def add_data_block(self, partition_id, x, y):
dbm = self._dbms[partition_id]
builder = DataBlockBuilder(
common.data_source_data_block_dir(self._data_source),
self._data_source.data_source_meta.name, partition_id,
dbm.get_dumped_data_block_count(),
dj_pb.WriterOptions(output_writer="TF_RECORD"), None)
builder.set_data_block_manager(dbm)
for i in range(x.shape[0]):
feat = {}
exam_id = '{}'.format(i).encode()
feat['example_id'] = Feature(
bytes_list=BytesList(value=[exam_id]))
feat['event_time'] = Feature(
int64_list = Int64List(value=[i])
)
feat['x'] = Feature(float_list=FloatList(value=list(x[i])))
if y is not None:
feat['y'] = Feature(int64_list=Int64List(value=[y[i]]))
example = Example(features=Features(feature=feat))
builder.append_item(TfExampleItem(example.SerializeToString()), i, 0)
return builder.finish_data_block()
def _create_data_block(self, data_source, partition_id, x, y):
data_block_metas = []
dbm = data_block_manager.DataBlockManager(data_source, partition_id)
self.assertEqual(dbm.get_dumped_data_block_count(), 0)
self.assertEqual(dbm.get_lastest_data_block_meta(), None)
N = 200
chunk_size = x.shape[0] // N
leader_index = 0
follower_index = N * chunk_size * 10
for i in range(N):
builder = DataBlockBuilder(
common.data_source_data_block_dir(data_source),
data_source.data_source_meta.name,
partition_id, i,
dj_pb.WriterOptions(output_writer="TF_RECORD"), None
)
builder.set_data_block_manager(dbm)
for j in range(chunk_size):
feat = {}
idx = i * chunk_size + j
exam_id = '{}'.format(idx).encode()
feat['example_id'] = Feature(
bytes_list=BytesList(value=[exam_id]))
evt_time = random.randint(1, 1000)
feat['event_time'] = Feature(
int64_list = Int64List(value=[evt_time])
)
feat['x'] = Feature(float_list=FloatList(value=list(x[idx])))
if y is not None:
feat['y'] = Feature(int64_list=Int64List(value=[y[idx]]))
feat['leader_index'] = Feature(
int64_list = Int64List(value=[leader_index])
)
feat['follower_index'] = Feature(
int64_list = Int64List(value=[follower_index])
)
example = Example(features=Features(feature=feat))
builder.append_item(TfExampleItem(example.SerializeToString()),
leader_index, follower_index)
leader_index += 1
follower_index += 1
data_block_metas.append(builder.finish_data_block())
self.max_index = follower_index
return data_block_metas
def _make_serialized_example(x):
example = Example()
example.features.feature["x"].float_list.value.append(x)
return example.SerializeToString()
def generate(shape, window_size=10, start=0, offset=5, noise_samples=0,
classes=None, damaged_subjects=None):
if classes is None:
classes = ["left-fist", "right-fist"]
if damaged_subjects is None:
damaged_subjects = ["S088", "S089", "S092", "S100", "S104"]
if type(shape) not in (tuple, list):
shape = [shape]
dataset_dir = os.path.join(PHYSIONET_DIR, "normalized-by-sample",
_get_window_folder_name(window_size, start, offset, noise_samples),
f"{window_size}x{'x'.join(str(dim) for dim in shape)}",
"-".join(classes))
executions = []
if any([c in classes for c in ["eyes-closed"]]):
executions.append("R02")
if any([c in classes for c in ["left-fist", "right-fist"]]):
for execution in ["R04", "R08", "R12"]:
executions.append(execution)
if any([c in classes for c in ["both-fists", "both-feet"]]):
for execution in ["R06", "R10", "R14"]:
executions.append(execution)
label_value = 0
labels = {}
if "eyes-closed" in classes:
labels["eyes-closed"] = label_value
label_value += 1
if "left-fist" in classes:
labels["left-fist"] = label_value
label_value += 1
if "right-fist" in classes:
labels["right-fist"] = label_value
label_value += 1
if "both-fists" in classes:
labels["both-fists"] = label_value
label_value += 1
if "both-feet" in classes:
labels["both-feet"] = label_value
label_value += 1
fsh.recreate_dir(dataset_dir)
regex_executions = f"({'|'.join(executions)})"
info = {
"n_samples_by_subject": 0
}
subjects = filter(lambda s: s not in damaged_subjects, sorted(os.listdir(RAW_EDF_FILES_DIR)))
for subject in filter(lambda f: re.match("S(\\d+)", f), subjects):
print(f"Generating TFRecord file from the subject {subject} ...")
