def test_nig_normal_latent_numbering():
with bayesdb_open(':memory:') as bdb:
bayesdb_register_metamodel(bdb, NIGNormalMetamodel())
bdb.sql_execute('create table t(id integer primary key, x, y)')
for x in xrange(100):
bdb.sql_execute('insert into t(x, y) values(?, ?)',
(x, x * x - 100))
bdb.execute('''
create population p for t(id ignore; model x,y as numerical)
''')
assert core.bayesdb_has_population(bdb, 'p')
pid = core.bayesdb_get_population(bdb, 'p')
assert core.bayesdb_variable_numbers(bdb, pid, None) == [1, 2]
bdb.execute('create generator g0 for p using nig_normal')
bdb.execute('''
create generator g1 for p using nig_normal(xe deviation(x))
''')
assert core.bayesdb_has_generator(bdb, pid, 'g0')
g0 = core.bayesdb_get_generator(bdb, pid, 'g0')
assert core.bayesdb_has_generator(bdb, pid, 'g1')
g1 = core.bayesdb_get_generator(bdb, pid, 'g1')
assert core.bayesdb_variable_numbers(bdb, pid, None) == [1, 2]
assert core.bayesdb_variable_numbers(bdb, pid, g0) == [1, 2]
assert core.bayesdb_generator_column_numbers(bdb, g0) == [1, 2]
assert core.bayesdb_variable_numbers(bdb, pid, g1) == [-1, 1, 2]
assert core.bayesdb_generator_column_numbers(bdb, g1) == [-1, 1, 2]
def bql_row_similarity(bdb, generator_id, modelno, rowid, target_rowid,
*colnos):
if target_rowid is None:
raise BQLError(bdb, 'No such target row for SIMILARITY')
metamodel = core.bayesdb_generator_metamodel(bdb, generator_id)
if len(colnos) == 0:
colnos = core.bayesdb_generator_column_numbers(bdb, generator_id)
return metamodel.row_similarity(bdb, generator_id, modelno, rowid,
target_rowid, colnos)
def bql_row_similarity(bdb, generator_id, modelno, rowid, target_rowid,
*colnos):
if target_rowid is None:
raise BQLError(bdb, 'No such target row for SIMILARITY')
metamodel = core.bayesdb_generator_metamodel(bdb, generator_id)
if len(colnos) == 0:
colnos = core.bayesdb_generator_column_numbers(bdb, generator_id)
return metamodel.row_similarity(bdb, generator_id, modelno, rowid,
target_rowid, colnos)
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
def test_cgpm_extravaganza__ci_slow():
try:
from cgpm.regressions.forest import RandomForest
from cgpm.regressions.linreg import LinearRegression
from cgpm.venturescript.vscgpm import VsCGpm
except ImportError:
pytest.skip('no sklearn or venturescript')
return
with bayesdb_open(':memory:', builtin_metamodels=False) as bdb:
# XXX Use the real satellites data instead of this bogosity?
bdb.sql_execute('''
CREATE TABLE satellites_ucs (
name,
apogee,
class_of_orbit,
country_of_operator,
launch_mass,
perigee,
period
)
''')
for l, f in [
('geo', lambda x, y: x + y**2),
('leo', lambda x, y: math.sin(x + y)),
]:
for x in xrange(1000):
for y in xrange(10):
countries = ['US', 'Russia', 'China', 'Bulgaria']
country = countries[bdb._np_prng.randint(
0, len(countries))]
name = 'sat-%s-%d' % (country,
bdb._np_prng.randint(0, 10**8))
mass = bdb._np_prng.normal(1000, 50)
bdb.sql_execute(
'''
INSERT INTO satellites_ucs
(name, country_of_operator, launch_mass,
class_of_orbit, apogee, perigee, period)
VALUES (?,?,?,?,?,?,?)
