mat3ra-esse 2024.4.8.post1__py3-none-any.whl → 2024.4.8.post2__py3-none-any.whl

mat3ra/esse/models/software_directory/ml/unit/processing/data_transformation/__init__.py

@@ -0,0 +1,199 @@
+# generated by datamodel-codegen:
+#   filename:  software_directory/ml/unit/processing/data_transformation.json
+#   version:   0.25.5
+
+from __future__ import annotations
+
+from enum import Enum
+from typing import Any, Dict, List, Optional, Union
+
+from pydantic import BaseModel, ConfigDict, Field, RootModel
+
+
+class Operation(Enum):
+    data_transformation = "data_transformation"
+
+
+class OperationType(Enum):
+    scale_and_reduce = "scale_and_reduce"
+
+
+class Scaler(Enum):
+    standard_scaler = "standard_scaler"
+
+
+class PerFeatureItem(BaseModel):
+    variance: Optional[float] = None
+    """
+    variance in original training data
+    """
+    mean: Optional[float] = None
+    """
+    mean value of the original training data
+    """
+    scale: float
+    """
+    scale multiplier for this feature/property
+    """
+    name: str
+    """
+    feature/property name in 'flattened' format
+    """
+
+
+class InputData(BaseModel):
+    scaler: Scaler
+    """
+    type of scaler to be applied
+    """
+    perFeature: Optional[List[PerFeatureItem]] = None
+    """
+    per-feature scaling data
+    """
+
+
+class Type(Enum):
+    processing = "processing"
+
+
+class Status(Enum):
+    idle = "idle"
+    active = "active"
+    warning = "warning"
+    error = "error"
+    finished = "finished"
+
+
+class Name(Enum):
+    default = "default"
+    atomsTooClose = "atomsTooClose"
+    atomsOverlap = "atomsOverlap"
+
+
+class Severity(Enum):
+    info = "info"
+    warning = "warning"
+    error = "error"
+
+
+class ConsistencyCheck(BaseModel):
+    key: str
+    """
+    Key of the property of the entity on which the consistency check is performed in Mongo dot notation, e.g. 'basis.coordinates.1'
+    """
+    name: Name
+    """
+    Name of the consistency check that is performed, which is listed in an enum.
+    """
+    severity: Severity
+    """
+    Severity level of the problem, which is used in UI to differentiate.
+    """
+    message: str
+    """
+    Message generated by the consistency check describing the problem.
+    """
+
+
+class NameResultSchema(BaseModel):
+    name: str
+    """
+    The name of this item. e.g. scf_accuracy
+    """
+
+
+class StatusTrackItem(BaseModel):
+    trackedAt: float
+    status: str
+    repetition: Optional[float] = None
+
+
+class ScaleAndReduceUnitSchema(BaseModel):
+    model_config = ConfigDict(
+        extra="allow",
+    )
+    operation: Operation
+    """
+    Contains information about the operation used.
+    """
+    operationType: OperationType
+    """
+    Contains information about the specific type of the operation used.
+    """
+    inputData: InputData
+    """
+    unit input (type to be specified by the child units)
+    """
+    type: Type
+    """
+    type of the unit
+    """
+    field_id: Optional[str] = Field(None, alias="_id")
+    """
+    entity identity
+    """
+    isDraft: Optional[bool] = None
+    name: Optional[str] = None
+    """
+    name of the unit. e.g. pw_scf
+    """
+    status: Optional[Status] = None
+    """
+    Status of the unit.
+    """
+    head: Optional[bool] = None
+    """
+    Whether this unit is the first one to be executed.
+    """
+    flowchartId: str
+    """
+    Identity of the unit in the workflow. Used to trace the execution flow of the workflow.
+    """
+    next: Optional[str] = None
+    """
+    Next unit's flowchartId. If empty, the current unit is the last.
+    """
+    enableRender: Optional[bool] = None
+    """
+    Whether Rupy should attempt to use Jinja templating to add context variables into the unit
+    """
+    context: Optional[Dict[str, Any]] = None
+    slug: Optional[str] = None
+    """
+    entity slug
+    """
+    systemName: Optional[str] = None
+    consistencyChecks: Optional[List[ConsistencyCheck]] = None
+    schemaVersion: Optional[str] = "2022.8.16"
+    """
+    entity's schema version. Used to distinct between different schemas.
+    """
+    isDefault: Optional[bool] = False
+    """
+    Identifies that entity is defaultable
+    """
+    preProcessors: Optional[List[Union[NameResultSchema, str]]] = None
+    """
+    names of the pre-processors for this calculation
+    """
+    postProcessors: Optional[List[Union[NameResultSchema, str]]] = None
+    """
+    names of the post-processors for this calculation
+    """
+    monitors: Optional[List[Union[NameResultSchema, str]]] = None
+    """
+    names of the monitors for this calculation
+    """
+    results: Optional[List[Union[NameResultSchema, str]]] = None
+    """
+    names of the results for this calculation
+    """
+    tags: Optional[List[str]] = None
+    """
+    entity tags
+    """
+    statusTrack: Optional[List[StatusTrackItem]] = None
+
+
+class ESSE(RootModel[ScaleAndReduceUnitSchema]):
+    root: ScaleAndReduceUnitSchema

mat3ra/esse/models/software_directory/ml/unit/processing/data_transformation/manipulation.py

