def get_colorinfo(r_name, clusters):
Nsig = ((clusters.loc[r_name].end_t - clusters.loc[r_name].start_t) / 10 +
1).sum()
# if sufficiently many significant effects
if Nsig >= 12:
# set non-significant effects to NaN
src_df_masked = ss.load_src_df(basefile, r_name, clusters,
use_basefile)
else:
# there are not sufficiently many significant effects after FDR,
# so don't mask
src_df_masked = ss.load_src_df(basefile, r_name, None, use_basefile)
if show_measure not in src_df_masked.columns:
ss.add_measure(src_df_masked, show_measure)
if Nsig >= 12:
# make colormap based on distribution of significant effects
colorinfo = {
'fmin': src_df_masked[show_measure].abs().min(),
'fmid': src_df_masked[show_measure].abs().median(),
'fmax': src_df_masked[show_measure].abs().max(),
'transparent': True,
'colormap': 'auto'
}
else:
# make colormap based on distribution of all effects
colorinfo = {
'fmin': src_df_masked[show_measure].abs().quantile(0.95),
'fmid': src_df_masked[show_measure].abs().quantile(0.99),
'fmax': src_df_masked[show_measure].abs().quantile(0.999),
'transparent': True,
'colormap': 'auto'
}
return colorinfo
elif r_name == 'accev':
x_times = [20, 150, 230, 300]
# colorinfo['fmin'] = 0
colorinfo['center'] = 0
elif r_name == 'dot_y':
x_times = [120, 180, 330, 410]
elif r_name == 'response':
if response_aligned:
x_times = [-30, 0, 30, 50]
else:
x_times = [780, 820, 890]
# load the selected regressors and mask as desired
src_df_masked = pd.concat(
[ss.load_src_df(basefile, reg, mask, use_basefile) for reg in regressors],
keys=regressors,
names=['regressor', 'label', 'time'])
times = src_df_masked.index.levels[2]
if show_measure not in src_df_masked.columns:
ss.add_measure(src_df_masked, show_measure)
if basefile.startswith('source_sequential'):
# flip sign of all non-nan values in accev for which there is a nan value
# in dot_x 100 ms later - these are the effects that are only present in
# accumulated evidence, but not in dot_x
fliptimes = times[times <= times[-1] - 100]
accevvals = src_df_masked.loc[('accev', slice(None), fliptimes),
show_measure]
clusters = ss.get_fdrcorr_clusters(basefile,
regressors,
measure,
threshold,
measure_cdf,
fdr_alpha=0.001,
use_basefile=True,
perm=perm)
print('cluster counts:')
print(clusters.label.groupby(level='regressor').count())
#%% load specific regressor
r_name = 'response'
show_measure = 'mlog10p'
src_df_masked = ss.load_src_df(basefile, r_name, clusters, use_basefile=True)
brain = Brain('fsaverage',
'both',
'inflated',
cortex='low_contrast',
subjects_dir=sv.subjects_dir,
background='w',
foreground='k')
labels = sv.show_labels_as_data(src_df_masked,
show_measure,
brain,
transparent=True)
brain.scale_data_colormap(src_df_masked[show_measure].min(),
#threshold = 0.5
#%% identify significant clusters
clusters = ss.get_fdrcorr_clusters(basefile,
regressors,
measure,
threshold,
measure_cdf,
fdr_alpha=0.001)
#%% load specific regressor
r_name = 'dot_x'
show_measure = 'mu_mean'
src_df_masked = ss.load_src_df(basefile, r_name, clusters)
brain = Brain('fsaverage',
'both',
'inflated',
cortex='low_contrast',
subjects_dir=sv.subjects_dir,
background='w',
foreground='k')
labels = sv.show_labels_as_data(src_df_masked,
show_measure,
brain,
transparent=True)
#brain.scale_data_colormap(src_df_masked[show_measure].min(),
figdir = os.path.expanduser('~/ZIH/texts/BeeMEG/figures')
#%% load data
r_names = ['dot_x', 'dot_y']
measure = 'tval'
make_figures = True
# vertices of pre-motor and motor areas, baseline (-0.3, 0), first 5 dots,
# trialregs_dot=0, source GLM, sum_dot_y, constregs=0 for 1st dot,
# subject-specific normalisation of DM without centering and scaling by std
# label_tc normalised across trials, times and subjects
basefile = 'source_sequential_201711271306.h5'
src_df = pd.concat([
ss.load_src_df(basefile, r_name, use_basefile=True) for r_name in r_names
],
keys=r_names,
names=['regressor', 'label', 'time'])
# this performs FDR-correction across all regressors, vertices and times
ss.add_measure(src_df, 'p_fdr')
#%% prepare plotting
def get_colorinfo(measure, src_df, fdr_alpha=0.01):