''', (name, country, mass, l, x, y, f(x, y)))
bdb.execute('''
CREATE POPULATION satellites FOR satellites_ucs (
name IGNORE;
apogee NUMERICAL;
class_of_orbit CATEGORICAL;
country_of_operator CATEGORICAL;
launch_mass NUMERICAL;
perigee NUMERICAL;
period NUMERICAL
)
''')
bdb.execute('''
ESTIMATE CORRELATION FROM PAIRWISE VARIABLES OF satellites
''').fetchall()
cgpm_registry = {
'venturescript': VsCGpm,
'linreg': LinearRegression,
'forest': RandomForest,
}
cgpmt = CGPM_Metamodel(cgpm_registry)
bayesdb_register_metamodel(bdb, cgpmt)
with pytest.raises(BQLError):
bdb.execute('''
CREATE METAMODEL g0 FOR satellites USING cgpm (
SET CATEGORY MODEL FOR apoge TO NORMAL
)
''')
with pytest.raises(BQLError):
bdb.execute('''
CREATE METAMODEL g0 FOR satellites USING cgpm (
OVERRIDE MODEL FOR perigee GIVEN apoge USING linreg
)
''')
with pytest.raises(BQLError):
bdb.execute('''
CREATE METAMODEL g0 FOR satellites USING cgpm (
LATENT apogee NUMERICAL
)
''')
bdb.execute('''
CREATE METAMODEL g0 FOR satellites USING cgpm (
SET CATEGORY MODEL FOR apogee TO NORMAL;
LATENT kepler_cluster_id NUMERICAL;
LATENT kepler_noise NUMERICAL;
OVERRIDE MODEL FOR kepler_cluster_id, kepler_noise, period
GIVEN apogee, perigee
USING venturescript (source = "{}");
OVERRIDE MODEL FOR
perigee
GIVEN apogee USING linreg;
OVERRIDE MODEL FOR class_of_orbit
GIVEN apogee, period, perigee, kepler_noise
USING forest (k = 4);
SUBSAMPLE 100,
)
'''.format(kepler_source))
population_id = core.bayesdb_get_population(bdb, 'satellites')
generator_id = core.bayesdb_get_generator(bdb, population_id, 'g0')
assert core.bayesdb_generator_column_numbers(bdb, generator_id) == \
[-2, -1, 1, 2, 3, 4, 5, 6]
assert core.bayesdb_variable_numbers(bdb, population_id, None) == \
[1, 2, 3, 4, 5, 6]
assert core.bayesdb_variable_numbers(
bdb, population_id, generator_id) == \
[-2, -1, 1, 2, 3, 4, 5, 6]
# -- MODEL country_of_operator GIVEN class_of_orbit USING forest;
bdb.execute('INITIALIZE 1 MODELS FOR g0')
bdb.execute('ANALYZE g0 FOR 1 iteration WAIT (;)')
bdb.execute('''
ANALYZE g0 FOR 1 iteration WAIT (VARIABLES kepler_cluster_id)
''')
bdb.execute('''
ANALYZE g0 FOR 1 iteration WAIT (
SKIP kepler_cluster_id, kepler_noise, period;
)
''')
# OPTIMIZED uses the lovecat backend.
bdb.execute('ANALYZE g0 FOR 20 iteration WAIT (OPTIMIZED)')
with pytest.raises(Exception):
# Disallow both SKIP and VARIABLES clauses.
#
# XXX Catch a more specific exception.
bdb.execute('''
ANALYZE g0 FOR 1 ITERATION WAIT (
SKIP kepler_cluster_id;
VARIABLES apogee, perigee;
)
''')
bdb.execute('''
ANALYZE g0 FOR 1 iteration WAIT (
SKIP kepler_cluster_id, kepler_noise, period;
)
''')
bdb.execute('ANALYZE g0 FOR 1 ITERATION WAIT')
bdb.execute('''
ESTIMATE DEPENDENCE PROBABILITY
OF kepler_cluster_id WITH period WITHIN satellites
MODELLED BY g0
''').fetchall()
bdb.execute('''
ESTIMATE PREDICTIVE PROBABILITY OF apogee FROM satellites LIMIT 1
''').fetchall()
bdb.execute('''
ESTIMATE PREDICTIVE PROBABILITY OF kepler_cluster_id
FROM satellites MODELLED BY g0 LIMIT 1
''').fetchall()
bdb.execute('''
ESTIMATE PREDICTIVE PROBABILITY OF kepler_noise
FROM satellites MODELLED BY g0 LIMIT 1
''').fetchall()
bdb.execute('''
ESTIMATE PREDICTIVE PROBABILITY OF period
FROM satellites LIMIT 1
''').fetchall()
bdb.execute('''
INFER EXPLICIT
PREDICT kepler_cluster_id CONFIDENCE kepler_cluster_id_conf
FROM satellites MODELLED BY g0 LIMIT 2;
''').fetchall()
bdb.execute('''
INFER EXPLICIT PREDICT kepler_noise CONFIDENCE kepler_noise_conf
FROM satellites MODELLED BY g0 LIMIT 2;
''').fetchall()
bdb.execute('''
INFER EXPLICIT PREDICT apogee CONFIDENCE apogee_conf
FROM satellites MODELLED BY g0 LIMIT 1;
''').fetchall()
bdb.execute('''
ESTIMATE PROBABILITY OF period = 42
GIVEN (apogee = 8 AND perigee = 7)
BY satellites
''').fetchall()
bdb.execute('''
SIMULATE kepler_cluster_id, apogee, perigee, period
FROM satellites MODELLED BY g0 LIMIT 4
''').fetchall()
bdb.execute('DROP MODELS FROM g0')
bdb.execute('DROP METAMODEL g0')
bdb.execute('DROP POPULATION satellites')
bdb.execute('DROP TABLE satellites_ucs')