X_segments = np.empty((0, 64))
y = np.empty(0, dtype=np.int64)
edf_subject_path_dir = os.path.join(RAW_EDF_FILES_DIR, subject)
edf_file_names = sorted(os.listdir(edf_subject_path_dir))
for edf_file_name in filter(lambda f: re.match(f"^{subject}{regex_executions}\\.edf$", f),
edf_file_names):
edf_file = EdfFile(edf_subject_path_dir, edf_file_name)
events_windows = [next(group) for key, group in groupby(enumerate(edf_file.labels), key=itemgetter(1))]
n_events = len(events_windows)
for index, (event_start_index, event) in enumerate(events_windows):
if event == "rest":
continue
event_start_index += start
X = edf_file.data[event_start_index:] if index + 1 == n_events \
else edf_file.data[event_start_index:events_windows[index + 1][0]]
n_segments = 0
for (start_segment, end_segment) in _windows(X, window_size, offset):
x_segment = X[start_segment:end_segment]
X_segments = np.vstack((X_segments, x_segment))
y = np.append(y, labels[event])
for _ in range(noise_samples):
noise = np.random.normal(0, 1, x_segment.shape)
X_segments = np.vstack((X_segments, x_segment + noise))
y = np.append(y, labels[event])
n_segments += 1
print(f"X{X.shape} splitted into {n_segments} segments of "
f"{window_size} samples with offset of {offset} plus {noise_samples} noise samples")
edf_file.close()
if len(y) > info["n_samples_by_subject"]:
info["n_samples_by_subject"] = len(y)
print("Labels: ", len(y), len(y[y == 0]), len(y[y == 1]))
X_segments = X_segments.reshape((-1, window_size, 64))
print("Has nan: ", np.isnan(X_segments).any())
tfrecord_subject_filepath = os.path.join(dataset_dir, f"{subject}.tfrecord")
options = tf.io.TFRecordOptions(compression_type="GZIP")
with tf.io.TFRecordWriter(tfrecord_subject_filepath, options) as writer:
for n_segment in range(len(y)):
X_segment = np.array(list(map(lambda x: _process_record(x, shape), X_segments[n_segment])))
eeg_example = Example(
features=Features(
feature={
"X": Feature(bytes_list=BytesList(value=[tf.io.serialize_tensor(X_segment).numpy()])),
"y": Feature(int64_list=Int64List(value=[y[n_segment]]))
}
)
)
writer.write(eeg_example.SerializeToString())
print("n_samples_by_subject: ", info["n_samples_by_subject"])
info_filepath = os.path.join(dataset_dir, "info.pkl")
with open(info_filepath, "wb") as fp:
pickle.dump(info, fp, protocol=4)
def generate(dataset_root_dir, events_enum, labels_enum, labels, classes,
window_size):
dataset_dir = os.path.join(dataset_root_dir, "normalized-by-sample",
f"window-{window_size}",
"-".join(classes).lower())
fsh.recreate_dir(dataset_dir)
info = {"n_samples_by_file": 0}
subjects_labels_counts = LabelsCounts()
subjects_session_labels_counts = LabelsCounts()
gdf_files_dir = os.path.join(dataset_root_dir, "gdf-files")
gdf_file_names = filter(lambda f: re.match(".*.gdf", f),
sorted(os.listdir(gdf_files_dir)))
for gdf_file_name in gdf_file_names:
gdf_file = mne.io.read_raw_gdf(os.path.join(gdf_files_dir,
gdf_file_name),
preload=True)
groups_gdf_file = re.match("(.)(\\d{2})(\\d{0,2})([ET])\\.gdf",
gdf_file_name).groups()
database_prefix = groups_gdf_file[0]
subject = groups_gdf_file[1]
session = groups_gdf_file[2]
session_type = groups_gdf_file[3]
labels_filepath = os.path.join(
gdf_files_dir, "labels",
f"{database_prefix}{subject}{session}{session_type}.mat")
