Class: EvaluationResult
Aggregate evaluation result (dspy.EvaluationResult).
classDiagram
class EvaluationResult
click EvaluationResult href "../EvaluationResult/"
Prediction <|-- EvaluationResult
click Prediction href "../Prediction/"
EvaluationResult : completions
EvaluationResult --> "0..1" Completions : completions
click Completions href "../Completions/"
EvaluationResult : description
EvaluationResult : fields
EvaluationResult --> "*" ExampleField : fields
click ExampleField href "../ExampleField/"
EvaluationResult : id
EvaluationResult : input_keys
EvaluationResult : lm_usage
EvaluationResult --> "0..1" LMUsage : lm_usage
click LMUsage href "../LMUsage/"
EvaluationResult : name
EvaluationResult : results
EvaluationResult --> "*" EvaluationRow : results
click EvaluationRow href "../EvaluationRow/"
EvaluationResult : score
Inheritance
- NamedThing
- Example
- Prediction
- EvaluationResult
- Prediction
- Example
Slots
| Name | Cardinality and Range | Description | Inheritance |
|---|---|---|---|
| results | * EvaluationRow |
Per-example evaluation rows aggregated into an EvaluationResult |
direct |
| score | 1 Float |
Numeric score attached to a Prediction (used for arithmetic / comparison) | Prediction |
| completions | 0..1 Completions |
Optional list of alternate completion candidates | Prediction |
| lm_usage | 0..1 LMUsage |
Token usage attributed to the prediction | Prediction |
| fields | * ExampleField |
Named scalar fields carried by an Example / Prediction |
Example |
| input_keys | * String |
Subset of fields flagged as inputs via ``with_inputs( |
Example |
| id | 1 Identifier |
Stable opaque identifier for an instance | NamedThing |
| name | 0..1 String |
Short human-readable name | NamedThing |
| description | 0..1 String |
Free-form description | NamedThing |
In Subsets
Identifier and Mapping Information
Annotations
| property | value |
|---|---|
| dspy_source_paths | ['dspy/evaluate/evaluate.py'] |
| dspy_source_urls | ['https://github.com/stanfordnlp/dspy/blob/main/dspy/evaluate/evaluate.py'] |
Schema Source
- from schema: https://w3id.org/lmodel/dspy
Mappings
| Mapping Type | Mapped Value |
|---|---|
| self | dspy:EvaluationResult |
| native | dspy:EvaluationResult |
| related | legal_eu_aiact:AISystemPerformance, iso22989:ConfidenceScore, nist_ai_100_1:Impact |
| close | nexus:AiEvalResult |
LinkML Source
Direct
name: EvaluationResult
annotations:
dspy_source_paths:
tag: dspy_source_paths
value:
- dspy/evaluate/evaluate.py
dspy_source_urls:
tag: dspy_source_urls
value:
- https://github.com/stanfordnlp/dspy/blob/main/dspy/evaluate/evaluate.py
description: Aggregate evaluation result (``dspy.EvaluationResult``).
in_subset:
- evaluation
from_schema: https://w3id.org/lmodel/dspy
close_mappings:
- nexus:AiEvalResult
related_mappings:
- legal_eu_aiact:AISystemPerformance
- iso22989:ConfidenceScore
- nist_ai_100_1:Impact
is_a: Prediction
slots:
- results
slot_usage:
score:
name: score
required: true
Induced
name: EvaluationResult
annotations:
dspy_source_paths:
tag: dspy_source_paths
value:
- dspy/evaluate/evaluate.py
dspy_source_urls:
tag: dspy_source_urls
value:
- https://github.com/stanfordnlp/dspy/blob/main/dspy/evaluate/evaluate.py
description: Aggregate evaluation result (``dspy.EvaluationResult``).
in_subset:
- evaluation
from_schema: https://w3id.org/lmodel/dspy
close_mappings:
- nexus:AiEvalResult
related_mappings:
- legal_eu_aiact:AISystemPerformance
- iso22989:ConfidenceScore
- nist_ai_100_1:Impact
is_a: Prediction
slot_usage:
score:
name: score
required: true
attributes:
results:
name: results
description: Per-example evaluation rows aggregated into an ``EvaluationResult``.
from_schema: https://w3id.org/lmodel/dspy
rank: 1000
owner: EvaluationResult
domain_of:
- EvaluationResult
range: EvaluationRow
multivalued: true
inlined: true
inlined_as_list: true
score:
name: score
description: Numeric score attached to a Prediction (used for arithmetic / comparison).
from_schema: https://w3id.org/lmodel/dspy
rank: 1000
owner: EvaluationResult
domain_of:
- Prediction
- EvaluationRow
range: float
required: true
completions:
name: completions
description: Optional list of alternate completion candidates.
from_schema: https://w3id.org/lmodel/dspy
rank: 1000
owner: EvaluationResult
domain_of:
- Prediction
range: Completions
inlined: true
lm_usage:
name: lm_usage
description: Token usage attributed to the prediction.
from_schema: https://w3id.org/lmodel/dspy
rank: 1000
owner: EvaluationResult
domain_of:
- Prediction
range: LMUsage
inlined: true
fields:
name: fields
description: Named scalar fields carried by an ``Example`` / ``Prediction``.
from_schema: https://w3id.org/lmodel/dspy
rank: 1000
owner: EvaluationResult
domain_of:
- Example
range: ExampleField
multivalued: true
inlined: true
inlined_as_list: true
input_keys:
name: input_keys
description: Subset of ``fields`` flagged as inputs via ``with_inputs(...)``.
from_schema: https://w3id.org/lmodel/dspy
rank: 1000
owner: EvaluationResult
domain_of:
- Example
range: string
multivalued: true
id:
name: id
description: Stable opaque identifier for an instance.
from_schema: https://w3id.org/lmodel/dspy
rank: 1000
slot_uri: schema:identifier
identifier: true
owner: EvaluationResult
domain_of:
- NamedThing
range: Identifier
required: true
name:
name: name
description: Short human-readable name.
from_schema: https://w3id.org/lmodel/dspy
rank: 1000
slot_uri: rdfs:label
owner: EvaluationResult
domain_of:
- NamedThing
- LMToolCallPart
- LMMessage
- LMToolSpec
range: string
description:
name: description
description: Free-form description.
from_schema: https://w3id.org/lmodel/dspy
rank: 1000
slot_uri: dct:description
owner: EvaluationResult
domain_of:
- NamedThing
- LMToolSpec
range: string