def create_generator(self, bdb, generator_id, schema, **kwargs):
# XXX Do something with the schema.
insert_column_sql = '''
INSERT INTO bayesdb_nig_normal_column
(population_id, generator_id, colno, count, sum, sumsq)
VALUES (:population_id, :generator_id, :colno,
:count, :sum, :sumsq)
'''
population_id = core.bayesdb_generator_population(bdb, generator_id)
table = core.bayesdb_population_table(bdb, population_id)
for colno in core.bayesdb_variable_numbers(bdb, population_id, None):
column_name = core.bayesdb_variable_name(bdb, population_id,
generator_id, colno)
stattype = core.bayesdb_variable_stattype(bdb, population_id,
generator_id, colno)
if not stattype == 'numerical':
raise BQLError(
bdb, 'NIG-Normal only supports'
' numerical columns, but %s is %s' %
(repr(column_name), repr(stattype)))
(count, xsum, sumsq) = data_suff_stats(bdb, table, column_name)
bdb.sql_execute(
insert_column_sql, {
'population_id': population_id,
'generator_id': generator_id,
'colno': colno,
'count': count,
'sum': xsum,
'sumsq': sumsq,
})
# XXX Make the schema a little more flexible.
if schema == [[]]:
return
for clause in schema:
if not (len(clause) == 3 and \
isinstance(clause[0], str) and \
clause[1] == 'deviation' and \
isinstance(clause[2], list) and \
len(clause[2]) == 1 and \
isinstance(clause[2][0], str)):
raise BQLError(bdb,
'Invalid nig_normal clause: %r' % (clause, ))
dev_var = clause[0]
obs_var = clause[2][0]
if not core.bayesdb_has_variable(bdb, population_id, None,
obs_var):
raise BQLError(bdb, 'No such variable: %r' % (obs_var, ))
obs_colno = core.bayesdb_variable_number(bdb, population_id, None,
obs_var)
dev_colno = core.bayesdb_add_latent(bdb, population_id,
generator_id, dev_var,
'numerical')
bdb.sql_execute(
'''
INSERT INTO bayesdb_nig_normal_deviation
(population_id, generator_id, deviation_colno,
observed_colno)
VALUES (?, ?, ?, ?)
''', (population_id, generator_id, dev_colno, obs_colno))
def analyze_models(self, bdb, generator_id, modelnos=None, iterations=1,
max_seconds=None, ckpt_iterations=None, ckpt_seconds=None,
program=None):
if program is not None:
# XXX
raise NotImplementedError('nig_normal analysis programs')
population_id = core.bayesdb_generator_population(bdb, generator_id)
# Ignore analysis timing control, because one step reaches the
# posterior anyway.
# NOTE: Does not update the model iteration count. This would
# manifest as failing to count the number of inference
# iterations taken. Since inference converges in one step,
# this consists of failing to track the metadata of whether
# that one step was done or not.
update_sample_sql = '''
UPDATE bayesdb_nig_normal_model SET mu = :mu, sigma = :sigma
WHERE
population_id = :population_id
AND generator_id = :generator_id
AND colno = :colno
AND modelno = :modelno
'''
if modelnos is None:
# This assumes that models x columns forms a dense
# rectangle in the database, which it should.
modelnos = self._modelnos(bdb, generator_id)
self._set_models(bdb, population_id, generator_id, modelnos,
update_sample_sql)
def column_mutual_information(self, bdb, generator_id, modelnos, colnos0,
colnos1, constraints, numsamples):
population_id = bayesdb_generator_population(bdb, generator_id)
colnames0 = [
str(bayesdb_variable_name(bdb, population_id, generator_id, colno))
for colno in colnos0
]
colnames1 = [
str(bayesdb_variable_name(bdb, population_id, generator_id, colno))
for colno in colnos1
]
server = self._get_preql_server(bdb, generator_id)
target_set = server._cols_to_mask(server.encode_set(colnames0))
query_set = server._cols_to_mask(server.encode_set(colnames1))
if self._marginize_cmi(constraints):
inner_numsamples = numsamples
conditioning_rows_loom_format = self._get_constraint_rows(
constraints, bdb, generator_id, population_id, modelnos,
server, inner_numsamples)
else:
conditioning_rows_loom_format = [
self._get_constraint_row(constraints, bdb, generator_id,
population_id, server)
]
mi_estimates = [
server._query_server.mutual_information(
target_set,
query_set,
entropys=None,
sample_count=loom.preql.SAMPLE_COUNT,
conditioning_row=conditioning_row_loom_format).mean
for conditioning_row_loom_format in conditioning_rows_loom_format
]
# Output requires an iterable.
return [arithmetic_mean(mi_estimates)]
def _get_ordered_column_names(self, bdb, generator_id):
"""Return list of column names ordered by their loom rank."""
population_id = bayesdb_generator_population(bdb, generator_id)
return [
bayesdb_variable_name(bdb, population_id, None, colno)
for colno in self._get_ordered_column_numbers(bdb, generator_id)
]
def logpdf_joint(self, bdb, generator_id, modelnos, rowid, targets,
constraints):
population_id = bayesdb_generator_population(bdb, generator_id)
ordered_column_names = self._get_ordered_column_names(bdb, generator_id)
# Pr[targets|constraints] = Pr[targets, constraints] / Pr[constraints]
# The numerator is and_case; denominator is conditional_case.
and_case = OrderedDict(
[(a, None) for a in ordered_column_names])
conditional_case = OrderedDict(
[(a, None) for a in ordered_column_names])
for (colno, value) in targets:
column_name = bayesdb_variable_name(bdb, population_id, None, colno)
and_case[column_name] = self._convert_to_proper_stattype(
bdb, generator_id, colno, value)
conditional_case[column_name] = None
for (colno, value) in constraints:
column_name = bayesdb_variable_name(bdb, population_id, None, colno)
processed_value = self._convert_to_proper_stattype(
bdb, generator_id, colno, value)
and_case[column_name] = processed_value
conditional_case[column_name] = processed_value
and_case = and_case.values()
conditional_case = conditional_case.values()
server = self._get_query_server(bdb, generator_id)
and_score = server.score(and_case)
conditional_score = server.score(conditional_case)
return and_score - conditional_score
def predict_confidence(self, bdb, generator_id, modelnos, rowid, colno,
numsamples=None):
if not numsamples:
numsamples = 2
assert numsamples > 0
def _impute_categorical(sample):
counts = Counter(s[0] for s in sample)
mode_count = max(counts[v] for v in counts)
pred = iter(v for v in counts if counts[v] == mode_count).next()
conf = float(mode_count) / numsamples
return pred, conf
def _impute_numerical(sample):
pred = sum(s[0] for s in sample) / float(len(sample))
conf = 0
return pred, conf
# Retrieve the samples: specifying rowid suffices to ensures that
# relevant constraints are retrieved by simulat_joint.
sample = self.simulate_joint(
bdb, generator_id, modelnos, rowid, [colno], [], numsamples)
# Determine the imputation strategy (mode or mean).
population_id = bayesdb_generator_population(bdb, generator_id)
stattype = bayesdb_variable_stattype(bdb, population_id, None, colno)
# Run the imputation.
if _is_nominal(stattype):
return _impute_categorical(sample)
else:
return _impute_numerical(sample)
def logpdf_joint(self, bdb, generator_id, modelnos, rowid, targets,
constraints):
population_id = bayesdb_generator_population(bdb, generator_id)
ordered_column_names = self._get_ordered_column_names(
bdb, generator_id)
# Pr[targets|constraints] = Pr[targets, constraints] / Pr[constraints]
# The numerator is and_case; denominator is conditional_case.
and_case = OrderedDict([(a, None) for a in ordered_column_names])
conditional_case = OrderedDict([(a, None)
for a in ordered_column_names])
for (colno, value) in targets:
column_name = bayesdb_variable_name(bdb, population_id, None,
colno)
and_case[column_name] = self._convert_to_proper_stattype(
bdb, generator_id, colno, value)
conditional_case[column_name] = None
for (colno, value) in constraints:
column_name = bayesdb_variable_name(bdb, population_id, None,
colno)
processed_value = self._convert_to_proper_stattype(
bdb, generator_id, colno, value)
and_case[column_name] = processed_value
conditional_case[column_name] = processed_value
and_case = and_case.values()
conditional_case = conditional_case.values()
server = self._get_query_server(bdb, generator_id)
and_score = server.score(and_case)
conditional_score = server.score(conditional_case)
return and_score - conditional_score
def _get_ordered_column_names(self, bdb, generator_id):
"""Return list of column names ordered by their loom rank."""
population_id = bayesdb_generator_population(bdb, generator_id)
return [
bayesdb_variable_name(bdb, population_id, None, colno)
for colno in self._get_ordered_column_numbers(bdb, generator_id)
]
def analyze_models(self,
bdb,
generator_id,
modelnos=None,
iterations=1,
max_seconds=None,
ckpt_iterations=None,
ckpt_seconds=None,
program=None):
if program is not None:
# XXX
raise NotImplementedError('nig_normal analysis programs')
population_id = core.bayesdb_generator_population(bdb, generator_id)
# Ignore analysis timing control, because one step reaches the
# posterior anyway.
# NOTE: Does not update the model iteration count. This would
# manifest as failing to count the number of inference
# iterations taken. Since inference converges in one step,
# this consists of failing to track the metadata of whether
# that one step was done or not.
update_sample_sql = '''
UPDATE bayesdb_nig_normal_model SET mu = :mu, sigma = :sigma
WHERE
population_id = :population_id
AND generator_id = :generator_id
AND colno = :colno
AND modelno = :modelno
'''
if modelnos is None:
# This assumes that models x columns forms a dense
# rectangle in the database, which it should.
modelnos = self._modelnos(bdb, generator_id)
self._set_models(bdb, population_id, generator_id, modelnos,
update_sample_sql)
def predict_confidence(self,
bdb,
generator_id,
modelnos,
rowid,
colno,
numsamples=None):
if not numsamples:
numsamples = 2
assert numsamples > 0
def _impute_categorical(sample):
counts = Counter(s[0] for s in sample)
mode_count = max(counts[v] for v in counts)
pred = iter(v for v in counts if counts[v] == mode_count).next()
conf = float(mode_count) / numsamples
return pred, conf
def _impute_numerical(sample):
pred = sum(s[0] for s in sample) / float(len(sample))
conf = 0
return pred, conf
# Retrieve the samples. Specifying `rowid` ensures that relevant
# constraints are retrieved by `simulate`,
# so provide empty constraints.
sample = self.simulate_joint(bdb, generator_id, modelnos, rowid,
[colno], [], numsamples)
# Determine the imputation strategy (mode or mean).
population_id = bayesdb_generator_population(bdb, generator_id)
stattype = bayesdb_variable_stattype(bdb, population_id, None, colno)
if _is_nominal(stattype):
return _impute_categorical(sample)
return _impute_numerical(sample)
def create_generator(self, bdb, generator_id, schema, **kwargs):
# XXX Do something with the schema.
insert_column_sql = '''
INSERT INTO bayesdb_nig_normal_column
(population_id, generator_id, colno, count, sum, sumsq)
VALUES (:population_id, :generator_id, :colno,
:count, :sum, :sumsq)
'''
population_id = core.bayesdb_generator_population(bdb, generator_id)
table = core.bayesdb_population_table(bdb, population_id)
for colno in core.bayesdb_variable_numbers(bdb, population_id, None):
column_name = core.bayesdb_variable_name(
bdb, population_id, generator_id, colno)
stattype = core.bayesdb_variable_stattype(
bdb, population_id, generator_id, colno)
if not stattype == 'numerical':
raise BQLError(bdb, 'NIG-Normal only supports'
' numerical columns, but %s is %s'
% (repr(column_name), repr(stattype)))
(count, xsum, sumsq) = data_suff_stats(bdb, table, column_name)
bdb.sql_execute(insert_column_sql, {
'population_id': population_id,
'generator_id': generator_id,
'colno': colno,
'count': count,
'sum': xsum,
'sumsq': sumsq,
})
# XXX Make the schema a little more flexible.
if schema == [[]]:
return
for clause in schema:
if not (len(clause) == 3 and \
isinstance(clause[0], str) and \
clause[1] == 'deviation' and \
isinstance(clause[2], list) and \
len(clause[2]) == 1 and \
isinstance(clause[2][0], str)):
raise BQLError(bdb, 'Invalid nig_normal clause: %r' %
(clause,))
dev_var = clause[0]
obs_var = clause[2][0]
if not core.bayesdb_has_variable(bdb, population_id, None,
obs_var):
raise BQLError(bdb, 'No such variable: %r' % (obs_var,))
obs_colno = core.bayesdb_variable_number(bdb, population_id, None,
obs_var)
dev_colno = core.bayesdb_add_latent(bdb, population_id,
generator_id, dev_var, 'numerical')
bdb.sql_execute('''
INSERT INTO bayesdb_nig_normal_deviation
(population_id, generator_id, deviation_colno,
observed_colno)
VALUES (?, ?, ?, ?)
''', (population_id, generator_id, dev_colno, obs_colno))
def initialize_models(self, bdb, generator_id, modelnos):
population_id = core.bayesdb_generator_population(bdb, generator_id)
insert_sample_sql = '''
INSERT INTO bayesdb_nig_normal_model
(population_id, generator_id, colno, modelno, mu, sigma)
VALUES (:population_id, :generator_id, :colno, :modelno,
:mu, :sigma)
'''
self._set_models(bdb, population_id, generator_id, modelnos,
insert_sample_sql)
def initialize_models(self, bdb, generator_id, modelnos):
population_id = core.bayesdb_generator_population(bdb, generator_id)
insert_sample_sql = '''
INSERT INTO bayesdb_nig_normal_model
(population_id, generator_id, colno, modelno, mu, sigma)
VALUES (:population_id, :generator_id, :colno, :modelno,
:mu, :sigma)
'''
self._set_models(bdb, population_id, generator_id, modelnos,
insert_sample_sql)
def _convert_to_proper_stattype(self, bdb, generator_id, colno, value):
"""Convert a value returned by the logpdf_joint method parameters into a
form that Loom can handle. For instance, convert from an integer to
real or, from a string to an integer.
"""
if value is None:
return value
population_id = bayesdb_generator_population(bdb, generator_id)
stattype = bayesdb_variable_stattype(bdb, population_id, None, colno)
# If nominal then return the integer code.
if _is_nominal(stattype):
return self._get_integer_form(bdb, generator_id, colno, value)
# Return the value as float.
return float(value)
def create_generator(self, bdb, generator_id, schema, **kwargs):
population_id = bayesdb_generator_population(bdb, generator_id)
table = bayesdb_population_table(bdb, population_id)
# Store generator info in bdb.
name = self._generate_name(bdb, generator_id)
bdb.sql_execute(
'''
INSERT INTO bayesdb_loom_generator
(generator_id, name, loom_store_path)
VALUES (?, ?, ?)
