curl --request GET \
--url https://{tenant}-api.mathfi.ai/api/v1/feature-refinery/{featureRefinementKey}/result \
--header 'Authorization: Bearer <token>'import requests
url = "https://{tenant}-api.mathfi.ai/api/v1/feature-refinery/{featureRefinementKey}/result"
headers = {"Authorization": "Bearer <token>"}
response = requests.get(url, headers=headers)
print(response.text){
"featureRefinementKey": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"state": "<string>",
"columnStatus": [
{
"columnIndex": 123,
"outcome": "KEEP",
"columnName": "<string>"
}
],
"refinedTrainUrl": "<string>",
"refinedPredictionUrl": "<string>",
"refinedColumnStatusUrl": "<string>"
}Feature refinement result — columnStatus + refined download links
The finished run’s outcome: each original column’s KEEP/REMOVE decision plus short-lived signed download URLs for the reduced train + prediction CSVs (the columns the loop eliminated are dropped). The download URLs are populated once the state is REFINEMENT_COMPLETED, and null before then.
curl --request GET \
--url https://{tenant}-api.mathfi.ai/api/v1/feature-refinery/{featureRefinementKey}/result \
--header 'Authorization: Bearer <token>'import requests
url = "https://{tenant}-api.mathfi.ai/api/v1/feature-refinery/{featureRefinementKey}/result"
headers = {"Authorization": "Bearer <token>"}
response = requests.get(url, headers=headers)
print(response.text){
"featureRefinementKey": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"state": "<string>",
"columnStatus": [
{
"columnIndex": 123,
"outcome": "KEEP",
"columnName": "<string>"
}
],
"refinedTrainUrl": "<string>",
"refinedPredictionUrl": "<string>",
"refinedColumnStatusUrl": "<string>"
}Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Path Parameters
Response
Result
The finished run's outcome — the per-column KEEP/REMOVE decisions and signed download URLs for the reduced deliverables. The download URLs are short-lived and null until the run reaches REFINEMENT_COMPLETED.
One entry per original column, in column order, with its keep/remove outcome.
Show child attributes
Show child attributes
Short-lived signed GET URL for the reduced train CSV. Null before REFINEMENT_COMPLETED.
Short-lived signed GET URL for the reduced prediction/test CSV. Null before REFINEMENT_COMPLETED.
Short-lived signed GET URL for the column-status filter file (the per-column KEEP/REMOVE 1/0 vector as CSV) — the same decisions as columnStatus above, downloadable as a file so it can be reapplied to drop columns from a later prediction file. Null before REFINEMENT_COMPLETED.