def test_math_func_one_param(name, probe):
# Retrieve result from python.
python_value_error = None
python_type_error = None
try:
result_python = get_python_math_call(name, probe)
except ValueError:
python_value_error = True
except TypeError:
python_type_error = True
# Retrieve result from SQL.
sql_value_error = None
sql_type_error = None
try:
with bayesdb_open(':memory:') as bdb:
cursor = bdb.execute(get_sql_math_call(name, probe))
result_sql = cursor_value(cursor)
except ValueError:
sql_value_error = True
except (TypeError, apsw.SQLError):
sql_type_error = True
# Domain error on both.
if python_value_error or sql_value_error:
assert python_value_error and sql_value_error
# Arity error on both.
elif python_type_error or sql_type_error:
assert python_type_error and sql_type_error
# Both invocations succeeded, confirm results match.
else:
assert abserr(result_python, result_sql) < 1e-4
def test_math_func_one_param(name, probe):
# Retrieve result from python.
python_value_error = None
python_type_error = None
try:
result_python = get_python_math_call(name, probe)
except ValueError:
python_value_error = True
except TypeError:
python_type_error = True
# Retrieve result from SQL.
sql_value_error = None
sql_type_error = None
try:
with bayesdb_open(':memory:') as bdb:
cursor = bdb.execute(get_sql_math_call(name, probe))
result_sql = cursor_value(cursor)
except ValueError:
sql_value_error = True
except (TypeError, apsw.SQLError):
sql_type_error = True
# Domain error on both.
if python_value_error or sql_value_error:
assert python_value_error and sql_value_error
# Arity error on both.
elif python_type_error or sql_type_error:
assert python_type_error and sql_type_error
# Both invocations succeeded, confirm results match.
else:
assert abserr(result_python, result_sql) < 1e-4
def test_correlation():
with bayeslite.bayesdb_open() as bdb:
bdb.sql_execute('CREATE TABLE u(id, c0, c1, n0, n1, r0, r1)')
bdb.execute('''
CREATE POPULATION q FOR u (
id IGNORE;
c0 NOMINAL;
c1 NOMINAL;
n0 NUMERICAL;
n1 NUMERICAL;
r0 CYCLIC;
r1 CYCLIC
)
''')
assert bdb.execute('ESTIMATE CORRELATION, CORRELATION PVALUE'
' FROM PAIRWISE COLUMNS OF q'
' WHERE name0 < name1'
' ORDER BY name0, name1').fetchall() == \
[
(1, 'c0', 'c1', None, None),
(1, 'c0', 'n0', None, None),
(1, 'c0', 'n1', None, None),
(1, 'c0', 'r0', None, None),
(1, 'c0', 'r1', None, None),
(1, 'c1', 'n0', None, None),
(1, 'c1', 'n1', None, None),
(1, 'c1', 'r0', None, None),
(1, 'c1', 'r1', None, None),
(1, 'n0', 'n1', None, None),
(1, 'n0', 'r0', None, None),
(1, 'n0', 'r1', None, None),
(1, 'n1', 'r0', None, None),
(1, 'n1', 'r1', None, None),
(1, 'r0', 'r1', None, None),
]
bdb.sql_execute('CREATE TABLE t'
'(id, c0, c1, cx, cy, n0, n1, nc, nl, nx, ny)')
data = [
('foo', 'quagga', 'x', 'y', 0, -1, +1, 1, 0, 13),
('bar', 'eland', 'x', 'y', 87, -2, -1, 2, 0, 13),
('baz', 'caribou', 'x', 'y', 92.1, -3, +1, 3, 0, 13),
] * 10
for i, row in enumerate(data):
row = (i + 1, ) + row
bdb.sql_execute('INSERT INTO t VALUES (?,?,?,?,?,?,?,?,?,?,?)',
row)
bdb.execute('''
CREATE POPULATION p FOR t (
id IGNORE;
c0 NOMINAL;
c1 NOMINAL;
cx NOMINAL;
cy NOMINAL;
n0 NUMERICAL;
n1 NUMERICAL;
nc NUMERICAL;
nl NUMERICAL;
nx NUMERICAL;
ny NUMERICAL
)
''')
result = bdb.execute('ESTIMATE CORRELATION, CORRELATION PVALUE'
' FROM PAIRWISE COLUMNS OF p'
' WHERE name0 < name1'
' ORDER BY name0, name1').fetchall()
expected = [
(2, 'c0', 'c1', 1., 2.900863120340436e-12),
