def filter_data_pre_raw(self, data, fcenter, bandwidth, order,
filter_type):
"""Filters the OpenBCI data using the BrainFlow functions before creating an MNE Raw object.
Parameters:
data
fcenter
bandwidth
order
filter_type
Returns:
data
"""
for channel in self.eeg_info[0]:
if filter_type == 'bandpass':
DataFilter.perform_bandpass(data[channel], self.eeg_info[1],
fcenter, bandwidth, order,
FilterTypes.BESSEL.value, 0)
elif filter_type == 'notch':
DataFilter.perform_bandstop(data[channel], self.eeg_info[1],
fcenter, bandwidth, order,
FilterTypes.BUTTERWORTH.value, 0)
elif filter_type == 'highpass':
DataFilter.perform_highpass(data[channel], self.eeg_info[1],
fcenter, order,
FilterTypes.BUTTERWORTH.value, 0)
return data
def main():
BoardShim.enable_dev_board_logger()
# use synthetic board for demo
params = BrainFlowInputParams()
board_id = BoardIds.SYNTHETIC_BOARD.value
board = BoardShim(board_id, params)
board.prepare_session()
board.start_stream()
BoardShim.log_message(LogLevels.LEVEL_INFO.value,
'start sleeping in the main thread')
time.sleep(10)
data = board.get_board_data()
board.stop_stream()
board.release_session()
# demo how to convert it to pandas DF and plot data
eeg_channels = BoardShim.get_eeg_channels(board_id)
df = pd.DataFrame(np.transpose(data))
plt.figure()
df[eeg_channels].plot(subplots=True)
plt.savefig('before_processing.png')
# for demo apply different filters to different channels, in production choose one
for count, channel in enumerate(eeg_channels):
# filters work in-place
if count == 0:
DataFilter.perform_bandpass(data[channel],
BoardShim.get_sampling_rate(board_id),
15.0, 6.0, 4, FilterTypes.BESSEL.value,
0)
elif count == 1:
DataFilter.perform_bandstop(data[channel],
BoardShim.get_sampling_rate(board_id),
30.0, 1.0, 3,
FilterTypes.BUTTERWORTH.value, 0)
elif count == 2:
DataFilter.perform_lowpass(data[channel],
BoardShim.get_sampling_rate(board_id),
20.0, 5,
FilterTypes.CHEBYSHEV_TYPE_1.value, 1)
elif count == 3:
DataFilter.perform_highpass(data[channel],
BoardShim.get_sampling_rate(board_id),
3.0, 4, FilterTypes.BUTTERWORTH.value,
0)
elif count == 4:
DataFilter.perform_rolling_filter(data[channel], 3,
AggOperations.MEAN.value)
else:
DataFilter.remove_environmental_noise(
data[channel], BoardShim.get_sampling_rate(board_id),
NoiseTypes.FIFTY.value)
df = pd.DataFrame(np.transpose(data))
plt.figure()
df[eeg_channels].plot(subplots=True)
plt.savefig('after_processing.png')
def high_pass(self, data, parameter_list):
filter_data = []
for i in range(parameter_list[-1]):
DataFilter.perform_highpass(data[i], parameter_list[1],
parameter_list[2], parameter_list[3],
parameter_list[4], 3)
filter_data.append(data[i])
filter_data = np.array(filter_data)
return filter_data
def filtering(signal, sf, chosen_channels):
for ch in chosen_channels:
copy_signal = copy.deepcopy(signal[ch])
DataFilter.perform_lowpass(copy_signal, sf, 50.0, 5,
FilterTypes.CHEBYSHEV_TYPE_1.value, 1)
DataFilter.perform_highpass(copy_signal, sf, 3.0, 4,
FilterTypes.BUTTERWORTH.value, 0)
signal[ch] = copy_signal
return signal
def main ():
parser = argparse.ArgumentParser ()
# use docs to check which parameters are required for specific board, e.g. for Cyton - set serial port
parser.add_argument ('--ip-port', type = int, help = 'ip port', required = False, default = 0)
parser.add_argument ('--ip-protocol', type = int, help = 'ip protocol, check IpProtocolType enum', required = False, default = 0)
parser.add_argument ('--ip-address', type = str, help = 'ip address', required = False, default = '')
parser.add_argument ('--serial-port', type = str, help = 'serial port', required = False, default = '')
parser.add_argument ('--mac-address', type = str, help = 'mac address', required = False, default = '')
parser.add_argument ('--other-info', type = str, help = 'other info', required = False, default = '')
