class IngredientLabelByProcessAndName(
Serializable['IngredientLabelByProcessAndName'], Variable):
"""[ALPHA] A boolean variable indicating whether a given label is applied.
Matches by process template, ingredient name, and the label string to check.
For example, a column might indicate whether or not the ingredient "ethanol" is labeled as a
"solvent" in the "second mixing" process. Many such columns would then support the
downstream analysis "get the volumetric average density of the solvents".
Parameters
---------
name: str
a short human-readable name to use when referencing the variable
headers: list[str]
sequence of column headers
process_template: LinkByUID
process template associated with this ingredient identifier
ingredient_name: str
name of ingredient
label: str
label to test
type_selector: DataObjectTypeSelector
strategy for selecting data object types to consider when matching, defaults to PREFER_RUN
"""
name = properties.String('name')
headers = properties.List(properties.String, 'headers')
process_template = properties.Object(LinkByUID, 'process_template')
ingredient_name = properties.String('ingredient_name')
label = properties.String('label')
type_selector = properties.Enumeration(DataObjectTypeSelector,
"type_selector")
typ = properties.String('type',
default="ing_label_by_process_and_name",
deserializable=False)
def _attrs(self) -> List[str]:
return [
"name", "headers", "process_template", "ingredient_name", "label",
"type_selector", "typ"
]
def __init__(
self,
*,
name: str,
headers: List[str],
process_template: LinkByUID,
ingredient_name: str,
label: str,
type_selector: DataObjectTypeSelector = DataObjectTypeSelector.
PREFER_RUN):
self.name = name
self.headers = headers
self.process_template = process_template
self.ingredient_name = ingredient_name
self.label = label
self.type_selector = type_selector
class FlatCompositionColumn(Serializable["FlatCompositionColumn"], Column):
"""[ALPHA] Column that flattens the composition into a string of names and quantities.
The numeric formatting tries to be human readable. For example, if all of the quantities
are round numbers like ``{"spam": 4.0, "eggs": 1.0}`` then the result omit the decimal points
like ``"(spam)4(eggs)1"`` (if sort_order is by quantity).
Parameters
----------
data_source: str
name of the variable to use when populating the column
sort_order: CompositionSortOrder
order with which to sort the components when generating the flat string
"""
data_source = properties.String('data_source')
sort_order = properties.Enumeration(CompositionSortOrder, 'sort_order')
typ = properties.String('type',
default="flat_composition_column",
deserializable=False)
def _attrs(self) -> List[str]:
return ["data_source", "sort_order", "typ"]
def __init__(self, *, data_source: str, sort_order: CompositionSortOrder):
self.data_source = data_source
self.sort_order = sort_order
class CategoricalConstraint(Serializable['CategoricalConstraint'], Constraint):
"""
[ALPHA] A constraint on a categorical material attribute to be in a set of acceptable values.
Parameters
----------
descriptor_key: str
the key corresponding to the associated Categorical descriptor
acceptable_categories: list[str]
the names of the acceptable categories to constrain to
"""
descriptor_key = properties.String('descriptor_key')
acceptable_categories = properties.List(properties.String(), 'acceptable_classes')
typ = properties.String('type', default='Categorical')
def __init__(self,
descriptor_key: str,
acceptable_categories: List[str],
session: Optional[Session] = None):
self.descriptor_key = descriptor_key
self.acceptable_categories = acceptable_categories
self.session = session
def __str__(self):
return '<CategoricalConstraint {!r}>'.format(self.descriptor_key)
class ComponentQuantityColumn(Serializable["ComponentQuantityColumn"], Column):
"""[ALPHA] Column that extracts the quantity of a given component.
If the component is not present in the composition, then the value in the column will be 0.0.
Parameters
----------
data_source: str
name of the variable to use when populating the column
component_name: str
name of the component from which to extract the quantity
normalize: bool
whether to normalize the quantity by the sum of all component amounts. Default is false
"""
data_source = properties.String('data_source')
component_name = properties.String("component_name")
normalize = properties.Boolean("normalize")
typ = properties.String('type',
default="component_quantity_column",
deserializable=False)
def _attrs(self) -> List[str]:
return ["data_source", "component_name", "normalize", "typ"]
def __init__(self,
*,
data_source: str,
component_name: str,
normalize: bool = False):
self.data_source = data_source
self.component_name = component_name
self.normalize = normalize
class NthBiggestComponentNameColumn(
Serializable["NthBiggestComponentNameColumn"], Column):
"""[ALPHA] Name of the Nth biggest component.
