def run(args):
''' Demo of inference confidence
`args` is a dict with the following keys
n_samples : int
the number of samples for imputation
n_steps : int
the number of corsscat iterations to use for confidence
n_modes : int
the number of modes from which to draw the sample data
mean_std : float (greater than 0)
the standard deviation between the means of the sample modes
std_std : float (greater than 0)
the standard deviation between the standard deviation of the modes
seed : int
RNG seed. If seed < 0, system time is used.
'''
n_samples = args['n_samples']
n_steps = args['n_steps']
n_modes = args['n_modes']
mean_std = args['mean_std']
std_std = args['std_std']
seed = args['seed']
if seed < 0:
import time
seed = int(time.time())
np.random.seed(seed)
means = np.random.normal(0, mean_std, n_modes)
stds = 1/np.random.gamma(1, 1/std_std, n_modes)
stds = [1.0]*n_modes
samples = np.zeros(n_samples)
for i in range(n_samples):
mode = np.random.randint(n_modes)
samples[i] = np.random.normal(means[mode], stds[mode])
imputed = np.median(samples)
conf, X_L_list, X_D_list = su.continuous_imputation_confidence(
samples, imputed, (), n_steps=n_steps, return_metadata=True)
results = {
'config': args,
'conf': conf,
'samples': samples,
'X_L_list': X_L_list,
'X_D_list': X_D_list,
}
return results
def _predict_confidence(self, bdb, genid, modelno, colno, rowid,
numsamples=None):
# Predicts a value for the cell [rowid, colno] with a confidence metric.
# XXX Prefer accuracy over speed for imputation.
if numsamples is None:
numsamples = self.n_samples
colnos = core.bayesdb_generator_column_numbers(bdb, genid)
colnames = core.bayesdb_generator_column_names(bdb, genid)
row = core.bayesdb_generator_row_values(bdb, genid, rowid)
# Account for multiple imputations if imputing parents.
parent_conf = 1
# Predicting lcol.
if colno in self.lcols(bdb, genid):
# Delegate to CC IFF
# (lcol has no children OR all its children are None).
children = [f for f in self.fcols(bdb, genid) if colno in
self.pcols(bdb, genid, f)]
if len(children) == 0 or \
all(row[i] is None for i in xrange(len(row)) if i+1
in children):
return self.cc(bdb, genid).predict_confidence(bdb,
self.cc_id(bdb, genid), modelno,
self.cc_colno(bdb, genid, colno), rowid)
else:
# Obtain likelihood weighted samples from posterior.
Q = [(rowid, colno)]
Y = [(rowid, c, v) for c,v in zip(colnos, row)
if c != colno and v is not None]
samples = self.simulate(bdb, genid, modelno, Q, Y,
numpredictions=numsamples)
samples = [s[0] for s in samples]
# Predicting fcol.
else:
conditions = {c:v for c,v in zip(colnames, row) if
core.bayesdb_generator_column_number(bdb, genid, c) in
self.pcols(bdb, genid, colno)}
for colname, val in conditions.iteritems():
# Impute all missing parents.
if val is None:
imp_col = core.bayesdb_generator_column_number(bdb, genid,
colname)
imp_val, imp_conf = self.predict_confidence(bdb, genid,
modelno, imp_col, rowid, numsamples=numsamples)
# XXX If imputing several parents, take the overall
# overall conf as min conf. If we define imp_conf as
# P[imp_val = correct] then we might choose to multiply
# the imp_confs, but we cannot assert that the imp_confs
# are independent so multiplying is extremely conservative.
parent_conf = min(parent_conf, imp_conf)
conditions[colname] = imp_val
assert all(v is not None for c,v in conditions.iteritems())
predictor = self.predictor(bdb, genid, colno)
samples = predictor.simulate(numsamples, conditions)
# Since foreign predictor does not know how to impute, imputation
# shall occur here in the composer by simulate/logpdf calls.
stattype = core.bayesdb_generator_column_stattype(bdb, genid, colno)
if stattype == 'categorical':
# imp_conf is most frequent.
imp_val = max(((val, samples.count(val)) for val in set(samples)),
key=lambda v: v[1])[0]
if colno in self.fcols(bdb, genid):
imp_conf = np.exp(predictor.logpdf(imp_val, conditions))
else:
imp_conf = sum(np.array(samples)==imp_val) / len(samples)
elif stattype == 'numerical':
# XXX The definition of confidence is P[k=1] where
# k=1 is the number of mixture componets (we need a distribution
# over GPMM to answer this question). The confidence is instead
# implemented as \max_i{p_i} where p_i are the weights of a
# fitted DPGMM.
imp_val = np.mean(samples)
imp_conf = su.continuous_imputation_confidence(samples, None, None,
n_steps=1000)
else:
raise ValueError('Unknown stattype "{}" for a foreign predictor '
'column encountered in predict_confidence.'.format(stattype))
return imp_val, imp_conf * parent_conf