parser.add_argument ('--board-id', type = int, help = 'board id, check docs to get a list of supported boards', required = True)
parser.add_argument ('--log', action = 'store_true')
args = parser.parse_args ()
params = BrainFlowInputParams ()
params.ip_port = args.ip_port
params.serial_port = args.serial_port
params.mac_address = args.mac_address
params.other_info = args.other_info
params.ip_address = args.ip_address
params.ip_protocol = args.ip_protocol
if (args.log):
BoardShim.enable_dev_board_logger ()
else:
BoardShim.disable_board_logger ()
board = BoardShim (args.board_id, params)
board.prepare_session ()
# disable 2nd channel for cyton use real board to check it, emulator ignores commands
if args.board_id == brainflow.board_shim.BoardIds.CYTON_BOARD.value:
board.config_board ('x2100000X')
board.start_stream ()
time.sleep (10)
data = board.get_board_data ()
board.stop_stream ()
board.release_session ()
eeg_channels = BoardShim.get_eeg_channels (args.board_id)
for count, channel in enumerate (eeg_channels):
if count == 0:
DataFilter.perform_bandpass (data[channel], BoardShim.get_sampling_rate (args.board_id), 15.0, 6.0, 4, FilterTypes.BESSEL.value, 0)
elif count == 1:
DataFilter.perform_bandstop (data[channel], BoardShim.get_sampling_rate (args.board_id), 5.0, 1.0, 3, FilterTypes.BUTTERWORTH.value, 0)
elif count == 2:
DataFilter.perform_lowpass (data[channel], BoardShim.get_sampling_rate (args.board_id), 9.0, 5, FilterTypes.CHEBYSHEV_TYPE_1.value, 1)
elif count == 3:
DataFilter.perform_highpass (data[channel], BoardShim.get_sampling_rate (args.board_id), 3.0, 4, FilterTypes.BUTTERWORTH.value, 0)
def plot(self):
plt.figure()
print('Only for channel #' + str(self.channels[0]))
data = self.board.get_current_board_data(num_samples=450000)
t = data[self.board.time_channel] - self.start_time
data = data[self.board.eeg_channels][self.channels[0]]
DataFilter.perform_highpass(data, self.board.rate, 3.0, 4, FilterTypes.BUTTERWORTH.value, 0)
plt.plot(t, data)
plt.title('OpenBCI Stream History')
plt.ylabel('Voltage')
plt.xlabel('Time (s)')
plt.show()
return data
def update(self):
# received_data, addr = sock.recvfrom(1024) # buffer size is 1024 bytes
# print("Received message: ", received_data)
data = self.board_shim.get_current_board_data(self.num_points)
if data[0:7, 0:250].shape == (7, 250):
for count, channel in enumerate(self.exg_channels):
# plot timeseries
DataFilter.perform_lowpass(
data[channel], BoardShim.get_sampling_rate(args.board_id),
high, 3, FilterTypes.BUTTERWORTH.value, 0)
DataFilter.perform_highpass(
data[channel], BoardShim.get_sampling_rate(args.board_id),
low, 3, FilterTypes.BUTTERWORTH.value, 0)
DataFilter.perform_bandstop(
data[channel], BoardShim.get_sampling_rate(args.board_id),
50, 2, 8, FilterTypes.BUTTERWORTH.value, 0)
self.curves[count + 1].setData(data[channel][-1001:].tolist())
window = data[0:8, -250:] # input window
window = window - window[3, :] # Cz reference
x = np.vstack((window[0:3, :], window[4:, :]))
x = create_data(x, fs, 1, low, high, n_freqs, zeros,
length) # convert to PSD
x = np.reshape(x, (1, n_channels_ref, n_freqs))
x_csp = csp2.transform(x)
window = np.reshape(window, (1, window.shape[0], window.shape[1]))
x_raw_csp = csp1.transform(window)
inference = np.hstack((x_csp, x_raw_csp))
current_time = datetime.now()
current_time = current_time.strftime("%M:%S")
result.append(model.predict(inference)[0])
MESSAGE = str(model.predict(inference)[0])
MESSAGE = bytes(MESSAGE, 'utf-8')
sock.sendto(MESSAGE, (UDP_IP, UDP_PORT))
pygame.time.delay(100)
self.curves[0].setData(result[-1001:])
self.app.processEvents()
def start_recording(total_sec, max_samples, params, args):
board = BoardShim(args.board_id, params)
board.prepare_session()
# board.start_stream () # use this for default options
board.start_stream(max_samples, args.streamer_params)
