def filter_neuroids(assembly, threshold):
ceiler = InternalConsistency()
ceiling = ceiler(assembly)
ceiling = ceiling.raw
ceiling = CrossValidation().aggregate(ceiling)
ceiling = ceiling.sel(aggregation='center')
pass_threshold = ceiling >= threshold
assembly = assembly[{'neuroid': pass_threshold}]
return assembly
def __init__(self, stimulus_coord='stimulus_sentence'):
self._rdm = RDM()
self._similarity = RDMSimilarity(comparison_coord=stimulus_coord)
self._cross_validation = CrossValidation(
test_size=.9, # leave 10% out
split_coord=stimulus_coord,
stratification_coord=None)
def __init__(self, regression, correlation, crossvalidation_kwargs=None):
regression = regression or pls_regression()
crossvalidation_defaults = dict(train_size=.9, test_size=None)
crossvalidation_kwargs = {
**crossvalidation_defaults,
**(crossvalidation_kwargs or {})
}
self.cross_validation = CrossValidation(**crossvalidation_kwargs)
self.regression = regression
self.correlation = correlation
def test_misaligned(self):
jumbled_source = NeuroidAssembly(np.random.rand(500, 10),
coords={'image_id': ('presentation', list(reversed(range(500)))),
'image_meta': ('presentation', [0] * 500),
'neuroid_id': ('neuroid', list(reversed(range(10)))),
'neuroid_meta': ('neuroid', [0] * 10)},
dims=['presentation', 'neuroid'])
target = jumbled_source.sortby(['image_id', 'neuroid_id'])
cv = CrossValidation(splits=10, stratification_coord=None)
metric = self.MetricPlaceholder()
score = cv(jumbled_source, target, apply=metric)
assert len(metric.train_source_assemblies) == len(metric.test_source_assemblies) == \
len(metric.train_target_assemblies) == len(metric.test_target_assemblies) == 10
assert len(score.attrs['raw']) == 10
def __init__(self):
self._cross_validation = CrossValidation(stratification_coord=None,
splits=10,
test_size=0.1)
self._i1 = I1()
self._predicted_osts, self._target_osts = [], []