# find measure value that is the first one with p-value equal or smaller
# than fdr_alpha
pdiff = src_df.p_fdr - fdr_alpha
try:
fmid = src_df[pdiff <= 0].sort_values('p_fdr')[measure].abs().iloc[-1]
'second_level')[measure][regressors]
second_level = second_level_perms.loc[0]
P = second_level_perms.index.get_level_values('permnr').unique().size
times = second_level.index.get_level_values('time').unique()
labels = second_level.index.get_level_values('label').unique()
#%% find brain areas with significant effects in selected time windows
clusters = ss.get_fdrcorr_clusters(basefile,
regressors,
fdr_alpha,
use_basefile=True)
srcdf_masked = pd.concat([
ss.load_src_df(basefile, reg, clusters, use_basefile=True)
for reg in regressors
],
keys=regressors,
names=['regressor', 'label', 'time'])
srcdf_masked.dropna(inplace=True)
is_significant = pd.DataFrame(
np.zeros((len(regressors) * len(labels), len(wnames)), dtype=bool),
index=pd.MultiIndex.from_product([regressors, labels],
names=['regressor', 'label']),
columns=wnames)
for name in wnames:
for win in twin[name]:
for reg in regressors:
#basefile = 'source_sequential_201807031144.h5'
# loose source orientations, but cortex normal currents
# label mode = mean_flip, baseline (-0.3, 0), all dots with toolate=-200,
# time window [0, 690], exclude time-outs, local normalisation of DM
# trialregs_dot=0, accev, sum_dot_y_prev, percupt, constregs=0 for 1st dot,
# label_tc normalised across trials but within times and subjects
basefile = 'source_sequential_201807041930.h5'
regressors = ['dot_x', 'dot_y', 'accev']
measure = 'mean'
if measure in ['mu_mean', 'mu_p_large']:
second_level = pd.concat(
[ss.load_src_df(basefile, reg) for reg in regressors],
axis=1,
keys=regressors,
names=['regressor', 'measure'])
second_level = second_level.swaplevel(axis=1).sort_index(axis=1)
else:
second_level_perms = pd.read_hdf(
os.path.join(helpers.resultsdir, basefile), 'second_level')
second_level = second_level_perms.loc[0]
P = second_level_perms.index.get_level_values('permnr').unique().size
first_level = pd.read_hdf(os.path.join(helpers.resultsdir, basefile),
'first_level')
# label_tc normalised across trials, times and subjects
basefile = 'source_sequential_201710231824.h5'
elif datatype == 'eog':
# eog event regression
basefile = 'eog_source_201802091232.h5'
elif datatype == 'evoked':
# evoked sources 300 to 500 ms after response
# basefile = 'evoked_source_201802091710.h5'
# evoked sources -1000 to 1000 after response
basefile = 'evoked_source_201802271701.h5'
if len(datatype) > 0 and not datatype.startswith('_'):
datatype = '_' + datatype
src_df = ss.load_src_df(basefile, r_name, use_basefile=True)
ss.add_measure(src_df, 'p_fdr')
if measure not in src_df.columns:
ss.add_measure(src_df, measure)
if make_figures == 'max':
make_figures = [src_df[measure].abs().groupby('time').max().idxmax()]
elif make_figures == 'mean':
make_figures = [src_df[measure].abs().groupby('time').mean().idxmax()]
#flips = sv.get_label_sign_flips(
# src_df.index.get_level_values('label').map(lambda s: s[:-7]).unique(),
# combine=True)
#for time in src_df.index.get_level_values('time').unique():
# src_df.loc[(slice(None), time), 'tval'] = (
# src_df.xs(time, level='time').tval * flips).values
use_basefile=True)
#%% save all significant r_name clusters to csv-file
def to_csv(areas, fname):
areas['label'] = areas['label'].map(lambda x: x[:-7])
areas.to_csv(fname)
to_csv(
clusters.loc[r_name].copy().sort_values('start_t')[[
'label', 'region', 'start_t', 'end_t', 'log10p'
]], os.path.join(figdir, 'significant_clusters_{}.csv'.format(r_name)))
#%%
src_df = ss.load_src_df(basefile, r_name, None, use_basefile)
if show_measure not in src_df.columns:
ss.add_measure(src_df, show_measure)
labels = src_df.index.levels[0]
def get_average_effects(twin, wname, top=5):
winclusters = clusters.loc[r_name]
winclusters = winclusters[((winclusters.start_t >= twin[0])
& (winclusters.start_t <= twin[1]))
| ((winclusters.end_t >= twin[0])
& (winclusters.end_t <= twin[1]))]
areas = winclusters.label.unique()