def split_ts(data, mmix, mask, acc):
"""
Splits `data` time series into accepted component time series and remainder
Parameters
----------
data : (S x T) array_like
Input data, where `S` is samples and `T` is time
mmix : (T x C) array_like
Mixing matrix for converting input data to component space, where `C`
is components and `T` is the same as in `data`
mask : (S,) array_like
Boolean mask array
acc : :obj:`list`
List of accepted components used to subset `mmix`
Returns
-------
hikts : (S x T) :obj:`numpy.ndarray`
Time series reconstructed using only components in `acc`
rest : (S x T) :obj:`numpy.ndarray`
Original data with `hikts` removed
"""
cbetas = model.get_coeffs(data - data.mean(axis=-1, keepdims=True),
mmix, mask)
betas = cbetas[mask]
if len(acc) != 0:
hikts = utils.unmask(betas[:, acc].dot(mmix.T[acc, :]), mask)
else:
hikts = None
resid = data - hikts
return hikts, resid
def split_ts(data, mmix, mask, acc):
"""
Splits `data` time series into accepted component time series and remainder
Parameters
----------
data : (S x T) array_like
Input data, where `S` is samples and `T` is time
mmix : (T x C) array_like
Mixing matrix for converting input data to component space, where `C`
is components and `T` is the same as in `data`
mask : (S,) array_like
Boolean mask array
acc : list
List of accepted components used to subset `mmix`
Returns
-------
hikts : (S x T) :obj:`numpy.ndarray`
Time series reconstructed using only components in `acc`
rest : (S x T) :obj:`numpy.ndarray`
Original data with `hikts` removed
"""
cbetas = model.get_coeffs(data - data.mean(axis=-1, keepdims=True), mask, mmix)
betas = cbetas[mask]
if len(acc) != 0:
hikts = utils.unmask(betas[:, acc].dot(mmix.T[acc, :]), mask)
else:
hikts = None
return hikts, data - hikts
def write_split_ts(data, mmix, mask, acc, rej, midk, ref_img, suffix=''):
"""
Splits `data` into denoised / noise / ignored time series and saves to disk
Parameters
----------
data : (S x T) array_like
Input time series
mmix : (C x T) array_like
Mixing matrix for converting input data to component space, where `C`
is components and `T` is the same as in `data`
mask : (S,) array_like
Boolean mask array
acc : list
Indices of accepted (BOLD) components in `mmix`
rej : list
Indices of rejected (non-BOLD) components in `mmix`
midk : list
Indices of mid-K (questionable) components in `mmix`
ref_img : str or img_like
Reference image to dictate how outputs are saved to disk
suffix : str, optional
Appended to name of saved files (before extension). Default: ''
Returns
-------
varexpl : float
Percent variance of data explained by extracted + retained components
"""
# mask and de-mean data
mdata = data[mask]
dmdata = mdata.T - mdata.T.mean(axis=0)
# get variance explained by retained components
betas = model.get_coeffs(utils.unmask(dmdata.T, mask), mask, mmix)[mask]
varexpl = (1 - ((dmdata.T - betas.dot(mmix.T))**2.).sum() / (dmdata**2.).sum()) * 100
LGR.info('Variance explained by ICA decomposition: {:.02f}%'.format(varexpl))
# create component and de-noised time series and save to files
hikts = betas[:, acc].dot(mmix.T[acc, :])
midkts = betas[:, midk].dot(mmix.T[midk, :])
lowkts = betas[:, rej].dot(mmix.T[rej, :])
dnts = data[mask] - lowkts - midkts
if len(acc) != 0:
fout = utils.filewrite(utils.unmask(hikts, mask), 'hik_ts_{0}'.format(suffix), ref_img)
LGR.info('Writing high-Kappa time series: {}'.format(op.abspath(fout)))
if len(midk) != 0:
fout = utils.filewrite(utils.unmask(midkts, mask), 'midk_ts_{0}'.format(suffix), ref_img)
LGR.info('Writing mid-Kappa time series: {}'.format(op.abspath(fout)))
if len(rej) != 0:
fout = utils.filewrite(utils.unmask(lowkts, mask), 'lowk_ts_{0}'.format(suffix), ref_img)
LGR.info('Writing low-Kappa time series: {}'.format(op.abspath(fout)))
fout = utils.filewrite(utils.unmask(dnts, mask), 'dn_ts_{0}'.format(suffix), ref_img)
LGR.info('Writing denoised time series: {}'.format(op.abspath(fout)))
return varexpl
def writeresults(ts, mask, comptable, mmix, n_vols, acc, rej, midk, empty, ref_img):
"""
Denoises `ts` and saves all resulting files to disk
Parameters
----------
ts : (S x T) array_like
