def test_register():
bdb = bayeslite.bayesdb_open()
composer = Composer(n_samples=5)
bayeslite.bayesdb_register_metamodel(bdb, composer)
# Check if globally registered.
try:
bdb.sql_execute('''
SELECT * FROM bayesdb_metamodel WHERE name={}
'''.format(quote(composer.name()))).next()
except StopIteration:
pytest.fail('Composer not registered in bayesdb_metamodel.')
# Check all tables/triggers.
schema = [('table', 'bayesdb_composer_cc_id'),
('table', 'bayesdb_composer_column_owner'),
('table', 'bayesdb_composer_column_toposort'),
('trigger', 'bayesdb_composer_column_toposort_check'),
('table', 'bayesdb_composer_column_parents'),
('table', 'bayesdb_composer_column_foreign_predictor'),
('trigger', 'bayesdb_composer_column_foreign_predictor_check')]
for kind, name in schema:
try:
bdb.sql_execute('''
SELECT * FROM sqlite_master WHERE type={} AND name={}
'''.format(quote(kind), quote(name))).next()
except StopIteration:
pytest.fail('Missing from Composer schema: {}'.format(
(kind, name)))
bdb.close()
def test_register():
bdb = bayeslite.bayesdb_open()
composer = Composer(n_samples=5)
bayeslite.bayesdb_register_metamodel(bdb, composer)
# Check if globally registered.
try:
bdb.sql_execute('''
SELECT * FROM bayesdb_metamodel WHERE name={}
'''.format(quote(composer.name()))).next()
except StopIteration:
pytest.fail('Composer not registered in bayesdb_metamodel.')
# Check all tables/triggers.
schema = [
('table', 'bayesdb_composer_cc_id'),
('table', 'bayesdb_composer_column_owner'),
('table', 'bayesdb_composer_column_toposort'),
('trigger', 'bayesdb_composer_column_toposort_check'),
('table', 'bayesdb_composer_column_parents'),
('table', 'bayesdb_composer_column_foreign_predictor'),
('trigger', 'bayesdb_composer_column_foreign_predictor_check')
]
for kind, name in schema:
try:
bdb.sql_execute('''
SELECT * FROM sqlite_master WHERE type={} AND name={}
'''.format(quote(kind), quote(name))).next()
except StopIteration:
pytest.fail('Missing from Composer schema: {}'.format((kind,name)))
bdb.close()
def drop_generator(self, bdb, genid):
with bdb.savepoint():
# Clear caches.
keys = [k for k in self._predictor_cache(bdb) if k[0] == genid]
for k in keys:
del self._predictor_cache(bdb)[k]
# Obtain before losing references.
cc_name = core.bayesdb_generator_name(bdb, self.cc_id(bdb, genid))
# Delete tables reverse order of insertion.
bdb.sql_execute('''
DELETE FROM bayesdb_composer_column_foreign_predictor
WHERE generator_id = ?
''', (genid,))
bdb.sql_execute('''
DELETE FROM bayesdb_composer_cc_id
WHERE generator_id = ?
''', (genid,))
bdb.sql_execute('''
DELETE FROM bayesdb_composer_column_toposort
WHERE generator_id = ?
''', (genid,))
bdb.sql_execute('''
DELETE FROM bayesdb_composer_column_parents
WHERE generator_id = ?
''', (genid,))
bdb.sql_execute('''
DELETE FROM bayesdb_composer_column_owner
WHERE generator_id = ?
''', (genid,))
# Drop internal crosscat.
bdb.execute('''
DROP GENERATOR {}
'''.format(quote(cc_name)))
def drop_models(self, bdb, genid, modelnos=None):
qg = quote(core.bayesdb_generator_name(bdb, self.cc_id(bdb, genid)))
if modelnos is not None:
models = ",".join(str(modelno) for modelno in modelnos)
bql = 'DROP MODELS {} FROM {};'.format(models, qg)
else:
bql = 'DROP MODELS FROM {};'.format(qg)
bdb.execute(bql)
def initialize_models(self, bdb, genid, modelnos, model_config):
# Initialize internal crosscat, maintaining equality of model numbers.
# The semantics of INITIALIZE are that it guarantees the existence
# of a sequence of models up to the requested number of them,
# and BayesDB computes the numbers that need to be filled in.
# The inverse of that computation is max(modelnos)+1.
qg = quote(core.bayesdb_generator_name(bdb, self.cc_id(bdb, genid)))
bql = 'INITIALIZE {} MODELS FOR {};'.format(max(modelnos)+1, qg)
bdb.execute(bql)
# Initialize the foriegn predictors.
for fcol in self.fcols(bdb, genid):
# Convert column numbers to names.
targets = \
[(core.bayesdb_generator_column_name(bdb, genid, fcol),
core.bayesdb_generator_column_stattype(bdb, genid, fcol))]
conditions = \
[(core.bayesdb_generator_column_name(bdb, genid, pcol),
core.bayesdb_generator_column_stattype(bdb, genid, pcol))
for pcol in self.pcols(bdb, genid, fcol)]
