##################################################
# Review
from pyitab.preprocessing.pipelines import PreprocessingPipeline
from pyitab.analysis.iterator import AnalysisIterator
from pyitab.analysis.configurator import AnalysisConfigurator
loader = DataLoader(
configuration_file="/home/carlos/fmri/carlo_ofp/ofp_new.conf",
task='OFP_NORES')
prepro = PreprocessingPipeline(nodes=[
#Transformer(),
Detrender(),
Detrender(chunks_attr='file'),
SampleZNormalizer(),
FeatureZNormalizer(),
])
ds = loader.fetch(prepro=prepro)
_default_options = {
'kwargs__roi': [['within_conjunction']],
#'sample_slicer__subject': [[s] for s in],
'sample_slicer__evidence': [[1], [2], [3]],
}
_default_config = {
'prepro': ['target_transformer', 'sample_slicer', 'balancer'],
'target_transformer__attr': 'decision',
'sample_slicer__decision': ['L', 'F'],
'balancer__attr': 'subject',
bids_atlas="complete",
bids_correction="corr",
bids_derivatives='True',
load_fx='hcp-blp')
ds = loader.fetch()
nodes = ds.fa.nodes_1
matrix = np.zeros_like(ds.samples[0])
nanmask = np.logical_not(np.isnan(ds.samples).sum(0))
ds = ds[:, nanmask]
prepro = [
SampleSlicer(task=['rest', 'task1', 'task2', 'task4', 'task5']),
FeatureZNormalizer(),
SampleAttributeTransformer(attr='dexterity1', fx=('zscore', zscore)),
SampleAttributeTransformer(attr='dexterity2', fx=('zscore', zscore)),
]
ds = PreprocessingPipeline(nodes=prepro).transform(ds)
bands = ['alpha', 'betahigh', 'betalow']
tasks = ['rest', 'task1', 'task2', 'task4', 'task5']
dataframe = dict()
for b, t in product(bands, tasks):
prepro = [SampleSlicer(task=[t], band=[b]), FeatureZNormalizer()]
ds_ = PreprocessingPipeline(nodes=prepro).transform(ds)
bids_derivatives='True',
load_fx='hcp-blp')
ds = loader.fetch()
nodes = ds.fa.nodes_1
matrix = np.zeros_like(ds.samples[0])
nanmask = np.logical_not(np.isnan(ds.samples).sum(0))
ds = ds[:, nanmask]
# 1. Transform dataset to have mean 0 and std 1
prepro = [
FeatureZNormalizer(),
SampleAttributeTransformer(attr='dexterity1', fx=('zscore', zscore)),
SampleAttributeTransformer(attr='dexterity2', fx=('zscore', zscore)),
]
ds = PreprocessingPipeline(nodes=prepro).transform(ds)
formulas = [
'task + dexterity1 - 1',
'task + dexterity2 - 1',
'task - 1',
'dexterity1 - 1',
'dexterity2 - 1',
]
roi_labels = {
os.path.basename(fname).split('_')[0]: fname
for fname in roi_labels_fname
}
loader = DataLoader(configuration_file=conf_file,
event_file='residuals_attributes_full',
roi_labels=roi_labels,
task='RESIDUALS_MVPA')
prepro = PreprocessingPipeline(nodes=[
#Transformer(),
#Detrender(attr='file'),
Detrender(attr='chunks'),
SampleZNormalizer(),
FeatureZNormalizer(),
SampleSlicer(frame=[1, 2, 3, 4, 5, 6, 7]),
#TargetTransformer(attr='decision'),
MemoryReducer(dtype=np.float16),
#Balancer(attr='frame'),
])
ds = loader.fetch(prepro=prepro, n_subjects=8)
ds = MemoryReducer(dtype=np.float16).transform(ds)
labels = list(roi_labels.keys())[:-1]
import sentry_sdk
sentry_sdk.init("https://[email protected]/1439199")