''', (generator_id, name, self.loom_store_path))
headers = []
data = []
data_by_column = {}
for colno in bayesdb_variable_numbers(bdb, population_id, None):
column_name = bayesdb_variable_name(bdb, population_id, None,
colno)
headers.append(column_name)
qt = sqlite3_quote_name(table)
qcn = sqlite3_quote_name(column_name)
cursor = bdb.sql_execute('SELECT %s FROM %s' % (qcn, qt))
col_data = [item for (item, ) in cursor.fetchall()]
data.append(col_data)
data_by_column[column_name] = col_data
data = [list(i) for i in zip(*data)]
# Ingest data into loom.
schema_file = self._data_to_schema(bdb, population_id, data_by_column)
csv_file = self._data_to_csv(bdb, headers, data)
project_path = self._get_loom_project_path(bdb, generator_id)
loom.tasks.ingest(project_path,
rows_csv=csv_file.name,
schema=schema_file.name)
# Store encoding info in bdb.
self._store_encoding_info(bdb, generator_id)
# Store rowid mapping in the bdb.
qt = sqlite3_quote_name(table)
rowids = bdb.sql_execute('SELECT oid FROM %s' % (qt, )).fetchall()
insertions = ','.join(
str((generator_id, table_rowid, loom_rowid))
for loom_rowid, (table_rowid, ) in enumerate(rowids))
bdb.sql_execute('''
INSERT INTO bayesdb_loom_rowid_mapping
(generator_id, table_rowid, loom_rowid)
VALUES %s
''' % (insertions, ))
def create_generator(self, bdb, generator_id, schema, **kwargs):
population_id = bayesdb_generator_population(bdb, generator_id)
table = bayesdb_population_table(bdb, population_id)
# Store generator info in bdb.
name = self._generate_name(bdb, generator_id)
bdb.sql_execute('''
INSERT INTO bayesdb_loom_generator
(generator_id, name, loom_store_path)
VALUES (?, ?, ?)
''', (generator_id, name, self.loom_store_path))
headers = []
data = []
data_by_column = {}
for colno in bayesdb_variable_numbers(bdb, population_id, None):
column_name = bayesdb_variable_name(bdb, population_id, None, colno)
headers.append(column_name)
qt = sqlite3_quote_name(table)
qcn = sqlite3_quote_name(column_name)
cursor = bdb.sql_execute('SELECT %s FROM %s' % (qcn, qt))
col_data = [item for (item,) in cursor.fetchall()]
data.append(col_data)
data_by_column[column_name] = col_data
data = [list(i) for i in zip(*data)]
# Ingest data into loom.
schema_file = self._data_to_schema(bdb, population_id, data_by_column)
csv_file = self._data_to_csv(bdb, headers, data)
project_path = self._get_loom_project_path(bdb, generator_id)
loom.tasks.ingest(project_path, rows_csv=csv_file.name,
schema=schema_file.name)
# Store encoding info in bdb.
self._store_encoding_info(bdb, generator_id)
# Store rowid mapping in the bdb.
qt = sqlite3_quote_name(table)
rowids = bdb.sql_execute('SELECT oid FROM %s' % (qt,)).fetchall()
insertions = ','.join(
str((generator_id, table_rowid, loom_rowid))
for loom_rowid, (table_rowid,) in enumerate(rowids)
)
bdb.sql_execute('''
INSERT INTO bayesdb_loom_rowid_mapping
(generator_id, table_rowid, loom_rowid)
VALUES %s
''' % (insertions,))
def _data(self, bdb, generator_id, vars):
# Get the column numbers and statistical types.
population_id = core.bayesdb_generator_population(bdb, generator_id)
colnos = [
core.bayesdb_variable_number(bdb, population_id, generator_id, var)
for var in vars
]
stattypes = [
core.bayesdb_variable_stattype(bdb, population_id, colno)
for colno in colnos
]
# Get the table name, quoted for constructing SQL.
table_name = core.bayesdb_generator_table(bdb, generator_id)
qt = sqlite3_quote_name(table_name)
# Create SQL expressions to cast each variable to the correct
# affinity for its statistical type.
def cast(var, colno, stattype):
if colno < 0:
return 'NULL'
qv = sqlite3_quote_name(var)
affinity = core.bayesdb_stattype_affinity(bdb, stattype)
qa = sqlite3_quote_name(affinity)
return 'CAST(t.%s AS %s)' % (qv, qa)
qexpressions = ','.join(map(cast, vars, colnos, stattypes))
# Get a cursor.
cursor = bdb.sql_execute(
'''
SELECT %s FROM %s AS t, bayesdb_cgpm_individual AS ci
WHERE ci.generator_id = ?
AND ci.table_rowid = t._rowid_
ORDER BY t._rowid_ ASC
''' % (qexpressions, qt), (generator_id, ))
# Map values to codes.
def map_value(colno, value):
return self._to_numeric(bdb, generator_id, colno, value)
return [
tuple(map_value(colno, x) for colno, x in zip(colnos, row))
for row in cursor
]
def _store_encoding_info(self, bdb, generator_id):
encoding_path = os.path.join(
self._get_loom_project_path(bdb, generator_id), 'ingest',
'encoding.json.gz')
with gzip.open(encoding_path) as encoding_file:
encoding = json.loads(encoding_file.read().decode('ascii'))
population_id = bayesdb_generator_population(bdb, generator_id)
table = bayesdb_population_table(bdb, population_id)
# Store string encoding.
insert_string_encoding = '''
INSERT INTO bayesdb_loom_string_encoding
(generator_id, colno, string_form, integer_form)
VALUES (:generator_id, :colno, :string_form, :integer_form)
'''
for col in encoding:
if 'symbols' in col:
colno = bayesdb_table_column_number(bdb, table,
str(col['name']))
for string_form, integer_form in col['symbols'].iteritems():
bdb.sql_execute(
insert_string_encoding, {
'generator_id': generator_id,
'colno': colno,
'string_form': string_form,
'integer_form': integer_form
})
# Store ordering of columns.
insert_order_sql = '''
INSERT INTO bayesdb_loom_column_ordering
(generator_id, colno, rank)
VALUES (:generator_id, :colno, :rank)
'''
for col_index in xrange(len(encoding)):
colno = bayesdb_table_column_number(
bdb, table, str(encoding[col_index]['name']))
bdb.sql_execute(insert_order_sql, {
'generator_id': generator_id,
'colno': colno,
'rank': col_index
})
def _store_encoding_info(self, bdb, generator_id):
encoding_path = os.path.join(
self._get_loom_project_path(bdb, generator_id),
'ingest', 'encoding.json.gz'
)
with gzip.open(encoding_path) as encoding_file:
encoding = json.loads(encoding_file.read().decode('ascii'))
population_id = bayesdb_generator_population(bdb, generator_id)
table = bayesdb_population_table(bdb, population_id)
# Store string encoding.
insert_string_encoding = '''
INSERT INTO bayesdb_loom_string_encoding
(generator_id, colno, string_form, integer_form)
VALUES (:generator_id, :colno, :string_form, :integer_form)
'''
for col in encoding:
if 'symbols' in col:
colno = bayesdb_table_column_number(bdb, table, str(col['name']))
for string_form, integer_form in col['symbols'].iteritems():
bdb.sql_execute(insert_string_encoding, {
'generator_id': generator_id,
'colno': colno,
'string_form': string_form,
'integer_form': integer_form
})
# Store ordering of columns.
insert_order_sql = '''
INSERT INTO bayesdb_loom_column_ordering
(generator_id, colno, rank)
VALUES (:generator_id, :colno, :rank)
'''
for col_index in xrange(len(encoding)):
colno = bayesdb_table_column_number(
bdb, table, str(encoding[col_index]['name']))
bdb.sql_execute(insert_order_sql, {
'generator_id': generator_id,
'colno': colno,
'rank': col_index
})
def _store_kind_partition(self, bdb, generator_id, modelnos):
population_id = bayesdb_generator_population(bdb, generator_id)
if modelnos is None:
modelnos = range(self._get_num_models(bdb, generator_id))
with bdb.savepoint():
for modelno in modelnos:
column_partition = self._retrieve_column_partition(
bdb, generator_id, modelno)
# Bulk insertion of mapping from colno to kind_id.
colnos = bayesdb_variable_numbers(bdb, population_id, None)
ranks = [self._get_loom_rank(bdb, generator_id, colno)
for colno in colnos]
insertions = ','.join(
str((generator_id, modelno, colno, column_partition[rank]))
for colno, rank in zip(colnos, ranks)
)
bdb.sql_execute('''
INSERT OR REPLACE INTO bayesdb_loom_column_kind_partition
(generator_id, modelno, colno, kind_id)
VALUES %s
''' % (insertions,))
# Bulk insertion of mapping from (kind_id, rowid) to cluster_id.
row_partition = self._retrieve_row_partition(
bdb, generator_id, modelno)
rowids = bdb.sql_execute('''
SELECT table_rowid, loom_rowid
FROM bayesdb_loom_rowid_mapping
''').fetchall()
insertions = ','.join(
str((generator_id, modelno, rowid[0], rowid[1],
kind_id, partition_id))
for kind_id in row_partition
for rowid, partition_id
in zip(rowids, row_partition[kind_id]))
bdb.sql_execute('''
INSERT OR REPLACE INTO
bayesdb_loom_row_kind_partition
(generator_id, modelno, table_rowid, loom_rowid,
kind_id, partition_id)
VALUES %s
''' % (insertions,))
def _store_kind_partition(self, bdb, generator_id, modelnos):
population_id = bayesdb_generator_population(bdb, generator_id)
if modelnos is None:
modelnos = range(self._get_num_models(bdb, generator_id))
with bdb.savepoint():
for modelno in modelnos:
column_partition = self._retrieve_column_partition(
bdb, generator_id, modelno)
# Bulk insertion of mapping from colno to kind_id.
colnos = bayesdb_variable_numbers(bdb, population_id, None)
ranks = [
self._get_loom_rank(bdb, generator_id, colno)
for colno in colnos
]
insertions = ','.join(
str((generator_id, modelno, colno, column_partition[rank]))
for colno, rank in zip(colnos, ranks))
bdb.sql_execute('''
INSERT OR REPLACE INTO bayesdb_loom_column_kind_partition
(generator_id, modelno, colno, kind_id)
VALUES %s
''' % (insertions, ))
# Bulk insertion of mapping from (kind_id, rowid) to cluster_id.
row_partition = self._retrieve_row_partition(
bdb, generator_id, modelno)
rowids = bdb.sql_execute('''
SELECT table_rowid, loom_rowid
FROM bayesdb_loom_rowid_mapping
''').fetchall()
insertions = ','.join(
str((generator_id, modelno, rowid[0], rowid[1], kind_id,
partition_id)) for kind_id in row_partition for rowid,
partition_id in zip(rowids, row_partition[kind_id]))
bdb.sql_execute('''
INSERT OR REPLACE INTO
bayesdb_loom_row_kind_partition
(generator_id, modelno, table_rowid, loom_rowid,
kind_id, partition_id)
VALUES %s
''' % (insertions, ))
def _convert_to_proper_stattype(self, bdb, generator_id, colno, value):
"""Convert a value returned by the logpdf_joint method parameters into a
form that Loom can handle. For instance, convert from an integer to
real or, from a string to an integer.
"""
if value is None:
return value
population_id = bayesdb_generator_population(bdb, generator_id)
stattype = bayesdb_variable_stattype(bdb, population_id, None, colno)
# If nominal, then return the integer code.
if _is_nominal(stattype):
return self._get_integer_form(bdb, generator_id, colno, value)
# If countable, then return value as integer.
elif _is_countable(stattype):
# XXX This is going to cause a counts of 2.4 to evaluate to 2.
# Better than having a StopIteration error coming from Loom.
return int(value)
# If continuous, return the value as float.
elif _is_continuous(stattype):
return float(value)
else:
assert False, 'Unknown stattype'
def _reorder_row(self, bdb, generator_id, row, dense=True):
"""Reorder a row of columns according to loom's column order.
Row should be a list of (colno, value) tuples
Returns a list of (colno, value) tuples in the proper order.
"""
ordered_column_labels = self._get_ordered_column_labels(
bdb, generator_id)
ordererd_column_dict = OrderedDict([(a, None)
for a in ordered_column_labels])
population_id = bayesdb_generator_population(bdb, generator_id)
for colno, value in zip(range(1, len(row) + 1), row):
column_name = bayesdb_variable_name(bdb, population_id, None,
colno)
ordererd_column_dict[column_name] = str(value)
if dense is False:
return [(colno, value)
for (colno, value) in ordererd_column_dict.iteritems()
if value is not None]
return ordererd_column_dict.iteritems()
def _initialize_engine(self, bdb, generator_id, n, variables):
population_id = core.bayesdb_generator_population(bdb, generator_id)
def map_var(var):
return core.bayesdb_variable_number(bdb, population_id,
generator_id, var)
# If no variables in the population modeled by the gpmcc, then create 1
# dummy variable with one measurement. The design space for how to
# refactor cgpm.crosscat.State to initialize without any variables is
# not simple, so we will live with this workaround for now.
if not variables:
(outputs, cctypes, distargs, gpmcc_data) = \
[7**10], ['bernoulli'], [None], [[0]]
else:
outputs = [map_var(var) for var, _st, _cct, _da in variables]
cctypes = [cctype for _n, _st, cctype, _da in variables]
distargs = [distargs for _n, _st, _cct, distargs in variables]
gpmcc_vars = [var for var, _stattype, _dist, _params in variables]
gpmcc_data = self._data(bdb, generator_id, gpmcc_vars)
# If gpmcc_data has any column which is all null, then crash early
# and notify the user of all offending column names.
n_rows = len(gpmcc_data[0])
nulls = [
v for i, v in enumerate(gpmcc_vars) if all(
math.isnan(gpmcc_data[r][i]) for r in xrange(n_rows))
]
if nulls:
raise BQLError(
bdb, 'Failed to initialize, '
'columns have all null values: %s' % repr(nulls))
return Engine(gpmcc_data,
num_states=n,
rng=bdb.np_prng,
multiprocess=self._ncpu,
outputs=outputs,
cctypes=cctypes,
distargs=distargs)
def _convert_to_proper_stattype(self, bdb, generator_id, colno, value):
"""Convert a value returned by the logpdf_joint method parameters into a
form that Loom can handle. For instance, convert from an integer to
real or, from a string to an integer.
