def get_change(self, retest_dataset):
demographics = self.data
retest = get_demographics(retest_dataset)
retest = residualize_baseline(retest, self.residualize_vars)
if 'BMI' in retest.columns:
retest.drop(['WeightPounds', 'HeightInches'], axis=1, inplace=True)
# get common variables
common_index = sorted(list(set(demographics.index) & set(retest.index)))
common_columns = sorted(list(set(demographics.columns) & set(retest.columns)))
demographics = demographics.loc[common_index, common_columns]
retest = retest.loc[common_index, common_columns]
raw_change = retest-demographics
# convert to scores
c = self.get_c()
demographic_factor_weights = get_attr(self.results['factor_tree_Rout_oblimin'][c],'weights')
demographic_scores = scale(demographics).dot(demographic_factor_weights)
retest_scores = scale(retest).dot(demographic_factor_weights)
factor_change = pd.DataFrame(retest_scores-demographic_scores,
index=common_index,
columns = self.get_scores().columns)
factor_change = self.reorder_factors(factor_change)
factor_change.columns = [i + ' Change' for i in factor_change.columns]
return factor_change, raw_change
def get_change(self, retest_dataset):
demographics = self.data
retest = get_demographics(retest_dataset)
retest = residualize_baseline(retest, self.residualize_vars)
if 'BMI' in retest.columns:
retest.drop(['WeightPounds', 'HeightInches'], axis=1, inplace=True)
# get common variables
common_index = sorted(list(set(demographics.index) & set(retest.index)))
common_columns = sorted(list(set(demographics.columns) & set(retest.columns)))
demographics = demographics.loc[common_index, common_columns]
retest = retest.loc[common_index, common_columns]
raw_change = retest-demographics
# convert to scores
c = self.get_c()
demographic_factor_weights = get_attr(self.results['factor_tree_Rout_oblimin'][c],'weights')
demographic_scores = scale(demographics).dot(demographic_factor_weights)
retest_scores = scale(retest).dot(demographic_factor_weights)
factor_change = pd.DataFrame(retest_scores-demographic_scores,
index=common_index,
columns = self.get_scores().columns)
factor_change = self.reorder_factors(factor_change)
factor_change.columns = [i + ' Change' for i in factor_change.columns]
return factor_change, raw_change
def __init__(self, data, residualize=True, residualize_vars=['Age', 'Sex'],
boot_iter=1000):
self.raw_data = data
self.residualize_vars = residualize_vars
if residualize:
data = residualize_baseline(data, self.residualize_vars)
if 'BMI' in data.columns:
data.drop(['WeightPounds', 'HeightInches'], axis=1, inplace=True)
super().__init__(data, boot_iter=boot_iter)
def __init__(self, data, residualize=True, residualize_vars=['Age', 'Sex'],
boot_iter=1000):
self.raw_data = data
self.residualize_vars = residualize_vars
if residualize:
data = residualize_baseline(data, self.residualize_vars)
if 'BMI' in data.columns:
data.drop(['WeightPounds', 'HeightInches'], axis=1, inplace=True)
super().__init__(data, boot_iter=boot_iter)
ideo_data = ideo_data.loc[ideo_demographics.index]
# define targets
targets = {'ideo_factors': ideo_data.filter(regex='Factor'),
'ideo_orientations': ideo_data.drop(ideo_data.filter(regex='Factor|SECS').columns, axis=1).drop(['Conservatism','Intellectual Humility'], axis=1),
'ideo_policies': ideo_data.filter(regex='SECS')}
for key, target in targets.items():
imputed = pd.DataFrame(SoftImpute().fit_transform(target),
index=target.index,
columns=target.columns)
# residualize
imputed = residualize_baseline(imputed.join(ideo_demographics),
baseline_vars=ideo_demographics.columns)
targets[key] = imputed+1E-5
# ****************************************************************
# run prediction
# ****************************************************************
predictors = {}
predictions = {}
shuffled_predictions = {}
# do prediction with ontological factors
if run_factors:
# define predictors
survey_scores = results['survey'].EFA.get_scores(rotate=EFA_rotation)
task_scores = results['task'].EFA.get_scores(rotate=EFA_rotation)
predictors.update({'survey_%s' % EFA_rotation: survey_scores,
'task_%s' % EFA_rotation: task_scores,