Skip to content
Snippets Groups Projects
FeatureEstimation.py 130 KiB
Newer Older
  • Learn to ignore specific revisions
  • glia's avatar
    glia committed
    # Reversed in inner loop is used to avoid sequencial data being overwritten.
    # E.g. if 0 is renamed to 1, then the next loop all 1's will be renamed to 2
    
    # Add group status
    Group_status = np.array(["CTRL"]*len(microstate_time_df["Subject_ID"]))
    Group_status[np.array([i in cases for i in microstate_time_df["Subject_ID"]])] = "PTSD"
    # Add to dataframe
    microstate_time_df.insert(2, "Group_status", Group_status)
    
    # Save df
    microstate_time_df.to_pickle(os.path.join(Feature_savepath,"microstate_time_df.pkl"))
    
    # Transition data - mean
    # Get index for groups
    PTSD_idx = np.array([i in cases for i in Subject_id])
    CTRL_idx = np.array([not i in cases for i in Subject_id])
    n_groups = 2
    
    microstate_transition_data_mean = np.zeros((n_groups,n_eye_status,n_maps,n_maps))
    microstate_transition_data_mean[0,:,:,:] = np.mean(microstate_transition_data[PTSD_idx,:,:,:], axis=0)
    microstate_transition_data_mean[1,:,:,:] = np.mean(microstate_transition_data[CTRL_idx,:,:,:], axis=0)
    
    # Convert entropy data to Pandas dataframe
    # The dimensions will each be a column with numbers and the last column will be the actual values
    arr = np.column_stack(list(map(np.ravel, np.meshgrid(*map(np.arange, microstate_entropy_data.shape), indexing="ij"))) + [microstate_entropy_data.ravel()])
    microstate_entropy_df = pd.DataFrame(arr, columns = ["Subject_ID", "Eye_status", "Value"])
    # Change from numerical coding to actual values
    eye_status = list(final_epochs[0].event_id.keys())
    
    index_values = [Subject_id,eye_status]
    for col in range(len(index_values)):
        col_name = microstate_entropy_df.columns[col]
        for shape in reversed(range(microstate_entropy_data.shape[col])): # notice this is the shape of original numpy array. Not shape of DF
            microstate_entropy_df.loc[microstate_entropy_df.iloc[:,col] == shape,col_name]\
            = index_values[col][shape]
    # Reversed in inner loop is used to avoid sequencial data being overwritten.
    # E.g. if 0 is renamed to 1, then the next loop all 1's will be renamed to 2
    
    # Add group status
    Group_status = np.array(["CTRL"]*len(microstate_entropy_df["Subject_ID"]))
    Group_status[np.array([i in cases for i in microstate_entropy_df["Subject_ID"]])] = "PTSD"
    # Add to dataframe
    microstate_entropy_df.insert(2, "Group_status", Group_status)
    # Add dummy variable for re-using plot code
    dummy_variable = ["Entropy"]*len(Group_status)
    microstate_entropy_df.insert(3, "Measurement", dummy_variable)
    
    # Save df
    microstate_entropy_df.to_pickle(os.path.join(Feature_savepath,"microstate_entropy_df.pkl"))
    
    
    # # %% Long-range temporal correlations (LRTC)
    # """
    # See Hardstone et al, 2012
    # Hurst exponent estimation steps:
    #     1. Preprocess
    #     2. Band-pass filter for frequency band of interest
    #     3. Hilbert transform to obtain amplitude envelope
    #     4. Perform DFA
    #         4.1 Compute cumulative sum of time series to create signal profile
    #         4.2 Define set of window sizes (see below)
    #         4.3 Remove the linear trend using least-squares for each window
    #         4.4 Calculate standard deviation for each window and take the mean
    #         4.5 Plot fluctuation function (Standard deviation) as function
    #             for all window sizes, on double logarithmic scale
    #         4.6 The DFA exponent alpha correspond to Hurst exponent
    #             f(L) = sd = L^alpha (with alpha as linear coefficient in log plot)
    
    # If 0 < alpha < 0.5: The process exhibits anti-correlations
    # If 0.5 < alpha < 1: The process exhibits positive correlations
    # If alpha = 0.5: The process is indistinguishable from a random process
    # If 1.0 < alpha < 2.0: The process is non-stationary. H = alpha - 1
    
    # Window sizes should be equally spaced on a logarithmic scale
    # Sizes should be at least 4 samples and up to 10% of total signal length
    # Filters can influence neighboring samples, thus filters should be tested
    # on white noise to estimate window sizes that are unaffected by filters
    
    # filter_length=str(2*1/fmin)+"s" # cannot be used with default transition bandwidth
    
    # """
    # # From simulations with white noise I determined window size thresholds for the 5 frequency bands:
    # thresholds = [7,7,7,6.5,6.5]
    # # And their corresponding log step sizes
    # with open("LRTC_log_win_sizes.pkl", "rb") as filehandle:
    #     log_win_sizes = pickle.load(filehandle)
    
    # # Variables for the the different conditions
    # # Sampling frequency
    # sfreq = final_epochs[0].info["sfreq"]
    # # Channels
    # ch_names = final_epochs[0].info["ch_names"]
    # n_channels = len(ch_names)
    # # Frequency
    # Freq_Bands = {"delta": [1.25, 4.0],
    #               "theta": [4.0, 8.0],
    #               "alpha": [8.0, 13.0],
    #               "beta": [13.0, 30.0],
    #               "gamma": [30.0, 49.0]}
    # n_freq_bands = len(Freq_Bands)
    # # Eye status
    # eye_status = list(final_epochs[0].event_id.keys())
    # n_eye_status = len(eye_status)
    
    # ### Estimating Hurst exponent for the data
    # # The data should be re-referenced to common average (Already done)
    
    # # Data are transformed to numpy arrays
    # # Then divided into EO and EC and further into each of the 5 trials
    # # So DFA is estimated for each trial separately, which was concluded from simulations
    # gaps_trials_idx = np.load("Gaps_trials_idx.npy") # re-used from microstate analysis
    # n_trials = 5
    
    # H_data = []
    # for i in range(n_subjects):
    #     # Transform data to correct shape
    #     temp_arr = final_epochs[i].get_data() # get data
    #     arr_shape = temp_arr.shape # get shape
    #     temp_arr = temp_arr.swapaxes(1,2) # swap ch and time axis
    #     temp_arr = temp_arr.reshape(arr_shape[0]*arr_shape[2],arr_shape[1]) # reshape by combining epochs and times
    #     # Get indices for eyes open and closed
    #     EC_index = final_epochs[i].events[:,2] == 1
    #     EO_index = final_epochs[i].events[:,2] == 2
    #     # Repeat with 4s * sample frequency to correct for concatenation of times and epochs
    #     EC_index = np.repeat(EC_index,4*sfreq)
    #     EO_index = np.repeat(EO_index,4*sfreq)
    #     # Divide into eye status
    #     EC_data = temp_arr[EC_index]
    #     EO_data = temp_arr[EO_index]
    #     # Divide into trials
    #     EC_gap_idx = np.array([0]+list(gaps_trials_idx[i,0])+[len(EC_data)])
    #     EO_gap_idx = np.array([0]+list(gaps_trials_idx[i,1])+[len(EO_data)])
    
    glia's avatar
    glia committed
        
    
    #     EC_trial_data = []
    #     EO_trial_data = []
    #     for t in range(n_trials):
    #         EC_trial_data.append(EC_data[EC_gap_idx[t]:EC_gap_idx[t+1]])
    #         EO_trial_data.append(EO_data[EO_gap_idx[t]:EO_gap_idx[t+1]])
    
    glia's avatar
    glia committed
            
    
    #     # Save data
    #     H_data.append([EC_trial_data,EO_trial_data]) # output [subject][eye][trial][time,ch]
    
    # # Calculate H for each subject, eye status, trial, freq and channel
    # H_arr = np.zeros((n_subjects,n_eye_status,n_trials,n_channels,n_freq_bands))
    # w_len = [len(ele) for ele in log_win_sizes]
    # DFA_arr = np.empty((n_subjects,n_eye_status,n_trials,n_channels,n_freq_bands,2,np.max(w_len)))
    # DFA_arr[:] = np.nan
    
