Load necessary libraries
In [1]:
%matplotlib inline
In [2]:
import numpy as np
import scipy as sp
import scipy.signal as sig
import pandas as pd
import matplotlib.pylab as plt
import matplotlib.mlab as m
import statsmodels.api as sm
Load labels
In [120]:
TrainLabels = pd.read_csv('../data/TrainLabels.csv', header=0)
TrainLabels.head()
Out[120]:
IdFeedBack
Prediction
0
S02_Sess01_FB001
1
1
S02_Sess01_FB002
1
2
S02_Sess01_FB003
0
3
S02_Sess01_FB004
0
4
S02_Sess01_FB005
1
In [121]:
TrainLabels['Subject'] = TrainLabels['IdFeedBack'].map(lambda s : int(s[1:3]))
TrainLabels['Session'] = TrainLabels['IdFeedBack'].map(lambda s : int(s[8:10]))
TrainLabels['FeedbackNo'] = TrainLabels['IdFeedBack'].map(lambda s : int(s[13:]))
TrainLabels = TrainLabels[['IdFeedBack', 'Subject','Session','FeedbackNo','Prediction']]
TrainLabels['Cz ERP'] = np.nan
TrainLabels['Cz ERP'] = TrainLabels['Cz ERP'].astype(object) # change dtype to object so it can contain np arrays
TrainLabels['Neg-ErrP'] = np.nan
TrainLabels['Pos-ErrP'] = np.nan
TrainLabels.loc[np.random.randint(0, 3000, 5)]
Out[121]:
IdFeedBack
Subject
Session
FeedbackNo
Prediction
Cz ERP
Neg-ErrP
Pos-ErrP
1968
S13_Sess05_FB029
13
5
29
0
NaN
NaN
NaN
1297
S11_Sess05_FB038
11
5
38
0
NaN
NaN
NaN
822
S07_Sess03_FB023
7
3
23
1
NaN
NaN
NaN
768
S07_Sess02_FB029
7
2
29
1
NaN
NaN
NaN
2867
S17_Sess03_FB028
17
3
28
0
NaN
NaN
NaN
In [271]:
# Number of correct and error trials
pd.value_counts(TrainLabels['Prediction'])
Out[271]:
1 3850
0 1590
dtype: int64
In [272]:
pd.value_counts(TrainLabels['Subject'])
Out[272]:
23 340
11 340
7 340
26 340
22 340
18 340
14 340
6 340
2 340
21 340
17 340
13 340
24 340
20 340
16 340
12 340
dtype: int64
In [273]:
ErrorFeedbacks = TrainLabels[TrainLabels['Prediction'] == 0]
ErrorFeedbacks = ErrorFeedbacks[['Subject','Session','FeedbackNo']]
pd.value_counts(ErrorFeedbacks['Subject'])
Out[273]:
13 162
26 159
12 151
16 129
14 125
2 120
23 119
11 115
17 114
20 104
24 101
18 79
7 33
21 28
22 27
6 24
dtype: int64
In [274]:
ErrorFeedbacks.head()
Out[274]:
Subject
Session
FeedbackNo
2
2
1
3
3
2
1
4
5
2
1
6
8
2
1
9
12
2
1
13
In [275]:
error_crosstab = pd.crosstab(ErrorFeedbacks['Session'], ErrorFeedbacks['Subject'], margins=True)
#error_crosstab = error_crosstab.drop('All', 1)
error_crosstab
Out[275]:
Subject
2
6
7
11
12
13
14
16
17
18
20
21
22
23
24
26
All
Session
1
10
1
4
14
19
22
23
16
6
9
17
2
3
18
6
25
195
2
17
3
7
18
19
30
16
19
17
14
14
2
4
24
9
23
236
3
24
5
3
18
27
35
18
22
24
14
18
4
6
21
14
30
283
4
25
4
7
21
27
25
18
25
26
15
19
5
5
17
23
21
283
5
44
11
12
44
59
50
50
47
41
27
36
15
9
39
49
60
593
All
120
24
33
115
151
162
125
129
114
79
104
28
27
119
101
159
1590
In [8]:
def compute_trial_idxs(sessions, feedbacknos):
trial_idxs = []
for (session, feedbackno) in zip(sessions, feedbacknos):
if session == 5:
trial_idxs.append(4 * 60 + feedbackno)
else:
trial_idxs.append((session - 1) * 60 + feedbackno)
return trial_idxs
In [ ]:
In [124]:
Fs = 200 # sampling frequency in Hz
F_nyq = Fs/2 # Nyquist frequency
Ts = 1./Fs # sampling period in seconds
# Test signal (mimicking an ErrP)
t_test = np.linspace(-1, 1, 2 * Fs, endpoint=False)
re, im= sig.gausspulse(t_test, fc=5, retquad=True, bw=2)
test_sig = im
In [161]:
plt.figure(figsize=(8,6))
plt.plot(t_test , test_sig)
plt.xticks(np.linspace(-1, 1, 10, endpoint=False))
plt.title('Test signal (pseudo ErrP)')
plt.ylim(-1.2,1.2)
plt.xlabel('Time (s)')
plt.ylabel('Amplitude (a.u.)')
plt.show()
In [125]:
# Design bandpass IIR filter
N_ord = 4 # order of the filter in samples
F_lo = 0.1 # cuttof frequency in Hz
F_hi = 30.0 # cuttof frequency in Hz
(b, a) = sig.butter(N_ord, [F_lo/F_nyq, F_hi/F_nyq], btype='bandpass')
w, h = sig.freqz(b, a)
In [222]:
plt.figure(figsize=(8,6))
plt.title('Digital filter frequency response')
#plt.plot(w/np.pi * Fs/2, 20*np.log10(np.abs(h)), 'b')
plt.plot(w/np.pi * Fs/2, np.abs(h), 'b')
plt.ylabel('Amplitude response (a.u.)')
plt.xlabel('Frequency (Hz)')
#plt.yticks(np.arange(-162, 20, 3))
plt.yticks(np.arange(0, 1.1, 0.1))
plt.ylim(0,1.1)
plt.xticks(np.arange(0, Fs/2, 2))
plt.xlim(0, 50)
plt.axvline(F_lo, color='green') # cutoff frequency
plt.axvline(F_hi, color='green') # cutoff frequency
plt.axhline(np.sqrt(2)/2, color='red') # half-power
plt.axhline(0.5, color='red') # half-amplitude
plt.show()
plt.figure(figsize=(18,12))
plt.title('Digital filter frequency response')
plt.plot(w/np.pi * Fs/2, 20*np.log10(np.abs(h)), 'b')
plt.ylabel('Amplitude Response (dB)')
plt.xlabel('Frequency (Hz)')
plt.yticks(np.arange(-162, 20, 3))
plt.xticks(np.arange(0, Fs/2, 2))
plt.xlim(0, 50)
plt.axvline(F_lo, color='green') # cutoff frequency
plt.axvline(F_hi, color='green') # cutoff frequency
plt.axhline(-3, color='red') # half-power
plt.axhline(-6, color='red') # half-amplitude
plt.ylim(-160, 20)
plt.show()
In [15]:
# Test signal bandpass filtered
y_bp = sig.filtfilt(b, a, test_sig)
plt.figure(figsize=(15,12))
plt.plot(t_test , test_sig, t_test, y_bp)
plt.xticks(np.linspace(-1, 1, 20, endpoint=False))
plt.grid()
In [228]:
# Noisy test signal bandpass filtered
test_sig_noisy = test_sig + np.random.normal(loc=0.0, scale=0.1, size=len(test_sig)) + 0.5*np.sin(2*np.pi*50*t_test)
y_bp_noisy = sig.filtfilt(b, a, test_sig_noisy, padlen=150, padtype='even')
In [229]:
plt.figure(figsize=(8,6))
plt.plot(t_test, test_sig_noisy, linewidth=0.7, color=sns.color_palette()[1])
plt.plot(t_test, y_bp_noisy, linewidth=2, color=sns.color_palette()[2])
plt.ylim(-1.2,1.2)
plt.title('Filtering the corrupted test signal')
plt.legend(['Noisy', 'Filtered'])
plt.xlabel('Time (s)')
plt.ylabel('Amplitude (a.u.)')
plt.xticks(np.linspace(-1, 1, 10, endpoint=False))
plt.figure(figsize=(8,6))
plt.plot(t_test, test_sig, linewidth=1.5, color=sns.color_palette()[0])
plt.plot(t_test, y_bp_noisy, linewidth=1.5, color=sns.color_palette()[2])
plt.ylim(-1.2,1.2)
plt.title('Original and filtered test signal')
plt.legend(['Original', 'Filtered'])
plt.xlabel('Time (s)')
plt.ylabel('Amplitude (a.u.)')
plt.xticks(np.linspace(-1, 1, 10, endpoint=False))
plt.show()
In [163]:
SessionData = pd.read_csv('../data/train/Data_S02_Sess01.csv', header=0, usecols=['Time', 'Cz', 'EOG', 'FeedBackEvent'])
SessionData.head()
Out[163]:
Time
Cz
EOG
FeedBackEvent
0
0.000
311.298295
-906.668876
0
1
0.005
551.888548
-1484.107119
0
2
0.010
478.480250
-1313.435186
0
3
0.015
502.729161
-1391.966973
0
4
0.020
479.678270
-1347.494166
0
In [168]:
t = SessionData['Time']
eog = SessionData['EOG']
cz = SessionData['Cz']
event_ch = SessionData['FeedBackEvent']
In [165]:
#%matplotlib qt
In [169]:
eog_filt = sig.filtfilt(b, a, eog, padtype='even')
cz_filt = sig.filtfilt(b, a, cz, padtype='even')
In [189]:
plt.figure()
plt.plot(t, eog, t, eog_filt)
plt.show()
In [22]:
plt.figure()
plt.plot(t, cz, t, cz_filt)
plt.show()
In [196]:
%matplotlib inline
plt.figure(figsize=(8,6))
plt.plot(t, cz_filt)
plt.plot(t, eog_filt)
plt.legend(['Cz', 'EOG'])
plt.title('Eye blink artifact')
plt.xlabel('Time (s)')
plt.ylabel('Amplitude (uV)')
plt.xlim(116, 120)
plt.ylim(-150, 250)
plt.show()
In [24]:
plt.figure()
plt.scatter(cz_filt, eog_filt)
plt.show()
In [25]:
mod = sm.OLS(cz_filt, eog_filt) # Describe model
res = mod.fit() # Fit model
print res.summary() # Summarize model
OLS Regression Results
==============================================================================
Dep. Variable: y R-squared: 0.391
Model: OLS Adj. R-squared: 0.391
Method: Least Squares F-statistic: 8.476e+04
Date: Thu, 11 Dec 2014 Prob (F-statistic): 0.00
Time: 17:13:29 Log-Likelihood: -5.5911e+05
No. Observations: 132001 AIC: 1.118e+06
Df Residuals: 132000 BIC: 1.118e+06
Df Model: 1
==============================================================================
coef std err t P>|t| [95.0% Conf. Int.]
------------------------------------------------------------------------------
x1 0.2061 0.001 291.132 0.000 0.205 0.208
==============================================================================
Omnibus: 78456.576 Durbin-Watson: 0.040
Prob(Omnibus): 0.000 Jarque-Bera (JB): 6048346.863
Skew: 2.049 Prob(JB): 0.00
Kurtosis: 35.907 Cond. No. 1.00
==============================================================================
In [26]:
cz_clean = cz_filt - res.params[0] * eog_filt
In [27]:
plt.figure()
plt.plot(t, cz_filt, t, cz_clean + 300, t, eog_filt - 300)
plt.show()
In [162]:
plt.figure()
plt.plot(t, cz_filt, t, cz_clean)
plt.show()
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
<ipython-input-162-24cfa32ad8aa> in <module>()
1 plt.figure()
----> 2 plt.plot(t, cz_filt, t, cz_clean)
3 plt.show()
NameError: name 't' is not defined
<matplotlib.figure.Figure at 0x10cb33150>
In [30]:
event_times = SessionData.Time[SessionData.FeedBackEvent == 1]
In [31]:
plt.figure()
plt.plot(t, cz_clean)
plt.plot(event_times, 100*np.ones(np.shape(event_times)), 'r|')
plt.show()
In [32]:
plt.figure()
plt.plot(t, eog_filt)
plt.plot(event_times, 100*np.ones(np.shape(event_times)), 'r|')
plt.show()
In [33]:
def get_epochs(x, idxs, epoch_start, epoch_end):
'''
The indices and boundaries are given in samples.
'''
epoched_x = x[:, np.array([idx + np.arange(epoch_start, epoch_end + 1) for idx in idxs])]
epoched_x = epoched_x.transpose([0, 2, 1]) # rearranges dimensions into: channel X time X epoch
return epoched_x
In [136]:
def remove_baseline(epoched_x, epoch_start, baseline_start, baseline_end):
new_epoched_x = np.zeros_like(epoched_x)
idx_start = baseline_start - epoch_start
idx_end = baseline_end - epoch_start
for i_trial in range(np.size(epoched_x, 2)):
for i_ch in range(np.size(epoched_x, 0)):
baseline = np.mean(epoched_x[i_ch, idx_start:idx_end, i_trial])
new_epoched_x[i_ch, :, i_trial] = epoched_x[i_ch, :, i_trial] - baseline
return new_epoched_x
In [34]:
def lat2idx(lats, Fs):
'''
Latencies lats in seconds transformed to sample indices using sampling frequency Fs in Hz.
'''
return np.array([int(lat * Fs) for lat in lats])
In [35]:
def idx2lat(idxs, Fs):
'''
Sample indices idxs transformed to latencies in seconds using sampling frequency Fs in Hz.