If there are fewer than N components in the composition, then this column will be empty.
Parameters
----------
data_source: str
name of the variable to use when populating the column
n: int
index of the component name to extract, starting with 1 for the biggest
"""
data_source = properties.String('data_source')
n = properties.Integer("n")
typ = properties.String('type',
default="biggest_component_name_column",
deserializable=False)
def _attrs(self) -> List[str]:
return ["data_source", "n", "typ"]
def __init__(self, *, data_source: str, n: int):
self.data_source = data_source
self.n = n
class Score(PolymorphicSerializable['Score']):
"""A Score is used to rank materials according to objectives and constraints.
Abstract type that returns the proper type given a serialized dict.
"""
_name = properties.String('name')
_description = properties.String('description')
@classmethod
def get_type(cls, data):
"""Return the subtype."""
return {'MLI': LIScore, 'MEI': EIScore, 'MEV': EVScore}[data['type']]
@property
def name(self):
"""Getter for the score's name."""
msg = "Getting the Score's name is deprecated."
warnings.warn(msg, category=DeprecationWarning)
return self._name
@property
def description(self):
"""Getter for the score's description."""
msg = "Getting the Score's description is deprecated."
warnings.warn(msg, category=DeprecationWarning)
return self._description
class FormulationDescriptor(Serializable['FormulationDescriptor'], Descriptor):
"""[ALPHA] A descriptor to hold formulations.
Parameters
----------
key: str
the key corresponding to a descriptor
"""
key = properties.String('descriptor_key')
typ = properties.String('type',
default='Formulation',
deserializable=False)
def __eq__(self, other):
try:
attrs = ["key", "typ"]
return all([
self.__getattribute__(key) == other.__getattribute__(key)
for key in attrs
])
except AttributeError:
return False
def __init__(self, key: str):
self.key: str = key
def __str__(self):
return "<FormulationDescriptor {!r}>".format(self.key)
def __repr__(self):
return "FormulationDescriptor(key={})".format(self.key)
class InorganicDescriptor(Serializable['InorganicDescriptor'], Descriptor):
"""Captures domain-specific context about the chemical formula for an inorganic compound.
Parameters
----------
key: str
the key corresponding to a descriptor
threshold: float
the threshold for valid chemical formulae. Users can think of this as a level of tolerance for typos and/or loss in interpreting a string input as a parseable chemical formula.
"""
key = properties.String('descriptor_key')
threshold = properties.Float('threshold')
type = properties.String('type', default='Inorganic', deserializable=False)
def __eq__(self, other):
try:
attrs = ["key", "type"]
return all([
self.__getattribute__(key) == other.__getattribute__(key)
for key in attrs
])
except Exception:
return False
def __init__(self, key: str, threshold: float = 1.0):
self.key: str = key
self.threshold = threshold
class RootIdentifier(Serializable['RootIdentifier'], Variable):
"""[ALPHA] Get the identifier for the root of the material history, by scope.
Parameters
---------
name: str
a short human-readable name to use when referencing the variable
headers: list[str]
sequence of column headers
scope: string
scope of the identifier (default: the Citrine scope)
"""
name = properties.String('name')
headers = properties.List(properties.String, 'headers')
scope = properties.String('scope')
typ = properties.String('type', default="root_id", deserializable=False)
def _attrs(self) -> List[str]:
return ["name", "headers", "scope", "typ"]
def __init__(self, *,
name: str,
headers: List[str],
scope: str):
self.name = name
self.headers = headers
self.scope = scope
class MolecularStructureDescriptor(
Serializable['MolecularStructureDescriptor'], Descriptor):
"""
[ALPHA] Material descriptor for an organic molecule.
Accepts SMILES, IUPAC, and InChI String values.