    # # Get current time
    # c_time1 = time.localtime()
    # c_time1 = time.strftime("%a %d %b %Y %H:%M:%S", c_time1)
    # print("Started",c_time1)
    
    # # Nolds are already using all cores so multiprocessing with make it slower
    # # Warning occurs when R2 is estimated during detrending - but R2 is not used
    # warnings.simplefilter("ignore")
    # for i in range(n_subjects):
    #     # Pre-allocate memory
    #     DFA_temp = np.empty((n_eye_status,n_trials,n_channels,n_freq_bands,2,np.max(w_len)))
    #     DFA_temp[:] = np.nan
    #     H_temp = np.empty((n_eye_status,n_trials,n_channels,n_freq_bands))
    #     for e in range(n_eye_status):
    #         for trial in range(n_trials):
    #             for c in range(n_channels):
    #                 # Get the data
    #                 signal = H_data[i][e][trial][:,c]
    
    glia's avatar
    glia committed
                    
    
    #                 counter = 0 # prepare counter
    #                 for fmin, fmax in Freq_Bands.values():
    #                     # Filter for each freq band
    #                     signal_filtered = mne.filter.filter_data(signal, sfreq=sfreq, verbose=0,
    #                                                   l_freq=fmin, h_freq=fmax)
    #                     # Hilbert transform
    #                     analytic_signal = scipy.signal.hilbert(signal_filtered)
    #                     # Get Amplitude envelope
    #                     # np.abs is the same as np.linalg.norm, i.e. the length for complex input which is the amplitude
    #                     ampltude_envelope = np.abs(analytic_signal)
    #                     # Perform DFA using predefined window sizes from simulation
    #                     a, dfa_data = nolds.dfa(ampltude_envelope,
    #                                             nvals=np.exp(log_win_sizes[counter]).astype("int"),
    #                                             debug_data=True)
    #                     # Save DFA results
    #                     DFA_temp[e,trial,c,counter,:,0:w_len[counter]] = dfa_data[0:2]
    #                     H_temp[e,trial,c,counter] = a
    #                     # Update counter
    #                     counter += 1
    
    #     # Print run status
    #     print("Finished {} out of {}".format(i+1,n_subjects))
    #     # Save the results
    #     H_arr[i] = H_temp
    #     DFA_arr[i] = DFA_temp
    
    # warnings.simplefilter("default")
    
    # # Get current time
    # c_time2 = time.localtime()
    # c_time2 = time.strftime("%a %d %b %Y %H:%M:%S", c_time2)
    # print("Started", c_time1, "\nCurrent Time",c_time2)
    
    # # Save the DFA analysis data 
    # np.save(Feature_savepath+"DFA_arr.npy", DFA_arr)
    # np.save(Feature_savepath+"H_arr.npy", H_arr)
    
    glia's avatar
    glia committed
    
    
    1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730
    # # Load
    # DFA_arr = np.load(Feature_savepath+"DFA_arr.npy")
    # H_arr = np.load(Feature_savepath+"H_arr.npy")
    
    # # Average the Hurst Exponent across trials
    # H_arr = np.mean(H_arr, axis=2)
    
    # # Convert to Pandas dataframe (Hurst exponent)
    # # The dimensions will each be a column with numbers and the last column will be the actual values
    # arr = np.column_stack(list(map(np.ravel, np.meshgrid(*map(np.arange, H_arr.shape), indexing="ij"))) + [H_arr.ravel()])
    # H_data_df = pd.DataFrame(arr, columns = ["Subject_ID", "Eye_status", "Channel", "Freq_band", "Value"])
    # # Change from numerical coding to actual values
    # eye_status = list(final_epochs[0].event_id.keys())
    # ch_name = final_epochs[0].info["ch_names"]
    
    # index_values = [Subject_id,eye_status,ch_name,list(Freq_Bands.keys())]
    # for col in range(len(index_values)):
    #     col_name = H_data_df.columns[col]
    #     for shape in range(H_arr.shape[col]): # notice this is the shape of original numpy array. Not shape of DF
    #         H_data_df.loc[H_data_df.iloc[:,col] == shape,col_name]\
    #         = index_values[col][shape]
    
    # # Add group status
    # Group_status = np.array(["CTRL"]*len(H_data_df["Subject_ID"]))
    # Group_status[np.array([i in cases for i in H_data_df["Subject_ID"]])] = "PTSD"
    # # Add to dataframe
    # H_data_df.insert(2, "Group_status", Group_status)
    
    # # Fix Freq_band categorical order
    # H_data_df["Freq_band"] = H_data_df["Freq_band"].astype("category").\
    #             cat.reorder_categories(list(Freq_Bands.keys()), ordered=True)
    
    # # Global Hurst exponent
    # H_data_df_global = H_data_df.groupby(["Subject_ID", "Eye_status", "Freq_band"]).mean().reset_index() # by default pandas mean skip nan
    # # Add group status (cannot use group_by as each subject only have 1 group, not both)
    # Group_status = np.array(["CTRL"]*len(H_data_df_global["Subject_ID"]))
    # Group_status[np.array([i in cases for i in H_data_df_global["Subject_ID"]])] = "PTSD"
    # # Add to dataframe
    # H_data_df_global.insert(2, "Group_status", Group_status)
    # # Add dummy variable for re-using plot code
    # dummy_variable = ["Global Hurst Exponent"]*H_data_df_global.shape[0]
    # H_data_df_global.insert(3, "Measurement", dummy_variable )
    
    # # Save the data
    # H_data_df.to_pickle(os.path.join(Feature_savepath,"H_data_df.pkl"))
    # H_data_df_global.to_pickle(os.path.join(Feature_savepath,"H_data_global_df.pkl"))
    
    # # %% Source localization of sensor data
    # # Using non-interpolated channels
    # # Even interpolated channels during preprocessing and visual inspection
    # # are dropped
    
    # # Prepare epochs for estimation of source connectivity
    # source_epochs = [0]*n_subjects
    # for i in range(n_subjects):
    #     source_epochs[i] = final_epochs[i].copy()
    