'''
return np.array([float(idx) / Fs for idx in idxs])
In [39]:
event_idxs = lat2idx(event_times, Fs)
(epoch_start, epoch_end) = lat2idx((-0.2, 0.8), Fs)
In [132]:
cz_clean_epoched = get_epochs(cz_clean[np.newaxis], event_idxs, epoch_start, epoch_end)
In [133]:
np.shape(cz_clean_epoched)
Out[133]:
(1, 201, 60)
In [134]:
t_epoch = np.linspace(-0.2, 0.8, epoch_end - epoch_start + 1)
plt.figure()
plt.plot(t_epoch, cz_clean_epoched[0,:,:])
plt.show()
In [82]:
error_idxs = ErrorFeedbacks[(ErrorFeedbacks['Subject'] == 2) & (ErrorFeedbacks['Session'] == 1)].FeedbackNo
In [135]:
plt.figure()
plt.plot(t_epoch, np.mean(cz_clean_epoched[0,:,:], 1))
plt.show()
In [118]:
plt.figure()
plt.plot(t_epoch, np.squeeze(np.mean(cz_clean_epoched[:,:,error_idxs.values], 2)))
plt.show()
In [102]:
np.shape(cz_clean_epoched[0,:,error_idxs.values[None].T])
Out[102]:
(10, 1, 201)
In [137]:
cz_clean_epoched_nobline = remove_baseline(cz_clean_epoched, -40, -40, 0)
In [138]:
plt.figure()
plt.plot(t_epoch, cz_clean_epoched_nobline[0,:,:])
plt.show()
In [151]:
plt.figure()
plt.plot(t_epoch, np.squeeze(np.mean(cz_clean_epoched_nobline[:,:,error_idxs.values], 2)) - np.mean(cz_clean_epoched_nobline[0,:,:], 1))
plt.grid()
plt.vlines([0.325,0.375], -20, 20, 'r')
plt.vlines([0.455,0.505], -20, 20, 'g')
plt.show()
In [282]:
TrainLabels['Cz ERP'] = (np.nan).astype(int)
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
<ipython-input-282-aaf88e310433> in <module>()
----> 1 TrainLabels['Cz ERP'] = (np.nan).astype(int)
AttributeError: 'float' object has no attribute 'astype'
In [281]:
TrainLabels.head()
Out[281]:
IdFeedBack
Subject
Session
FeedbackNo
Prediction
Cz ERP
0
S02_Sess01_FB001
2
1
1
1
NaN
1
S02_Sess01_FB002
2
1
2
1
NaN
2
S02_Sess01_FB003
2
1
3
0
NaN
3
S02_Sess01_FB004
2
1
4
0
NaN
4
S02_Sess01_FB005
2
1
5
1
NaN
In [220]:
gb = TrainLabels.groupby(['Subject', 'Session'])
In [240]:
len(gb.groups)
Out[240]:
80
In [283]:
TrainLabels['Cz ERP'] = TrainLabels['Cz ERP'].astype(object)
In [284]:
TrainLabels.dtypes
Out[284]:
IdFeedBack object
Subject int64
Session int64
FeedbackNo int64
Prediction int64
Cz ERP object
dtype: object
In [251]:
df=pd.DataFrame(index=['A','B','C'], columns=['x','y'])
In [252]:
df
Out[252]:
x
y
A
NaN
NaN
B
NaN
NaN
C
NaN
NaN
In [257]:
df.at['A','y'] = np.array([2,4,5])
In [258]:
df
Out[258]:
x
y
A
NaN
[2, 4, 5]
B
NaN
NaN
C
NaN
NaN
In [259]:
df.dtypes
Out[259]:
x object
y object
dtype: object
In [285]:
TrainLabels.dtypes
Out[285]:
IdFeedBack object
Subject int64
Session int64
FeedbackNo int64
Prediction int64
Cz ERP object
dtype: object
In [286]:
TrainGroups = TrainLabels.groupby(['Subject','Session'])
In [292]:
Out[292]:
<function items>
In [312]:
for ((subject, session), rows) in TrainGroups.groups.iteritems():
print subject, session, rows[0:5], '...'
23 4 [4600, 4601, 4602, 4603, 4604] ...
7 3 [800, 801, 802, 803, 804] ...
12 1 [1360, 1361, 1362, 1363, 1364] ...
20 3 [3520, 3521, 3522, 3523, 3524] ...
17 5 [2960, 2961, 2962, 2963, 2964] ...
14 4 [2220, 2221, 2222, 2223, 2224] ...
11 2 [1080, 1081, 1082, 1083, 1084] ...
17 3 [2840, 2841, 2842, 2843, 2844] ...
16 1 [2380, 2381, 2382, 2383, 2384] ...
2 1 [0, 1, 2, 3, 4] ...
13 5 [1940, 1941, 1942, 1943, 1944] ...
12 5 [1600, 1601, 1602, 1603, 1604] ...
23 3 [4540, 4541, 4542, 4543, 4544] ...
6 2 [400, 401, 402, 403, 404] ...
17 2 [2780, 2781, 2782, 2783, 2784] ...
13 2 [1760, 1761, 1762, 1763, 1764] ...
2 5 [240, 241, 242, 243, 244] ...
7 2 [740, 741, 742, 743, 744] ...
12 2 [1420, 1421, 1422, 1423, 1424] ...
22 2 [4140, 4141, 4142, 4143, 4144] ...
14 5 [2280, 2281, 2282, 2283, 2284] ...
11 5 [1260, 1261, 1262, 1263, 1264] ...
21 1 [3740, 3741, 3742, 3743, 3744] ...
16 3 [2500, 2501, 2502, 2503, 2504] ...
16 4 [2560, 2561, 2562, 2563, 2564] ...
18 4 [3240, 3241, 3242, 3243, 3244] ...
26 5 [5340, 5341, 5342, 5343, 5344] ...
23 2 [4480, 4481, 4482, 4483, 4484] ...
6 3 [460, 461, 462, 463, 464] ...
14 1 [2040, 2041, 2042, 2043, 2044] ...
11 1 [1020, 1021, 1022, 1023, 1024] ...
17 4 [2900, 2901, 2902, 2903, 2904] ...
2 2 [60, 61, 62, 63, 64] ...
24 1 [4760, 4761, 4762, 4763, 4764] ...
20 4 [3580, 3581, 3582, 3583, 3584] ...
13 4 [1880, 1881, 1882, 1883, 1884] ...
12 3 [1480, 1481, 1482, 1483, 1484] ...
21 5 [3980, 3981, 3982, 3983, 3984] ...
22 3 [4200, 4201, 4202, 4203, 4204] ...
6 4 [520, 521, 522, 523, 524] ...
18 2 [3120, 3121, 3122, 3123, 3124] ...
11 4 [1200, 1201, 1202, 1203, 1204] ...
7 1 [680, 681, 682, 683, 684] ...
24 5 [5000, 5001, 5002, 5003, 5004] ...
21 2 [3800, 3801, 3802, 3803, 3804] ...
20 1 [3400, 3401, 3402, 3403, 3404] ...
17 1 [2720, 2721, 2722, 2723, 2724] ...
16 2 [2440, 2441, 2442, 2443, 2444] ...
18 5 [3300, 3301, 3302, 3303, 3304] ...
21 4 [3920, 3921, 3922, 3923, 3924] ...
7 5 [920, 921, 922, 923, 924] ...
2 3 [120, 121, 122, 123, 124] ...
24 2 [4820, 4821, 4822, 4823, 4824] ...
23 1 [4420, 4421, 4422, 4423, 4424] ...
20 5 [3640, 3641, 3642, 3643, 3644] ...
18 3 [3180, 3181, 3182, 3183, 3184] ...
14 2 [2100, 2101, 2102, 2103, 2104] ...
6 5 [580, 581, 582, 583, 584] ...
13 1 [1700, 1701, 1702, 1703, 1704] ...
18 1 [3060, 3061, 3062, 3063, 3064] ...
23 5 [4660, 4661, 4662, 4663, 4664] ...
16 5 [2620, 2621, 2622, 2623, 2624] ...
26 1 [5100, 5101, 5102, 5103, 5104] ...
22 4 [4260, 4261, 4262, 4263, 4264] ...
20 2 [3460, 3461, 3462, 3463, 3464] ...
6 1 [340, 341, 342, 343, 344] ...
13 3 [1820, 1821, 1822, 1823, 1824] ...
26 2 [5160, 5161, 5162, 5163, 5164] ...
11 3 [1140, 1141, 1142, 1143, 1144] ...
22 5 [4320, 4321, 4322, 4323, 4324] ...
21 3 [3860, 3861, 3862, 3863, 3864] ...
7 4 [860, 861, 862, 863, 864] ...
24 3 [4880, 4881, 4882, 4883, 4884] ...
12 4 [1540, 1541, 1542, 1543, 1544] ...
24 4 [4940, 4941, 4942, 4943, 4944] ...
26 3 [5220, 5221, 5222, 5223, 5224] ...
14 3 [2160, 2161, 2162, 2163, 2164] ...
22 1 [4080, 4081, 4082, 4083, 4084] ...
2 4 [180, 181, 182, 183, 184] ...
26 4 [5280, 5281, 5282, 5283, 5284] ...
In [314]:
'../data/train/Data_S%02d_Sess%02d.csv' % (5,13)
Out[314]:
'../data/train/Data_S05_Sess13.csv'
In [341]:
def mean_amplitude(epoched_x, epoch_start, peak_start, peak_end):
'''
Calculates mean amplitude for each channel and each trial of epoched x. Peak start and end are given in sample indices.
'''
idx_start = peak_start - epoch_start
idx_end = peak_end - epoch_start
n_trial = np.size(epoched_x, 2)
n_chan = np.size(epoched_x, 0)
amps = np.zeros((n_trial, n_chan))
for i_trial in range(n_trial):
for i_chan in range(n_chan):
amps[i_trial, i_chan] = np.mean(epoched_x[i_chan, idx_start:idx_end, i_trial])
return amps
In [316]:
np.shape(cz_clean_epoched_nobline)
Out[316]:
(1, 201, 60)
In [343]:
np.size(mean_amplitude(cz_clean_epoched_nobline, epoch_start, 50, 60))
Out[343]:
60
In [349]:
plt.figure()
plt.plot(test_sig)
plt.grid()
plt.vlines([185,195], -1, 1, 'r')
plt.vlines([205,215], -1, 1, 'g')
plt.show()
In [360]:
test_sig2 = test_sig[None][None]
np.shape(test_sig2)
test_sig2 = np.transpose(test_sig2, [0, 2, 1])
np.shape(test_sig2)
Out[360]:
(1, 400, 1)
In [370]:
mean_amplitude(test_sig2,199,-15,-5)
Out[370]:
array([[-0.40887806]])
In [371]:
mean_amplitude(test_sig2,199,5,15)
Out[371]:
array([[ 0.36179721]])
In [211]:
import pickle
Results = pd.read_csv('../results/trial_description.csv', header=0, index_col=0)
Cz_ERP = pickle.load(open('../results/Cz_ERP.out','rb'))
In [212]:
Results.head()
Out[212]:
IdFeedBack
Subject
Session
FeedbackNo
AbsTrialNum
Prediction
Neg-ErrP
Pos-ErrP
0
S02_Sess01_FB001
2
1
1
1
1
-1.961917
-13.298846
1
S02_Sess01_FB002
2
1
2
2
1
-6.076947
-6.784920
2
S02_Sess01_FB003
2
1
3
3
0
-12.275108
-10.378506
3
S02_Sess01_FB004
2
1
4
4
0
-4.015466
5.733316
4
S02_Sess01_FB005
2
1
5
5
1
-15.741248
-34.713033
In [213]:
Results.describe()
Out[213]:
Subject
Session
FeedbackNo
AbsTrialNum
Prediction
Neg-ErrP
Pos-ErrP
count
5440.000000
5440.000000
5440.000000
5440.000000
5440.000000
5440.000000
5440.000000
mean
15.750000
3.235294
36.382353
170.500000
0.707721
10.287424
11.973373
std
6.732075
1.476595
23.236257
98.158144
0.454852
26.247572
31.330566
min
2.000000
1.000000
1.000000
1.000000
0.000000
-779.111783
-1031.277903
25%
11.750000
2.000000
17.750000
85.750000
0.000000
0.730229
1.311256
50%
16.500000
3.000000
34.500000
170.500000
1.000000
10.440637
11.996883
75%
21.250000
5.000000
51.250000
255.250000
1.000000
20.555335
22.990085
max
26.000000
5.000000
100.000000
340.000000
1.000000
763.365087
532.537258
In [43]:
np.shape(Cz_ERP[256])
Out[43]:
(1, 201)
In [214]:
n_errors = 0
n_corr = 0
grand_avg_err = np.zeros_like(Cz_ERP[1])
grand_avg_corr = np.zeros_like(Cz_ERP[1])
for row in Results.index:
if Results.loc[row, 'Prediction'] == 0:
grand_avg_err += Cz_ERP[row]
n_errors += 1
else:
grand_avg_corr += Cz_ERP[row]
n_corr += 1
grand_avg_err /= n_errors
grand_avg_corr /= n_corr
In [36]:
n_errors, n_corr
Out[36]:
(1590, 3850)
In [227]:
t_epoch = np.linspace(-0.2, 0.8, 201)
plt.figure(figsize=(10,6))
plt.plot(t_epoch, grand_avg_err[0], t_epoch, grand_avg_corr[0], t_epoch, grand_avg_err[0] - grand_avg_corr[0])
plt.title('Grand average event-related potentials')
plt.xlabel('Time (s)')
plt.ylabel('Amplitude (uV)')
plt.vlines([0.325,0.435], -5, 20, 'm', linestyles='dashed')
plt.vlines([0.550,0.650], -5, 20, 'c', linestyles='dashed')
plt.legend(['Error', 'Correct', 'Error - Correct', 'Neg-ErrP', 'Pos-ErrP'], loc='best')
plt.show()
In [65]:
np.shape(t_epoch)
Out[65]:
(201,)
In [218]:
import seaborn as sns
sns.set(style="darkgrid")
color = sns.color_palette()[2]
g = sns.jointplot("AbsTrialNum", "Neg-ErrP", data=Results[Results['Prediction'] == 0], kind="reg",
xlim=(0, 340), ylim=(-75, 75), color=color, size=7)
In [219]:
color = sns.color_palette()[2]
g = sns.jointplot("AbsTrialNum", "Pos-ErrP", data=Results[Results['Prediction'] == 0], kind="reg",
xlim=(0, 340), ylim=(-75, 75), color=color, size=7)
In [47]:
sns.set(style="ticks")
g = sns.factorplot("Subject", "Neg-ErrP", data=Results[Results['Prediction'] == 0], kind="box", aspect=1.25)
plt.ylim(-50, 50)
Out[47]:
(-50, 50)
In [26]:
sns.boxplot(Results[['Subject','Neg-ErrP']], groupby = 'Subject')
Out[26]:
<matplotlib.axes._subplots.AxesSubplot at 0x10b5ecdd0>
In [31]:
groups = pd.groupby(Results['Neg-ErrP'], 'Subject')
---------------------------------------------------------------------------
KeyError Traceback (most recent call last)
<ipython-input-31-dbbf6f76fcc0> in <module>()
----> 1 groups = pd.groupby(Results['Neg-ErrP'], 'Subject')
/Users/fmelinscak/anaconda/lib/python2.7/site-packages/pandas/core/groupby.pyc in groupby(obj, by, **kwds)
1140 raise TypeError('invalid type: %s' % type(obj))
1141
-> 1142 return klass(obj, by, **kwds)
1143
1144
/Users/fmelinscak/anaconda/lib/python2.7/site-packages/pandas/core/groupby.pyc in __init__(self, obj, keys, axis, level, grouper, exclusions, selection, as_index, sort, group_keys, squeeze)
386 if grouper is None:
387 grouper, exclusions, obj = _get_grouper(obj, keys, axis=axis,
--> 388 level=level, sort=sort)
389
390 self.obj = obj
/Users/fmelinscak/anaconda/lib/python2.7/site-packages/pandas/core/groupby.pyc in _get_grouper(obj, key, axis, level, sort)
2039 exclusions.append(gpr)
2040 name = gpr
-> 2041 gpr = obj[gpr]
2042
2043 if isinstance(gpr, Categorical) and len(gpr) != len(obj):
/Users/fmelinscak/anaconda/lib/python2.7/site-packages/pandas/core/series.pyc in __getitem__(self, key)
482 def __getitem__(self, key):
483 try:
--> 484 result = self.index.get_value(self, key)
485
486 if not np.isscalar(result):
/Users/fmelinscak/anaconda/lib/python2.7/site-packages/pandas/core/index.pyc in get_value(self, series, key)
1194
1195 try:
-> 1196 return self._engine.get_value(s, k)
1197 except KeyError as e1:
1198 if len(self) > 0 and self.inferred_type in ['integer','boolean']:
/Users/fmelinscak/anaconda/lib/python2.7/site-packages/pandas/index.so in pandas.index.IndexEngine.get_value (pandas/index.c:2993)()
/Users/fmelinscak/anaconda/lib/python2.7/site-packages/pandas/index.so in pandas.index.IndexEngine.get_value (pandas/index.c:2808)()
/Users/fmelinscak/anaconda/lib/python2.7/site-packages/pandas/index.so in pandas.index.IndexEngine.get_loc (pandas/index.c:3583)()
KeyError: 'Subject'
In [48]:
SubjectResults = pd.groupby(Results, 'Subject')
In [55]:
for subject in SubjectResults.groups:
x = SubjectResults.get_group(subject)
print x
AbsTrialNum FeedbackNo IdFeedBack Neg-ErrP Pos-ErrP \
0 1 1 S02_Sess01_FB001 1.366985 11.883175
1 2 2 S02_Sess01_FB002 -4.938311 -9.079726
2 3 3 S02_Sess01_FB003 -8.499408 -18.628724
3 4 4 S02_Sess01_FB004 1.258571 -2.071433
4 5 5 S02_Sess01_FB005 -13.459864 -24.976446
5 6 6 S02_Sess01_FB006 2.706470 -10.709682
6 7 7 S02_Sess01_FB007 27.539364 9.371415
7 8 8 S02_Sess01_FB008 24.590155 19.551647
8 9 9 S02_Sess01_FB009 5.173467 -2.336465
9 10 10 S02_Sess01_FB010 11.225228 6.547423
10 11 11 S02_Sess01_FB011 13.285976 3.230335
11 12 12 S02_Sess01_FB012 -8.017653 -6.543260
12 13 13 S02_Sess01_FB013 18.734346 -3.818736
13 14 14 S02_Sess01_FB014 2.590997 0.879611
14 15 15 S02_Sess01_FB015 32.855044 23.473103
15 16 16 S02_Sess01_FB016 19.650544 19.782064
16 17 17 S02_Sess01_FB017 -16.675222 -17.406362
17 18 18 S02_Sess01_FB018 48.006727 93.138928
18 19 19 S02_Sess01_FB019 24.447331 30.274885
19 20 20 S02_Sess01_FB020 31.481804 16.322803
20 21 21 S02_Sess01_FB021 57.926558 35.345646
21 22 22 S02_Sess01_FB022 1.648875 -3.550466
22 23 23 S02_Sess01_FB023 1.817606 -7.283275
23 24 24 S02_Sess01_FB024 -1.681148 -9.692342
24 25 25 S02_Sess01_FB025 66.940484 49.242642
25 26 26 S02_Sess01_FB026 -5.686291 -0.312290
26 27 27 S02_Sess01_FB027 13.234326 4.838569
27 28 28 S02_Sess01_FB028 -17.936231 -11.699768
28 29 29 S02_Sess01_FB029 17.221904 -17.483522
29 30 30 S02_Sess01_FB030 13.469410 7.813637
.. ... ... ... ... ...