"""
if value is None:
return value
population_id = bayesdb_generator_population(bdb, generator_id)
stattype = bayesdb_variable_stattype(bdb, population_id, None, colno)
# If nominal, then return the integer code.
if _is_nominal(stattype):
return self._get_integer_form(bdb, generator_id, colno, value)
# If countable, then return value as integer.
elif _is_countable(stattype):
# XXX This is going to cause a counts of 2.4 to evaluate to 2.
# Better than having a StopIteration error coming from Loom.
return int(value)
# If continuous, return the value as float.
elif _is_continuous(stattype):
return float(value)
else:
assert False, 'Unknown stattype'
def column_mutual_information(self, bdb, generator_id, modelnos, colnos0,
colnos1, constraints, numsamples):
# XXX Why are the constraints being ignored? If Loom does not support
# conditioning, then implement constraints using the simple Monte Carlo
# estimator.
population_id = bayesdb_generator_population(bdb, generator_id)
colnames0 = [
str(bayesdb_variable_name(bdb, population_id, None, colno))
for colno in colnos0
]
colnames1 = [
str(bayesdb_variable_name(bdb, population_id, None, colno))
for colno in colnos1
]
server = self._get_cache_entry(bdb, generator_id, 'preql_server')
target_set = server._cols_to_mask(server.encode_set(colnames0))
query_set = server._cols_to_mask(server.encode_set(colnames1))
mi = server._query_server.mutual_information(
target_set,
query_set,
entropys=None,
sample_count=loom.preql.SAMPLE_COUNT)
return mi
def _initialize_cgpm(self, bdb, generator_id, cgpm_ext):
population_id = core.bayesdb_generator_population(bdb, generator_id)
def map_var(var):
return core.bayesdb_variable_number(bdb, population_id,
generator_id, var)
name = cgpm_ext['name']
outputs = map(map_var, cgpm_ext['outputs'])
inputs = map(map_var, cgpm_ext['inputs'])
args = cgpm_ext.get('args', ())
kwds = cgpm_ext.get('kwds', {})
if name not in self._cgpm_registry:
raise BQLError(bdb, 'Unknown CGPM: %s' % (repr(name), ))
cls = self._cgpm_registry[name]
cgpm_vars = cgpm_ext['outputs'] + cgpm_ext['inputs']
cgpm_data = self._data(bdb, generator_id, cgpm_vars)
cgpm = cls(outputs, inputs, rng=bdb.np_prng, *args, **kwds)
for cgpm_rowid, row in enumerate(cgpm_data):
# CGPMs do not uniformly handle null values or missing
# values sensibly yet, so until we have that sorted
# out we both (a) omit nulls and (b) ignore errors in
# incorporate.
query = {
colno: row[i]
for i, colno in enumerate(outputs) if not math.isnan(row[i])
}
n = len(outputs)
evidence = {
colno: row[n + i]
for i, colno in enumerate(inputs) if not math.isnan(row[n + i])
}
try:
cgpm.incorporate(cgpm_rowid, query, evidence)
except Exception:
pass
return cgpm
def column_mutual_information(self, bdb, generator_id, modelnos, colnos0,
colnos1, constraints, numsamples):
population_id = bayesdb_generator_population(bdb, generator_id)
colnames0 = [
str(bayesdb_variable_name(bdb, population_id, generator_id, colno))
for colno in colnos0
]
colnames1 = [
str(bayesdb_variable_name(bdb, population_id, generator_id, colno))
for colno in colnos1
]
server = self._get_preql_server(bdb, generator_id)
target_set = server._cols_to_mask(server.encode_set(colnames0))
query_set = server._cols_to_mask(server.encode_set(colnames1))
if self._marginize_cmi(constraints):
inner_numsamples = numsamples
conditioning_rows_loom_format = self._get_constraint_rows(
constraints, bdb, generator_id, population_id, modelnos, server,
inner_numsamples)
else:
conditioning_rows_loom_format = [
self._get_constraint_row(constraints, bdb, generator_id,
population_id, server)
]
mi_estimates = [
server._query_server.mutual_information(
target_set,
query_set,
entropys=None,
sample_count=loom.preql.SAMPLE_COUNT,
conditioning_row=conditioning_row_loom_format
).mean
for conditioning_row_loom_format in conditioning_rows_loom_format
]
# Output requires an iterable.
return [arithmetic_mean(mi_estimates)]
def predict_confidence(self,
bdb,
generator_id,
modelno,
colno,
rowid,
numsamples=None):
if not numsamples:
numsamples = 2
assert numsamples > 0
def _impute_categorical(sample):
counts = Counter(s[0] for s in sample)
mode_count = max(counts[v] for v in counts)
pred = iter(v for v in counts if counts[v] == mode_count).next()
conf = float(mode_count) / numsamples
return pred, conf
def _impute_numerical(sample):
pred = sum(s[0] for s in sample) / float(len(sample))
conf = 0 # XXX Punt confidence for now
return pred, conf
constraints = []
# If rowid is a hypothetical cell for cgpm (did not exist at the time
# of INITIALIZE), but exists in the base table (by INSERT INTO), then
# retrieve all values for rowid as the constraints.
exists = rowid < core.bayesdb_generator_fresh_row_id(bdb, generator_id)
max_cgpm_rowid = bdb.sql_execute(
'''
SELECT MAX(table_rowid) FROM bayesdb_cgpm_individual
WHERE generator_id = ?
''', (generator_id, )).fetchall()[0][0]
hypothetical = rowid > max_cgpm_rowid
if exists and hypothetical:
population_id = core.bayesdb_generator_population(
bdb, generator_id)
# Retrieve all other variables except colno, and ignore latents in
# generator_id, and place them in the constraints.
pop_names = core.bayesdb_variable_names(bdb, population_id, None)
avoid_name = core.bayesdb_variable_name(bdb, population_id, colno)
constraints_names = [n for n in pop_names if n != avoid_name]
# Obtain the row.
qt_names = str.join(',', map(sqlite3_quote_name,
constraints_names))
qt_table = sqlite3_quote_name(
core.bayesdb_population_table(bdb, population_id))
data = bdb.sql_execute(
'''
SELECT %s FROM %s WHERE oid = ?
''' % (
qt_names,
qt_table,
), (rowid, )).fetchall()[0]
# Build the constraints.
pop_nos = core.bayesdb_variable_numbers(bdb, population_id, None)
constraints_nos = [n for n in pop_nos if n != colno]
# import ipdb; ipdb.set_trace()
assert len(data) == len(constraints_nos)
constraints = [(rowid, c, v)
for c, v in zip(constraints_nos, data)
if (v is not None) and v]
# Retrieve the samples.
sample = self.simulate_joint(bdb, generator_id, [(rowid, colno)],
constraints, modelno, numsamples)
# Determine the imputation strategy (mode or mean).
stattype = core.bayesdb_variable_stattype(
bdb, core.bayesdb_generator_population(bdb, generator_id), colno)
if _is_categorical(stattype):
return _impute_categorical(sample)
else:
return _impute_numerical(sample)
def analyze_models(self,
bdb,
generator_id,
modelnos=None,
iterations=1,
max_seconds=None,
ckpt_iterations=None,
ckpt_seconds=None,
program=None):
assert modelnos is None
if ckpt_iterations is not None or ckpt_seconds is not None:
# XXX
raise NotImplementedError(
'CGpm analysis checkpoint not supported.')
if program is None:
program = []
population_id = core.bayesdb_generator_population(bdb, generator_id)
def retrieve_analyze_variables(ast):
# Transition all variables by default.
variables = None
# Exactly 1 VARIABLES or SKIP clause supported for simplicity.
seen_variables, seen_skip, seen_optimized = False, False, False
for clause in ast:
# Transition user specified variables only.
if isinstance(clause, cgpm_analyze.parse.Variables):
if seen_variables or seen_skip:
raise BQLError(
bdb,
'Only 1 VARIABLES or SKIP clause allowed in ANALYZE'
)
seen_variables = True
included = set()
unknown = set()
for var in clause.vars:
if not core.bayesdb_has_variable(
bdb, population_id, generator_id, var):
unknown.add(var)
included.add(var)
if unknown:
raise BQLError(
bdb, 'Unknown variables in ANALYZE: %r' %
(sorted(unknown), ))
variables = sorted(included)
# Transition all variables except user specified skip.
elif isinstance(clause, cgpm_analyze.parse.Skip):
if seen_variables or seen_skip:
raise BQLError(
bdb,
'Only 1 VARIABLES or SKIP clause allowed in ANALYZE'
)
seen_skip = True
excluded = set()
unknown = set()
for var in clause.vars:
if not core.bayesdb_has_variable(
bdb, population_id, generator_id, var):
unknown.add(var)
excluded.add(var)
if unknown:
raise BQLError(
bdb, 'Unknown variables in ANALYZE: %r' %
(sorted(unknown), ))
all_vars = core.bayesdb_variable_names(
bdb, population_id, generator_id)
variables = sorted(set(all_vars) - excluded)
elif isinstance(clause, cgpm_analyze.parse.Optimized):
seen_optimized = True
# Unknown/impossible clause.
else:
raise ValueError('Unknown clause in ANALYZE: %s.' % ast)
if variables is None:
variables = core.bayesdb_variable_names(
bdb, population_id, generator_id)
varnos = [
core.bayesdb_variable_number(bdb, population_id, generator_id,
v) for v in variables
]
# TODO Perform error checking if the OPTIMIZED clause is used.
# In particular, the variables in OPTIMIZED must correspond
# EXACTLY to the variables that are modeled by the CrossCat
# baseline. Avoided this check for now since the nature of a
# variable is not stored in the bdb. For now, just check the
# user did not include a VARIABLES clause.
if seen_optimized:
if seen_variables:
raise BQLError(bdb,
'OPTIMIZED incompatible with VARIABLES')
# TODO Check if varnos are exactly the CrossCat variables.
# raise BQLError(bdb,
# 'The OPTIMIZED phrase in ANALYZE must target all the '
# 'variables modeled by the baseline, only. '
# 'Use SKIP to explicitly ignore analysis of overriden '
# 'variables')
return varnos, seen_optimized
# Retrieve target variables and whether optimized.
analyze_ast = cgpm_analyze.parse.parse(program)
varnos, optimized = retrieve_analyze_variables(analyze_ast)
engine = self._engine(bdb, generator_id)
if optimized:
engine.transition_lovecat(N=iterations,
S=max_seconds,
multiprocess=self._ncpu)
else:
engine.transition(N=iterations,
S=max_seconds,
cols=varnos,
multiprocess=self._ncpu)
# Serialize the engine.
engine_json = json_dumps(engine.to_metadata())
# Update the engine.
bdb.sql_execute(
'''
UPDATE bayesdb_cgpm_generator
SET engine_json = :engine_json
WHERE generator_id = :generator_id
''', {
'generator_id': generator_id,
'engine_json': engine_json
})
def _retrieve_analyze_variables(bdb, generator_id, ast):
population_id = core.bayesdb_generator_population(bdb, generator_id)
# Transitions all variables by default.
variables = None
# Exactly 1 VARIABLES or SKIP clause supported for simplicity.
seen_variables, seen_skip, seen_optimized = False, False, False
for clause in ast:
# Transition user specified variables only.
if isinstance(clause, cgpm_analyze.parse.Variables):
if seen_variables or seen_skip:
raise BQLError(
bdb, 'Only 1 VARIABLES or SKIP clause allowed in ANALYZE')
seen_variables = True
included = set()
unknown = set()
for var in clause.vars:
if not core.bayesdb_has_variable(bdb, population_id,
generator_id, var):
unknown.add(var)
included.add(var)
if unknown:
raise BQLError(
bdb,
'Unknown variables in ANALYZE: %r' % (sorted(unknown), ))
variables = sorted(included)
# Transition all variables except user specified skip.
elif isinstance(clause, cgpm_analyze.parse.Skip):
if seen_variables or seen_skip:
raise BQLError(
bdb, 'Only 1 VARIABLES or SKIP clause allowed in ANALYZE')
seen_skip = True
excluded = set()
unknown = set()
for var in clause.vars:
if not core.bayesdb_has_variable(bdb, population_id,
generator_id, var):
unknown.add(var)
excluded.add(var)
if unknown:
raise BQLError(
bdb,
'Unknown variables in ANALYZE: %r' % (sorted(unknown), ))
all_vars = core.bayesdb_variable_names(bdb, population_id,
generator_id)
variables = sorted(set(all_vars) - excluded)
# OPTIMIZED is incompatible with any other clause.
elif isinstance(clause, cgpm_analyze.parse.Optimized):
seen_optimized = True
# Unknown/impossible clause.
else:
raise BQLError(bdb, 'Unknown clause in ANALYZE: %s.' % (ast, ))
# OPTIMIZED is incompatible with any other clause.
if seen_optimized:
if seen_variables or seen_skip:
raise BQLError(bdb, 'OPTIMIZED incompatible with other clauses.')
variable_numbers = [
core.bayesdb_variable_number(bdb, population_id, generator_id, v)
for v in variables
] if variables else None
return (variable_numbers, seen_optimized)
def simulate_joint(self,
bdb,
generator_id,
modelnos,
rowid,
targets,
constraints,
num_samples=1,
accuracy=None):
# Retrieve the population id.
population_id = bayesdb_generator_population(bdb, generator_id)
table = bayesdb_population_table(bdb, population_id)
# Prepare list of full constraints, potentially adding data from table.
constraints_full = constraints
# If rowid exist in base table, retrieve conditioning data.
# Conditioning values are fetched for any rowid that exists in the base
# table irrespective of whether the rowid is incorporated in the Loom
# model or whether it was added after creation.
if bayesdb_table_has_rowid(bdb, table, rowid):
# Fetch population column numbers and row values.
colnos = bayesdb_variable_numbers(bdb, population_id, generator_id)
rowvals = bayesdb_population_row_values(bdb, population_id, rowid)
observations = [(colno, rowval)
for colno, rowval in zip(colnos, rowvals)
if rowval is not None and colno not in targets]
# Raise error if a constraint overrides an observed cell.
colnos_constrained = [constraint[0] for constraint in constraints]
colnos_observed = [observation[0] for observation in observations]
if set.intersection(set(colnos_constrained), set(colnos_observed)):
raise BQLError(
bdb, 'Overlap between constraints and'
' target row in simulate.')
# Update the constraints.
constraints_full = constraints + observations
# Store mapping from target column name to column number and stattype.
target_colno_to_name = {
colno: bayesdb_variable_name(bdb, generator_id, None, colno)
for colno in targets
}
target_colno_to_stattype = {
colno: bayesdb_variable_stattype(bdb, population_id, None, colno)
for colno in targets
}
# Construct the CSV row for targets.
row_targets = {target_colno_to_name[colno]: '' for colno in targets}
row_constraints = {
bayesdb_variable_name(bdb, generator_id, None, colno): value
for colno, value in constraints_full
}
row = dict(
itertools.chain(row_targets.iteritems(),
row_constraints.iteritems()))
# Fetch the server.
server = self._get_preql_server(bdb, generator_id)
# Prepare the csv header and values.
csv_headers = map(str, row.iterkeys())
csv_values = map(str, row.itervalues())
# Prepare streams for the server.
outfile = StringIO()
writer = loom.preql.CsvWriter(outfile, returns=outfile.getvalue)
reader = iter([csv_headers] + [csv_values])
# Obtain the prediction.
server._predict(reader, num_samples, writer, False)
# Parse the CSV output.
output_csv = writer.result()
output_rows = output_csv.strip().split('\r\n')
# Extract the header of the CSV file.
header = output_rows[0].split(CSV_DELIMITER)
# Extract list of simulated rows. Each simulated row is represented
# as a dictionary mapping column name to its simulated value.
simulated_rows = [
dict(zip(header, row.split(CSV_DELIMITER)))
for row in output_rows[1:]
]
# Prepare the return list of simulated_rows.
def _extract_simulated_value(row, colno):
colname = target_colno_to_name[colno]
stattype = target_colno_to_stattype[colno]
value = row[colname]
return value if _is_nominal(stattype) else float(value)
# Return the list of samples.
return [[_extract_simulated_value(row, colno) for colno in targets]
for row in simulated_rows]
def _create_schema(bdb, generator_id, schema_ast, **kwargs):
# Get some parameters.
population_id = core.bayesdb_generator_population(bdb, generator_id)
table = core.bayesdb_population_table(bdb, population_id)
# State.
variables = []
variable_dist = {}
latents = {}
cgpm_composition = []
modelled = set()
default_modelled = set()
subsample = None
deferred_input = defaultdict(lambda: [])
deferred_output = dict()
# Error-reporting state.
duplicate = set()
unknown = set()
needed = set()
existing_latent = set()
must_exist = []