Parameters
----------
key: str
The column header key corresponding to this descriptor
"""
key = properties.String('descriptor_key')
typ = properties.String('type', default='Organic', deserializable=False)
def __eq__(self, other):
try:
attrs = ["key", "typ"]
return all([
self.__getattribute__(key) == other.__getattribute__(key)
for key in attrs
])
except AttributeError:
return False
def __init__(self, key: str):
self.key: str = key
def __str__(self):
return "<MolecularStructureDescriptor {!r}>".format(self.key)
def __repr__(self):
return "MolecularStructureDescriptor(key={})".format(self.key)
class CategoricalDescriptor(Serializable['CategoricalDescriptor'], Descriptor):
"""A descriptor to hold categorical variables. An exhaustive list of categorical values may be supplied.
Parameters
----------
key: str
the key corresponding to a descriptor
categories: list[str]
possible categories for this descriptor
"""
key = properties.String('descriptor_key')
type = properties.String('type',
default='Categorical',
deserializable=False)
categories = properties.List(properties.String, 'descriptor_values')
def __eq__(self, other):
try:
attrs = ["key", "type"]
return all([
self.__getattribute__(key) == other.__getattribute__(key)
for key in attrs
]) and set(
self.categories) == set(self.categories + other.categories)
except Exception:
return False
def __init__(self, key: str, categories: List[str]):
self.key: str = key
self.categories: List[str] = categories
class ConcatColumn(Serializable['ConcatColumn'], Column):
"""[ALPHA] Column that concatenates multiple values produced by a list- or set-valued variable.
The input subcolumn need not exist elsewhere in the table config, and its parameters have
no bearing on how the table is constructed. Only the type of column is relevant. That a
complete Column object is required is simply a limitation of the current API.
Parameters
----------
data_source: str
name of the variable to use when populating the column
subcolumn: Column
a column of the type of the individual values to be concatenated
"""
data_source = properties.String('data_source')
subcolumn = properties.Object(Column, 'subcolumn')
typ = properties.String('type',
default="concat_column",
deserializable=False)
def _attrs(self) -> List[str]:
return ["data_source", "typ"]
def __init__(self, *, data_source: str, subcolumn: Column):
self.data_source = data_source
self.subcolumn = subcolumn
class MeanColumn(Serializable['MeanColumn'], Column):
"""[ALPHA] Column containing the mean of a real-valued variable.
Parameters
----------
data_source: str
name of the variable to use when populating the column
target_units: Optional[str]
units to convert the real variable into
"""
data_source = properties.String('data_source')
target_units = properties.Optional(properties.String, "target_units")
typ = properties.String('type',
default="mean_column",
deserializable=False)
def _attrs(self) -> List[str]:
return ["data_source", "target_units", "typ"]
def __init__(self,
*,
data_source: str,
target_units: Optional[str] = None):
self.data_source = data_source
self.target_units = target_units
class NthBiggestComponentQuantityColumn(
Serializable["NthBiggestComponentQuantityColumn"], Column):
"""[ALPHA] Quantity of the Nth biggest component.
If there are fewer than N components in the composition, then this column will be empty.
Parameters
----------
data_source: str
name of the variable to use when populating the column
n: int
index of the component quantity to extract, starting with 1 for the biggest
normalize: bool
whether to normalize the quantity by the sum of all component amounts. Default is false
"""
data_source = properties.String('data_source')
n = properties.Integer("n")
normalize = properties.Boolean("normalize")
typ = properties.String('type',
default="biggest_component_quantity_column",
deserializable=False)
def _attrs(self) -> List[str]:
return ["data_source", "n", "normalize", "typ"]
def __init__(self, *, data_source: str, n: int, normalize: bool = False):
self.data_source = data_source
self.n = n
self.normalize = normalize
class MolecularStructureColumn(Serializable['MolecularStructureColumn'],
Column):
"""[ALPHA] Column containing a representation of a molecular structure.
Parameters
----------
data_source: str
name of the variable to use when populating the column
format: ChemicalDisplayFormat
the format in which to display the molecular structure
"""
data_source = properties.String('data_source')
format = properties.Enumeration(ChemicalDisplayFormat, 'format')
typ = properties.String('type',
default="molecular_structure_column",
deserializable=False)
def _attrs(self) -> List[str]:
return ["data_source", "format", "typ"]
def __init__(self, *, data_source: str, format: ChemicalDisplayFormat):
self.data_source = data_source
self.format = format
class ScalarMinObjective(Serializable['ScalarMinObjective'], Objective):
"""Simple single-response minimization objective with optional bounds on the objective space.
