import os
from dataframer import Dataframer
client = Dataframer(
api_key=os.environ.get("DATAFRAMER_API_KEY"), # This is the default and can be omitted
)
evaluation = client.dataframer.evaluations.retrieve(
"182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
)
print(evaluation.id)curl https://df-api.dataframer.ai/api/dataframer/evaluations/$EVALUATION_ID/ \
-H "Authorization: Bearer $DATAFRAMER_API_KEY"{
"id": "f4e64db3-3cac-4706-9fd0-c6695ae4694a",
"run_id": "a98715da-921d-4326-bbf8-208f8bcc2956",
"status": "SUCCEEDED",
"distribution_analysis": [
{
"property_name": "sentiment",
"total_samples": 100,
"requested_distributions": {
"positive": 40,
"negative": 30,
"neutral": 30
},
"expected_distributions": {
"positive": 42,
"negative": 30,
"neutral": 28
},
"evaluated_distributions": {
"positive": 45,
"negative": 28,
"neutral": 27
},
"total_samples_analyzed": 100
}
],
"sample_classifications": [
{
"id": "ad7913d9-a0aa-4a80-83a7-70026e3c1f1d",
"evaluation_id": "f4e64db3-3cac-4706-9fd0-c6695ae4694a",
"sample_identifier": "sample_1",
"classifications": {
"sentiment": "positive",
"topic": "technology"
},
"created_at": "2025-01-15T10:30:00Z"
}
],
"completed_at": "2025-01-15T10:31:00Z",
"error_message": null,
"created_by_email": "user@example.com",
"created_at": "2025-01-15T10:30:00Z"
}Get evaluation
Retrieve full evaluation details including distribution analysis
import os
from dataframer import Dataframer
client = Dataframer(
api_key=os.environ.get("DATAFRAMER_API_KEY"), # This is the default and can be omitted
)
evaluation = client.dataframer.evaluations.retrieve(
"182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
)
print(evaluation.id)curl https://df-api.dataframer.ai/api/dataframer/evaluations/$EVALUATION_ID/ \
-H "Authorization: Bearer $DATAFRAMER_API_KEY"{
"id": "f4e64db3-3cac-4706-9fd0-c6695ae4694a",
"run_id": "a98715da-921d-4326-bbf8-208f8bcc2956",
"status": "SUCCEEDED",
"distribution_analysis": [
{
"property_name": "sentiment",
"total_samples": 100,
"requested_distributions": {
"positive": 40,
"negative": 30,
"neutral": 30
},
"expected_distributions": {
"positive": 42,
"negative": 30,
"neutral": 28
},
"evaluated_distributions": {
"positive": 45,
"negative": 28,
"neutral": 27
},
"total_samples_analyzed": 100
}
],
"sample_classifications": [
{
"id": "ad7913d9-a0aa-4a80-83a7-70026e3c1f1d",
"evaluation_id": "f4e64db3-3cac-4706-9fd0-c6695ae4694a",
"sample_identifier": "sample_1",
"classifications": {
"sentiment": "positive",
"topic": "technology"
},
"created_at": "2025-01-15T10:30:00Z"
}
],
"completed_at": "2025-01-15T10:31:00Z",
"error_message": null,
"created_by_email": "user@example.com",
"created_at": "2025-01-15T10:30:00Z"
}- conformance_score: Overall score (0-100) measuring how well samples match expected distributions
- distribution_analysis: Per-property comparison of expected vs observed percentages
- sample_classifications: How each generated sample was classified for each property
Authorizations
API Key authentication. Format: "Bearer YOUR_API_KEY"
Path Parameters
Unique identifier of the evaluation
Response
Evaluation details, including distribution analysis and sample classifications
Unique identifier for the evaluation
ID of the run being evaluated
Current status of the evaluation
PENDING, PROCESSING, SUCCEEDED, FAILED Per-property comparison of expected vs observed distributions. Null until evaluation completes. Also empty when content_unavailable_reason is set.
Show child attributes
Show child attributes
Classification results for each generated sample. Empty until evaluation completes. Also empty when content_unavailable_reason is set.
Show child attributes
Show child attributes
When evaluation completed
Error message if evaluation failed
Email of the user who created the evaluation
When the evaluation was created
Where the evaluation's results are stored in your own cloud (null unless your deployment is customer-hosted)
Show child attributes
Show child attributes
Set when distribution_analysis and sample_classifications are empty because they are stored in your own cloud, not because nothing was classified. Absent or null otherwise. The Python SDK reads the text from your data plane, fills the fields and clears this
result_content_in_data_plane