def transform(self, collection, transformations):
"""Apply all transformations to the variables in the collection.
Parameters
----------
collection: BIDSVariableCollection
The BIDSVariableCollection containing variables to transform.
transformations : list
List of transformations to apply.
"""
for t in transformations:
t = convert_JSON(t) # make sure all keys are snake case
kwargs = dict(t)
name = self._sanitize_name(kwargs.pop('name'))
cols = kwargs.pop('input', None)
# Check registered transformations; fall back on default module
func = self.transformations.get(name, None)
if func is None:
if not hasattr(self.default, name):
raise ValueError("No transformation '%s' found: either "
"explicitly register a handler, or pass a"
" default module that supports it." %
name)
func = getattr(self.default, name)
func(collection, cols, **kwargs)
return collection
def _load_model(model, validate=True):
# Load model info from JSON and do some validation
if isinstance(model, str):
with open(model, 'r', encoding='utf-8') as fobj:
model = json.load(fobj)
# Convert JSON from CamelCase to snake_case keys
model = convert_JSON(model)
if validate:
validate_model(model)
return model
def _load_model(self, model):
if isinstance(model, str):
with open(model, 'r', encoding='utf-8') as fobj:
model = json.load(fobj)
# Convert JSON from CamelCase to snake_case keys
self.model = convert_JSON(model)
steps = self.model['steps']
self.steps = []
for i, step_args in enumerate(steps):
step = Step(self.layout, index=i, **step_args)
self.steps.append(step)
def _load_model(self, model):
if isinstance(model, str):
model = json.load(open(model))
# Convert JSON from CamelCase to snake_case keys
self.model = convert_JSON(model)
steps = self.model['steps']
self.steps = []
for i, step_args in enumerate(steps):
step_args['level'] = step_args['level'].lower()
step = Step(self.layout, index=i, **step_args)
self.steps.append(step)
def _load_model(self, model):
if isinstance(model, str):
with open(model, 'r', encoding='utf-8') as fobj:
model = json.load(fobj)
# Convert JSON from CamelCase to snake_case keys
self.model = convert_JSON(model)
steps = self.model['steps']
self.steps = []
for i, step_args in enumerate(steps):
step_args['level'] = step_args['level'].lower()
step = Step(self.layout, index=i, **step_args)
self.steps.append(step)
def from_df(cls, df, model, metadata=None, formula=None):
""" Initialize a GLMMSpec instance from a BIDSVariableCollection and
a BIDS-StatsModels JSON spec.
Parameters
----------
df : DataFrame
A pandas DataFrame containing predictor information (i.e., the
fixed component of the design matrix).
model : dict
The "Model" section from a BIDS-StatsModel specification.
metadata: DataFrame
Optional DataFrame containing additional columns that are not part
of the design matrix but may have downstream informational use
and/or contain variables needed to define random effects. Rows must
map 1-to-1 with those in `df`.
formula: str
Optional Wilkinson (R-style) formula specifying the fixed (X) part
of the design matrix. All variables referenced in the formula must
be present as columns in `df`. Output names will follow the
conventions specified in the `formulaic` documentation. Note that
only the right-hand part of the formula should be passed (i.e.,
pass "X1 * X2", not "y ~ X1 * X2"). If provided, willl take
precedence over any formula found in the `model`.
Returns
-------
A GLMMSpec instance.
"""
kwargs = {}
# Fixed terms
model = convert_JSON(model)
formula = formula or model.get('formula')
if formula is not None:
df = model_matrix(formula, df)
kwargs['X'] = df
# Variance components
vcs = model.get('variance_components', [])
Z_list = []
if vcs:
# VCs can be defined by variables in either the fixed predictor
# DF or the supplementary metadata DF, so concatenate them.
all_vars = [df, metadata] if metadata is not None else [df]
all_vars = pd.concat(all_vars, axis=1)
for vc in vcs:
# Levels can either be defined by the levels of a single
# categorical ("LevelsFrom") or by a set of binary variables.
if 'levels_from' in vc:
data = all_vars[vc['levels_from']].values
Z_list.append(pd.get_dummies(data).values)
else:
df = all_vars.loc[:, vc['levels']]
Z_list.append(df.values)
Z = np.concatenate(Z_list, axis=1)
groups = np.zeros((Z.shape[1], len(Z_list)))
c = 0
for i, vc in enumerate(Z_list):
n = vc.shape[1]
groups[c:(c+n), i] = 1
c += n
groups = pd.DataFrame(groups, columns=[vc['name'] for vc in vcs])
kwargs['Z'] = Z
kwargs['groups'] = groups
error = model.get('error')
if error:
kwargs['family'] = error.get('family')
kwargs['link'] = error.get('link')
return GLMMSpec(**kwargs)
def from_collection(cls, collection, model):
""" Initialize a GLMMSpec instance from a BIDSVariableCollection and
a BIDS-StatsModels JSON spec.
Parameters
----------
collection : BIDSVariableCollection
A BIDSVariableCollection containing variable information.
model : dict
The "Model" section from a BIDS-StatsModel specification.
Returns
-------
A GLMMSpec instance.
"""
if isinstance(collection, BIDSRunVariableCollection):
if not collection.all_dense():
raise ValueError(
"Input BIDSRunVariableCollection contains at "
"least one sparse variable. All variables must"
" be dense!")
kwargs = {}
# Fixed terms
model = convert_JSON(model)
names = model.get('x', [])
if names:
names = collection.match_variables(names)
X = collection.to_df(names).loc[:, names]
kwargs['X'] = X
# Variance components
vcs = model.get('variance_components', [])
Z_list = []
if vcs:
for vc in vcs:
# Levels can either be defined by the levels of a single
# categorical ("LevelsFrom") or by a set of binary variables.
if 'levels_from' in vc:
data = collection.variables[vc['levels_from']].values
Z_list.append(pd.get_dummies(data).values)
else:
names = collection.match_variables(vc['levels'])
df = collection.to_df(names).loc[:, names]
Z_list.append(df.values)
Z = np.concatenate(Z_list, axis=1)
groups = np.zeros((Z.shape[1], len(Z_list)))
c = 0
for i, vc in enumerate(Z_list):
n = vc.shape[1]
groups[c:(c + n), i] = 1
c += n
groups = pd.DataFrame(groups, columns=[vc['name'] for vc in vcs])
kwargs['Z'] = Z
kwargs['groups'] = groups
error = model.get('error')
if error:
kwargs['family'] = error.get('family')
kwargs['link'] = error.get('link')
return GLMMSpec(**kwargs)
