def cgpm_dummy_satellites_pop_bdb():
with cgpm_dummy_satellites_bdb() as bdb:
bdb.execute('''
create population satellites for satellites_ucs with schema(
apogee numerical;
class_of_orbit nominal;
country_of_operator nominal;
launch_mass numerical;
perigee numerical;
period numerical
)
''')
backend = CGPM_Backend(dict(), multiprocess=0)
bayesdb_register_backend(bdb, backend)
yield bdb
def cgpm_dummy_satellites_pop_bdb():
with cgpm_dummy_satellites_bdb() as bdb:
bdb.execute('''
create population satellites for satellites_ucs with schema(
model apogee as numerical;
model class_of_orbit as categorical;
model country_of_operator as categorical;
model launch_mass as numerical;
model perigee as numerical;
model period as numerical
)
''')
metamodel = CGPM_Metamodel(dict(), multiprocess=0)
bayesdb_register_metamodel(bdb, metamodel)
yield bdb
def test_regress_bonanza__ci_integration():
with cgpm_dummy_satellites_bdb() as bdb:
bayesdb_register_metamodel(
bdb, CGPM_Metamodel(dict(), multiprocess=0))
bdb.execute('''
CREATE POPULATION satellites FOR satellites_ucs WITH SCHEMA(
MODEL apogee AS NUMERICAL;
MODEL class_of_orbit AS NOMINAL;
MODEL country_of_operator AS NOMINAL;
MODEL launch_mass AS NUMERICAL;
MODEL perigee AS NUMERICAL;
MODEL period AS NUMERICAL
)
''')
bdb.execute('''
CREATE METAMODEL m FOR satellites WITH BASELINE crosscat;
''')
bdb.execute('INITIALIZE 2 MODELS FOR m;')
def check_regression_variables(results, numericals, nominals):
seen = set()
for r in results:
assert len(r) == 2
variable = r[0]
assert variable not in seen
assert variable in numericals or \
any(variable.startswith('%s_dum_' % (nominal,))
for nominal in nominals)
seen.add(variable)
# Regression on 1 numerical variable.
results = bdb.execute('''
REGRESS apogee GIVEN (perigee) USING 12 SAMPLES BY satellites;
''').fetchall()
assert len(results) == 2
check_regression_variables(results, ['intercept', 'perigee'], [])
# Regression on 1 nominal variable.
results = bdb.execute('''
REGRESS apogee GIVEN (country_of_operator)
USING 12 SAMPLES BY satellites;
''').fetchall()
check_regression_variables(
results, ['intercept'], ['country_of_operator'])
# Regression on 1 nominal + 1 numerical variable.
bdb.execute('''
REGRESS apogee GIVEN (perigee, country_of_operator)
USING 12 SAMPLES BY satellites;
''').fetchall()
check_regression_variables(
results, ['intercept', 'perigee'], ['country_of_operator'])
# Regression on all variables.
results = bdb.execute('''
REGRESS apogee GIVEN (*) USING 12 SAMPLES BY satellites;
''', (3,)).fetchall()
check_regression_variables(
results,
['intercept', 'perigee', 'launch_mass', 'period',],
['country_of_operator', 'class_of_orbit',],
)
# Regression on column selector subexpression with a binding.
results = bdb.execute('''
REGRESS apogee GIVEN (
satellites.(
ESTIMATE * FROM VARIABLES OF satellites
ORDER BY dependence probability with apogee DESC
LIMIT ?
)
)
USING 12 SAMPLES BY satellites MODELLED BY m USING MODEL 1;
''', (3,)).fetchall()
cursor = bdb.execute('''
ESTIMATE * FROM VARIABLES OF satellites
ORDER BY dependence probability with apogee DESC
LIMIT ?
''', (3,)).fetchall()
top_variables = [c[0] for c in cursor]
nominals = [
var for var in top_variables
if var in ['country_of_operator', 'class_of_orbit',]
]
numericals = [var for var in top_variables if var not in nominals]
check_regression_variables(
results, numericals + ['intercept'], nominals)
# Cannot mix * with other variables.
with pytest.raises(BQLError):
bdb.execute('''
REGRESS apogee GIVEN (*, class_of_orbit)
USING 1 SAMPLES BY satellites;
''').fetchall()
