import os import shutil import numpy as np import pandas as pd from scipy.signal import iirnotch, lfilter from data_utils import butter_bandpass_filter, correct_ecg_inversion import matplotlib.pyplot as plt from tqdm import tqdm import shutil import librosa import pickle import gc BASE_PATH = os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__))), 'datasets') SAMPLING_RATE = 200 TARGET_RESAMPLE = 100 NOTCH_FREQ = 60 EEG_LOWCUT = 0.3 EEG_HIGHCUT = 40 EMG_LOWCUT = 10 EMG_HIGHCUT = 1000 ECG_LOWCUT = 0.3 ECG_HIGHCUT = 70 FLOW_LOWCUT = 0 FLOW_HIGHCUT = 15 do_resample = (SAMPLING_RATE != TARGET_RESAMPLE) NUM_PROCESS = 4 import argparse import multiprocessing def process_ecg(args): sig, chn_grp, chn, split = args sig_path = os.path.join(BASE_PATH, cfg.data_dir, chn_grp, chn, sig) data = np.load(sig_path) # data = data.reshape(-1, 1) data = data.reshape(-1,) # Apply bandpass filter filtered = butter_bandpass_filter(data, ECG_LOWCUT, ECG_HIGHCUT, SAMPLING_RATE) b_notch, a_notch = iirnotch(NOTCH_FREQ, 30, SAMPLING_RATE) filtered = lfilter(b_notch, a_notch, filtered) filtered = filtered.reshape(-1, SAMPLING_RATE*30) filtered_epochs = [] for epoch in filtered: inv_epoch, _ = correct_ecg_inversion(epoch, SAMPLING_RATE) filtered_epochs.append(inv_epoch) filtered = np.stack(filtered_epochs, axis=0) if do_resample: filtered = np.reshape(filtered, (-1,1)) filtered = librosa.resample(filtered, orig_sr=SAMPLING_RATE, target_sr=TARGET_RESAMPLE, axis=0, res_type='soxr_qq') filtered = filtered.reshape(-1, TARGET_RESAMPLE*30) if cfg.save_type == 'npy': # Save processed data output_path = os.path.join(BASE_PATH, cfg.output_dir, split, chn_grp, chn, sig) os.makedirs(os.path.dirname(output_path), exist_ok=True) np.save(output_path, filtered.astype(np.float32)) return else: return filtered def process_eeg(args): sig, chn_grp, chn, split = args sig_path = os.path.join(BASE_PATH, cfg.data_dir, chn_grp, chn, sig) data = np.load(sig_path) # data = data.reshape(-1, 1) data = data.reshape(-1,) # Apply bandpass filter filtered = butter_bandpass_filter(data, EEG_LOWCUT, EEG_HIGHCUT, SAMPLING_RATE) b_notch, a_notch = iirnotch(NOTCH_FREQ, 30, SAMPLING_RATE) filtered = lfilter(b_notch, a_notch, filtered) if do_resample: filtered = librosa.resample(filtered, orig_sr=SAMPLING_RATE, target_sr=TARGET_RESAMPLE, axis=0, res_type='soxr_qq') filtered = filtered.reshape(-1, TARGET_RESAMPLE*30) if cfg.save_type == 'npy': # Save processed data output_path = os.path.join(BASE_PATH, cfg.output_dir, split, chn_grp, chn, sig) os.makedirs(os.path.dirname(output_path), exist_ok=True) np.save(output_path, filtered.astype(np.float32)) return else: return filtered def process_emg(args): sig, chn_grp, chn, split = args sig_path = os.path.join(BASE_PATH, cfg.data_dir, chn_grp, chn, sig) data = np.load(sig_path) # data = data.reshape(-1, 1) data = data.reshape(-1,) # Apply bandpass filter filtered = butter_bandpass_filter(data, EMG_LOWCUT, EMG_HIGHCUT, SAMPLING_RATE) b_notch, a_notch = iirnotch(NOTCH_FREQ, 30, SAMPLING_RATE) filtered = lfilter(b_notch, a_notch, filtered) if do_resample: filtered = librosa.resample(filtered, orig_sr=SAMPLING_RATE, target_sr=TARGET_RESAMPLE, axis=0, res_type='soxr_qq') filtered = filtered.reshape(-1, TARGET_RESAMPLE*30) if cfg.save_type == 'npy': # Save processed data output_path = os.path.join(BASE_PATH, cfg.output_dir, split, chn_grp, chn, sig) os.makedirs(os.path.dirname(output_path), exist_ok=True) np.save(output_path, filtered.astype(np.float32)) return else: return filtered