    # ### Make forward solutions
    # # A forward solution is first made for all individuals with no dropped channels
    # # Afterwards individual forward solutions are made for subjects with bad
    # # channels that were interpolated in preprocessing and these are dropped
    # # First forward operator is computed using a template MRI for each dataset
    # fs_dir = "/home/glia/MNE-fsaverage-data/fsaverage"
    # subjects_dir = os.path.dirname(fs_dir)
    # trans = "fsaverage"
    # src = os.path.join(fs_dir, "bem", "fsaverage-ico-5-src.fif")
    # bem = os.path.join(fs_dir, "bem", "fsaverage-5120-5120-5120-bem-sol.fif")
    
    # # Read the template sourcespace
    # sourcespace = mne.read_source_spaces(src)
    
    # temp_idx = 0 # Index with subject that had no bad channels
    # subject_eeg = source_epochs[temp_idx].copy()
    # subject_eeg.set_eeg_reference(projection=True) # needed for inverse modelling
    # # Make forward solution
    # fwd = mne.make_forward_solution(subject_eeg.info, trans=trans, src=src,
    #                             bem=bem, eeg=True, mindist=5.0, n_jobs=1)
    # # Save forward operator
    # fname_fwd = "./Source_fwd/fsaverage-fwd.fif"
    # mne.write_forward_solution(fname_fwd, fwd, overwrite=True)
    
    # # A specific forward solution is also made for each subject with bad channels
    # with open("./Preprocessing/bad_ch.pkl", "rb") as file:
    #    bad_ch = pickle.load(file)
    
    # All_bad_ch = bad_ch
    # All_drop_epochs = dropped_epochs_df
    # All_dropped_ch = []
    
    # Bad_ch_idx = [idx for idx, item in enumerate(All_bad_ch) if item != 0]
    # Bad_ch_subjects = All_drop_epochs["Subject_ID"][Bad_ch_idx]
    # # For each subject with bad channels, drop the channels and make forward operator
    # for n in range(len(Bad_ch_subjects)):
    #     Subject = Bad_ch_subjects.iloc[n]
    #     try:
    #         Subject_idx = Subject_id.index(Subject)
    #         # Get unique bad channels
    #         Bad_ch0 = All_bad_ch[Bad_ch_idx[n]]
    #         Bad_ch1 = []
    #         for i2 in range(len(Bad_ch0)):
    #             if type(Bad_ch0[i2]) == list:
    #                 for i3 in range(len(Bad_ch0[i2])):
    #                     Bad_ch1.append(Bad_ch0[i2][i3])
    #             elif type(Bad_ch0[i2]) == str:
    #                 Bad_ch1.append(Bad_ch0[i2])
    #         Bad_ch1 = np.unique(Bad_ch1)
    #         # Drop the bad channels
    #         source_epochs[Subject_idx].drop_channels(Bad_ch1)
    #         # Save the overview of dropped channels
    #         All_dropped_ch.append([Subject,Subject_idx,Bad_ch1])
    #         # Make forward operator
    #         subject_eeg = source_epochs[Subject_idx].copy()
    #         subject_eeg.set_eeg_reference(projection=True) # needed for inverse modelling
    #         # Make forward solution
    #         fwd = mne.make_forward_solution(subject_eeg.info, trans=trans, src=src,
    #                                     bem=bem, eeg=True, mindist=5.0, n_jobs=1)
    #         # Save forward operator
    #         fname_fwd = "./Source_fwd/fsaverage_{}-fwd.fif".format(Subject)
    #         mne.write_forward_solution(fname_fwd, fwd, overwrite=True)
    #     except:
    #         print(Subject,"was already dropped")
    
    # with open("./Preprocessing/All_datasets_bad_ch.pkl", "wb") as filehandle:
    #     pickle.dump(All_dropped_ch, filehandle)
    
    
    # # %% Load forward operators
    # # Re-use for all subjects without dropped channels
    # fname_fwd = "./Source_fwd/fsaverage-fwd.fif"
    # fwd = mne.read_forward_solution(fname_fwd)
    
    # fwd_list = [fwd]*n_subjects
    
    # # Use specific forward solutions for subjects with dropped channels
    # with open("./Preprocessing/All_datasets_bad_ch.pkl", "rb") as file:
    #    All_dropped_ch = pickle.load(file)
    
    # for i in range(len(All_dropped_ch)):
    #     Subject = All_dropped_ch[i][0]
    #     Subject_idx = All_dropped_ch[i][1]
    #     fname_fwd = "./Source_fwd/fsaverage_{}-fwd.fif".format(Subject)
    #     fwd = mne.read_forward_solution(fname_fwd)
    #     fwd_list[Subject_idx] = fwd
    
    # # Check the correct number of channels are present in fwd
    # random_point = int(np.random.randint(0,len(All_dropped_ch)-1,1))
    # assert len(fwds[All_dropped_ch[random_point][1]].ch_names) == source_epochs[All_dropped_ch[random_point][1]].info["nchan"]
    
    # # %% Make parcellation
    # # After mapping to source space, I end up with 20484 vertices
    # # but I wanted to map to fewer sources and not many more
    # # Thus I need to perform parcellation
    # # Get labels for FreeSurfer "aparc" cortical parcellation (example with 74 labels/hemi - Destriuex)
    # labels_aparc = mne.read_labels_from_annot("fsaverage", parc="aparc.a2009s",
    #                                     subjects_dir=subjects_dir)
    # labels_aparc = labels_aparc[:-2] # remove unknowns
    
    # labels_aparc_names = [label.name for label in labels_aparc]
    
    # # Manually adding the 31 ROIs (14-lh/rh + 3 in midline) from Toll et al, 2020
    # # Making fuction to take subset of a label
    # def label_subset(label, subset, name="ROI_name"):
    #     label_subset = mne.Label(label.vertices[subset], label.pos[subset,:],
    #                          label.values[subset], label.hemi,
    #                          name = "{}-{}".format(name,label.hemi),
    #                          subject = label.subject, color = None)
    #     return label_subset
    
    # ### Visual area 1 (V1 and somatosensory cortex BA1-3)
    # label_filenames = ["lh.V1.label", "rh.V1.label",
    #                    "lh.BA1.label", "rh.BA1.label",
    #                    "lh.BA2.label", "rh.BA2.label",
    #                    "lh.BA3a.label", "rh.BA3a.label",
    #                    "lh.BA3b.label", "rh.BA3b.label"]
    # labels0 = [0]*len(label_filenames)
    # for i, filename in enumerate(label_filenames):
    #     labels0[i] = mne.read_label(os.path.join(fs_dir, "label", filename), subject="fsaverage")
    # # Add V1 to final label variable
    # labels = labels0[:2]
    # # Rename to remove redundant hemi information
    # labels[0].name = "V1-{}".format(labels[0].hemi)
    # labels[1].name = "V1-{}".format(labels[1].hemi)
    # # Assign a color
    # labels[0].color = matplotlib.colors.to_rgba("salmon")
    # labels[1].color = matplotlib.colors.to_rgba("salmon")
    # # Combine Brodmann Areas for SMC. Only use vertices ones to avoid duplication error
    # SMC_labels = labels0[2:]
    # for hem in range(2):
    #     SMC_p1 = SMC_labels[hem]
    #     for i in range(1,len(SMC_labels)//2):
    #         SMC_p2 = SMC_labels[hem+2*i]
    #         p2_idx = np.isin(SMC_p2.vertices, SMC_p1.vertices, invert=True)
    #         SMC_p21 = label_subset(SMC_p2, p2_idx, "SMC")
    #         SMC_p1 = SMC_p1.__add__(SMC_p21)
    #     SMC_p1.name = SMC_p21.name
    #     # Assign a color
    #     SMC_p1.color = matplotlib.colors.to_rgba("orange")
    #     labels.append(SMC_p1)
    