310 311 71 S02_Sess05_FB071 4.985427 33.282233
311 312 72 S02_Sess05_FB072 34.846949 68.439222
312 313 73 S02_Sess05_FB073 -6.900609 19.982901
313 314 74 S02_Sess05_FB074 21.102449 63.323580
314 315 75 S02_Sess05_FB075 31.471588 50.180836
315 316 76 S02_Sess05_FB076 53.063619 66.219441
316 317 77 S02_Sess05_FB077 -8.085234 21.544697
317 318 78 S02_Sess05_FB078 36.890445 86.466944
318 319 79 S02_Sess05_FB079 6.252487 78.811318
319 320 80 S02_Sess05_FB080 42.490300 66.498834
320 321 81 S02_Sess05_FB081 41.632993 64.586751
321 322 82 S02_Sess05_FB082 49.158672 115.013883
322 323 83 S02_Sess05_FB083 75.995710 77.655199
323 324 84 S02_Sess05_FB084 42.311855 81.592186
324 325 85 S02_Sess05_FB085 58.722835 70.558536
325 326 86 S02_Sess05_FB086 12.812951 51.258342
326 327 87 S02_Sess05_FB087 60.157683 70.970268
327 328 88 S02_Sess05_FB088 41.252863 23.026006
328 329 89 S02_Sess05_FB089 32.997368 72.153128
329 330 90 S02_Sess05_FB090 55.512597 91.463860
330 331 91 S02_Sess05_FB091 11.034939 60.444842
331 332 92 S02_Sess05_FB092 52.313117 65.810760
332 333 93 S02_Sess05_FB093 44.267945 86.257290
333 334 94 S02_Sess05_FB094 32.778179 -10.661591
334 335 95 S02_Sess05_FB095 40.164872 55.344174
335 336 96 S02_Sess05_FB096 26.765588 51.568619
336 337 97 S02_Sess05_FB097 38.626983 64.088686
337 338 98 S02_Sess05_FB098 77.450398 78.689340
338 339 99 S02_Sess05_FB099 5.498765 47.071841
339 340 100 S02_Sess05_FB100 37.012523 56.669087
Prediction Session
0 1 1
1 1 1
2 0 1
3 0 1
4 1 1
5 0 1
6 1 1
7 1 1
8 0 1
9 1 1
10 1 1
11 1 1
12 0 1
13 1 1
14 1 1
15 1 1
16 1 1
17 1 1
18 1 1
19 1 1
20 1 1
21 1 1
22 1 1
23 0 1
24 1 1
25 0 1
26 1 1
27 0 1
28 1 1
29 1 1
.. ... ...
310 0 5
311 0 5
312 1 5
313 0 5
314 0 5
315 1 5
316 0 5
317 0 5
318 1 5
319 1 5
320 1 5
321 1 5
322 0 5
323 1 5
324 1 5
325 0 5
326 1 5
327 1 5
328 0 5
329 1 5
330 0 5
331 1 5
332 1 5
333 1 5
334 1 5
335 0 5
336 1 5
337 0 5
338 1 5
339 1 5
[340 rows x 7 columns]
AbsTrialNum FeedbackNo IdFeedBack Neg-ErrP Pos-ErrP \
340 1 1 S06_Sess01_FB001 24.516450 26.967332
341 2 2 S06_Sess01_FB002 -1.571457 7.859290
342 3 3 S06_Sess01_FB003 18.008877 4.799151
343 4 4 S06_Sess01_FB004 -16.404307 -4.139963
344 5 5 S06_Sess01_FB005 -29.325994 -79.589553
345 6 6 S06_Sess01_FB006 31.715947 25.602029
346 7 7 S06_Sess01_FB007 -6.264365 21.677672
347 8 8 S06_Sess01_FB008 -259.656984 -274.254850
348 9 9 S06_Sess01_FB009 -130.529955 -147.739422
349 10 10 S06_Sess01_FB010 -10.030934 4.783460
350 11 11 S06_Sess01_FB011 -17.611165 -30.878224
351 12 12 S06_Sess01_FB012 -21.639176 -30.647879
352 13 13 S06_Sess01_FB013 28.827496 12.430681
353 14 14 S06_Sess01_FB014 7.896840 12.888608
354 15 15 S06_Sess01_FB015 35.565193 40.717481
355 16 16 S06_Sess01_FB016 -0.029457 -6.062491
356 17 17 S06_Sess01_FB017 26.263635 8.208457
357 18 18 S06_Sess01_FB018 -23.617190 -24.286659
358 19 19 S06_Sess01_FB019 25.091303 25.322554
359 20 20 S06_Sess01_FB020 -6.997923 -13.106334
360 21 21 S06_Sess01_FB021 15.699354 17.465577
361 22 22 S06_Sess01_FB022 16.873847 5.736772
362 23 23 S06_Sess01_FB023 4.176602 19.173692
363 24 24 S06_Sess01_FB024 23.667446 31.609571
364 25 25 S06_Sess01_FB025 9.094528 17.059385
365 26 26 S06_Sess01_FB026 -13.772834 -6.284825
366 27 27 S06_Sess01_FB027 -16.805666 -15.312830
367 28 28 S06_Sess01_FB028 15.953913 3.730197
368 29 29 S06_Sess01_FB029 10.399631 22.246044
369 30 30 S06_Sess01_FB030 -24.106649 -22.987131
.. ... ... ... ... ...
650 311 71 S06_Sess05_FB071 14.733682 18.859735
651 312 72 S06_Sess05_FB072 13.741071 16.107147
652 313 73 S06_Sess05_FB073 12.398834 20.633635
653 314 74 S06_Sess05_FB074 32.042877 27.920632
654 315 75 S06_Sess05_FB075 19.935026 21.314393
655 316 76 S06_Sess05_FB076 16.295927 12.842023
656 317 77 S06_Sess05_FB077 -7.923389 -7.497991
657 318 78 S06_Sess05_FB078 16.719632 5.276841
658 319 79 S06_Sess05_FB079 45.791659 34.315218
659 320 80 S06_Sess05_FB080 0.000643 10.820290
660 321 81 S06_Sess05_FB081 17.623747 5.514624
661 322 82 S06_Sess05_FB082 20.928623 6.894884
662 323 83 S06_Sess05_FB083 51.941621 51.641251
663 324 84 S06_Sess05_FB084 9.718535 5.162707
664 325 85 S06_Sess05_FB085 -17.156129 -1.853606
665 326 86 S06_Sess05_FB086 8.056371 -2.951979
666 327 87 S06_Sess05_FB087 2.855830 -5.441513
667 328 88 S06_Sess05_FB088 15.824977 22.874169
668 329 89 S06_Sess05_FB089 6.291315 47.335430
669 330 90 S06_Sess05_FB090 3.404851 70.189845
670 331 91 S06_Sess05_FB091 9.348092 5.533807
671 332 92 S06_Sess05_FB092 -8.556433 -39.973318
672 333 93 S06_Sess05_FB093 2.185702 4.966683
673 334 94 S06_Sess05_FB094 -15.557040 -14.561372
674 335 95 S06_Sess05_FB095 -24.416008 -21.845899
675 336 96 S06_Sess05_FB096 28.120297 29.882190
676 337 97 S06_Sess05_FB097 83.945864 76.459103
677 338 98 S06_Sess05_FB098 3.490937 14.409418
678 339 99 S06_Sess05_FB099 0.678528 18.233418
679 340 100 S06_Sess05_FB100 -18.676292 52.868546
Prediction Session
340 1 1
341 1 1
342 1 1
343 1 1
344 0 1
345 1 1
346 1 1
347 1 1
348 1 1
349 1 1
350 1 1
351 1 1
352 1 1
353 1 1
354 1 1
355 1 1
356 1 1
357 1 1
358 1 1
359 1 1
360 1 1
361 1 1
362 1 1
363 1 1
364 1 1
365 1 1
366 1 1
367 1 1
368 1 1
369 1 1
.. ... ...
650 1 5
651 1 5
652 0 5
653 1 5
654 1 5
655 1 5
656 0 5
657 1 5
658 1 5
659 1 5
660 1 5
661 1 5
662 1 5
663 1 5
664 1 5
665 1 5
666 1 5
667 1 5
668 0 5
669 1 5
670 1 5
671 1 5
672 1 5
673 0 5
674 1 5
675 1 5
676 1 5
677 1 5
678 1 5
679 1 5
[340 rows x 7 columns]
AbsTrialNum FeedbackNo IdFeedBack Neg-ErrP Pos-ErrP \
680 1 1 S07_Sess01_FB001 36.231992 26.215220
681 2 2 S07_Sess01_FB002 28.203432 18.473505
682 3 3 S07_Sess01_FB003 -0.927078 -10.290959
683 4 4 S07_Sess01_FB004 9.993619 11.040110
684 5 5 S07_Sess01_FB005 -35.464155 -15.333664
685 6 6 S07_Sess01_FB006 -1.426977 1.972742
686 7 7 S07_Sess01_FB007 3.782477 -7.507769
687 8 8 S07_Sess01_FB008 15.030526 19.029792
688 9 9 S07_Sess01_FB009 -1.467589 7.110596
689 10 10 S07_Sess01_FB010 8.504749 -8.086662
690 11 11 S07_Sess01_FB011 28.191398 20.653657
691 12 12 S07_Sess01_FB012 39.351436 15.062619
692 13 13 S07_Sess01_FB013 23.412663 11.910919
693 14 14 S07_Sess01_FB014 -4.983552 -8.528601
694 15 15 S07_Sess01_FB015 8.806599 3.146630
695 16 16 S07_Sess01_FB016 19.938292 17.676531
696 17 17 S07_Sess01_FB017 -12.424730 -19.661963
697 18 18 S07_Sess01_FB018 4.833348 5.635439
698 19 19 S07_Sess01_FB019 16.518733 12.124657
699 20 20 S07_Sess01_FB020 17.066172 15.420350
700 21 21 S07_Sess01_FB021 37.163043 20.878709
701 22 22 S07_Sess01_FB022 10.112337 5.603287
702 23 23 S07_Sess01_FB023 1.485260 -15.865401
703 24 24 S07_Sess01_FB024 21.900605 15.007809
704 25 25 S07_Sess01_FB025 31.834711 15.097741
705 26 26 S07_Sess01_FB026 9.461583 -0.161290
706 27 27 S07_Sess01_FB027 20.359069 2.412795
707 28 28 S07_Sess01_FB028 16.530734 19.645678
708 29 29 S07_Sess01_FB029 16.649784 7.510850
709 30 30 S07_Sess01_FB030 57.588212 40.992248
... ... ... ... ... ...
990 311 71 S07_Sess05_FB071 3.734795 6.024993
991 312 72 S07_Sess05_FB072 21.948160 6.134331
992 313 73 S07_Sess05_FB073 9.280023 -4.971403
993 314 74 S07_Sess05_FB074 50.003939 1.979386
994 315 75 S07_Sess05_FB075 50.768812 45.718208
995 316 76 S07_Sess05_FB076 14.857076 3.387264
996 317 77 S07_Sess05_FB077 29.013135 52.778367
997 318 78 S07_Sess05_FB078 -2.991216 4.048272
998 319 79 S07_Sess05_FB079 34.133482 26.910144
999 320 80 S07_Sess05_FB080 64.376267 37.539420
1000 321 81 S07_Sess05_FB081 31.054400 10.511128
1001 322 82 S07_Sess05_FB082 15.033324 28.372196
1002 323 83 S07_Sess05_FB083 20.951837 18.931128
1003 324 84 S07_Sess05_FB084 21.961522 4.542804
1004 325 85 S07_Sess05_FB085 45.777401 42.194833
1005 326 86 S07_Sess05_FB086 37.815130 21.260477
1006 327 87 S07_Sess05_FB087 5.573733 15.432372
1007 328 88 S07_Sess05_FB088 36.486626 33.424498
1008 329 89 S07_Sess05_FB089 18.450914 65.253658
1009 330 90 S07_Sess05_FB090 59.467047 43.165089
1010 331 91 S07_Sess05_FB091 41.004553 31.421037
1011 332 92 S07_Sess05_FB092 13.144689 34.823930
1012 333 93 S07_Sess05_FB093 66.561925 61.604131
1013 334 94 S07_Sess05_FB094 25.026416 15.325064
1014 335 95 S07_Sess05_FB095 1.349447 -17.336960
1015 336 96 S07_Sess05_FB096 49.532020 26.027032
1016 337 97 S07_Sess05_FB097 16.735650 46.272287
1017 338 98 S07_Sess05_FB098 -1.012769 -3.759822
1018 339 99 S07_Sess05_FB099 77.206836 36.327444
1019 340 100 S07_Sess05_FB100 51.950106 36.564545
Prediction Session
680 1 1
681 1 1
682 1 1
683 1 1
684 1 1
685 1 1
686 0 1
687 0 1
688 1 1
689 1 1
690 1 1
691 1 1
692 1 1
693 1 1
694 1 1
695 1 1
696 1 1
697 1 1
698 1 1
699 1 1
700 1 1
701 1 1
702 1 1
703 1 1
704 1 1
705 1 1
706 1 1
707 1 1
708 1 1
709 1 1
... ... ...