time.sleep(total_sec)
# data = board.get_current_board_data (256) # get latest 256 packages or less, doesnt remove them from internal buffer
data = board.get_board_data(
) # get all data and remove it from internal buffer
timestamp_channel = board.get_timestamp_channel(board_id=0)
board.stop_stream()
board.release_session()
# demo how to convert it to pandas DF and plot data
eeg_channels = BoardShim.get_eeg_channels(args.board_id)
print(eeg_channels)
df = pd.DataFrame(np.transpose(data))
plt.figure()
df[eeg_channels].plot(subplots=True)
plt.savefig('data/before_processing.png')
# for demo apply different filters to different channels, in production choose one
for count, channel in enumerate(eeg_channels):
DataFilter.perform_lowpass(data[channel],
BoardShim.get_sampling_rate(args.board_id),
30, 3, FilterTypes.BUTTERWORTH.value, 0)
DataFilter.perform_highpass(data[channel],
BoardShim.get_sampling_rate(args.board_id),
5, 3, FilterTypes.BUTTERWORTH.value, 0)
DataFilter.perform_bandstop(data[channel],
BoardShim.get_sampling_rate(args.board_id),
50, 2, 8, FilterTypes.BUTTERWORTH.value, 0)
df = pd.DataFrame(np.transpose(
data[:, 1000:])) # Usable after 1000 given order of filters are 3
plt.figure()
df[eeg_channels].plot(subplots=True)
plt.savefig('data/after_processing.png')
return data, timestamp_channel
def run(self):
# Initialize Acquisition Paramenters
window_size = 3
sleep_time = 0.5
points_per_update = window_size * self.sampling_rate
# Load Decoder
classifier = keras.models.load_model(
'..\jupyter-notebooks\classifier_22_v3')
# Initialize Actuator
# LIF Parameters:
alpha = 0.4
beta = 0.1
v_ref = 0
v_thresh = 1
v_prev = np.zeros(4)
v = np.zeros(4)
# Manipulator Initialization
portHandler = PortHandler(DEVICE_NAME)
# There's also a class type that handles how to send packages across the COM port
packetHandler = PacketHandler(PROTOCOL_VERSION)
# Open the port
if portHandler.openPort():
print('Succeeded to open the port')
else:
print('Failed to open the port')
quit()
enable_motor(MOTOR_ID_Y, packetHandler, portHandler)
enable_motor(3, packetHandler, portHandler)
enable_motor(2, packetHandler, portHandler)
enable_motor(MOTOR_ID_Z, packetHandler, portHandler)
position_my = 1900
position_mz = 1900
move_motor(position_my, MOTOR_ID_Y, packetHandler, portHandler)
move_motor(1900, 3, packetHandler, portHandler)
move_motor(1900, 2, packetHandler, portHandler)
move_motor(position_mz, MOTOR_ID_Z, packetHandler, portHandler)
_ = input()
while self.keep_alive:
start_time = time.time()
time.sleep(sleep_time)
# get current board data doesnt remove data from the buffer
data = self.board.get_current_board_data(int(points_per_update))
# print('Data Shape %s' % (str(data.shape)))
first_channel = True
for channel in self.eeg_channels:
# filters work in-place
DataFilter.perform_highpass(data[channel], self.sampling_rate,
0.5, 4,
FilterTypes.BUTTERWORTH.value, 0)
DataFilter.perform_bandstop(data[channel], self.sampling_rate,
60.0, 2.0, 4,
FilterTypes.BUTTERWORTH.value, 0)
DataFilter.perform_bandpass(data[channel], self.sampling_rate,
19.0, 12.0, 4,
FilterTypes.BUTTERWORTH.value, 0)
stft_data = data[channel].copy()
_, _, Zxx = signal.stft(stft_data,
self.sampling_rate,
nperseg=128,
noverlap=127,
nfft=256)
spectro = np.asarray(Zxx[7:32, :])
spectro = np.abs(spectro)
spectro = np.expand_dims(spectro, axis=2)
if first_channel:
tfi = spectro.copy()
first_channel = False
else:
tfi = np.dstack((tfi, spectro))
res_tfi = resize(tfi, (64, 64, 8))
res_tfi = np.reshape(res_tfi, (1, 64, 64, 8))
outputs = classifier.predict(res_tfi)
outputs = np.reshape(outputs, -1)
output = np.argmax(outputs)
exc = np.zeros(4)
if output == 0:
exc[0] = 1
elif output == 2:
exc[1] = 1
elif output == 3:
exc[2] = 1
elif output == 4:
exc[3] = 1
print(v)
dv = np.subtract((alpha * exc), (beta * v_prev))