# Not enough data for regression, 1 unique nominal variable.
with pytest.raises(ValueError):
bdb.execute('''
REGRESS apogee GIVEN (class_of_orbit)
USING 1 SAMPLES BY satellites;
''').fetchall()
def test_regress_bonanza__ci_integration():
with cgpm_dummy_satellites_bdb() as bdb:
bayesdb_register_backend(
bdb, CGPM_Backend(dict(), multiprocess=0))
bdb.execute('''
CREATE POPULATION satellites FOR satellites_ucs WITH SCHEMA(
apogee NUMERICAL;
class_of_orbit NOMINAL;
country_of_operator NOMINAL;
launch_mass NUMERICAL;
perigee NUMERICAL;
period NUMERICAL;
)
''')
bdb.execute('''
CREATE GENERATOR m FOR satellites;
''')
bdb.execute('INITIALIZE 2 MODELS FOR m;')
def check_regression_variables(results, numericals, nominals):
seen = set()
for r in results:
assert len(r) == 2
variable = r[0]
assert variable not in seen
assert variable in numericals or \
any(variable.startswith('%s_dum_' % (nominal,))
for nominal in nominals)
seen.add(variable)
# Regression on 1 numerical variable.
results = bdb.execute('''
REGRESS apogee GIVEN (perigee) USING 12 SAMPLES BY satellites;
''').fetchall()
assert len(results) == 2
check_regression_variables(results, ['intercept', 'perigee'], [])
# Regression on 1 nominal variable.
results = bdb.execute('''
REGRESS apogee GIVEN (country_of_operator)
USING 12 SAMPLES BY satellites;
''').fetchall()
check_regression_variables(
results, ['intercept'], ['country_of_operator'])
# Regression on 1 nominal + 1 numerical variable.
bdb.execute('''
REGRESS apogee GIVEN (perigee, country_of_operator)
USING 12 SAMPLES BY satellites;
''').fetchall()
check_regression_variables(
results, ['intercept', 'perigee'], ['country_of_operator'])
# Regression on all variables.
results = bdb.execute('''
REGRESS apogee GIVEN (*) USING 12 SAMPLES BY satellites;
''', (3,)).fetchall()
check_regression_variables(
results,
['intercept', 'perigee', 'launch_mass', 'period',],
['country_of_operator', 'class_of_orbit',],
)
# Regression on column selector subexpression with a binding.
results = bdb.execute('''
REGRESS apogee GIVEN (
satellites.(
ESTIMATE * FROM VARIABLES OF satellites
ORDER BY dependence probability with apogee DESC
LIMIT ?
)
)
USING 12 SAMPLES BY satellites MODELED BY m USING MODEL 1;
''', (3,)).fetchall()
cursor = bdb.execute('''
ESTIMATE * FROM VARIABLES OF satellites
ORDER BY dependence probability with apogee DESC
LIMIT ?
''', (3,)).fetchall()
top_variables = [c[0] for c in cursor]
nominals = [
var for var in top_variables
if var in ['country_of_operator', 'class_of_orbit',]
]
numericals = [var for var in top_variables if var not in nominals]
check_regression_variables(
results, numericals + ['intercept'], nominals)
# Cannot mix * with other variables.
with pytest.raises(BQLError):
bdb.execute('''
REGRESS apogee GIVEN (*, class_of_orbit)
USING 1 SAMPLES BY satellites;
''').fetchall()
# Not enough data for regression, 1 unique nominal variable.
with pytest.raises(ValueError):
bdb.execute('''
REGRESS apogee GIVEN (class_of_orbit)
USING 1 SAMPLES BY satellites;
''').fetchall()
def test_analysis_subproblems_basic():
with cgpm_dummy_satellites_bdb() as bdb:
bdb.execute('''
CREATE POPULATION satellites FOR satellites_ucs WITH SCHEMA(
MODEL apogee AS NUMERICAL;
MODEL class_of_orbit AS CATEGORICAL;
MODEL country_of_operator AS CATEGORICAL;
MODEL launch_mass AS NUMERICAL;
MODEL perigee AS NUMERICAL;
MODEL period AS NUMERICAL
)
''')
bayesdb_register_metamodel(bdb, CGPM_Metamodel(dict(), multiprocess=0))
bdb.execute('''
CREATE ANALYSIS SCHEMA g0 FOR satellites USING cgpm(
SUBSAMPLE 10
);
''')
bdb.execute('INITIALIZE 4 ANALYSES FOR g0')
# Test each subproblem individually except for variable hyperparameters.
for optimized in [
'',
'OPTIMIZED;',
]:
for subproblem in [
'variable clustering',
'variable clustering concentration',
'row clustering',
'row clustering concentration',
]:
bdb.execute('''
ANALYZE g0 ANALYSES 0,1 FOR 4 ITERATION WAIT(
SUBPROBLEM %s;
%s
);
''' % (subproblem, optimized))