Parameters
----------
descriptor_key: str
the key from which to pull the values
lower_bound: float
the lower bound on the space, e.g. 0 for a non-negative property
upper_bound: float
the upper bound on the space, e.g. 0 for a non-positive property
"""
descriptor_key = properties.String('descriptor_key')
lower_bound = properties.Optional(properties.Float, 'lower_bound')
upper_bound = properties.Optional(properties.Float, 'upper_bound')
typ = properties.String('type', default='ScalarMin')
def __init__(self,
descriptor_key: str,
lower_bound: Optional[float] = None,
upper_bound: Optional[float] = None,
session: Optional[Session] = None):
self.descriptor_key = descriptor_key
self.lower_bound = lower_bound
self.upper_bound = upper_bound
self.session: Optional[Session] = session
def __str__(self):
return '<ScalarMinObjective {!r}>'.format(self.descriptor_key)
class JobStatusResponse(Resource['JobStatusResponse']):
"""[ALPHA] a response to a job status check.
The JobStatusResponse summarizes the status for the entire job.
Parameters
----------
job_type: str
the type of job for this status report
status: str
the actual status of the job.
One of "Running", "Success", or "Failure".
tasks: List[TaskNode]
all of the constituent task required to complete this job
output: Optional[Map[String,String]]
job output properties and results
"""
job_type = properties.String("job_type")
status = properties.String("status")
tasks = properties.List(Object(TaskNode), "tasks")
output = properties.Optional(properties.Mapping(String, String), 'output')
def __init__(
self,
job_type: str,
status: str,
tasks: List[TaskNode],
output: Optional[Dict[str, str]]
):
self.job_type = job_type
self.status = status
self.tasks = tasks
self.output = output
class RootInfo(Serializable['RootInfo'], Variable):
"""[ALPHA] Metadata from the root of the material history.
Parameters
----------
name: str
a short human-readable name to use when referencing the variable
headers: list[str]
sequence of column headers
field: str
name of the field to assign the variable to
"""
name = properties.String('name')
headers = properties.List(properties.String, 'headers')
field = properties.String('field')
typ = properties.String('type', default="root_info", deserializable=False)
def _attrs(self) -> List[str]:
return ["name", "headers", "field", "typ"]
def __init__(self, *,
name: str,
headers: List[str],
field: str):
self.name = name
self.headers = headers
self.field = field
class EnumeratedDimension(Serializable['EnumeratedDimension'], Dimension):
"""A finite, enumerated dimension.
Parameters
----------
descriptor: Descriptor
a descriptor of the single dimension
template_id: UUID
UUID that corresponds to the template in DC
values: list[str]
list of values that can be parsed by the descriptor
"""
descriptor = properties.Object(Descriptor, 'descriptor')
values = properties.List(properties.String(), 'list')
typ = properties.String('type', default='EnumeratedDimension', deserializable=False)
template_id = properties.Optional(properties.UUID, 'template_id', default=uuid4())
def __init__(self,
descriptor: Descriptor,
values: List[str],
template_id: Optional[UUID] = None):
self.descriptor: Descriptor = descriptor
self.values: List[str] = values
self.template_id: Optional[UUID] = template_id
class CategoricalConstraint(Serializable['CategoricalConstraint'], Constraint):
"""
[DEPRECATED] A constraint on a categorical material attribute in a set of acceptable values.
Parameters
----------
descriptor_key: str
the key corresponding to the associated Categorical descriptor
acceptable_categories: list[str]
the names of the acceptable categories to constrain to
"""
descriptor_key = properties.String('descriptor_key')
acceptable_categories = properties.List(properties.String(), 'acceptable_classes')
typ = properties.String('type', default='AcceptableCategoriesConstraint')
def __init__(self,
descriptor_key: str,
acceptable_categories: List[str],
session: Optional[Session] = None):
msg = "{this_class} is deprecated. Please use {replacement} instead.".format(
this_class="CategoricalConstraint",
replacement=AcceptableCategoriesConstraint.__name__)
warn(msg, category=DeprecationWarning)
self.descriptor_key = descriptor_key
self.acceptable_categories = acceptable_categories
self.session = session
def __str__(self):
return '<CategoricalConstraint {!r}>'.format(self.descriptor_key)
class DesignSpace(Module):
"""A Citrine Design Space describes the set of materials that can be made.
Abstract type that returns the proper type given a serialized dict.