@@ -0,0 +1,176 @@
+# generated by datamodel-codegen:
+#   filename:  software_directory/ml/unit/processing/data_transformation/manipulation.json
+#   version:   0.25.5
+
+from __future__ import annotations
+
+from enum import Enum
+from typing import Any, Dict, List, Optional, Union
+
+from pydantic import BaseModel, ConfigDict, Field
+
+
+class Operation(Enum):
+    data_transformation = "data_transformation"
+
+
+class OperationType(Enum):
+    manipulation = "manipulation"
+
+
+class InputData(BaseModel):
+    cleanMissingData: bool
+    """
+    whether to clean missing data, eg. NaN
+    """
+    removeDuplicateRows: bool
+    """
+    whether to remove duplicate rows
+    """
+    replaceNoneValuesWith: float
+    """
+    replace None values with a given value
+    """
+
+
+class Type(Enum):
+    processing = "processing"
+
+
+class Status(Enum):
+    idle = "idle"
+    active = "active"
+    warning = "warning"
+    error = "error"
+    finished = "finished"
+
+
+class Name(Enum):
+    default = "default"
+    atomsTooClose = "atomsTooClose"
+    atomsOverlap = "atomsOverlap"
+
+
+class Severity(Enum):
+    info = "info"
+    warning = "warning"
+    error = "error"
+
+
+class ConsistencyCheck(BaseModel):
+    key: str
+    """
+    Key of the property of the entity on which the consistency check is performed in Mongo dot notation, e.g. 'basis.coordinates.1'
+    """
+    name: Name
+    """
+    Name of the consistency check that is performed, which is listed in an enum.
+    """
+    severity: Severity
+    """
+    Severity level of the problem, which is used in UI to differentiate.
+    """
+    message: str
+    """
+    Message generated by the consistency check describing the problem.
+    """
+
+
+class NameResultSchema(BaseModel):
+    name: str
+    """
+    The name of this item. e.g. scf_accuracy
+    """
+
+
+class StatusTrackItem(BaseModel):
+    trackedAt: float
+    status: str
+    repetition: Optional[float] = None
+
+
+class ManipulationUnitSchema(BaseModel):
+    model_config = ConfigDict(
+        extra="allow",
+    )
+    operation: Operation
+    """
+    Contains information about the operation used.
+    """
+    operationType: OperationType
+    """
+    Contains information about the specific type of the operation used.
+    """
+    inputData: InputData
+    """
+    unit input (type to be specified by the child units)
+    """
+    type: Type
+    """
+    type of the unit
+    """
+    field_id: Optional[str] = Field(None, alias="_id")
+    """
+    entity identity
+    """
+    isDraft: Optional[bool] = None
+    name: Optional[str] = None
+    """
+    name of the unit. e.g. pw_scf
+    """
+    status: Optional[Status] = None
+    """
+    Status of the unit.
+    """
+    head: Optional[bool] = None
+    """
+    Whether this unit is the first one to be executed.
+    """
+    flowchartId: str
+    """
+    Identity of the unit in the workflow. Used to trace the execution flow of the workflow.
+    """
+    next: Optional[str] = None
+    """
+    Next unit's flowchartId. If empty, the current unit is the last.
+    """
+    enableRender: Optional[bool] = None
+    """
+    Whether Rupy should attempt to use Jinja templating to add context variables into the unit
+    """
+    context: Optional[Dict[str, Any]] = None
+    slug: Optional[str] = None
+    """
+    entity slug
+    """
+    systemName: Optional[str] = None
+    consistencyChecks: Optional[List[ConsistencyCheck]] = None
+    schemaVersion: Optional[str] = "2022.8.16"
+    """
+    entity's schema version. Used to distinct between different schemas.
+    """
+    isDefault: Optional[bool] = False
+    """
+    Identifies that entity is defaultable
+    """
+    preProcessors: Optional[List[Union[NameResultSchema, str]]] = None
+    """
+    names of the pre-processors for this calculation
+    """
+    postProcessors: Optional[List[Union[NameResultSchema, str]]] = None
+    """
+    names of the post-processors for this calculation
+    """
+    monitors: Optional[List[Union[NameResultSchema, str]]] = None
+    """
+    names of the monitors for this calculation
+    """
+    results: Optional[List[Union[NameResultSchema, str]]] = None
+    """
+    names of the results for this calculation
+    """
+    tags: Optional[List[str]] = None
+    """
+    entity tags
+    """
+    statusTrack: Optional[List[StatusTrackItem]] = None

mat3ra/esse/models/software_directory/ml/unit/processing/data_transformation/scale_and_reduce.py