    # ### Inferior frontal junction
    # # Located at junction between inferior frontal and inferior precentral sulcus
    # label_aparc_names0 = ["S_front_inf","S_precentral-inf-part"]
    # temp_labels = []
    # for i in range(len(label_aparc_names0)):
    #     labels_aparc_idx = [labels_aparc_names.index(l) for l in labels_aparc_names if l.startswith(label_aparc_names0[i])]
    #     for i2 in range(len(labels_aparc_idx)):
    #         temp_labels.append(labels_aparc[labels_aparc_idx[i2]].copy())
    
    # pos1 = temp_labels[0].pos
    # pos2 = temp_labels[2].pos
    # distm = scipy.spatial.distance.cdist(pos1,pos2)
    # # Find the closest points between the 2 ROIs
    # l1_idx = np.unique(np.where(distm<np.quantile(distm, 0.001))[0]) # q chosen to correspond to around 10% of ROI
    # l2_idx = np.unique(np.where(distm<np.quantile(distm, 0.0005))[1]) # q chosen to correspond to around 10% of ROI
    
    # IFJ_label_p1 = label_subset(temp_labels[0], l1_idx, "IFJ")
    # IFJ_label_p2 = label_subset(temp_labels[2], l2_idx, "IFJ")
    # # Combine the 2 parts
    # IFJ_label = IFJ_label_p1.__add__(IFJ_label_p2)
    # IFJ_label.name = IFJ_label_p1.name
    # # Assign a color
    # IFJ_label.color = matplotlib.colors.to_rgba("chartreuse")
    # # Append to final list
    # labels.append(IFJ_label)
    
    # # Do the same for the right hemisphere
    # pos1 = temp_labels[1].pos
    # pos2 = temp_labels[3].pos
    # distm = scipy.spatial.distance.cdist(pos1,pos2)
    # # Find the closest points between the 2 ROIs
    # l1_idx = np.unique(np.where(distm<np.quantile(distm, 0.00075))[0]) # q chosen to correspond to around 10% of ROI
    # l2_idx = np.unique(np.where(distm<np.quantile(distm, 0.0005))[1]) # q chosen to correspond to around 10% of ROI
    # IFJ_label_p1 = label_subset(temp_labels[1], l1_idx, "IFJ")
    # IFJ_label_p2 = label_subset(temp_labels[3], l2_idx, "IFJ")
    # # Combine the 2 parts
    # IFJ_label = IFJ_label_p1.__add__(IFJ_label_p2)
    # IFJ_label.name = IFJ_label_p1.name
    # # Assign a color
    # IFJ_label.color = matplotlib.colors.to_rgba("chartreuse")
    # # Append to final list
    # labels.append(IFJ_label)
    
    # ### Intraparietal sulcus
    # label_aparc_names0 = ["S_intrapariet_and_P_trans"]
    # labels_aparc_idx = [labels_aparc_names.index(l) for l in labels_aparc_names if l.startswith(label_aparc_names0[0])]
    # for i in range(len(labels_aparc_idx)):
    #     labels.append(labels_aparc[labels_aparc_idx[i]].copy())
    #     labels[-1].name = "IPS-{}".format(labels[-1].hemi)
    
    # ### Frontal eye field as intersection between middle frontal gyrus and precentral gyrus
    # label_aparc_names0 = ["G_front_middle","G_precentral"]
    # temp_labels = []
    # for i in range(len(label_aparc_names0)):
    #     labels_aparc_idx = [labels_aparc_names.index(l) for l in labels_aparc_names if l.startswith(label_aparc_names0[i])]
    #     for i2 in range(len(labels_aparc_idx)):
    #         temp_labels.append(labels_aparc[labels_aparc_idx[i2]].copy())
    
    # # Take 10% of middle frontal gyrus closest to precentral gyrus (most posterior)
    # temp_label0 = temp_labels[0]
    # G_fm_y = temp_label0.pos[:,1]
    # thres_G_fm_y = np.sort(G_fm_y)[len(G_fm_y)//10]
    # idx_p1 = np.where(G_fm_y<thres_G_fm_y)[0]
    # FEF_label_p1 = label_subset(temp_label0, idx_p1, "FEF")
    # # Take 10% closest for precentral gyrus (most anterior)
    # temp_label0 = temp_labels[2]
    # # I cannot only use y (anterior/posterior) but also need to restrict z-position
    # G_pre_cen_z = temp_label0.pos[:,2]
    # thres_G_pre_cen_z = 0.04 # visually inspected threshold
    # G_pre_cen_y = temp_label0.pos[:,1]
    # thres_G_pre_cen_y = np.sort(G_pre_cen_y[G_pre_cen_z>thres_G_pre_cen_z])[-len(G_pre_cen_y)//10] # notice - for anterior
    # idx_p2 = np.where((G_pre_cen_y>thres_G_pre_cen_y) & (G_pre_cen_z>thres_G_pre_cen_z))[0]
    # FEF_label_p2 = label_subset(temp_label0, idx_p2, "FEF")
    # # Combine the 2 parts
    # FEF_label = FEF_label_p1.__add__(FEF_label_p2)
    # FEF_label.name = FEF_label_p1.name
    # # Assign a color
    # FEF_label.color = matplotlib.colors.to_rgba("aqua")
    # # Append to final list
    # labels.append(FEF_label)
    
    # # Do the same for the right hemisphere
    # temp_label0 = temp_labels[1]
    # G_fm_y = temp_label0.pos[:,1]
    # thres_G_fm_y = np.sort(G_fm_y)[len(G_fm_y)//10]
    # idx_p1 = np.where(G_fm_y<thres_G_fm_y)[0]
    # FEF_label_p1 = label_subset(temp_label0, idx_p1, "FEF")
    
    # temp_label0 = temp_labels[3]
    # G_pre_cen_z = temp_label0.pos[:,2]
    # thres_G_pre_cen_z = 0.04 # visually inspected threshold
    # G_pre_cen_y = temp_label0.pos[:,1]
    # thres_G_pre_cen_y = np.sort(G_pre_cen_y[G_pre_cen_z>thres_G_pre_cen_z])[-len(G_pre_cen_y)//10] # notice - for anterior
    # idx_p2 = np.where((G_pre_cen_y>thres_G_pre_cen_y) & (G_pre_cen_z>thres_G_pre_cen_z))[0]
    # FEF_label_p2 = label_subset(temp_label0, idx_p2, "FEF")
    # # Combine the 2 parts
    # FEF_label = FEF_label_p1.__add__(FEF_label_p2)
    # FEF_label.name = FEF_label_p1.name
    # # Assign a color
    # FEF_label.color = matplotlib.colors.to_rgba("aqua")
    # # Append to final list
    # labels.append(FEF_label)
    