unknown_stattype = {}
# XXX Convert all Foreign.exposed lists to Latent clauses.
# Retrieve Foreign clauses with exposed variables.
foreign_clauses = [
c for c in schema_ast
if isinstance(c, cgpm_schema.parse.Foreign) and len(c.exposed) > 0
]
# Add the exposed variables to Foreign.outputs
# Note that this assumes if there are K exposed variables, then they are
# necessarily the last K outputs of the fc.outputs.
for fc in foreign_clauses:
fc.outputs.extend([e[0] for e in fc.exposed])
# Convert exposed entries into Latent clauses.
latent_vars = list(
itertools.chain.from_iterable(c.exposed for c in foreign_clauses))
latent_clauses = [cgpm_schema.parse.Latent(v, s) for (v, s) in latent_vars]
# Append the Latent clauses to the ast.
schema_ast.extend(latent_clauses)
# XXX Convert the baseline to a Foreign clause.
# Currently the baselines do not accept a schema, and will fail if
# `schema_ast` has any entries.
baseline = kwargs.get('baseline', None)
if baseline is not None and casefold(baseline.name) != 'crosscat':
if schema_ast:
raise BQLError(
bdb, 'Cannot accept schema with baseline: %s.' % schema_ast)
# Retrieve all variable names in the population
outputs = core.bayesdb_variable_names(bdb, population_id, None)
# Convert the LITERAL namedtuples to their raw values.
ps, vs = zip(*baseline.params)
vs_new = [v.value for v in vs]
params = zip(ps, vs_new)
# Create the clause.
clause = cgpm_schema.parse.Foreign(outputs, [], [], baseline.name,
params)
# And add append it to the schema_ast.
schema_ast.append(clause)
# Process each clause one by one.
for clause in schema_ast:
if isinstance(clause, cgpm_schema.parse.Basic):
# Basic Crosscat component model: one variable to be put
# into Crosscat views.
var = clause.var
dist = clause.dist
params = dict(clause.params) # XXX error checking
# Reject if the variable does not exist.
if not core.bayesdb_has_variable(bdb, population_id, None, var):
unknown.add(var)
continue
# Reject if the variable has already been modelled.
if var in modelled:
duplicate.add(var)
continue
# Reject if the variable is latent.
if core.bayesdb_has_latent(bdb, population_id, var):
existing_latent.add(var)
continue
# Get the column number.
colno = core.bayesdb_variable_number(bdb, population_id, None, var)
assert 0 <= colno
# Add it to the list and mark it modelled by default.
stattype = core.bayesdb_variable_stattype(bdb, population_id,
colno)
variables.append([var, stattype, dist, params])
assert var not in variable_dist
variable_dist[var] = (stattype, dist, params)
modelled.add(var)
default_modelled.add(var)
elif isinstance(clause, cgpm_schema.parse.Latent):
var = clause.name
stattype = clause.stattype
# Reject if the variable has already been modelled by the
# default model.
if var in default_modelled:
duplicate.add(var)
continue
# Reject if the variable even *exists* in the population
# at all yet.
if core.bayesdb_has_variable(bdb, population_id, None, var):
duplicate.add(var)
continue
# Reject if the variable is already latent, from another
# generator.
if core.bayesdb_has_latent(bdb, population_id, var):
existing_latent.add(var)
continue
# Reject if we've already processed it.
if var in latents:
duplicate.add(var)
continue
# Add it to the set of latent variables.
latents[var] = stattype
elif isinstance(clause, cgpm_schema.parse.Foreign):
# Foreign model: some set of output variables is to be
# modelled by foreign logic, possibly conditional on some
# set of input variables.
#
# Gather up the state for a cgpm_composition record, which
# we may have to do incrementally because it must refer to
# the distribution types of variables we may not have
# seen.
name = clause.name
outputs = clause.outputs
inputs = clause.inputs
output_stattypes = []
output_statargs = []
input_stattypes = []
input_statargs = []
distargs = {
'inputs': {
'stattypes': input_stattypes,
'statargs': input_statargs
},
'outputs': {
'stattypes': output_stattypes,
'statargs': output_statargs,
}
}
kwds = {'distargs': distargs}
kwds.update(clause.params)
# First make sure all the output variables exist and have
# not yet been modelled.
for var in outputs:
must_exist.append(var)
if var in modelled:
duplicate.add(var)
continue
modelled.add(var)
# Add the output statistical type and its parameters.
i = len(output_stattypes)
assert i == len(output_statargs)
output_stattypes.append(None)
output_statargs.append(None)
deferred_output[var] = (output_stattypes, output_statargs, i)
# Next make sure all the input variables exist, mark them
# needed, and record where to put their distribution type
# and parameters.
for var in inputs:
must_exist.append(var)
needed.add(var)
i = len(input_stattypes)
assert i == len(input_statargs)
input_stattypes.append(None)
input_statargs.append(None)
deferred_input[var].append(
(input_stattypes, input_statargs, i))
# Finally, add a cgpm_composition record.
cgpm_composition.append({
'name': name,
'inputs': inputs,
'outputs': outputs,
'kwds': kwds,
})
elif isinstance(clause, cgpm_schema.parse.Subsample):
if subsample is not None:
raise BQLError(bdb, 'Duplicate subsample: %r' % (clause.n, ))
subsample = clause.n
else:
raise BQLError(bdb, 'Unknown clause: %r' % (clause, ))
# Make sure all the outputs and inputs exist, either in the
# population or as latents in this generator.
for var in must_exist:
if core.bayesdb_has_variable(bdb, population_id, None, var):
continue
if var in latents:
continue
unknown.add(var)
# Raise an exception if there were duplicates or unknown
# variables.
if duplicate:
raise BQLError(bdb,
'Duplicate model variables: %r' % (sorted(duplicate), ))
if existing_latent:
raise BQLError(
bdb, 'Latent variables already defined: %r' %
(sorted(existing_latent), ))
if unknown:
raise BQLError(bdb,
'Unknown model variables: %r' % (sorted(unknown), ))
def default_dist(var, stattype):
stattype = casefold(stattype)
if stattype not in _DEFAULT_DIST:
if var in unknown_stattype:
assert unknown_stattype[var] == stattype
else:
unknown_stattype[var] = stattype
return None
dist, params = _DEFAULT_DIST[stattype](bdb, generator_id, var)
return dist, params
# Use the default distribution for any variables that remain to be
# modelled, excluding any that are latent or that have statistical
# types we don't know about.
for var in core.bayesdb_variable_names(bdb, population_id, None):
if var in modelled:
continue
colno = core.bayesdb_variable_number(bdb, population_id, None, var)
assert 0 <= colno
stattype = core.bayesdb_variable_stattype(bdb, population_id, colno)
distparams = default_dist(var, stattype)
if distparams is None:
continue
dist, params = distparams
variables.append([var, stattype, dist, params])
assert var not in variable_dist
variable_dist[var] = (stattype, dist, params)
modelled.add(var)
# Fill in the deferred_input statistical type assignments.
for var in sorted(deferred_input.iterkeys()):
# Check whether the variable is modelled. If not, skip -- we
# will fail later because this variable is guaranteed to also
# be in needed.
if var not in modelled:
assert var in needed
continue
# Determine (possibly fictitious) distribution and parameters.
if var in default_modelled:
# Manifest variable modelled by default Crosscat model.
assert var in variable_dist
stattype, dist, params = variable_dist[var]
else:
# Modelled by a foreign model. Assign a fictitious
# default distribution because the 27B/6 of CGPM requires
# this.
if var in latents:
# Latent variable modelled by a foreign model. Use
# the statistical type specified for it.
stattype = latents[var]
else:
# Manifest variable modelled by a foreign model. Use
# the statistical type in the population.
assert core.bayesdb_has_variable(bdb, population_id, None, var)
colno = core.bayesdb_variable_number(bdb, population_id, None,
var)
stattype = core.bayesdb_variable_stattype(
bdb, population_id, colno)
distparams = default_dist(var, stattype)
if distparams is None:
continue
dist, params = distparams
# Assign the distribution and parameters.
for cctypes, ccargs, i in deferred_input[var]:
assert cctypes[i] is None
assert ccargs[i] is None
cctypes[i] = dist
ccargs[i] = params
# Fill in the deferred_output statistical type assignments. The need to be
# in the form NUMERICAL or CATEGORICAL.
for var in deferred_output:
if var in latents:
# Latent variable modelled by a foreign model. Use
# the statistical type specified for it.
var_stattype = casefold(latents[var])
if var_stattype not in _DEFAULT_DIST:
if var in unknown_stattype:
assert unknown_stattype[var] == var_stattype
else:
unknown_stattype[var] = var_stattype
# XXX Cannot specify statargs for a latent variable. Trying to using
# default_dist might lookup the counts for unique values of the
# categorical in the base table causing a failure.
var_statargs = {}
else:
# Manifest variable modelled by a foreign model. Use
# the statistical type and arguments from the population.
assert core.bayesdb_has_variable(bdb, population_id, None, var)
colno = core.bayesdb_variable_number(bdb, population_id, None, var)
var_stattype = core.bayesdb_variable_stattype(
bdb, population_id, colno)
distparams = default_dist(var, var_stattype)
if distparams is None:
continue
_, var_statargs = distparams
stattypes, statargs, i = deferred_output[var]
assert stattypes[i] is None
assert statargs[i] is None
stattypes[i] = var_stattype
statargs[i] = var_statargs
if unknown_stattype:
raise BQLError(
bdb, 'Unknown statistical types for variables: %r' %
(sorted(unknown_stattype.iteritems(), )))
# If there remain any variables that we needed to model, because
# others are conditional on them, fail.
needed -= modelled
if needed:
raise BQLError(bdb, 'Unmodellable variables: %r' % (needed, ))
# Finally, create a CGPM schema.
return {
'variables': variables,
'cgpm_composition': cgpm_composition,
'subsample': subsample,
'latents': latents,
}
def _cmd_render_crosscat(self, query, sql=None, **kwargs):
'''Returns a rendering of the specified crosscat state
Usage: .render_crosscat [options] <generator> <modelno>.
Options:
--subsample=<n>
--width=<w>
--height=<c>
--rowlabels=<colname>
--progress=[True|False]
--yticklabeslize=<fontsize>
--xticklabeslize=<fontsize>
The allowable fontsize strings are:
xx-small, x-small, # small, medium, large, x-large, xx-large
'''
tokens = query.split()
if len(tokens) != 2:
self.write_stderr('Usage: .render_crosscat <generator> <modelno>')
return
generator = tokens[0]
modelno = int(tokens[1])
if not bayesdb_has_generator(self._bdb, None, generator):
self.write_stderr('No such generator: %s.' % (generator, ))
return
generator_id = bayesdb_get_generator(self._bdb, None, generator)
population_id = bayesdb_generator_population(self._bdb, generator_id)
backend = bayesdb_generator_backend(self._bdb, generator_id)
if backend.name() != 'cgpm':
self.write_stderr('.render_crosscat requires generator from the '
'cgpm backend')
return
engine = backend._engine(self._bdb, generator_id)
cursor = self._bdb.sql_execute(
'''
SELECT cgpm_modelno FROM bayesdb_cgpm_modelno
WHERE generator_id = ? AND modelno = ?
''', (
generator_id,
modelno,
))
cgpm_modelno = cursor_value(cursor, nullok=True)
if cgpm_modelno is None:
self.write_stderr('No such model number: %d.' % (modelno, ))
return
state = engine.get_state(cgpm_modelno)
row_names = None
row_index_column = kwargs.get('rowlabels', None)
if row_index_column is not None:
table_name = bayesdb_generator_table(self._bdb, generator_id)
qt = bql_quote_name(table_name)
qc = bql_quote_name(row_index_column)
cursor = self._bdb.sql_execute(
'''
SELECT %s FROM %s WHERE oid IN (
SELECT table_rowid FROM bayesdb_cgpm_individual
WHERE generator_id = ?
)
''' % (qc, qt), (generator_id, ))
row_names = [c[0] for c in cursor]
if 'progress' in kwargs:
sys.stdout.write('Creating figure...\n')
import cgpm.utils.render
if 'variable' not in kwargs:
# Plot the entire state.
col_names = [
bayesdb_variable_name(self._bdb, population_id, None, colno)
for colno in state.outputs
]
fig, _ax = cgpm.utils.render.viz_state(state,
col_names=col_names,
row_names=row_names,
**kwargs)
else:
# Plot the view of the requested variable.
varno = bayesdb_variable_number(self._bdb, population_id,
generator_id, kwargs['variable'])
view = state.view_for(varno)
col_names = [
bayesdb_variable_name(self._bdb, population_id, None, colno)
for colno in view.outputs[1:]
]
fig, _ax = cgpm.utils.render.viz_view(view,
col_names=col_names,
row_names=row_names,
**kwargs)
(width, height) = fig.get_size_inches()
if 'width' in kwargs:
width = float(kwargs['width'])
fig.set_size_inches(width, height)
if 'height' in kwargs:
height = float(kwargs['height'])
fig.set_size_inches(width, height)
if 'progress' in kwargs:
sys.stdout.write('Rendering figure...\n')
def _get_ordered_column_labels(self, bdb, generator_id):
population_id = bayesdb_generator_population(bdb, generator_id)
return [
bayesdb_variable_name(bdb, population_id, None, colno)
for colno in self._get_order(bdb, generator_id)
]
def execute_phrase(bdb, phrase, bindings=()):
"""Execute the BQL AST phrase `phrase` and return a cursor of results."""
if isinstance(phrase, ast.Parametrized):
n_numpar = phrase.n_numpar
nampar_map = phrase.nampar_map
phrase = phrase.phrase
assert 0 < n_numpar
else:
n_numpar = 0
nampar_map = None
# Ignore extraneous bindings. XXX Bad idea?
if ast.is_query(phrase):
# Compile the query in the transaction in case we need to
# execute subqueries to determine column lists. Compiling is
# a quick tree descent, so this should be fast.
out = compiler.Output(n_numpar, nampar_map, bindings)
with bdb.savepoint():
compiler.compile_query(bdb, phrase, out)
winders, unwinders = out.getwindings()
return execute_wound(bdb, winders, unwinders, out.getvalue(),
out.getbindings())
if isinstance(phrase, ast.Begin):
txn.bayesdb_begin_transaction(bdb)
return empty_cursor(bdb)
if isinstance(phrase, ast.Rollback):
txn.bayesdb_rollback_transaction(bdb)
return empty_cursor(bdb)
if isinstance(phrase, ast.Commit):
txn.bayesdb_commit_transaction(bdb)
return empty_cursor(bdb)
if isinstance(phrase, ast.CreateTabAs):
assert ast.is_query(phrase.query)
with bdb.savepoint():
if core.bayesdb_has_table(bdb, phrase.name):
if phrase.ifnotexists:
return empty_cursor(bdb)
else:
raise BQLError(
bdb, 'Name already defined as table: %s' %
(repr(phrase.name), ))
out = compiler.Output(n_numpar, nampar_map, bindings)
qt = sqlite3_quote_name(phrase.name)
temp = 'TEMP ' if phrase.temp else ''
ifnotexists = 'IF NOT EXISTS ' if phrase.ifnotexists else ''
out.write('CREATE %sTABLE %s%s AS ' % (temp, ifnotexists, qt))
compiler.compile_query(bdb, phrase.query, out)
winders, unwinders = out.getwindings()
with compiler.bayesdb_wind(bdb, winders, unwinders):
bdb.sql_execute(out.getvalue(), out.getbindings())
return empty_cursor(bdb)
if isinstance(phrase, ast.CreateTabCsv):
with bdb.savepoint():
table_exists = core.bayesdb_has_table(bdb, phrase.name)
if table_exists:
if phrase.ifnotexists:
return empty_cursor(bdb)
else:
raise BQLError(
bdb,
'Table already exists: %s' % (repr(phrase.name), ))
bayesdb_read_csv_file(bdb,
phrase.name,
phrase.csv,
header=True,
create=True)
return empty_cursor(bdb)
if isinstance(phrase, ast.DropTab):
with bdb.savepoint():
sql = 'SELECT COUNT(*) FROM bayesdb_population WHERE tabname = ?'