# Initialize the foreign predictor.
table_name = core.bayesdb_generator_table(bdb, genid)
predictor_name = self.predictor_name(bdb, genid, fcol)
builder = self.predictor_builder[predictor_name]
predictor = builder.create(bdb, table_name, targets, conditions)
# Store in the database.
with bdb.savepoint():
sql = '''
UPDATE bayesdb_composer_column_foreign_predictor SET
predictor_binary = :predictor_binary
WHERE generator_id = :genid AND colno = :colno
'''
predictor_binary = builder.serialize(bdb, predictor)
bdb.sql_execute(sql, {
'genid': genid,
'predictor_binary': sqlite3.Binary(predictor_binary),
'colno': fcol
})
def test_drop_generator():
bdb = bayeslite.bayesdb_open()
# Initialize the database
bayeslite.bayesdb_read_csv_file(bdb, 'satellites', PATH_SATELLITES_CSV,
header=True, create=True)
composer = Composer(n_samples=5)
bayeslite.bayesdb_register_metamodel(bdb, composer)
composer.register_foreign_predictor(random_forest.RandomForest)
composer.register_foreign_predictor(multiple_regression.MultipleRegression)
composer.register_foreign_predictor(keplers_law.KeplersLaw)
bdb.execute('''
CREATE GENERATOR t1 FOR satellites USING composer(
default (
Country_of_Operator CATEGORICAL, Operator_Owner CATEGORICAL,
Users CATEGORICAL, Purpose CATEGORICAL,
Class_of_orbit CATEGORICAL, Perigee_km NUMERICAL,
Apogee_km NUMERICAL, Eccentricity NUMERICAL,
Launch_Mass_kg NUMERICAL, Dry_Mass_kg NUMERICAL,
Power_watts NUMERICAL, Date_of_Launch NUMERICAL,
Contractor CATEGORICAL,
Country_of_Contractor CATEGORICAL, Launch_Site CATEGORICAL,
Launch_Vehicle CATEGORICAL,
Source_Used_for_Orbital_Data CATEGORICAL,
longitude_radians_of_geo NUMERICAL,
Inclination_radians NUMERICAL,
),
random_forest (
Type_of_Orbit CATEGORICAL
GIVEN Apogee_km, Perigee_km,
Eccentricity, Period_minutes, Launch_Mass_kg,
Power_watts, Anticipated_Lifetime, Class_of_orbit
),
keplers_law (
Period_minutes NUMERICAL
GIVEN Perigee_km, Apogee_km
),
multiple_regression (
Anticipated_Lifetime NUMERICAL
GIVEN Dry_Mass_kg, Power_watts, Launch_Mass_kg,
Contractor
),
DEPENDENT(Apogee_km, Perigee_km, Eccentricity),
DEPENDENT(Contractor, Country_of_Contractor),
INDEPENDENT(Country_of_Operator, Date_of_Launch)
);''')
generator_id = bayeslite.core.bayesdb_get_generator(bdb, 't1')
schema = [
('table', 'bayesdb_composer_cc_id'),
('table', 'bayesdb_composer_column_owner'),
('table', 'bayesdb_composer_column_toposort'),
('table', 'bayesdb_composer_column_parents'),
('table', 'bayesdb_composer_column_foreign_predictor'),
]
# Iterate through tables before dropping.
for _, name in schema:
bdb.sql_execute('''
SELECT * FROM {} WHERE generator_id=?
'''.format(quote(name)), (generator_id,)).next()
# Drop generator and ensure table lookups with generator_id throw error.
bdb.execute('DROP GENERATOR t1')
for _, name in schema:
with pytest.raises(StopIteration):
bdb.sql_execute('''
SELECT * FROM {} WHERE generator_id=?
'''.format(quote(name)), (generator_id,)).next()
assert not bayeslite.core.bayesdb_has_generator(bdb, 't1')
assert not bayeslite.core.bayesdb_has_generator(bdb, 't1_cc')
bdb.close()
def create_generator(self, bdb, table, schema, instantiate):
# Parse the schema.
(columns, lcols, _fcols, fcol_to_pcols, fcol_to_fpred,
dependencies) = self.parse(schema)
# Instantiate **this** generator.
genid, bdbcolumns = instantiate(columns.items())
# Create internal crosscat generator. The name will be the same as
# this generator name, with a _cc suffix.
SUFFIX = '_cc'
cc_name = bayeslite.core.bayesdb_generator_name(bdb, genid) + SUFFIX
# Create strings for crosscat schema.
cc_cols = ','.join('{} {}'.format(quote(c), quote(columns[c]))
for c in lcols)
cc_dep = []
for dep, colnames in dependencies:
qcns = ','.join(map(quote, colnames))
if dep:
cc_dep.append('DEPENDENT({})'.format(qcns))
else:
cc_dep.append('INDEPENDENT({})'.format(qcns))
bql = """
CREATE GENERATOR {} FOR {} USING crosscat(
{}, {}
);
""".format(quote(cc_name), quote(table), cc_cols, ','.join(cc_dep))
bdb.execute(bql)
# Convert strings to column numbers.
fcolno_to_pcolnos = {}
for f in fcol_to_pcols:
fcolno = core.bayesdb_generator_column_number(bdb, genid, f)
fcolno_to_pcolnos[fcolno] = [core.bayesdb_generator_column_number(
bdb, genid, col) for col in fcol_to_pcols[f]]
with bdb.savepoint():
# Save internal cc generator id.
bdb.sql_execute('''
INSERT INTO bayesdb_composer_cc_id
(generator_id, crosscat_generator_id) VALUES (?,?)
