from sklearn.preprocessing import normalize
from sklearn.preprocessing import StandardScaler, RobustScaler, MinMaxScaler

ch_ids = range(32)
i_stop = -1
i_start = 0
fs = 50
color = 'C0'
array_msk = []
step = 1

data = data_tot[0, 0]

if ch_ids == []:
    ch_ids = range(data.shape[1])
if i_stop == -1:
    i_stop = data.shape[0]

# data2 = normalize(data)
# data2 = standardize(data)
scaler = StandardScaler() #MinMaxScaler()  #RobustScaler()
# scaler = 
scaler.fit(data)
data2 = scaler.transform(data)
data2 = np.copy(data)

# offset = np.cumsum(4 * np.var(data2[:, ch_ids], axis=0)[:, np.newaxis]).T
offset = np.cumsum(4 * np.var(data2[:, ch_ids], axis=0)[:, np.newaxis]).T

plt.figure(1)
plt.clf()
plt.plot(np.arange(i_start, i_stop) / fs, data2[i_start:i_stop, ch_ids] + offset, color=color, lw=1)
if array_msk != []:  # highlight excluded channels
    plt.plot(np.arange(i_start, i_stop) / fs, data2[i_start:i_stop, array_msk] + offset[array_msk], color='C3', lw=1)

plt.xlabel('Time (sec)')
plt.yticks(offset[::step], range(0, len(ch_ids), step))
plt.ylim(0, offset[-1] + 4)
# plt.title(f'raw data2 from array {arr_id}')
plt.tight_layout()

plt.draw()
plt.show()