def process_flow(args): sig, chn_grp, chn, split = args sig_path = os.path.join(BASE_PATH, cfg.data_dir, chn_grp, chn, sig) data = np.load(sig_path) # data = data.reshape(-1, 1) data = data.reshape(-1,) # Apply bandpass filter filtered = butter_bandpass_filter(data, FLOW_LOWCUT, FLOW_HIGHCUT, SAMPLING_RATE) # median filter? if do_resample: filtered = librosa.resample(filtered, orig_sr=SAMPLING_RATE, target_sr=TARGET_RESAMPLE, axis=0, res_type='soxr_qq') filtered = filtered.reshape(-1, TARGET_RESAMPLE*30) if cfg.save_type == 'npy': # Save processed data output_path = os.path.join(BASE_PATH, cfg.output_dir, split, chn_grp, chn, sig) os.makedirs(os.path.dirname(output_path), exist_ok=True) np.save(output_path, filtered.astype(np.float32)) return else: return filtered def save_mmap(results, sig_list, chn_grp, chn, split='train'): signame_list = [sig.split('.')[0] for sig in sig_list] epoch_lengths = [sig.shape[0] for sig in results] metadata = dict() sig_info = dict() start, end = 0, 0 for signame, sig in zip(signame_list, results): length = sig.shape[0] end = start + length info = dict() info['pos'] = (start, end) info['stats'] = {'sum': float(np.sum(sig)), 'sumsq': float(np.sum(sig ** 2))} sig_info[signame] = info start = end mmap_path = os.path.join(BASE_PATH, cfg.output_dir, split, chn_grp, f'{chn}.mmap') signals_cat = np.concatenate(results, axis=0).astype(np.float32) os.makedirs(os.path.dirname(mmap_path), exist_ok=True) data = np.memmap(mmap_path, dtype=np.float32, mode='w+', shape=signals_cat.shape) data[:] = signals_cat data.flush() metadata['sig_info'] = sig_info metadata['data_shape'] = signals_cat.shape info_path = os.path.join(BASE_PATH, cfg.output_dir, split, chn_grp, f'{chn}.pickle') with open(info_path, 'wb') as f: pickle.dump(metadata, f) del data def preprocess(sig_list, chn_grp=None, chn=None, split='train'): def _process(sig_list, chn_grp, chn, split): print(f"Processing {chn_grp}/{chn}") if chn_grp in ['EEG','EOG']: # sig_list = sorted(os.listdir(os.path.join(BASE_PATH, cfg.data_dir, chn_grp, chn))) input_list = [(sig, chn_grp, chn, split) for sig in sig_list] with multiprocessing.Pool(NUM_PROCESS) as pool: results = list(tqdm(pool.imap(process_eeg, input_list), total=len(input_list))) if cfg.save_type == 'mmap': save_mmap(results, sig_list, chn_grp, chn, split) del results elif chn_grp in ['EMG']: # sig_list = sorted(os.listdir(os.path.join(BASE_PATH, cfg.data_dir, chn_grp, chn))) input_list = [(sig, chn_grp, chn, split) for sig in sig_list] with multiprocessing.Pool(NUM_PROCESS) as pool: results = list(tqdm(pool.imap(process_emg, input_list), total=len(input_list))) if cfg.save_type == 'mmap': save_mmap(results, sig_list, chn_grp, chn, split) del results elif chn_grp in ['ECG']: # sig_list = sorted(os.listdir(os.path.join(BASE_PATH, cfg.data_dir, chn_grp, chn))) input_list = [(sig, chn_grp, chn, split) for sig in sig_list] with multiprocessing.Pool(NUM_PROCESS) as pool: results = list(tqdm(pool.imap(process_ecg, input_list), total=len(input_list))) if cfg.save_type == 'mmap': save_mmap(results, sig_list, chn_grp, chn, split) del results elif chn_grp in ['ABD', 'CHEST', 'AIRFLOW']: # sig_list = sorted(os.listdir(os.path.join(BASE_PATH, cfg.data_dir, chn_grp, chn))) input_list = [(sig, chn_grp, chn, split) for sig in sig_list] with multiprocessing.Pool(NUM_PROCESS) as pool: results = list(tqdm(pool.imap(process_flow, input_list), total=len(input_list))) if cfg.save_type == 'mmap': save_mmap(results, sig_list, chn_grp, chn, split) del