    # ### Supplementary eye fields
    # # Located at caudal end of frontal gyrus and upper part of paracentral sulcus
    # label_aparc_names0 = ["G_and_S_paracentral","G_front_sup"]
    # temp_labels = []
    # for i in range(len(label_aparc_names0)):
    #     labels_aparc_idx = [labels_aparc_names.index(l) for l in labels_aparc_names if l.startswith(label_aparc_names0[i])]
    #     for i2 in range(len(labels_aparc_idx)):
    #         temp_labels.append(labels_aparc[labels_aparc_idx[i2]].copy())
    
    # pos1 = temp_labels[0].pos
    # pos2 = temp_labels[2].pos
    # distm = scipy.spatial.distance.cdist(pos1,pos2)
    # # Find the closest points between the 2 ROIs
    # l1_idx = np.unique(np.where(distm<np.quantile(distm, 0.0005))[0]) # q chosen to correspond to around 15% of ROI
    # l2_idx = np.unique(np.where(distm<np.quantile(distm, 0.005))[1]) # q chosen to correspond to around 10% of ROI
    # # Notice that superior frontal gyrus is around 4 times bigger than paracentral
    # len(l1_idx)/pos1.shape[0]
    # len(l2_idx)/pos2.shape[0]
    # # Only use upper part
    # z_threshold = 0.06 # visually inspected
    # l1_idx = l1_idx[pos1[l1_idx,2] > z_threshold]
    # l2_idx = l2_idx[pos2[l2_idx,2] > z_threshold]
    
    # SEF_label_p1 = label_subset(temp_labels[0], l1_idx, "SEF")
    # SEF_label_p2 = label_subset(temp_labels[2], l2_idx, "SEF")
    # # Combine the 2 parts
    # SEF_label = SEF_label_p1.__add__(SEF_label_p2)
    # SEF_label.name = SEF_label_p1.name
    # # Assign a color
    # SEF_label.color = matplotlib.colors.to_rgba("royalblue")
    # # Append to final list
    # labels.append(SEF_label)
    
    # # Do the same for the right hemisphere
    # pos1 = temp_labels[1].pos
    # pos2 = temp_labels[3].pos
    # distm = scipy.spatial.distance.cdist(pos1,pos2)
    # # Find the closest points between the 2 ROIs
    # l1_idx = np.unique(np.where(distm<np.quantile(distm, 0.0005))[0]) # q chosen to correspond to around 15% of ROI
    # l2_idx = np.unique(np.where(distm<np.quantile(distm, 0.005))[1]) # q chosen to correspond to around 10% of ROI
    # # Notice that superior frontal gyrus is around 4 times bigger than paracentral
    # len(l1_idx)/pos1.shape[0]
    # len(l2_idx)/pos2.shape[0]
    # # Only use upper part
    # z_threshold = 0.06 # visually inspected
    # l1_idx = l1_idx[pos1[l1_idx,2] > z_threshold]
    # l2_idx = l2_idx[pos2[l2_idx,2] > z_threshold]
    
    # SEF_label_p1 = label_subset(temp_labels[1], l1_idx, "SEF")
    # SEF_label_p2 = label_subset(temp_labels[3], l2_idx, "SEF")
    # # Combine the 2 parts
    # SEF_label = SEF_label_p1.__add__(SEF_label_p2)
    # SEF_label.name = SEF_label_p1.name
    # # Assign a color
    # SEF_label.color = matplotlib.colors.to_rgba("royalblue")
    # # Append to final list
    # labels.append(SEF_label)
    
    # ### Posterior cingulate cortex
    # label_aparc_names0 = ["G_cingul-Post-dorsal", "G_cingul-Post-ventral"]
    # temp_labels = []
    # for i in range(len(label_aparc_names0)):
    #     labels_aparc_idx = [labels_aparc_names.index(l) for l in labels_aparc_names if l.startswith(label_aparc_names0[i])]
    #     for i2 in range(len(labels_aparc_idx)):
    #         temp_labels.append(labels_aparc[labels_aparc_idx[i2]].copy())
    # labels0 = []
    # for hem in range(2):
    #     PCC_p1 = temp_labels[hem]
    #     for i in range(1,len(temp_labels)//2):
    #         PCC_p2 = temp_labels[hem+2*i]
    #         PCC_p1 = PCC_p1.__add__(PCC_p2)
    #     PCC_p1.name = "PCC-{}".format(PCC_p1.hemi)
    #     labels0.append(PCC_p1)
    # # Combine the 2 hemisphere in 1 label
    # labels.append(labels0[0].__add__(labels0[1]))
    
    # ### Medial prefrontal cortex
    # # From their schematic it looks like rostral 1/4 of superior frontal gyrus
    # label_aparc_names0 = ["G_front_sup"]
    # temp_labels = []
    # for i in range(len(label_aparc_names0)):
    #     labels_aparc_idx = [labels_aparc_names.index(l) for l in labels_aparc_names if l.startswith(label_aparc_names0[i])]
    #     for i2 in range(len(labels_aparc_idx)):
    #         temp_labels0 = labels_aparc[labels_aparc_idx[i2]].copy()
    #         temp_labels0 = temp_labels0.split(4, subjects_dir=subjects_dir)[3]
    #         temp_labels0.name = "mPFC-{}".format(temp_labels0.hemi)
    #         temp_labels.append(temp_labels0)
    # # Combine the 2 hemisphere in 1 label
    # labels.append(temp_labels[0].__add__(temp_labels[1]))
    
    # ### Angular gyrus
    # label_aparc_names0 = ["G_pariet_inf-Angular"]
    # for i in range(len(label_aparc_names0)):
    #     labels_aparc_idx = [labels_aparc_names.index(l) for l in labels_aparc_names if l.startswith(label_aparc_names0[i])]
    #     for i2 in range(len(labels_aparc_idx)):
    #         temp_labels = labels_aparc[labels_aparc_idx[i2]].copy()
    #         temp_labels.name = "ANG-{}".format(temp_labels.hemi)
    #         labels.append(temp_labels)
    
    # ### Posterior middle frontal gyrus
    # label_aparc_names0 = ["G_front_middle"]
    # for i in range(len(label_aparc_names0)):
    #     labels_aparc_idx = [labels_aparc_names.index(l) for l in labels_aparc_names if l.startswith(label_aparc_names0[i])]
    #     for i2 in range(len(labels_aparc_idx)):
    #         temp_labels = labels_aparc[labels_aparc_idx[i2]].copy()
    #         temp_labels = temp_labels.split(2, subjects_dir=subjects_dir)[0]
    #         temp_labels.name = "PMFG-{}".format(temp_labels.hemi)
    #         labels.append(temp_labels)
    
