_counter() print('project pca', t2 - t1) # cluster t1 = time.perf_counter() cc.find_clusters(method='pruningshears') t2 = time.perf_counter() print('find_clusters', t2 - t1) print(cc) t1 = time.perf_counter() cc.auto_split_cluster() t2 = time.perf_counter() print('auto_split_cluster', t2 - t1) t1 = time.perf_counter() cc.trash_not_aligned() t2 = time.perf_counter() print('trash_not_aligned', t2 - t1) t1 = time.perf_counter() cc.auto_merge_cluster() t2 = time.perf_counter() print('auto_merge_cluster', t2 - t1) t1 = time.perf_counter() cc.trash_low_extremum() t2 = time.perf_counter() print('trash_low_extremum', t2 - t1) t1 = time.perf_counter() cc.trash_small_cluster() t2 = time.perf_counter() print('trash_small_cluster', t2 - t1)