(2, 'c0', 'cx', None, None),
(2, 'c0', 'cy', None, None),
(2, 'c0', 'n0', 1., 0.),
(2, 'c0', 'n1', 1., 0.),
(2, 'c0', 'nc', 1., 0.),
(2, 'c0', 'nl', 1., 0.),
(2, 'c0', 'nx', None, None),
(2, 'c0', 'ny', None, None),
(2, 'c1', 'cx', None, None),
(2, 'c1', 'cy', None, None),
(2, 'c1', 'n0', 1., 0.),
(2, 'c1', 'n1', 1., 0.),
(2, 'c1', 'nc', 1., 0.),
(2, 'c1', 'nl', 1., 0.),
(2, 'c1', 'nx', None, None),
(2, 'c1', 'ny', None, None),
(2, 'cx', 'cy', None, None),
(2, 'cx', 'n0', None, None),
(2, 'cx', 'n1', None, None),
(2, 'cx', 'nc', None, None),
(2, 'cx', 'nl', None, None),
(2, 'cx', 'nx', None, None),
(2, 'cx', 'ny', None, None),
(2, 'cy', 'n0', None, None),
(2, 'cy', 'n1', None, None),
(2, 'cy', 'nc', None, None),
(2, 'cy', 'nl', None, None),
(2, 'cy', 'nx', None, None),
(2, 'cy', 'ny', None, None),
(2, 'n0', 'n1', 0.7913965673596881, 0.),
(2, 'n0', 'nc', 0.20860343264031175, 0.0111758925135),
(2, 'n0', 'nl', 0.7913965673596881, 0.),
(2, 'n0', 'nx', None, None),
(2, 'n0', 'ny', None, None),
(2, 'n1', 'nc', 0., 1.),
(2, 'n1', 'nl', 1., 0.),
(2, 'n1', 'nx', None, None),
(2, 'n1', 'ny', None, None),
(2, 'nc', 'nl', 0., 1.),
(2, 'nc', 'nx', None, None),
(2, 'nc', 'ny', None, None),
(2, 'nl', 'nx', None, None),
(2, 'nl', 'ny', None, None),
(2, 'nx', 'ny', None, None),
]
for expected_item, observed_item in zip(expected, result):
(xpd_genid, xpd_name0, xpd_name1, xpd_corr, xpd_corr_p) = expected_item
(obs_genid, obs_name0, obs_name1, obs_corr, obs_corr_p) = observed_item
assert xpd_genid == obs_genid
assert xpd_name0 == obs_name0
assert xpd_name1 == obs_name1
assert xpd_corr == obs_corr or relerr(xpd_corr, obs_corr) < 1e-10
assert (xpd_corr == obs_corr or abserr(xpd_corr_p, obs_corr_p) < 1e-10
or relerr(xpd_corr_p, obs_corr_p) < 1e-1)
def test_cgpm_alter_basic():
with cgpm_dummy_satellites_pop_bdb() as bdb:
bdb.execute('''
create generator g0 for satellites using cgpm(
subsample 10
);
''')
bdb.execute('initialize 4 models for g0')
population_id = bayeslite.core.bayesdb_get_population(
bdb, 'satellites')
generator_id = bayeslite.core.bayesdb_get_generator(
bdb, population_id, 'g0')
# Make all variables independent in models 0-1.
bdb.execute('''
alter generator g0 models (0,1)
ensure variables * independent;
''')
dependencies = bdb.execute('''
estimate dependence probability from pairwise variables of
satellites modeled by g0 using models 0-1;
''').fetchall()
for _, var0, var1, value in dependencies:
assert value == int(var0 == var1)
# Make all variables dependent in all models.
bdb.execute('''
alter generator g0
ensure variables * dependent;
''')
dependencies = bdb.execute('''
estimate dependence probability from pairwise variables of
satellites
''').fetchall()
for _, _, _, value in dependencies:
assert value == 1
# Make all variables independent again.
bdb.execute('''
alter generator g0
ensure variables * independent;
''')
# Move apogee, perigee->view(period), launch_mass->view(class_of_orbit)
# All other variables should remain independent.
bdb.execute('''
alter generator g0
ensure variables (apogee, period, perigee) in context of period,
ensure variable launch_mass in context of class_of_orbit;
''')
dependencies = bdb.execute('''
estimate dependence probability from pairwise variables of
satellites
''').fetchall()
blocks = [
['apogee','perigee','period'],
['launch_mass', 'class_of_orbit']
]
for _, var0, var1, value in dependencies:
if var0 in blocks[0] and var1 in blocks[0]:
assert value == 1.