cursor = bdb.sql_execute(sql, (phrase.name, ))
if 0 < cursor_value(cursor):
raise BQLError(
bdb, 'Table still in use by populations: %s' %
(repr(phrase.name), ))
bdb.sql_execute('DELETE FROM bayesdb_column WHERE tabname = ?',
(phrase.name, ))
ifexists = 'IF EXISTS ' if phrase.ifexists else ''
qt = sqlite3_quote_name(phrase.name)
return bdb.sql_execute('DROP TABLE %s%s' % (ifexists, qt))
if isinstance(phrase, ast.AlterTab):
with bdb.savepoint():
table = phrase.table
if not core.bayesdb_has_table(bdb, table):
raise BQLError(bdb, 'No such table: %s' % (repr(table), ))
for cmd in phrase.commands:
if isinstance(cmd, ast.AlterTabRenameTab):
# If the names differ only in case, we have to do
# some extra work because SQLite will reject the
# table rename. Note that we may even have table
# == cmd.name here, but if the stored table name
# differs in case from cmd.name, we want to update
# it anyway.
if casefold(table) == casefold(cmd.name):
# Go via a temporary table.
temp = table + '_temp'
while core.bayesdb_has_table(bdb, temp):
temp += '_temp'
rename_table(bdb, table, temp)
rename_table(bdb, temp, cmd.name)
else:
# Make sure nothing else has this name and
# rename it.
if core.bayesdb_has_table(bdb, cmd.name):
raise BQLError(
bdb, 'Name already defined as table: %s' %
(repr(cmd.name), ))
rename_table(bdb, table, cmd.name)
# If table has implicit population, rename it too.
if core.bayesdb_table_has_implicit_population(
bdb, cmd.name):
populations = \
core.bayesdb_table_populations(bdb, cmd.name)
assert len(populations) == 1
population_name = core.bayesdb_population_name(
bdb, populations[0])
qt = sqlite3_quote_name(cmd.name)
qp = sqlite3_quote_name(population_name)
bdb.execute('ALTER POPULATION %s RENAME TO %s' %
(qp, qt))
# Remember the new name for subsequent commands.
table = cmd.name
elif isinstance(cmd, ast.AlterTabRenameCol):
# XXX Need to deal with this in the compiler.
raise NotImplementedError('Renaming columns'
' not yet implemented.')
# Make sure the old name exist and the new name does not.
old_folded = casefold(cmd.old)
new_folded = casefold(cmd.new)
if old_folded != new_folded:
if not core.bayesdb_table_has_column(
bdb, table, cmd.old):
raise BQLError(
bdb, 'No such column in table %s'
': %s' % (repr(table), repr(cmd.old)))
if core.bayesdb_table_has_column(bdb, table, cmd.new):
raise BQLError(
bdb, 'Column already exists'
' in table %s: %s' %
(repr(table), repr(cmd.new)))
# Update bayesdb_column. Everything else refers
# to columns by (tabname, colno) pairs rather than
# by names.
update_column_sql = '''
UPDATE bayesdb_column SET name = :new
WHERE tabname = :table AND name = :old
'''
total_changes = bdb._sqlite3.totalchanges()
bdb.sql_execute(update_column_sql, {
'table': table,
'old': cmd.old,
'new': cmd.new,
})
assert bdb._sqlite3.totalchanges() - total_changes == 1
# ...except backends may have the (case-folded) name cached.
if old_folded != new_folded:
populations_sql = '''
SELECT id FROM bayesdb_population WHERE tabname = ?
'''
cursor = bdb.sql_execute(populations_sql, (table, ))
generators = [
core.bayesdb_population_generators(
bdb, population_id)
for (population_id, ) in cursor
]
for generator_id in set(generators):
backend = core.bayesdb_generator_backend(
bdb, generator_id)
backend.rename_column(bdb, generator_id,
old_folded, new_folded)
else:
assert False, 'Invalid alter table command: %s' % \
(cmd,)
return empty_cursor(bdb)
if isinstance(phrase, ast.GuessSchema):
if not core.bayesdb_has_table(bdb, phrase.table):
raise BQLError(bdb, 'No such table : %s' % phrase.table)
out = compiler.Output(0, {}, {})
with bdb.savepoint():
qt = sqlite3_quote_name(phrase.table)
temptable = bdb.temp_table_name()
qtt = sqlite3_quote_name(temptable)
cursor = bdb.sql_execute('SELECT * FROM %s' % (qt, ))
column_names = [d[0] for d in cursor.description]
rows = cursor.fetchall()
stattypes = bayesdb_guess_stattypes(column_names, rows)
distinct_value_counts = [
len(set([row[i] for row in rows]))
for i in range(len(column_names))
]
out.winder(
'''
CREATE TEMP TABLE %s (
column TEXT,
stattype TEXT,
num_distinct INTEGER,
reason TEXT
)
''' % (qtt, ), ())
for cn, st, ct in zip(column_names, stattypes,
distinct_value_counts):
out.winder(
'''
INSERT INTO %s VALUES (?, ?, ?, ?)
''' % (qtt), (cn, st[0], ct, st[1]))
out.write('SELECT * FROM %s' % (qtt, ))
out.unwinder('DROP TABLE %s' % (qtt, ), ())
winders, unwinders = out.getwindings()
return execute_wound(bdb, winders, unwinders, out.getvalue(),
out.getbindings())
if isinstance(phrase, ast.CreatePop):
with bdb.savepoint():
_create_population(bdb, phrase)
return empty_cursor(bdb)
if isinstance(phrase, ast.DropPop):
with bdb.savepoint():
if not core.bayesdb_has_population(bdb, phrase.name):
if phrase.ifexists:
return empty_cursor(bdb)
raise BQLError(bdb, 'No such population: %r' % (phrase.name, ))
population_id = core.bayesdb_get_population(bdb, phrase.name)
generator_ids = core.bayesdb_population_generators(
bdb, population_id)
if generator_ids:
generators = [
core.bayesdb_generator_name(bdb, gid)
for gid in generator_ids
]
raise BQLError(
bdb, 'Population %r still has generators: %r' %
(phrase.name, generators))
# XXX helpful error checking if generators still exist
# XXX check change counts
bdb.sql_execute(
'''
DELETE FROM bayesdb_variable WHERE population_id = ?
''', (population_id, ))
bdb.sql_execute(
'''
DELETE FROM bayesdb_population WHERE id = ?
''', (population_id, ))
return empty_cursor(bdb)
if isinstance(phrase, ast.AlterPop):
with bdb.savepoint():
population = phrase.population
if not core.bayesdb_has_population(bdb, population):
raise BQLError(bdb,
'No such population: %s' % (repr(population), ))
population_id = core.bayesdb_get_population(bdb, population)
for cmd in phrase.commands:
if isinstance(cmd, ast.AlterPopRenamePop):
table = core.bayesdb_population_table(bdb, population_id)
# Prevent renaming of implicit population directly, unless
# being called by ast.AlterTabRenameTab in which case the
# table name and population name will not be matching.
if core.bayesdb_population_is_implicit(bdb, population_id) \
and casefold(population) == casefold(table):
raise BQLError(
bdb, 'Cannot rename implicit'
'population %s; rename base table instead' %
(population, ))
# Make sure nothing else has this name.
if casefold(population) != casefold(cmd.name):
if core.bayesdb_has_population(bdb, cmd.name):
raise BQLError(
bdb, 'Name already defined as population'
': %s' % (repr(cmd.name), ))
# Update bayesdb_population. Everything else
# refers to it by id.
update_generator_sql = '''
UPDATE bayesdb_population SET name = ? WHERE id = ?
'''
total_changes = bdb._sqlite3.totalchanges()
bdb.sql_execute(update_generator_sql,
(cmd.name, population_id))
assert bdb._sqlite3.totalchanges() - total_changes == 1
# If population has implicit generator, rename it too.
if core.bayesdb_population_has_implicit_generator(
bdb, population_id):
generators = core.bayesdb_population_generators(
bdb, population_id)
assert len(generators) == 1
generator_name = core.bayesdb_generator_name(
bdb, generators[0])
qp = sqlite3_quote_name(cmd.name)
qg = sqlite3_quote_name(generator_name)
bdb.execute('ALTER GENERATOR %s RENAME TO %s' % (
qg,
qp,
))
# Remember the new name for subsequent commands.
population = cmd.name
elif isinstance(cmd, ast.AlterPopAddVar):
# Ensure column exists in base table.
table = core.bayesdb_population_table(bdb, population_id)
if not core.bayesdb_table_has_column(bdb, table, cmd.name):
raise BQLError(
bdb,
'No such variable in base table: %s' % (cmd.name))
# Ensure variable not already in population.
if core.bayesdb_has_variable(bdb, population_id, None,
cmd.name):
raise BQLError(
bdb,
'Variable already in population: %s' % (cmd.name))
# Ensure there is at least observation in the column.
qt = sqlite3_quote_name(table)
qc = sqlite3_quote_name(cmd.name)
cursor = bdb.sql_execute(
'SELECT COUNT(*) FROM %s WHERE %s IS NOT NULL' %
(qt, qc))
if cursor_value(cursor) == 0:
raise BQLError(
bdb, 'Cannot add variable without any values: %s' %
(cmd.name))
# If stattype is None, guess.
if cmd.stattype is None:
cursor = bdb.sql_execute('SELECT %s FROM %s' %
(qc, qt))
rows = cursor.fetchall()
[stattype,
reason] = bayesdb_guess_stattypes([cmd.name], rows)[0]
# Fail if trying to model a key.
if stattype == 'key':
raise BQLError(
bdb, 'Values in column %s appear to be keys.' %
(cmd.name, ))
# Fail if cannot determine a stattype.
elif stattype == 'ignore':
raise BQLError(
bdb, 'Failed to determine a stattype for %s, '
'please specify one manually.' % (cmd.name, ))
# If user specified stattype, ensure it exists.
elif not core.bayesdb_has_stattype(bdb, cmd.stattype):
raise BQLError(bdb,
'Invalid stattype: %s' % (cmd.stattype))
else:
stattype = cmd.stattype
# Check that strings are not being modeled as numerical.
if stattype == 'numerical' \
and _column_contains_string(bdb, table, cmd.name):
raise BQLError(
bdb,
'Numerical column contains string values: %r ' %
(qc, ))
with bdb.savepoint():
# Add the variable to the population.
core.bayesdb_add_variable(bdb, population_id, cmd.name,
stattype)
colno = core.bayesdb_variable_number(
bdb, population_id, None, cmd.name)
# Add the variable to each (initialized) generator in
# the population.
generator_ids = filter(
lambda g: core.bayesdb_generator_modelnos(bdb, g),
core.bayesdb_population_generators(
bdb, population_id),
)
for generator_id in generator_ids:
backend = core.bayesdb_generator_backend(
bdb, generator_id)
backend.add_column(bdb, generator_id, colno)
elif isinstance(cmd, ast.AlterPopStatType):
# Check the no generators are defined for this population.
generators = core.bayesdb_population_generators(
bdb, population_id)
if generators:
raise BQLError(
bdb,
'Cannot update statistical types for population '
'%s, it has generators: %s' % (
repr(population),
repr(generators),
))
# Check all the variables are in the population.
unknown = [
c for c in cmd.names if not core.bayesdb_has_variable(
bdb, population_id, None, c)
]
if unknown:
raise BQLError(
bdb, 'No such variables in population: %s' %
(repr(unknown)))
# Check the statistical type is valid.
if not core.bayesdb_has_stattype(bdb, cmd.stattype):
raise BQLError(
bdb, 'Invalid statistical type: %r' %
(repr(cmd.stattype), ))
# Check that strings are not being modeled as numerical.
if cmd.stattype == 'numerical':
table = core.bayesdb_population_table(
bdb, population_id)
numerical_string_vars = [
col for col in cmd.names
if _column_contains_string(bdb, table, col)
]
if numerical_string_vars:
raise BQLError(
bdb, 'Columns with string values modeled as '
'numerical: %r' % (numerical_string_vars, ))
# Perform the stattype update.
colnos = [
core.bayesdb_variable_number(bdb, population_id, None,
c) for c in cmd.names
]
qcolnos = ','.join('%d' % (colno, ) for colno in colnos)
update_stattype_sql = '''
UPDATE bayesdb_variable SET stattype = ?
WHERE population_id = ? AND colno IN (%s)
''' % (qcolnos, )
bdb.sql_execute(update_stattype_sql, (
casefold(cmd.stattype),
population_id,
))
else:
assert False, 'Invalid ALTER POPULATION command: %s' % \
(repr(cmd),)
return empty_cursor(bdb)
if isinstance(phrase, ast.CreateGen):
# Find the population.
if not core.bayesdb_has_population(bdb, phrase.population):
raise BQLError(bdb,
'No such population: %r' % (phrase.population, ))
population_id = core.bayesdb_get_population(bdb, phrase.population)
# Find the backend, or use the default.
backend_name = phrase.backend
if phrase.backend is None:
backend_name = 'cgpm'
if backend_name not in bdb.backends:
raise BQLError(bdb, 'No such backend: %s' % (repr(backend_name), ))
backend = bdb.backends[backend_name]
# Retrieve the (possibility implicit) generator name.
generator_name = phrase.name or phrase.population
implicit = 1 if phrase.name is None else 0
with bdb.savepoint():
if core.bayesdb_has_generator(bdb, population_id, generator_name):
if not phrase.ifnotexists:
raise BQLError(
bdb, 'Name already defined as generator: %s' %
(repr(generator_name), ))
else:
# Insert a record into bayesdb_generator and get the
# assigned id.
bdb.sql_execute(
'''
INSERT INTO bayesdb_generator
(name, population_id, backend, implicit)
VALUES (?, ?, ?, ?)
''', (generator_name, population_id, backend.name(), implicit))
generator_id = core.bayesdb_get_generator(
bdb, population_id, generator_name)
# Do any backend-specific initialization.
backend.create_generator(bdb, generator_id, phrase.schema)
# All done. Nothing to return.
return empty_cursor(bdb)
if isinstance(phrase, ast.DropGen):
with bdb.savepoint():
if not core.bayesdb_has_generator(bdb, None, phrase.name):
if phrase.ifexists:
return empty_cursor(bdb)
raise BQLError(bdb,
'No such generator: %s' % (repr(phrase.name), ))
generator_id = core.bayesdb_get_generator(bdb, None, phrase.name)
backend = core.bayesdb_generator_backend(bdb, generator_id)
# Backend-specific destruction.
backend.drop_generator(bdb, generator_id)
# Drop latent variables, models, and, finally, generator.
drop_columns_sql = '''
DELETE FROM bayesdb_variable WHERE generator_id = ?
'''
bdb.sql_execute(drop_columns_sql, (generator_id, ))
drop_model_sql = '''
DELETE FROM bayesdb_generator_model WHERE generator_id = ?
'''
bdb.sql_execute(drop_model_sql, (generator_id, ))
drop_generator_sql = '''
DELETE FROM bayesdb_generator WHERE id = ?
