def JsonSchemaToSearchSpaceHelper(
self,
longName: str,
path: str,
schema: JsonSchema,
relevantFields: Optional[Set[str]],
pgo_freqs: pgo_part = None,
sub_space: bool = True,
) -> Dict[str, SearchSpace]:
if "properties" not in schema:
return {}
props = schema["properties"]
hyp: Dict[str, SearchSpace] = {}
for p, s in props.items():
if relevantFields is None or p in relevantFields:
# We would need to specify what is correct in that case
sub_freqs = freqs_wrapper_lookup(pgo_freqs, p)
sub_sch = self.schemaToSearchSpaceHelper_(longName,
path + "_" + p,
s,
None,
pgo_freqs=sub_freqs)
if sub_sch is None:
# if it is a required field, this entire thing should be None
hyp[p] = SearchSpaceConstant(None)
else:
hyp[p] = sub_sch
else:
logger.debug(
f"schemaToSearchSpace: skipping not relevant field {p}")
return hyp
def visitSearchSpaceSum(self,
op: SearchSpaceSum) -> SearchSpaceGridInternalType:
sub_spaces: List[SearchSpace] = op.sub_spaces
sub_grids: Iterable[SearchSpaceGridInternalType] = [
accept(cur_space, self) for cur_space in sub_spaces
]
if len(sub_spaces) == 1:
return list(sub_grids)[0]
else:
fixed_grids: Iterable[List[SearchSpaceGrid]] = (
SearchSpaceToGridVisitor.fixupDegenerateSearchSpaces(grid)
for grid in sub_grids)
final_grids: List[SearchSpaceGrid] = []
for i, grids in enumerate(fixed_grids):
if not grids:
grids = [{}]
else:
# we need to add in this nesting
# in case a higher order operator directly contains
# another
grids = nest_choice_all_HPparams(grids)
discriminated_grids: List[SearchSpaceGrid] = [{
**d, discriminant_name:
SearchSpaceConstant(i)
} for d in grids]
final_grids.extend(discriminated_grids)
return final_grids
def _searchSpaceList(self, space: SearchSpaceArray, *,
size: int) -> List[SearchSpaceGrid]:
sub_spaces = space.items(max=size)
param_grids: List[List[SearchSpaceGrid]] = [
nest_all_HPparams(
str(index), self.fixupDegenerateSearchSpaces(accept(sub,
self)))
for index, sub in enumerate(sub_spaces)
]
param_grids_product: Iterable[
Iterable[SearchSpaceGrid]] = itertools.product(*param_grids)
chained_grids: List[SearchSpaceGrid] = [
dict(ChainMap(*gridline, )) for gridline in param_grids_product
]
if space.is_tuple:
st_val = structure_type_tuple
else:
st_val = structure_type_list
discriminated_grids: List[SearchSpaceGrid] = [{
**d, structure_type_name:
SearchSpaceConstant(st_val)
} for d in chained_grids]
return discriminated_grids
def add_sub_space(space, k, v):
""" Given a search space and a "key",
if the defined subschema does not exist,
set it to be the constant v space
"""
# TODO!
# I should parse __ and such and walk down the schema
if isinstance(space, SearchSpaceObject):
if k not in space.keys:
space.keys.append(k)
space.choices = (c + (SearchSpaceConstant(v),) for c in space.choices)
return
def visitSearchSpaceDict(
self, op: SearchSpaceDict) -> SearchSpaceGridInternalType:
sub_spaces = op.space_dict.items()
param_grids: List[List[SearchSpaceGrid]] = [
nest_all_HPparams(
name,
self.fixupDegenerateSearchSpaces(accept(space, self)),
) for name, space in sub_spaces
]
param_grids_product: Iterable[
Iterable[SearchSpaceGrid]] = itertools.product(*param_grids)
chained_grids: List[SearchSpaceGrid] = [
dict(ChainMap(*gridline)) for gridline in param_grids_product
]
discriminated_grids: List[SearchSpaceGrid] = [{
**d, structure_type_name:
SearchSpaceConstant(structure_type_dict)
} for d in chained_grids]
return discriminated_grids
def schemaToSearchSpaceHelper_(
self,
longName,
path: str,
schema: JsonSchema,
relevantFields: Optional[Set[str]],
pgo_freqs: pgo_part = None,
sub_space: bool = True,
) -> Optional[SearchSpace]:
# TODO: handle degenerate cases
# right now, this handles only a very fixed form
if is_false_schema(schema):
return None
typ: Optional[str] = None
typ = schema.get("laleType", None)
if typ is None:
typ = schema.get("type", None)
else:
typ = typ
if "enum" in schema and typ != "operator":