990 1 5
991 1 5
992 1 5
993 1 5
994 1 5
995 1 5
996 0 5
997 1 5
998 1 5
999 1 5
1000 1 5
1001 0 5
1002 1 5
1003 1 5
1004 1 5
1005 1 5
1006 0 5
1007 1 5
1008 1 5
1009 1 5
1010 1 5
1011 0 5
1012 1 5
1013 1 5
1014 1 5
1015 1 5
1016 1 5
1017 1 5
1018 1 5
1019 1 5
[340 rows x 7 columns]
AbsTrialNum FeedbackNo IdFeedBack Neg-ErrP Pos-ErrP \
1020 1 1 S11_Sess01_FB001 6.156023 -2.008641
1021 2 2 S11_Sess01_FB002 20.312577 22.520090
1022 3 3 S11_Sess01_FB003 13.250036 4.955888
1023 4 4 S11_Sess01_FB004 -4.848267 6.661369
1024 5 5 S11_Sess01_FB005 22.836204 9.291899
1025 6 6 S11_Sess01_FB006 102.301281 100.226499
1026 7 7 S11_Sess01_FB007 2.937390 25.477451
1027 8 8 S11_Sess01_FB008 10.454844 13.330175
1028 9 9 S11_Sess01_FB009 49.715077 36.482008
1029 10 10 S11_Sess01_FB010 12.779451 22.673896
1030 11 11 S11_Sess01_FB011 13.219372 11.213483
1031 12 12 S11_Sess01_FB012 20.316180 49.106566
1032 13 13 S11_Sess01_FB013 21.434543 24.025209
1033 14 14 S11_Sess01_FB014 -5.682758 3.508702
1034 15 15 S11_Sess01_FB015 0.505871 -11.524283
1035 16 16 S11_Sess01_FB016 21.494218 23.330326
1036 17 17 S11_Sess01_FB017 21.579479 30.905180
1037 18 18 S11_Sess01_FB018 6.039637 0.145763
1038 19 19 S11_Sess01_FB019 101.401253 89.704477
1039 20 20 S11_Sess01_FB020 -5.058795 7.351653
1040 21 21 S11_Sess01_FB021 -5.264386 32.447571
1041 22 22 S11_Sess01_FB022 -1.607967 3.663647
1042 23 23 S11_Sess01_FB023 6.948438 1.035405
1043 24 24 S11_Sess01_FB024 11.545528 20.752368
1044 25 25 S11_Sess01_FB025 20.844426 25.123220
1045 26 26 S11_Sess01_FB026 19.524024 25.804269
1046 27 27 S11_Sess01_FB027 6.843052 21.809518
1047 28 28 S11_Sess01_FB028 13.523960 37.333475
1048 29 29 S11_Sess01_FB029 27.324038 56.122951
1049 30 30 S11_Sess01_FB030 33.331649 18.045014
... ... ... ... ... ...
1330 311 71 S11_Sess05_FB071 2.389672 5.211503
1331 312 72 S11_Sess05_FB072 -4.760572 0.439412
1332 313 73 S11_Sess05_FB073 3.365925 5.294221
1333 314 74 S11_Sess05_FB074 20.313625 9.074438
1334 315 75 S11_Sess05_FB075 6.645309 13.090499
1335 316 76 S11_Sess05_FB076 -1.466836 -14.081043
1336 317 77 S11_Sess05_FB077 -8.057450 4.527307
1337 318 78 S11_Sess05_FB078 -5.366447 1.841160
1338 319 79 S11_Sess05_FB079 14.422551 3.934760
1339 320 80 S11_Sess05_FB080 11.957266 9.960944
1340 321 81 S11_Sess05_FB081 12.209595 0.972433
1341 322 82 S11_Sess05_FB082 35.599733 17.750516
1342 323 83 S11_Sess05_FB083 26.697741 14.175505
1343 324 84 S11_Sess05_FB084 42.237536 23.763551
1344 325 85 S11_Sess05_FB085 -9.749808 -7.038086
1345 326 86 S11_Sess05_FB086 25.926657 16.706111
1346 327 87 S11_Sess05_FB087 -8.360216 -2.483734
1347 328 88 S11_Sess05_FB088 -5.693127 -6.601169
1348 329 89 S11_Sess05_FB089 17.113126 14.221195
1349 330 90 S11_Sess05_FB090 -9.368427 10.966437
1350 331 91 S11_Sess05_FB091 0.391088 -6.408398
1351 332 92 S11_Sess05_FB092 2.796218 -10.106973
1352 333 93 S11_Sess05_FB093 12.871285 10.602265
1353 334 94 S11_Sess05_FB094 21.056257 19.602685
1354 335 95 S11_Sess05_FB095 5.039098 -0.368288
1355 336 96 S11_Sess05_FB096 -0.067822 3.070768
1356 337 97 S11_Sess05_FB097 3.813603 -9.730324
1357 338 98 S11_Sess05_FB098 -11.269726 21.971938
1358 339 99 S11_Sess05_FB099 -4.219015 -13.731775
1359 340 100 S11_Sess05_FB100 6.069752 11.617642
Prediction Session
1020 1 1
1021 1 1
1022 1 1
1023 1 1
1024 1 1
1025 1 1
1026 0 1
1027 1 1
1028 1 1
1029 0 1
1030 1 1
1031 0 1
1032 1 1
1033 1 1
1034 1 1
1035 1 1
1036 1 1
1037 0 1
1038 1 1
1039 1 1
1040 0 1
1041 1 1
1042 1 1
1043 1 1
1044 1 1
1045 1 1
1046 0 1
1047 0 1
1048 0 1
1049 1 1
... ... ...
1330 1 5
1331 1 5
1332 1 5
1333 1 5
1334 0 5
1335 1 5
1336 0 5
1337 0 5
1338 1 5
1339 1 5
1340 1 5
1341 1 5
1342 1 5
1343 1 5
1344 0 5
1345 0 5
1346 0 5
1347 0 5
1348 0 5
1349 1 5
1350 0 5
1351 0 5
1352 1 5
1353 1 5
1354 1 5
1355 1 5
1356 1 5
1357 0 5
1358 1 5
1359 0 5
[340 rows x 7 columns]
AbsTrialNum FeedbackNo IdFeedBack Neg-ErrP Pos-ErrP \
1360 1 1 S12_Sess01_FB001 14.473362 16.169187
1361 2 2 S12_Sess01_FB002 1.986397 15.675379
1362 3 3 S12_Sess01_FB003 20.202987 42.963893
1363 4 4 S12_Sess01_FB004 62.056532 25.578654
1364 5 5 S12_Sess01_FB005 7.095019 -0.087720
1365 6 6 S12_Sess01_FB006 19.714179 26.890339
1366 7 7 S12_Sess01_FB007 45.669534 69.784010
1367 8 8 S12_Sess01_FB008 62.326772 27.536216
1368 9 9 S12_Sess01_FB009 -24.608802 -37.706682
1369 10 10 S12_Sess01_FB010 43.844189 98.133649
1370 11 11 S12_Sess01_FB011 -39.075452 -50.453328
1371 12 12 S12_Sess01_FB012 56.328030 83.522247
1372 13 13 S12_Sess01_FB013 33.214944 -5.515200
1373 14 14 S12_Sess01_FB014 42.724451 40.581939
1374 15 15 S12_Sess01_FB015 113.480114 160.716071
1375 16 16 S12_Sess01_FB016 59.905196 114.990402
1376 17 17 S12_Sess01_FB017 18.676258 12.766036
1377 18 18 S12_Sess01_FB018 -35.584414 -35.438108
1378 19 19 S12_Sess01_FB019 -9.401732 -2.025098
1379 20 20 S12_Sess01_FB020 65.518192 45.158094
1380 21 21 S12_Sess01_FB021 23.587999 5.668379
1381 22 22 S12_Sess01_FB022 32.842217 77.638100
1382 23 23 S12_Sess01_FB023 18.335711 20.637413
1383 24 24 S12_Sess01_FB024 -6.489138 -6.920497
1384 25 25 S12_Sess01_FB025 10.402965 58.449201
1385 26 26 S12_Sess01_FB026 11.520816 6.272943
1386 27 27 S12_Sess01_FB027 -4.070149 16.892421
1387 28 28 S12_Sess01_FB028 123.903521 189.972064
1388 29 29 S12_Sess01_FB029 -14.975533 -21.121432
1389 30 30 S12_Sess01_FB030 94.786190 45.566329
... ... ... ... ... ...
1670 311 71 S12_Sess05_FB071 31.288572 25.086881
1671 312 72 S12_Sess05_FB072 16.136568 11.580709
1672 313 73 S12_Sess05_FB073 -5.113096 3.335114
1673 314 74 S12_Sess05_FB074 35.312999 32.932732
1674 315 75 S12_Sess05_FB075 6.701893 -0.420051
1675 316 76 S12_Sess05_FB076 4.697637 -2.092917
1676 317 77 S12_Sess05_FB077 15.401515 25.386383
1677 318 78 S12_Sess05_FB078 27.220737 23.382565
1678 319 79 S12_Sess05_FB079 -11.629784 -15.956306
1679 320 80 S12_Sess05_FB080 -0.238841 -16.183892
1680 321 81 S12_Sess05_FB081 30.522651 2.407790
1681 322 82 S12_Sess05_FB082 0.791001 14.120927
1682 323 83 S12_Sess05_FB083 9.680444 9.601416
1683 324 84 S12_Sess05_FB084 -4.376626 12.922841
1684 325 85 S12_Sess05_FB085 20.923432 13.230110
1685 326 86 S12_Sess05_FB086 5.972461 1.057274
1686 327 87 S12_Sess05_FB087 15.559365 3.402627
1687 328 88 S12_Sess05_FB088 44.066592 50.828820
1688 329 89 S12_Sess05_FB089 4.682198 13.471654
1689 330 90 S12_Sess05_FB090 48.060620 13.863689
1690 331 91 S12_Sess05_FB091 16.935913 11.843748
1691 332 92 S12_Sess05_FB092 -2.728013 -14.668489
1692 333 93 S12_Sess05_FB093 26.580598 16.764857
1693 334 94 S12_Sess05_FB094 39.062204 17.607855
1694 335 95 S12_Sess05_FB095 5.950217 9.730150
1695 336 96 S12_Sess05_FB096 6.535442 -7.249934
1696 337 97 S12_Sess05_FB097 0.701936 1.219666
1697 338 98 S12_Sess05_FB098 5.062529 10.913262
1698 339 99 S12_Sess05_FB099 7.694641 -19.108262
1699 340 100 S12_Sess05_FB100 27.383877 36.783107
Prediction Session
1360 0 1
1361 0 1
1362 0 1
1363 1 1
1364 1 1
1365 1 1
1366 1 1
1367 1 1
1368 1 1
1369 0 1
1370 1 1
1371 1 1
1372 1 1
1373 1 1
1374 1 1
1375 1 1
1376 1 1
1377 1 1
1378 1 1
1379 1 1
1380 1 1
1381 1 1
1382 1 1
1383 1 1
1384 1 1
1385 1 1
1386 0 1
1387 0 1
1388 1 1
1389 1 1
... ... ...
1670 0 5
1671 0 5
1672 0 5
1673 1 5
1674 0 5
1675 0 5
1676 0 5
1677 1 5
1678 0 5
1679 0 5
1680 1 5
1681 1 5
1682 0 5
1683 0 5
1684 1 5
1685 0 5
1686 1 5
1687 0 5
1688 1 5
1689 1 5
1690 1 5
1691 0 5
1692 1 5
1693 0 5
1694 0 5
1695 0 5
1696 1 5
1697 0 5
1698 0 5
1699 0 5
[340 rows x 7 columns]
AbsTrialNum FeedbackNo IdFeedBack Neg-ErrP Pos-ErrP \
1700 1 1 S13_Sess01_FB001 31.059202 7.544054
1701 2 2 S13_Sess01_FB002 18.302414 9.560086
1702 3 3 S13_Sess01_FB003 12.167608 26.104703
1703 4 4 S13_Sess01_FB004 21.763409 17.675169
1704 5 5 S13_Sess01_FB005 17.073542 30.261018
1705 6 6 S13_Sess01_FB006 3.417622 9.785759
1706 7 7 S13_Sess01_FB007 -13.521533 15.933960
1707 8 8 S13_Sess01_FB008 2.559403 3.544624
1708 9 9 S13_Sess01_FB009 13.576933 -3.216148
1709 10 10 S13_Sess01_FB010 -29.492332 -33.586760
1710 11 11 S13_Sess01_FB011 5.945580 21.240541
1711 12 12 S13_Sess01_FB012 11.302642 12.492005
1712 13 13 S13_Sess01_FB013 -10.923104 17.920996
1713 14 14 S13_Sess01_FB014 -4.577746 -0.959501
1714 15 15 S13_Sess01_FB015 28.380812 20.249574
1715 16 16 S13_Sess01_FB016 16.953031 24.402124
1716 17 17 S13_Sess01_FB017 -1.525392 3.515052
1717 18 18 S13_Sess01_FB018 9.683628 18.724011
1718 19 19 S13_Sess01_FB019 -23.886966 -2.385221
1719 20 20 S13_Sess01_FB020 6.656085 15.979973
1720 21 21 S13_Sess01_FB021 28.181089 32.705268
1721 22 22 S13_Sess01_FB022 -4.823034 -23.133854
1722 23 23 S13_Sess01_FB023 33.371779 61.792701
1723 24 24 S13_Sess01_FB024 1.128963 10.804839
1724 25 25 S13_Sess01_FB025 8.392038 20.332731
1725 26 26 S13_Sess01_FB026 6.852378 6.567842
1726 27 27 S13_Sess01_FB027 31.163850 15.170253
1727 28 28 S13_Sess01_FB028 7.245852 17.869782
1728 29 29 S13_Sess01_FB029 5.857333 12.158087
1729 30 30 S13_Sess01_FB030 -12.111540 19.044432
... ... ... ... ... ...