Time series to denoise and save to disk
mask : (S,) array_like
Boolean mask array
comptable : (N x 5) array_like
Array with columns denoting (1) index of component, (2) Kappa score of
component, (3) Rho score of component, (4) variance explained by
component, and (5) normalized variance explained by component
mmix : (C x T) array_like
Mixing matrix for converting input data to component space, where `C`
is components and `T` is the same as in `data`
acc : list
Indices of accepted (BOLD) components in `mmix`
rej : list
Indices of rejected (non-BOLD) components in `mmix`
midk : list
Indices of mid-K (questionable) components in `mmix`
empty : list
Indices of ignored components in `mmix`
ref_img : str or img_like
Reference image to dictate how outputs are saved to disk
"""
fout = utils.filewrite(ts, 'ts_OC', ref_img)
LGR.info('Writing optimally-combined time series: {}'.format(op.abspath(fout)))
varexpl = write_split_ts(ts, mmix, mask, acc, rej, midk, ref_img, suffix='OC')
ts_B = model.get_coeffs(ts, mask, mmix)
fout = utils.filewrite(ts_B, 'betas_OC', ref_img)
LGR.info('Writing full ICA coefficient feature set: {}'.format(op.abspath(fout)))
if len(acc) != 0:
fout = utils.filewrite(ts_B[:, acc], 'betas_hik_OC', ref_img)
LGR.info('Writing denoised ICA coefficient feature set: {}'.format(op.abspath(fout)))
fout = writefeats(split_ts(ts, mmix, mask, acc)[0],
mmix[:, acc], mask, ref_img, suffix='OC2')
LGR.info('Writing Z-normalized spatial component maps: {}'.format(op.abspath(fout)))
writect(comptable, n_vols, acc, rej, midk, empty, ctname='comp_table.txt',
varexpl=varexpl)
LGR.info('Writing component table: {}'.format(op.abspath('comp_table.txt')))
def split_ts(data, mmix, mask, comptable):
"""
Splits `data` time series into accepted component time series and remainder
Parameters
----------
data : (S x T) array_like
Input data, where `S` is samples and `T` is time
mmix : (T x C) array_like
Mixing matrix for converting input data to component space, where `C`
is components and `T` is the same as in `data`
mask : (S,) array_like
Boolean mask array
comptable : (C x X) :obj:`pandas.DataFrame`
Component metric table. One row for each component, with a column for
each metric. Requires at least two columns: "component" and
"classification".
Returns
-------
hikts : (S x T) :obj:`numpy.ndarray`
Time series reconstructed using only components in `acc`
rest : (S x T) :obj:`numpy.ndarray`
Original data with `hikts` removed
"""
acc = comptable[comptable.classification == 'accepted'].index.values
cbetas = model.get_coeffs(data - data.mean(axis=-1, keepdims=True),
mmix, mask)
betas = cbetas[mask]
if len(acc) != 0:
hikts = utils.unmask(betas[:, acc].dot(mmix.T[acc, :]), mask)
else:
hikts = None
resid = data - hikts
return hikts, resid
def writeresults(ts, mask, comptable, mmix, n_vols, fixed_seed,
acc, rej, midk, empty, ref_img):
"""
Denoises `ts` and saves all resulting files to disk
Parameters
----------
ts : (S x T) array_like
Time series to denoise and save to disk
mask : (S,) array_like
Boolean mask array
comptable : (N x 5) array_like
Array with columns denoting (1) index of component, (2) Kappa score of
component, (3) Rho score of component, (4) variance explained by
component, and (5) normalized variance explained by component
mmix : (C x T) array_like
Mixing matrix for converting input data to component space, where `C`
is components and `T` is the same as in `data`
n_vols : :obj:`int`
Number of volumes in original time series
fixed_seed: :obj:`int`
Integer value used in seeding ICA
acc : :obj:`list`
Indices of accepted (BOLD) components in `mmix`
rej : :obj:`list`
Indices of rejected (non-BOLD) components in `mmix`
midk : :obj:`list`
Indices of mid-K (questionable) components in `mmix`
empty : :obj:`list`
Indices of ignored components in `mmix`
ref_img : :obj:`str` or img_like
Reference image to dictate how outputs are saved to disk
Notes
-----
This function writes out several files:
====================== =================================================
Filename Content
====================== =================================================
ts_OC.nii Optimally combined 4D time series.
hik_ts_OC.nii High-Kappa time series. Generated by
:py:func:`tedana.utils.io.write_split_ts`.
midk_ts_OC.nii Mid-Kappa time series. Generated by
:py:func:`tedana.utils.io.write_split_ts`.
low_ts_OC.nii Low-Kappa time series. Generated by
:py:func:`tedana.utils.io.write_split_ts`.
dn_ts_OC.nii Denoised time series. Generated by
:py:func:`tedana.utils.io.write_split_ts`.
betas_OC.nii Full ICA coefficient feature set.
betas_hik_OC.nii Denoised ICA coefficient feature set.
feats_OC2.nii Z-normalized spatial component maps. Generated
by :py:func:`tedana.utils.io.writefeats`.
comp_table.txt Component table. Generated by
:py:func:`tedana.utils.io.writect`.
====================== =================================================
"""
fout = filewrite(ts, 'ts_OC', ref_img)
LGR.info('Writing optimally-combined time series: {}'.format(op.abspath(fout)))
write_split_ts(ts, mmix, mask, acc, rej, midk, ref_img, suffix='OC')
ts_B = model.get_coeffs(ts, mmix, mask)
fout = filewrite(ts_B, 'betas_OC', ref_img)
LGR.info('Writing full ICA coefficient feature set: {}'.format(op.abspath(fout)))
if len(acc) != 0:
fout = filewrite(ts_B[:, acc], 'betas_hik_OC', ref_img)
LGR.info('Writing denoised ICA coefficient feature set: {}'.format(op.abspath(fout)))
fout = writefeats(split_ts(ts, mmix, mask, acc)[0],
mmix[:, acc], mask, ref_img, suffix='OC2')
LGR.info('Writing Z-normalized spatial component maps: {}'.format(op.abspath(fout)))
def write_split_ts(data, mmix, mask, acc, rej, midk, ref_img, suffix=''):
"""
Splits `data` into denoised / noise / ignored time series and saves to disk
Parameters
----------
data : (S x T) array_like
Input time series
mmix : (C x T) array_like
Mixing matrix for converting input data to component space, where `C`
is components and `T` is the same as in `data`
mask : (S,) array_like
Boolean mask array
acc : :obj:`list`
Indices of accepted (BOLD) components in `mmix`
rej : :obj:`list`
Indices of rejected (non-BOLD) components in `mmix`
midk : :obj:`list`
Indices of mid-K (questionable) components in `mmix`
ref_img : :obj:`str` or img_like
Reference image to dictate how outputs are saved to disk
suffix : :obj:`str`, optional
Appended to name of saved files (before extension). Default: ''
Returns
-------
varexpl : :obj:`float`
Percent variance of data explained by extracted + retained components
Notes
-----
This function writes out several files:
====================== =================================================
Filename Content
====================== =================================================
hik_ts_[suffix].nii High-Kappa time series.
midk_ts_[suffix].nii Mid-Kappa time series.
low_ts_[suffix].nii Low-Kappa time series.
dn_ts_[suffix].nii Denoised time series.