''', (genid, core.bayesdb_get_generator(bdb, cc_name),))
# Save lcols/fcolnos.
for colno, _, _ in bdbcolumns:
local = colno not in fcolno_to_pcolnos
bdb.sql_execute('''
INSERT INTO bayesdb_composer_column_owner
(generator_id, colno, local) VALUES (?,?,?)
''', (genid, colno, int(local),))
# Save parents of foreign columns.
for fcolno in fcolno_to_pcolnos:
for pcolno in fcolno_to_pcolnos[fcolno]:
bdb.sql_execute('''
INSERT INTO bayesdb_composer_column_parents
(generator_id, fcolno, pcolno) VALUES (?,?,?)
''', (genid, fcolno, pcolno,))
# Save topological order.
topo = self.topological_sort(fcolno_to_pcolnos)
for position, (colno, _) in enumerate(topo):
bdb.sql_execute('''
INSERT INTO bayesdb_composer_column_toposort
(generator_id, colno, position) VALUES (?,?,?)
''', (genid, colno, position,))
# Save predictor names of foreign columns.
for fcolno in fcolno_to_pcolnos:
fp_name = fcol_to_fpred[casefold(
core.bayesdb_generator_column_name(bdb,genid, fcolno))]
bdb.sql_execute('''
INSERT INTO bayesdb_composer_column_foreign_predictor
(generator_id, colno, predictor_name) VALUES (?,?,?)
''', (genid, fcolno, casefold(fp_name)))
def test_drop_generator():
bdb = bayeslite.bayesdb_open()
# Initialize the database
bayeslite.bayesdb_read_csv_file(bdb,
'satellites',
PATH_SATELLITES_CSV,
header=True,
create=True)
composer = Composer(n_samples=5)
bayeslite.bayesdb_register_metamodel(bdb, composer)
composer.register_foreign_predictor(random_forest.RandomForest)
composer.register_foreign_predictor(multiple_regression.MultipleRegression)
composer.register_foreign_predictor(keplers_law.KeplersLaw)
bdb.execute('''
CREATE GENERATOR t1 FOR satellites USING composer(
default (
Country_of_Operator CATEGORICAL, Operator_Owner CATEGORICAL,
Users CATEGORICAL, Purpose CATEGORICAL,
Class_of_orbit CATEGORICAL, Perigee_km NUMERICAL,
Apogee_km NUMERICAL, Eccentricity NUMERICAL,
Launch_Mass_kg NUMERICAL, Dry_Mass_kg NUMERICAL,
Power_watts NUMERICAL, Date_of_Launch NUMERICAL,
Contractor CATEGORICAL,
Country_of_Contractor CATEGORICAL, Launch_Site CATEGORICAL,
Launch_Vehicle CATEGORICAL,
Source_Used_for_Orbital_Data CATEGORICAL,
longitude_radians_of_geo NUMERICAL,
Inclination_radians NUMERICAL,
),
random_forest (
Type_of_Orbit CATEGORICAL
GIVEN Apogee_km, Perigee_km,
Eccentricity, Period_minutes, Launch_Mass_kg,
Power_watts, Anticipated_Lifetime, Class_of_orbit
),
keplers_law (
Period_minutes NUMERICAL
GIVEN Perigee_km, Apogee_km
),
multiple_regression (
Anticipated_Lifetime NUMERICAL
GIVEN Dry_Mass_kg, Power_watts, Launch_Mass_kg,
Contractor
),
DEPENDENT(Apogee_km, Perigee_km, Eccentricity),
DEPENDENT(Contractor, Country_of_Contractor),
INDEPENDENT(Country_of_Operator, Date_of_Launch)
);''')
generator_id = bayeslite.core.bayesdb_get_generator(bdb, 't1')
schema = [
('table', 'bayesdb_composer_cc_id'),
('table', 'bayesdb_composer_column_owner'),
('table', 'bayesdb_composer_column_toposort'),
('table', 'bayesdb_composer_column_parents'),
('table', 'bayesdb_composer_column_foreign_predictor'),
]
# Iterate through tables before dropping.
for _, name in schema:
bdb.sql_execute(
'''
SELECT * FROM {} WHERE generator_id=?
'''.format(quote(name)), (generator_id, )).next()
# Drop generator and ensure table lookups with generator_id throw error.
bdb.execute('DROP GENERATOR t1')
for _, name in schema:
with pytest.raises(StopIteration):
bdb.sql_execute(
'''
SELECT * FROM {} WHERE generator_id=?
'''.format(quote(name)), (generator_id, )).next()
assert not bayeslite.core.bayesdb_has_generator(bdb, 't1')
assert not bayeslite.core.bayesdb_has_generator(bdb, 't1_cc')
bdb.close()
