def __init__(self, identifier):
regression = linear_regression(xarray_kwargs=dict(stimulus_coord='stimulus_id')) # word
correlation = pearsonr_correlation(xarray_kwargs=dict(correlation_coord='stimulus_id'))
metric = CrossRegressedCorrelation(regression=regression, correlation=correlation,
crossvalidation_kwargs=dict(splits=5, kfold=True, split_coord='stimulus_id',
stratification_coord='sentence_id'))
super(Fedorenko2016Encoding, self).__init__(identifier=identifier, metric=metric)
def __init__(self,
identifier,
split_coord='word',
unique_split_values=False):
self._logger = logging.getLogger(fullname(self))
self._identifier = identifier
assembly = LazyLoad(self._load_assembly)
self._target_assembly = assembly
regression = linear_regression(xarray_kwargs=dict(
stimulus_coord='word_id',
neuroid_coord='subject_id')) # used for sorting -- keep at word_id
correlation = pearsonr_correlation(xarray_kwargs=dict(
correlation_coord='word_id',
neuroid_coord='subject_id')) # used for sorting -- keep at word_id
self._metric = CrossRegressedCorrelation(
regression=regression,
correlation=correlation,
crossvalidation_kwargs=dict(
splits=5,
kfold=True,
split_coord=split_coord,
stratification_coord='sentence_id',
unique_split_values=unique_split_values))
self._cross_subject = CartesianProduct(dividers=['subject_id'])
self._ceiler = self.ManySubjectExtrapolationCeiling(
subject_column='subject_id')
def __init__(self, **kwargs):
metric = CrossRegressedCorrelation(
regression=linear_regression(xarray_kwargs=dict(stimulus_coord='stimulus_id')),
correlation=pearsonr_correlation(xarray_kwargs=dict(correlation_coord='stimulus_id')),
crossvalidation_kwargs=dict(split_coord='stimulus_id', stratification_coord=None))
metric = Invert(metric)
super(PereiraDecoding, self).__init__(metric=metric, **kwargs)
def __init__(self, *args, **kwargs):
super(Blank2014fROIEncoding, self).__init__(*args, **kwargs)
regression = linear_regression(xarray_kwargs=dict(
stimulus_coord='stimulus_id', neuroid_coord='fROI_area'))
correlation = pearsonr_correlation(xarray_kwargs=dict(
correlation_coord='stimulus_id', neuroid_coord='fROI_area'))
self._metric = CrossRegressedCorrelation(
regression=regression, correlation=correlation,
crossvalidation_kwargs=dict(splits=5, kfold=True, split_coord='stimulus_id', stratification_coord='story'))
def __init__(self, identifier, bold_shift=4):
self._identifier = identifier
assembly = LazyLoad(lambda: self._load_assembly(bold_shift))
self._target_assembly = assembly
regression = linear_regression(xarray_kwargs=dict(
stimulus_coord='stimulus_id', neuroid_coord='neuroid_id'))
correlation = pearsonr_correlation(xarray_kwargs=dict(
correlation_coord='stimulus_id', neuroid_coord='neuroid_id'))
self._metric = CrossRegressedCorrelation(
regression=regression, correlation=correlation,
crossvalidation_kwargs=dict(splits=5, kfold=True, split_coord='stimulus_id', stratification_coord='story'))
self._ceiler = ExtrapolationCeiling(subject_column='subject_UID', post_process=self.post_process_ceilings)
def __init__(self, *args, **kwargs):
super(Futrell2018SentencesEncoding, self).__init__(*args, **kwargs)
regression = linear_regression(xarray_kwargs=dict(
stimulus_coord='word_id', neuroid_coord='subject_id'))
correlation = pearsonr_correlation(xarray_kwargs=dict(
correlation_coord='word_id', neuroid_coord='subject_id'))
self._metric = CrossRegressedCorrelation(
regression=regression,
correlation=correlation,
crossvalidation_kwargs=dict(splits=5,
kfold=True,
unique_split_values=True,
split_coord='sentence_id',
stratification_coord=None))
def __init__(self, identifier):
self._logger = logging.getLogger(fullname(self))
self._identifier = identifier
assembly = LazyLoad(self._load_assembly)
self._target_assembly = assembly
regression = linear_regression(xarray_kwargs=dict(
stimulus_coord='word_id', neuroid_coord='subject_id'))
correlation = pearsonr_correlation(xarray_kwargs=dict(
correlation_coord='word_id', neuroid_coord='subject_id'))
self._metric = CrossRegressedCorrelation(
regression=regression,
correlation=correlation,
crossvalidation_kwargs=dict(splits=5,
kfold=True,
split_coord='word_id',
stratification_coord='sentence_id'))
def load_Pereira2018_Blank_languageresiduals():
# hijack the corresponding encoding benchmark to regress, but then store residuals instead of correlate
from neural_nlp.benchmarks.neural import PereiraEncoding
benchmark = PereiraEncoding()
assembly, cross = benchmark._target_assembly, benchmark._cross
residuals = []
def store_residuals(nonlanguage_prediction, language_target):
residual = language_target - nonlanguage_prediction
residuals.append(residual)
return Score([0],
coords={'neuroid_id': ('neuroid', [0])},
dims=['neuroid']) # dummy score
pseudo_metric = CrossRegressedCorrelation(regression=linear_regression(
xarray_kwargs=dict(stimulus_coord='stimulus_id')),
correlation=store_residuals,
crossvalidation_kwargs=dict(
splits=5,
kfold=True,
split_coord='stimulus_id',
stratification_coord=None))
# separate language from non-language networks
language_assembly = assembly[{
'neuroid': [
atlas in ['DMN', 'MD', 'language']
for atlas in assembly['atlas'].values
]
}]
nonlanguage_assembly = assembly[{
'neuroid': [
atlas in ['visual', 'auditory']
for atlas in assembly['atlas'].values
]
}]
# run
def apply_cross(source_assembly, target_assembly):
# filter experiment
source_assembly = source_assembly[{
'presentation': [
stimulus_id in target_assembly['stimulus_id'].values
for stimulus_id in source_assembly['stimulus_id'].values
]
}]
assert all(source_assembly['stimulus_id'].values ==
target_assembly['stimulus_id'].values)
# filter subjects that have not done this experiment
source_assembly = source_assembly.dropna('neuroid')
# for the target assembly, it's going to become awkward if we just drop those neuroids.
# instead, we set them to zero which makes for simple zero regression weights.
target_assembly = target_assembly.fillna(0)
# this will regress from joint visual+auditory neural space to one of the language networks
return pseudo_metric(source_assembly, target_assembly)
cross(language_assembly,
apply=lambda cross_assembly: apply_cross(nonlanguage_assembly,
cross_assembly))
# combine residuals
assert len(
residuals
) == 5 * 2 * 3 # 5-fold CV, 2 experiments, 3 language brain networks
# ensure uniqueness
neuroid_ids, stimulus_ids = [], []
for residual in residuals:
neuroid_ids += residual['neuroid_id'].values.tolist()
stimulus_ids += residual['stimulus_id'].values.tolist()
assert len(neuroid_ids) == len(language_assembly['neuroid']) * 5 * 2
assert len(set(neuroid_ids)) == len(
set(language_assembly['neuroid_id'].values))
assert len(stimulus_ids) == len(language_assembly['presentation']) * 3
assert len(set(stimulus_ids)) == len(
set(language_assembly['stimulus_id'].values))
residuals = merge_data_arrays(residuals)
residuals = type(language_assembly)(residuals)
residuals.attrs['stimulus_set'] = assembly.stimulus_set
return residuals