elif var0 in blocks[1] and var1 in blocks[1]:
assert value == 1.
elif var0 == var1:
assert value == 1.
else:
assert value == 0.
# Move period to a singleton in model 3.
bdb.execute('''
alter generator g0 model (3)
ensure variable period in singleton view
''')
dependencies = bdb.execute('''
estimate dependence probability with period from variables of
satellites modeled by g0 using models 0,1,2
''')
for _, var0, value in dependencies:
if var0 in blocks[0]:
assert value == 1
else:
assert value == 0
dependencies = bdb.execute('''
estimate dependence probability with period from variables of
satellites modeled by g0 using models 3
''')
for _, var0, value in dependencies:
assert value == 0
# Change the column crp concentration.
bdb.execute('''
alter generator g0
set view concentration parameter to 1000
''')
engine = bdb.backends['cgpm']._engine(bdb, generator_id)
for state in engine.states:
assert abserr(1./1000, state.alpha()) < 1e-5
# Change row crp concentration in view of period.
engine = bdb.backends['cgpm']._engine(bdb, generator_id)
varno = bayeslite.core.bayesdb_variable_number(
bdb, population_id, generator_id, 'period')
initial_alphas = [s.view_for(varno).alpha() for s in engine.states]
bdb.execute('''
alter generator g0 models (1,3)
set row cluster concentration parameter
within view of period to 12;
''')
for i, state in enumerate(engine.states):
view_alpha = state.view_for(varno).alpha()
if i in [1,3]:
assert abserr(1./12, view_alpha) < 1e-5
else:
assert abserr(initial_alphas[i], view_alpha) < 1e-8
# Run 10 steps of analysis.
bdb.execute('analyze g0 for 4 iteration (optimized)')
# Retrieve rows in the subsample.
cursor = bdb.execute('''
SELECT table_rowid FROM bayesdb_cgpm_individual
WHERE generator_id = ?
''', (generator_id,))
subsample_rows = [c[0] for c in cursor]
# Move all rows to same cluster in view of country_of_operator.
bdb.execute('''
alter generator g0
ensure rows * in cluster of row %s
within context of country_of_operator
''' % (subsample_rows[0],))
similarities = bdb.execute('''
estimate similarity in the context of country_of_operator
from pairwise satellites
''')
for row0, row1, value in similarities:
if row0 in subsample_rows and row1 in subsample_rows:
assert value == 1.
else:
assert value is None
def test_correlation():
with bayeslite.bayesdb_open() as bdb:
bdb.sql_execute('CREATE TABLE u(id, c0, c1, n0, n1, r0, r1)')
bdb.execute('''
CREATE POPULATION q FOR u (
id IGNORE;
c0 NOMINAL;
c1 NOMINAL;
n0 NUMERICAL;
n1 NUMERICAL;
r0 CYCLIC;
r1 CYCLIC
)
''')
assert bdb.execute('ESTIMATE CORRELATION, CORRELATION PVALUE'
' FROM PAIRWISE COLUMNS OF q'
' WHERE name0 < name1'
' ORDER BY name0, name1').fetchall() == \
[
(1, 'c0', 'c1', None, None),
(1, 'c0', 'n0', None, None),
(1, 'c0', 'n1', None, None),
(1, 'c0', 'r0', None, None),
(1, 'c0', 'r1', None, None),
