def test_subsample():
with bayeslite.bayesdb_open(builtin_backends=False) as bdb:
backend = CGPM_Backend(cgpm_registry={}, multiprocess=False)
bayeslite.bayesdb_register_backend(bdb, backend)
with open(dha_csv, 'rU') as f:
read_csv.bayesdb_read_csv(bdb, 'dha', f, header=True, create=True)
bayesdb_guess_population(bdb, 'hospitals_full', 'dha',
overrides=[('name', 'key')])
bayesdb_guess_population(bdb, 'hospitals_sub', 'dha',
overrides=[('name', 'key')])
bdb.execute('''
CREATE GENERATOR hosp_full_cc FOR hospitals_full USING cgpm;
''')
bdb.execute('''
CREATE GENERATOR hosp_sub_cc FOR hospitals_sub USING cgpm(
SUBSAMPLE 100
)
''')
bdb.execute('INITIALIZE 1 MODEL FOR hosp_sub_cc')
bdb.execute('ANALYZE hosp_sub_cc FOR 1 ITERATION (OPTIMIZED)')
bdb.execute('''
ESTIMATE SIMILARITY TO (_rowid_=2) IN THE CONTEXT OF PNEUM_SCORE
FROM hospitals_sub WHERE _rowid_ = 1 OR _rowid_ = 101
''').fetchall()
bdb.execute('''
ESTIMATE SIMILARITY TO (_rowid_=102) IN THE CONTEXT OF
N_DEATH_ILL FROM hospitals_sub
WHERE _rowid_ = 1 OR _rowid_ = 101
''').fetchall()
bdb.execute('''
ESTIMATE PREDICTIVE PROBABILITY OF mdcr_spnd_amblnc
FROM hospitals_sub
WHERE _rowid_ = 1 OR _rowid_ = 101
''').fetchall()
bdb.execute('''
ESTIMATE SIMILARITY IN THE CONTEXT OF PNEUM_SCORE
FROM PAIRWISE hospitals_sub
WHERE (r0._rowid_ = 1 OR r0._rowid_ = 101) AND
(r1._rowid_ = 1 OR r1._rowid_ = 101)
''').fetchall()
bdb.execute('''
INFER mdcr_spnd_amblnc FROM hospitals_sub
WHERE _rowid_ = 1 OR _rowid_ = 101
''').fetchall()
sql = '''
SELECT table_rowid FROM bayesdb_cgpm_individual
WHERE generator_id = ?
ORDER BY cgpm_rowid ASC
LIMIT 100
'''
gid_full = bayesdb_get_generator(bdb, None, 'hosp_full_cc')
cursor = bdb.sql_execute(sql, (gid_full,))
assert [row[0] for row in cursor] == range(1, 100 + 1)
gid = bayesdb_get_generator(bdb, None, 'hosp_sub_cc')
cursor = bdb.sql_execute(sql, (gid,))
assert [row[0] for row in cursor] != range(1, 100 + 1)
bdb.execute('DROP GENERATOR hosp_sub_cc')
bdb.execute('DROP GENERATOR hosp_full_cc')
bdb.execute('DROP POPULATION hospitals_sub')
bdb.execute('DROP POPULATION hospitals_full')
def test_simulate_drawconstraint_error__ci_slow():
with bayeslite.bayesdb_open() as bdb:
with open(dha_csv, 'rU') as f:
read_csv.bayesdb_read_csv(bdb, 'dha', f, header=True, create=True)
bdb.backends['cgpm'].set_multiprocess(False)
bayesdb_guess_population(
bdb, 'hospital', 'dha', overrides=[('name', 'key')])
bdb.execute(
'CREATE GENERATOR hospital_cc FOR hospital USING cgpm;')
bdb.execute('INITIALIZE 1 MODEL FOR hospital_cc')
bdb.execute('ANALYZE hospital_cc FOR 1 ITERATION (OPTIMIZED);')
with pytest.raises(ValueError):