labels_file = io.loadmat(labels_filepath)["classlabel"]
annotations = gdf_file.annotations
start_trials_indexes = [
event_index for event_index in range(len(annotations.description))
if events_enum.get(annotations.description[event_index]) ==
"NEW_TRIAL"
]
indexes_channels_eeg = [
index for index, _ in enumerate(
filter(lambda ch: "EEG" in ch, gdf_file.ch_names))
]
n_channels = len(indexes_channels_eeg)
frequency = int(gdf_file.info["sfreq"])
# should consider the complete motor imagery period (4s),
# not only the cue exhibition period (1.25s)
duration_event = window_size // frequency
n_samples = frequency * duration_event
rejected_trials = 0
ignored_trials = 0
X = np.empty((0, n_channels))
y = np.empty(0, dtype=np.int64)
for n_trial, event_start_trial_index in enumerate(
start_trials_indexes):
cue_event_index = event_start_trial_index + 1
onset_event = annotations.onset[cue_event_index]
onset_index = int(np.ceil(onset_event * frequency))
end_index = int(np.ceil(
(onset_event + duration_event) * frequency))
event_samples = end_index - onset_index
if event_samples != n_samples:
end_index += n_samples - event_samples
# The event correspondent to the trial is the following the start trial event
if events_enum[annotations.
description[cue_event_index]] == "REJECTED_TRIAL":
rejected_trials += 1
continue
label = labels_enum[labels_file[n_trial][0]]
if label not in classes:
ignored_trials += 1
continue
# The index 0 returns the data array of the gdf_file
# The index 1 returns the times array of the gdf_file
x = gdf_file[indexes_channels_eeg, onset_index:end_index][0].T
x = (x - np.mean(x)) / np.std(x)
X = np.vstack((X, x))
y = np.append(y, labels[label])
gdf_file.close()
X = X.reshape((-1, n_samples, n_channels))
tfrecord_filepath = os.path.join(
dataset_dir,
f"{database_prefix}{subject}{session}{session_type}.tfrecord")
options = tf.io.TFRecordOptions(compression_type="GZIP")
with tf.io.TFRecordWriter(tfrecord_filepath, options) as writer:
for n_segment in range(len(y)):
eeg_example = Example(features=Features(
feature={
"X":
Feature(bytes_list=BytesList(value=[
tf.io.serialize_tensor(X[n_segment]).numpy()
])),
"y":
Feature(int64_list=Int64List(value=[y[n_segment]]))
}))
writer.write(eeg_example.SerializeToString())
valid_trials = len(y)
if valid_trials > info["n_samples_by_file"]:
info["n_samples_by_file"] = valid_trials
labels_counts = np.unique(y, return_counts=True)[1]
subjects_labels_counts.put(subject, labels_counts)
subjects_session_labels_counts.put(subject + session_type,
labels_counts)
print("Info from file " + gdf_file_name)
print(f"Labels counts: {labels_counts}")
print("Valid Trials: " + str(valid_trials))
print("Ignored Trials: " + str(ignored_trials))
print("Rejected Trials: " + str(rejected_trials))
print("Total Trials: " +
str(valid_trials + ignored_trials + rejected_trials))
print("Subjects Labels Counts:")
print(subjects_labels_counts)
print("Subjects Session Counts:")
print(subjects_session_labels_counts)
print("Generation dataset ended, saving info data ...")
print("info[n_samples_by_file]=", info["n_samples_by_file"])
info_filepath = os.path.join(dataset_dir, "info.pkl")
with open(info_filepath, "wb") as fp:
pickle.dump(info, fp, protocol=4)