2010 311 71 S13_Sess05_FB071 46.224906 88.205482
2011 312 72 S13_Sess05_FB072 -3.196911 -7.106135
2012 313 73 S13_Sess05_FB073 -2.733913 2.893935
2013 314 74 S13_Sess05_FB074 11.397531 8.173266
2014 315 75 S13_Sess05_FB075 -7.533837 -1.646587
2015 316 76 S13_Sess05_FB076 43.651700 98.870578
2016 317 77 S13_Sess05_FB077 -3.427884 -17.734669
2017 318 78 S13_Sess05_FB078 -24.213998 -8.025336
2018 319 79 S13_Sess05_FB079 4.087416 50.214670
2019 320 80 S13_Sess05_FB080 -17.072033 -11.319198
2020 321 81 S13_Sess05_FB081 5.022695 29.718878
2021 322 82 S13_Sess05_FB082 8.359061 22.095987
2022 323 83 S13_Sess05_FB083 -59.545761 -63.399879
2023 324 84 S13_Sess05_FB084 20.784941 34.202497
2024 325 85 S13_Sess05_FB085 16.521904 71.264508
2025 326 86 S13_Sess05_FB086 23.922833 -9.312406
2026 327 87 S13_Sess05_FB087 -40.706515 -10.553819
2027 328 88 S13_Sess05_FB088 32.955004 51.126326
2028 329 89 S13_Sess05_FB089 -0.042839 -7.714302
2029 330 90 S13_Sess05_FB090 9.561565 18.091648
2030 331 91 S13_Sess05_FB091 46.715972 92.124662
2031 332 92 S13_Sess05_FB092 23.228336 43.031582
2032 333 93 S13_Sess05_FB093 2.866864 20.940583
2033 334 94 S13_Sess05_FB094 23.515532 12.752665
2034 335 95 S13_Sess05_FB095 32.458063 62.256060
2035 336 96 S13_Sess05_FB096 21.050446 71.203552
2036 337 97 S13_Sess05_FB097 5.214531 12.278901
2037 338 98 S13_Sess05_FB098 18.577094 22.667660
2038 339 99 S13_Sess05_FB099 29.789288 31.504919
2039 340 100 S13_Sess05_FB100 18.309206 28.682529
Prediction Session
1700 1 1
1701 1 1
1702 0 1
1703 1 1
1704 0 1
1705 0 1
1706 0 1
1707 1 1
1708 1 1
1709 0 1
1710 1 1
1711 1 1
1712 1 1
1713 0 1
1714 1 1
1715 0 1
1716 1 1
1717 0 1
1718 0 1
1719 1 1
1720 1 1
1721 0 1
1722 1 1
1723 0 1
1724 0 1
1725 1 1
1726 1 1
1727 0 1
1728 1 1
1729 1 1
... ... ...
2010 1 5
2011 0 5
2012 1 5
2013 1 5
2014 1 5
2015 1 5
2016 1 5
2017 0 5
2018 0 5
2019 0 5
2020 0 5
2021 0 5
2022 1 5
2023 0 5
2024 0 5
2025 1 5
2026 1 5
2027 1 5
2028 1 5
2029 0 5
2030 0 5
2031 0 5
2032 0 5
2033 1 5
2034 1 5
2035 1 5
2036 1 5
2037 1 5
2038 0 5
2039 0 5
[340 rows x 7 columns]
AbsTrialNum FeedbackNo IdFeedBack Neg-ErrP Pos-ErrP \
2040 1 1 S14_Sess01_FB001 4.646199 -2.132442
2041 2 2 S14_Sess01_FB002 -2.395114 4.269851
2042 3 3 S14_Sess01_FB003 14.192623 18.488419
2043 4 4 S14_Sess01_FB004 9.506020 16.201482
2044 5 5 S14_Sess01_FB005 0.517585 14.699045
2045 6 6 S14_Sess01_FB006 13.348447 18.832368
2046 7 7 S14_Sess01_FB007 5.257059 -5.942089
2047 8 8 S14_Sess01_FB008 22.276050 6.329993
2048 9 9 S14_Sess01_FB009 17.694296 4.251621
2049 10 10 S14_Sess01_FB010 -11.328399 -14.117458
2050 11 11 S14_Sess01_FB011 -18.742241 -0.622577
2051 12 12 S14_Sess01_FB012 18.239327 21.105283
2052 13 13 S14_Sess01_FB013 15.479501 19.479444
2053 14 14 S14_Sess01_FB014 1.573853 10.770864
2054 15 15 S14_Sess01_FB015 -4.913709 9.393512
2055 16 16 S14_Sess01_FB016 10.897917 3.537591
2056 17 17 S14_Sess01_FB017 34.756992 14.779642
2057 18 18 S14_Sess01_FB018 22.567610 14.355098
2058 19 19 S14_Sess01_FB019 28.788154 47.929069
2059 20 20 S14_Sess01_FB020 13.707941 30.065264
2060 21 21 S14_Sess01_FB021 8.043897 12.504621
2061 22 22 S14_Sess01_FB022 23.215441 14.219337
2062 23 23 S14_Sess01_FB023 12.351726 4.486815
2063 24 24 S14_Sess01_FB024 4.739017 6.675200
2064 25 25 S14_Sess01_FB025 22.251697 9.576591
2065 26 26 S14_Sess01_FB026 18.646519 4.453807
2066 27 27 S14_Sess01_FB027 0.526317 17.784591
2067 28 28 S14_Sess01_FB028 -6.769111 -11.712266
2068 29 29 S14_Sess01_FB029 18.048404 19.878413
2069 30 30 S14_Sess01_FB030 -1.438176 0.890960
... ... ... ... ... ...
2350 311 71 S14_Sess05_FB071 19.981365 32.286665
2351 312 72 S14_Sess05_FB072 21.164653 7.149256
2352 313 73 S14_Sess05_FB073 22.677346 13.319355
2353 314 74 S14_Sess05_FB074 18.659328 9.610958
2354 315 75 S14_Sess05_FB075 3.858238 21.019673
2355 316 76 S14_Sess05_FB076 -1.868056 7.645032
2356 317 77 S14_Sess05_FB077 13.255622 16.034717
2357 318 78 S14_Sess05_FB078 6.142827 27.011785
2358 319 79 S14_Sess05_FB079 -0.336612 0.450347
2359 320 80 S14_Sess05_FB080 11.220977 6.716098
2360 321 81 S14_Sess05_FB081 10.210705 24.747781
2361 322 82 S14_Sess05_FB082 11.811263 22.496328
2362 323 83 S14_Sess05_FB083 29.753475 33.608907
2363 324 84 S14_Sess05_FB084 25.681022 25.264685
2364 325 85 S14_Sess05_FB085 15.183712 20.619146
2365 326 86 S14_Sess05_FB086 25.741780 37.714432
2366 327 87 S14_Sess05_FB087 -8.159123 8.776121
2367 328 88 S14_Sess05_FB088 16.008576 4.644317
2368 329 89 S14_Sess05_FB089 18.433870 22.700307
2369 330 90 S14_Sess05_FB090 14.751893 20.572894
2370 331 91 S14_Sess05_FB091 21.570401 23.815085
2371 332 92 S14_Sess05_FB092 26.402468 17.099964
2372 333 93 S14_Sess05_FB093 20.591835 4.870529
2373 334 94 S14_Sess05_FB094 -5.593955 -12.942980
2374 335 95 S14_Sess05_FB095 23.722077 27.143132
2375 336 96 S14_Sess05_FB096 17.898830 7.924022
2376 337 97 S14_Sess05_FB097 19.799590 15.510403
2377 338 98 S14_Sess05_FB098 -3.285615 11.909514
2378 339 99 S14_Sess05_FB099 11.150284 12.647242
2379 340 100 S14_Sess05_FB100 26.074647 60.125825
Prediction Session
2040 1 1
2041 1 1
2042 0 1
2043 1 1
2044 0 1
2045 1 1
2046 1 1
2047 1 1
2048 1 1
2049 1 1
2050 0 1
2051 1 1
2052 1 1
2053 0 1
2054 1 1
2055 1 1
2056 1 1
2057 1 1
2058 0 1
2059 0 1
2060 1 1
2061 1 1
2062 1 1
2063 1 1
2064 1 1
2065 1 1
2066 0 1
2067 1 1
2068 0 1
2069 0 1
... ... ...
2350 0 5
2351 0 5
2352 0 5
2353 0 5
2354 1 5
2355 1 5
2356 1 5
2357 0 5
2358 0 5
2359 1 5
2360 1 5
2361 0 5
2362 1 5
2363 1 5
2364 1 5
2365 1 5
2366 0 5
2367 1 5
2368 0 5
2369 1 5
2370 0 5
2371 0 5
2372 0 5
2373 0 5
2374 0 5
2375 0 5
2376 0 5
2377 1 5
2378 0 5
2379 1 5
[340 rows x 7 columns]
AbsTrialNum FeedbackNo IdFeedBack Neg-ErrP Pos-ErrP \
2380 1 1 S16_Sess01_FB001 8.507131 35.127216
2381 2 2 S16_Sess01_FB002 10.811457 19.816239
2382 3 3 S16_Sess01_FB003 15.011905 7.696000
2383 4 4 S16_Sess01_FB004 16.671855 26.482954
2384 5 5 S16_Sess01_FB005 -7.959492 21.050129
2385 6 6 S16_Sess01_FB006 26.639155 24.972501
2386 7 7 S16_Sess01_FB007 46.634550 44.041711
2387 8 8 S16_Sess01_FB008 6.394156 -4.741661
2388 9 9 S16_Sess01_FB009 21.595429 22.417891
2389 10 10 S16_Sess01_FB010 -12.336981 -1.837616
2390 11 11 S16_Sess01_FB011 2.141592 12.292403
2391 12 12 S16_Sess01_FB012 0.518505 -1.060314
2392 13 13 S16_Sess01_FB013 15.691646 7.528341
2393 14 14 S16_Sess01_FB014 14.875031 13.738459
2394 15 15 S16_Sess01_FB015 14.973064 13.200627
2395 16 16 S16_Sess01_FB016 1.154376 27.079492
2396 17 17 S16_Sess01_FB017 34.024019 26.666868
2397 18 18 S16_Sess01_FB018 -1.669288 -22.850530
2398 19 19 S16_Sess01_FB019 20.540740 28.807557
2399 20 20 S16_Sess01_FB020 -2.679465 3.595601
2400 21 21 S16_Sess01_FB021 21.877403 18.513492
2401 22 22 S16_Sess01_FB022 1.176397 8.752281
2402 23 23 S16_Sess01_FB023 2.154327 19.528094
2403 24 24 S16_Sess01_FB024 -17.593072 -6.692541
2404 25 25 S16_Sess01_FB025 17.708204 11.092337
2405 26 26 S16_Sess01_FB026 6.916158 -26.692452
2406 27 27 S16_Sess01_FB027 12.711208 23.359700
2407 28 28 S16_Sess01_FB028 5.461362 0.955807
2408 29 29 S16_Sess01_FB029 15.942753 23.797482
2409 30 30 S16_Sess01_FB030 10.143697 -9.649565
... ... ... ... ... ...
2690 311 71 S16_Sess05_FB071 15.452414 5.934080
2691 312 72 S16_Sess05_FB072 21.336813 11.957187
2692 313 73 S16_Sess05_FB073 28.699762 26.657476
2693 314 74 S16_Sess05_FB074 18.582277 18.905140
2694 315 75 S16_Sess05_FB075 12.215434 20.051817
2695 316 76 S16_Sess05_FB076 12.467265 17.571138
2696 317 77 S16_Sess05_FB077 15.037584 16.735072
2697 318 78 S16_Sess05_FB078 17.652448 16.534037
2698 319 79 S16_Sess05_FB079 6.361796 10.156351
2699 320 80 S16_Sess05_FB080 -2.515948 10.479095
2700 321 81 S16_Sess05_FB081 5.177208 17.618569
2701 322 82 S16_Sess05_FB082 2.319438 -5.924392
2702 323 83 S16_Sess05_FB083 0.487856 -7.000597
2703 324 84 S16_Sess05_FB084 0.048411 2.014211
2704 325 85 S16_Sess05_FB085 11.231602 10.475800
2705 326 86 S16_Sess05_FB086 -0.325244 18.071841
2706 327 87 S16_Sess05_FB087 -3.834875 15.405218
2707 328 88 S16_Sess05_FB088 20.097501 26.716723
2708 329 89 S16_Sess05_FB089 -13.207517 -9.772022
2709 330 90 S16_Sess05_FB090 -5.368113 -9.003123
2710 331 91 S16_Sess05_FB091 -1.484701 -0.935853
2711 332 92 S16_Sess05_FB092 24.000288 28.625209
2712 333 93 S16_Sess05_FB093 -5.451896 3.674354
2713 334 94 S16_Sess05_FB094 0.346199 30.060026
2714 335 95 S16_Sess05_FB095 -4.355300 -15.308197
2715 336 96 S16_Sess05_FB096 -5.724422 9.154516
2716 337 97 S16_Sess05_FB097 -2.180768 12.260874
2717 338 98 S16_Sess05_FB098 10.348225 14.635092
2718 339 99 S16_Sess05_FB099 8.337411 12.309642
2719 340 100 S16_Sess05_FB100 14.379221 -10.747147
Prediction Session
2380 1 1
2381 1 1
2382 1 1
2383 1 1
2384 0 1
2385 1 1
2386 1 1
2387 1 1
2388 1 1
2389 0 1
2390 1 1
2391 1 1
2392 1 1
2393 1 1
2394 1 1
2395 0 1
2396 1 1
2397 1 1
2398 1 1
2399 1 1
2400 1 1
2401 1 1
2402 0 1
2403 0 1
2404 1 1
2405 1 1
2406 0 1
2407 1 1
2408 0 1
2409 0 1
... ... ...