results else: results = [] for sig in tqdm(sig_list): sig_path = os.path.join(BASE_PATH, cfg.data_dir, chn_grp, chn, sig) data = np.load(sig_path) if do_resample or chn == 'SaO2': data = data.reshape(-1, 1) if chn == 'SaO2': data = librosa.resample(data, orig_sr=SAMPLING_RATE, target_sr=1, axis=0, res_type='soxr_qq') data = data / 1e8 if round(np.max(data)) > 1 or round(np.min(data)) < 0: print(f"Warning: SaO2 values out of range: {sig} with min {np.min(data)} and max {np.max(data)}") data = data.reshape(-1, 1*30) else: data = librosa.resample(data, orig_sr=SAMPLING_RATE, target_sr=TARGET_RESAMPLE, axis=0, res_type='soxr_qq') data = data.reshape(-1, TARGET_RESAMPLE*30) # output_path = os.path.join(BASE_PATH, cfg.output_dir, chn_grp, chn, sig) # shutil.copy(sig_path, output_path) if cfg.save_type == 'npy': # Save processed data output_path = os.path.join(BASE_PATH, cfg.output_dir, split, chn_grp, chn, sig) os.makedirs(os.path.dirname(output_path), exist_ok=True) np.save(output_path, data) elif cfg.save_type == 'mmap': results.append(data) # sig_list = sorted(os.listdir(os.path.join(BASE_PATH, cfg.data_dir, chn_grp, chn))) save_mmap(results, sig_list, chn_grp, chn, split) del results gc.collect() if chn_grp is not None and chn is not None: _process(sig_list, chn_grp, chn, split) return else: for chn_grp in os.listdir(os.path.join(BASE_PATH, cfg.data_dir)): if not os.path.isdir(os.path.join(BASE_PATH, cfg.data_dir, chn_grp)): continue for chn in os.listdir(os.path.join(BASE_PATH, cfg.data_dir, chn_grp)): if not os.path.isdir(os.path.join(BASE_PATH, cfg.data_dir, chn_grp, chn)): continue _process(sig_list, chn_grp, chn, split) parser = argparse.ArgumentParser() parser.add_argument('--data_dir', default='isruc_all/signals_MAE', help='Physionet 2018 raw data location') parser.add_argument('--output_dir', default='isruc_all/mmap_signals_MAE_processed', help='Physionet 2018 processed data location') parser.add_argument('--save_type', default='mmap', help='Which data type to save. "npy" or "mmap"') parser.add_argument('--chn_grp', default=None, help='If specified, only preprocess this channel group') parser.add_argument('--chn', default=None, help='If specified, only preprocess this channel') parser.add_argument('--ann_split', action='store_true', help='To split annotation files into train/val/test') parser.add_argument('--num_train', type=int, default=50, help='Number of training samples') cfg = parser.parse_args() def get_isruc_filename(ids, ds_id): if ds_id == 2: return [f"sg{ds_id}_{id:03d}_1.npy" for id in ids] + [f"sg{ds_id}_{id:03d}_2.npy" for id in ids] else: return [f"sg{ds_id}_{id:03d}.npy" for id in ids] if __name__ == "__main__": skip_val, skip_test = False, False if cfg.num_train < 90: if os.path.exists(os.path.join(BASE_PATH, cfg.output_dir, 'val')): skip_val = True if os.path.exists(os.path.join(BASE_PATH, cfg.output_dir, 'test')): skip_test = True cfg.output_dir += f"_train{cfg.num_train}" list_files_train = sorted(get_isruc_filename(list(range(1,93)), ds_id=1)) # subjet 8, 40 are missing list_files_val = sorted(get_isruc_filename(list(range(93,101)), ds_id=1)) list_files_test = sorted(get_isruc_filename(list(range(1,9)), ds_id=2)) list_files_test += sorted(get_isruc_filename(list(range(1,11)), ds_id=3)) sig_list = sorted(os.listdir(os.path.join(BASE_PATH, cfg.data_dir, "EEG", "C3-A2"))) for chn_grp in os.listdir(os.path.join(BASE_PATH, cfg.data_dir)): # Skip any files that are not directories if not os.path.isdir(os.path.join(BASE_PATH, cfg.data_dir, chn_grp)): continue