"""
_project_id: Optional[UUID] = None
_session: Optional[Session] = None
uid = properties.Optional(properties.UUID, 'id', serializable=False)
""":Optional[UUID]: Citrine Platform unique identifier"""
name = properties.String('config.name')
description = properties.Optional(properties.String(),
'config.description')
@classmethod
def get_type(cls, data) -> Type[Serializable]:
"""Return the subtype."""
from .data_source_design_space import DataSourceDesignSpace
from .enumerated_design_space import EnumeratedDesignSpace
from .formulation_design_space import FormulationDesignSpace
from .product_design_space import ProductDesignSpace
return {
'Univariate': ProductDesignSpace,
'ProductDesignSpace': ProductDesignSpace,
'EnumeratedDesignSpace': EnumeratedDesignSpace,
'FormulationDesignSpace': FormulationDesignSpace,
'DataSourceDesignSpace': DataSourceDesignSpace
}[data['config']['type']]
class ExpressionPredictor(Resource['ExpressionPredictor'], Predictor,
AIResourceMetadata):
"""A predictor that computes an output from an expression and set of bounded inputs.
For a discussion of expression syntax and a list of allowed symbols,
please see the :ref:`documentation<Expression Predictor>`.
.. seealso::
If you are using the deprecated predictor please see
:class:`~citrine.informatics.predictors.DeprecatedExpressionPredictor` for an example that
shows how to migrate to the new format.
Parameters
----------
name: str
name of the configuration
description: str
the description of the predictor
expression: str
expression that computes an output from aliased inputs
output: RealDescriptor
descriptor that represents the output of the expression
aliases: Mapping[str, RealDescriptor]
a mapping from each unknown argument to its descriptor.
All unknown arguments must have an associated descriptor.
"""
expression = _properties.String('config.expression')
output = _properties.Object(RealDescriptor, 'config.output')
aliases = _properties.Mapping(_properties.String,
_properties.Object(RealDescriptor),
'config.aliases')
typ = _properties.String('config.type',
default='AnalyticExpression',
deserializable=False)
module_type = _properties.String('module_type', default='PREDICTOR')
def __init__(self,
name: str,
description: str,
expression: str,
output: RealDescriptor,
aliases: Mapping[str, RealDescriptor],
archived: bool = False):
self.name: str = name
self.description: str = description
self.expression: str = expression
self.output: RealDescriptor = output
self.aliases: Mapping[str, RealDescriptor] = aliases
self.archived: bool = archived
def _post_dump(self, data: dict) -> dict:
data['display_name'] = data['config']['name']
return data
def __str__(self):
return '<ExpressionPredictor {!r}>'.format(self.name)
class SimpleMixturePredictor(Resource['SimpleMixturePredictor'], Predictor,
AIResourceMetadata):
"""A predictor interface that flattens a formulation into a simple mixture.
Parameters
----------
name: str
name of the configuration
description: str
description of the predictor
input_descriptor: FormulationDescriptor
input descriptor for the hierarchical (un-mixed) formulation
output_descriptor: FormulationDescriptor
output descriptor for the flat (mixed) formulation
training_data: Optional[List[DataSource]]
Sources of training data. Each can be either a CSV or an GEM Table. Candidates from
multiple data sources will be combined into a flattened list and de-duplicated by uid and
identifiers. De-duplication is performed if a uid or identifier is shared between two or
more rows. The content of a de-duplicated row will contain the union of data across all
rows that share the same uid or at least 1 identifier. Training data is unnecessary if the
predictor is part of a graph that includes all training data required by this predictor.
"""
_resource_type = ResourceTypeEnum.MODULE
input_descriptor = _properties.Object(FormulationDescriptor,
'config.input')
output_descriptor = _properties.Object(FormulationDescriptor,
'config.output')
training_data = _properties.List(_properties.Object(DataSource),
'config.training_data')
typ = _properties.String('config.type',
default='SimpleMixture',
deserializable=False)
module_type = _properties.String('module_type', default='PREDICTOR')
def __init__(self,
name: str,
description: str,
input_descriptor: FormulationDescriptor,
output_descriptor: FormulationDescriptor,
training_data: Optional[List[DataSource]] = None,
archived: bool = False):
self.name: str = name
self.description: str = description
self.input_descriptor: FormulationDescriptor = input_descriptor
self.output_descriptor: FormulationDescriptor = output_descriptor
self.training_data: List[DataSource] = self._wrap_training_data(
training_data)
self.archived: bool = archived
def _post_dump(self, data: dict) -> dict:
data['display_name'] = data['config']['name']
return data
def __str__(self):
return '<SimpleMixturePredictor {!r}>'.format(self.name)
class AttributeByTemplateAndObjectTemplate(
Serializable['AttributeByTemplateAndObjectTemplate'], Variable):
"""[ALPHA] Attribute marked by an attribute template and an object template.