2690 1 5
2691 1 5
2692 1 5
2693 1 5
2694 1 5
2695 1 5
2696 0 5
2697 1 5
2698 1 5
2699 1 5
2700 1 5
2701 0 5
2702 1 5
2703 0 5
2704 1 5
2705 0 5
2706 0 5
2707 1 5
2708 0 5
2709 1 5
2710 0 5
2711 0 5
2712 0 5
2713 0 5
2714 0 5
2715 1 5
2716 0 5
2717 0 5
2718 0 5
2719 1 5
[340 rows x 7 columns]
AbsTrialNum FeedbackNo IdFeedBack Neg-ErrP Pos-ErrP \
2720 1 1 S17_Sess01_FB001 -3.538740 -4.882719
2721 2 2 S17_Sess01_FB002 5.000830 12.138864
2722 3 3 S17_Sess01_FB003 5.863484 3.235123
2723 4 4 S17_Sess01_FB004 5.652813 6.999445
2724 5 5 S17_Sess01_FB005 -2.075097 5.554232
2725 6 6 S17_Sess01_FB006 -1.706608 2.055854
2726 7 7 S17_Sess01_FB007 2.229217 6.420040
2727 8 8 S17_Sess01_FB008 4.547705 6.495656
2728 9 9 S17_Sess01_FB009 19.568655 15.675891
2729 10 10 S17_Sess01_FB010 4.629917 2.014258
2730 11 11 S17_Sess01_FB011 5.632142 3.791794
2731 12 12 S17_Sess01_FB012 5.836386 0.183228
2732 13 13 S17_Sess01_FB013 7.699592 3.383412
2733 14 14 S17_Sess01_FB014 2.522197 -1.161877
2734 15 15 S17_Sess01_FB015 3.700560 1.897049
2735 16 16 S17_Sess01_FB016 9.083640 7.561210
2736 17 17 S17_Sess01_FB017 5.672421 11.301944
2737 18 18 S17_Sess01_FB018 8.415876 4.118974
2738 19 19 S17_Sess01_FB019 4.188345 3.393662
2739 20 20 S17_Sess01_FB020 11.720464 8.389673
2740 21 21 S17_Sess01_FB021 10.807205 12.465562
2741 22 22 S17_Sess01_FB022 8.420720 15.068847
2742 23 23 S17_Sess01_FB023 2.752797 1.194245
2743 24 24 S17_Sess01_FB024 -1.082652 -3.456185
2744 25 25 S17_Sess01_FB025 2.666465 1.796676
2745 26 26 S17_Sess01_FB026 3.932710 9.066013
2746 27 27 S17_Sess01_FB027 -3.604686 -6.369981
2747 28 28 S17_Sess01_FB028 6.465248 3.716907
2748 29 29 S17_Sess01_FB029 3.447991 4.257312
2749 30 30 S17_Sess01_FB030 6.806481 9.435632
... ... ... ... ... ...
3030 311 71 S17_Sess05_FB071 8.008686 -0.587527
3031 312 72 S17_Sess05_FB072 34.728197 16.642602
3032 313 73 S17_Sess05_FB073 8.254784 -17.011572
3033 314 74 S17_Sess05_FB074 2.790443 1.355551
3034 315 75 S17_Sess05_FB075 18.666652 10.992925
3035 316 76 S17_Sess05_FB076 -5.994771 10.141370
3036 317 77 S17_Sess05_FB077 25.120987 25.548121
3037 318 78 S17_Sess05_FB078 -4.202176 17.310734
3038 319 79 S17_Sess05_FB079 -1.026938 8.854554
3039 320 80 S17_Sess05_FB080 5.905379 34.041096
3040 321 81 S17_Sess05_FB081 -6.117034 -4.548870
3041 322 82 S17_Sess05_FB082 5.854803 12.161198
3042 323 83 S17_Sess05_FB083 28.221480 14.327056
3043 324 84 S17_Sess05_FB084 7.256943 -5.462304
3044 325 85 S17_Sess05_FB085 28.307992 6.271081
3045 326 86 S17_Sess05_FB086 -9.421265 1.140162
3046 327 87 S17_Sess05_FB087 8.308022 20.296629
3047 328 88 S17_Sess05_FB088 12.513554 17.216834
3048 329 89 S17_Sess05_FB089 -28.541007 -22.346015
3049 330 90 S17_Sess05_FB090 12.562717 13.200511
3050 331 91 S17_Sess05_FB091 31.601491 17.970184
3051 332 92 S17_Sess05_FB092 3.678668 6.962816
3052 333 93 S17_Sess05_FB093 -4.512323 7.423751
3053 334 94 S17_Sess05_FB094 12.849761 9.300951
3054 335 95 S17_Sess05_FB095 13.722720 21.095209
3055 336 96 S17_Sess05_FB096 28.759496 12.369206
3056 337 97 S17_Sess05_FB097 10.726261 32.630034
3057 338 98 S17_Sess05_FB098 3.140350 48.259564
3058 339 99 S17_Sess05_FB099 -5.680694 18.052038
3059 340 100 S17_Sess05_FB100 18.725310 9.779171
Prediction Session
2720 0 1
2721 1 1
2722 1 1
2723 1 1
2724 1 1
2725 1 1
2726 1 1
2727 1 1
2728 1 1
2729 1 1
2730 1 1
2731 1 1
2732 1 1
2733 1 1
2734 1 1
2735 1 1
2736 1 1
2737 1 1
2738 1 1
2739 1 1
2740 1 1
2741 1 1
2742 1 1
2743 1 1
2744 1 1
2745 1 1
2746 1 1
2747 0 1
2748 1 1
2749 1 1
... ... ...
3030 1 5
3031 1 5
3032 1 5
3033 0 5
3034 1 5
3035 0 5
3036 1 5
3037 1 5
3038 1 5
3039 0 5
3040 1 5
3041 0 5
3042 1 5
3043 1 5
3044 1 5
3045 0 5
3046 1 5
3047 0 5
3048 0 5
3049 1 5
3050 1 5
3051 0 5
3052 0 5
3053 0 5
3054 1 5
3055 1 5
3056 0 5
3057 0 5
3058 0 5
3059 0 5
[340 rows x 7 columns]
AbsTrialNum FeedbackNo IdFeedBack Neg-ErrP Pos-ErrP \
3060 1 1 S18_Sess01_FB001 -18.980332 -11.354005
3061 2 2 S18_Sess01_FB002 -2.871877 -14.581185
3062 3 3 S18_Sess01_FB003 5.338259 25.889873
3063 4 4 S18_Sess01_FB004 6.148954 7.210483
3064 5 5 S18_Sess01_FB005 20.584636 36.309461
3065 6 6 S18_Sess01_FB006 8.854936 0.582282
3066 7 7 S18_Sess01_FB007 -7.126731 2.274601
3067 8 8 S18_Sess01_FB008 10.250832 25.150305
3068 9 9 S18_Sess01_FB009 -9.957468 6.301409
3069 10 10 S18_Sess01_FB010 -6.317089 -0.139769
3070 11 11 S18_Sess01_FB011 -23.885545 -23.426768
3071 12 12 S18_Sess01_FB012 23.213527 14.601598
3072 13 13 S18_Sess01_FB013 13.560765 -1.106585
3073 14 14 S18_Sess01_FB014 -31.084523 -8.922545
3074 15 15 S18_Sess01_FB015 4.704851 -11.236192
3075 16 16 S18_Sess01_FB016 0.048576 -17.350239
3076 17 17 S18_Sess01_FB017 -20.951106 -22.929657
3077 18 18 S18_Sess01_FB018 3.070373 3.586818
3078 19 19 S18_Sess01_FB019 -13.701856 17.962573
3079 20 20 S18_Sess01_FB020 14.155713 12.230820
3080 21 21 S18_Sess01_FB021 -3.359947 -23.007031
3081 22 22 S18_Sess01_FB022 -8.236801 5.620808
3082 23 23 S18_Sess01_FB023 -9.162115 4.953875
3083 24 24 S18_Sess01_FB024 23.560352 21.299068
3084 25 25 S18_Sess01_FB025 -1.371802 21.347554
3085 26 26 S18_Sess01_FB026 11.582641 9.621575
3086 27 27 S18_Sess01_FB027 -8.304474 -5.319203
3087 28 28 S18_Sess01_FB028 14.148954 -9.716585
3088 29 29 S18_Sess01_FB029 -20.026620 -6.210589
3089 30 30 S18_Sess01_FB030 -14.844802 -16.941607
... ... ... ... ... ...
3370 311 71 S18_Sess05_FB071 -0.779735 -18.738569
3371 312 72 S18_Sess05_FB072 -20.357014 -22.302278
3372 313 73 S18_Sess05_FB073 -8.414113 -14.629298
3373 314 74 S18_Sess05_FB074 9.775296 21.708170
3374 315 75 S18_Sess05_FB075 -32.042030 -22.019952
3375 316 76 S18_Sess05_FB076 15.056356 18.762769
3376 317 77 S18_Sess05_FB077 -6.980314 5.344788
3377 318 78 S18_Sess05_FB078 -69.517958 -86.930927
3378 319 79 S18_Sess05_FB079 3.672123 10.201169
3379 320 80 S18_Sess05_FB080 -23.446058 -18.301119
3380 321 81 S18_Sess05_FB081 18.084035 74.526065
3381 322 82 S18_Sess05_FB082 9.505522 12.270870
3382 323 83 S18_Sess05_FB083 -13.286961 -10.809305
3383 324 84 S18_Sess05_FB084 3.152720 8.434931
3384 325 85 S18_Sess05_FB085 -28.221685 -2.933289
3385 326 86 S18_Sess05_FB086 -25.817695 -31.348292
3386 327 87 S18_Sess05_FB087 13.917722 11.545032
3387 328 88 S18_Sess05_FB088 -10.473280 -4.176705
3388 329 89 S18_Sess05_FB089 -30.409099 -17.362984
3389 330 90 S18_Sess05_FB090 36.865073 122.182569
3390 331 91 S18_Sess05_FB091 8.403006 16.293583
3391 332 92 S18_Sess05_FB092 -20.871072 -17.343619
3392 333 93 S18_Sess05_FB093 -57.584152 -61.963505
3393 334 94 S18_Sess05_FB094 -13.090622 -4.246522
3394 335 95 S18_Sess05_FB095 -25.069166 -1.903483
3395 336 96 S18_Sess05_FB096 -48.762189 -49.060504
3396 337 97 S18_Sess05_FB097 2.640926 11.750153
3397 338 98 S18_Sess05_FB098 5.409686 4.859216
3398 339 99 S18_Sess05_FB099 -25.806308 -19.207381
3399 340 100 S18_Sess05_FB100 -38.900841 -16.865793
Prediction Session
3060 1 1
3061 1 1
3062 1 1
3063 1 1
3064 1 1
3065 1 1
3066 1 1
3067 1 1
3068 1 1
3069 0 1
3070 1 1
3071 1 1
3072 1 1
3073 1 1
3074 1 1
3075 1 1
3076 1 1
3077 0 1
3078 1 1
3079 1 1
3080 1 1
3081 1 1
3082 0 1
3083 0 1
3084 0 1
3085 1 1
3086 1 1
3087 1 1
3088 0 1
3089 1 1
... ... ...
3370 1 5
3371 1 5
3372 1 5
3373 1 5
3374 0 5
3375 1 5
3376 1 5
3377 0 5
3378 1 5
3379 1 5
3380 1 5
3381 1 5
3382 0 5
3383 1 5
3384 0 5
3385 1 5
3386 1 5
3387 0 5
3388 1 5
3389 1 5
3390 1 5
3391 1 5
3392 1 5
3393 0 5
3394 1 5
3395 1 5
3396 0 5
3397 1 5
3398 1 5
3399 1 5
[340 rows x 7 columns]
AbsTrialNum FeedbackNo IdFeedBack Neg-ErrP Pos-ErrP \
3400 1 1 S20_Sess01_FB001 -108.775930 -117.218229
3401 2 2 S20_Sess01_FB002 -47.279488 -48.651628
3402 3 3 S20_Sess01_FB003 -15.939171 -13.458225
3403 4 4 S20_Sess01_FB004 -10.847338 -4.657511
3404 5 5 S20_Sess01_FB005 -13.993944 -1.983751
3405 6 6 S20_Sess01_FB006 7.740781 116.433431
3406 7 7 S20_Sess01_FB007 -3.030874 -13.397314
3407 8 8 S20_Sess01_FB008 -27.572587 -29.258135
3408 9 9 S20_Sess01_FB009 -13.234616 48.983286
3409 10 10 S20_Sess01_FB010 -3.219217 2.752531
3410 11 11 S20_Sess01_FB011 -3.855209 -2.565122
3411 12 12 S20_Sess01_FB012 9.474102 33.447871
3412 13 13 S20_Sess01_FB013 -19.883341 -12.441973
3413 14 14 S20_Sess01_FB014 -5.092147 -4.848089
3414 15 15 S20_Sess01_FB015 -12.647322 -12.927195
3415 16 16 S20_Sess01_FB016 -39.154211 -0.226412
3416 17 17 S20_Sess01_FB017 -7.556511 15.840537
3417 18 18 S20_Sess01_FB018 -7.352393 -0.351940
3418 19 19 S20_Sess01_FB019 16.962609 10.680378
3419 20 20 S20_Sess01_FB020 5.413783 -13.793824
3420 21 21 S20_Sess01_FB021 33.566679 109.244779
3421 22 22 S20_Sess01_FB022 -37.489117 -21.903445
3422 23 23 S20_Sess01_FB023 36.253662 23.231735
3423 24 24 S20_Sess01_FB024 -3.112282 -11.346316
3424 25 25 S20_Sess01_FB025 -14.234161 -16.231303
3425 26 26 S20_Sess01_FB026 4.046664 6.890892
3426 27 27 S20_Sess01_FB027 -36.492234 -26.095513
3427 28 28 S20_Sess01_FB028 -25.297322 -3.916846
3428 29 29 S20_Sess01_FB029 0.888747 -18.881346
3429 30 30 S20_Sess01_FB030 -11.095177 -1.031779
... ... ... ... ... ...
3710 311 71 S20_Sess05_FB071 0.007871 10.667033
3711 312 72 S20_Sess05_FB072 -4.013980 6.220624
3712 313 73 S20_Sess05_FB073 -3.804045 19.112499
3713 314 74 S20_Sess05_FB074 -0.075884 0.794905
3714 315 75 S20_Sess05_FB075 -3.536214 -10.746282
3715 316 76 S20_Sess05_FB076 13.531159 2.824520
3716 317 77 S20_Sess05_FB077 -14.966593 -4.998212
3717 318 78 S20_Sess05_FB078 12.254050 15.124790
3718 319 79 S20_Sess05_FB079 24.619691 18.943731
3719 320 80 S20_Sess05_FB080 -10.220343 12.834698
3720 321 81 S20_Sess05_FB081 -7.109164 -2.677909
3721 322 82 S20_Sess05_FB082 -15.555359 -16.694602
3722 323 83 S20_Sess05_FB083 0.709263 34.176976
3723 324 84 S20_Sess05_FB084 -10.649290 -19.367307
3724 325 85 S20_Sess05_FB085 45.423773 39.360186
3725 326 86 S20_Sess05_FB086 1.380035 25.085894
3726 327 87 S20_Sess05_FB087 -5.967891 -27.143081
3727 328 88 S20_Sess05_FB088 -8.715220 59.833383
3728 329 89 S20_Sess05_FB089 -7.885051 45.191625
3729 330 90 S20_Sess05_FB090 -8.767987 -2.356558
3730 331 91 S20_Sess05_FB091 -12.310840 5.379323
3731 332 92 S20_Sess05_FB092 9.115420 -12.082190
3732 333 93 S20_Sess05_FB093 -3.958071 9.832353
3733 334 94 S20_Sess05_FB094 11.755361 -4.344686
3734 335 95 S20_Sess05_FB095 -3.154758 -8.178439
3735 336 96 S20_Sess05_FB096 -2.863222 -4.516469
3736 337 97 S20_Sess05_FB097 28.526740 85.022489
3737 338 98 S20_Sess05_FB098 -9.882184 -17.260617
3738 339 99 S20_Sess05_FB099 -18.714137 -2.821443
3739 340 100 S20_Sess05_FB100 -3.004793 -17.738395
Prediction Session
3400 1 1
3401 1 1
3402 1 1
3403 1 1
3404 1 1
3405 1 1
3406 1 1
3407 1 1
3408 1 1
3409 1 1
3410 1 1
3411 0 1
3412 0 1
3413 1 1
3414 1 1
3415 0 1
3416 1 1
3417 1 1
3418 1 1
3419 1 1
3420 1 1
3421 1 1
3422 0 1
3423 1 1
3424 1 1
3425 1 1
3426 1 1
3427 0 1
3428 1 1
3429 1 1
... ... ...