    # ### Inferior parietal lobule
    # # From their parcellation figure seems to be rostral angular gyrus and posterior supramarginal gyrus
    # label_aparc_names0 = ["G_pariet_inf-Angular","G_pariet_inf-Supramar"]
    # temp_labels = []
    # for i in range(len(label_aparc_names0)):
    #     labels_aparc_idx = [labels_aparc_names.index(l) for l in labels_aparc_names if l.startswith(label_aparc_names0[i])]
    #     for i2 in range(len(labels_aparc_idx)):
    #         temp_labels.append(labels_aparc[labels_aparc_idx[i2]].copy())
    # # Split angular in 2 and get rostral part
    # temp_labels[0] = temp_labels[0].split(2, subjects_dir=subjects_dir)[1]
    # temp_labels[1] = temp_labels[1].split(2, subjects_dir=subjects_dir)[1]
    # # Split supramarginal in 2 and get posterior part
    # temp_labels[2] = temp_labels[2].split(2, subjects_dir=subjects_dir)[0]
    # temp_labels[3] = temp_labels[3].split(2, subjects_dir=subjects_dir)[0]
    
    # for hem in range(2):
    #     PCC_p1 = temp_labels[hem]
    #     for i in range(1,len(temp_labels)//2):
    #         PCC_p2 = temp_labels[hem+2*i]
    #         PCC_p1 = PCC_p1.__add__(PCC_p2)
    #     PCC_p1.name = "IPL-{}".format(PCC_p1.hemi)
    #     labels.append(PCC_p1)
    
    # ### Orbital gyrus
    # # From their figure it seems to correspond to orbital part of inferior frontal gyrus
    # label_aparc_names0 = ["G_front_inf-Orbital"]
    # for i in range(len(label_aparc_names0)):
    #     labels_aparc_idx = [labels_aparc_names.index(l) for l in labels_aparc_names if l.startswith(label_aparc_names0[i])]
    #     for i2 in range(len(labels_aparc_idx)):
    #         temp_labels = labels_aparc[labels_aparc_idx[i2]].copy()
    #         temp_labels.name = "ORB-{}".format(temp_labels.hemi)
    #         labels.append(temp_labels)
    
    # ### Middle temporal gyrus
    # # From their figure it seems to only be 1/4 of MTG at the 2nd to last caudal part
    # label_aparc_names0 = ["G_temporal_middle"]
    # for i in range(len(label_aparc_names0)):
    #     labels_aparc_idx = [labels_aparc_names.index(l) for l in labels_aparc_names if l.startswith(label_aparc_names0[i])]
    #     for i2 in range(len(labels_aparc_idx)):
    #         temp_labels = labels_aparc[labels_aparc_idx[i2]].copy()
    #         temp_labels = temp_labels.split(4, subjects_dir=subjects_dir)[1]
    #         temp_labels.name = "MTG-{}".format(temp_labels.hemi)
    #         labels.append(temp_labels)
    
    # ### Anterior middle frontal gyrus
    # label_aparc_names0 = ["G_front_middle"]
    # for i in range(len(label_aparc_names0)):
    #     labels_aparc_idx = [labels_aparc_names.index(l) for l in labels_aparc_names if l.startswith(label_aparc_names0[i])]
    #     for i2 in range(len(labels_aparc_idx)):
    #         temp_labels = labels_aparc[labels_aparc_idx[i2]].copy()
    #         temp_labels = temp_labels.split(2, subjects_dir=subjects_dir)[1]
    #         temp_labels.name = "AMFG-{}".format(temp_labels.hemi)
    #         labels.append(temp_labels)
    
    # ### Insula
    # label_aparc_names0 = ["G_Ins_lg_and_S_cent_ins","G_insular_short"]
    # temp_labels = []
    # for i in range(len(label_aparc_names0)):
    #     labels_aparc_idx = [labels_aparc_names.index(l) for l in labels_aparc_names if l.startswith(label_aparc_names0[i])]
    #     for i2 in range(len(labels_aparc_idx)):
    #         temp_labels.append(labels_aparc[labels_aparc_idx[i2]].copy())
    # for hem in range(2):
    #     PCC_p1 = temp_labels[hem]
    #     for i in range(1,len(temp_labels)//2):
    #         PCC_p2 = temp_labels[hem+2*i]
    #         PCC_p1 = PCC_p1.__add__(PCC_p2)
    #     PCC_p1.name = "INS-{}".format(PCC_p1.hemi)
    #     labels.append(PCC_p1)
    
    # ### (Dorsal) Anterior Cingulate Cortex
    # label_aparc_names0 = ["G_and_S_cingul-Ant"]
    # temp_labels = []
    # for i in range(len(label_aparc_names0)):
    #     labels_aparc_idx = [labels_aparc_names.index(l) for l in labels_aparc_names if l.startswith(label_aparc_names0[i])]
    #     for i2 in range(len(labels_aparc_idx)):
    #         temp_labels.append(labels_aparc[labels_aparc_idx[i2]].copy())
    #         temp_labels[-1].name = "ACC-{}".format(temp_labels[-1].hemi)
    # # Combine the 2 hemisphere in 1 label
    # labels.append(temp_labels[0].__add__(temp_labels[1]))
    
    # ### Supramarginal Gyrus
    # label_aparc_names0 = ["G_pariet_inf-Supramar"]
    # for i in range(len(label_aparc_names0)):
    #     labels_aparc_idx = [labels_aparc_names.index(l) for l in labels_aparc_names if l.startswith(label_aparc_names0[i])]
    #     for i2 in range(len(labels_aparc_idx)):
    #         temp_labels = labels_aparc[labels_aparc_idx[i2]].copy()
    #         temp_labels.name = "SUP-{}".format(temp_labels.hemi)
    #         labels.append(temp_labels)
    
    # print("{} ROIs have been defined".format(len(labels)))
    
    # # # Visualize positions
    # # fig = plt.figure()
    # # ax = fig.add_subplot(111, projection="3d")
    # # for i in range(0,3):
    # #     temp_pos = temp_labels[i].pos
    # #     ax.scatter(temp_pos[:,0],temp_pos[:,1],temp_pos[:,2], marker="o", alpha=0.1)
    # # # Add to plot
    # # ax.scatter(labels[-1].pos[:,0],labels[-1].pos[:,1],labels[-1].pos[:,2], marker="o")
    
    # # # Visualize the labels
    # # # temp_l = labels_aparc[labels_aparc_idx[0]]
    # # temp_l = labels[-2]
    # # l_stc = stc[100].in_label(temp_l)
    # # l_stc.vertices
    
    # # l_stc.plot(**surfer_kwargs)
    
    # # Save the annotation file
    # with open("custom_aparc2009_Li_et_al_2022.pkl", "wb") as file:
    #     pickle.dump(labels, file)
    
    # # %% Calculate orthogonalized power envelope connectivity in source space
    # # In non-interpolated channels
    # # Updated 22/1 - 2021 to use delta = 1/81 and assumption
    # # about non-correlated and equal variance noise covariance matrix for channels
    
    glia's avatar
    glia committed
    
    
    # # Load
    # with open("custom_aparc2009_Li_et_al_2022.pkl", "rb") as file:
    #     labels = pickle.load(file)
    # label_names = [label.name for label in labels]
    
    # # Define function to estimate PEC
    # def PEC_estimation(x, freq_bands, sfreq=200):
    #     """
    #     This function takes a source timeseries signal x and performs:
    #         1. Bandpass filtering
    #         2. Hilbert transform to yield analytical signal
    #         3. Compute all to all connectivity by iteratively computing for each pair
    #             a. Orthogonalization
    #             b. Computing power envelopes by squaring the signals |x|^2
    #             c. Log-transform to enhance normality
    #             d. Pearson's correlation between each pair
    #             e. Fisher's r-to-z transform to enhance normality
    #     The code has been optimized by inspiration from MNE-Python's function:
    #     mne.connectivity.enelope_correlation.
    