# Test variable hyperparameters.
bdb.execute('''
ANALYZE g0 FOR 1 ITERATION WAIT (
VARIABLES period, launch_mass;
SUBPROBLEM variable hyperparameters;
)
''')
with pytest.raises(BQLError):
# OPTIMIZED backend does not support variable hyperparameters.
bdb.execute('''
ANALYZE g0 FOR 1 SECONDS WAIT (
SUBPROBLEM variable hyperparameters;
OPTIMIZED;
)
''')
# Test rows.
generator_id = bayeslite.core.bayesdb_get_generator(bdb, None, 'g0')
cursor = bdb.execute(
'''
SELECT table_rowid FROM bayesdb_cgpm_individual
WHERE generator_id = ?
''', (generator_id, ))
subsample_rows = [c[0] for c in cursor]
bad_rows = [i for i in xrange(20) if i not in subsample_rows]
for optimized in ['', 'OPTIMIZED;']:
bdb.execute('''
ANALYZE g0 ANALYSIS 3 FOR 1 ITERATION WAIT (
VARIABLES class_of_orbit;
ROWS %s;
SUBPROBLEMS (
row clustering,
row clustering concentration
);
%s
)
''' % (','.join(map(str, subsample_rows)), optimized))
with pytest.raises(BQLError):
# Fail on rows not in the population or subsample.
bdb.execute('''
ANALYZE g0 ANALYSIS 3 FOR 1 ITERATION WAIT (
VARIABLES class_of_orbit;
ROWS %s;
SUBPROBLEMS (
row clustering,
row clustering concentration
);
%s
)
''' % (','.join(map(str, bad_rows)), optimized))
def test_analysis_subproblems_basic():
with cgpm_dummy_satellites_bdb() as bdb:
bdb.execute('''
CREATE POPULATION satellites FOR satellites_ucs WITH SCHEMA(
SET STATTYPE OF apogee TO NUMERICAL;
SET STATTYPE OF class_of_orbit TO NOMINAL;
SET STATTYPE OF country_of_operator TO NOMINAL;
SET STATTYPE OF launch_mass TO NUMERICAL;
SET STATTYPE OF perigee TO NUMERICAL;
SET STATTYPE OF period TO NUMERICAL
)
''')
bayesdb_register_backend(bdb, CGPM_Backend(dict(), multiprocess=0))
bdb.execute('''
CREATE GENERATOR g0 FOR satellites USING cgpm(
SUBSAMPLE 10
);
''')
bdb.execute('INITIALIZE 4 MODELS FOR g0')
# Test each subproblem individually except for variable hyperparameters.
for optimized in ['', 'OPTIMIZED;',]:
for subproblem in [
'variable clustering',
'variable clustering concentration',
'row clustering',
'row clustering concentration',
]:
bdb.execute('''
ANALYZE g0 MODELS 0,1 FOR 4 ITERATION(
SUBPROBLEM %s;
%s
);
''' % (subproblem, optimized))
# Test variable hyperparameters.
bdb.execute('''
ANALYZE g0 FOR 1 ITERATION (
VARIABLES period, launch_mass;
SUBPROBLEM variable hyperparameters;
)
''')
with pytest.raises(BQLError):
# OPTIMIZED backend does not support variable hyperparameters.
bdb.execute('''
ANALYZE g0 FOR 1 SECONDS (
SUBPROBLEM variable hyperparameters;
OPTIMIZED;
)
''')
# Test rows.
generator_id = bayeslite.core.bayesdb_get_generator(bdb, None, 'g0')
cursor = bdb.execute('''
SELECT table_rowid FROM bayesdb_cgpm_individual
WHERE generator_id = ?
''', (generator_id,))
subsample_rows = [c[0] for c in cursor]
bad_rows = [i for i in xrange(20) if i not in subsample_rows]
for optimized in ['', 'OPTIMIZED;']:
bdb.execute('''
ANALYZE g0 MODEL 3 FOR 1 ITERATION (
VARIABLES class_of_orbit;
ROWS %s;
SUBPROBLEMS (
row clustering,
row clustering concentration
);
%s
)
''' % (','.join(map(str, subsample_rows)), optimized))
with pytest.raises(BQLError):
# Fail on rows not in the population or subsample.
bdb.execute('''
ANALYZE g0 MODEL 3 FOR 1 ITERATION (
VARIABLES class_of_orbit;
ROWS %s;
SUBPROBLEMS (
row clustering,
row clustering concentration
);
%s
)
''' % (','.join(map(str, bad_rows)), optimized))