'''
bdb.sql_execute(drop_generator_sql, (generator_id, ))
return empty_cursor(bdb)
if isinstance(phrase, ast.AlterGen):
with bdb.savepoint():
generator = phrase.generator
if not core.bayesdb_has_generator(bdb, None, generator):
raise BQLError(bdb,
'No such generator: %s' % (repr(generator), ))
generator_id = core.bayesdb_get_generator(bdb, None, generator)
cmds_generic = []
for cmd in phrase.commands:
if isinstance(cmd, ast.AlterGenRenameGen):
population_id = core.bayesdb_generator_population(
bdb, generator_id)
population = core.bayesdb_population_name(
bdb, population_id)
# Prevent renaming of implicit generator directly, unless
# being called by ast.AlterPopRenamePop in which case the
# population name and generator name will not be matching.
if core.bayesdb_population_is_implicit(bdb, generator_id) \
and casefold(generator) == casefold(population):
raise BQLError(
bdb, 'Cannot rename implicit '
'generator; rename base population instead')
# Disable modelnos with AlterGenRenameGen.
if phrase.modelnos is not None:
raise BQLError(bdb, 'Cannot specify models for RENAME')
# Make sure nothing else has this name.
if casefold(generator) != casefold(cmd.name):
if core.bayesdb_has_generator(bdb, None, cmd.name):
raise BQLError(
bdb, 'Name already defined'
' as generator: %s' % (repr(cmd.name), ))
# Update bayesdb_generator. Everything else
# refers to it by id.
update_generator_sql = '''
UPDATE bayesdb_generator SET name = ? WHERE id = ?
'''
total_changes = bdb._sqlite3.totalchanges()
bdb.sql_execute(update_generator_sql,
(cmd.name, generator_id))
assert bdb._sqlite3.totalchanges() - total_changes == 1
# Remember the new name for subsequent commands.
generator = cmd.name
elif isinstance(cmd, ast.AlterGenGeneric):
cmds_generic.append(cmd.command)
else:
assert False, 'Invalid ALTER GENERATOR command: %s' % \
(repr(cmd),)
if cmds_generic:
modelnos = phrase.modelnos
modelnos_invalid = None if modelnos is None else [
modelno for modelno in modelnos
if not core.bayesdb_generator_has_model(
bdb, generator_id, modelno)
]
if modelnos_invalid:
raise BQLError(
bdb, 'No such models in generator %s: %s' %
(repr(phrase.generator), repr(modelnos)))
# Call generic alternations on the backend.
backend = core.bayesdb_generator_backend(bdb, generator_id)
backend.alter(bdb, generator_id, modelnos, cmds_generic)
return empty_cursor(bdb)
if isinstance(phrase, ast.InitModels):
if not core.bayesdb_has_generator(bdb, None, phrase.generator):
raise BQLError(bdb, 'No such generator: %s' % (phrase.generator, ))
generator_id = core.bayesdb_get_generator(bdb, None, phrase.generator)
modelnos = range(phrase.nmodels)
with bdb.savepoint():
# Find the model numbers. Omit existing ones for
# ifnotexists; reject existing ones otherwise.
if phrase.ifnotexists:
modelnos = set(modelno for modelno in modelnos
if not core.bayesdb_generator_has_model(
bdb, generator_id, modelno))
else:
existing = set(modelno for modelno in modelnos
if core.bayesdb_generator_has_model(
bdb, generator_id, modelno))
if 0 < len(existing):
raise BQLError(
bdb, 'Generator %s already has models: %s' %
(repr(phrase.generator), sorted(existing)))
# Stop now if there's nothing to initialize.
if len(modelnos) == 0:
return
# Create the bayesdb_generator_model records.
modelnos = sorted(modelnos)
insert_model_sql = '''
INSERT INTO bayesdb_generator_model
(generator_id, modelno)
VALUES (:generator_id, :modelno)
'''
for modelno in modelnos:
bdb.sql_execute(insert_model_sql, {
'generator_id': generator_id,
'modelno': modelno,
})
# Do backend-specific initialization.
backend = core.bayesdb_generator_backend(bdb, generator_id)
backend.initialize_models(bdb, generator_id, modelnos)
return empty_cursor(bdb)
if isinstance(phrase, ast.AnalyzeModels):
# WARNING: It is the backend's responsibility to work in a
# transaction.
#
# WARNING: It is the backend's responsibility to update the
# iteration count in bayesdb_generator_model records.
#
# We do this so that the backend can save incremental
# progress in case of ^C in the middle.
#
# XXX Put these warning somewhere more appropriate.
if not core.bayesdb_has_generator(bdb, None, phrase.generator):
raise BQLError(bdb, 'No such generator: %s' % (phrase.generator, ))
generator_id = core.bayesdb_get_generator(bdb, None, phrase.generator)
backend = core.bayesdb_generator_backend(bdb, generator_id)
# XXX Should allow parameters for iterations and ckpt/iter.
backend.analyze_models(bdb,
generator_id,
modelnos=phrase.modelnos,
iterations=phrase.iterations,
max_seconds=phrase.seconds,
ckpt_iterations=phrase.ckpt_iterations,
ckpt_seconds=phrase.ckpt_seconds,
program=phrase.program)
return empty_cursor(bdb)
if isinstance(phrase, ast.DropModels):
with bdb.savepoint():
generator_id = core.bayesdb_get_generator(bdb, None,
phrase.generator)
backend = core.bayesdb_generator_backend(bdb, generator_id)
modelnos = None
if phrase.modelnos is not None:
lookup_model_sql = '''
SELECT COUNT(*) FROM bayesdb_generator_model
WHERE generator_id = :generator_id
AND modelno = :modelno
'''
modelnos = sorted(list(phrase.modelnos))
for modelno in modelnos:
cursor = bdb.sql_execute(lookup_model_sql, {
'generator_id': generator_id,
'modelno': modelno,
})
if cursor_value(cursor) == 0:
raise BQLError(
bdb, 'No such model'
' in generator %s: %s' %
(repr(phrase.generator), repr(modelno)))
backend.drop_models(bdb, generator_id, modelnos=modelnos)
if modelnos is None:
drop_models_sql = '''
DELETE FROM bayesdb_generator_model WHERE generator_id = ?
'''
bdb.sql_execute(drop_models_sql, (generator_id, ))
else:
drop_model_sql = '''
DELETE FROM bayesdb_generator_model
WHERE generator_id = :generator_id
AND modelno = :modelno
'''
for modelno in modelnos:
bdb.sql_execute(drop_model_sql, {
'generator_id': generator_id,
'modelno': modelno,
})
return empty_cursor(bdb)
if isinstance(phrase, ast.Regress):
# Retrieve the population.
if not core.bayesdb_has_population(bdb, phrase.population):
raise BQLError(bdb,
'No such population: %r' % (phrase.population, ))
population_id = core.bayesdb_get_population(bdb, phrase.population)
# Retrieve the generator
generator_id = None
if phrase.generator:
if not core.bayesdb_has_generator(bdb, population_id,
phrase.generator):
raise BQLError(bdb,
'No such generator: %r' % (phrase.generator, ))
generator_id = core.bayesdb_get_generator(bdb, population_id,
phrase.generator)
# Retrieve the target variable.
if not core.bayesdb_has_variable(bdb, population_id, None,
phrase.target):
raise BQLError(bdb, 'No such variable: %r' % (phrase.target, ))
colno_target = core.bayesdb_variable_number(bdb, population_id, None,
phrase.target)
stattype = core.bayesdb_variable_stattype(bdb, population_id,
generator_id, colno_target)
if stattype != 'numerical':
raise BQLError(
bdb,
'Target variable is not numerical: %r' % (phrase.target, ))
# Build the given variables.
if any(isinstance(col, ast.SelColAll) for col in phrase.givens):
# Using * is not allowed to be mixed with other variables.
if len(phrase.givens) > 1:
raise BQLError(bdb, 'Cannot use (*) with other givens.')
colno_givens = core.bayesdb_variable_numbers(
bdb, population_id, None)
else:
if any(isinstance(col, ast.SelColSub) for col in phrase.givens):
# Subexpression needs special compiling.
out = compiler.Output(n_numpar, nampar_map, bindings)
bql_compiler = compiler.BQLCompiler_None()
givens = compiler.expand_select_columns(
bdb, phrase.givens, True, bql_compiler, out)
else:
givens = phrase.givens
colno_givens = [
core.bayesdb_variable_number(bdb, population_id, None,
given.expression.column)
for given in givens
]
# Build the arguments to bqlfn.bayesdb_simulate.
colno_givens_unique = set(colno for colno in colno_givens
if colno != colno_target)
if len(colno_givens_unique) == 0:
raise BQLError(bdb, 'No matching given columns.')
constraints = []
colnos = [colno_target] + list(colno_givens_unique)
nsamp = 100 if phrase.nsamp is None else phrase.nsamp.value.value
modelnos = None if phrase.modelnos is None else str(phrase.modelnos)
rows = bqlfn.bayesdb_simulate(bdb,
population_id,
generator_id,
modelnos,
constraints,
colnos,
numpredictions=nsamp)
# Retrieve the stattypes.
stattypes = [
core.bayesdb_variable_stattype(bdb, population_id, generator_id,
colno_given)
for colno_given in colno_givens_unique
]
# Separate the target values from the given values.
target_values = [row[0] for row in rows]
given_values = [row[1:] for row in rows]
given_names = [
core.bayesdb_variable_name(bdb, population_id, generator_id, given)
for given in colno_givens_unique
]
# Compute the coefficients. The import to regress_ols is here since the
# feature depends on pandas + sklearn, so avoid module-wide import.
from bayeslite.regress import regress_ols
coefficients = regress_ols(target_values, given_values, given_names,
stattypes)
# Store the results in a winder.
temptable = bdb.temp_table_name()
qtt = sqlite3_quote_name(temptable)
out = compiler.Output(0, {}, {})
out.winder(
'''
CREATE TEMP TABLE %s (variable TEXT, coefficient REAL);
''' % (qtt, ), ())
for variable, coef in coefficients:
out.winder(
'''
INSERT INTO %s VALUES (?, ?)
''' % (qtt), (
variable,
coef,
))
out.write('SELECT * FROM %s ORDER BY variable' % (qtt, ))
out.unwinder('DROP TABLE %s' % (qtt, ), ())
winders, unwinders = out.getwindings()
return execute_wound(bdb, winders, unwinders, out.getvalue(),
out.getbindings())
assert False # XXX
def simulate_joint(self, bdb, generator_id, modelnos, rowid, targets,
constraints, num_samples=1, accuracy=None):
# Retrieve the population id.
population_id = bayesdb_generator_population(bdb, generator_id)
table = bayesdb_population_table(bdb, population_id)
# Prepare list of full constraints, potentially adding data from table.
constraints_full = constraints
# If rowid exist in base table, retrieve conditioning data.
# Conditioning values are fetched for any rowid that exists in the base
# table irrespective of whether the rowid is incorporated in the Loom
# model or whether it was added after creation.
if bayesdb_table_has_rowid(bdb, table, rowid):
# Fetch population column numbers and row values.
colnos = bayesdb_variable_numbers(bdb, population_id, generator_id)
rowvals = bayesdb_population_row_values(bdb, population_id, rowid)
observations = [
(colno, rowval)
for colno, rowval in zip(colnos, rowvals)
if rowval is not None and colno not in targets
]
# Raise error if a constraint overrides an observed cell.
colnos_constrained = [constraint[0] for constraint in constraints]
colnos_observed = [observation[0] for observation in observations]
if set.intersection(set(colnos_constrained), set(colnos_observed)):
raise BQLError(bdb, 'Overlap between constraints and'
' target row in simulate.')
# Update the constraints.
constraints_full = constraints + observations
# Store mapping from target column name to column number and stattype.
target_colno_to_name = {
colno: bayesdb_variable_name(bdb, generator_id, None, colno)
for colno in targets
}
target_colno_to_stattype = {
colno: bayesdb_variable_stattype(bdb, population_id, None, colno)
for colno in targets
}
# Construct the CSV row for targets.
row_targets = {target_colno_to_name[colno] : '' for colno in targets}
row_constraints = {
bayesdb_variable_name(bdb, generator_id, None, colno) : value
for colno, value in constraints_full
}
row = dict(itertools.chain(
row_targets.iteritems(), row_constraints.iteritems()))
# Fetch the server.
server = self._get_preql_server(bdb, generator_id)
# Prepare the csv header and values.
csv_headers = map(str, row.iterkeys())
csv_values = map(str, row.itervalues())
# Prepare streams for the server.
outfile = StringIO()
writer = loom.preql.CsvWriter(outfile, returns=outfile.getvalue)
reader = iter([csv_headers]+[csv_values])
# Obtain the prediction.
server._predict(reader, num_samples, writer, False)
# Parse the CSV output.
output_csv = writer.result()
output_rows = output_csv.strip().split('\r\n')
# Extract the header of the CSV file.
header = output_rows[0].split(CSV_DELIMITER)
# Extract list of simulated rows. Each simulated row is represented
# as a dictionary mapping column name to its simulated value.
simulated_rows = [
dict(zip(header, row.split(CSV_DELIMITER)))
for row in output_rows[1:]
]
# Prepare the return list of simulated_rows.
def _extract_simulated_value(row, colno):
colname = target_colno_to_name[colno]
stattype = target_colno_to_stattype[colno]
value = row[colname]
return value if _is_nominal(stattype) else float(value)
# Return the list of samples.
return [
[_extract_simulated_value(row, colno) for colno in targets]
for row in simulated_rows
]
def execute_phrase(bdb, phrase, bindings=()):
"""Execute the BQL AST phrase `phrase` and return a cursor of results."""
if isinstance(phrase, ast.Parametrized):
n_numpar = phrase.n_numpar
nampar_map = phrase.nampar_map
phrase = phrase.phrase
assert 0 < n_numpar
else:
n_numpar = 0
nampar_map = None
# Ignore extraneous bindings. XXX Bad idea?
if ast.is_query(phrase):
# Compile the query in the transaction in case we need to
# execute subqueries to determine column lists. Compiling is
# a quick tree descent, so this should be fast.
out = compiler.Output(n_numpar, nampar_map, bindings)
with bdb.savepoint():
compiler.compile_query(bdb, phrase, out)
winders, unwinders = out.getwindings()
return execute_wound(bdb, winders, unwinders, out.getvalue(),
out.getbindings())
if isinstance(phrase, ast.Begin):
txn.bayesdb_begin_transaction(bdb)
return empty_cursor(bdb)
if isinstance(phrase, ast.Rollback):
txn.bayesdb_rollback_transaction(bdb)
return empty_cursor(bdb)
if isinstance(phrase, ast.Commit):
txn.bayesdb_commit_transaction(bdb)
return empty_cursor(bdb)
if isinstance(phrase, ast.CreateTabAs):
assert ast.is_query(phrase.query)
with bdb.savepoint():
if core.bayesdb_has_table(bdb, phrase.name):
if phrase.ifnotexists:
return empty_cursor(bdb)
else:
raise BQLError(bdb,
'Name already defined as table: %s' %
(repr(phrase.name),))
out = compiler.Output(n_numpar, nampar_map, bindings)
qt = sqlite3_quote_name(phrase.name)
temp = 'TEMP ' if phrase.temp else ''
ifnotexists = 'IF NOT EXISTS ' if phrase.ifnotexists else ''
out.write('CREATE %sTABLE %s%s AS ' % (temp, ifnotexists, qt))
compiler.compile_query(bdb, phrase.query, out)
winders, unwinders = out.getwindings()
with compiler.bayesdb_wind(bdb, winders, unwinders):
bdb.sql_execute(out.getvalue(), out.getbindings())
return empty_cursor(bdb)
if isinstance(phrase, ast.CreateTabCsv):
with bdb.savepoint():
table_exists = core.bayesdb_has_table(bdb, phrase.name)
if table_exists:
if phrase.ifnotexists:
return empty_cursor(bdb)
else:
raise BQLError(bdb, 'Table already exists: %s' %
(repr(phrase.name),))
bayesdb_read_csv_file(
bdb, phrase.name, phrase.csv, header=True, create=True)
return empty_cursor(bdb)
if isinstance(phrase, ast.DropTab):
with bdb.savepoint():
sql = 'SELECT COUNT(*) FROM bayesdb_population WHERE tabname = ?'