3710 1 5
3711 1 5
3712 0 5
3713 1 5
3714 1 5
3715 1 5
3716 1 5
3717 1 5
3718 1 5
3719 0 5
3720 0 5
3721 1 5
3722 1 5
3723 0 5
3724 1 5
3725 0 5
3726 1 5
3727 0 5
3728 1 5
3729 1 5
3730 0 5
3731 1 5
3732 1 5
3733 1 5
3734 1 5
3735 1 5
3736 1 5
3737 1 5
3738 1 5
3739 1 5
[340 rows x 7 columns]
AbsTrialNum FeedbackNo IdFeedBack Neg-ErrP Pos-ErrP \
3740 1 1 S21_Sess01_FB001 9.918977 3.527615
3741 2 2 S21_Sess01_FB002 7.777863 8.904748
3742 3 3 S21_Sess01_FB003 36.961099 40.413224
3743 4 4 S21_Sess01_FB004 31.455408 37.692148
3744 5 5 S21_Sess01_FB005 -4.654562 1.262518
3745 6 6 S21_Sess01_FB006 11.606108 14.617941
3746 7 7 S21_Sess01_FB007 11.024178 4.800845
3747 8 8 S21_Sess01_FB008 -5.964427 -0.681407
3748 9 9 S21_Sess01_FB009 11.039854 2.991388
3749 10 10 S21_Sess01_FB010 35.782776 51.559266
3750 11 11 S21_Sess01_FB011 -5.681879 -2.360956
3751 12 12 S21_Sess01_FB012 20.853564 11.719164
3752 13 13 S21_Sess01_FB013 17.558544 29.222112
3753 14 14 S21_Sess01_FB014 -22.833874 5.063086
3754 15 15 S21_Sess01_FB015 -13.576490 2.876774
3755 16 16 S21_Sess01_FB016 5.730922 17.355333
3756 17 17 S21_Sess01_FB017 9.832168 24.374245
3757 18 18 S21_Sess01_FB018 9.666354 15.628824
3758 19 19 S21_Sess01_FB019 15.750141 11.359372
3759 20 20 S21_Sess01_FB020 19.341317 68.304772
3760 21 21 S21_Sess01_FB021 15.976573 19.940336
3761 22 22 S21_Sess01_FB022 8.849852 28.916058
3762 23 23 S21_Sess01_FB023 35.200909 62.701477
3763 24 24 S21_Sess01_FB024 16.035510 40.339883
3764 25 25 S21_Sess01_FB025 32.423556 87.082536
3765 26 26 S21_Sess01_FB026 2.770297 -6.107094
3766 27 27 S21_Sess01_FB027 15.816677 31.698467
3767 28 28 S21_Sess01_FB028 14.387673 20.231716
3768 29 29 S21_Sess01_FB029 14.753543 14.533345
3769 30 30 S21_Sess01_FB030 15.233880 17.724005
... ... ... ... ... ...
4050 311 71 S21_Sess05_FB071 12.898423 16.110936
4051 312 72 S21_Sess05_FB072 7.676653 21.777476
4052 313 73 S21_Sess05_FB073 -1.528287 0.815686
4053 314 74 S21_Sess05_FB074 21.429173 48.333205
4054 315 75 S21_Sess05_FB075 16.820355 11.545901
4055 316 76 S21_Sess05_FB076 5.587213 42.935743
4056 317 77 S21_Sess05_FB077 24.781789 43.381975
4057 318 78 S21_Sess05_FB078 -0.607129 22.527650
4058 319 79 S21_Sess05_FB079 -7.784411 -4.072513
4059 320 80 S21_Sess05_FB080 20.310275 37.144164
4060 321 81 S21_Sess05_FB081 32.856986 34.055729
4061 322 82 S21_Sess05_FB082 18.509027 21.919304
4062 323 83 S21_Sess05_FB083 19.964483 38.412004
4063 324 84 S21_Sess05_FB084 44.522225 53.531595
4064 325 85 S21_Sess05_FB085 22.157238 47.415409
4065 326 86 S21_Sess05_FB086 -11.332569 21.121701
4066 327 87 S21_Sess05_FB087 24.338322 36.022922
4067 328 88 S21_Sess05_FB088 12.210753 27.852804
4068 329 89 S21_Sess05_FB089 4.197409 12.294785
4069 330 90 S21_Sess05_FB090 -4.667618 17.333222
4070 331 91 S21_Sess05_FB091 20.980702 73.282250
4071 332 92 S21_Sess05_FB092 7.658145 31.291714
4072 333 93 S21_Sess05_FB093 29.016896 54.659246
4073 334 94 S21_Sess05_FB094 10.123564 55.244179
4074 335 95 S21_Sess05_FB095 54.930655 37.706251
4075 336 96 S21_Sess05_FB096 5.864008 16.089350
4076 337 97 S21_Sess05_FB097 24.712732 31.243914
4077 338 98 S21_Sess05_FB098 34.536495 81.337637
4078 339 99 S21_Sess05_FB099 36.509563 50.018423
4079 340 100 S21_Sess05_FB100 16.018920 0.118533
Prediction Session
3740 1 1
3741 1 1
3742 1 1
3743 1 1
3744 1 1
3745 1 1
3746 1 1
3747 1 1
3748 1 1
3749 1 1
3750 1 1
3751 1 1
3752 1 1
3753 0 1
3754 1 1
3755 1 1
3756 1 1
3757 1 1
3758 1 1
3759 1 1
3760 1 1
3761 1 1
3762 1 1
3763 1 1
3764 1 1
3765 1 1
3766 1 1
3767 1 1
3768 1 1
3769 1 1
... ... ...
4050 1 5
4051 1 5
4052 0 5
4053 1 5
4054 1 5
4055 0 5
4056 0 5
4057 1 5
4058 1 5
4059 1 5
4060 1 5
4061 1 5
4062 1 5
4063 1 5
4064 1 5
4065 1 5
4066 1 5
4067 1 5
4068 1 5
4069 1 5
4070 1 5
4071 0 5
4072 1 5
4073 1 5
4074 1 5
4075 1 5
4076 1 5
4077 0 5
4078 1 5
4079 1 5
[340 rows x 7 columns]
AbsTrialNum FeedbackNo IdFeedBack Neg-ErrP Pos-ErrP \
4080 1 1 S22_Sess01_FB001 19.361371 25.529706
4081 2 2 S22_Sess01_FB002 40.254226 55.674234
4082 3 3 S22_Sess01_FB003 24.413096 20.933934
4083 4 4 S22_Sess01_FB004 15.286017 17.504957
4084 5 5 S22_Sess01_FB005 -15.227827 -20.822294
4085 6 6 S22_Sess01_FB006 102.634557 55.199880
4086 7 7 S22_Sess01_FB007 18.829866 37.063682
4087 8 8 S22_Sess01_FB008 16.584223 43.568611
4088 9 9 S22_Sess01_FB009 -7.037852 1.399304
4089 10 10 S22_Sess01_FB010 18.937652 42.807272
4090 11 11 S22_Sess01_FB011 36.759981 29.484052
4091 12 12 S22_Sess01_FB012 20.775764 15.798983
4092 13 13 S22_Sess01_FB013 18.711675 66.418391
4093 14 14 S22_Sess01_FB014 47.664322 20.300127
4094 15 15 S22_Sess01_FB015 -17.430362 50.248708
4095 16 16 S22_Sess01_FB016 -40.874126 -43.171272
4096 17 17 S22_Sess01_FB017 -4.839638 -21.053488
4097 18 18 S22_Sess01_FB018 60.531672 81.288335
4098 19 19 S22_Sess01_FB019 -12.208159 -10.157972
4099 20 20 S22_Sess01_FB020 32.899060 21.402504
4100 21 21 S22_Sess01_FB021 -16.792369 -17.380068
4101 22 22 S22_Sess01_FB022 -17.682119 -25.844585
4102 23 23 S22_Sess01_FB023 10.652665 23.326419
4103 24 24 S22_Sess01_FB024 -25.889191 -4.334531
4104 25 25 S22_Sess01_FB025 52.625201 91.688595
4105 26 26 S22_Sess01_FB026 13.969412 42.009795
4106 27 27 S22_Sess01_FB027 -6.546237 -10.376219
4107 28 28 S22_Sess01_FB028 -16.673359 5.094438
4108 29 29 S22_Sess01_FB029 -15.478893 -4.461337
4109 30 30 S22_Sess01_FB030 3.988104 7.843417
... ... ... ... ... ...
4390 311 71 S22_Sess05_FB071 27.966361 43.724229
4391 312 72 S22_Sess05_FB072 7.417690 7.622794
4392 313 73 S22_Sess05_FB073 19.181741 12.760692
4393 314 74 S22_Sess05_FB074 29.300625 33.344474
4394 315 75 S22_Sess05_FB075 21.917085 44.615175
4395 316 76 S22_Sess05_FB076 27.242091 64.868306
4396 317 77 S22_Sess05_FB077 -6.708120 30.020179
4397 318 78 S22_Sess05_FB078 8.705181 52.721249
4398 319 79 S22_Sess05_FB079 18.282947 21.195177
4399 320 80 S22_Sess05_FB080 15.556890 20.562328
4400 321 81 S22_Sess05_FB081 26.806602 67.708624
4401 322 82 S22_Sess05_FB082 28.940054 28.143831
4402 323 83 S22_Sess05_FB083 15.855356 43.063811
4403 324 84 S22_Sess05_FB084 15.768145 14.717355
4404 325 85 S22_Sess05_FB085 5.709061 17.239519
4405 326 86 S22_Sess05_FB086 -10.132637 1.548907
4406 327 87 S22_Sess05_FB087 26.224560 54.593515
4407 328 88 S22_Sess05_FB088 41.063564 86.240044
4408 329 89 S22_Sess05_FB089 11.509769 58.917372
4409 330 90 S22_Sess05_FB090 11.664510 20.493452
4410 331 91 S22_Sess05_FB091 11.528388 18.802157
4411 332 92 S22_Sess05_FB092 1.116280 35.166561
4412 333 93 S22_Sess05_FB093 11.844708 17.549551
4413 334 94 S22_Sess05_FB094 9.890693 27.986975
4414 335 95 S22_Sess05_FB095 16.264292 17.110640
4415 336 96 S22_Sess05_FB096 15.039692 68.198990
4416 337 97 S22_Sess05_FB097 90.412738 69.411723
4417 338 98 S22_Sess05_FB098 19.951819 21.132138
4418 339 99 S22_Sess05_FB099 0.379395 21.240856
4419 340 100 S22_Sess05_FB100 -10.499566 -9.371605
Prediction Session
4080 1 1
4081 1 1
4082 1 1
4083 1 1
4084 1 1
4085 1 1
4086 1 1
4087 1 1
4088 1 1
4089 1 1
4090 1 1
4091 1 1
4092 1 1
4093 1 1
4094 1 1
4095 1 1
4096 1 1
4097 1 1
4098 1 1
4099 1 1
4100 1 1
4101 1 1
4102 1 1
4103 0 1
4104 1 1
4105 1 1
4106 1 1
4107 1 1
4108 1 1
4109 1 1
... ... ...
4390 1 5
4391 1 5
4392 1 5
4393 1 5
4394 1 5
4395 1 5
4396 0 5
4397 1 5
4398 1 5
4399 1 5
4400 1 5
4401 1 5
4402 1 5
4403 1 5
4404 1 5
4405 1 5
4406 1 5
4407 1 5
4408 1 5
4409 1 5
4410 0 5
4411 0 5
4412 1 5
4413 1 5
4414 0 5
4415 1 5
4416 1 5
4417 1 5
4418 1 5
4419 1 5
[340 rows x 7 columns]
AbsTrialNum FeedbackNo IdFeedBack Neg-ErrP Pos-ErrP \
4420 1 1 S23_Sess01_FB001 6.964617 14.407417
4421 2 2 S23_Sess01_FB002 15.526723 14.430522
4422 3 3 S23_Sess01_FB003 -17.860883 -1.233647
4423 4 4 S23_Sess01_FB004 11.347024 16.604931
4424 5 5 S23_Sess01_FB005 -2.626723 13.249664
4425 6 6 S23_Sess01_FB006 12.422938 14.200635
4426 7 7 S23_Sess01_FB007 -12.554403 -7.396085
4427 8 8 S23_Sess01_FB008 26.771554 52.397142
4428 9 9 S23_Sess01_FB009 15.084782 20.806080
4429 10 10 S23_Sess01_FB010 -16.093256 -6.919956
4430 11 11 S23_Sess01_FB011 -14.207838 10.664057
4431 12 12 S23_Sess01_FB012 13.369100 36.567831
4432 13 13 S23_Sess01_FB013 -1.052522 3.738903
4433 14 14 S23_Sess01_FB014 4.357752 -0.032665
4434 15 15 S23_Sess01_FB015 5.463661 13.236563
4435 16 16 S23_Sess01_FB016 10.196675 51.632615
4436 17 17 S23_Sess01_FB017 39.790273 30.633542
4437 18 18 S23_Sess01_FB018 11.944061 14.703918
4438 19 19 S23_Sess01_FB019 20.268053 -6.314163
4439 20 20 S23_Sess01_FB020 8.427300 17.883812
4440 21 21 S23_Sess01_FB021 2.399705 17.111437
4441 22 22 S23_Sess01_FB022 28.413348 36.828575
4442 23 23 S23_Sess01_FB023 6.039251 16.925393
4443 24 24 S23_Sess01_FB024 -4.500479 5.885908
4444 25 25 S23_Sess01_FB025 11.900001 12.175329
4445 26 26 S23_Sess01_FB026 10.451310 16.610063
4446 27 27 S23_Sess01_FB027 21.677426 21.077598
4447 28 28 S23_Sess01_FB028 20.730424 9.738529
4448 29 29 S23_Sess01_FB029 18.086051 9.760627
4449 30 30 S23_Sess01_FB030 8.460273 21.779477
... ... ... ... ... ...