    glia's avatar
    glia committed
        
    
    #     In MNE-python version < 0.22 there was a bug, but after the fix in 0.22
    #     the mne function is equivalent to my implementation, although they don't
    #     use epsilon but gives same result with a RuntimeWarning about log(0)
    
    glia's avatar
    glia committed
        
    
    #     IMPORTANT NOTE:
    #         Filtering introduce artifacts for first and last timepoint
    #     The values are very low, more than 1e-12 less than the others
    #     If they are not removed, then they will heavily influence Pearson's
    #     correlation as it is outlier sensitive
    
    glia's avatar
    glia committed
        
    
    #     Inputs:
    #         x - The signal in source space as np.array with shape (ROIs,Timepoints)
    #         freq_bands - The frequency bands of interest as a dictionary e.g.
    #                      {"alpha": [8.0, 13.0], "beta": [13.0, 30.0]}
    #         sfreq - The sampling frequency in Hertz
    
    glia's avatar
    glia committed
        
    
    #     Output:
    #         The pairwise connectivity matrix
    #     """
    #     n_roi, n_timepoints = x.shape
    #     n_freq_bands = len(freq_bands)
    
    glia's avatar
    glia committed
        
    
    #     epsilon = 1e-100 # small value to prevent log(0) errors
    
    glia's avatar
    glia committed
        
    
    #     # Filter the signal in the different freq bands
    #     PEC_con0 = np.zeros((n_roi,n_roi,n_freq_bands))
    #     for fname, frange in freq_bands.items():
    #         fmin, fmax = [float(interval) for interval in frange]
    #         signal_filtered = mne.filter.filter_data(x, sfreq, fmin, fmax,
    #                                           fir_design="firwin", verbose=0)
    #         # Filtering on finite signals will yield very low values for first
    #         # and last timepoint, which can create outliers. E.g. 1e-29 compared to 1e-14
    #         # Outlier sensitive methods, like Pearson's correlation, is therefore
    #         # heavily affected and this systematic error is removed by removing
    #         # the first and last timepoint
    #         signal_filtered = signal_filtered[:,1:-1]
    
    glia's avatar
    glia committed
            
    
    #         # Hilbert transform
    #         analytic_signal = scipy.signal.hilbert(signal_filtered)
    #         # I will use x and y to keep track of orthogonalization
    #         x0 = analytic_signal
    #         # Get power envelope
    #         x0_mag = np.abs(x0)
    #         # Get scaled conjugate used for orthogonalization estimation
    #         x0_conj_scaled = x0.conj()
    #         x0_conj_scaled /= x0_mag
    #         # Take square power envelope
    #         PEx = np.square(x0_mag)
    #         # Take log transform
    #         lnPEx = np.log(PEx+epsilon)
    #         # Remove mean for Pearson correlation calculation
    #         lnPEx_nomean = lnPEx - np.mean(lnPEx, axis=-1, keepdims=True) # normalize each roi timeseries
    #         # Get std for Pearson correlation calculation
    #         lnPEx_std = np.std(lnPEx, axis=-1)
    #         lnPEx_std[lnPEx_std == 0] = 1 # Prevent std = 0 problems
    #         # Prepare con matrix
    #         con0 = np.zeros((n_roi,n_roi))
    #         for roi_r, y0 in enumerate(x0): # for each y0
    #             # Calculate orthogonalized signal y with respect to x for all x
    #             # Using y_ort = imag(y*x_conj/|x|)
    #             # I checked the formula in temp_v3 and it works as intended
    #             # I want to orthogonalize element wise for each timepoint
    #             y0_ort = (y0*x0_conj_scaled).imag
    #             # Here y0_ort.shape = (n_roi, n_timepoints)
    #             # So y is current roi and the first axis gives each x it is orthogonalized to
    #             # Take the abs to get power envelope
    #             y0_ort = np.abs(y0_ort)
    #             # Prevent log(0) error when calculating y_ort on y
    #             y0_ort[roi_r] = 1. # this will be 0 zero after mean subtraction
    #             # Take square power envelope
    #             PEy = np.square(y0_ort) # squared power envelope
    #             # Take log transform
    #             lnPEy = np.log(PEy+epsilon)
    #             # Remove mean for pearson correlation calculation
    #             lnPEy_nomean = lnPEy - np.mean(lnPEy, axis=-1, keepdims=True)
    #             # Get std for Pearson correlation calculation
    #             lnPEy_std = np.std(lnPEy, axis=-1)
    #             lnPEy_std[lnPEy_std == 0] = 1.
    #             # Pearson correlation is expectation of X_nomean * Y_nomean for each time-series divided with standard deviations
    #             PEC = np.mean(lnPEx_nomean*lnPEy_nomean, axis=-1)
    #             PEC /= lnPEx_std
    #             PEC /= lnPEy_std
    #             con0[roi_r] = PEC
    #         # The con0 connectivity matrix should be read as correlation between
    #         # orthogonalized y (row number) and x (column number)
    #         # It is not symmetrical, as cor(roi2_ort, roi1) is not cor(roi1_ort, roi2)
    #         # To make it symmetrical the average of the absolute correlation
    #         # of the 2 possibilities for each pair are taken
    #         con0 = np.abs(con0)
    #         con0 = (con0.T+con0)/2.
    #         # Fisher's z transform - which is equivalent to arctanh
    #         con0 = np.arctanh(con0)
    #         # The diagonal is not 0 as I wanted to avoid numerical errors with log(0)
    #         # and used a small epsilon value. Thus the diagonal is explicitly set to 0
    
    glia's avatar
    glia committed
            
    
    #         # Save to array
    #         PEC_con0[:,:,list(freq_bands.keys()).index(fname)] = con0
    #     return PEC_con0
    
    # # Prepare variables
    # Freq_Bands = {"delta": [1.25, 4.0],
    #               "theta": [4.0, 8.0],
    #               "alpha": [8.0, 13.0],
    #               "beta": [13.0, 30.0],
    #               "gamma": [30.0, 49.0]}
    # n_freq_bands = len(Freq_Bands)
    # n_roi = len(labels)
    
    # # Get current time
    # c_time1 = time.localtime()
    # c_time1 = time.strftime("%a %d %b %Y %H:%M:%S", c_time1)
    # print(c_time1)
    
    # # PEC analysis
    # PEC_data_list = [0]*n_subjects
    # STCs_list = [0]*n_subjects
    
    # # Using inverse operator as generator interferes with concurrent processes
    # # If I run it for multiple subjects I run out of ram
    # # Thus concurrent processes are used inside the for loop
    # def PEC_analysis(input_args): # iterable epoch number and corresponding ts
    #     i2, ts = input_args
    #     # Estimate PEC
    #     PEC_con0 = PEC_estimation(ts, Freq_Bands, sfreq)
    #     print("Finished {} out of {} epochs".format(i2+1,n_epochs))
    #     return i2, PEC_con0, ts
    