cursor = bdb.sql_execute(sql, (phrase.name,))
if 0 < cursor_value(cursor):
raise BQLError(bdb, 'Table still in use by populations: %s' %
(repr(phrase.name),))
bdb.sql_execute('DELETE FROM bayesdb_column WHERE tabname = ?',
(phrase.name,))
ifexists = 'IF EXISTS ' if phrase.ifexists else ''
qt = sqlite3_quote_name(phrase.name)
return bdb.sql_execute('DROP TABLE %s%s' % (ifexists, qt))
if isinstance(phrase, ast.AlterTab):
with bdb.savepoint():
table = phrase.table
if not core.bayesdb_has_table(bdb, table):
raise BQLError(bdb, 'No such table: %s' % (repr(table),))
for cmd in phrase.commands:
if isinstance(cmd, ast.AlterTabRenameTab):
# If the names differ only in case, we have to do
# some extra work because SQLite will reject the
# table rename. Note that we may even have table
# == cmd.name here, but if the stored table name
# differs in case from cmd.name, we want to update
# it anyway.
if casefold(table) == casefold(cmd.name):
# Go via a temporary table.
temp = table + '_temp'
while core.bayesdb_has_table(bdb, temp):
temp += '_temp'
rename_table(bdb, table, temp)
rename_table(bdb, temp, cmd.name)
else:
# Make sure nothing else has this name and
# rename it.
if core.bayesdb_has_table(bdb, cmd.name):
raise BQLError(bdb,
'Name already defined as table: %s'
% (repr(cmd.name),))
rename_table(bdb, table, cmd.name)
# If table has implicit population, rename it too.
if core.bayesdb_table_has_implicit_population(
bdb, cmd.name):
populations = \
core.bayesdb_table_populations(bdb, cmd.name)
assert len(populations) == 1
population_name = core.bayesdb_population_name(
bdb, populations[0])
qt = sqlite3_quote_name(cmd.name)
qp = sqlite3_quote_name(population_name)
bdb.execute('ALTER POPULATION %s RENAME TO %s'
% (qp, qt))
# Remember the new name for subsequent commands.
table = cmd.name
elif isinstance(cmd, ast.AlterTabRenameCol):
# XXX Need to deal with this in the compiler.
raise NotImplementedError('Renaming columns'
' not yet implemented.')
# Make sure the old name exist and the new name does not.
old_folded = casefold(cmd.old)
new_folded = casefold(cmd.new)
if old_folded != new_folded:
if not core.bayesdb_table_has_column(bdb, table,
cmd.old):
raise BQLError(bdb, 'No such column in table %s'
': %s' %
(repr(table), repr(cmd.old)))
if core.bayesdb_table_has_column(bdb, table, cmd.new):
raise BQLError(bdb, 'Column already exists'
' in table %s: %s' %
(repr(table), repr(cmd.new)))
# Update bayesdb_column. Everything else refers
# to columns by (tabname, colno) pairs rather than
# by names.
update_column_sql = '''
UPDATE bayesdb_column SET name = :new
WHERE tabname = :table AND name = :old
'''
total_changes = bdb._sqlite3.totalchanges()
bdb.sql_execute(update_column_sql, {
'table': table,
'old': cmd.old,
'new': cmd.new,
})
assert bdb._sqlite3.totalchanges() - total_changes == 1
# ...except backends may have the (case-folded) name cached.
if old_folded != new_folded:
populations_sql = '''
SELECT id FROM bayesdb_population WHERE tabname = ?
'''
cursor = bdb.sql_execute(populations_sql, (table,))
generators = [
core.bayesdb_population_generators(
bdb, population_id)
for (population_id,) in cursor
]
for generator_id in set(generators):
backend = core.bayesdb_generator_backend(bdb,
generator_id)
backend.rename_column(bdb, generator_id,
old_folded, new_folded)
else:
assert False, 'Invalid alter table command: %s' % \
(cmd,)
return empty_cursor(bdb)
if isinstance(phrase, ast.GuessSchema):
if not core.bayesdb_has_table(bdb, phrase.table):
raise BQLError(bdb, 'No such table : %s' % phrase.table)
out = compiler.Output(0, {}, {})
with bdb.savepoint():
qt = sqlite3_quote_name(phrase.table)
temptable = bdb.temp_table_name()
qtt = sqlite3_quote_name(temptable)
cursor = bdb.sql_execute('SELECT * FROM %s' % (qt,))
column_names = [d[0] for d in cursor.description]
rows = cursor.fetchall()
stattypes = bayesdb_guess_stattypes(column_names, rows)
distinct_value_counts = [
len(set([row[i] for row in rows]))
for i in range(len(column_names))
]
out.winder('''
CREATE TEMP TABLE %s (
column TEXT,
stattype TEXT,
num_distinct INTEGER,
reason TEXT
)
''' % (qtt,), ())
for cn, st, ct in zip(column_names, stattypes, distinct_value_counts):
out.winder('''
INSERT INTO %s VALUES (?, ?, ?, ?)
''' % (qtt), (cn, st[0], ct, st[1]))
out.write('SELECT * FROM %s' % (qtt,))
out.unwinder('DROP TABLE %s' % (qtt,), ())
winders, unwinders = out.getwindings()
return execute_wound(
bdb, winders, unwinders, out.getvalue(), out.getbindings())
if isinstance(phrase, ast.CreatePop):
with bdb.savepoint():
_create_population(bdb, phrase)
return empty_cursor(bdb)
if isinstance(phrase, ast.DropPop):
with bdb.savepoint():
if not core.bayesdb_has_population(bdb, phrase.name):
if phrase.ifexists:
return empty_cursor(bdb)
raise BQLError(bdb, 'No such population: %r' % (phrase.name,))
population_id = core.bayesdb_get_population(bdb, phrase.name)
generator_ids = core.bayesdb_population_generators(
bdb, population_id)
if generator_ids:
generators = [core.bayesdb_generator_name(bdb, gid)
for gid in generator_ids]
raise BQLError(bdb, 'Population %r still has generators: %r' %
(phrase.name, generators))
# XXX helpful error checking if generators still exist
# XXX check change counts
bdb.sql_execute('''
DELETE FROM bayesdb_variable WHERE population_id = ?
''', (population_id,))
bdb.sql_execute('''
DELETE FROM bayesdb_population WHERE id = ?
''', (population_id,))
return empty_cursor(bdb)
if isinstance(phrase, ast.AlterPop):
with bdb.savepoint():
population = phrase.population
if not core.bayesdb_has_population(bdb, population):
raise BQLError(bdb, 'No such population: %s' %
(repr(population),))
population_id = core.bayesdb_get_population(bdb, population)
for cmd in phrase.commands:
if isinstance(cmd, ast.AlterPopRenamePop):
table = core.bayesdb_population_table(bdb, population_id)
# Prevent renaming of implicit population directly, unless
# being called by ast.AlterTabRenameTab in which case the
# table name and population name will not be matching.
if core.bayesdb_population_is_implicit(bdb, population_id) \
and casefold(population) == casefold(table):
raise BQLError(bdb, 'Cannot rename implicit'
'population %s; rename base table instead'
% (population,))
# Make sure nothing else has this name.
if casefold(population) != casefold(cmd.name):
if core.bayesdb_has_population(bdb, cmd.name):
raise BQLError(bdb,
'Name already defined as population' ': %s'
% (repr(cmd.name),))
# Update bayesdb_population. Everything else
# refers to it by id.
update_generator_sql = '''
UPDATE bayesdb_population SET name = ? WHERE id = ?
'''
total_changes = bdb._sqlite3.totalchanges()
bdb.sql_execute(update_generator_sql,
(cmd.name, population_id))
assert bdb._sqlite3.totalchanges() - total_changes == 1
# If population has implicit generator, rename it too.
if core.bayesdb_population_has_implicit_generator(
bdb, population_id):
generators = core.bayesdb_population_generators(
bdb, population_id)
assert len(generators) == 1
generator_name = core.bayesdb_generator_name(
bdb, generators[0])
qp = sqlite3_quote_name(cmd.name)
qg = sqlite3_quote_name(generator_name)
bdb.execute('ALTER GENERATOR %s RENAME TO %s'
% (qg, qp,))
# Remember the new name for subsequent commands.
population = cmd.name
elif isinstance(cmd, ast.AlterPopAddVar):
# Ensure column exists in base table.
table = core.bayesdb_population_table(bdb, population_id)
if not core.bayesdb_table_has_column(
bdb, table, cmd.name):
raise BQLError(bdb,
'No such variable in base table: %s'
% (cmd.name))
# Ensure variable not already in population.
if core.bayesdb_has_variable(
bdb, population_id, None, cmd.name):
raise BQLError(bdb,
'Variable already in population: %s'
% (cmd.name))
# Ensure there is at least observation in the column.
qt = sqlite3_quote_name(table)
qc = sqlite3_quote_name(cmd.name)
cursor = bdb.sql_execute(
'SELECT COUNT(*) FROM %s WHERE %s IS NOT NULL' %
(qt, qc))
if cursor_value(cursor) == 0:
raise BQLError(bdb,
'Cannot add variable without any values: %s'
% (cmd.name))
# If stattype is None, guess.
if cmd.stattype is None:
cursor = bdb.sql_execute(
'SELECT %s FROM %s' % (qc, qt))
rows = cursor.fetchall()
[stattype, reason] = bayesdb_guess_stattypes(
[cmd.name], rows)[0]
# Fail if trying to model a key.
if stattype == 'key':
raise BQLError(bdb,
'Values in column %s appear to be keys.'
% (cmd.name,))
# Fail if cannot determine a stattype.
elif stattype == 'ignore':
raise BQLError(bdb,
'Failed to determine a stattype for %s, '
'please specify one manually.' % (cmd.name,))
# If user specified stattype, ensure it exists.
elif not core.bayesdb_has_stattype(bdb, cmd.stattype):
raise BQLError(bdb,
'Invalid stattype: %s' % (cmd.stattype))
else:
stattype = cmd.stattype
# Check that strings are not being modeled as numerical.
if stattype == 'numerical' \
and _column_contains_string(bdb, table, cmd.name):
raise BQLError(bdb,
'Numerical column contains string values: %r '
% (qc,))
with bdb.savepoint():
# Add the variable to the population.
core.bayesdb_add_variable(
bdb, population_id, cmd.name, stattype)
colno = core.bayesdb_variable_number(
bdb, population_id, None, cmd.name)
# Add the variable to each (initialized) generator in
# the population.
generator_ids = filter(
lambda g: core.bayesdb_generator_modelnos(bdb, g),
core.bayesdb_population_generators(
bdb, population_id),
)
for generator_id in generator_ids:
backend = core.bayesdb_generator_backend(
bdb, generator_id)
backend.add_column(bdb, generator_id, colno)
elif isinstance(cmd, ast.AlterPopStatType):
# Check the no generators are defined for this population.
generators = core.bayesdb_population_generators(
bdb, population_id)
if generators:
raise BQLError(bdb,
'Cannot update statistical types for population '
'%s, it has generators: %s'
% (repr(population), repr(generators),))
# Check all the variables are in the population.
unknown = [
c for c in cmd.names if not
core.bayesdb_has_variable(bdb, population_id, None, c)
]
if unknown:
raise BQLError(bdb,
'No such variables in population: %s'
% (repr(unknown)))
# Check the statistical type is valid.
if not core.bayesdb_has_stattype(bdb, cmd.stattype):
raise BQLError(bdb,
'Invalid statistical type: %r'
% (repr(cmd.stattype),))
# Check that strings are not being modeled as numerical.
if cmd.stattype == 'numerical':
table = core.bayesdb_population_table(
bdb, population_id)
numerical_string_vars = [
col for col in cmd.names
if _column_contains_string(bdb, table, col)
]
if numerical_string_vars:
raise BQLError(bdb,
'Columns with string values modeled as '
'numerical: %r' % (numerical_string_vars,))
# Perform the stattype update.
colnos = [
core.bayesdb_variable_number(
bdb, population_id, None, c) for c in cmd.names
]
qcolnos = ','.join('%d' % (colno,) for colno in colnos)
update_stattype_sql = '''
UPDATE bayesdb_variable SET stattype = ?
WHERE population_id = ? AND colno IN (%s)
''' % (qcolnos,)
bdb.sql_execute(
update_stattype_sql,
(casefold(cmd.stattype), population_id,))
else:
assert False, 'Invalid ALTER POPULATION command: %s' % \
(repr(cmd),)
return empty_cursor(bdb)
if isinstance(phrase, ast.CreateGen):
# Find the population.
if not core.bayesdb_has_population(bdb, phrase.population):
raise BQLError(bdb, 'No such population: %r' %
(phrase.population,))
population_id = core.bayesdb_get_population(bdb, phrase.population)
# Find the backend, or use the default.
backend_name = phrase.backend
if phrase.backend is None:
backend_name = 'cgpm'
if backend_name not in bdb.backends:
raise BQLError(bdb, 'No such backend: %s' %
(repr(backend_name),))
backend = bdb.backends[backend_name]
# Retrieve the (possibility implicit) generator name.
generator_name = phrase.name or phrase.population
implicit = 1 if phrase.name is None else 0
with bdb.savepoint():
if core.bayesdb_has_generator(bdb, population_id, generator_name):
if not phrase.ifnotexists:
raise BQLError(
bdb, 'Name already defined as generator: %s' %
(repr(generator_name),))
else:
# Insert a record into bayesdb_generator and get the
# assigned id.
bdb.sql_execute('''
INSERT INTO bayesdb_generator
(name, population_id, backend, implicit)
VALUES (?, ?, ?, ?)
''', (generator_name, population_id, backend.name(), implicit))
generator_id = core.bayesdb_get_generator(
bdb, population_id, generator_name)
# Do any backend-specific initialization.
backend.create_generator(bdb, generator_id, phrase.schema)
# All done. Nothing to return.
return empty_cursor(bdb)
if isinstance(phrase, ast.DropGen):
with bdb.savepoint():
if not core.bayesdb_has_generator(bdb, None, phrase.name):
if phrase.ifexists:
return empty_cursor(bdb)
raise BQLError(bdb, 'No such generator: %s' %
(repr(phrase.name),))
generator_id = core.bayesdb_get_generator(bdb, None, phrase.name)
backend = core.bayesdb_generator_backend(bdb, generator_id)
# Backend-specific destruction.
backend.drop_generator(bdb, generator_id)
# Drop latent variables, models, and, finally, generator.
drop_columns_sql = '''
DELETE FROM bayesdb_variable WHERE generator_id = ?
'''
bdb.sql_execute(drop_columns_sql, (generator_id,))
drop_model_sql = '''
DELETE FROM bayesdb_generator_model WHERE generator_id = ?
'''
bdb.sql_execute(drop_model_sql, (generator_id,))
drop_generator_sql = '''
DELETE FROM bayesdb_generator WHERE id = ?