4730 311 71 S23_Sess05_FB071 26.901188 30.329121
4731 312 72 S23_Sess05_FB072 28.138672 23.754638
4732 313 73 S23_Sess05_FB073 5.232998 0.305243
4733 314 74 S23_Sess05_FB074 6.447243 0.234788
4734 315 75 S23_Sess05_FB075 1.232431 5.770238
4735 316 76 S23_Sess05_FB076 18.964855 17.764340
4736 317 77 S23_Sess05_FB077 -10.860286 -6.319786
4737 318 78 S23_Sess05_FB078 6.332115 21.225316
4738 319 79 S23_Sess05_FB079 22.958848 5.560908
4739 320 80 S23_Sess05_FB080 11.604563 27.328872
4740 321 81 S23_Sess05_FB081 7.727802 20.450295
4741 322 82 S23_Sess05_FB082 4.437204 -2.688332
4742 323 83 S23_Sess05_FB083 27.786422 27.211814
4743 324 84 S23_Sess05_FB084 4.206713 -2.401320
4744 325 85 S23_Sess05_FB085 8.136194 14.093590
4745 326 86 S23_Sess05_FB086 20.241516 17.866405
4746 327 87 S23_Sess05_FB087 31.604648 35.955409
4747 328 88 S23_Sess05_FB088 6.569808 17.136714
4748 329 89 S23_Sess05_FB089 14.781923 1.089332
4749 330 90 S23_Sess05_FB090 22.234418 25.138641
4750 331 91 S23_Sess05_FB091 8.032507 11.902692
4751 332 92 S23_Sess05_FB092 9.831695 27.626460
4752 333 93 S23_Sess05_FB093 19.299162 27.990667
4753 334 94 S23_Sess05_FB094 15.005621 5.441098
4754 335 95 S23_Sess05_FB095 18.542089 21.214704
4755 336 96 S23_Sess05_FB096 8.135528 21.206373
4756 337 97 S23_Sess05_FB097 5.961659 24.755437
4757 338 98 S23_Sess05_FB098 16.976787 18.757931
4758 339 99 S23_Sess05_FB099 11.428107 15.458807
4759 340 100 S23_Sess05_FB100 -0.930624 7.683284
Prediction Session
4420 1 1
4421 1 1
4422 1 1
4423 1 1
4424 1 1
4425 1 1
4426 1 1
4427 1 1
4428 1 1
4429 0 1
4430 0 1
4431 0 1
4432 1 1
4433 1 1
4434 1 1
4435 0 1
4436 0 1
4437 1 1
4438 0 1
4439 1 1
4440 0 1
4441 1 1
4442 0 1
4443 0 1
4444 1 1
4445 1 1
4446 1 1
4447 1 1
4448 1 1
4449 1 1
... ... ...
4730 1 5
4731 1 5
4732 1 5
4733 1 5
4734 1 5
4735 1 5
4736 1 5
4737 0 5
4738 0 5
4739 0 5
4740 0 5
4741 1 5
4742 1 5
4743 1 5
4744 1 5
4745 1 5
4746 0 5
4747 0 5
4748 1 5
4749 1 5
4750 1 5
4751 1 5
4752 0 5
4753 1 5
4754 0 5
4755 1 5
4756 0 5
4757 1 5
4758 1 5
4759 0 5
[340 rows x 7 columns]
AbsTrialNum FeedbackNo IdFeedBack Neg-ErrP Pos-ErrP \
4760 1 1 S24_Sess01_FB001 15.797038 24.111834
4761 2 2 S24_Sess01_FB002 9.570967 7.551568
4762 3 3 S24_Sess01_FB003 4.137291 29.022937
4763 4 4 S24_Sess01_FB004 32.799424 22.931377
4764 5 5 S24_Sess01_FB005 28.077536 23.657030
4765 6 6 S24_Sess01_FB006 -2.990167 -14.074747
4766 7 7 S24_Sess01_FB007 20.941986 9.407094
4767 8 8 S24_Sess01_FB008 8.363415 17.106430
4768 9 9 S24_Sess01_FB009 6.823747 14.589716
4769 10 10 S24_Sess01_FB010 43.379741 12.910282
4770 11 11 S24_Sess01_FB011 20.610187 69.939143
4771 12 12 S24_Sess01_FB012 5.011562 6.741889
4772 13 13 S24_Sess01_FB013 23.334349 16.005650
4773 14 14 S24_Sess01_FB014 23.836588 41.354551
4774 15 15 S24_Sess01_FB015 18.459825 22.866910
4775 16 16 S24_Sess01_FB016 15.056674 -0.213125
4776 17 17 S24_Sess01_FB017 -7.488087 10.926187
4777 18 18 S24_Sess01_FB018 3.654254 15.795202
4778 19 19 S24_Sess01_FB019 23.576752 26.636969
4779 20 20 S24_Sess01_FB020 9.507051 22.938638
4780 21 21 S24_Sess01_FB021 36.695217 30.661226
4781 22 22 S24_Sess01_FB022 18.890458 18.431197
4782 23 23 S24_Sess01_FB023 25.031058 15.463956
4783 24 24 S24_Sess01_FB024 10.552007 18.330102
4784 25 25 S24_Sess01_FB025 8.661296 5.080851
4785 26 26 S24_Sess01_FB026 29.703250 18.709001
4786 27 27 S24_Sess01_FB027 22.632584 27.037377
4787 28 28 S24_Sess01_FB028 14.537837 -6.392169
4788 29 29 S24_Sess01_FB029 27.660443 8.238318
4789 30 30 S24_Sess01_FB030 10.832001 8.072958
... ... ... ... ... ...
5070 311 71 S24_Sess05_FB071 -12.090705 -10.126545
5071 312 72 S24_Sess05_FB072 12.987973 12.758999
5072 313 73 S24_Sess05_FB073 10.813507 6.079190
5073 314 74 S24_Sess05_FB074 26.563751 17.679058
5074 315 75 S24_Sess05_FB075 -4.735739 10.910250
5075 316 76 S24_Sess05_FB076 10.653578 15.992671
5076 317 77 S24_Sess05_FB077 13.695042 11.163860
5077 318 78 S24_Sess05_FB078 6.380233 8.634079
5078 319 79 S24_Sess05_FB079 13.677141 34.234649
5079 320 80 S24_Sess05_FB080 14.563856 16.173336
5080 321 81 S24_Sess05_FB081 13.386523 7.666330
5081 322 82 S24_Sess05_FB082 29.463825 11.672691
5082 323 83 S24_Sess05_FB083 40.522707 34.262527
5083 324 84 S24_Sess05_FB084 0.881618 12.973467
5084 325 85 S24_Sess05_FB085 8.844992 14.949622
5085 326 86 S24_Sess05_FB086 -8.985641 -9.332934
5086 327 87 S24_Sess05_FB087 21.929031 22.690776
5087 328 88 S24_Sess05_FB088 21.192889 35.285507
5088 329 89 S24_Sess05_FB089 12.122834 23.350016
5089 330 90 S24_Sess05_FB090 21.354895 48.708957
5090 331 91 S24_Sess05_FB091 4.443124 9.500195
5091 332 92 S24_Sess05_FB092 36.773106 36.203168
5092 333 93 S24_Sess05_FB093 7.321561 8.624413
5093 334 94 S24_Sess05_FB094 22.540152 3.080367
5094 335 95 S24_Sess05_FB095 10.878288 12.417984
5095 336 96 S24_Sess05_FB096 -2.867416 1.652018
5096 337 97 S24_Sess05_FB097 -10.631554 -4.510344
5097 338 98 S24_Sess05_FB098 15.572115 15.284296
5098 339 99 S24_Sess05_FB099 10.744418 24.700719
5099 340 100 S24_Sess05_FB100 25.393096 22.638933
Prediction Session
4760 1 1
4761 1 1
4762 1 1
4763 1 1
4764 1 1
4765 1 1
4766 1 1
4767 1 1
4768 1 1
4769 1 1
4770 1 1
4771 1 1
4772 1 1
4773 1 1
4774 1 1
4775 1 1
4776 0 1
4777 0 1
4778 1 1
4779 1 1
4780 1 1
4781 1 1
4782 1 1
4783 1 1
4784 1 1
4785 1 1
4786 1 1
4787 1 1
4788 0 1
4789 1 1
... ... ...
5070 1 5
5071 1 5
5072 0 5
5073 1 5
5074 1 5
5075 1 5
5076 1 5
5077 0 5
5078 1 5
5079 1 5
5080 1 5
5081 1 5
5082 1 5
5083 0 5
5084 0 5
5085 0 5
5086 1 5
5087 1 5
5088 0 5
5089 0 5
5090 1 5
5091 1 5
5092 0 5
5093 0 5
5094 1 5
5095 0 5
5096 1 5
5097 1 5
5098 1 5
5099 1 5
[340 rows x 7 columns]
AbsTrialNum FeedbackNo IdFeedBack Neg-ErrP Pos-ErrP \
5100 1 1 S26_Sess01_FB001 -17.835067 -15.349737
5101 2 2 S26_Sess01_FB002 0.223728 13.755387
5102 3 3 S26_Sess01_FB003 16.923154 36.454711
5103 4 4 S26_Sess01_FB004 -16.340530 -23.141672
5104 5 5 S26_Sess01_FB005 -12.458557 -1.095576
5105 6 6 S26_Sess01_FB006 9.164063 12.765821
5106 7 7 S26_Sess01_FB007 28.535157 35.325979
5107 8 8 S26_Sess01_FB008 -12.024415 -24.079037
5108 9 9 S26_Sess01_FB009 -4.296152 4.055176
5109 10 10 S26_Sess01_FB010 -10.899673 -21.339597
5110 11 11 S26_Sess01_FB011 -13.247508 -3.945720
5111 12 12 S26_Sess01_FB012 14.859581 16.560407
5112 13 13 S26_Sess01_FB013 -10.805579 10.098402
5113 14 14 S26_Sess01_FB014 -47.429366 -7.920698
5114 15 15 S26_Sess01_FB015 9.663814 28.449187
5115 16 16 S26_Sess01_FB016 -6.353594 8.696453
5116 17 17 S26_Sess01_FB017 1.244654 -10.080705
5117 18 18 S26_Sess01_FB018 2.700416 3.835694
5118 19 19 S26_Sess01_FB019 12.887190 22.222383
5119 20 20 S26_Sess01_FB020 27.545404 32.406007
5120 21 21 S26_Sess01_FB021 -11.776416 24.135708
5121 22 22 S26_Sess01_FB022 4.124480 20.137981
5122 23 23 S26_Sess01_FB023 46.632672 48.747940
5123 24 24 S26_Sess01_FB024 4.078963 9.430104
5124 25 25 S26_Sess01_FB025 -89.405952 -84.070651
5125 26 26 S26_Sess01_FB026 -46.199185 -59.234786
5126 27 27 S26_Sess01_FB027 -72.832485 -82.318029
5127 28 28 S26_Sess01_FB028 -6.022510 -17.419189
5128 29 29 S26_Sess01_FB029 -13.941927 -18.034183
5129 30 30 S26_Sess01_FB030 -3.656347 0.770218
... ... ... ... ... ...
5410 311 71 S26_Sess05_FB071 -0.055823 17.297297
5411 312 72 S26_Sess05_FB072 -41.363148 -43.706876
5412 313 73 S26_Sess05_FB073 -12.680868 -17.743182
5413 314 74 S26_Sess05_FB074 -7.441454 -11.065392
5414 315 75 S26_Sess05_FB075 -2.868921 -14.657838
5415 316 76 S26_Sess05_FB076 -5.681827 0.306574
5416 317 77 S26_Sess05_FB077 26.300601 56.605756
5417 318 78 S26_Sess05_FB078 7.034021 10.836101
5418 319 79 S26_Sess05_FB079 -14.758654 -3.553181
5419 320 80 S26_Sess05_FB080 33.573468 19.137276
5420 321 81 S26_Sess05_FB081 8.392691 -1.128361
5421 322 82 S26_Sess05_FB082 18.535116 28.092087
5422 323 83 S26_Sess05_FB083 65.442238 50.077209
5423 324 84 S26_Sess05_FB084 20.237419 10.595119
5424 325 85 S26_Sess05_FB085 15.330598 19.452277
5425 326 86 S26_Sess05_FB086 7.598349 5.952117
5426 327 87 S26_Sess05_FB087 -4.900567 10.504052
5427 328 88 S26_Sess05_FB088 1.626417 10.327717
5428 329 89 S26_Sess05_FB089 63.851362 65.893073
5429 330 90 S26_Sess05_FB090 4.179417 0.620516
5430 331 91 S26_Sess05_FB091 7.859489 4.203566
5431 332 92 S26_Sess05_FB092 6.553163 -1.505099
5432 333 93 S26_Sess05_FB093 -11.465528 4.192061
5433 334 94 S26_Sess05_FB094 1.182656 -12.969050
5434 335 95 S26_Sess05_FB095 2.838056 -3.272424
5435 336 96 S26_Sess05_FB096 25.499657 29.991916
5436 337 97 S26_Sess05_FB097 5.022608 -26.748085
5437 338 98 S26_Sess05_FB098 -11.899268 6.080850
5438 339 99 S26_Sess05_FB099 -9.257370 -17.227621
5439 340 100 S26_Sess05_FB100 -17.299156 -6.162429
Prediction Session
5100 1 1
5101 1 1
5102 0 1
5103 0 1
5104 1 1
5105 1 1
5106 1 1
5107 0 1
5108 0 1
5109 0 1
5110 1 1
5111 1 1
5112 1 1
5113 0 1
5114 1 1
5115 1 1
5116 1 1
5117 0 1
5118 1 1
5119 1 1
5120 1 1
5121 0 1
5122 1 1
5123 0 1
5124 1 1
5125 0 1
5126 1 1
5127 0 1
5128 0 1
5129 1 1
... ... ...
5410 1 5
5411 0 5
5412 1 5
5413 0 5
5414 0 5
5415 0 5
5416 0 5
5417 1 5
5418 0 5
5419 1 5
5420 1 5
5421 0 5
5422 0 5
5423 0 5
5424 0 5
5425 1 5
5426 0 5
5427 0 5
5428 0 5
5429 1 5
5430 1 5
5431 0 5
5432 1 5
5433 1 5
5434 0 5
5435 1 5
5436 0 5
5437 0 5
5438 0 5
5439 1 5
[340 rows x 7 columns]
In [216]:
sns.set(style="darkgrid")
color = sns.color_palette()[0]
ax = plt.figure(figsize=(10,6))
sns.regplot('AbsTrialNum', 'Neg-ErrP', data=Results[Results['Prediction'] == 0],
color=color, truncate=True, line_kws = {'color' : sns.color_palette()[2]})
plt.title('Effect of elapsed time on the Neg-ErrP')
plt.xlabel('Trial number')
plt.ylabel('Mean amplitude of Neg-ErrP (uV)')
plt.ylim(-75,75)
plt.xlim(0, 345)
plt.xticks(np.arange(0, 341, 20))
plt.show()
In [217]:
sns.set(style="darkgrid")
color = sns.color_palette()[0]
ax = plt.figure(figsize=(10,6))
sns.regplot('AbsTrialNum', 'Pos-ErrP', data=Results[Results['Prediction'] == 0],
color=color, truncate=True, line_kws = {'color' : sns.color_palette()[2]})
plt.title('Effect of elapsed time on the Pos-ErrP')
plt.xlabel('Trial number')
plt.ylabel('Mean amplitude of Pos-ErrP (uV)')
plt.ylim(-75,75)
plt.xlim(0, 345)
plt.xticks(np.arange(0, 341, 20))
plt.show()
In [63]:
ax = sns.residplot('AbsTrialNum', 'Neg-ErrP', data=Results)
plt.xlim(1, 340)
plt.ylim(-20, 20)
Out[63]:
(-20, 20)
In [60]:
Out[60]:
(1, 340)
In [ ]:
Content source: fmelinscak/error-py
Similar notebooks: