def tqdm(iterable, *args, enabled=None, **kwargs):
if enabled is None:
enabled = set_tqdm_enabled.value
from tqdm import tqdm as tqdm_
if enabled:
return tqdm_(iterable, *args, **kwargs)
return iterable
def tqdm(*args, mininterval=5.0, **kwargs):
return tqdm_(*args, mininterval=mininterval, **kwargs)
def get_contrasts(fmri_img: Union[str, PathLike,
PosixPath, Nifti1Image],
events: Union[str, PathLike,
PosixPath, pd.DataFrame],
desc: str = 'effect_size',
design_kws: Union[dict, Bunch] = None,
glm_kws: Union[dict, Bunch] = None,
masker_kws: Union[dict, Bunch] = None,
standardize: bool = True,
scale: bool = False,
scale_between: tuple = (0, 1),
maximize: bool = False,
masker: [MultiNiftiMasker, NiftiLabelsMasker,
NiftiMapsMasker, NiftiMasker] = None,
feature_labels: Union[Sequence, pd.Index] = None,
session=None,
**kwargs
) -> Bunch:
"""
Return dict-like structure containing experimental contrasts.
Using ``nilearn.glm.first_level.FirstLevel`` object,
contrasts are first computed trial-wise. Then, the same is done
for each experimental condition in ``trial_type_cols`` if a
list of string is provided.
Args:
fmri_img: str, PathLike, PosixPath or Nifti1Image
In-memory or path pointing to a ``nibabel.nifti1.Nifti1Image``.
events: : str, PathLike, PosixPath or DataFrame
In-memory or path pointing to a ``pandas.DataFrame``.
desc: str (Default = 'effect_size')
String passed to
``nilearn.glm.first_level.FirstLevel.compute_contrast``
``desc`` parameter.
design_kws: dict or Bunch (Deault = None)
Dict-like mapping of keyword arguments passed to
``nilearn.glm.first_level.make_first_level_design_matrix``.
If a ``session`` object is passed in the parameters,
the value under the corresponding key is used.
glm_kws: dict or Bunch (Deault = None)
Dict-like mapping of keyword arguments passed to
``nilearn.glm.first_level.FirstLevel.__init__``.
If a ``session`` object is passed in the parameters,
the value under the corresponding key is used.
masker_kws: dict or Bunch (Deault = None)
Dict-like mapping of keyword arguments passed to
``masker.__init__``.
If a ``session`` object is passed in the parameters,
the value under the corresponding key is used.
standardize: bool (Default = True)
If true (by default), the extracted brain signals are
standardized using a ``sklearn.preprocessing.StandardScaler``
object (demeaning ans scaling to variance). It is generally
advised to standardize data for machine-learning operations.
See notes for documentation, tutorials and more.
scale: bool (Default = False)
If true, the extracted brain signals are
scaled (between 0 and 1 by default) using a
``sklearn.preprocessing.MinMaxScaler`` object. It is generally
advised to standardize data for machine-learning operations.
See notes for documentation, tutorials and more.
scale_between: tuple (Default = (0, 1)
Values between which the signal should be scaled.
Default is (0, 1) - left = min, right = max.
Only used if ``scale`` parameter is True.
maximize: bool (Default = False)
If true, scale each feature by its maximum absolute value.
From the docs of ``sklearn.preprocessing.MaxAbsScaler``:
'[...] Scales and translates each feature individually
such that the maximal absolute value of each feature in
training set is 1.0. Does not shift/center the data,
and thus does not destroy any sparsity.'
masker: MultiNiftiMasker, NiftiLabelsMasker,
NiftiMapsMasker or NiftiMasker (Default = None)
Masker object from the ``nilearn.input_data`` module meant
to perform brain signal extraction (conversion from 4D or 3D
image to 2D data).
If omitted, a NiftiMasker with default parameters is used.
feature_labels: List or pd.Index (Default = None)
List of feature names used as columns for the brain signal matrix.
Number of labels and number of features must match.
An error is raised otherwise.
session: dict or Bunch (Default = None)
Dict-like structure containing all required and/or optional
parameters. The functions ``fetch_fmriprep_session`` and
``get_fmri_session`` from ``cimaq_decoding_utils``
return a ``session`` object. It is similar to the return
values of ``nilearn.datasets.fetch{dataset_name}`` functions.