====================== =================================================
"""
# mask and de-mean data
mdata = data[mask]
dmdata = mdata.T - mdata.T.mean(axis=0)
# get variance explained by retained components
betas = model.get_coeffs(dmdata.T, mmix, mask=None)
varexpl = (1 - ((dmdata.T - betas.dot(mmix.T))**2.).sum() /
(dmdata**2.).sum()) * 100
LGR.info('Variance explained by ICA decomposition: '
'{:.02f}%'.format(varexpl))
# create component and de-noised time series and save to files
hikts = betas[:, acc].dot(mmix.T[acc, :])
midkts = betas[:, midk].dot(mmix.T[midk, :])
lowkts = betas[:, rej].dot(mmix.T[rej, :])
dnts = data[mask] - lowkts - midkts
if len(acc) != 0:
fout = filewrite(utils.unmask(hikts, mask),
'hik_ts_{0}'.format(suffix), ref_img)
LGR.info('Writing high-Kappa time series: {}'.format(op.abspath(fout)))
if len(midk) != 0:
fout = filewrite(utils.unmask(midkts, mask),
'midk_ts_{0}'.format(suffix), ref_img)
LGR.info('Writing mid-Kappa time series: {}'.format(op.abspath(fout)))
if len(rej) != 0:
fout = filewrite(utils.unmask(lowkts, mask),
'lowk_ts_{0}'.format(suffix), ref_img)
LGR.info('Writing low-Kappa time series: {}'.format(op.abspath(fout)))
fout = filewrite(utils.unmask(dnts, mask),
'dn_ts_{0}'.format(suffix), ref_img)
LGR.info('Writing denoised time series: {}'.format(op.abspath(fout)))
return varexpl
def writeresults(ts, mask, comptable, mmix, n_vols, acc, rej, midk, empty,
ref_img):
"""
Denoises `ts` and saves all resulting files to disk
Parameters
----------
ts : (S x T) array_like
Time series to denoise and save to disk
mask : (S,) array_like
Boolean mask array
comptable : (N x 5) array_like
Array with columns denoting (1) index of component, (2) Kappa score of
component, (3) Rho score of component, (4) variance explained by
component, and (5) normalized variance explained by component
mmix : (C x T) array_like
Mixing matrix for converting input data to component space, where `C`
is components and `T` is the same as in `data`
acc : list
Indices of accepted (BOLD) components in `mmix`
rej : list
Indices of rejected (non-BOLD) components in `mmix`
midk : list
Indices of mid-K (questionable) components in `mmix`
empty : list
Indices of ignored components in `mmix`
ref_img : str or img_like
Reference image to dictate how outputs are saved to disk
"""
fout = utils.filewrite(ts, 'ts_OC', ref_img)
LGR.info('Writing optimally-combined time series: {}'.format(
op.abspath(fout)))
varexpl = write_split_ts(ts,
mmix,
mask,
acc,
rej,
midk,
ref_img,
suffix='OC')
ts_B = model.get_coeffs(ts, mask, mmix)
fout = utils.filewrite(ts_B, 'betas_OC', ref_img)
LGR.info('Writing full ICA coefficient feature set: {}'.format(
op.abspath(fout)))
if len(acc) != 0:
fout = utils.filewrite(ts_B[:, acc], 'betas_hik_OC', ref_img)
LGR.info('Writing denoised ICA coefficient feature set: {}'.format(
op.abspath(fout)))
fout = writefeats(split_ts(ts, mmix, mask, acc)[0],
mmix[:, acc],
mask,
ref_img,
suffix='OC2')
LGR.info('Writing Z-normalized spatial component maps: {}'.format(
op.abspath(fout)))
writect(comptable,
n_vols,
acc,
rej,
midk,
empty,
ctname='comp_table.txt',
varexpl=varexpl)
LGR.info('Writing component table: {}'.format(
op.abspath('comp_table.txt')))
def write_comp_figs(ts, mask, comptable, mmix, ref_img, out_dir, png_cmap):
"""
Creates static figures that highlight certain aspects of tedana processing
This includes a figure for each component showing the component time course,
the spatial weight map and a fast Fourier transform of the time course
Parameters
----------
ts : (S x T) array_like
Time series from which to derive ICA betas
mask : (S,) array_like
Boolean mask array
comptable : (C x X) :obj:`pandas.DataFrame`
Component metric table. One row for each component, with a column for
each metric. The index should be the component number.
mmix : (C x T) array_like
Mixing matrix for converting input data to component space, where `C`
is components and `T` is the same as in `data`
ref_img : :obj:`str` or img_like
Reference image to dictate how outputs are saved to disk
out_dir : :obj:`str`
Figures folder within output directory
png_cmap : :obj:`str`
The name of a matplotlib colormap to use when making figures. Optional.