v = np.add(v_prev, dv)
print(v)
if v[0] > v_thresh:
position_my = move_down(position_my, packetHandler,
portHandler)
v[0] = v_ref
elif v[1] > v_thresh:
position_mz = move_left(position_mz, packetHandler,
portHandler)
v[1] = v_ref
elif v[2] > v_thresh:
position_mz = move_right(position_mz, packetHandler,
portHandler)
v[2] = v_ref
elif v[3] > v_thresh:
position_my = move_up(position_my, packetHandler, portHandler)
v[3] = v_ref
else:
print('do not move')
v_prev = v
print(time.time() - start_time)
disable_motor(MOTOR_ID_Y, packetHandler, portHandler)
disable_motor(3, packetHandler, portHandler)
disable_motor(2, packetHandler, portHandler)
disable_motor(MOTOR_ID_Z, packetHandler, portHandler)
# Close the port
portHandler.closePort()
def main():
parser = argparse.ArgumentParser()
# use docs to check which parameters are required for specific board, e.g. for Cyton - set serial port,
parser.add_argument('--ip-port',
type=int,
help='ip port',
required=False,
default=0)
parser.add_argument('--ip-protocol',
type=int,
help='ip protocol, check IpProtocolType enum',
required=False,
default=0)
parser.add_argument('--ip-address',
type=str,
help='ip address',
required=False,
default='')
parser.add_argument('--serial-port',
type=str,
help='serial port',
required=False,
default='')
parser.add_argument('--mac-address',
type=str,
help='mac address',
required=False,
default='')
parser.add_argument('--other-info',
type=str,
help='other info',
required=False,
default='')
parser.add_argument(
'--board-id',
type=int,
help='board id, check docs to get a list of supported boards',
required=True)
parser.add_argument('--log', action='store_true')
args = parser.parse_args()
params = BrainFlowInputParams()
params.ip_port = args.ip_port
params.serial_port = args.serial_port
params.mac_address = args.mac_address
params.other_info = args.other_info
params.ip_address = args.ip_address
params.ip_protocol = args.ip_protocol
if (args.log):
BoardShim.enable_dev_board_logger()
else:
BoardShim.disable_board_logger()
# demo how to read data as 2d numpy array
board = BoardShim(args.board_id, params)
board.prepare_session()
board.start_stream()
BoardShim.log_message(LogLevels.LEVEL_INFO.value,
'start sleeping in the main thread')
time.sleep(10)
# data = board.get_current_board_data (256) # get latest 256 packages or less, doesnt remove them from internal buffer
data = board.get_board_data(
) # get all data and remove it from internal buffer
board.stop_stream()
board.release_session()
# demo how to convert it to pandas DF and plot data
eeg_channels = BoardShim.get_eeg_channels(args.board_id)
df = pd.DataFrame(np.transpose(data))
print('Data From the Board')
print(df.head())
plt.figure()
df[eeg_channels].plot(subplots=True)
plt.savefig('before_processing.png')
# demo for data serialization
DataFilter.write_file(data, 'test.csv', 'w')
restored_data = DataFilter.read_file('test.csv')
restored_df = pd.DataFrame(np.transpose(restored_data))
print('Data From the File')
print(restored_df.head())
# demo how to perform signal processing
for count, channel in enumerate(eeg_channels):
if count == 0:
DataFilter.perform_bandpass(
data[channel], BoardShim.get_sampling_rate(args.board_id),
15.0, 6.0, 4, FilterTypes.BESSEL.value, 0)
elif count == 1:
DataFilter.perform_bandstop(
data[channel], BoardShim.get_sampling_rate(args.board_id), 5.0,
1.0, 3, FilterTypes.BUTTERWORTH.value, 0)
elif count == 2:
DataFilter.perform_lowpass(
data[channel], BoardShim.get_sampling_rate(args.board_id), 9.0,
5, FilterTypes.CHEBYSHEV_TYPE_1.value, 1)
elif count == 3:
DataFilter.perform_highpass(
data[channel], BoardShim.get_sampling_rate(args.board_id), 3.0,
4, FilterTypes.BUTTERWORTH.value, 0)
df = pd.DataFrame(np.transpose(data))
print('Data After Processing')
print(df.head())
plt.figure()
df[eeg_channels].plot(subplots=True)
plt.savefig('after_processing.png')
BUFFER_TIME = args.buffer
params = BrainFlowInputParams() if args.synth else fill_in_cyton_params()
board = BoardShim(board_id=board_id, input_params=params)
board.prepare_session()
board.start_stream()
time.sleep(BUFFER_TIME)
for i in range(
3
): #TODO: make while(True) and elegantly shutdown when board is shutdown or keyboard interrupt
data = board.get_board_data()
channel = eegs[1]
print(data.shape)
foo = np.mean(data[channel])
log_info(
f"eeg type is {type(data[channel])} with shape {data[eegs[1]].shape}")
DataFilter.perform_highpass(data[channel],
BoardShim.get_sampling_rate(board_id), 20.0, 5,
FilterTypes.CHEBYSHEV_TYPE_1.value, 1)
# DataFilter.perform_bandstop (data[channel], BoardShim.get_sampling_rate (board_id), 30.0, 1.0, 3, FilterTypes.BUTTERWORTH.value, 0)
print(f"is foo the same as data[channel]? {foo == np.mean(data[channel])}")
indexes = [timestamp, *eegs, *others]
data_to_write = data[indexes]
DataFilter.write_file(data=data_to_write,
file_name=raw_data_path,
file_mode='a')
log_debug(f"sample {i}:: data is {data} or len {len(data)}")
time.sleep(1)
board.stop_stream()
board.release_session()
async def capture(self, stream,url, port=None,plot=False, model=None,categories=None,details=None):
# Authenticate
res = self.session.post(url + '/login')
cookies = ""
cookieDict = res.cookies.get_dict()
for cookie in (cookieDict):
cookies += str(cookie + "=" + cookieDict[cookie] + "; ")
o = urlparse(url)
if (o.scheme == 'http'):
uri = "ws://" + o.netloc
elif (o.scheme == 'https'):
uri = "wss://" + o.netloc
else:
print('not a valid url scheme')
async with websockets.connect(uri,ping_interval=None, extra_headers=[('cookie', cookies)]) as websocket:
print('Initializing board')
self.board = initialize_board(stream,port)
print('Starting stream')
self.board.start_stream(num_samples=450000)
self.start_time = time.time()
signal.signal(signal.SIGINT, self.signal_handler)
# # initialise plot and line
# fig = plt.figure()
# ax = fig.add_subplot(1, 1, 1)
# xs = []
# ys = []
# def animate(i, xs, ys):
# data = self.board.get_current_board_data(num_samples=DataFilter.get_nearest_power_of_two(self.board.rate))#1)
# t = data[self.board.time_channel]
# data = data[self.board.eeg_channels][self.channel]
# if len(t) > 0:
# t = t - self.start_time
# DataFilter.perform_highpass(data, self.board.rate, 3.0, 4, FilterTypes.BUTTERWORTH.value, 0)
# self.socket.emit('bci', {'signal':(data).tolist(),
# 'time': (t*1000).tolist()})
# xs.append(t[-1])
# ys.append(data[-1])
# # Limit x and y lists to 20 items
# xs = xs[-20:]
# ys = ys[-20:]
# # Draw x and y lists
# ax.clear()
# ax.plot(xs, ys)
# # Format plot
# plt.xticks(rotation=45, ha='right')
# plt.subplots_adjust(bottom=0.30)
# plt.title('OpenBCI Live Stream')
# plt.ylabel('Voltage')
# ani = animation.FuncAnimation(fig, animate, fargs=(xs, ys), interval=1)
# plt.show()
while True:
# Get Data
pass_data = []
rate = DataFilter.get_nearest_power_of_two(self.board.rate)
data = self.board.get_current_board_data(num_samples=rate)#1)
t = data[self.board.time_channel]
if self.all_channels:
data = data[self.board.eeg_channels] # SCALED
else:
data = data[self.board.eeg_channels][self.channels] # SCALED
for entry in data:
DataFilter.perform_highpass(entry, self.board.rate, 3.0, 4, FilterTypes.BUTTERWORTH.value, 0)
pass_data.append((entry).tolist())
if len(t) > 0:
t = t - self.start_time
message = {
'destination': 'bci',
'data': {'ts_filtered':pass_data}
}
message = json.dumps(message, separators=(',', ':'))
# (Re)Open Websocket Connection
if not websocket.open:
try:
print('Websocket is NOT connected. Reconnecting...')
websocket = await websockets.connect(uri,ping_interval=None, extra_headers=[('cookie', cookies)])
except:
print('Unable to reconnect, trying again.')
await websocket.send(message)
time.sleep(.01)