# Raises a ValueError since the condition variables and query
# variables both ttl_mdcr_spnd. ValueError is returned since the
# CGPM runtime, not cgpm_backend, captures the error.
bdb.execute('''
SIMULATE ttl_mdcr_spnd, n_death_ill FROM hospital
GIVEN ttl_mdcr_spnd = 40000
LIMIT 100
''').fetchall()
samples = bdb.execute('''
SIMULATE n_death_ill FROM hospital
GIVEN ttl_mdcr_spnd = 40000
LIMIT 100
''').fetchall()
assert len(samples) == 100
assert all(len(s) == 1 for s in samples)
def test_simulate_drawconstraint_error__ci_slow():
with bayeslite.bayesdb_open() as bdb:
with open(dha_csv, 'rU') as f:
read_csv.bayesdb_read_csv(bdb, 'dha', f, header=True, create=True)
bdb.backends['cgpm'].set_multiprocess(False)
bayesdb_guess_population(bdb,
'hospital',
'dha',
overrides=[('name', 'key')])
bdb.execute('CREATE GENERATOR hospital_cc FOR hospital USING cgpm;')
bdb.execute('INITIALIZE 1 MODEL FOR hospital_cc')
bdb.execute('ANALYZE hospital_cc FOR 1 ITERATION (OPTIMIZED);')
with pytest.raises(ValueError):
# Raises a ValueError since the condition variables and query
# variables both ttl_mdcr_spnd. ValueError is returned since the
# CGPM runtime, not cgpm_backend, captures the error.
bdb.execute('''
SIMULATE ttl_mdcr_spnd, n_death_ill FROM hospital
GIVEN ttl_mdcr_spnd = 40000
LIMIT 100
''').fetchall()
samples = bdb.execute('''
SIMULATE n_death_ill FROM hospital
GIVEN ttl_mdcr_spnd = 40000
LIMIT 100
''').fetchall()
assert len(samples) == 100
assert all(len(s) == 1 for s in samples)
def test_subsample():
with bayeslite.bayesdb_open(builtin_metamodels=False) as bdb:
cc = crosscat.LocalEngine.LocalEngine(seed=0)
metamodel = CrosscatMetamodel(cc)
bayeslite.bayesdb_register_metamodel(bdb, metamodel)
with open(dha_csv, 'rU') as f:
read_csv.bayesdb_read_csv(bdb, 'dha', f, header=True, create=True)
bayesdb_guess_population(bdb,
'hospitals_full',
'dha',
overrides=[('name', 'key')])
bayesdb_guess_population(bdb,
'hospitals_sub',
'dha',
overrides=[('name', 'key')])
bdb.execute('''
CREATE GENERATOR hosp_full_cc FOR hospitals_full USING crosscat (
SUBSAMPLE(OFF)
)
''')
bdb.execute('''
CREATE GENERATOR hosp_sub_cc FOR hospitals_sub USING crosscat (
SUBSAMPLE(100)
)
''')
bdb.execute('INITIALIZE 1 MODEL FOR hosp_sub_cc')
bdb.execute('ANALYZE hosp_sub_cc FOR 1 ITERATION WAIT')
bdb.execute('ESTIMATE SIMILARITY TO (_rowid_=2) FROM hospitals_sub'
' WHERE _rowid_ = 1 OR _rowid_ = 101').fetchall()
bdb.execute('ESTIMATE SIMILARITY TO (_rowid_=102) FROM hospitals_sub'
' WHERE _rowid_ = 1 OR _rowid_ = 101').fetchall()
bdb.execute('ESTIMATE PREDICTIVE PROBABILITY OF mdcr_spnd_amblnc'
' FROM hospitals_sub'
' WHERE _rowid_ = 1 OR _rowid_ = 101').fetchall()
bdb.execute('ESTIMATE SIMILARITY FROM PAIRWISE hospitals_sub'
' WHERE (r0._rowid_ = 1 OR r0._rowid_ = 101) AND'
' (r1._rowid_ = 1 OR r1._rowid_ = 101)').fetchall()
bdb.execute('INFER mdcr_spnd_amblnc FROM hospitals_sub'
' WHERE _rowid_ = 1 OR _rowid_ = 101').fetchall()
sql = '''
SELECT sql_rowid FROM bayesdb_crosscat_subsample
WHERE generator_id = ?