Default colormap is 'coolwarm'
"""
# Get the lenght of the timeseries
n_vols = len(mmix)
# Check that colormap provided exists
if png_cmap not in plt.colormaps():
LGR.warning(
'Provided colormap is not recognized, proceeding with default')
png_cmap = 'coolwarm'
# regenerate the beta images
ts_B = model.get_coeffs(ts, mmix, mask)
ts_B = ts_B.reshape(ref_img.shape[:3] + ts_B.shape[1:])
# trim edges from ts_B array
ts_B = trim_edge_zeros(ts_B)
# Mask out remaining zeros
ts_B = np.ma.masked_where(ts_B == 0, ts_B)
# Get repetition time from ref_img
tr = ref_img.header.get_zooms()[-1]
# Create indices for 6 cuts, based on dimensions
cuts = [ts_B.shape[dim] // 6 for dim in range(3)]
expl_text = ''
# Remove trailing ';' from rationale column
comptable['rationale'] = comptable['rationale'].str.rstrip(';')
for compnum in comptable.index.values:
if comptable.loc[compnum, "classification"] == 'accepted':
line_color = 'g'
expl_text = 'accepted'
elif comptable.loc[compnum, "classification"] == 'rejected':
line_color = 'r'
expl_text = 'rejection reason(s): ' + comptable.loc[compnum,
"rationale"]
elif comptable.loc[compnum, "classification"] == 'ignored':
line_color = 'k'
expl_text = 'ignored reason(s): ' + comptable.loc[compnum,
"rationale"]
else:
# Classification not added
# If new, this will keep code running
line_color = '0.75'
expl_text = 'other classification'
allplot = plt.figure(figsize=(10, 9))
ax_ts = plt.subplot2grid((5, 6), (0, 0),
rowspan=1,
colspan=6,
fig=allplot)
ax_ts.set_xlabel('TRs')
ax_ts.set_xlim(0, n_vols)
plt.yticks([])
# Make a second axis with units of time (s)
max_xticks = 10
xloc = plt.MaxNLocator(max_xticks)
ax_ts.xaxis.set_major_locator(xloc)
ax_ts2 = ax_ts.twiny()
ax1Xs = ax_ts.get_xticks()
ax2Xs = []
for X in ax1Xs:
# Limit to 2 decimal places
seconds_val = round(X * tr, 2)
ax2Xs.append(seconds_val)
ax_ts2.set_xticks(ax1Xs)
ax_ts2.set_xlim(ax_ts.get_xbound())
ax_ts2.set_xticklabels(ax2Xs)
ax_ts2.set_xlabel('seconds')
ax_ts.plot(mmix[:, compnum], color=line_color)
# Title will include variance from comptable
comp_var = "{0:.2f}".format(comptable.loc[compnum,
"variance explained"])
comp_kappa = "{0:.2f}".format(comptable.loc[compnum, "kappa"])
comp_rho = "{0:.2f}".format(comptable.loc[compnum, "rho"])
plt_title = ('Comp. {}: variance: {}%, kappa: {}, rho: {}, '
'{}'.format(compnum, comp_var, comp_kappa, comp_rho,
expl_text))
title = ax_ts.set_title(plt_title)
title.set_y(1.5)
# Set range to ~1/10th of max positive or negative beta
imgmax = 0.1 * np.abs(ts_B[:, :, :, compnum]).max()
imgmin = imgmax * -1
for idx, cut in enumerate(cuts):
for imgslice in range(1, 6):
ax = plt.subplot2grid((5, 6), (idx + 1, imgslice - 1),
rowspan=1,
colspan=1)
ax.axis('off')
if idx == 0:
to_plot = np.rot90(ts_B[imgslice * cuts[idx], :, :,
compnum])
if idx == 1:
to_plot = np.rot90(ts_B[:, imgslice * cuts[idx], :,
compnum])
if idx == 2:
to_plot = ts_B[:, :, imgslice * cuts[idx], compnum]
ax_im = ax.imshow(to_plot,
vmin=imgmin,
vmax=imgmax,
aspect='equal',
cmap=png_cmap)