'''
bdb.sql_execute(drop_generator_sql, (generator_id,))
return empty_cursor(bdb)
if isinstance(phrase, ast.AlterGen):
with bdb.savepoint():
generator = phrase.generator
if not core.bayesdb_has_generator(bdb, None, generator):
raise BQLError(bdb, 'No such generator: %s' %
(repr(generator),))
generator_id = core.bayesdb_get_generator(bdb, None, generator)
cmds_generic = []
for cmd in phrase.commands:
if isinstance(cmd, ast.AlterGenRenameGen):
population_id = core.bayesdb_generator_population(
bdb, generator_id)
population = core.bayesdb_population_name(
bdb, population_id)
# Prevent renaming of implicit generator directly, unless
# being called by ast.AlterPopRenamePop in which case the
# population name and generator name will not be matching.
if core.bayesdb_population_is_implicit(bdb, generator_id) \
and casefold(generator) == casefold(population):
raise BQLError(bdb, 'Cannot rename implicit '
'generator; rename base population instead')
# Disable modelnos with AlterGenRenameGen.
if phrase.modelnos is not None:
raise BQLError(bdb, 'Cannot specify models for RENAME')
# Make sure nothing else has this name.
if casefold(generator) != casefold(cmd.name):
if core.bayesdb_has_generator(bdb, None, cmd.name):
raise BQLError(bdb, 'Name already defined'
' as generator: %s' %
(repr(cmd.name),))
# Update bayesdb_generator. Everything else
# refers to it by id.
update_generator_sql = '''
UPDATE bayesdb_generator SET name = ? WHERE id = ?
'''
total_changes = bdb._sqlite3.totalchanges()
bdb.sql_execute(update_generator_sql,
(cmd.name, generator_id))
assert bdb._sqlite3.totalchanges() - total_changes == 1
# Remember the new name for subsequent commands.
generator = cmd.name
elif isinstance(cmd, ast.AlterGenGeneric):
cmds_generic.append(cmd.command)
else:
assert False, 'Invalid ALTER GENERATOR command: %s' % \
(repr(cmd),)
if cmds_generic:
modelnos = phrase.modelnos
modelnos_invalid = None if modelnos is None else [
modelno for modelno in modelnos if not
core.bayesdb_generator_has_model(bdb, generator_id, modelno)
]
if modelnos_invalid:
raise BQLError(bdb,
'No such models in generator %s: %s' %
(repr(phrase.generator), repr(modelnos)))
# Call generic alternations on the backend.
backend = core.bayesdb_generator_backend(bdb, generator_id)
backend.alter(bdb, generator_id, modelnos, cmds_generic)
return empty_cursor(bdb)
if isinstance(phrase, ast.InitModels):
if not core.bayesdb_has_generator(bdb, None, phrase.generator):
raise BQLError(bdb, 'No such generator: %s' %
(phrase.generator,))
generator_id = core.bayesdb_get_generator(bdb, None, phrase.generator)
modelnos = range(phrase.nmodels)
with bdb.savepoint():
# Find the model numbers. Omit existing ones for
# ifnotexists; reject existing ones otherwise.
if phrase.ifnotexists:
modelnos = set(modelno for modelno in modelnos
if not core.bayesdb_generator_has_model(bdb, generator_id,
modelno))
else:
existing = set(modelno for modelno in modelnos
if core.bayesdb_generator_has_model(bdb, generator_id,
modelno))
if 0 < len(existing):
raise BQLError(bdb, 'Generator %s already has models: %s' %
(repr(phrase.generator), sorted(existing)))
# Stop now if there's nothing to initialize.
if len(modelnos) == 0:
return
# Create the bayesdb_generator_model records.
modelnos = sorted(modelnos)
insert_model_sql = '''
INSERT INTO bayesdb_generator_model
(generator_id, modelno)
VALUES (:generator_id, :modelno)
'''
for modelno in modelnos:
bdb.sql_execute(insert_model_sql, {
'generator_id': generator_id,
'modelno': modelno,
})
# Do backend-specific initialization.
backend = core.bayesdb_generator_backend(bdb, generator_id)
backend.initialize_models(bdb, generator_id, modelnos)
return empty_cursor(bdb)
if isinstance(phrase, ast.AnalyzeModels):
# WARNING: It is the backend's responsibility to work in a
# transaction.
#
# WARNING: It is the backend's responsibility to update the
# iteration count in bayesdb_generator_model records.
#
# We do this so that the backend can save incremental
# progress in case of ^C in the middle.
#
# XXX Put these warning somewhere more appropriate.
if not core.bayesdb_has_generator(bdb, None, phrase.generator):
raise BQLError(bdb, 'No such generator: %s' %
(phrase.generator,))
generator_id = core.bayesdb_get_generator(bdb, None, phrase.generator)
backend = core.bayesdb_generator_backend(bdb, generator_id)
# XXX Should allow parameters for iterations and ckpt/iter.
backend.analyze_models(bdb, generator_id,
modelnos=phrase.modelnos,
iterations=phrase.iterations,
max_seconds=phrase.seconds,
ckpt_iterations=phrase.ckpt_iterations,
ckpt_seconds=phrase.ckpt_seconds,
program=phrase.program)
return empty_cursor(bdb)
if isinstance(phrase, ast.DropModels):
with bdb.savepoint():
generator_id = core.bayesdb_get_generator(
bdb, None, phrase.generator)
backend = core.bayesdb_generator_backend(bdb, generator_id)
modelnos = None
if phrase.modelnos is not None:
lookup_model_sql = '''
SELECT COUNT(*) FROM bayesdb_generator_model
WHERE generator_id = :generator_id
AND modelno = :modelno
'''
modelnos = sorted(list(phrase.modelnos))
for modelno in modelnos:
cursor = bdb.sql_execute(lookup_model_sql, {
'generator_id': generator_id,
'modelno': modelno,
})
if cursor_value(cursor) == 0:
raise BQLError(bdb, 'No such model'
' in generator %s: %s' %
(repr(phrase.generator), repr(modelno)))
backend.drop_models(bdb, generator_id, modelnos=modelnos)
if modelnos is None:
drop_models_sql = '''
DELETE FROM bayesdb_generator_model WHERE generator_id = ?
'''
bdb.sql_execute(drop_models_sql, (generator_id,))
else:
drop_model_sql = '''
DELETE FROM bayesdb_generator_model
WHERE generator_id = :generator_id
AND modelno = :modelno
'''
for modelno in modelnos:
bdb.sql_execute(drop_model_sql, {
'generator_id': generator_id,
'modelno': modelno,
})
return empty_cursor(bdb)
if isinstance(phrase, ast.Regress):
# Retrieve the population.
if not core.bayesdb_has_population(bdb, phrase.population):
raise BQLError(bdb, 'No such population: %r' % (phrase.population,))
population_id = core.bayesdb_get_population(bdb, phrase.population)
# Retrieve the generator
generator_id = None
if phrase.generator:
if not core.bayesdb_has_generator(bdb, population_id,
phrase.generator):
raise BQLError(bdb,
'No such generator: %r' % (phrase.generator,))
generator_id = core.bayesdb_get_generator(
bdb, population_id, phrase.generator)
# Retrieve the target variable.
if not core.bayesdb_has_variable(
bdb, population_id, None, phrase.target):
raise BQLError(bdb, 'No such variable: %r' % (phrase.target,))
colno_target = core.bayesdb_variable_number(
bdb, population_id, None, phrase.target)
stattype = core.bayesdb_variable_stattype(bdb, population_id,
generator_id, colno_target)
if stattype != 'numerical':
raise BQLError(bdb,
'Target variable is not numerical: %r' % (phrase.target,))
# Build the given variables.
if any(isinstance(col, ast.SelColAll) for col in phrase.givens):
# Using * is not allowed to be mixed with other variables.
if len(phrase.givens) > 1:
raise BQLError(bdb, 'Cannot use (*) with other givens.')
colno_givens = core.bayesdb_variable_numbers(
bdb, population_id, None)
else:
if any(isinstance(col, ast.SelColSub) for col in phrase.givens):
# Subexpression needs special compiling.
out = compiler.Output(n_numpar, nampar_map, bindings)
bql_compiler = compiler.BQLCompiler_None()
givens = compiler.expand_select_columns(
bdb, phrase.givens, True, bql_compiler, out)
else:
givens = phrase.givens
colno_givens = [
core.bayesdb_variable_number(
bdb, population_id, None, given.expression.column)
for given in givens
]
# Build the arguments to bqlfn.bayesdb_simulate.
colno_givens_unique = set(
colno for colno in colno_givens if colno!= colno_target
)
if len(colno_givens_unique) == 0:
raise BQLError(bdb, 'No matching given columns.')
constraints = []
colnos = [colno_target] + list(colno_givens_unique)
nsamp = 100 if phrase.nsamp is None else phrase.nsamp.value.value
modelnos = None if phrase.modelnos is None else str(phrase.modelnos)
rows = bqlfn.bayesdb_simulate(
bdb, population_id, generator_id, modelnos, constraints,
colnos, numpredictions=nsamp)
# Retrieve the stattypes.
stattypes = [
core.bayesdb_variable_stattype(
bdb, population_id, generator_id, colno_given)
for colno_given in colno_givens_unique
]
# Separate the target values from the given values.
target_values = [row[0] for row in rows]
given_values = [row[1:] for row in rows]
given_names = [
core.bayesdb_variable_name(bdb, population_id, generator_id, given)
for given in colno_givens_unique
]
# Compute the coefficients. The import to regress_ols is here since the
# feature depends on pandas + sklearn, so avoid module-wide import.
from bayeslite.regress import regress_ols
coefficients = regress_ols(
target_values, given_values, given_names, stattypes)
# Store the results in a winder.
temptable = bdb.temp_table_name()
qtt = sqlite3_quote_name(temptable)
out = compiler.Output(0, {}, {})
out.winder('''
CREATE TEMP TABLE %s (variable TEXT, coefficient REAL);
''' % (qtt,), ())
for variable, coef in coefficients:
out.winder('''
INSERT INTO %s VALUES (?, ?)
''' % (qtt), (variable, coef,))
out.write('SELECT * FROM %s ORDER BY variable' % (qtt,))
out.unwinder('DROP TABLE %s' % (qtt,), ())
winders, unwinders = out.getwindings()
return execute_wound(
bdb, winders, unwinders, out.getvalue(), out.getbindings())
assert False # XXX
def create_generator(self, bdb, generator_id, schema_tokens, **kwargs):
schema_ast = cgpm_schema.parse.parse(schema_tokens)
schema = _create_schema(bdb, generator_id, schema_ast, **kwargs)
# Store the schema.
bdb.sql_execute(
'''
INSERT INTO bayesdb_cgpm_generator (generator_id, schema_json)
VALUES (?, ?)
''', (generator_id, json_dumps(schema)))
# Get the underlying population and table.
population_id = core.bayesdb_generator_population(bdb, generator_id)
table = core.bayesdb_population_table(bdb, population_id)
qt = sqlite3_quote_name(table)
# Assign latent variable numbers.
for var, stattype in sorted(schema['latents'].iteritems()):
core.bayesdb_add_latent(bdb, population_id, generator_id, var,
stattype)
# Assign codes to categories and consecutive column numbers to
# the modelled variables.
vars_cursor = bdb.sql_execute(
'''
SELECT colno, name, stattype FROM bayesdb_variable
WHERE population_id = ? AND 0 <= colno
''', (population_id, ))
for colno, name, stattype in vars_cursor:
if _is_categorical(stattype):
qn = sqlite3_quote_name(name)
cursor = bdb.sql_execute('''
SELECT DISTINCT %s FROM %s WHERE %s IS NOT NULL
''' % (qn, qt, qn))
for code, (value, ) in enumerate(cursor):
bdb.sql_execute(
'''
INSERT INTO bayesdb_cgpm_category
(generator_id, colno, value, code)
VALUES (?, ?, ?, ?)
''', (generator_id, colno, value, code))
# Assign contiguous 0-indexed ids to the individuals in the
# table.
if schema['subsample']:
k = schema['subsample']
n = cursor_value(
bdb.sql_execute('SELECT COUNT(*) FROM %s' % (qt, )))
cursor = bdb.sql_execute(
'SELECT _rowid_ FROM %s ORDER BY _rowid_ ASC' % (qt, ))
uniform = bdb._prng.weakrandom_uniform
# https://en.wikipedia.org/wiki/Reservoir_sampling
samples = []
for i, row in enumerate(cursor):
if i < k:
samples.append(row)
else:
r = uniform(i + 1)
if r < k:
samples[r] = row
cursor = samples
else:
cursor = bdb.sql_execute('SELECT _rowid_ FROM %s' % (qt, ))
for cgpm_rowid, (table_rowid, ) in enumerate(cursor):
bdb.sql_execute(
'''
INSERT INTO bayesdb_cgpm_individual
(generator_id, table_rowid, cgpm_rowid)
VALUES (?, ?, ?)
''', (generator_id, table_rowid, cgpm_rowid))
def simulate_joint(self,
bdb,
generator_id,
modelnos,
rowid,
targets,
constraints,
num_samples=1,
accuracy=None):
# Retrieve the population id.
population_id = bayesdb_generator_population(bdb, generator_id)
# If rowid exists, retrieve conditioning data from the table.
if rowid != bayesdb_population_fresh_row_id(bdb, generator_id):
row_values_raw = bayesdb_population_row_values(
bdb, population_id, rowid)
row_values = [
str(a) if isinstance(a, unicode) else a for a in row_values_raw
]
row = [
entry for entry in enumerate(row_values)
if entry[1] is not None
]
constraints_colnos = [c[0] for c in constraints]
row_colnos = [r[0] for r in row]
if any([colno in constraints_colnos for colno in row_colnos]):
raise BQLError(bdb, 'Overlap between constraints and' \
'target row in simulate.')
constraints.extend(row)
# Prepare the query row to provide to Loom.
row = {}
target_num_to_name = {}
for colno in targets:
name = bayesdb_variable_name(bdb, generator_id, None, colno)
target_num_to_name[colno] = name
row[name] = ''
for (colno, value) in constraints:
name = bayesdb_variable_name(bdb, generator_id, None, colno)
row[name] = value
# Fetch the server.
server = self._get_cache_entry(bdb, generator_id, 'preql_server')
# Prepare the csv header.
csv_headers, csv_values = zip(*row.iteritems())
lower_to_upper = {str(a).lower(): str(a) for a in csv_headers}
csv_headers = lower_to_upper.keys()
csv_values = [str(a) for a in csv_values]
# Retrieve the samples from the server..
outfile = StringIO()
writer = loom.preql.CsvWriter(outfile, returns=outfile.getvalue)
reader = iter([csv_headers] + [csv_values])
server._predict(reader, num_samples, writer, False)
output = writer.result()
# Parse output.
returned_headers = [
lower_to_upper[a]
for a in output.strip().split('\r\n')[0].split(CSV_DELIMITER)
]
loom_output = [
zip(returned_headers, a.split(CSV_DELIMITER))
for a in output.strip().split('\r\n')[1:]
]
return_list = []
for row in loom_output:
# Prepare the row.
row_values = []
row_dict = dict(row)
for colno in targets:
colname = target_num_to_name[colno]
value = row_dict[colname]
stattype = bayesdb_variable_stattype(bdb, population_id, None,
colno)
if not _is_nominal(stattype):
value = float(value)
row_values.append(value)
# Add this row to the return list.
return_list.append(row_values)
return return_list