ORDER BY cc_row_id ASC
LIMIT 100
'''
gid_full = bayesdb_get_generator(bdb, None, 'hosp_full_cc')
cursor = bdb.sql_execute(sql, (gid_full, ))
assert [row[0] for row in cursor] == range(1, 100 + 1)
gid = bayesdb_get_generator(bdb, None, 'hosp_sub_cc')
cursor = bdb.sql_execute(sql, (gid, ))
assert [row[0] for row in cursor] != range(1, 100 + 1)
bdb.execute('DROP GENERATOR hosp_sub_cc')
bdb.execute('DROP GENERATOR hosp_full_cc')
bdb.execute('DROP POPULATION hospitals_sub')
bdb.execute('DROP POPULATION hospitals_full')
def test_simulate_drawconstraint():
with bayeslite.bayesdb_open() as bdb:
with open(dha_csv, 'rU') as f:
read_csv.bayesdb_read_csv(bdb, 'dha', f, header=True, create=True)
bayesdb_guess_population(
bdb, 'hospital', 'dha', overrides=[('name', 'key')])
bdb.execute(
'CREATE METAMODEL hospital_cc FOR hospital USING crosscat()')
bdb.execute('INITIALIZE 1 MODEL FOR hospital_cc')
bdb.execute('ANALYZE hospital_cc FOR 1 ITERATION WAIT')
samples = bdb.execute('''
SIMULATE ttl_mdcr_spnd, n_death_ill FROM hospital
GIVEN TTL_MDCR_SPND = 40000
LIMIT 100
''').fetchall()
assert [s[0] for s in samples] == [40000] * 100
def dot_guess(self, line):
'''guess population schema
<population> <table>
Create a population named <population> with variables
corresponding to columns in table <table>, heuristically
guessing their statistical types.
'''
# XXX Lousy, lousy tokenizer.
tokens = line.split()
if len(tokens) != 2:
self.stdout.write('Usage: .guess <population> <table>\n')
return
population = tokens[0]
table = tokens[1]
try:
guess.bayesdb_guess_population(self._bdb, population, table)
except Exception:
self.stdout.write(traceback.format_exc())
def dot_guess(self, line):
'''guess population schema
<population> <table>
Create a population named <population> with variables
corresponding to columns in table <table>, heuristically
guessing their statistical types.
'''
# XXX Lousy, lousy tokenizer.
tokens = line.split()
if len(tokens) != 2:
self.stdout.write('Usage: .guess <population> <table>\n')
return
population = tokens[0]
table = tokens[1]
try:
guess.bayesdb_guess_population(self._bdb, population, table)
except Exception:
self.stdout.write(traceback.format_exc())
def test_guess_population():
with bayeslite.bayesdb_open() as bdb:
bdb.sql_execute('CREATE TABLE t(x NUMERIC, y NUMERIC, z NUMERIC)')
a_z = range(ord('a'), ord('z') + 1)
aa_zz = ((c, d) for c in a_z for d in a_z)
data = ((chr(c) + chr(d), (c + d) % 2, math.sqrt(c + d))
for c, d in aa_zz)
for row in data:
bdb.sql_execute('INSERT INTO t (x, y, z) VALUES (?, ?, ?)', row)
with pytest.raises(ValueError):
# No modeled columns. (x is key.)
bayesdb_guess_population(bdb,
'p',
't',
overrides=[('y', 'ignore'),
('z', 'ignore')])
bayesdb_guess_population(bdb, 'p', 't')
with pytest.raises(ValueError):
# Population already exists.
bayesdb_guess_population(bdb, 'p', 't')
assert bdb.sql_execute(
'SELECT * FROM bayesdb_variable').fetchall() == [
(1, None, 1, 'y', 'nominal'),
(1, None, 2, 'z', 'numerical'),
]
def test_guess_population():
with bayeslite.bayesdb_open() as bdb:
bdb.sql_execute('CREATE TABLE t(x NUMERIC, y NUMERIC, z NUMERIC)')
a_z = range(ord('a'), ord('z') + 1)
aa_zz = ((c, d) for c in a_z for d in a_z)
data = ((chr(c) + chr(d), (c + d) % 2, math.sqrt(c + d))
for c, d in aa_zz)
for row in data:
bdb.sql_execute('INSERT INTO t (x, y, z) VALUES (?, ?, ?)', row)
with pytest.raises(ValueError):