For example, one property may be measured by two different measurement techniques. In this
case, that property would have the same attribute template. Filtering by measurement
templates, which identify the measurement techniques, disambiguates the technique used to
measure that otherwise ambiguous property.
Parameters
---------
name: str
a short human-readable name to use when referencing the variable
headers: list[str]
sequence of column headers
attribute_template: LinkByUID
attribute template that identifies the attribute to assign to the variable
object_template: LinkByUID
template that identifies the associated object
attribute_constraints: list[(LinkByUID, Bounds)]
constraints on object attributes in the target object that must be satisfied. Constraints
are expressed as Bounds. Attributes are expressed with links. The attribute that the
variable is being set to may be the target of a constraint as well.
type_selector: DataObjectTypeSelector
strategy for selecting data object types to consider when matching, defaults to PREFER_RUN
"""
name = properties.String('name')
headers = properties.List(properties.String, 'headers')
attribute_template = properties.Object(LinkByUID, 'attribute_template')
object_template = properties.Object(LinkByUID, 'object_template')
attribute_constraints = properties.Optional(
properties.List(
properties.SpecifiedMixedList(
[properties.Object(LinkByUID), properties.Object(BaseBounds)]
)
), 'attribute_constraints')
type_selector = properties.Enumeration(DataObjectTypeSelector, "type_selector")
typ = properties.String('type', default="attribute_by_object", deserializable=False)
def _attrs(self) -> List[str]:
return ["name", "headers", "attribute_template", "object_template",
"attribute_constraints", "type_selector", "typ"]
def __init__(self, *,
name: str,
headers: List[str],
attribute_template: LinkByUID,
object_template: LinkByUID,
attribute_constraints: List[List[Union[LinkByUID, BaseBounds]]] = None,
type_selector: DataObjectTypeSelector = DataObjectTypeSelector.PREFER_RUN):
self.name = name
self.headers = headers
self.attribute_template = attribute_template
self.object_template = object_template
self.attribute_constraints = attribute_constraints
self.type_selector = type_selector
class DesignWorkflow(Resource['DesignWorkflow'], Workflow):
"""Object that generates scored materials that may approach higher values of the score.
Parameters
----------
name: str
the name of the workflow
design_space_id: UUID
the UUID corresponding to the design space to use
processor_id: UUID
the UUID corresponding to the processor to use
predictor_id: UUID
the UUID corresponding to the predictor to use
project_id: UUID
the UUID corresponding to the project to use
"""
uid = properties.Optional(properties.UUID, 'id', serializable=False)
name = properties.String('display_name')
status = properties.String('status', serializable=False)
status_info = properties.Optional(properties.List(properties.String()),
'status_info',
serializable=False)
# TODO: Figure out how to make these fields richer/use actual objects
design_space_id = properties.UUID('modules.design_space_id')
processor_id = properties.UUID('modules.processor_id')
predictor_id = properties.UUID('modules.predictor_id')
# The project_id is used to keep a reference to the project under which the workflow was
# created. It is currently unclear if this is the best way to do this. Another option might
# be to have all objects have a context object, but that also seems to have downsides.
def __init__(self,
name: str,
design_space_id: UUID,
processor_id: UUID,
predictor_id: UUID,
project_id: Optional[UUID] = None,
session: Session = Session()):
self.name = name
self.design_space_id = design_space_id
self.processor_id = processor_id
self.predictor_id = predictor_id
self.project_id = project_id
self.session = session
def __str__(self):
return '<DesignWorkflow {!r}>'.format(self.name)
@property
def executions(self) -> WorkflowExecutionCollection:
"""Return a resource representing all visible executions of this workflow."""
if getattr(self, 'project_id', None) is None:
raise AttributeError(
'Cannot initialize execution without project reference!')
return WorkflowExecutionCollection(self.project_id, self.uid,
self.session)
class ModelSummary(Serializable['ModelSummary']):
"""[ALPHA] Summary of information about a single model in a predictor.
ModelSummary objects are constructed from saved models and should not be user-instantiated.
Parameters
----------
name: str
the name of the model
type_: str
the type of the model (e.g., "ML Model", "Featurizer", etc.)
inputs: List[Descriptor]
list of input descriptors
outputs: List[Descriptor]
list of output descriptors
model_settings: dict
settings of the model, as a dictionary (details depend on model type)
feature_importances: List[FeatureImportanceReport]
list of feature importance reports, one for each output
predictor_name: str
the name of the predictor that created this model
predictor_uid: Optional[uuid]
the uid of the predictor that created this model
"""
name = properties.String('name')
type_ = properties.String('type')
inputs = properties.List(properties.String(), 'inputs')
outputs = properties.List(properties.String(), 'outputs')
model_settings = properties.Raw('model_settings')
feature_importances = properties.List(
properties.Object(FeatureImportanceReport), 'feature_importances')
predictor_name = properties.String('predictor_configuration_name', default='')
predictor_uid = properties.Optional(properties.UUID(), 'predictor_configuration_uid')
def __init__(self,
name: str,
type_: str,
inputs: List[Descriptor],
outputs: List[Descriptor],
model_settings: Dict[str, Any],
feature_importances: List[FeatureImportanceReport],
predictor_name: str,
predictor_uid: Optional[UUID] = None):
self.name = name
self.type_ = type_
self.inputs = inputs
self.outputs = outputs
self.model_settings = model_settings
self.feature_importances = feature_importances
self.predictor_name = predictor_name
self.predictor_uid = predictor_uid
def __str__(self):
return '<ModelSummary {!r}>'.format(self.name)
class CoverageProbability(Serializable["CoverageProbability"],
PredictorEvaluationMetric):
"""Percentage of observations that fall within a given confidence interval.
The coverage level can be specified to 3 digits, e.g., 0.123, but not 0.1234.
Parameters
----------
coverage_level: Union[str, float]
Confidence-interval coverage level.
The coverage level must be between 0 and 1.0 (non-inclusive) and will be rounded
to 3 significant figures. Default: 0.683 corresponds to one std. deviation
"""
_level_str = properties.String("coverage_level")
typ = properties.String("type",
default="CoverageProbability",
deserializable=False)
def __init__(self, coverage_level: Union[str, float] = "0.683"):
if isinstance(coverage_level, str):
try:
raw_float = float(coverage_level)
except ValueError:
raise ValueError(
"Invalid coverage level string '{requested_level}'. "
"Coverage level must represent a floating point number between "
"0 and 1 (non-inclusive).".format(
requested_level=coverage_level))
elif isinstance(coverage_level, float):
raw_float = coverage_level
else:
raise TypeError("Coverage level must be a string or float")
if raw_float >= 1.0 or raw_float <= 0.0:
raise ValueError(
"Coverage level must be between 0 and 1 (non-inclusive).")
_level_float = round(raw_float, 3)
if not isclose(_level_float, raw_float):
warn("Coverage level can only be specified to 3 decimal places."
"Requested level '{requested_level}' will be rounded "
"to {rounded_level}.".format(requested_level=coverage_level,
rounded_level=_level_float))
self._level_str = "{:5.3f}".format(_level_float)
def _attrs(self) -> List[str]:
return ["typ", "_level_str"]
def __repr__(self):
return "coverage_probability_{}".format(self._level_str)
def __str__(self):
return "Coverage Probability ({})".format(self._level_str)
class AttributeByTemplate(Serializable['AttributeByTemplate'], Variable):
"""[ALPHA] Attribute marked by an attribute template.