vals = schema["enum"]
return SearchSpaceEnum(vals,
pgo=asFreqs(pgo_freqs),
default=get_default(schema))
if typ is not None:
if typ == "boolean":
return SearchSpaceBool(pgo=asFreqs(pgo_freqs),
default=get_default(schema))
elif typ == "number" or typ == "integer":
exclusive_minimum = False
minimum = schema.get("minimumForOptimizer", None)
if minimum is not None:
exclusive_minimum = schema.get(
"exclusiveMinimumForOptimizer", False)
else:
minimum = schema.get("minimum", None)
if minimum is not None:
exclusive_minimum = schema.get("exclusiveMinimum",
False)
exclusive_maximum = False
maximum = schema.get("maximumForOptimizer", None)
if maximum is not None:
exclusive_maximum = schema.get(
"exclusiveMaximumForOptimizer", False)
else:
maximum = schema.get("maximum", None)
if maximum is not None:
exclusive_maximum = schema.get("exclusiveMaximum",
False)
distribution = schema.get("distribution", None)
laleType = schema.get("laleType", None)
if laleType is None:
laleType = typ
if laleType == "number":
discrete = False
elif laleType == "integer":
discrete = True
else:
raise OperatorSchemaError(
path,
f"specified laleType should be a number or integer, not: {laleType}.",
)
pgo: Freqs
return SearchSpaceNumber(
minimum=minimum,
exclusiveMinimum=exclusive_minimum,
maximum=maximum,
exclusiveMaximum=exclusive_maximum,
discrete=discrete,
distribution=distribution,
pgo=asFreqs(pgo_freqs),
default=get_default(schema),
)
elif typ == "array" or typ == "tuple":
laleType = schema.get("laleType", None)
if laleType is None:
laleType = typ
is_tuple: bool = laleType == "tuple"
min_items = schema.get("minItemsForOptimizer", None)
if min_items is None:
min_items = schema.get("minItems", None)
if min_items is None:
min_items = 0
max_items = schema.get("maxItemsForOptimizer", None)
if max_items is None:
max_items = schema.get("maxItems", None)
items_schema = schema.get("itemsForOptimizer", None)
if items_schema is None:
items_schema = schema.get("items", None)
if items_schema is None:
raise OperatorSchemaError(
path,
f"An array type was found without a provided schema for the items in the schema {schema}. Please provide a schema for the items (consider using itemsForOptimizer)",
)
# we can search an empty list even without schemas
if max_items == 0:
if is_tuple:
return SearchSpaceConstant([()])
else:
return SearchSpaceConstant([[]])
prefix: Optional[List[SearchSpace]] = None
additional: Optional[SearchSpace] = None
if isinstance(items_schema, list):
prefix = []
for i, sub_schema in enumerate(items_schema):
sub = self.schemaToSearchSpaceHelper_(
longName, path + "_" + str(i), sub_schema,
relevantFields)
if sub is None:
return None
else:
prefix.append(sub)
prefix_len = len(prefix)
additional_items_schema = schema.get(
"additionalItemsForOptimizer", None)
if additional_items_schema is None:
additional_items_schema = schema.get(
"additionalItems", None)
if additional_items_schema is None:
if max_items is None or max_items > prefix_len:
raise OperatorSchemaError(
path,
f"An array type was found with provided schemas for {prefix_len} elements, but either an unspecified or too high a maxItems, and no schema for the additionalItems. Please constraing maxItems to <= {prefix_len} (you can set maxItemsForOptimizer), or provide a schema for additionalItems",
)
elif additional_items_schema is False:
if max_items is None:
max_items = prefix_len
else:
max_items = min(max_items, prefix_len)
else:
additional = self.schemaToSearchSpaceHelper_(
longName,
path + "-",
additional_items_schema,
relevantFields,
)
# if items_schema is None:
# raise ValueError(f"an array type was found without a provided schema for the items in the schema {schema}. Please provide a schema for the items (consider using itemsForOptimizer)")
else:
additional = self.schemaToSearchSpaceHelper_(
longName, path + "-", items_schema, relevantFields)
if max_items is None:
raise OperatorSchemaError(
path,