# No modeled columns. (x is key.)
bayesdb_guess_population(bdb, 'p', 't',
overrides=[('y', 'ignore'), ('z', 'ignore')])
bayesdb_guess_population(bdb, 'p', 't')
with pytest.raises(ValueError):
# Population already exists.
bayesdb_guess_population(bdb, 'p', 't')
assert bdb.sql_execute('SELECT * FROM bayesdb_variable').fetchall() == [
(1, None, 1, 'y', 'nominal'),
(1, None, 2, 'z', 'numerical'),
]
def test_subsample():
with bayeslite.bayesdb_open(builtin_backends=False) as bdb:
backend = CGPM_Backend(cgpm_registry={}, multiprocess=False)
bayeslite.bayesdb_register_backend(bdb, backend)
with open(dha_csv, 'rU') as f:
read_csv.bayesdb_read_csv(bdb, 'dha', f, header=True, create=True)
bayesdb_guess_population(bdb,
'hospitals_full',
'dha',
overrides=[('name', 'key')])
bayesdb_guess_population(bdb,
'hospitals_sub',
'dha',
overrides=[('name', 'key')])
bdb.execute('''
CREATE GENERATOR hosp_full_cc FOR hospitals_full USING cgpm;
''')
bdb.execute('''
CREATE GENERATOR hosp_sub_cc FOR hospitals_sub USING cgpm(
SUBSAMPLE 100
)
''')
bdb.execute('INITIALIZE 1 MODEL FOR hosp_sub_cc')
bdb.execute('ANALYZE hosp_sub_cc FOR 1 ITERATION (OPTIMIZED)')
bdb.execute('''
ESTIMATE SIMILARITY TO (_rowid_=2) IN THE CONTEXT OF PNEUM_SCORE
FROM hospitals_sub WHERE _rowid_ = 1 OR _rowid_ = 101
''').fetchall()
bdb.execute('''
ESTIMATE SIMILARITY TO (_rowid_=102) IN THE CONTEXT OF
N_DEATH_ILL FROM hospitals_sub
WHERE _rowid_ = 1 OR _rowid_ = 101
''').fetchall()
bdb.execute('''
ESTIMATE PREDICTIVE PROBABILITY OF mdcr_spnd_amblnc
FROM hospitals_sub
WHERE _rowid_ = 1 OR _rowid_ = 101
''').fetchall()
bdb.execute('''
ESTIMATE SIMILARITY IN THE CONTEXT OF PNEUM_SCORE
FROM PAIRWISE hospitals_sub
WHERE (r0._rowid_ = 1 OR r0._rowid_ = 101) AND
(r1._rowid_ = 1 OR r1._rowid_ = 101)
''').fetchall()
bdb.execute('''
INFER mdcr_spnd_amblnc FROM hospitals_sub
WHERE _rowid_ = 1 OR _rowid_ = 101
''').fetchall()
sql = '''
SELECT table_rowid FROM bayesdb_cgpm_individual
WHERE generator_id = ?
ORDER BY cgpm_rowid ASC
LIMIT 100
'''
gid_full = bayesdb_get_generator(bdb, None, 'hosp_full_cc')
cursor = bdb.sql_execute(sql, (gid_full, ))
assert [row[0] for row in cursor] == range(1, 100 + 1)
gid = bayesdb_get_generator(bdb, None, 'hosp_sub_cc')
cursor = bdb.sql_execute(sql, (gid, ))
assert [row[0] for row in cursor] != range(1, 100 + 1)
bdb.execute('DROP GENERATOR hosp_sub_cc')
bdb.execute('DROP GENERATOR hosp_full_cc')
bdb.execute('DROP POPULATION hospitals_sub')
bdb.execute('DROP POPULATION hospitals_full')