Parameters
----------
name: str
a short human-readable name to use when referencing the variable
headers: list[str]
sequence of column headers
template: LinkByUID
attribute template that identifies the attribute to assign to the variable
attribute_constraints: list[list[LinkByUID, Bounds]]
constraints on object attributes in the target object that must be satisfied. Constraints
are expressed as Bounds. Attributes are expressed with links. The attribute that the
variable is being set to may be the target of a constraint as well.
type_selector: DataObjectTypeSelector
strategy for selecting data object types to consider when matching, defaults to PREFER_RUN
"""
name = properties.String('name')
headers = properties.List(properties.String, 'headers')
template = properties.Object(LinkByUID, 'template')
attribute_constraints = properties.Optional(
properties.List(
properties.SpecifiedMixedList(
[properties.Object(LinkByUID),
properties.Object(BaseBounds)])), 'attribute_constraints')
type_selector = properties.Enumeration(DataObjectTypeSelector,
"type_selector")
typ = properties.String('type',
default="attribute_by_template",
deserializable=False)
def _attrs(self) -> List[str]:
return [
"name", "headers", "template", "attribute_constraints",
"type_selector", "typ"
]
def __init__(
self,
*,
name: str,
headers: List[str],
template: LinkByUID,
attribute_constraints: Optional[List[List[Union[LinkByUID,
BaseBounds]]]] = None,
type_selector: DataObjectTypeSelector = DataObjectTypeSelector.
PREFER_RUN):
self.name = name
self.headers = headers
self.template = template
self.attribute_constraints = attribute_constraints
self.type_selector = type_selector
class IngredientIdentifierByProcessTemplateAndName(
Serializable['IngredientIdentifierByProcessAndName'], Variable):
"""[ALPHA] Ingredient identifier associated with a process template and a name.
Parameters
---------
name: str
a short human-readable name to use when referencing the variable
headers: list[str]
sequence of column headers
process_template: LinkByUID
process template associated with this ingredient identifier
ingredient_name: str
name of ingredient
scope: str
scope of the identifier (default: the Citrine scope)
type_selector: DataObjectTypeSelector
strategy for selecting data object types to consider when matching, defaults to PREFER_RUN
"""
name = properties.String('name')
headers = properties.List(properties.String, 'headers')
process_template = properties.Object(LinkByUID, 'process_template')
ingredient_name = properties.String('ingredient_name')
scope = properties.String('scope')
type_selector = properties.Enumeration(DataObjectTypeSelector,
"type_selector")
typ = properties.String('type',
default="ing_id_by_process_and_name",
deserializable=False)
def _attrs(self) -> List[str]:
return [
"name", "headers", "process_template", "ingredient_name", "scope",
"type_selector", "typ"
]
def __init__(
self,
*,
name: str,
headers: List[str],
process_template: LinkByUID,
ingredient_name: str,
scope: str,
type_selector: DataObjectTypeSelector = DataObjectTypeSelector.
PREFER_RUN):
self.name = name
self.headers = headers
self.process_template = process_template
self.ingredient_name = ingredient_name
self.scope = scope
self.type_selector = type_selector
class AIResourceMetadata():
"""Abstract class for representing common metadata for Resources."""
created_by = properties.Optional(properties.UUID,
'created_by',
serializable=False)
""":Optional[UUID]: id of the user who created the resource"""
create_time = properties.Optional(properties.Datetime,
'create_time',
serializable=False)
""":Optional[datetime]: date and time at which the resource was created"""
updated_by = properties.Optional(properties.UUID,
'updated_by',
serializable=False)
""":Optional[UUID]: id of the user who most recently updated the resource,
if it has been updated"""
update_time = properties.Optional(properties.Datetime,
'update_time',
serializable=False)
""":Optional[datetime]: date and time at which the resource was most recently updated,
if it has been updated"""
archived = properties.Boolean('archived', default=False)
""":bool: whether the resource is archived (hidden but not deleted)"""
archived_by = properties.Optional(properties.UUID,
'archived_by',
serializable=False)
""":Optional[UUID]: id of the user who archived the resource, if it has been archived"""
archive_time = properties.Optional(properties.Datetime,
'archive_time',
serializable=False)
""":Optional[datetime]: date and time at which the resource was archived,
if it has been archived"""
experimental = properties.Boolean("experimental",
serializable=False,
default=True)
""":bool: whether the resource is experimental (newer, less well-tested functionality)"""
experimental_reasons = properties.Optional(properties.List(
properties.String()),
'experimental_reasons',
serializable=False)
""":Optional[List[str]]: human-readable reasons why the resource is experimental"""
status = properties.Optional(properties.String(),
'status',
serializable=False)
""":Optional[str]: short description of the resource's status"""
status_info = properties.Optional(properties.List(properties.String()),
'status_info',
serializable=False)
""":Optional[List[str]]: human-readable explanations of the status"""