@@ -0,0 +1,195 @@
+# generated by datamodel-codegen:
+#   filename:  software_directory/ml/unit/processing/data_transformation/scale_and_reduce.json
+#   version:   0.25.5
+
+from __future__ import annotations
+
+from enum import Enum
+from typing import Any, Dict, List, Optional, Union
+
+from pydantic import BaseModel, ConfigDict, Field
+
+
+class Operation(Enum):
+    data_transformation = "data_transformation"
+
+
+class OperationType(Enum):
+    scale_and_reduce = "scale_and_reduce"
+
+
+class Scaler(Enum):
+    standard_scaler = "standard_scaler"
+
+
+class PerFeatureItem(BaseModel):
+    variance: Optional[float] = None
+    """
+    variance in original training data
+    """
+    mean: Optional[float] = None
+    """
+    mean value of the original training data
+    """
+    scale: float
+    """
+    scale multiplier for this feature/property
+    """
+    name: str
+    """
+    feature/property name in 'flattened' format
+    """
+
+
+class InputData(BaseModel):
+    scaler: Scaler
+    """
+    type of scaler to be applied
+    """
+    perFeature: Optional[List[PerFeatureItem]] = None
+    """
+    per-feature scaling data
+    """
+
+
+class Type(Enum):
+    processing = "processing"
+
+
+class Status(Enum):
+    idle = "idle"
+    active = "active"
+    warning = "warning"
+    error = "error"
+    finished = "finished"
+
+
+class Name(Enum):
+    default = "default"
+    atomsTooClose = "atomsTooClose"
+    atomsOverlap = "atomsOverlap"
+
+
+class Severity(Enum):
+    info = "info"
+    warning = "warning"
+    error = "error"
+
+
+class ConsistencyCheck(BaseModel):
+    key: str
+    """
+    Key of the property of the entity on which the consistency check is performed in Mongo dot notation, e.g. 'basis.coordinates.1'
+    """
+    name: Name
+    """
+    Name of the consistency check that is performed, which is listed in an enum.
+    """
+    severity: Severity
+    """
+    Severity level of the problem, which is used in UI to differentiate.
+    """
+    message: str
+    """
+    Message generated by the consistency check describing the problem.
+    """
+
+
+class NameResultSchema(BaseModel):
+    name: str
+    """
+    The name of this item. e.g. scf_accuracy
+    """
+
+
+class StatusTrackItem(BaseModel):
+    trackedAt: float
+    status: str
+    repetition: Optional[float] = None
+
+
+class ScaleAndReduceUnitSchema(BaseModel):
+    model_config = ConfigDict(
+        extra="allow",
+    )
+    operation: Operation
+    """
+    Contains information about the operation used.
+    """
+    operationType: OperationType
+    """
+    Contains information about the specific type of the operation used.
+    """
+    inputData: InputData
+    """
+    unit input (type to be specified by the child units)
+    """
+    type: Type
+    """
+    type of the unit
+    """
+    field_id: Optional[str] = Field(None, alias="_id")
+    """
+    entity identity
+    """
+    isDraft: Optional[bool] = None
+    name: Optional[str] = None
+    """
+    name of the unit. e.g. pw_scf
+    """
+    status: Optional[Status] = None
+    """
+    Status of the unit.
+    """
+    head: Optional[bool] = None
+    """
+    Whether this unit is the first one to be executed.
+    """
+    flowchartId: str
+    """
+    Identity of the unit in the workflow. Used to trace the execution flow of the workflow.
+    """
+    next: Optional[str] = None
+    """
+    Next unit's flowchartId. If empty, the current unit is the last.
+    """
+    enableRender: Optional[bool] = None
+    """
+    Whether Rupy should attempt to use Jinja templating to add context variables into the unit
+    """
+    context: Optional[Dict[str, Any]] = None
+    slug: Optional[str] = None
+    """
+    entity slug
+    """
+    systemName: Optional[str] = None
+    consistencyChecks: Optional[List[ConsistencyCheck]] = None
+    schemaVersion: Optional[str] = "2022.8.16"
+    """
+    entity's schema version. Used to distinct between different schemas.
+    """
+    isDefault: Optional[bool] = False
+    """
+    Identifies that entity is defaultable
+    """
+    preProcessors: Optional[List[Union[NameResultSchema, str]]] = None
+    """
+    names of the pre-processors for this calculation
+    """
+    postProcessors: Optional[List[Union[NameResultSchema, str]]] = None
+    """
+    names of the post-processors for this calculation
+    """
+    monitors: Optional[List[Union[NameResultSchema, str]]] = None
+    """
+    names of the monitors for this calculation
+    """
+    results: Optional[List[Union[NameResultSchema, str]]] = None
+    """
+    names of the results for this calculation
+    """
+    tags: Optional[List[str]] = None
+    """
+    entity tags
+    """
+    statusTrack: Optional[List[StatusTrackItem]] = None