# Add a color bar to the plot.
ax_cbar = allplot.add_axes([0.8, 0.3, 0.03, 0.37])
cbar = allplot.colorbar(ax_im, ax_cbar)
cbar.set_label('Component Beta', rotation=90)
cbar.ax.yaxis.set_label_position('left')
# Get fft and freqs for this subject
# adapted from @dangom
spectrum, freqs = get_spectrum(mmix[:, compnum], tr)
# Plot it
ax_fft = plt.subplot2grid((5, 6), (4, 0), rowspan=1, colspan=6)
ax_fft.plot(freqs, spectrum)
ax_fft.set_title('One Sided fft')
ax_fft.set_xlabel('Hz')
ax_fft.set_xlim(freqs[0], freqs[-1])
plt.yticks([])
# Fix spacing so TR label does overlap with other plots
allplot.subplots_adjust(hspace=0.4)
plot_name = 'comp_{}.png'.format(str(compnum).zfill(3))
compplot_name = os.path.join(out_dir, plot_name)
plt.savefig(compplot_name)
plt.close()
def writeresults(ts, mask, comptable, mmix, n_vols, ref_img):
"""
Denoises `ts` and saves all resulting files to disk
Parameters
----------
ts : (S x T) array_like
Time series to denoise and save to disk
mask : (S,) array_like
Boolean mask array
comptable : (C x X) :obj:`pandas.DataFrame`
Component metric table. One row for each component, with a column for
each metric. Requires at least two columns: "component" and
"classification".
mmix : (C x T) array_like
Mixing matrix for converting input data to component space, where `C`
is components and `T` is the same as in `data`
n_vols : :obj:`int`
Number of volumes in original time series
ref_img : :obj:`str` or img_like
Reference image to dictate how outputs are saved to disk
Notes
-----
This function writes out several files:
====================== =================================================
Filename Content
====================== =================================================
ts_OC.nii Optimally combined 4D time series.
hik_ts_OC.nii High-Kappa time series. Generated by
:py:func:`tedana.utils.io.write_split_ts`.
midk_ts_OC.nii Mid-Kappa time series. Generated by
:py:func:`tedana.utils.io.write_split_ts`.
low_ts_OC.nii Low-Kappa time series. Generated by
:py:func:`tedana.utils.io.write_split_ts`.
dn_ts_OC.nii Denoised time series. Generated by
:py:func:`tedana.utils.io.write_split_ts`.
betas_OC.nii Full ICA coefficient feature set.
betas_hik_OC.nii Denoised ICA coefficient feature set.
feats_OC2.nii Z-normalized spatial component maps. Generated
by :py:func:`tedana.utils.io.writefeats`.
comp_table.txt Component table. Generated by
:py:func:`tedana.utils.io.writect`.
====================== =================================================
"""
acc = comptable[comptable.classification == 'accepted'].index.values
fout = filewrite(ts, 'ts_OC', ref_img)
LGR.info('Writing optimally-combined time series: {}'.format(op.abspath(fout)))
write_split_ts(ts, mmix, mask, comptable, ref_img, suffix='OC')
ts_B = model.get_coeffs(ts, mmix, mask)
fout = filewrite(ts_B, 'betas_OC', ref_img)
LGR.info('Writing full ICA coefficient feature set: {}'.format(op.abspath(fout)))
if len(acc) != 0:
fout = filewrite(ts_B[:, acc], 'betas_hik_OC', ref_img)
LGR.info('Writing denoised ICA coefficient feature set: {}'.format(op.abspath(fout)))
fout = writefeats(split_ts(ts, mmix, mask, comptable)[0],
mmix[:, acc], mask, ref_img, suffix='OC2')
LGR.info('Writing Z-normalized spatial component maps: {}'.format(op.abspath(fout)))