for chn in os.listdir(os.path.join(BASE_PATH, cfg.data_dir, chn_grp)): # Skip any files that are not directories if not os.path.isdir(os.path.join(BASE_PATH, cfg.data_dir, chn_grp, chn)): continue sig_list_chn = sorted(os.listdir(os.path.join(BASE_PATH, cfg.data_dir, chn_grp, chn))) print(f"Number of records in {chn_grp}/{chn}:", len(sig_list_chn)) sig_list = list(set(sig_list).intersection(set(sig_list_chn))) print(f"Number of records that exist in all chns:", len(sig_list)) # Total 7698 -> 7579 records list_files_train = sorted(list(set(list_files_train).intersection(set(sig_list)))) list_files_val = sorted(list(set(list_files_val).intersection(set(sig_list)))) list_files_test = sorted(list(set(list_files_test).intersection(set(sig_list)))) # if cfg.num_train < 50: list_files_train = list_files_train[:cfg.num_train] print("Number of records in training set:", len(list_files_train)) print("Number of records in validation set:", len(list_files_val)) print("Number of records in test set:", len(list_files_test)) print("Processing training set...") preprocess(list_files_train, cfg.chn_grp, cfg.chn, split='train') if skip_val: val_output_dir = cfg.output_dir val_output_dir = val_output_dir.replace(f"_train{cfg.num_train}","") os.symlink(os.path.join(BASE_PATH, val_output_dir, 'val'), os.path.join(BASE_PATH, cfg.output_dir, 'val')) else: print("Processing evaluation set...") preprocess(list_files_val, cfg.chn_grp, cfg.chn, split='val') if skip_test: test_output_dir = cfg.output_dir test_output_dir = test_output_dir.replace(f"_train{cfg.num_train}","") os.symlink(os.path.join(BASE_PATH, test_output_dir, 'test'), os.path.join(BASE_PATH, cfg.output_dir, 'test')) else: print("Processing test set...") preprocess(list_files_test, cfg.chn_grp, cfg.chn, split='test') if cfg.ann_split: # Reorganize annotations files ANN_PATH = os.path.join(BASE_PATH, 'ISRUC_SG1/annotations') NEW_ANN_PATH = os.path.join(BASE_PATH, 'ISRUC_SG1/annotations_split') os.makedirs(NEW_ANN_PATH, exist_ok=True) os.makedirs(os.path.join(NEW_ANN_PATH,'train'), exist_ok=True) os.makedirs(os.path.join(NEW_ANN_PATH,'val'), exist_ok=True) os.makedirs(os.path.join(NEW_ANN_PATH,'test'), exist_ok=True) for fname in list_files_train: ann_fname = fname.replace('.npy', '_ann.npy') shutil.copy(os.path.join(ANN_PATH, ann_fname), os.path.join(NEW_ANN_PATH, 'train', ann_fname)) for fname in list_files_val: ann_fname = fname.replace('.npy', '_ann.npy') shutil.copy(os.path.join(ANN_PATH, ann_fname), os.path.join(NEW_ANN_PATH, 'val', ann_fname)) for fname in list_files_test: ann_fname = fname.replace('.npy', '_ann.npy') shutil.copy(os.path.join(ANN_PATH, ann_fname), os.path.join(NEW_ANN_PATH, 'test', ann_fname)) for split in ['train', 'val', 'test']: # create link files to respiratory channels os.makedirs(os.path.join(BASE_PATH, cfg.output_dir, split, 'RESP'), exist_ok=True) for chn_grp in ['ABD', 'CHEST', 'AIRFLOW']: chns = [f.split('.')[0] for f in os.listdir(os.path.join(BASE_PATH, cfg.output_dir, split, chn_grp))] for chn in chns: src_mmap = os.path.join(BASE_PATH, cfg.output_dir, split, chn_grp, f'{chn}.mmap') src_pickle = os.path.join(BASE_PATH, cfg.output_dir, split, chn_grp, f'{chn}.pickle') dst_mmap = os.path.join(BASE_PATH, cfg.output_dir, split, 'RESP', f'{chn}.mmap') dst_pickle = os.path.join(BASE_PATH, cfg.output_dir, split, 'RESP', f'{chn}.pickle') if not os.path.exists(dst_mmap): os.symlink(src_mmap, dst_mmap) if not os.path.exists(dst_pickle): os.symlink(src_pickle, dst_pickle)