Start the run once inputs are uploaded
curl --request POST \
--url https://{tenant}-api.mathfi.ai/api/v1/feature-refinery/{featureRefinementKey}/start \
--header 'Authorization: Bearer <token>'import requests
url = "https://{tenant}-api.mathfi.ai/api/v1/feature-refinery/{featureRefinementKey}/start"
headers = {"Authorization": "Bearer <token>"}
response = requests.post(url, headers=headers)
print(response.text){
"featureRefinementKey": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"state": "<string>"
}Feature Refinery
Start the run once inputs are uploaded
Begin the run once the inputs are uploaded, then poll /progress for state and the top-performance
metrics as refinement proceeds.
Validates that both the train and labelled-test CSVs have been uploaded first. If either is missing, or the training file has more columns than the run accepts, it returns 400 and does NOT start.
The size of the data is not validated here. The train file needs at least 25 labelled rows for the least common target value, counted after the split. A run below that starts, then fails while preparing the data, so a 200 from this call is not confirmation that the data can be trained on.
POST
/
api
/
v1
/
feature-refinery
/
{featureRefinementKey}
/
start
Start the run once inputs are uploaded
curl --request POST \
--url https://{tenant}-api.mathfi.ai/api/v1/feature-refinery/{featureRefinementKey}/start \
--header 'Authorization: Bearer <token>'import requests
url = "https://{tenant}-api.mathfi.ai/api/v1/feature-refinery/{featureRefinementKey}/start"
headers = {"Authorization": "Bearer <token>"}
response = requests.post(url, headers=headers)
print(response.text){
"featureRefinementKey": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"state": "<string>"
}Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.