    # for i in range(n_subjects):
    #     n_epochs, n_ch, n_timepoints = source_epochs[i].get_data().shape
    #     # Use different forward solutions depending on number of channels
    #     cur_subject_id = Subject_id[i]
    #     fwd = fwds[i]
    
    glia's avatar
    glia committed
        
    
    #     # Using assumption about equal variance and no correlations I make a diagonal matrix
    #     # Using the default option for 0.2µV std for EEG data
    #     noise_cov = mne.make_ad_hoc_cov(source_epochs[i].info, None)
    
    glia's avatar
    glia committed
        
    
    #     # Make inverse operator
    #     # Using default depth parameter = 0.8 and free orientation (loose = 1)
    #     inverse_operator = mne.minimum_norm.make_inverse_operator(source_epochs[i].info,
    #                                                               fwd, noise_cov,
    #                                                               loose = 1, depth = 0.8,
    #                                                               verbose = 0)
    #     src_inv = inverse_operator["src"]
    #     # Compute inverse solution and retrieve time series for each label
    #     # Preallocate memory
    #     label_ts = np.full((n_epochs,len(labels),n_timepoints),np.nan)
    #     # Define regularization
    #     snr = 9 # Zhang et al, 2020 used delta = 1/81, which is inverse SNR and correspond to lambda2
    #     # A for loop is used for each label due to memory issues when doing all labels at the same time
    #     for l in range(len(labels)):
    #         stc = mne.minimum_norm.apply_inverse_epochs(source_epochs[i],inverse_operator,
    #                                                     lambda2 = 1/(snr**2),
    #                                                     label = labels[l],
    #                                                     pick_ori = "vector",
    #                                                     return_generator=False,
    #                                                     method = "MNE", verbose = 0)
    #         # Use PCA to reduce the 3 orthogonal directions to 1 principal direction with max power
    #         # There can be ambiguity about the orientation, thus the one that
    #         # is pointing most "normal", i.e. closest 90 degrees to the skull is used
    #         stc_pca = [0]*len(stc)
    #         for ep in range(n_epochs):
    #             stc_pca[ep], pca_dir = stc[ep].project(directions="pca", src=src_inv)
    #         # Get mean time series for the whole label
    #         temp_label_ts = mne.extract_label_time_course(stc_pca, labels[l], src_inv, mode="mean_flip",
    #                                          return_generator=False, verbose=0)
    #         # Save to array
    #         label_ts[:,l,:] = np.squeeze(np.array(temp_label_ts))
    #         print("Finished estimating STC for {} out of {} ROIs".format(l+1,len(labels)))
    
    glia's avatar
    glia committed
        
    
    #     # Free up memory
    #     del stc
    
    #     # Prepare variables
    #     sfreq=source_epochs[i].info["sfreq"]
    #     n_epochs = len(source_epochs[i])
    #     # Estimate the pairwise PEC for each epoch
    #     PEC_con_subject = np.zeros((n_epochs,n_roi,n_roi,n_freq_bands))
    #     stcs0 = np.zeros((n_epochs,n_roi,int(sfreq)*4)) # 4s epochs
    #     # Make list of arguments to pass into PEC_analysis using the helper func
    #     args = []
    #     for i2 in range(n_epochs):
    #         args.append((i2,label_ts[i2]))
    
    glia's avatar
    glia committed
        
    
    #     with concurrent.futures.ProcessPoolExecutor(max_workers=16) as executor:
    #         for i2, PEC_result, stc_result in executor.map(PEC_analysis, args): # Function and arguments
    #             PEC_con_subject[i2] = PEC_result
    #             stcs0[i2] = stc_result
    
    glia's avatar
    glia committed
        
    
    #     # Save to list
    #     PEC_data_list[i] = PEC_con_subject # [subject](epoch,ch,ch,freq)
    #     STCs_list[i] = stcs0 # [subject][epoch,roi,timepoint]
    
    glia's avatar
    glia committed
        
    
    #     # Print progress
    #     print("Finished {} out of {} subjects".format(i+1,n_subjects))
    
    glia's avatar
    glia committed
    
    
    # # Get current time
    # c_time2 = time.localtime()
    # c_time2 = time.strftime("%a %d %b %Y %H:%M:%S", c_time2)
    # print("Started", c_time1, "\nFinished",c_time2)
    
    glia's avatar
    glia committed
    
    
    # with open(Feature_savepath+"PEC_each_epoch_drop_interpol_ch_fix_snr.pkl", "wb") as file:
    #     pickle.dump(PEC_data_list, file)
    # with open(Feature_savepath+"STCs_each_epoch_drop_interpol_ch_fix_snr.pkl", "wb") as file:
    #     pickle.dump(STCs_list, file)
    
    # # # # Load
    # # with open(Feature_savepath+"PEC_each_epoch_drop_interpol_ch_fix_snr.pkl", "rb") as file:
    # #     PEC_data_list = pickle.load(file)
    
    glia's avatar
    glia committed
    
    # # # Load
    
    # # with open(Feature_savepath+"STCs_each_epoch_drop_interpol_ch_fix_snr.pkl", "rb") as file:
    # #     STCs_list = pickle.load(file)
    
    # # Average over eye status
    # eye_status = list(source_epochs[0].event_id.keys())
    # n_eye_status = len(eye_status)
    # pec_data = np.zeros((n_subjects,n_eye_status,n_roi,n_roi,n_freq_bands))
    # for i in range(n_subjects):
    #     # Get indices for eyes open and closed
    #     EC_index = source_epochs[i].events[:,2] == 1
    #     EO_index = source_epochs[i].events[:,2] == 2
    #     # Average over the indices and save to array
    #     pec_data[i,0] = np.mean(PEC_data_list[i][EC_index], axis=0)
    #     pec_data[i,1] = np.mean(PEC_data_list[i][EO_index], axis=0)
    #     # Only use the lower diagonal as the diagonal should be 0 (or very small due to numerical errors)
    #     # And it is symmetric
    #     for f in range(n_freq_bands):
    #         pec_data[i,0,:,:,f] = np.tril(pec_data[i,0,:,:,f],k=-1)
    #         pec_data[i,1,:,:,f] = np.tril(pec_data[i,1,:,:,f],k=-1)
    
    # # Also save as dataframe format for feature selection
    # # Convert to Pandas dataframe
    # # The dimensions will each be a column with numbers and the last column will be the actual values
    # arr = np.column_stack(list(map(np.ravel, np.meshgrid(*map(np.arange, pec_data.shape), indexing="ij"))) + [pec_data.ravel()])
    # pec_data_df = pd.DataFrame(arr, columns = ["Subject_ID", "Eye_status", "chx", "chy", "Freq_band", "Value"])
    # # Change from numerical coding to actual values
    # eye_status = list(source_epochs[0].event_id.keys())
    # freq_bands_name = list(Freq_Bands.keys())
    # label_names = [label.name for label in labels]
    
    # index_values = [Subject_id,eye_status,label_names,label_names,freq_bands_name]
    # for col in range(len(index_values)):
    #     col_name = pec_data_df.columns[col]
    #     for shape in range(pec_data.shape[col]): # notice not dataframe but the array
    #         pec_data_df.loc[pec_data_df.iloc[:,col] == shape,col_name]\
    #         = index_values[col][shape]
    
    # # Add group status