(1, 'c1', 'n0', None, None),
(1, 'c1', 'n1', None, None),
(1, 'c1', 'r0', None, None),
(1, 'c1', 'r1', None, None),
(1, 'n0', 'n1', None, None),
(1, 'n0', 'r0', None, None),
(1, 'n0', 'r1', None, None),
(1, 'n1', 'r0', None, None),
(1, 'n1', 'r1', None, None),
(1, 'r0', 'r1', None, None),
]
bdb.sql_execute('CREATE TABLE t'
'(id, c0, c1, cx, cy, n0, n1, nc, nl, nx, ny)')
data = [
('foo', 'quagga', 'x', 'y', 0, -1, +1, 1, 0, 13),
('bar', 'eland', 'x', 'y', 87, -2, -1, 2, 0, 13),
('baz', 'caribou', 'x', 'y', 92.1, -3, +1, 3, 0, 13),
] * 10
for i, row in enumerate(data):
row = (i + 1,) + row
bdb.sql_execute('INSERT INTO t VALUES (?,?,?,?,?,?,?,?,?,?,?)',
row)
bdb.execute('''
CREATE POPULATION p FOR t (
id IGNORE;
c0 NOMINAL;
c1 NOMINAL;
cx NOMINAL;
cy NOMINAL;
n0 NUMERICAL;
n1 NUMERICAL;
nc NUMERICAL;
nl NUMERICAL;
nx NUMERICAL;
ny NUMERICAL
)
''')
result = bdb.execute('ESTIMATE CORRELATION, CORRELATION PVALUE'
' FROM PAIRWISE COLUMNS OF p'
' WHERE name0 < name1'
' ORDER BY name0, name1').fetchall()
expected = [
(2, 'c0', 'c1', 1., 2.900863120340436e-12),
(2, 'c0', 'cx', None, None),
(2, 'c0', 'cy', None, None),
(2, 'c0', 'n0', 1., 0.),
(2, 'c0', 'n1', 1., 0.),
(2, 'c0', 'nc', 1., 0.),
(2, 'c0', 'nl', 1., 0.),
(2, 'c0', 'nx', None, None),
(2, 'c0', 'ny', None, None),
(2, 'c1', 'cx', None, None),
(2, 'c1', 'cy', None, None),
(2, 'c1', 'n0', 1., 0.),
(2, 'c1', 'n1', 1., 0.),
(2, 'c1', 'nc', 1., 0.),
(2, 'c1', 'nl', 1., 0.),
(2, 'c1', 'nx', None, None),
(2, 'c1', 'ny', None, None),
(2, 'cx', 'cy', None, None),
(2, 'cx', 'n0', None, None),
(2, 'cx', 'n1', None, None),
(2, 'cx', 'nc', None, None),
(2, 'cx', 'nl', None, None),
(2, 'cx', 'nx', None, None),
(2, 'cx', 'ny', None, None),
(2, 'cy', 'n0', None, None),
(2, 'cy', 'n1', None, None),
(2, 'cy', 'nc', None, None),
(2, 'cy', 'nl', None, None),
(2, 'cy', 'nx', None, None),
(2, 'cy', 'ny', None, None),
(2, 'n0', 'n1', 0.7913965673596881, 0.),
(2, 'n0', 'nc', 0.20860343264031175, 0.0111758925135),
(2, 'n0', 'nl', 0.7913965673596881, 0.),
(2, 'n0', 'nx', None, None),
(2, 'n0', 'ny', None, None),
(2, 'n1', 'nc', 0., 1.),
(2, 'n1', 'nl', 1., 0.),
(2, 'n1', 'nx', None, None),
(2, 'n1', 'ny', None, None),
(2, 'nc', 'nl', 0., 1.),
(2, 'nc', 'nx', None, None),
(2, 'nc', 'ny', None, None),
(2, 'nl', 'nx', None, None),
(2, 'nl', 'ny', None, None),
(2, 'nx', 'ny', None, None),
]
for expected_item, observed_item in zip(expected, result):
(xpd_genid, xpd_name0, xpd_name1, xpd_corr, xpd_corr_p) = expected_item
(obs_genid, obs_name0, obs_name1, obs_corr, obs_corr_p) = observed_item
assert xpd_genid == obs_genid
assert xpd_name0 == obs_name0
assert xpd_name1 == obs_name1
assert xpd_corr == obs_corr or relerr(xpd_corr, obs_corr) < 1e-10
assert (xpd_corr == obs_corr
or abserr(xpd_corr_p, obs_corr_p) < 1e-10
or relerr(xpd_corr_p, obs_corr_p) < 1e-1)