f"An array type was found without a provided maximum number of items in the schema {schema}, and it is not a list with 'additionalItems' set to False. Please provide a maximum (consider using maxItemsForOptimizer), or, if you are using a list, set additionalItems to False",
)
return SearchSpaceArray(
prefix=prefix,
minimum=min_items,
maximum=max_items,
additional=additional,
is_tuple=is_tuple,
)
elif typ == "object":
if "properties" not in schema:
return SearchSpaceObject(longName, [], [])
o = self.JsonSchemaToSearchSpaceHelper(
longName,
path,
schema,
relevantFields,
pgo_freqs=pgo_freqs,
sub_space=sub_space,
)
if sub_space:
return SearchSpaceDict(o)
else:
all_keys = list(o.keys())
all_keys.sort()
o_choice = tuple([o.get(k, None) for k in all_keys])
return SearchSpaceObject(longName, all_keys, [o_choice])
elif typ == "string":
pass
elif typ == "operator":
# TODO: If there is a default, we could use it
vals = schema.get("enum", None)
if vals is None:
logger.error(
"An operator is required by the schema but was not provided"
)
return None
sub_schemas: List[SearchSpace] = [
accept(op, self)
if isinstance(op, Operator) else SearchSpaceConstant(op)
for op in vals
]
combined_sub_schema: SearchSpace
if len(sub_schemas) == 1:
combined_sub_schema = sub_schemas[0]
if isinstance(combined_sub_schema, SearchSpaceConstant):
return combined_sub_schema
else:
combined_sub_schema = SearchSpaceSum(sub_schemas)
if all((isinstance(x, SearchSpaceConstant)
for x in sub_schemas)):
return combined_sub_schema
return SearchSpaceOperator(combined_sub_schema)
elif typ == "Any":
raise OperatorSchemaError(
path,
f"A search space was found with laleType ({typ}), which is not searchable. Please mark the relevant hyperparameter as not relevant for the optimizer. schema: {schema}",
)
else:
raise OperatorSchemaError(
path,
f"An unknown type ({typ}) was found in the schema {schema}"
)
if "anyOf" in schema:
objs = []
for s_obj in schema["anyOf"]:
if "type" in s_obj and s_obj["type"] == "object":
o = self.JsonSchemaToSearchSpaceHelper(
longName,
path,
s_obj,
relevantFields,
pgo_freqs=pgo_freqs,
sub_space=sub_space,
)
if o:
objs.append(o)
if objs:
# First, gather a list of all the properties
keys_list = [set(o.keys()) for o in objs]
# make sure the iterator is deterministic
all_keys = list(set.union(*keys_list))
# and we might as well make it sorted
all_keys.sort()
def as_str(k, c):
if c is None:
return "None"
else:
return search_space_to_str_for_comparison(
c, path + "_" + k)
anys: Dict[str, Any] = {}
for o in objs:
o_choice = tuple([o.get(k, None) for k in all_keys])
k = str([
as_str(all_keys[idx], c)
for idx, c in enumerate(o_choice)
])
if k in anys:
logger.info(
f"Ignoring Duplicate SearchSpace entry {k}")
anys[k] = o_choice
return SearchSpaceObject(longName, all_keys, anys.values())
else:
return SearchSpaceObject(longName, [], [])
if "allOf" in schema:
# if all but one are negated constraints, we will just ignore them
pos_sub_schema: List[JsonSchema] = []
for sub_schema in schema["allOf"]:
if "not" not in sub_schema:
pos_sub_schema.append(sub_schema)
if len(pos_sub_schema) > 1:
raise OperatorSchemaError(
path,
f"schemaToSearchSpaceHelper does not yet know how to compile the given schema {schema}, because it is an allOf with more than one non-negated schemas ({pos_sub_schema})",
)
if len(pos_sub_schema) == 0:
raise OperatorSchemaError(
path,
f"schemaToSearchSpaceHelper does not yet know how to compile the given schema {schema}, because it is an allOf with only negated schemas",
)
logger.debug(
f"[{path}]: schemaToSearchSpaceHelper: ignoring negated schemas in the conjunction {schema}"
)
return self.schemaToSearchSpaceHelper_(
longName,
path,
pos_sub_schema[0],
relevantFields,
pgo_freqs=pgo_freqs,
sub_space=sub_space,
)
# TODO: handle degenerate cases
raise OperatorSchemaError(
path,
f"schemaToSearchSpaceHelper does not yet know how to compile the given schema {schema}",
)