Returns: ``sklearn.utils.Bunch``
Dict-like structure with the following keys:
['model', 'contrast_img', 'signals',
'feature_labels', 'condition_labels']
Notes:
https://scikit-learn.org/stable/modules/preprocessing.html#preprocessing
"""
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import MaxAbsScaler, MinMaxScaler
from sklearn.preprocessing import StandardScaler
from cimaq_decoding_utils import get_frame_times, get_t_r
# Parameter initialization
design_defs, glm_defs = {}, {}
fmri_img = nimage.image.load_img(fmri_img)
events = [events if isinstance(events, pd.DataFrame)
else pd.read_csv(events,
sep=['\t' if splitext(events)[1][1] == 't'
else ','][0])][0]
if session is not None:
design_defs.update(session.design_defs)
glm_defs.update(session.glm_defs)
t_r, frame_times = get_t_r(fmri_img), get_frame_times(fmri_img)
if design_kws is not None:
design_defs.update(design_kws)
if glm_kws is not None:
glm_defs.update(glm_kws)
# GLM initialization and contrast computation
design = make_first_level_design_matrix(frame_times, events=events.iloc[1:, :],
**design_defs)
model = FirstLevelModel(**glm_defs).fit(run_imgs=fmri_img,
design_matrices=design.iloc[:, 1:])
contrasts = nimage.concat_imgs([model.compute_contrast(
trial, desc=desc) for trial in
tqdm_(design.columns[:-1].astype(str),
ncols=100,
desc='Computing Contrasts')])
# Brain signals extraction
pipe_components = ((standardize, 'standardize', StandardScaler()),
(maximize, 'maximize', MaxAbsScaler()),
(scale, 'scale', MinMaxScaler(scale_between)))
pipe_components = [item[1:] for item in
list(filter(lambda x: x[0], pipe_components))]
signals = masker.transform_single_imgs(contrasts)
if pipe_components != []:
pipeline = Pipeline(pipe_components)
signals = pipeline.fit_transform(signals)
signals = pd.DataFrame(signals,
index=design.iloc[:, :-1].columns)
if feature_labels is not None:
signals.set_axis(feature_labels, axis=1, inplace=True)
return Bunch(model=model, contrast_img=contrasts,
signals=signals, feature_labels=feature_labels)
def parse(self, process=None, batch=200, remove_after=False):
"""
Write a serie of compressed dict files to disk. Structure :
for each page :
- page_len : the xml lenght of the page
- content : all the words, lower case, no ponct
- ns : namespace
- redirect : if the page redirect, where to
- meta : the metadata of pages (infobox...)
"""
with open(self.work_directory+BLOCKLIST_PATH) as f:
blocklist = json.load(f)
global worker
def worker(t):
pages, blocklist = t
parser = PageParser()
pages = pages.split('<page>')
dic = {}
redirect = {}
n_skip = 0
for page in pages:
try:
title = rx_title.search(page)[0]
if not self.__is_ok(title, blocklist):
n_skip += 1
continue
except TypeError:
if len(page) != 2: # real parsing errors
print(page)
continue
if '<redirect' not in page:
# xml parse
namespace = int(rx_nm.search(page)[0])
text = page.split('<text', 1)[1].split('>', 1)[1].split('</text>')[0]
# wikicode parse
data = parser.parse(text)
data['ns'] = namespace
dic[title] = data
dic[title]['page_len'] = len(page)
else:
to_page = page.split('<redirect title="', 1)[1].split('" />', 1)[0]
redirect[title] = {'redirect': to_page}
redirect[title]['page_len'] = len(page)
return dic, redirect, n_skip
print('[DumpParser] Start parsing...')
g = self.generate_chunks()
with mp.Pool(process) as p:
bar = tqdm_(total=self.total)
buff = {}
redirect = {}
params = ((i, blocklist) for i in g)
i = 0
n_buf, n_red = 0, 0
for rep, red, n_skip in p.imap_unordered(worker, params):
bar.update(len(rep)+len(red)+n_skip)
buff.update(rep)
redirect.update(red)
if i%(batch//2) == 0:
size = dict_size(buff)/1024**2
if size > batch:
filename = 'pages_{}'.format(n_buf)
self.__write_to_disk(buff, filename)
buff.clear()
n_buf += 1
if i%(batch*2) == 0:
size = dict_size(redirect)/1024**2
if size > batch:
filename = 'redirect_{}'.format(n_red)
self.__write_to_disk(redirect, filename)
redirect.clear()
n_red += 1
i += 1
filename = 'pages_{}'.format(n_buf)
self.__write_to_disk(buff, filename)
filename = 'redirect_{}'.format(n_red)
self.__write_to_disk(redirect, filename)
if remove_after:
os.remove(self.path_data)
os.remove(self.path_index)
print('[DumpParser] Files removed')
self.thread.join()
print('[DumpParser] Parsing to dictionnary finished!')
